Total coverage: 230714 (15%)of 1558713
9 9 9 9 9 143 11 132 143 142 143 142 9 9 143 25 121 120 10 9 9 9 9 9 9 9 9 134 102 122 134 103 121 135 26 118 9 9 9 9 98 98 97 98 98 1 97 7 94 98 98 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 /* * Copyright (C) 2018 Intel Corp. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * * Authors: * Rob Clark <robdclark@gmail.com> * Daniel Vetter <daniel.vetter@ffwll.ch> */ #include <drm/drm_atomic.h> #include <drm/drm_atomic_state_helper.h> #include <drm/drm_blend.h> #include <drm/drm_bridge.h> #include <drm/drm_connector.h> #include <drm/drm_crtc.h> #include <drm/drm_device.h> #include <drm/drm_framebuffer.h> #include <drm/drm_plane.h> #include <drm/drm_print.h> #include <drm/drm_vblank.h> #include <drm/drm_writeback.h> #include <linux/slab.h> #include <linux/dma-fence.h> /** * DOC: atomic state reset and initialization * * Both the drm core and the atomic helpers assume that there is always the full * and correct atomic software state for all connectors, CRTCs and planes * available. Which is a bit a problem on driver load and also after system * suspend. One way to solve this is to have a hardware state read-out * infrastructure which reconstructs the full software state (e.g. the i915 * driver). * * The simpler solution is to just reset the software state to everything off, * which is easiest to do by calling drm_mode_config_reset(). To facilitate this * the atomic helpers provide default reset implementations for all hooks. * * On the upside the precise state tracking of atomic simplifies system suspend * and resume a lot. For drivers using drm_mode_config_reset() a complete recipe * is implemented in drm_atomic_helper_suspend() and drm_atomic_helper_resume(). * For other drivers the building blocks are split out, see the documentation * for these functions. */ /** * __drm_atomic_helper_crtc_state_reset - reset the CRTC state * @crtc_state: atomic CRTC state, must not be NULL * @crtc: CRTC object, must not be NULL * * Initializes the newly allocated @crtc_state with default * values. This is useful for drivers that subclass the CRTC state. */ void __drm_atomic_helper_crtc_state_reset(struct drm_crtc_state *crtc_state, struct drm_crtc *crtc) { crtc_state->crtc = crtc; } EXPORT_SYMBOL(__drm_atomic_helper_crtc_state_reset); /** * __drm_atomic_helper_crtc_reset - reset state on CRTC * @crtc: drm CRTC * @crtc_state: CRTC state to assign * * Initializes the newly allocated @crtc_state and assigns it to * the &drm_crtc->state pointer of @crtc, usually required when * initializing the drivers or when called from the &drm_crtc_funcs.reset * hook. * * This is useful for drivers that subclass the CRTC state. */ void __drm_atomic_helper_crtc_reset(struct drm_crtc *crtc, struct drm_crtc_state *crtc_state) { if (crtc_state) __drm_atomic_helper_crtc_state_reset(crtc_state, crtc); if (drm_dev_has_vblank(crtc->dev)) drm_crtc_vblank_reset(crtc); crtc->state = crtc_state; } EXPORT_SYMBOL(__drm_atomic_helper_crtc_reset); /** * drm_atomic_helper_crtc_reset - default &drm_crtc_funcs.reset hook for CRTCs * @crtc: drm CRTC * * Resets the atomic state for @crtc by freeing the state pointer (which might * be NULL, e.g. at driver load time) and allocating a new empty state object. */ void drm_atomic_helper_crtc_reset(struct drm_crtc *crtc) { struct drm_crtc_state *crtc_state = kzalloc(sizeof(*crtc->state), GFP_KERNEL); if (crtc->state) crtc->funcs->atomic_destroy_state(crtc, crtc->state); __drm_atomic_helper_crtc_reset(crtc, crtc_state); } EXPORT_SYMBOL(drm_atomic_helper_crtc_reset); /** * __drm_atomic_helper_crtc_duplicate_state - copy atomic CRTC state * @crtc: CRTC object * @state: atomic CRTC state * * Copies atomic state from a CRTC's current state and resets inferred values. * This is useful for drivers that subclass the CRTC state. */ void __drm_atomic_helper_crtc_duplicate_state(struct drm_crtc *crtc, struct drm_crtc_state *state) { memcpy(state, crtc->state, sizeof(*state)); if (state->mode_blob) drm_property_blob_get(state->mode_blob); if (state->degamma_lut) drm_property_blob_get(state->degamma_lut); if (state->ctm) drm_property_blob_get(state->ctm); if (state->gamma_lut) drm_property_blob_get(state->gamma_lut); state->mode_changed = false; state->active_changed = false; state->planes_changed = false; state->connectors_changed = false; state->color_mgmt_changed = false; state->zpos_changed = false; state->commit = NULL; state->event = NULL; state->async_flip = false; /* Self refresh should be canceled when a new update is available */ state->active = drm_atomic_crtc_effectively_active(state); state->self_refresh_active = false; } EXPORT_SYMBOL(__drm_atomic_helper_crtc_duplicate_state); /** * drm_atomic_helper_crtc_duplicate_state - default state duplicate hook * @crtc: drm CRTC * * Default CRTC state duplicate hook for drivers which don't have their own * subclassed CRTC state structure. */ struct drm_crtc_state * drm_atomic_helper_crtc_duplicate_state(struct drm_crtc *crtc) { struct drm_crtc_state *state; if (WARN_ON(!crtc->state)) return NULL; state = kmalloc(sizeof(*state), GFP_KERNEL); if (state) __drm_atomic_helper_crtc_duplicate_state(crtc, state); return state; } EXPORT_SYMBOL(drm_atomic_helper_crtc_duplicate_state); /** * __drm_atomic_helper_crtc_destroy_state - release CRTC state * @state: CRTC state object to release * * Releases all resources stored in the CRTC state without actually freeing * the memory of the CRTC state. This is useful for drivers that subclass the * CRTC state. */ void __drm_atomic_helper_crtc_destroy_state(struct drm_crtc_state *state) { if (state->commit) { /* * In the event that a non-blocking commit returns * -ERESTARTSYS before the commit_tail work is queued, we will * have an extra reference to the commit object. Release it, if * the event has not been consumed by the worker. * * state->event may be freed, so we can't directly look at * state->event->base.completion. */ if (state->event && state->commit->abort_completion) drm_crtc_commit_put(state->commit); kfree(state->commit->event); state->commit->event = NULL; drm_crtc_commit_put(state->commit); } drm_property_blob_put(state->mode_blob); drm_property_blob_put(state->degamma_lut); drm_property_blob_put(state->ctm); drm_property_blob_put(state->gamma_lut); } EXPORT_SYMBOL(__drm_atomic_helper_crtc_destroy_state); /** * drm_atomic_helper_crtc_destroy_state - default state destroy hook * @crtc: drm CRTC * @state: CRTC state object to release * * Default CRTC state destroy hook for drivers which don't have their own * subclassed CRTC state structure. */ void drm_atomic_helper_crtc_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *state) { __drm_atomic_helper_crtc_destroy_state(state); kfree(state); } EXPORT_SYMBOL(drm_atomic_helper_crtc_destroy_state); /** * __drm_atomic_helper_plane_state_reset - resets plane state to default values * @plane_state: atomic plane state, must not be NULL * @plane: plane object, must not be NULL * * Initializes the newly allocated @plane_state with default * values. This is useful for drivers that subclass the CRTC state. */ void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state, struct drm_plane *plane) { u64 val; plane_state->plane = plane; plane_state->rotation = DRM_MODE_ROTATE_0; plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE; plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI; if (plane->color_encoding_property) { if (!drm_object_property_get_default_value(&plane->base, plane->color_encoding_property, &val)) plane_state->color_encoding = val; } if (plane->color_range_property) { if (!drm_object_property_get_default_value(&plane->base, plane->color_range_property, &val)) plane_state->color_range = val; } if (plane->zpos_property) { if (!drm_object_property_get_default_value(&plane->base, plane->zpos_property, &val)) { plane_state->zpos = val; plane_state->normalized_zpos = val; } } if (plane->hotspot_x_property) { if (!drm_object_property_get_default_value(&plane->base, plane->hotspot_x_property, &val)) plane_state->hotspot_x = val; } if (plane->hotspot_y_property) { if (!drm_object_property_get_default_value(&plane->base, plane->hotspot_y_property, &val)) plane_state->hotspot_y = val; } } EXPORT_SYMBOL(__drm_atomic_helper_plane_state_reset); /** * __drm_atomic_helper_plane_reset - reset state on plane * @plane: drm plane * @plane_state: plane state to assign * * Initializes the newly allocated @plane_state and assigns it to * the &drm_crtc->state pointer of @plane, usually required when * initializing the drivers or when called from the &drm_plane_funcs.reset * hook. * * This is useful for drivers that subclass the plane state. */ void __drm_atomic_helper_plane_reset(struct drm_plane *plane, struct drm_plane_state *plane_state) { if (plane_state) __drm_atomic_helper_plane_state_reset(plane_state, plane); plane->state = plane_state; } EXPORT_SYMBOL(__drm_atomic_helper_plane_reset); /** * drm_atomic_helper_plane_reset - default &drm_plane_funcs.reset hook for planes * @plane: drm plane * * Resets the atomic state for @plane by freeing the state pointer (which might * be NULL, e.g. at driver load time) and allocating a new empty state object. */ void drm_atomic_helper_plane_reset(struct drm_plane *plane) { if (plane->state) __drm_atomic_helper_plane_destroy_state(plane->state); kfree(plane->state); plane->state = kzalloc(sizeof(*plane->state), GFP_KERNEL); if (plane->state) __drm_atomic_helper_plane_reset(plane, plane->state); } EXPORT_SYMBOL(drm_atomic_helper_plane_reset); /** * __drm_atomic_helper_plane_duplicate_state - copy atomic plane state * @plane: plane object * @state: atomic plane state * * Copies atomic state from a plane's current state. This is useful for * drivers that subclass the plane state. */ void __drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane, struct drm_plane_state *state) { memcpy(state, plane->state, sizeof(*state)); if (state->fb) drm_framebuffer_get(state->fb); state->fence = NULL; state->commit = NULL; state->fb_damage_clips = NULL; state->color_mgmt_changed = false; } EXPORT_SYMBOL(__drm_atomic_helper_plane_duplicate_state); /** * drm_atomic_helper_plane_duplicate_state - default state duplicate hook * @plane: drm plane * * Default plane state duplicate hook for drivers which don't have their own * subclassed plane state structure. */ struct drm_plane_state * drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane) { struct drm_plane_state *state; if (WARN_ON(!plane->state)) return NULL; state = kmalloc(sizeof(*state), GFP_KERNEL); if (state) __drm_atomic_helper_plane_duplicate_state(plane, state); return state; } EXPORT_SYMBOL(drm_atomic_helper_plane_duplicate_state); /** * __drm_atomic_helper_plane_destroy_state - release plane state * @state: plane state object to release * * Releases all resources stored in the plane state without actually freeing * the memory of the plane state. This is useful for drivers that subclass the * plane state. */ void __drm_atomic_helper_plane_destroy_state(struct drm_plane_state *state) { if (state->fb) drm_framebuffer_put(state->fb); if (state->fence) dma_fence_put(state->fence); if (state->commit) drm_crtc_commit_put(state->commit); drm_property_blob_put(state->fb_damage_clips); } EXPORT_SYMBOL(__drm_atomic_helper_plane_destroy_state); /** * drm_atomic_helper_plane_destroy_state - default state destroy hook * @plane: drm plane * @state: plane state object to release * * Default plane state destroy hook for drivers which don't have their own * subclassed plane state structure. */ void drm_atomic_helper_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state) { __drm_atomic_helper_plane_destroy_state(state); kfree(state); } EXPORT_SYMBOL(drm_atomic_helper_plane_destroy_state); /** * __drm_atomic_helper_connector_state_reset - reset the connector state * @conn_state: atomic connector state, must not be NULL * @connector: connectotr object, must not be NULL * * Initializes the newly allocated @conn_state with default * values. This is useful for drivers that subclass the connector state. */ void __drm_atomic_helper_connector_state_reset(struct drm_connector_state *conn_state, struct drm_connector *connector) { conn_state->connector = connector; } EXPORT_SYMBOL(__drm_atomic_helper_connector_state_reset); /** * __drm_atomic_helper_connector_reset - reset state on connector * @connector: drm connector * @conn_state: connector state to assign * * Initializes the newly allocated @conn_state and assigns it to * the &drm_connector->state pointer of @connector, usually required when * initializing the drivers or when called from the &drm_connector_funcs.reset * hook. * * This is useful for drivers that subclass the connector state. */ void __drm_atomic_helper_connector_reset(struct drm_connector *connector, struct drm_connector_state *conn_state) { if (conn_state) __drm_atomic_helper_connector_state_reset(conn_state, connector); connector->state = conn_state; } EXPORT_SYMBOL(__drm_atomic_helper_connector_reset); /** * drm_atomic_helper_connector_reset - default &drm_connector_funcs.reset hook for connectors * @connector: drm connector * * Resets the atomic state for @connector by freeing the state pointer (which * might be NULL, e.g. at driver load time) and allocating a new empty state * object. */ void drm_atomic_helper_connector_reset(struct drm_connector *connector) { struct drm_connector_state *conn_state = kzalloc(sizeof(*conn_state), GFP_KERNEL); if (connector->state) __drm_atomic_helper_connector_destroy_state(connector->state); kfree(connector->state); __drm_atomic_helper_connector_reset(connector, conn_state); } EXPORT_SYMBOL(drm_atomic_helper_connector_reset); /** * drm_atomic_helper_connector_tv_margins_reset - Resets TV connector properties * @connector: DRM connector * * Resets the TV-related properties attached to a connector. */ void drm_atomic_helper_connector_tv_margins_reset(struct drm_connector *connector) { struct drm_cmdline_mode *cmdline = &connector->cmdline_mode; struct drm_connector_state *state = connector->state; state->tv.margins.left = cmdline->tv_margins.left; state->tv.margins.right = cmdline->tv_margins.right; state->tv.margins.top = cmdline->tv_margins.top; state->tv.margins.bottom = cmdline->tv_margins.bottom; } EXPORT_SYMBOL(drm_atomic_helper_connector_tv_margins_reset); /** * drm_atomic_helper_connector_tv_reset - Resets Analog TV connector properties * @connector: DRM connector * * Resets the analog TV properties attached to a connector */ void drm_atomic_helper_connector_tv_reset(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct drm_cmdline_mode *cmdline = &connector->cmdline_mode; struct drm_connector_state *state = connector->state; struct drm_property *prop; uint64_t val; prop = dev->mode_config.tv_mode_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.mode = val; if (cmdline->tv_mode_specified) state->tv.mode = cmdline->tv_mode; prop = dev->mode_config.tv_select_subconnector_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.select_subconnector = val; prop = dev->mode_config.tv_subconnector_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.subconnector = val; prop = dev->mode_config.tv_brightness_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.brightness = val; prop = dev->mode_config.tv_contrast_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.contrast = val; prop = dev->mode_config.tv_flicker_reduction_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.flicker_reduction = val; prop = dev->mode_config.tv_overscan_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.overscan = val; prop = dev->mode_config.tv_saturation_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.saturation = val; prop = dev->mode_config.tv_hue_property; if (prop) if (!drm_object_property_get_default_value(&connector->base, prop, &val)) state->tv.hue = val; drm_atomic_helper_connector_tv_margins_reset(connector); } EXPORT_SYMBOL(drm_atomic_helper_connector_tv_reset); /** * drm_atomic_helper_connector_tv_check - Validate an analog TV connector state * @connector: DRM Connector * @state: the DRM State object * * Checks the state object to see if the requested state is valid for an * analog TV connector. * * Return: * %0 for success, a negative error code on error. */ int drm_atomic_helper_connector_tv_check(struct drm_connector *connector, struct drm_atomic_state *state) { struct drm_connector_state *old_conn_state = drm_atomic_get_old_connector_state(state, connector); struct drm_connector_state *new_conn_state = drm_atomic_get_new_connector_state(state, connector); struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; crtc = new_conn_state->crtc; if (!crtc) return 0; crtc_state = drm_atomic_get_new_crtc_state(state, crtc); if (!crtc_state) return -EINVAL; if (old_conn_state->tv.mode != new_conn_state->tv.mode) crtc_state->mode_changed = true; if (old_conn_state->tv.margins.left != new_conn_state->tv.margins.left || old_conn_state->tv.margins.right != new_conn_state->tv.margins.right || old_conn_state->tv.margins.top != new_conn_state->tv.margins.top || old_conn_state->tv.margins.bottom != new_conn_state->tv.margins.bottom || old_conn_state->tv.mode != new_conn_state->tv.mode || old_conn_state->tv.brightness != new_conn_state->tv.brightness || old_conn_state->tv.contrast != new_conn_state->tv.contrast || old_conn_state->tv.flicker_reduction != new_conn_state->tv.flicker_reduction || old_conn_state->tv.overscan != new_conn_state->tv.overscan || old_conn_state->tv.saturation != new_conn_state->tv.saturation || old_conn_state->tv.hue != new_conn_state->tv.hue) crtc_state->connectors_changed = true; return 0; } EXPORT_SYMBOL(drm_atomic_helper_connector_tv_check); /** * __drm_atomic_helper_connector_duplicate_state - copy atomic connector state * @connector: connector object * @state: atomic connector state * * Copies atomic state from a connector's current state. This is useful for * drivers that subclass the connector state. */ void __drm_atomic_helper_connector_duplicate_state(struct drm_connector *connector, struct drm_connector_state *state) { memcpy(state, connector->state, sizeof(*state)); if (state->crtc) drm_connector_get(connector); state->commit = NULL; if (state->hdr_output_metadata) drm_property_blob_get(state->hdr_output_metadata); /* Don't copy over a writeback job, they are used only once */ state->writeback_job = NULL; } EXPORT_SYMBOL(__drm_atomic_helper_connector_duplicate_state); /** * drm_atomic_helper_connector_duplicate_state - default state duplicate hook * @connector: drm connector * * Default connector state duplicate hook for drivers which don't have their own * subclassed connector state structure. */ struct drm_connector_state * drm_atomic_helper_connector_duplicate_state(struct drm_connector *connector) { struct drm_connector_state *state; if (WARN_ON(!connector->state)) return NULL; state = kmalloc(sizeof(*state), GFP_KERNEL); if (state) __drm_atomic_helper_connector_duplicate_state(connector, state); return state; } EXPORT_SYMBOL(drm_atomic_helper_connector_duplicate_state); /** * __drm_atomic_helper_connector_destroy_state - release connector state * @state: connector state object to release * * Releases all resources stored in the connector state without actually * freeing the memory of the connector state. This is useful for drivers that * subclass the connector state. */ void __drm_atomic_helper_connector_destroy_state(struct drm_connector_state *state) { if (state->crtc) drm_connector_put(state->connector); if (state->commit) drm_crtc_commit_put(state->commit); if (state->writeback_job) drm_writeback_cleanup_job(state->writeback_job); drm_property_blob_put(state->hdr_output_metadata); } EXPORT_SYMBOL(__drm_atomic_helper_connector_destroy_state); /** * drm_atomic_helper_connector_destroy_state - default state destroy hook * @connector: drm connector * @state: connector state object to release * * Default connector state destroy hook for drivers which don't have their own * subclassed connector state structure. */ void drm_atomic_helper_connector_destroy_state(struct drm_connector *connector, struct drm_connector_state *state) { __drm_atomic_helper_connector_destroy_state(state); kfree(state); } EXPORT_SYMBOL(drm_atomic_helper_connector_destroy_state); /** * __drm_atomic_helper_private_obj_duplicate_state - copy atomic private state * @obj: CRTC object * @state: new private object state * * Copies atomic state from a private objects's current state and resets inferred values. * This is useful for drivers that subclass the private state. */ void __drm_atomic_helper_private_obj_duplicate_state(struct drm_private_obj *obj, struct drm_private_state *state) { memcpy(state, obj->state, sizeof(*state)); } EXPORT_SYMBOL(__drm_atomic_helper_private_obj_duplicate_state); /** * __drm_atomic_helper_bridge_duplicate_state() - Copy atomic bridge state * @bridge: bridge object * @state: atomic bridge state * * Copies atomic state from a bridge's current state and resets inferred values. * This is useful for drivers that subclass the bridge state. */ void __drm_atomic_helper_bridge_duplicate_state(struct drm_bridge *bridge, struct drm_bridge_state *state) { __drm_atomic_helper_private_obj_duplicate_state(&bridge->base, &state->base); state->bridge = bridge; } EXPORT_SYMBOL(__drm_atomic_helper_bridge_duplicate_state); /** * drm_atomic_helper_bridge_duplicate_state() - Duplicate a bridge state object * @bridge: bridge object * * Allocates a new bridge state and initializes it with the current bridge * state values. This helper is meant to be used as a bridge * &drm_bridge_funcs.atomic_duplicate_state hook for bridges that don't * subclass the bridge state. */ struct drm_bridge_state * drm_atomic_helper_bridge_duplicate_state(struct drm_bridge *bridge) { struct drm_bridge_state *new; if (WARN_ON(!bridge->base.state)) return NULL; new = kzalloc(sizeof(*new), GFP_KERNEL); if (new) __drm_atomic_helper_bridge_duplicate_state(bridge, new); return new; } EXPORT_SYMBOL(drm_atomic_helper_bridge_duplicate_state); /** * drm_atomic_helper_bridge_destroy_state() - Destroy a bridge state object * @bridge: the bridge this state refers to * @state: bridge state to destroy * * Destroys a bridge state previously created by * &drm_atomic_helper_bridge_reset() or * &drm_atomic_helper_bridge_duplicate_state(). This helper is meant to be * used as a bridge &drm_bridge_funcs.atomic_destroy_state hook for bridges * that don't subclass the bridge state. */ void drm_atomic_helper_bridge_destroy_state(struct drm_bridge *bridge, struct drm_bridge_state *state) { kfree(state); } EXPORT_SYMBOL(drm_atomic_helper_bridge_destroy_state); /** * __drm_atomic_helper_bridge_reset() - Initialize a bridge state to its * default * @bridge: the bridge this state refers to * @state: bridge state to initialize * * Initializes the bridge state to default values. This is meant to be called * by the bridge &drm_bridge_funcs.atomic_reset hook for bridges that subclass * the bridge state. */ void __drm_atomic_helper_bridge_reset(struct drm_bridge *bridge, struct drm_bridge_state *state) { memset(state, 0, sizeof(*state)); state->bridge = bridge; } EXPORT_SYMBOL(__drm_atomic_helper_bridge_reset); /** * drm_atomic_helper_bridge_reset() - Allocate and initialize a bridge state * to its default * @bridge: the bridge this state refers to * * Allocates the bridge state and initializes it to default values. This helper * is meant to be used as a bridge &drm_bridge_funcs.atomic_reset hook for * bridges that don't subclass the bridge state. */ struct drm_bridge_state * drm_atomic_helper_bridge_reset(struct drm_bridge *bridge) { struct drm_bridge_state *bridge_state; bridge_state = kzalloc(sizeof(*bridge_state), GFP_KERNEL); if (!bridge_state) return ERR_PTR(-ENOMEM); __drm_atomic_helper_bridge_reset(bridge, bridge_state); return bridge_state; } EXPORT_SYMBOL(drm_atomic_helper_bridge_reset);
3 9 7 2 9 9 3 3 9 2 7 7 2 2 3 3 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 // SPDX-License-Identifier: GPL-2.0 /* dvb-usb-dvb.c is part of the DVB USB library. * * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de) * see dvb-usb-init.c for copyright information. * * This file contains functions for initializing and handling the * linux-dvb API. */ #include "dvb-usb-common.h" #include <media/media-device.h> /* does the complete input transfer handling */ static int dvb_usb_ctrl_feed(struct dvb_demux_feed *dvbdmxfeed, int onoff) { struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv; int newfeedcount, ret; if (adap == NULL) return -ENODEV; if ((adap->active_fe < 0) || (adap->active_fe >= adap->num_frontends_initialized)) { return -EINVAL; } newfeedcount = adap->feedcount + (onoff ? 1 : -1); /* stop feed before setting a new pid if there will be no pid anymore */ if (newfeedcount == 0) { deb_ts("stop feeding\n"); usb_urb_kill(&adap->fe_adap[adap->active_fe].stream); if (adap->props.fe[adap->active_fe].streaming_ctrl != NULL) { ret = adap->props.fe[adap->active_fe].streaming_ctrl(adap, 0); if (ret < 0) { err("error while stopping stream."); return ret; } } } adap->feedcount = newfeedcount; /* activate the pid on the device specific pid_filter */ deb_ts("setting pid (%s): %5d %04x at index %d '%s'\n", adap->fe_adap[adap->active_fe].pid_filtering ? "yes" : "no", dvbdmxfeed->pid, dvbdmxfeed->pid, dvbdmxfeed->index, onoff ? "on" : "off"); if (adap->props.fe[adap->active_fe].caps & DVB_USB_ADAP_HAS_PID_FILTER && adap->fe_adap[adap->active_fe].pid_filtering && adap->props.fe[adap->active_fe].pid_filter != NULL) adap->props.fe[adap->active_fe].pid_filter(adap, dvbdmxfeed->index, dvbdmxfeed->pid, onoff); /* start the feed if this was the first feed and there is still a feed * for reception. */ if (adap->feedcount == onoff && adap->feedcount > 0) { deb_ts("controlling pid parser\n"); if (adap->props.fe[adap->active_fe].caps & DVB_USB_ADAP_HAS_PID_FILTER && adap->props.fe[adap->active_fe].caps & DVB_USB_ADAP_PID_FILTER_CAN_BE_TURNED_OFF && adap->props.fe[adap->active_fe].pid_filter_ctrl != NULL) { ret = adap->props.fe[adap->active_fe].pid_filter_ctrl(adap, adap->fe_adap[adap->active_fe].pid_filtering); if (ret < 0) { err("could not handle pid_parser"); return ret; } } deb_ts("start feeding\n"); if (adap->props.fe[adap->active_fe].streaming_ctrl != NULL) { ret = adap->props.fe[adap->active_fe].streaming_ctrl(adap, 1); if (ret < 0) { err("error while enabling fifo."); return ret; } } deb_ts("submitting all URBs\n"); usb_urb_submit(&adap->fe_adap[adap->active_fe].stream); } return 0; } static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed) { deb_ts("start pid: 0x%04x, feedtype: %d\n", dvbdmxfeed->pid, dvbdmxfeed->type); return dvb_usb_ctrl_feed(dvbdmxfeed, 1); } static int dvb_usb_stop_feed(struct dvb_demux_feed *dvbdmxfeed) { deb_ts("stop pid: 0x%04x, feedtype: %d\n", dvbdmxfeed->pid, dvbdmxfeed->type); return dvb_usb_ctrl_feed(dvbdmxfeed, 0); } static int dvb_usb_media_device_init(struct dvb_usb_adapter *adap) { #ifdef CONFIG_MEDIA_CONTROLLER_DVB struct media_device *mdev; struct dvb_usb_device *d = adap->dev; struct usb_device *udev = d->udev; mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return -ENOMEM; media_device_usb_init(mdev, udev, d->desc->name); dvb_register_media_controller(&adap->dvb_adap, mdev); dev_info(&d->udev->dev, "media controller created\n"); #endif return 0; } static int dvb_usb_media_device_register(struct dvb_usb_adapter *adap) { #ifdef CONFIG_MEDIA_CONTROLLER_DVB return media_device_register(adap->dvb_adap.mdev); #else return 0; #endif } static void dvb_usb_media_device_unregister(struct dvb_usb_adapter *adap) { #ifdef CONFIG_MEDIA_CONTROLLER_DVB if (!adap->dvb_adap.mdev) return; mutex_lock(&adap->dvb_adap.mdev_lock); media_device_unregister(adap->dvb_adap.mdev); media_device_cleanup(adap->dvb_adap.mdev); kfree(adap->dvb_adap.mdev); adap->dvb_adap.mdev = NULL; mutex_unlock(&adap->dvb_adap.mdev_lock); #endif } int dvb_usb_adapter_dvb_init(struct dvb_usb_adapter *adap, short *adapter_nums) { int i; int ret = dvb_register_adapter(&adap->dvb_adap, adap->dev->desc->name, adap->dev->owner, &adap->dev->udev->dev, adapter_nums); if (ret < 0) { deb_info("dvb_register_adapter failed: error %d", ret); goto err; } adap->dvb_adap.priv = adap; ret = dvb_usb_media_device_init(adap); if (ret < 0) { deb_info("dvb_usb_media_device_init failed: error %d", ret); goto err_mc; } if (adap->dev->props.read_mac_address) { if (adap->dev->props.read_mac_address(adap->dev, adap->dvb_adap.proposed_mac) == 0) info("MAC address: %pM", adap->dvb_adap.proposed_mac); else err("MAC address reading failed."); } adap->demux.dmx.capabilities = DMX_TS_FILTERING | DMX_SECTION_FILTERING; adap->demux.priv = adap; adap->demux.filternum = 0; for (i = 0; i < adap->props.num_frontends; i++) { if (adap->demux.filternum < adap->fe_adap[i].max_feed_count) adap->demux.filternum = adap->fe_adap[i].max_feed_count; } adap->demux.feednum = adap->demux.filternum; adap->demux.start_feed = dvb_usb_start_feed; adap->demux.stop_feed = dvb_usb_stop_feed; adap->demux.write_to_decoder = NULL; if ((ret = dvb_dmx_init(&adap->demux)) < 0) { err("dvb_dmx_init failed: error %d", ret); goto err_dmx; } adap->dmxdev.filternum = adap->demux.filternum; adap->dmxdev.demux = &adap->demux.dmx; adap->dmxdev.capabilities = 0; if ((ret = dvb_dmxdev_init(&adap->dmxdev, &adap->dvb_adap)) < 0) { err("dvb_dmxdev_init failed: error %d", ret); goto err_dmx_dev; } if ((ret = dvb_net_init(&adap->dvb_adap, &adap->dvb_net, &adap->demux.dmx)) < 0) { err("dvb_net_init failed: error %d", ret); goto err_net_init; } adap->state |= DVB_USB_ADAP_STATE_DVB; return 0; err_net_init: dvb_dmxdev_release(&adap->dmxdev); err_dmx_dev: dvb_dmx_release(&adap->demux); err_dmx: dvb_usb_media_device_unregister(adap); err_mc: dvb_unregister_adapter(&adap->dvb_adap); err: return ret; } int dvb_usb_adapter_dvb_exit(struct dvb_usb_adapter *adap) { if (adap->state & DVB_USB_ADAP_STATE_DVB) { deb_info("unregistering DVB part\n"); dvb_net_release(&adap->dvb_net); adap->demux.dmx.close(&adap->demux.dmx); dvb_dmxdev_release(&adap->dmxdev); dvb_dmx_release(&adap->demux); dvb_usb_media_device_unregister(adap); dvb_unregister_adapter(&adap->dvb_adap); adap->state &= ~DVB_USB_ADAP_STATE_DVB; } return 0; } static int dvb_usb_set_active_fe(struct dvb_frontend *fe, int onoff) { struct dvb_usb_adapter *adap = fe->dvb->priv; int ret = (adap->props.frontend_ctrl) ? adap->props.frontend_ctrl(fe, onoff) : 0; if (ret < 0) { err("frontend_ctrl request failed"); return ret; } if (onoff) adap->active_fe = fe->id; return 0; } static int dvb_usb_fe_wakeup(struct dvb_frontend *fe) { struct dvb_usb_adapter *adap = fe->dvb->priv; dvb_usb_device_power_ctrl(adap->dev, 1); dvb_usb_set_active_fe(fe, 1); if (adap->fe_adap[fe->id].fe_init) adap->fe_adap[fe->id].fe_init(fe); return 0; } static int dvb_usb_fe_sleep(struct dvb_frontend *fe) { struct dvb_usb_adapter *adap = fe->dvb->priv; if (adap->fe_adap[fe->id].fe_sleep) adap->fe_adap[fe->id].fe_sleep(fe); dvb_usb_set_active_fe(fe, 0); return dvb_usb_device_power_ctrl(adap->dev, 0); } int dvb_usb_adapter_frontend_init(struct dvb_usb_adapter *adap) { int ret, i; /* register all given adapter frontends */ for (i = 0; i < adap->props.num_frontends; i++) { if (adap->props.fe[i].frontend_attach == NULL) { err("strange: '%s' #%d,%d doesn't want to attach a frontend.", adap->dev->desc->name, adap->id, i); return 0; } ret = adap->props.fe[i].frontend_attach(adap); if (ret || adap->fe_adap[i].fe == NULL) { /* only print error when there is no FE at all */ if (i == 0) err("no frontend was attached by '%s'", adap->dev->desc->name); return 0; } adap->fe_adap[i].fe->id = i; /* re-assign sleep and wakeup functions */ adap->fe_adap[i].fe_init = adap->fe_adap[i].fe->ops.init; adap->fe_adap[i].fe->ops.init = dvb_usb_fe_wakeup; adap->fe_adap[i].fe_sleep = adap->fe_adap[i].fe->ops.sleep; adap->fe_adap[i].fe->ops.sleep = dvb_usb_fe_sleep; if (dvb_register_frontend(&adap->dvb_adap, adap->fe_adap[i].fe)) { err("Frontend %d registration failed.", i); dvb_frontend_detach(adap->fe_adap[i].fe); adap->fe_adap[i].fe = NULL; /* In error case, do not try register more FEs, * still leaving already registered FEs alive. */ if (i == 0) return -ENODEV; else return 0; } /* only attach the tuner if the demod is there */ if (adap->props.fe[i].tuner_attach != NULL) adap->props.fe[i].tuner_attach(adap); adap->num_frontends_initialized++; } ret = dvb_create_media_graph(&adap->dvb_adap, true); if (ret) return ret; ret = dvb_usb_media_device_register(adap); return ret; } int dvb_usb_adapter_frontend_exit(struct dvb_usb_adapter *adap) { int i = adap->num_frontends_initialized - 1; /* unregister all given adapter frontends */ for (; i >= 0; i--) { if (adap->fe_adap[i].fe != NULL) { dvb_unregister_frontend(adap->fe_adap[i].fe); dvb_frontend_detach(adap->fe_adap[i].fe); } } adap->num_frontends_initialized = 0; return 0; }
2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 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 // SPDX-License-Identifier: GPL-2.0-only /* * MCP2221A - Microchip USB to I2C Host Protocol Bridge * * Copyright (c) 2020, Rishi Gupta <gupt21@gmail.com> * * Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/20005565B.pdf */ #include <linux/module.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/bitfield.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/hid.h> #include <linux/hidraw.h> #include <linux/i2c.h> #include <linux/gpio/driver.h> #include <linux/iio/iio.h> #include "hid-ids.h" /* Commands codes in a raw output report */ enum { MCP2221_I2C_WR_DATA = 0x90, MCP2221_I2C_WR_NO_STOP = 0x94, MCP2221_I2C_RD_DATA = 0x91, MCP2221_I2C_RD_RPT_START = 0x93, MCP2221_I2C_GET_DATA = 0x40, MCP2221_I2C_PARAM_OR_STATUS = 0x10, MCP2221_I2C_SET_SPEED = 0x20, MCP2221_I2C_CANCEL = 0x10, MCP2221_GPIO_SET = 0x50, MCP2221_GPIO_GET = 0x51, MCP2221_SET_SRAM_SETTINGS = 0x60, MCP2221_GET_SRAM_SETTINGS = 0x61, MCP2221_READ_FLASH_DATA = 0xb0, }; /* Response codes in a raw input report */ enum { MCP2221_SUCCESS = 0x00, MCP2221_I2C_ENG_BUSY = 0x01, MCP2221_I2C_START_TOUT = 0x12, MCP2221_I2C_STOP_TOUT = 0x62, MCP2221_I2C_WRADDRL_TOUT = 0x23, MCP2221_I2C_WRDATA_TOUT = 0x44, MCP2221_I2C_WRADDRL_NACK = 0x25, MCP2221_I2C_MASK_ADDR_NACK = 0x40, MCP2221_I2C_WRADDRL_SEND = 0x21, MCP2221_I2C_ADDR_NACK = 0x25, MCP2221_I2C_READ_PARTIAL = 0x54, MCP2221_I2C_READ_COMPL = 0x55, MCP2221_ALT_F_NOT_GPIOV = 0xEE, MCP2221_ALT_F_NOT_GPIOD = 0xEF, }; /* MCP GPIO direction encoding */ enum { MCP2221_DIR_OUT = 0x00, MCP2221_DIR_IN = 0x01, }; #define MCP_NGPIO 4 /* MCP GPIO set command layout */ struct mcp_set_gpio { u8 cmd; u8 dummy; struct { u8 change_value; u8 value; u8 change_direction; u8 direction; } gpio[MCP_NGPIO]; } __packed; /* MCP GPIO get command layout */ struct mcp_get_gpio { u8 cmd; u8 dummy; struct { u8 value; u8 direction; } gpio[MCP_NGPIO]; } __packed; /* * There is no way to distinguish responses. Therefore next command * is sent only after response to previous has been received. Mutex * lock is used for this purpose mainly. */ struct mcp2221 { struct hid_device *hdev; struct i2c_adapter adapter; struct mutex lock; struct completion wait_in_report; struct delayed_work init_work; u8 *rxbuf; u8 txbuf[64]; int rxbuf_idx; int status; u8 cur_i2c_clk_div; struct gpio_chip *gc; u8 gp_idx; u8 gpio_dir; u8 mode[4]; #if IS_REACHABLE(CONFIG_IIO) struct iio_chan_spec iio_channels[3]; u16 adc_values[3]; u8 adc_scale; u8 dac_value; u16 dac_scale; #endif }; struct mcp2221_iio { struct mcp2221 *mcp; }; /* * Default i2c bus clock frequency 400 kHz. Modify this if you * want to set some other frequency (min 50 kHz - max 400 kHz). */ static uint i2c_clk_freq = 400; /* Synchronously send output report to the device */ static int mcp_send_report(struct mcp2221 *mcp, u8 *out_report, size_t len) { u8 *buf; int ret; buf = kmemdup(out_report, len, GFP_KERNEL); if (!buf) return -ENOMEM; /* mcp2221 uses interrupt endpoint for out reports */ ret = hid_hw_output_report(mcp->hdev, buf, len); kfree(buf); if (ret < 0) return ret; return 0; } /* * Send o/p report to the device and wait for i/p report to be * received from the device. If the device does not respond, * we timeout. */ static int mcp_send_data_req_status(struct mcp2221 *mcp, u8 *out_report, int len) { int ret; unsigned long t; reinit_completion(&mcp->wait_in_report); ret = mcp_send_report(mcp, out_report, len); if (ret) return ret; t = wait_for_completion_timeout(&mcp->wait_in_report, msecs_to_jiffies(4000)); if (!t) return -ETIMEDOUT; return mcp->status; } /* Check pass/fail for actual communication with i2c slave */ static int mcp_chk_last_cmd_status(struct mcp2221 *mcp) { memset(mcp->txbuf, 0, 8); mcp->txbuf[0] = MCP2221_I2C_PARAM_OR_STATUS; return mcp_send_data_req_status(mcp, mcp->txbuf, 8); } /* Cancels last command releasing i2c bus just in case occupied */ static int mcp_cancel_last_cmd(struct mcp2221 *mcp) { memset(mcp->txbuf, 0, 8); mcp->txbuf[0] = MCP2221_I2C_PARAM_OR_STATUS; mcp->txbuf[2] = MCP2221_I2C_CANCEL; return mcp_send_data_req_status(mcp, mcp->txbuf, 8); } /* Check if the last command succeeded or failed and return the result. * If the command did fail, cancel that command which will free the i2c bus. */ static int mcp_chk_last_cmd_status_free_bus(struct mcp2221 *mcp) { int ret; ret = mcp_chk_last_cmd_status(mcp); if (ret) { /* The last command was a failure. * Send a cancel which will also free the bus. */ usleep_range(980, 1000); mcp_cancel_last_cmd(mcp); } return ret; } static int mcp_set_i2c_speed(struct mcp2221 *mcp) { int ret; memset(mcp->txbuf, 0, 8); mcp->txbuf[0] = MCP2221_I2C_PARAM_OR_STATUS; mcp->txbuf[3] = MCP2221_I2C_SET_SPEED; mcp->txbuf[4] = mcp->cur_i2c_clk_div; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 8); if (ret) { /* Small delay is needed here */ usleep_range(980, 1000); mcp_cancel_last_cmd(mcp); } return 0; } /* * An output report can contain minimum 1 and maximum 60 user data * bytes. If the number of data bytes is more then 60, we send it * in chunks of 60 bytes. Last chunk may contain exactly 60 or less * bytes. Total number of bytes is informed in very first report to * mcp2221, from that point onwards it first collect all the data * from host and then send to i2c slave device. */ static int mcp_i2c_write(struct mcp2221 *mcp, struct i2c_msg *msg, int type, u8 last_status) { int ret, len, idx, sent; idx = 0; sent = 0; if (msg->len < 60) len = msg->len; else len = 60; do { mcp->txbuf[0] = type; mcp->txbuf[1] = msg->len & 0xff; mcp->txbuf[2] = msg->len >> 8; mcp->txbuf[3] = (u8)(msg->addr << 1); memcpy(&mcp->txbuf[4], &msg->buf[idx], len); ret = mcp_send_data_req_status(mcp, mcp->txbuf, len + 4); if (ret) return ret; usleep_range(980, 1000); if (last_status) { ret = mcp_chk_last_cmd_status_free_bus(mcp); if (ret) return ret; } sent = sent + len; if (sent >= msg->len) break; idx = idx + len; if ((msg->len - sent) < 60) len = msg->len - sent; else len = 60; /* * Testing shows delay is needed between successive writes * otherwise next write fails on first-try from i2c core. * This value is obtained through automated stress testing. */ usleep_range(980, 1000); } while (len > 0); return ret; } /* * Device reads all data (0 - 65535 bytes) from i2c slave device and * stores it in device itself. This data is read back from device to * host in multiples of 60 bytes using input reports. */ static int mcp_i2c_smbus_read(struct mcp2221 *mcp, struct i2c_msg *msg, int type, u16 smbus_addr, u8 smbus_len, u8 *smbus_buf) { int ret; u16 total_len; int retries = 0; mcp->txbuf[0] = type; if (msg) { mcp->txbuf[1] = msg->len & 0xff; mcp->txbuf[2] = msg->len >> 8; mcp->txbuf[3] = (u8)(msg->addr << 1); total_len = msg->len; mcp->rxbuf = msg->buf; } else { mcp->txbuf[1] = smbus_len; mcp->txbuf[2] = 0; mcp->txbuf[3] = (u8)(smbus_addr << 1); total_len = smbus_len; mcp->rxbuf = smbus_buf; } ret = mcp_send_data_req_status(mcp, mcp->txbuf, 4); if (ret) return ret; mcp->rxbuf_idx = 0; do { /* Wait for the data to be read by the device */ usleep_range(980, 1000); memset(mcp->txbuf, 0, 4); mcp->txbuf[0] = MCP2221_I2C_GET_DATA; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); if (ret) { if (retries < 5) { /* The data wasn't ready to read. * Wait a bit longer and try again. */ usleep_range(90, 100); retries++; } else { return ret; } } else { retries = 0; } } while (mcp->rxbuf_idx < total_len); usleep_range(980, 1000); ret = mcp_chk_last_cmd_status_free_bus(mcp); return ret; } static int mcp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg msgs[], int num) { int ret; struct mcp2221 *mcp = i2c_get_adapdata(adapter); hid_hw_power(mcp->hdev, PM_HINT_FULLON); mutex_lock(&mcp->lock); if (num == 1) { if (msgs->flags & I2C_M_RD) { ret = mcp_i2c_smbus_read(mcp, msgs, MCP2221_I2C_RD_DATA, 0, 0, NULL); } else { ret = mcp_i2c_write(mcp, msgs, MCP2221_I2C_WR_DATA, 1); } if (ret) goto exit; ret = num; } else if (num == 2) { /* Ex transaction; send reg address and read its contents */ if (msgs[0].addr == msgs[1].addr && !(msgs[0].flags & I2C_M_RD) && (msgs[1].flags & I2C_M_RD)) { ret = mcp_i2c_write(mcp, &msgs[0], MCP2221_I2C_WR_NO_STOP, 0); if (ret) goto exit; ret = mcp_i2c_smbus_read(mcp, &msgs[1], MCP2221_I2C_RD_RPT_START, 0, 0, NULL); if (ret) goto exit; ret = num; } else { dev_err(&adapter->dev, "unsupported multi-msg i2c transaction\n"); ret = -EOPNOTSUPP; } } else { dev_err(&adapter->dev, "unsupported multi-msg i2c transaction\n"); ret = -EOPNOTSUPP; } exit: hid_hw_power(mcp->hdev, PM_HINT_NORMAL); mutex_unlock(&mcp->lock); return ret; } static int mcp_smbus_write(struct mcp2221 *mcp, u16 addr, u8 command, u8 *buf, u8 len, int type, u8 last_status) { int data_len, ret; mcp->txbuf[0] = type; mcp->txbuf[1] = len + 1; /* 1 is due to command byte itself */ mcp->txbuf[2] = 0; mcp->txbuf[3] = (u8)(addr << 1); mcp->txbuf[4] = command; switch (len) { case 0: data_len = 5; break; case 1: mcp->txbuf[5] = buf[0]; data_len = 6; break; case 2: mcp->txbuf[5] = buf[0]; mcp->txbuf[6] = buf[1]; data_len = 7; break; default: if (len > I2C_SMBUS_BLOCK_MAX) return -EINVAL; memcpy(&mcp->txbuf[5], buf, len); data_len = len + 5; } ret = mcp_send_data_req_status(mcp, mcp->txbuf, data_len); if (ret) return ret; if (last_status) { usleep_range(980, 1000); ret = mcp_chk_last_cmd_status_free_bus(mcp); } return ret; } static int mcp_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data) { int ret; struct mcp2221 *mcp = i2c_get_adapdata(adapter); hid_hw_power(mcp->hdev, PM_HINT_FULLON); mutex_lock(&mcp->lock); switch (size) { case I2C_SMBUS_QUICK: if (read_write == I2C_SMBUS_READ) ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_DATA, addr, 0, &data->byte); else ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_DATA, 1); break; case I2C_SMBUS_BYTE: if (read_write == I2C_SMBUS_READ) ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_DATA, addr, 1, &data->byte); else ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_DATA, 1); break; case I2C_SMBUS_BYTE_DATA: if (read_write == I2C_SMBUS_READ) { ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_NO_STOP, 0); if (ret) goto exit; ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_RPT_START, addr, 1, &data->byte); } else { ret = mcp_smbus_write(mcp, addr, command, &data->byte, 1, MCP2221_I2C_WR_DATA, 1); } break; case I2C_SMBUS_WORD_DATA: if (read_write == I2C_SMBUS_READ) { ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_NO_STOP, 0); if (ret) goto exit; ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_RPT_START, addr, 2, (u8 *)&data->word); } else { ret = mcp_smbus_write(mcp, addr, command, (u8 *)&data->word, 2, MCP2221_I2C_WR_DATA, 1); } break; case I2C_SMBUS_BLOCK_DATA: if (read_write == I2C_SMBUS_READ) { ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_NO_STOP, 1); if (ret) goto exit; mcp->rxbuf_idx = 0; mcp->rxbuf = data->block; mcp->txbuf[0] = MCP2221_I2C_GET_DATA; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); if (ret) goto exit; } else { if (!data->block[0]) { ret = -EINVAL; goto exit; } ret = mcp_smbus_write(mcp, addr, command, data->block, data->block[0] + 1, MCP2221_I2C_WR_DATA, 1); } break; case I2C_SMBUS_I2C_BLOCK_DATA: if (read_write == I2C_SMBUS_READ) { ret = mcp_smbus_write(mcp, addr, command, NULL, 0, MCP2221_I2C_WR_NO_STOP, 1); if (ret) goto exit; mcp->rxbuf_idx = 0; mcp->rxbuf = data->block; mcp->txbuf[0] = MCP2221_I2C_GET_DATA; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); if (ret) goto exit; } else { if (!data->block[0]) { ret = -EINVAL; goto exit; } ret = mcp_smbus_write(mcp, addr, command, &data->block[1], data->block[0], MCP2221_I2C_WR_DATA, 1); } break; case I2C_SMBUS_PROC_CALL: ret = mcp_smbus_write(mcp, addr, command, (u8 *)&data->word, 2, MCP2221_I2C_WR_NO_STOP, 0); if (ret) goto exit; ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_RPT_START, addr, 2, (u8 *)&data->word); break; case I2C_SMBUS_BLOCK_PROC_CALL: ret = mcp_smbus_write(mcp, addr, command, data->block, data->block[0] + 1, MCP2221_I2C_WR_NO_STOP, 0); if (ret) goto exit; ret = mcp_i2c_smbus_read(mcp, NULL, MCP2221_I2C_RD_RPT_START, addr, I2C_SMBUS_BLOCK_MAX, data->block); break; default: dev_err(&mcp->adapter.dev, "unsupported smbus transaction size:%d\n", size); ret = -EOPNOTSUPP; } exit: hid_hw_power(mcp->hdev, PM_HINT_NORMAL); mutex_unlock(&mcp->lock); return ret; } static u32 mcp_i2c_func(struct i2c_adapter *adapter) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_READ_BLOCK_DATA | I2C_FUNC_SMBUS_BLOCK_PROC_CALL | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_PEC); } static const struct i2c_algorithm mcp_i2c_algo = { .master_xfer = mcp_i2c_xfer, .smbus_xfer = mcp_smbus_xfer, .functionality = mcp_i2c_func, }; #if IS_REACHABLE(CONFIG_GPIOLIB) static int mcp_gpio_get(struct gpio_chip *gc, unsigned int offset) { int ret; struct mcp2221 *mcp = gpiochip_get_data(gc); mcp->txbuf[0] = MCP2221_GPIO_GET; mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset]); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); mutex_unlock(&mcp->lock); return ret; } static void mcp_gpio_set(struct gpio_chip *gc, unsigned int offset, int value) { struct mcp2221 *mcp = gpiochip_get_data(gc); memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].value); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = !!value; mutex_lock(&mcp->lock); mcp_send_data_req_status(mcp, mcp->txbuf, 18); mutex_unlock(&mcp->lock); } static int mcp_gpio_dir_set(struct mcp2221 *mcp, unsigned int offset, u8 val) { memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].direction); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = val; return mcp_send_data_req_status(mcp, mcp->txbuf, 18); } static int mcp_gpio_direction_input(struct gpio_chip *gc, unsigned int offset) { int ret; struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_IN); mutex_unlock(&mcp->lock); return ret; } static int mcp_gpio_direction_output(struct gpio_chip *gc, unsigned int offset, int value) { int ret; struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_OUT); mutex_unlock(&mcp->lock); /* Can't configure as output, bailout early */ if (ret) return ret; mcp_gpio_set(gc, offset, value); return 0; } static int mcp_gpio_get_direction(struct gpio_chip *gc, unsigned int offset) { int ret; struct mcp2221 *mcp = gpiochip_get_data(gc); mcp->txbuf[0] = MCP2221_GPIO_GET; mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset]); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); mutex_unlock(&mcp->lock); if (ret) return ret; if (mcp->gpio_dir == MCP2221_DIR_IN) return GPIO_LINE_DIRECTION_IN; return GPIO_LINE_DIRECTION_OUT; } #endif /* Gives current state of i2c engine inside mcp2221 */ static int mcp_get_i2c_eng_state(struct mcp2221 *mcp, u8 *data, u8 idx) { int ret; switch (data[idx]) { case MCP2221_I2C_WRADDRL_NACK: case MCP2221_I2C_WRADDRL_SEND: ret = -ENXIO; break; case MCP2221_I2C_START_TOUT: case MCP2221_I2C_STOP_TOUT: case MCP2221_I2C_WRADDRL_TOUT: case MCP2221_I2C_WRDATA_TOUT: ret = -ETIMEDOUT; break; case MCP2221_I2C_ENG_BUSY: ret = -EAGAIN; break; case MCP2221_SUCCESS: ret = 0x00; break; default: ret = -EIO; } return ret; } /* * MCP2221 uses interrupt endpoint for input reports. This function * is called by HID layer when it receives i/p report from mcp2221, * which is actually a response to the previously sent command. * * MCP2221A firmware specific return codes are parsed and 0 or * appropriate negative error code is returned. Delayed response * results in timeout error and stray reponses results in -EIO. */ static int mcp2221_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { u8 *buf; struct mcp2221 *mcp = hid_get_drvdata(hdev); switch (data[0]) { case MCP2221_I2C_WR_DATA: case MCP2221_I2C_WR_NO_STOP: case MCP2221_I2C_RD_DATA: case MCP2221_I2C_RD_RPT_START: switch (data[1]) { case MCP2221_SUCCESS: mcp->status = 0; break; default: mcp->status = mcp_get_i2c_eng_state(mcp, data, 2); } complete(&mcp->wait_in_report); break; case MCP2221_I2C_PARAM_OR_STATUS: switch (data[1]) { case MCP2221_SUCCESS: if ((mcp->txbuf[3] == MCP2221_I2C_SET_SPEED) && (data[3] != MCP2221_I2C_SET_SPEED)) { mcp->status = -EAGAIN; break; } if (data[20] & MCP2221_I2C_MASK_ADDR_NACK) { mcp->status = -ENXIO; break; } mcp->status = mcp_get_i2c_eng_state(mcp, data, 8); #if IS_REACHABLE(CONFIG_IIO) memcpy(&mcp->adc_values, &data[50], sizeof(mcp->adc_values)); #endif break; default: mcp->status = -EIO; } complete(&mcp->wait_in_report); break; case MCP2221_I2C_GET_DATA: switch (data[1]) { case MCP2221_SUCCESS: if (data[2] == MCP2221_I2C_ADDR_NACK) { mcp->status = -ENXIO; break; } if (!mcp_get_i2c_eng_state(mcp, data, 2) && (data[3] == 0)) { mcp->status = 0; break; } if (data[3] == 127) { mcp->status = -EIO; break; } if (data[2] == MCP2221_I2C_READ_COMPL || data[2] == MCP2221_I2C_READ_PARTIAL) { buf = mcp->rxbuf; memcpy(&buf[mcp->rxbuf_idx], &data[4], data[3]); mcp->rxbuf_idx = mcp->rxbuf_idx + data[3]; mcp->status = 0; break; } mcp->status = -EIO; break; default: mcp->status = -EIO; } complete(&mcp->wait_in_report); break; case MCP2221_GPIO_GET: switch (data[1]) { case MCP2221_SUCCESS: if ((data[mcp->gp_idx] == MCP2221_ALT_F_NOT_GPIOV) || (data[mcp->gp_idx + 1] == MCP2221_ALT_F_NOT_GPIOD)) { mcp->status = -ENOENT; } else { mcp->status = !!data[mcp->gp_idx]; mcp->gpio_dir = data[mcp->gp_idx + 1]; } break; default: mcp->status = -EAGAIN; } complete(&mcp->wait_in_report); break; case MCP2221_GPIO_SET: switch (data[1]) { case MCP2221_SUCCESS: if ((data[mcp->gp_idx] == MCP2221_ALT_F_NOT_GPIOV) || (data[mcp->gp_idx - 1] == MCP2221_ALT_F_NOT_GPIOV)) { mcp->status = -ENOENT; } else { mcp->status = 0; } break; default: mcp->status = -EAGAIN; } complete(&mcp->wait_in_report); break; case MCP2221_SET_SRAM_SETTINGS: switch (data[1]) { case MCP2221_SUCCESS: mcp->status = 0; break; default: mcp->status = -EAGAIN; } complete(&mcp->wait_in_report); break; case MCP2221_GET_SRAM_SETTINGS: switch (data[1]) { case MCP2221_SUCCESS: memcpy(&mcp->mode, &data[22], 4); #if IS_REACHABLE(CONFIG_IIO) mcp->dac_value = data[6] & GENMASK(4, 0); #endif mcp->status = 0; break; default: mcp->status = -EAGAIN; } complete(&mcp->wait_in_report); break; case MCP2221_READ_FLASH_DATA: switch (data[1]) { case MCP2221_SUCCESS: mcp->status = 0; /* Only handles CHIP SETTINGS subpage currently */ if (mcp->txbuf[1] != 0) { mcp->status = -EIO; break; } #if IS_REACHABLE(CONFIG_IIO) { u8 tmp; /* DAC scale value */ tmp = FIELD_GET(GENMASK(7, 6), data[6]); if ((data[6] & BIT(5)) && tmp) mcp->dac_scale = tmp + 4; else mcp->dac_scale = 5; /* ADC scale value */ tmp = FIELD_GET(GENMASK(4, 3), data[7]); if ((data[7] & BIT(2)) && tmp) mcp->adc_scale = tmp - 1; else mcp->adc_scale = 0; } #endif break; default: mcp->status = -EAGAIN; } complete(&mcp->wait_in_report); break; default: mcp->status = -EIO; complete(&mcp->wait_in_report); } return 1; } /* Device resource managed function for HID unregistration */ static void mcp2221_hid_unregister(void *ptr) { struct hid_device *hdev = ptr; hid_hw_close(hdev); hid_hw_stop(hdev); } /* This is needed to be sure hid_hw_stop() isn't called twice by the subsystem */ static void mcp2221_remove(struct hid_device *hdev) { #if IS_REACHABLE(CONFIG_IIO) struct mcp2221 *mcp = hid_get_drvdata(hdev); cancel_delayed_work_sync(&mcp->init_work); #endif } #if IS_REACHABLE(CONFIG_IIO) static int mcp2221_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *channel, int *val, int *val2, long mask) { struct mcp2221_iio *priv = iio_priv(indio_dev); struct mcp2221 *mcp = priv->mcp; int ret; if (mask == IIO_CHAN_INFO_SCALE) { if (channel->output) *val = 1 << mcp->dac_scale; else *val = 1 << mcp->adc_scale; return IIO_VAL_INT; } mutex_lock(&mcp->lock); if (channel->output) { *val = mcp->dac_value; ret = IIO_VAL_INT; } else { /* Read ADC values */ ret = mcp_chk_last_cmd_status(mcp); if (!ret) { *val = le16_to_cpu((__force __le16) mcp->adc_values[channel->address]); if (*val >= BIT(10)) ret = -EINVAL; else ret = IIO_VAL_INT; } } mutex_unlock(&mcp->lock); return ret; } static int mcp2221_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, int val2, long mask) { struct mcp2221_iio *priv = iio_priv(indio_dev); struct mcp2221 *mcp = priv->mcp; int ret; if (val < 0 || val >= BIT(5)) return -EINVAL; mutex_lock(&mcp->lock); memset(mcp->txbuf, 0, 12); mcp->txbuf[0] = MCP2221_SET_SRAM_SETTINGS; mcp->txbuf[4] = BIT(7) | val; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 12); if (!ret) mcp->dac_value = val; mutex_unlock(&mcp->lock); return ret; } static const struct iio_info mcp2221_info = { .read_raw = &mcp2221_read_raw, .write_raw = &mcp2221_write_raw, }; static int mcp_iio_channels(struct mcp2221 *mcp) { int idx, cnt = 0; bool dac_created = false; /* GP0 doesn't have ADC/DAC alternative function */ for (idx = 1; idx < MCP_NGPIO; idx++) { struct iio_chan_spec *chan = &mcp->iio_channels[cnt]; switch (mcp->mode[idx]) { case 2: chan->address = idx - 1; chan->channel = cnt++; break; case 3: /* GP1 doesn't have DAC alternative function */ if (idx == 1 || dac_created) continue; /* DAC1 and DAC2 outputs are connected to the same DAC */ dac_created = true; chan->output = 1; cnt++; break; default: continue; } chan->type = IIO_VOLTAGE; chan->indexed = 1; chan->info_mask_separate = BIT(IIO_CHAN_INFO_RAW); chan->info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE); chan->scan_index = -1; } return cnt; } static void mcp_init_work(struct work_struct *work) { struct iio_dev *indio_dev; struct mcp2221 *mcp = container_of(work, struct mcp2221, init_work.work); struct mcp2221_iio *data; static int retries = 5; int ret, num_channels; hid_hw_power(mcp->hdev, PM_HINT_FULLON); mutex_lock(&mcp->lock); mcp->txbuf[0] = MCP2221_GET_SRAM_SETTINGS; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); if (ret == -EAGAIN) goto reschedule_task; num_channels = mcp_iio_channels(mcp); if (!num_channels) goto unlock; mcp->txbuf[0] = MCP2221_READ_FLASH_DATA; mcp->txbuf[1] = 0; ret = mcp_send_data_req_status(mcp, mcp->txbuf, 2); if (ret == -EAGAIN) goto reschedule_task; indio_dev = devm_iio_device_alloc(&mcp->hdev->dev, sizeof(*data)); if (!indio_dev) goto unlock; data = iio_priv(indio_dev); data->mcp = mcp; indio_dev->name = "mcp2221"; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &mcp2221_info; indio_dev->channels = mcp->iio_channels; indio_dev->num_channels = num_channels; devm_iio_device_register(&mcp->hdev->dev, indio_dev); unlock: mutex_unlock(&mcp->lock); hid_hw_power(mcp->hdev, PM_HINT_NORMAL); return; reschedule_task: mutex_unlock(&mcp->lock); hid_hw_power(mcp->hdev, PM_HINT_NORMAL); if (!retries--) return; /* Device is not ready to read SRAM or FLASH data, try again */ schedule_delayed_work(&mcp->init_work, msecs_to_jiffies(100)); } #endif static int mcp2221_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; struct mcp2221 *mcp; mcp = devm_kzalloc(&hdev->dev, sizeof(*mcp), GFP_KERNEL); if (!mcp) return -ENOMEM; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "can't parse reports\n"); return ret; } /* * This driver uses the .raw_event callback and therefore does not need any * HID_CONNECT_xxx flags. */ ret = hid_hw_start(hdev, 0); if (ret) { hid_err(hdev, "can't start hardware\n"); return ret; } hid_info(hdev, "USB HID v%x.%02x Device [%s] on %s\n", hdev->version >> 8, hdev->version & 0xff, hdev->name, hdev->phys); ret = hid_hw_open(hdev); if (ret) { hid_err(hdev, "can't open device\n"); hid_hw_stop(hdev); return ret; } mutex_init(&mcp->lock); init_completion(&mcp->wait_in_report); hid_set_drvdata(hdev, mcp); mcp->hdev = hdev; ret = devm_add_action_or_reset(&hdev->dev, mcp2221_hid_unregister, hdev); if (ret) return ret; hid_device_io_start(hdev); /* Set I2C bus clock diviser */ if (i2c_clk_freq > 400) i2c_clk_freq = 400; if (i2c_clk_freq < 50) i2c_clk_freq = 50; mcp->cur_i2c_clk_div = (12000000 / (i2c_clk_freq * 1000)) - 3; ret = mcp_set_i2c_speed(mcp); if (ret) { hid_err(hdev, "can't set i2c speed: %d\n", ret); return ret; } mcp->adapter.owner = THIS_MODULE; mcp->adapter.class = I2C_CLASS_HWMON; mcp->adapter.algo = &mcp_i2c_algo; mcp->adapter.retries = 1; mcp->adapter.dev.parent = &hdev->dev; ACPI_COMPANION_SET(&mcp->adapter.dev, ACPI_COMPANION(hdev->dev.parent)); snprintf(mcp->adapter.name, sizeof(mcp->adapter.name), "MCP2221 usb-i2c bridge"); i2c_set_adapdata(&mcp->adapter, mcp); ret = devm_i2c_add_adapter(&hdev->dev, &mcp->adapter); if (ret) { hid_err(hdev, "can't add usb-i2c adapter: %d\n", ret); return ret; } #if IS_REACHABLE(CONFIG_GPIOLIB) /* Setup GPIO chip */ mcp->gc = devm_kzalloc(&hdev->dev, sizeof(*mcp->gc), GFP_KERNEL); if (!mcp->gc) return -ENOMEM; mcp->gc->label = "mcp2221_gpio"; mcp->gc->direction_input = mcp_gpio_direction_input; mcp->gc->direction_output = mcp_gpio_direction_output; mcp->gc->get_direction = mcp_gpio_get_direction; mcp->gc->set = mcp_gpio_set; mcp->gc->get = mcp_gpio_get; mcp->gc->ngpio = MCP_NGPIO; mcp->gc->base = -1; mcp->gc->can_sleep = 1; mcp->gc->parent = &hdev->dev; ret = devm_gpiochip_add_data(&hdev->dev, mcp->gc, mcp); if (ret) return ret; #endif #if IS_REACHABLE(CONFIG_IIO) INIT_DELAYED_WORK(&mcp->init_work, mcp_init_work); schedule_delayed_work(&mcp->init_work, msecs_to_jiffies(100)); #endif return 0; } static const struct hid_device_id mcp2221_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_MCP2221) }, { } }; MODULE_DEVICE_TABLE(hid, mcp2221_devices); static struct hid_driver mcp2221_driver = { .name = "mcp2221", .id_table = mcp2221_devices, .probe = mcp2221_probe, .remove = mcp2221_remove, .raw_event = mcp2221_raw_event, }; /* Register with HID core */ module_hid_driver(mcp2221_driver); MODULE_AUTHOR("Rishi Gupta <gupt21@gmail.com>"); MODULE_DESCRIPTION("MCP2221 Microchip HID USB to I2C master bridge"); MODULE_LICENSE("GPL v2");
2 1 1 2 9 2 2 1 1 26 26 5 5 5 4 1 3 10 10 5 2 2 1 6 6 1 8 9 1 8 7 7 8 8 8 16 16 18 16 11 9 9 17 18 8 10 17 1 7 7 7 15 15 15 8 15 15 24 22 3 1 13 14 1 14 14 14 14 14 1 10 10 10 1 1 1 1 26 11 15 15 2 11 1 26 1 1 1 38 65 60 1 4 2 2 47 12 1 54 4 2 26 10 19 18 1 1 2 31 30 5 26 26 26 3 23 25 1 1 25 56 46 2 8 5 2 36 15 2 1 11 37 10 2 2 34 6 38 7 41 4 39 5 1 1 38 5 33 1 5 4 35 4 3 36 1 3 2 40 1 7 29 2 4 18 5 6 9 24 36 5 9 24 4 7 4 6 7 4 20 10 10 10 10 4 4 46 92 3 74 64 1 1 91 1 2 92 1424 1424 1 35 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 // SPDX-License-Identifier: GPL-2.0-only /* * GENEVE: Generic Network Virtualization Encapsulation * * Copyright (c) 2015 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/ipv6_stubs.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> #include <net/gro.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" #define GENEVE_N_VID (1u << 24) #define GENEVE_VID_MASK (GENEVE_N_VID - 1) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) #define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) #define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; struct list_head sock_list; }; static unsigned int geneve_net_id; struct geneve_dev_node { struct hlist_node hlist; struct geneve_dev *geneve; }; struct geneve_config { struct ip_tunnel_info info; bool collect_md; bool use_udp6_rx_checksums; bool ttl_inherit; enum ifla_geneve_df df; bool inner_proto_inherit; }; /* Pseudo network device */ struct geneve_dev { struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ #endif struct list_head next; /* geneve's per namespace list */ struct gro_cells gro_cells; struct geneve_config cfg; }; struct geneve_sock { bool collect_md; struct list_head list; struct socket *sock; struct rcu_head rcu; int refcnt; struct hlist_head vni_list[VNI_HASH_SIZE]; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) { __u32 vnid; vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2]; return hash_32(vnid, VNI_HASH_BITS); } static __be64 vni_to_tunnel_id(const __u8 *vni) { #ifdef __BIG_ENDIAN return (vni[0] << 16) | (vni[1] << 8) | vni[2]; #else return (__force __be64)(((__force u64)vni[0] << 40) | ((__force u64)vni[1] << 48) | ((__force u64)vni[2] << 56)); #endif } /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { #ifdef __BIG_ENDIAN vni[0] = (__force __u8)(tun_id >> 16); vni[1] = (__force __u8)(tun_id >> 8); vni[2] = (__force __u8)tun_id; #else vni[0] = (__force __u8)((__force u64)tun_id >> 40); vni[1] = (__force __u8)((__force u64)tun_id >> 48); vni[2] = (__force __u8)((__force u64)tun_id >> 56); #endif } static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { return !memcmp(vni, &tun_id[5], 3); } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) { return gs->sock->sk->sk_family; } static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && addr == node->geneve->cfg.info.key.u.ipv4.dst) return node->geneve; } return NULL; } #if IS_ENABLED(CONFIG_IPV6) static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, struct in6_addr addr6, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst)) return node->geneve; } return NULL; } #endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, struct sk_buff *skb) { static u8 zero_vni[3]; u8 *vni; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph; __be32 addr; iph = ip_hdr(skb); /* outer IP header... */ if (gs->collect_md) { vni = zero_vni; addr = 0; } else { vni = geneve_hdr(skb)->vni; addr = iph->saddr; } return geneve_lookup(gs, addr, vni); #if IS_ENABLED(CONFIG_IPV6) } else if (geneve_get_sk_family(gs) == AF_INET6) { static struct in6_addr zero_addr6; struct ipv6hdr *ip6h; struct in6_addr addr6; ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ if (gs->collect_md) { vni = zero_vni; addr6 = zero_addr6; } else { vni = geneve_hdr(skb)->vni; addr6 = ip6h->saddr; } return geneve6_lookup(gs, addr6, vni); #endif } return NULL; } /* geneve receive/decap routine */ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct sk_buff *skb) { struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_KEY_BIT, flags); __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } /* Update tunnel dst according to Geneve options. */ ip_tunnel_flags_zero(flags); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, flags); } else { /* Drop packets w/ critical options, * since we don't support any... */ if (gnvh->critical) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } if (tun_dst) skb_dst_set(skb, &tun_dst->dst); if (gnvh->proto_type == htons(ETH_P_TEB)) { skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } else { skb_reset_mac_header(skb); skb->dev = geneve->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(geneve->dev, rx_length_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err)) { if (log_ecn_error) { if (geneve_get_sk_family(gs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); #if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); #endif } if (err > 1) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_sw_netstats_rx_add(geneve->dev, len); return; drop: /* Consume bad packet */ kfree_skb(skb); } /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); int err; err = gro_cells_init(&geneve->gro_cells, dev); if (err) return err; err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { gro_cells_destroy(&geneve->gro_cells); return err; } netdev_lockdep_set_classes(dev); return 0; } static void geneve_uninit(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); } /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; geneve = geneve_lookup_skb(gs, skb); if (!geneve) goto drop; inner_proto = geneveh->proto_type; if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } geneve_rx(geneve, gs, skb); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_sock *gs; u8 zero_vni[3] = { 0 }; u8 *vni = zero_vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN)) return -EINVAL; geneveh = geneve_hdr(skb); if (geneveh->ver != GENEVE_VER) return -EINVAL; if (geneveh->proto_type != htons(ETH_P_TEB)) return -EINVAL; gs = rcu_dereference_sk_user_data(sk); if (!gs) return -ENOENT; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph = ip_hdr(skb); __be32 addr4 = 0; if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr4 = iph->daddr; } return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT; } #if IS_ENABLED(CONFIG_IPV6) if (geneve_get_sk_family(gs) == AF_INET6) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct in6_addr addr6; memset(&addr6, 0, sizeof(struct in6_addr)); if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr6 = ip6h->daddr; } return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT; } #endif return -EPFNOSUPPORT; } static struct socket *geneve_create_sock(struct net *net, bool ipv6, __be16 port, bool ipv6_rx_csum) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = ipv6_rx_csum; } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); } udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } static int geneve_hlen(struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; } static struct sk_buff *geneve_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; __be16 type; int flush = 1; off_gnv = skb_gro_offset(skb); hlen = off_gnv + sizeof(*gh); gh = skb_gro_header(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; if (gh->ver != GENEVE_VER || gh->oam) goto out; gh_len = geneve_hlen(gh); hlen = off_gnv + gh_len; if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; } list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; gh2 = (struct genevehdr *)(p->data + off_gnv); if (gh->opt_len != gh2->opt_len || memcmp(gh, gh2, gh_len)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); type = gh->proto_type; if (likely(type == htons(ETH_P_TEB))) return call_gro_receive(eth_gro_receive, head, skb); ptype = gro_find_receive_by_type(type); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct genevehdr *gh; struct packet_offload *ptype; __be16 type; int gh_len; int err = -ENOSYS; gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; /* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */ if (likely(type == htons(ETH_P_TEB))) return eth_gro_complete(skb, nhoff + gh_len); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, bool ipv6, bool ipv6_rx_csum) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; struct socket *sock; struct udp_tunnel_sock_cfg tunnel_cfg; int h; gs = kzalloc(sizeof(*gs), GFP_KERNEL); if (!gs) return ERR_PTR(-ENOMEM); sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); } gs->sock = sock; gs->refcnt = 1; for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&gs->vni_list[h]); /* Initialize the geneve udp offloads structure */ udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; tunnel_cfg.gro_receive = geneve_gro_receive; tunnel_cfg.gro_complete = geneve_gro_complete; tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); list_add(&gs->list, &gn->sock_list); return gs; } static void __geneve_sock_release(struct geneve_sock *gs) { if (!gs || --gs->refcnt) return; list_del(&gs->list); udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); udp_tunnel_sock_release(gs->sock); kfree_rcu(gs, rcu); } static void geneve_sock_release(struct geneve_dev *geneve) { struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); #endif rcu_assign_pointer(geneve->sock4, NULL); synchronize_net(); __geneve_sock_release(gs4); #if IS_ENABLED(CONFIG_IPV6) __geneve_sock_release(gs6); #endif } static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sock->sk)->inet_sport == dst_port && geneve_get_sk_family(gs) == family) { return gs; } } return NULL; } static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev_node *node; struct geneve_sock *gs; __u8 vni[3]; __u32 hash; gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst); if (gs) { gs->refcnt++; goto out; } gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6, geneve->cfg.use_udp6_rx_checksums); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->cfg.collect_md; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(geneve->sock6, gs); node = &geneve->hlist6; } else #endif { rcu_assign_pointer(geneve->sock4, gs); node = &geneve->hlist4; } node->geneve = geneve; tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni); hash = geneve_net_vni_hash(vni); hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]); return 0; } static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); bool metadata = geneve->cfg.collect_md; bool ipv4, ipv6; int ret = 0; ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || metadata; ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { ret = geneve_sock_add(geneve, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); return ret; } static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); hlist_del_init_rcu(&geneve->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&geneve->hlist6.hlist); #endif geneve_sock_release(geneve); return 0; } static void geneve_build_header(struct genevehdr *geneveh, const struct ip_tunnel_info *info, __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; int err; skb_reset_mac_header(skb); skb_scrub_packet(skb, xnet); min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + GENEVE_BASE_HLEN + info->options_len + ip_hdr_len; err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len); inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); geneve_build_header(gnvh, info, inner_proto); skb_set_inner_protocol(skb, inner_proto); return 0; free_dst: dst_release(dst); return err; } static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, const struct ip_tunnel_info *info, bool *use_cache) { struct geneve_dev *geneve = netdev_priv(dev); u8 dsfield; dsfield = info->key.tos; if (dsfield == 1 && !geneve->cfg.collect_md) { dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb); *use_cache = false; } return dsfield; } static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; bool use_cache; __u8 tos, ttl; __be16 df = 0; __be32 saddr; __be16 sport; int err; if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(&rt->dst); return err; } else if (err) { struct ip_tunnel_info *info; info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(&rt->dst); return -ENOMEM; } unclone->key.u.ipv4.dst = saddr; unclone->key.u.ipv4.src = info->key.u.ipv4.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(&rt->dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); if (geneve->cfg.df == GENEVE_DF_SET) { df = htons(IP_DF); } else if (geneve->cfg.df == GENEVE_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6) { df = htons(IP_DF); } else if (ntohs(eth->h_proto) == ETH_P_IP) { struct iphdr *iph = ip_hdr(skb); if (iph->frag_off & htons(IP_DF)) df = htons(IP_DF); } } } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr; bool use_cache; __u8 prio, ttl; __be16 sport; int err; if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(dst); return err; } else if (err) { struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(dst); return -ENOMEM; } unclone->key.u.ipv6.dst = saddr; unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #endif static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (geneve->cfg.collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } } else { info = &geneve->cfg.info; } rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; if (err != -EMSGSIZE) dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int geneve_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; else if (new_mtu < dev->min_mtu) new_mtu = dev->min_mtu; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); bool use_cache; __be32 saddr; u8 tos; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); struct in6_addr saddr; bool use_cache; u8 prio; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver)); } static const struct ethtool_ops geneve_ethtool_ops = { .get_drvinfo = geneve_get_drvinfo, .get_link = ethtool_op_get_link, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type geneve_type = { .name = "geneve", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening GENEVE udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void geneve_offload_rx_ports(struct net_device *dev, bool push) { struct net *net = dev_net(dev); struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; rcu_read_lock(); list_for_each_entry_rcu(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } else { udp_tunnel_drop_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } } rcu_read_unlock(); } /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &geneve_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. This will be further reduced by IPvX hdr size. */ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->lltx = true; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UNSPEC] = { .strict_start_type = IFLA_GENEVE_INNER_PROTO_INHERIT }, [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, [IFLA_GENEVE_DF] = { .type = NLA_U8 }, [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (vni >= GENEVE_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_ID], "Geneve ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_GENEVE_DF]) { enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) { struct geneve_dev *geneve, *t = NULL; *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { if (info->key.tp_dst == geneve->cfg.info.key.tp_dst) { *tun_collect_md = geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && info->key.tp_dst == geneve->cfg.info.key.tp_dst && !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u))) t = geneve; } return t; } static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) == AF_INET) return a->key.u.ipv4.dst == b->key.u.ipv4.dst; else return ipv6_addr_equal(&a->key.u.ipv6.dst, &b->key.u.ipv6.dst); } static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct geneve_config *cfg) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); const struct ip_tunnel_info *info = &cfg->info; bool tun_collect_md, tun_on_same_port; int err, encap_len; if (cfg->collect_md && !is_tnl_info_zero(info)) { NL_SET_ERR_MSG(extack, "Device is externally controlled, so attributes (VNI, Port, and so on) must not be specified"); return -EINVAL; } geneve->net = net; geneve->dev = dev; t = geneve_find_dev(gn, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; /* make enough headroom for basic scenario */ encap_len = GENEVE_BASE_HLEN + ETH_HLEN; if (!cfg->collect_md && ip_tunnel_info_af(info) == AF_INET) { encap_len += sizeof(struct iphdr); dev->max_mtu -= sizeof(struct iphdr); } else { encap_len += sizeof(struct ipv6hdr); dev->max_mtu -= sizeof(struct ipv6hdr); } dev->needed_headroom = encap_len + ETH_HLEN; if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, "There can be only one externally controlled device on a destination port"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, "There already exists an externally controlled device on this destination port"); return -EPERM; } } dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); if (geneve->cfg.inner_proto_inherit) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP; } err = register_netdevice(dev); if (err) return err; list_add(&geneve->next, &gn->geneve_list); return 0; } static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) { memset(info, 0, sizeof(*info)); info->key.tp_dst = htons(dst_port); } static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct geneve_config *cfg, bool changelink) { struct ip_tunnel_info *info = &cfg->info; int attrtype; if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) { NL_SET_ERR_MSG(extack, "Cannot specify both IPv4 and IPv6 Remote addresses"); return -EINVAL; } if (data[IFLA_GENEVE_REMOTE]) { if (changelink && (ip_tunnel_info_af(info) == AF_INET6)) { attrtype = IFLA_GENEVE_REMOTE; goto change_notsup; } info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; } } if (data[IFLA_GENEVE_REMOTE6]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; } info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.dst = nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); if (ipv6_addr_type(&info->key.u.ipv6.dst) & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be link-local"); return -EINVAL; } if (ipv6_addr_is_multicast(&info->key.u.ipv6.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; __be64 tunid; vni = nla_get_u32(data[IFLA_GENEVE_ID]); tvni[0] = (vni & 0x00ff0000) >> 16; tvni[1] = (vni & 0x0000ff00) >> 8; tvni[2] = vni & 0x000000ff; tunid = vni_to_tunnel_id(tvni); if (changelink && (tunid != info->key.tun_id)) { attrtype = IFLA_GENEVE_ID; goto change_notsup; } info->key.tun_id = tunid; } if (data[IFLA_GENEVE_TTL_INHERIT]) { if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) cfg->ttl_inherit = true; else cfg->ttl_inherit = false; } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); cfg->ttl_inherit = false; } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_DF]) cfg->df = nla_get_u8(data[IFLA_GENEVE_DF]); if (data[IFLA_GENEVE_LABEL]) { info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & IPV6_FLOWLABEL_MASK; if (info->key.label && (!(info->mode & IP_TUNNEL_INFO_IPV6))) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LABEL], "Label attribute only applies for IPv6 Geneve devices"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT]) { if (changelink) { attrtype = IFLA_GENEVE_PORT; goto change_notsup; } info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]); } if (data[IFLA_GENEVE_COLLECT_METADATA]) { if (changelink) { attrtype = IFLA_GENEVE_COLLECT_METADATA; goto change_notsup; } cfg->collect_md = true; } if (data[IFLA_GENEVE_UDP_CSUM]) { if (changelink) { attrtype = IFLA_GENEVE_UDP_CSUM; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) cfg->use_udp6_rx_checksums = false; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { if (changelink) { attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; goto change_notsup; } cfg->inner_proto_inherit = true; } return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } static void geneve_link_config(struct net_device *dev, struct ip_tunnel_info *info, struct nlattr *tb[]) { struct geneve_dev *geneve = netdev_priv(dev); int ldev_mtu = 0; if (tb[IFLA_MTU]) { geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return; } switch (ip_tunnel_info_af(info)) { case AF_INET: { struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; struct rtable *rt = ip_route_output_key(geneve->net, &fl4); if (!IS_ERR(rt) && rt->dst.dev) { ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; ip_rt_put(rt); } break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct rt6_info *rt; if (!__in6_dev_get(dev)) break; rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; ip6_rt_put(rt); break; } #endif } if (ldev_mtu <= 0) return; geneve_change_mtu(dev, ldev_mtu - info->options_len); } static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, .ttl_inherit = false, .collect_md = false, }; int err; init_tnl_info(&cfg.info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &cfg, false); if (err) return err; err = geneve_configure(net, dev, extack, &cfg); if (err) return err; geneve_link_config(dev, &cfg.info, tb); return 0; } /* Quiesces the geneve device data path for both TX and RX. * * On transmit geneve checks for non-NULL geneve_sock before it proceeds. * So, if we set that socket to NULL under RCU and wait for synchronize_net() * to complete for the existing set of in-flight packets to be transmitted, * then we would have quiesced the transmit data path. All the future packets * will get dropped until we unquiesce the data path. * * On receive geneve dereference the geneve_sock stashed in the socket. So, * if we set that to NULL under RCU and wait for synchronize_net() to * complete, then we would have quiesced the receive data path. */ static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4, struct geneve_sock **gs6) { *gs4 = rtnl_dereference(geneve->sock4); rcu_assign_pointer(geneve->sock4, NULL); if (*gs4) rcu_assign_sk_user_data((*gs4)->sock->sk, NULL); #if IS_ENABLED(CONFIG_IPV6) *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); if (*gs6) rcu_assign_sk_user_data((*gs6)->sock->sk, NULL); #else *gs6 = NULL; #endif synchronize_net(); } /* Resumes the geneve device data path for both TX and RX. */ static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4, struct geneve_sock __maybe_unused *gs6) { rcu_assign_pointer(geneve->sock4, gs4); if (gs4) rcu_assign_sk_user_data(gs4->sock->sk, gs4); #if IS_ENABLED(CONFIG_IPV6) rcu_assign_pointer(geneve->sock6, gs6); if (gs6) rcu_assign_sk_user_data(gs6->sock->sk, gs6); #endif synchronize_net(); } static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4, *gs6; struct geneve_config cfg; int err; /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ if (geneve->cfg.collect_md) return -EOPNOTSUPP; /* Start with the existing info. */ memcpy(&cfg, &geneve->cfg, sizeof(cfg)); err = geneve_nl2info(tb, data, extack, &cfg, true); if (err) return err; if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) { dst_cache_reset(&cfg.info.dst_cache); geneve_link_config(dev, &cfg.info, tb); } geneve_quiesce(geneve, &gs4, &gs6); memcpy(&geneve->cfg, &cfg, sizeof(cfg)); geneve_unquiesce(geneve, gs4, gs6); return 0; } static void geneve_dellink(struct net_device *dev, struct list_head *head) { struct geneve_dev *geneve = netdev_priv(dev); list_del(&geneve->next); unregister_netdevice_queue(dev, head); } static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ nla_total_size(0) + /* IFLA_GENEVE_INNER_PROTO_INHERIT */ 0; } static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->cfg.info; bool ttl_inherit = geneve->cfg.ttl_inherit; bool metadata = geneve->cfg.collect_md; __u8 tmp_vni[3]; __u32 vni; tunnel_id_to_vni(info->key.tun_id, tmp_vni); vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2]; if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; if (!metadata && ip_tunnel_info_af(info) == AF_INET) { if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else if (!metadata) { if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #endif } if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst)) goto nla_put_failure; if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->cfg.use_udp6_rx_checksums)) goto nla_put_failure; #endif if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; if (geneve->cfg.inner_proto_inherit && nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops geneve_link_ops __read_mostly = { .kind = "geneve", .maxtype = IFLA_GENEVE_MAX, .policy = geneve_policy, .priv_size = sizeof(struct geneve_dev), .setup = geneve_setup, .validate = geneve_validate, .newlink = geneve_newlink, .changelink = geneve_changelink, .dellink = geneve_dellink, .get_size = geneve_get_size, .fill_info = geneve_fill_info, }; struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); int err; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = true, .ttl_inherit = false, .collect_md = true, }; memset(tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; init_tnl_info(&cfg.info, dst_port); err = geneve_configure(net, dev, NULL, &cfg); if (err) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = geneve_change_mtu(dev, IP_MAX_MTU); if (err) goto err; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; return dev; err: geneve_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); static int geneve_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) geneve_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) geneve_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block geneve_notifier_block __read_mostly = { .notifier_call = geneve_netdevice_event, }; static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); INIT_LIST_HEAD(&gn->geneve_list); INIT_LIST_HEAD(&gn->sock_list); return 0; } static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; struct net_device *dev, *aux; /* gather any geneve devices that were moved into this ns */ for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &geneve_link_ops) unregister_netdevice_queue(dev, head); /* now gather any other geneve devices that were created in this ns */ list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { /* If geneve->dev is in the same netns, it was already added * to the list by the previous loop. */ if (!net_eq(dev_net(geneve->dev), net)) unregister_netdevice_queue(geneve->dev, head); } } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; list_for_each_entry(net, net_list, exit_list) geneve_destroy_tunnels(net, dev_to_kill); } static void __net_exit geneve_exit_net(struct net *net) { const struct geneve_net *gn = net_generic(net, geneve_net_id); WARN_ON_ONCE(!list_empty(&gn->sock_list)); } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, .exit_batch_rtnl = geneve_exit_batch_rtnl, .exit = geneve_exit_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; static int __init geneve_init_module(void) { int rc; rc = register_pernet_subsys(&geneve_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; rc = rtnl_link_register(&geneve_link_ops); if (rc) goto out3; return 0; out3: unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: return rc; } late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(GENEVE_NETDEV_VER); MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>"); MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("geneve");
3 3 3 5 2 3 3 2 9 8 1 4 5 3 3 3 3 3 2 2 2 2 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 // SPDX-License-Identifier: GPL-2.0 /* * cdc-wdm.c * * This driver supports USB CDC WCM Device Management. * * Copyright (c) 2007-2009 Oliver Neukum * * Some code taken from cdc-acm.c * * Released under the GPLv2. * * Many thanks to Carl Nordbeck */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/ioctl.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/poll.h> #include <linux/skbuff.h> #include <linux/usb.h> #include <linux/usb/cdc.h> #include <linux/wwan.h> #include <asm/byteorder.h> #include <linux/unaligned.h> #include <linux/usb/cdc-wdm.h> #define DRIVER_AUTHOR "Oliver Neukum" #define DRIVER_DESC "USB Abstract Control Model driver for USB WCM Device Management" static const struct usb_device_id wdm_ids[] = { { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS | USB_DEVICE_ID_MATCH_INT_SUBCLASS, .bInterfaceClass = USB_CLASS_COMM, .bInterfaceSubClass = USB_CDC_SUBCLASS_DMM }, { } }; MODULE_DEVICE_TABLE (usb, wdm_ids); #define WDM_MINOR_BASE 176 #define WDM_IN_USE 1 #define WDM_DISCONNECTING 2 #define WDM_RESULT 3 #define WDM_READ 4 #define WDM_INT_STALL 5 #define WDM_POLL_RUNNING 6 #define WDM_RESPONDING 7 #define WDM_SUSPENDING 8 #define WDM_RESETTING 9 #define WDM_OVERFLOW 10 #define WDM_WWAN_IN_USE 11 #define WDM_MAX 16 /* we cannot wait forever at flush() */ #define WDM_FLUSH_TIMEOUT (30 * HZ) /* CDC-WMC r1.1 requires wMaxCommand to be "at least 256 decimal (0x100)" */ #define WDM_DEFAULT_BUFSIZE 256 static DEFINE_MUTEX(wdm_mutex); static DEFINE_SPINLOCK(wdm_device_list_lock); static LIST_HEAD(wdm_device_list); /* --- method tables --- */ struct wdm_device { u8 *inbuf; /* buffer for response */ u8 *outbuf; /* buffer for command */ u8 *sbuf; /* buffer for status */ u8 *ubuf; /* buffer for copy to user space */ struct urb *command; struct urb *response; struct urb *validity; struct usb_interface *intf; struct usb_ctrlrequest *orq; struct usb_ctrlrequest *irq; spinlock_t iuspin; unsigned long flags; u16 bufsize; u16 wMaxCommand; u16 wMaxPacketSize; __le16 inum; int reslength; int length; int read; int count; dma_addr_t shandle; dma_addr_t ihandle; struct mutex wlock; struct mutex rlock; wait_queue_head_t wait; struct work_struct rxwork; struct work_struct service_outs_intr; int werr; int rerr; int resp_count; struct list_head device_list; int (*manage_power)(struct usb_interface *, int); enum wwan_port_type wwanp_type; struct wwan_port *wwanp; }; static struct usb_driver wdm_driver; /* return intfdata if we own the interface, else look up intf in the list */ static struct wdm_device *wdm_find_device(struct usb_interface *intf) { struct wdm_device *desc; spin_lock(&wdm_device_list_lock); list_for_each_entry(desc, &wdm_device_list, device_list) if (desc->intf == intf) goto found; desc = NULL; found: spin_unlock(&wdm_device_list_lock); return desc; } static struct wdm_device *wdm_find_device_by_minor(int minor) { struct wdm_device *desc; spin_lock(&wdm_device_list_lock); list_for_each_entry(desc, &wdm_device_list, device_list) if (desc->intf->minor == minor) goto found; desc = NULL; found: spin_unlock(&wdm_device_list_lock); return desc; } /* --- callbacks --- */ static void wdm_out_callback(struct urb *urb) { struct wdm_device *desc; unsigned long flags; desc = urb->context; spin_lock_irqsave(&desc->iuspin, flags); desc->werr = urb->status; spin_unlock_irqrestore(&desc->iuspin, flags); kfree(desc->outbuf); desc->outbuf = NULL; clear_bit(WDM_IN_USE, &desc->flags); wake_up_all(&desc->wait); } static void wdm_wwan_rx(struct wdm_device *desc, int length); static void wdm_in_callback(struct urb *urb) { unsigned long flags; struct wdm_device *desc = urb->context; int status = urb->status; int length = urb->actual_length; spin_lock_irqsave(&desc->iuspin, flags); clear_bit(WDM_RESPONDING, &desc->flags); if (status) { switch (status) { case -ENOENT: dev_dbg(&desc->intf->dev, "nonzero urb status received: -ENOENT\n"); goto skip_error; case -ECONNRESET: dev_dbg(&desc->intf->dev, "nonzero urb status received: -ECONNRESET\n"); goto skip_error; case -ESHUTDOWN: dev_dbg(&desc->intf->dev, "nonzero urb status received: -ESHUTDOWN\n"); goto skip_error; case -EPIPE: dev_err(&desc->intf->dev, "nonzero urb status received: -EPIPE\n"); break; default: dev_err(&desc->intf->dev, "Unexpected error %d\n", status); break; } } if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { wdm_wwan_rx(desc, length); goto out; } /* * only set a new error if there is no previous error. * Errors are only cleared during read/open * Avoid propagating -EPIPE (stall) to userspace since it is * better handled as an empty read */ if (desc->rerr == 0 && status != -EPIPE) desc->rerr = status; if (length + desc->length > desc->wMaxCommand) { /* The buffer would overflow */ set_bit(WDM_OVERFLOW, &desc->flags); } else { /* we may already be in overflow */ if (!test_bit(WDM_OVERFLOW, &desc->flags)) { memmove(desc->ubuf + desc->length, desc->inbuf, length); desc->length += length; desc->reslength = length; } } skip_error: if (desc->rerr) { /* * Since there was an error, userspace may decide to not read * any data after poll'ing. * We should respond to further attempts from the device to send * data, so that we can get unstuck. */ schedule_work(&desc->service_outs_intr); } else { set_bit(WDM_READ, &desc->flags); wake_up(&desc->wait); } out: spin_unlock_irqrestore(&desc->iuspin, flags); } static void wdm_int_callback(struct urb *urb) { unsigned long flags; int rv = 0; int responding; int status = urb->status; struct wdm_device *desc; struct usb_cdc_notification *dr; desc = urb->context; dr = (struct usb_cdc_notification *)desc->sbuf; if (status) { switch (status) { case -ESHUTDOWN: case -ENOENT: case -ECONNRESET: return; /* unplug */ case -EPIPE: set_bit(WDM_INT_STALL, &desc->flags); dev_err(&desc->intf->dev, "Stall on int endpoint\n"); goto sw; /* halt is cleared in work */ default: dev_err_ratelimited(&desc->intf->dev, "nonzero urb status received: %d\n", status); break; } } if (urb->actual_length < sizeof(struct usb_cdc_notification)) { dev_err_ratelimited(&desc->intf->dev, "wdm_int_callback - %d bytes\n", urb->actual_length); goto exit; } switch (dr->bNotificationType) { case USB_CDC_NOTIFY_RESPONSE_AVAILABLE: dev_dbg(&desc->intf->dev, "NOTIFY_RESPONSE_AVAILABLE received: index %d len %d\n", le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength)); break; case USB_CDC_NOTIFY_NETWORK_CONNECTION: dev_dbg(&desc->intf->dev, "NOTIFY_NETWORK_CONNECTION %s network\n", dr->wValue ? "connected to" : "disconnected from"); goto exit; case USB_CDC_NOTIFY_SPEED_CHANGE: dev_dbg(&desc->intf->dev, "SPEED_CHANGE received (len %u)\n", urb->actual_length); goto exit; default: clear_bit(WDM_POLL_RUNNING, &desc->flags); dev_err(&desc->intf->dev, "unknown notification %d received: index %d len %d\n", dr->bNotificationType, le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength)); goto exit; } spin_lock_irqsave(&desc->iuspin, flags); responding = test_and_set_bit(WDM_RESPONDING, &desc->flags); if (!desc->resp_count++ && !responding && !test_bit(WDM_DISCONNECTING, &desc->flags) && !test_bit(WDM_SUSPENDING, &desc->flags)) { rv = usb_submit_urb(desc->response, GFP_ATOMIC); dev_dbg(&desc->intf->dev, "submit response URB %d\n", rv); } spin_unlock_irqrestore(&desc->iuspin, flags); if (rv < 0) { clear_bit(WDM_RESPONDING, &desc->flags); if (rv == -EPERM) return; if (rv == -ENOMEM) { sw: rv = schedule_work(&desc->rxwork); if (rv) dev_err(&desc->intf->dev, "Cannot schedule work\n"); } } exit: rv = usb_submit_urb(urb, GFP_ATOMIC); if (rv) dev_err(&desc->intf->dev, "%s - usb_submit_urb failed with result %d\n", __func__, rv); } static void poison_urbs(struct wdm_device *desc) { /* the order here is essential */ usb_poison_urb(desc->command); usb_poison_urb(desc->validity); usb_poison_urb(desc->response); } static void unpoison_urbs(struct wdm_device *desc) { /* * the order here is not essential * it is symmetrical just to be nice */ usb_unpoison_urb(desc->response); usb_unpoison_urb(desc->validity); usb_unpoison_urb(desc->command); } static void free_urbs(struct wdm_device *desc) { usb_free_urb(desc->validity); usb_free_urb(desc->response); usb_free_urb(desc->command); } static void cleanup(struct wdm_device *desc) { kfree(desc->sbuf); kfree(desc->inbuf); kfree(desc->orq); kfree(desc->irq); kfree(desc->ubuf); free_urbs(desc); kfree(desc); } static ssize_t wdm_write (struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { u8 *buf; int rv = -EMSGSIZE, r, we; struct wdm_device *desc = file->private_data; struct usb_ctrlrequest *req; if (count > desc->wMaxCommand) count = desc->wMaxCommand; spin_lock_irq(&desc->iuspin); we = desc->werr; desc->werr = 0; spin_unlock_irq(&desc->iuspin); if (we < 0) return usb_translate_errors(we); buf = memdup_user(buffer, count); if (IS_ERR(buf)) return PTR_ERR(buf); /* concurrent writes and disconnect */ r = mutex_lock_interruptible(&desc->wlock); rv = -ERESTARTSYS; if (r) goto out_free_mem; if (test_bit(WDM_DISCONNECTING, &desc->flags)) { rv = -ENODEV; goto out_free_mem_lock; } r = usb_autopm_get_interface(desc->intf); if (r < 0) { rv = usb_translate_errors(r); goto out_free_mem_lock; } if (!(file->f_flags & O_NONBLOCK)) r = wait_event_interruptible(desc->wait, !test_bit(WDM_IN_USE, &desc->flags)); else if (test_bit(WDM_IN_USE, &desc->flags)) r = -EAGAIN; if (test_bit(WDM_RESETTING, &desc->flags)) r = -EIO; if (test_bit(WDM_DISCONNECTING, &desc->flags)) r = -ENODEV; if (r < 0) { rv = r; goto out_free_mem_pm; } req = desc->orq; usb_fill_control_urb( desc->command, interface_to_usbdev(desc->intf), /* using common endpoint 0 */ usb_sndctrlpipe(interface_to_usbdev(desc->intf), 0), (unsigned char *)req, buf, count, wdm_out_callback, desc ); req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE); req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; req->wValue = 0; req->wIndex = desc->inum; /* already converted */ req->wLength = cpu_to_le16(count); set_bit(WDM_IN_USE, &desc->flags); desc->outbuf = buf; rv = usb_submit_urb(desc->command, GFP_KERNEL); if (rv < 0) { desc->outbuf = NULL; clear_bit(WDM_IN_USE, &desc->flags); wake_up_all(&desc->wait); /* for wdm_wait_for_response() */ dev_err(&desc->intf->dev, "Tx URB error: %d\n", rv); rv = usb_translate_errors(rv); goto out_free_mem_pm; } else { dev_dbg(&desc->intf->dev, "Tx URB has been submitted index=%d\n", le16_to_cpu(req->wIndex)); } usb_autopm_put_interface(desc->intf); mutex_unlock(&desc->wlock); return count; out_free_mem_pm: usb_autopm_put_interface(desc->intf); out_free_mem_lock: mutex_unlock(&desc->wlock); out_free_mem: kfree(buf); return rv; } /* * Submit the read urb if resp_count is non-zero. * * Called with desc->iuspin locked */ static int service_outstanding_interrupt(struct wdm_device *desc) { int rv = 0; /* submit read urb only if the device is waiting for it */ if (!desc->resp_count || !--desc->resp_count) goto out; if (test_bit(WDM_DISCONNECTING, &desc->flags)) { rv = -ENODEV; goto out; } if (test_bit(WDM_RESETTING, &desc->flags)) { rv = -EIO; goto out; } set_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); rv = usb_submit_urb(desc->response, GFP_KERNEL); spin_lock_irq(&desc->iuspin); if (rv) { if (!test_bit(WDM_DISCONNECTING, &desc->flags)) dev_err(&desc->intf->dev, "usb_submit_urb failed with result %d\n", rv); /* make sure the next notification trigger a submit */ clear_bit(WDM_RESPONDING, &desc->flags); desc->resp_count = 0; } out: return rv; } static ssize_t wdm_read (struct file *file, char __user *buffer, size_t count, loff_t *ppos) { int rv, cntr; int i = 0; struct wdm_device *desc = file->private_data; rv = mutex_lock_interruptible(&desc->rlock); /*concurrent reads */ if (rv < 0) return -ERESTARTSYS; cntr = READ_ONCE(desc->length); if (cntr == 0) { desc->read = 0; retry: if (test_bit(WDM_DISCONNECTING, &desc->flags)) { rv = -ENODEV; goto err; } if (test_bit(WDM_OVERFLOW, &desc->flags)) { clear_bit(WDM_OVERFLOW, &desc->flags); rv = -ENOBUFS; goto err; } i++; if (file->f_flags & O_NONBLOCK) { if (!test_bit(WDM_READ, &desc->flags)) { rv = -EAGAIN; goto err; } rv = 0; } else { rv = wait_event_interruptible(desc->wait, test_bit(WDM_READ, &desc->flags)); } /* may have happened while we slept */ if (test_bit(WDM_DISCONNECTING, &desc->flags)) { rv = -ENODEV; goto err; } if (test_bit(WDM_RESETTING, &desc->flags)) { rv = -EIO; goto err; } usb_mark_last_busy(interface_to_usbdev(desc->intf)); if (rv < 0) { rv = -ERESTARTSYS; goto err; } spin_lock_irq(&desc->iuspin); if (desc->rerr) { /* read completed, error happened */ rv = usb_translate_errors(desc->rerr); desc->rerr = 0; spin_unlock_irq(&desc->iuspin); goto err; } /* * recheck whether we've lost the race * against the completion handler */ if (!test_bit(WDM_READ, &desc->flags)) { /* lost race */ spin_unlock_irq(&desc->iuspin); goto retry; } if (!desc->reslength) { /* zero length read */ dev_dbg(&desc->intf->dev, "zero length - clearing WDM_READ\n"); clear_bit(WDM_READ, &desc->flags); rv = service_outstanding_interrupt(desc); spin_unlock_irq(&desc->iuspin); if (rv < 0) goto err; goto retry; } cntr = desc->length; spin_unlock_irq(&desc->iuspin); } if (cntr > count) cntr = count; rv = copy_to_user(buffer, desc->ubuf, cntr); if (rv > 0) { rv = -EFAULT; goto err; } spin_lock_irq(&desc->iuspin); for (i = 0; i < desc->length - cntr; i++) desc->ubuf[i] = desc->ubuf[i + cntr]; desc->length -= cntr; /* in case we had outstanding data */ if (!desc->length) { clear_bit(WDM_READ, &desc->flags); service_outstanding_interrupt(desc); } spin_unlock_irq(&desc->iuspin); rv = cntr; err: mutex_unlock(&desc->rlock); return rv; } static int wdm_wait_for_response(struct file *file, long timeout) { struct wdm_device *desc = file->private_data; long rv; /* Use long here because (int) MAX_SCHEDULE_TIMEOUT < 0. */ /* * Needs both flags. We cannot do with one because resetting it would * cause a race with write() yet we need to signal a disconnect. */ rv = wait_event_interruptible_timeout(desc->wait, !test_bit(WDM_IN_USE, &desc->flags) || test_bit(WDM_DISCONNECTING, &desc->flags), timeout); /* * To report the correct error. This is best effort. * We are inevitably racing with the hardware. */ if (test_bit(WDM_DISCONNECTING, &desc->flags)) return -ENODEV; if (!rv) return -EIO; if (rv < 0) return -EINTR; spin_lock_irq(&desc->iuspin); rv = desc->werr; desc->werr = 0; spin_unlock_irq(&desc->iuspin); return usb_translate_errors(rv); } /* * You need to send a signal when you react to malicious or defective hardware. * Also, don't abort when fsync() returned -EINVAL, for older kernels which do * not implement wdm_flush() will return -EINVAL. */ static int wdm_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return wdm_wait_for_response(file, MAX_SCHEDULE_TIMEOUT); } /* * Same with wdm_fsync(), except it uses finite timeout in order to react to * malicious or defective hardware which ceased communication after close() was * implicitly called due to process termination. */ static int wdm_flush(struct file *file, fl_owner_t id) { return wdm_wait_for_response(file, WDM_FLUSH_TIMEOUT); } static __poll_t wdm_poll(struct file *file, struct poll_table_struct *wait) { struct wdm_device *desc = file->private_data; unsigned long flags; __poll_t mask = 0; spin_lock_irqsave(&desc->iuspin, flags); if (test_bit(WDM_DISCONNECTING, &desc->flags)) { mask = EPOLLHUP | EPOLLERR; spin_unlock_irqrestore(&desc->iuspin, flags); goto desc_out; } if (test_bit(WDM_READ, &desc->flags)) mask = EPOLLIN | EPOLLRDNORM; if (desc->rerr || desc->werr) mask |= EPOLLERR; if (!test_bit(WDM_IN_USE, &desc->flags)) mask |= EPOLLOUT | EPOLLWRNORM; spin_unlock_irqrestore(&desc->iuspin, flags); poll_wait(file, &desc->wait, wait); desc_out: return mask; } static int wdm_open(struct inode *inode, struct file *file) { int minor = iminor(inode); int rv = -ENODEV; struct usb_interface *intf; struct wdm_device *desc; mutex_lock(&wdm_mutex); desc = wdm_find_device_by_minor(minor); if (!desc) goto out; intf = desc->intf; if (test_bit(WDM_DISCONNECTING, &desc->flags)) goto out; file->private_data = desc; if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { rv = -EBUSY; goto out; } rv = usb_autopm_get_interface(desc->intf); if (rv < 0) { dev_err(&desc->intf->dev, "Error autopm - %d\n", rv); goto out; } /* using write lock to protect desc->count */ mutex_lock(&desc->wlock); if (!desc->count++) { desc->werr = 0; desc->rerr = 0; rv = usb_submit_urb(desc->validity, GFP_KERNEL); if (rv < 0) { desc->count--; dev_err(&desc->intf->dev, "Error submitting int urb - %d\n", rv); rv = usb_translate_errors(rv); } } else { rv = 0; } mutex_unlock(&desc->wlock); if (desc->count == 1) desc->manage_power(intf, 1); usb_autopm_put_interface(desc->intf); out: mutex_unlock(&wdm_mutex); return rv; } static int wdm_release(struct inode *inode, struct file *file) { struct wdm_device *desc = file->private_data; mutex_lock(&wdm_mutex); /* using write lock to protect desc->count */ mutex_lock(&desc->wlock); desc->count--; mutex_unlock(&desc->wlock); if (!desc->count) { if (!test_bit(WDM_DISCONNECTING, &desc->flags)) { dev_dbg(&desc->intf->dev, "wdm_release: cleanup\n"); poison_urbs(desc); spin_lock_irq(&desc->iuspin); desc->resp_count = 0; clear_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); desc->manage_power(desc->intf, 0); unpoison_urbs(desc); } else { /* must avoid dev_printk here as desc->intf is invalid */ pr_debug(KBUILD_MODNAME " %s: device gone - cleaning up\n", __func__); cleanup(desc); } } mutex_unlock(&wdm_mutex); return 0; } static long wdm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct wdm_device *desc = file->private_data; int rv = 0; switch (cmd) { case IOCTL_WDM_MAX_COMMAND: if (copy_to_user((void __user *)arg, &desc->wMaxCommand, sizeof(desc->wMaxCommand))) rv = -EFAULT; break; default: rv = -ENOTTY; } return rv; } static const struct file_operations wdm_fops = { .owner = THIS_MODULE, .read = wdm_read, .write = wdm_write, .fsync = wdm_fsync, .open = wdm_open, .flush = wdm_flush, .release = wdm_release, .poll = wdm_poll, .unlocked_ioctl = wdm_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static struct usb_class_driver wdm_class = { .name = "cdc-wdm%d", .fops = &wdm_fops, .minor_base = WDM_MINOR_BASE, }; /* --- WWAN framework integration --- */ #ifdef CONFIG_WWAN static int wdm_wwan_port_start(struct wwan_port *port) { struct wdm_device *desc = wwan_port_get_drvdata(port); /* The interface is both exposed via the WWAN framework and as a * legacy usbmisc chardev. If chardev is already open, just fail * to prevent concurrent usage. Otherwise, switch to WWAN mode. */ mutex_lock(&wdm_mutex); if (desc->count) { mutex_unlock(&wdm_mutex); return -EBUSY; } set_bit(WDM_WWAN_IN_USE, &desc->flags); mutex_unlock(&wdm_mutex); desc->manage_power(desc->intf, 1); /* tx is allowed */ wwan_port_txon(port); /* Start getting events */ return usb_submit_urb(desc->validity, GFP_KERNEL); } static void wdm_wwan_port_stop(struct wwan_port *port) { struct wdm_device *desc = wwan_port_get_drvdata(port); /* Stop all transfers and disable WWAN mode */ poison_urbs(desc); desc->manage_power(desc->intf, 0); clear_bit(WDM_READ, &desc->flags); clear_bit(WDM_WWAN_IN_USE, &desc->flags); unpoison_urbs(desc); } static void wdm_wwan_port_tx_complete(struct urb *urb) { struct sk_buff *skb = urb->context; struct wdm_device *desc = skb_shinfo(skb)->destructor_arg; usb_autopm_put_interface(desc->intf); wwan_port_txon(desc->wwanp); kfree_skb(skb); } static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb) { struct wdm_device *desc = wwan_port_get_drvdata(port); struct usb_interface *intf = desc->intf; struct usb_ctrlrequest *req = desc->orq; int rv; rv = usb_autopm_get_interface(intf); if (rv) return rv; usb_fill_control_urb( desc->command, interface_to_usbdev(intf), usb_sndctrlpipe(interface_to_usbdev(intf), 0), (unsigned char *)req, skb->data, skb->len, wdm_wwan_port_tx_complete, skb ); req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE); req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; req->wValue = 0; req->wIndex = desc->inum; req->wLength = cpu_to_le16(skb->len); skb_shinfo(skb)->destructor_arg = desc; rv = usb_submit_urb(desc->command, GFP_KERNEL); if (rv) usb_autopm_put_interface(intf); else /* One transfer at a time, stop TX until URB completion */ wwan_port_txoff(port); return rv; } static const struct wwan_port_ops wdm_wwan_port_ops = { .start = wdm_wwan_port_start, .stop = wdm_wwan_port_stop, .tx = wdm_wwan_port_tx, }; static void wdm_wwan_init(struct wdm_device *desc) { struct usb_interface *intf = desc->intf; struct wwan_port *port; /* Only register to WWAN core if protocol/type is known */ if (desc->wwanp_type == WWAN_PORT_UNKNOWN) { dev_info(&intf->dev, "Unknown control protocol\n"); return; } port = wwan_create_port(&intf->dev, desc->wwanp_type, &wdm_wwan_port_ops, NULL, desc); if (IS_ERR(port)) { dev_err(&intf->dev, "%s: Unable to create WWAN port\n", dev_name(intf->usb_dev)); return; } desc->wwanp = port; } static void wdm_wwan_deinit(struct wdm_device *desc) { if (!desc->wwanp) return; wwan_remove_port(desc->wwanp); desc->wwanp = NULL; } static void wdm_wwan_rx(struct wdm_device *desc, int length) { struct wwan_port *port = desc->wwanp; struct sk_buff *skb; /* Forward data to WWAN port */ skb = alloc_skb(length, GFP_ATOMIC); if (!skb) return; skb_put_data(skb, desc->inbuf, length); wwan_port_rx(port, skb); /* inbuf has been copied, it is safe to check for outstanding data */ schedule_work(&desc->service_outs_intr); } #else /* CONFIG_WWAN */ static void wdm_wwan_init(struct wdm_device *desc) {} static void wdm_wwan_deinit(struct wdm_device *desc) {} static void wdm_wwan_rx(struct wdm_device *desc, int length) {} #endif /* CONFIG_WWAN */ /* --- error handling --- */ static void wdm_rxwork(struct work_struct *work) { struct wdm_device *desc = container_of(work, struct wdm_device, rxwork); unsigned long flags; int rv = 0; int responding; spin_lock_irqsave(&desc->iuspin, flags); if (test_bit(WDM_DISCONNECTING, &desc->flags)) { spin_unlock_irqrestore(&desc->iuspin, flags); } else { responding = test_and_set_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irqrestore(&desc->iuspin, flags); if (!responding) rv = usb_submit_urb(desc->response, GFP_KERNEL); if (rv < 0 && rv != -EPERM) { spin_lock_irqsave(&desc->iuspin, flags); clear_bit(WDM_RESPONDING, &desc->flags); if (!test_bit(WDM_DISCONNECTING, &desc->flags)) schedule_work(&desc->rxwork); spin_unlock_irqrestore(&desc->iuspin, flags); } } } static void service_interrupt_work(struct work_struct *work) { struct wdm_device *desc; desc = container_of(work, struct wdm_device, service_outs_intr); spin_lock_irq(&desc->iuspin); service_outstanding_interrupt(desc); if (!desc->resp_count) { set_bit(WDM_READ, &desc->flags); wake_up(&desc->wait); } spin_unlock_irq(&desc->iuspin); } /* --- hotplug --- */ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, u16 bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)) { int rv = -ENOMEM; struct wdm_device *desc; desc = kzalloc(sizeof(struct wdm_device), GFP_KERNEL); if (!desc) goto out; INIT_LIST_HEAD(&desc->device_list); mutex_init(&desc->rlock); mutex_init(&desc->wlock); spin_lock_init(&desc->iuspin); init_waitqueue_head(&desc->wait); desc->wMaxCommand = bufsize; /* this will be expanded and needed in hardware endianness */ desc->inum = cpu_to_le16((u16)intf->cur_altsetting->desc.bInterfaceNumber); desc->intf = intf; desc->wwanp_type = type; INIT_WORK(&desc->rxwork, wdm_rxwork); INIT_WORK(&desc->service_outs_intr, service_interrupt_work); if (!usb_endpoint_is_int_in(ep)) { rv = -EINVAL; goto err; } desc->wMaxPacketSize = usb_endpoint_maxp(ep); desc->orq = kmalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL); if (!desc->orq) goto err; desc->irq = kmalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL); if (!desc->irq) goto err; desc->validity = usb_alloc_urb(0, GFP_KERNEL); if (!desc->validity) goto err; desc->response = usb_alloc_urb(0, GFP_KERNEL); if (!desc->response) goto err; desc->command = usb_alloc_urb(0, GFP_KERNEL); if (!desc->command) goto err; desc->ubuf = kmalloc(desc->wMaxCommand, GFP_KERNEL); if (!desc->ubuf) goto err; desc->sbuf = kmalloc(desc->wMaxPacketSize, GFP_KERNEL); if (!desc->sbuf) goto err; desc->inbuf = kmalloc(desc->wMaxCommand, GFP_KERNEL); if (!desc->inbuf) goto err; usb_fill_int_urb( desc->validity, interface_to_usbdev(intf), usb_rcvintpipe(interface_to_usbdev(intf), ep->bEndpointAddress), desc->sbuf, desc->wMaxPacketSize, wdm_int_callback, desc, ep->bInterval ); desc->irq->bRequestType = (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE); desc->irq->bRequest = USB_CDC_GET_ENCAPSULATED_RESPONSE; desc->irq->wValue = 0; desc->irq->wIndex = desc->inum; /* already converted */ desc->irq->wLength = cpu_to_le16(desc->wMaxCommand); usb_fill_control_urb( desc->response, interface_to_usbdev(intf), /* using common endpoint 0 */ usb_rcvctrlpipe(interface_to_usbdev(desc->intf), 0), (unsigned char *)desc->irq, desc->inbuf, desc->wMaxCommand, wdm_in_callback, desc ); desc->manage_power = manage_power; spin_lock(&wdm_device_list_lock); list_add(&desc->device_list, &wdm_device_list); spin_unlock(&wdm_device_list_lock); rv = usb_register_dev(intf, &wdm_class); if (rv < 0) goto err; else dev_info(&intf->dev, "%s: USB WDM device\n", dev_name(intf->usb_dev)); wdm_wwan_init(desc); out: return rv; err: spin_lock(&wdm_device_list_lock); list_del(&desc->device_list); spin_unlock(&wdm_device_list_lock); cleanup(desc); return rv; } static int wdm_manage_power(struct usb_interface *intf, int on) { /* need autopm_get/put here to ensure the usbcore sees the new value */ int rv = usb_autopm_get_interface(intf); intf->needs_remote_wakeup = on; if (!rv) usb_autopm_put_interface(intf); return 0; } static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id) { int rv = -EINVAL; struct usb_host_interface *iface; struct usb_endpoint_descriptor *ep; struct usb_cdc_parsed_header hdr; u8 *buffer = intf->altsetting->extra; int buflen = intf->altsetting->extralen; u16 maxcom = WDM_DEFAULT_BUFSIZE; if (!buffer) goto err; cdc_parse_cdc_header(&hdr, intf, buffer, buflen); if (hdr.usb_cdc_dmm_desc) maxcom = le16_to_cpu(hdr.usb_cdc_dmm_desc->wMaxCommand); iface = intf->cur_altsetting; if (iface->desc.bNumEndpoints != 1) goto err; ep = &iface->endpoint[0].desc; rv = wdm_create(intf, ep, maxcom, WWAN_PORT_UNKNOWN, &wdm_manage_power); err: return rv; } /** * usb_cdc_wdm_register - register a WDM subdriver * @intf: usb interface the subdriver will associate with * @ep: interrupt endpoint to monitor for notifications * @bufsize: maximum message size to support for read/write * @type: Type/protocol of the transported data (MBIM, QMI...) * @manage_power: call-back invoked during open and release to * manage the device's power * Create WDM usb class character device and associate it with intf * without binding, allowing another driver to manage the interface. * * The subdriver will manage the given interrupt endpoint exclusively * and will issue control requests referring to the given intf. It * will otherwise avoid interferring, and in particular not do * usb_set_intfdata/usb_get_intfdata on intf. * * The return value is a pointer to the subdriver's struct usb_driver. * The registering driver is responsible for calling this subdriver's * disconnect, suspend, resume, pre_reset and post_reset methods from * its own. */ struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)) { int rv; rv = wdm_create(intf, ep, bufsize, type, manage_power); if (rv < 0) goto err; return &wdm_driver; err: return ERR_PTR(rv); } EXPORT_SYMBOL(usb_cdc_wdm_register); static void wdm_disconnect(struct usb_interface *intf) { struct wdm_device *desc; unsigned long flags; usb_deregister_dev(intf, &wdm_class); desc = wdm_find_device(intf); mutex_lock(&wdm_mutex); wdm_wwan_deinit(desc); /* the spinlock makes sure no new urbs are generated in the callbacks */ spin_lock_irqsave(&desc->iuspin, flags); set_bit(WDM_DISCONNECTING, &desc->flags); set_bit(WDM_READ, &desc->flags); spin_unlock_irqrestore(&desc->iuspin, flags); wake_up_all(&desc->wait); mutex_lock(&desc->rlock); mutex_lock(&desc->wlock); poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); mutex_unlock(&desc->wlock); mutex_unlock(&desc->rlock); /* the desc->intf pointer used as list key is now invalid */ spin_lock(&wdm_device_list_lock); list_del(&desc->device_list); spin_unlock(&wdm_device_list_lock); if (!desc->count) cleanup(desc); else dev_dbg(&intf->dev, "%d open files - postponing cleanup\n", desc->count); mutex_unlock(&wdm_mutex); } #ifdef CONFIG_PM static int wdm_suspend(struct usb_interface *intf, pm_message_t message) { struct wdm_device *desc = wdm_find_device(intf); int rv = 0; dev_dbg(&desc->intf->dev, "wdm%d_suspend\n", intf->minor); /* if this is an autosuspend the caller does the locking */ if (!PMSG_IS_AUTO(message)) { mutex_lock(&desc->rlock); mutex_lock(&desc->wlock); } spin_lock_irq(&desc->iuspin); if (PMSG_IS_AUTO(message) && (test_bit(WDM_IN_USE, &desc->flags) || test_bit(WDM_RESPONDING, &desc->flags))) { spin_unlock_irq(&desc->iuspin); rv = -EBUSY; } else { set_bit(WDM_SUSPENDING, &desc->flags); spin_unlock_irq(&desc->iuspin); /* callback submits work - order is essential */ poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); unpoison_urbs(desc); } if (!PMSG_IS_AUTO(message)) { mutex_unlock(&desc->wlock); mutex_unlock(&desc->rlock); } return rv; } #endif static int recover_from_urb_loss(struct wdm_device *desc) { int rv = 0; if (desc->count) { rv = usb_submit_urb(desc->validity, GFP_NOIO); if (rv < 0) dev_err(&desc->intf->dev, "Error resume submitting int urb - %d\n", rv); } return rv; } #ifdef CONFIG_PM static int wdm_resume(struct usb_interface *intf) { struct wdm_device *desc = wdm_find_device(intf); int rv; dev_dbg(&desc->intf->dev, "wdm%d_resume\n", intf->minor); clear_bit(WDM_SUSPENDING, &desc->flags); rv = recover_from_urb_loss(desc); return rv; } #endif static int wdm_pre_reset(struct usb_interface *intf) { struct wdm_device *desc = wdm_find_device(intf); /* * we notify everybody using poll of * an exceptional situation * must be done before recovery lest a spontaneous * message from the device is lost */ spin_lock_irq(&desc->iuspin); set_bit(WDM_RESETTING, &desc->flags); /* inform read/write */ set_bit(WDM_READ, &desc->flags); /* unblock read */ clear_bit(WDM_IN_USE, &desc->flags); /* unblock write */ desc->rerr = -EINTR; spin_unlock_irq(&desc->iuspin); wake_up_all(&desc->wait); mutex_lock(&desc->rlock); mutex_lock(&desc->wlock); poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); return 0; } static int wdm_post_reset(struct usb_interface *intf) { struct wdm_device *desc = wdm_find_device(intf); int rv; unpoison_urbs(desc); clear_bit(WDM_OVERFLOW, &desc->flags); clear_bit(WDM_RESETTING, &desc->flags); rv = recover_from_urb_loss(desc); mutex_unlock(&desc->wlock); mutex_unlock(&desc->rlock); return rv; } static struct usb_driver wdm_driver = { .name = "cdc_wdm", .probe = wdm_probe, .disconnect = wdm_disconnect, #ifdef CONFIG_PM .suspend = wdm_suspend, .resume = wdm_resume, .reset_resume = wdm_resume, #endif .pre_reset = wdm_pre_reset, .post_reset = wdm_post_reset, .id_table = wdm_ids, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; module_usb_driver(wdm_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL");
737 736 1 605 301 120 97 95 301 269 33 706 702 707 620 423 596 707 709 1 1 18 1 744 18 78 709 741 741 1 744 3 745 743 2 707 7 440 440 430 10 425 14 431 7 3 7 438 5 439 233 437 438 437 437 437 27 28 28 71 71 70 71 71 24 24 24 24 24 24 24 15 47 47 47 44 47 78 79 4 76 76 75 1 74 4 71 38 33 1 33 15 8 28 24 23 24 23 8 44 4 51 2 152 103 2 51 45 14 858 557 562 562 2 480 126 814 592 155 723 761 264 7 39 758 1 24 121 693 153 682 33 151 150 152 114 108 7 65 49 48 308 317 318 258 65 64 65 65 64 65 318 318 346 46 317 344 345 1 1 336 5 339 6 281 8 65 40 22 2 18 1 11 6 299 6 317 6 11 334 323 48 24 316 315 36 289 2 99 245 311 4 315 311 294 28 242 98 53 10 6 1 45 45 43 40 5 227 121 16 3 270 271 10 45 232 232 262 337 282 319 39 305 3 295 14 306 41 307 307 295 21 47 274 305 306 307 207 14 121 14 132 102 297 15 217 216 1 216 53 19 20 35 34 35 100 100 3 1 95 20 88 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 output functions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_output.c * * Changes: * A.N.Kuznetsov : airthmetics in fragmentation. * extension headers are implemented. * route changes now work. * ip6_forward does not confuse sniffers. * etc. * * H. von Brand : Added missing #include <linux/string.h> * Imran Patel : frag id should be in NBO * Kazunori MIYAZAWA @USAGI * : add ip6_append_data and related functions * for datagram xmit */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/in6.h> #include <linux/tcp.h> #include <linux/route.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/bpf-cgroup.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/sock.h> #include <net/snmp.h> #include <net/gso.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/rawv6.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *daddr, *nexthop; struct ipv6hdr *hdr; struct neighbour *neigh; int ret; /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOMEM; } rcu_read_unlock(); } hdr = ipv6_hdr(skb); daddr = &hdr->daddr; if (ipv6_addr_is_multicast(daddr)) { if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (hdr->hop_limit == 0) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; } } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(IS_ERR_OR_NULL(neigh))) { if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (IS_ERR(neigh)) { rcu_read_unlock(); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; } } sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } static int ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* Please see corresponding comment in ip_finish_output_gso * describing the cases where GSO segment length exceeds the * egress MTU. */ features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); /* Last GSO segment can be smaller than gso_size (and MTU). * Adding a fragment header would produce an "atomic fragment", * which is considered harmful (RFC-8021). Avoid that. */ err = segs->len > mtu ? ip6_fragment(net, sk, segs, ip6_finish_output2) : ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } return ret; } static int ip6_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && !skb_gso_validate_network_len(skb, mtu)) return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); return ip6_finish_output2(net, sk, skb); } static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip6_skb_dst_mtu(skb); if (skb_is_gso(skb)) return ip6_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: case NET_XMIT_CN: return __ip6_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; } return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct sock *sk) { if (!inet6_test_bit(AUTOFLOWLABEL_SET, sk)) return ip6_default_np_autolabel(net); return inet6_test_bit(AUTOFLOWLABEL, sk); } /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified * by calls to skb_set_owner_w() and ipv6_local_error(), * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOBUFS; } rcu_read_unlock(); } if (opt) { seg_len += opt->opt_nflen + opt->opt_flen; if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop, &fl6->saddr); } if (unlikely(seg_len > IPV6_MAXPLEN)) { hop_jumbo = skb_push(skb, hoplen); hop_jumbo->nexthdr = proto; hop_jumbo->hdrlen = 0; hop_jumbo->tlv_type = IPV6_TLV_JUMBO; hop_jumbo->tlv_len = 4; hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen); proto = IPPROTO_HOPOPTS; seg_len = 0; IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO; } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ if (np) hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; skb->protocol = htons(ETH_P_IPV6); skb->priority = priority; skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out((struct sock *)sk, skb); if (unlikely(!skb)) return 0; /* hooks should never assume socket lock is held. * we promote our socket to non const */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dev, dst_output); } skb->dev = dev; /* ipv6_local_error() does not require socket lock, * we promote our socket to non const */ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } EXPORT_SYMBOL(ip6_xmit); static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; struct sock *last = NULL; read_lock(&ip6_ra_lock); for (ra = ip6_ra_chain; ra; ra = ra->next) { struct sock *sk = ra->sk; if (sk && ra->sel == sel && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == skb->dev->ifindex)) { if (inet6_test_bit(RTALERT_ISOLATE, sk) && !net_eq(sock_net(sk), dev_net(skb->dev))) { continue; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) rawv6_rcv(last, skb2); } last = sk; } } if (last) { rawv6_rcv(last, skb); read_unlock(&ip6_ra_lock); return 1; } read_unlock(&ip6_ra_lock); return 0; } static int ip6_forward_proxy_check(struct sk_buff *skb) { struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; if (ipv6_ext_hdr(nexthdr)) { offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) return 0; } else offset = sizeof(struct ipv6hdr); if (nexthdr == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6; if (!pskb_may_pull(skb, (skb_network_header(skb) + offset + 1 - skb->data))) return 0; icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: /* For reaction involving unicast neighbor discovery * message destined to the proxied address, pass it to * input function. */ return 1; default: break; } } /* * The proxying router can't forward traffic sent to a link-local * address, so signal the sender and discard the packet. This * behavior is clarified by the MIPv6 specification. */ if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { dst_link_failure(skb); return -1; } return 0; } static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); return 0; } #endif skb_clear_tstamp(skb); return dst_output(net, sk, skb); } static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; if (skb->ignore_df) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) goto error; if (skb->pkt_type != PACKET_HOST) goto drop; if (unlikely(skb->sk)) goto drop; if (skb_warn_if_lro(skb)) goto drop; if (!READ_ONCE(net->ipv6.devconf_all->disable_policy) && (!idev || !READ_ONCE(idev->cnf.disable_policy)) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } skb_forward_csum(skb); /* * We DO NOT make any processing on * RA packets, pushing them to user level AS IS * without ane WARRANTY that application will be able * to interpret them. The reason is that we * cannot make anything clever here. * * We are not end-node, so that if packet contains * AH/ESP, we cannot make anything. * Defragmentation also would be mistake, RA packets * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { if (ip6_call_ra_chain(skb, ntohs(opt->ra))) return 0; } /* * check and decrement ttl */ if (hdr->hop_limit <= 1) { icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return -ETIMEDOUT; } /* XXX: idev->cnf.proxy_ndp? */ if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit * here by 1, as we do at the end of the * function too. * * But that would be incorrect, as proxying is * not forwarding. The ip6_input function * will handle this packet locally, and it * depends on the hop limit being unchanged. * * One example is the NDP hop limit, that * always has to stay 255, but other would be * similar checks around RA packets, where the * user can even change the desired limit. */ return ip6_input(skb); } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); SKB_DR_SET(reason, XFRM_POLICY); goto drop; } dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ if (IP6CB(skb)->iif == dst->dev->ifindex && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; struct rt6_info *rt; /* * incoming and outgoing devices are the same * send a redirect. */ rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else target = &hdr->daddr; peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); if (peer) inet_putpeer(peer); } else { int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ if (addrtype == IPV6_ADDR_ANY || addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ hdr->hop_limit--; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); error: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); SKB_DR_SET(reason, IP_INADDRERRORS); drop: kfree_skb_reason(skb, reason); return -EINVAL; } static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; skb_dst_drop(to); skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); skb_copy_secmark(to, from); } int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter) { unsigned int first_len; struct frag_hdr *fh; /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!iter->tmp_hdr) return -ENOMEM; iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->hlen = hlen; iter->frag_id = frag_id; iter->nexthdr = nexthdr; __skb_pull(skb, hlen); fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), iter->tmp_hdr, hlen); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); return 0; } EXPORT_SYMBOL(ip6_fraglist_init); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter) { struct sk_buff *frag = iter->frag; unsigned int hlen = iter->hlen; struct frag_hdr *fh; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iter->tmp_hdr, hlen); iter->offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = iter->nexthdr; fh->reserved = 0; fh->frag_off = htons(iter->offset); if (frag->next) fh->frag_off |= htons(IP6_MF); fh->identification = iter->frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } EXPORT_SYMBOL(ip6_fraglist_prepare); 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) { state->prevhdr = prevhdr; state->nexthdr = nexthdr; state->frag_id = frag_id; state->hlen = hlen; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->hroom = hdr_room; state->troom = needed_tailroom; state->offset = 0; } EXPORT_SYMBOL(ip6_frag_init); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state) { u8 *prevhdr = state->prevhdr, *fragnexthdr_offset; struct sk_buff *frag; struct frag_hdr *fh; unsigned int len; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) len &= ~7; /* Allocate buffer */ frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) + state->hroom + state->troom, GFP_ATOMIC); if (!frag) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, state->hroom); skb_put(frag, len + state->hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen); frag->transport_header = (frag->network_header + state->hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen); fragnexthdr_offset = skb_network_header(frag); fragnexthdr_offset += prevhdr - skb_network_header(skb); *fragnexthdr_offset = NEXTHDR_FRAGMENT; /* * Build fragment header. */ fh->nexthdr = state->nexthdr; fh->reserved = 0; fh->identification = state->frag_id; /* * Copy a block of the IP datagram. */ BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag), len)); state->left -= len; fh->frag_off = htons(state->offset); if (state->left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); state->ptr += len; state->offset += len; return frag; } EXPORT_SYMBOL(ip6_frag_next); int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; u8 tstamp_type = skb->tstamp_type; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) goto fail; hlen = err; nexthdr = *prevhdr; nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (unlikely(!skb->ignore_df && skb->len > mtu)) goto fail_toobig; if (IP6CB(skb)->frag_max_size) { if (IP6CB(skb)->frag_max_size > mtu) goto fail_toobig; /* don't send fragments larger than what we received */ mtu = IP6CB(skb)->frag_max_size; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; } if (np) { u32 frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; } if (mtu < hlen + sizeof(struct frag_hdr) + 8) goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); struct ip6_fraglist_iter iter; struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb) || skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, &iter); if (err < 0) goto fail; /* We prevent @rt from being freed. */ rcu_read_lock(); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) ip6_fraglist_prepare(skb, &iter); skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip6_fraglist_next(&iter); } kfree(iter.tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); rcu_read_unlock(); return 0; } kfree_skb_list(iter.frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); rcu_read_unlock(); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom, LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { frag = ip6_frag_next(skb, &state); if (IS_ERR(frag)) { err = PTR_ERR(frag); goto fail; } /* * Put this fragment into the sending queue. */ skb_set_delivery_time(frag, tstamp, tstamp_type); err = output(net, sk, frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); consume_skb(skb); return err; fail_toobig: icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; } static inline int ip6_rt_check(const struct rt6key *rt_key, const struct in6_addr *fl_addr, const struct in6_addr *addr_cache) { return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && (!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt; if (!dst) goto out; if (dst->ops->family != AF_INET6) { dst_release(dst); return NULL; } rt = dst_rt6_info(dst); /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, * and MSG_DONTROUTE --ANK (980726) * * 1. ip6_rt_check(): If route was host route, * check that cached destination is current. * If it is network route, we still may * check its validity using saved pointer * to the last used address: daddr_cache. * We do not want to save whole address now, * (because main consumer of this service * is tcp, which has not this problem), * so that the last trick works only on connected * sockets. * 2. oif also should be the same. */ if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } out: return dst; } static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; #endif int err; int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, * the route-specific preferred source forces the * ip6_route_output call _before_ ip6_route_get_saddr. * * In source specific routing (no src=any default route), * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : dst_rt6_info(*dst); rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0, fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); if (err) goto out_err_release; /* If we had an erroneous initial result, pretend it * never existed and let the SA-enabled version take * over. */ if ((*dst)->error) { dst_release(*dst); *dst = NULL; } if (fl6->flowi6_oif) flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) goto out_err_release; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * Here if the dst entry we've looked up * has a neighbour entry that is in the INCOMPLETE * state and the src address from the flow is * marked as OPTIMISTIC, we release the found * dst entry and replace it instead with the * dst entry of the nexthop router */ rt = dst_rt6_info(*dst); rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock(); if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); if (ifp) in6_ifa_put(ifp); if (redirect) { /* * We need to get the dst entry for the * default router instead */ dst_release(*dst); memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); *dst = ip6_route_output(net, sk, &fl_gw6); err = (*dst)->error; if (err) goto out_err_release; } } #endif if (ipv6_addr_v4mapped(&fl6->saddr) && !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { err = -EAFNOSUPPORT; goto out_err_release; } return 0; out_err_release: dst_release(*dst); *dst = NULL; if (err == -ENETUNREACH) IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); return err; } /** * ip6_dst_lookup - perform route lookup on flow * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup * * This function performs a route lookup on the given flow. * * It returns zero on success, or a standard errno code on error. */ int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { *dst = NULL; return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * * This function performs a route lookup on the given flow. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ 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 *dst = NULL; int err; err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); /** * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * @connected: whether @sk is connected or not * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * * In addition, for a connected socket, cache the dst in the socket * if the current cache is not valid. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ 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 *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); dst = ip6_sk_dst_check(sk, dst, fl6); if (dst) return dst; dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); return dst; } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (!skb) { /* first fragment, reserve header_len */ *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); } } static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu, frag_size; struct ipv6_txoptions *nopt, *opt = ipc6->opt; /* callers pass dst together with a reference, set it first so * ip6_cork_release() can put it down even in case of an error. */ cork->base.dst = &rt->dst; /* * setup for corking */ if (opt) { if (WARN_ON(v6_cork->opt)) return -EINVAL; nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!nopt)) return -ENOBUFS; nopt->tot_len = sizeof(*opt); nopt->opt_flen = opt->opt_flen; nopt->opt_nflen = opt->opt_nflen; nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst)); frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); cork->base.length = 0; cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; } static int __ip6_append_data(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; struct inet_cork *cork = &cork_full->base; struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; bool zc = false; u32 tskey = 0; struct rt6_info *rt = dst_rt6_info(cork->dst); bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; skb = skb_peek_tail(queue); if (!skb) { exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } paged = !!cork->gso_size; mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize; maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ if (headersize + transhdrlen > mtu) goto emsgsize; if (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; if (cork->length + length > maxnonfragsize - headersize) { emsgsize: pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0); ipv6_local_error(sk, EMSGSIZE, fl6, pmtu); return -EMSGSIZE; } /* CHECKSUM_PARTIAL only with no extension headers and when * we are not going to fragment */ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } else if ((flags & MSG_SPLICE_PAGES) && length) { if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) /* We need an empty buffer to attach stuff to */ paged = true; else flags &= ~MSG_SPLICE_PAGES; } hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; if (hold_tskey) tskey = atomic_inc_return(&sk->sk_tskey) - 1; /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ cork->length += length; if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (!skb || !skb_prev) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len; alloc_extra += dst_exthdrlen; alloc_extra += rt->dst.trailer_len; /* We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloc_extra += sizeof(struct frag_hdr); if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } fraglen = datalen + fragheaderlen; copy = datalen - transhdrlen - fraggap - pagedlen; /* [!] NOTE: copy may be negative if pagedlen>0 * because then the equation may reduces to -fraggap. */ if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) { err = -EINVAL; goto error; } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); /* * Find where to start putting bytes */ data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } else if (flags & MSG_SPLICE_PAGES) { copy = 0; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* Only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; err = -EIO; if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) goto error; copy = err; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } 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, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int exthdrlen; int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, ipc6, rt); if (err) return err; inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { transhdrlen = 0; } return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) { struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; skb_dst_set(skb, dst); } static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { struct ipv6_txoptions *opt = v6_cork->opt; kfree(opt->dst0opt); kfree(opt->dst1opt); kfree(opt->hopopt); kfree(opt->srcrt); kfree(opt); v6_cork->opt = NULL; } if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; } } 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 *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr *final_dst; struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; struct rt6_info *rt = dst_rt6_info(cork->base.dst); struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); __skb_pull(skb, skb_network_header_len(skb)); final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); else skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; if (sk->sk_socket->type == SOCK_RAW && !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } ip6_cork_release(cork, v6_cork); out: return skb; } int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return err; } int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; skb = ip6_finish_skb(sk); if (!skb) return 0; return ip6_send_skb(skb); } EXPORT_SYMBOL_GPL(ip6_push_pending_frames); static void __ip6_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) { if (skb_dst(skb)) IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } ip6_cork_release(cork, v6_cork); } void ip6_flush_pending_frames(struct sock *sk) { __ip6_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); 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, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; if (flags & MSG_PROBE) { dst_release(&rt->dst); return NULL; } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk); err = __ip6_append_data(sk, &queue, cork, &v6_cork, &current->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } return __ip6_make_skb(sk, &queue, cork, &v6_cork); }
85 14 14 14 71 71 92 2 87 19 2 27 664 6 662 307 305 307 304 4 305 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 // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> #include <net/secure_seq.h> #include <linux/netfilter.h> static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { return get_random_u32_above(0); } /* This function exists only for tap drivers that must support broken * clients requesting UFO without specifying an IPv6 fragment ID. * * This is similar to ipv6_select_ident() but we use an independent hash * seed to limit information leakage. * * The network header must be set before calling this. */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; addrs = skb_header_pointer(skb, skb_network_offset(skb) + offsetof(struct ipv6hdr, saddr), sizeof(buf), buf); if (!addrs) return 0; id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { u32 id; id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { case NEXTHDR_HOP: break; case NEXTHDR_ROUTING: found_rhdr = 1; break; case NEXTHDR_DEST: #if IS_ENABLED(CONFIG_IPV6_MIP6) if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) break; #endif if (found_rhdr) return offset; break; default: return offset; } if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) return -EINVAL; exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); offset += ipv6_optlen(exthdr); if (offset > IPV6_MAXPLEN) return -EINVAL; *nexthdr = &exthdr->nexthdr; } return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); #if IS_ENABLED(CONFIG_IPV6) int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); if (hoplimit == 0) { struct net_device *dev = dst->dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) hoplimit = READ_ONCE(idev->cnf.hop_limit); else hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); rcu_read_unlock(); } return hoplimit; } EXPORT_SYMBOL(ip6_dst_hoplimit); #endif int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int len; len = skb->len - sizeof(struct ipv6hdr); if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IPV6); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip6_local_out);
2 5 2 2 11 9 2 1 1 2 2 2 2 2 2 13 6 7 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 /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (C) 2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifndef __IP_SET_BITMAP_IP_GEN_H #define __IP_SET_BITMAP_IP_GEN_H #include <linux/rcupdate_wait.h> #define mtype_do_test IPSET_TOKEN(MTYPE, _do_test) #define mtype_gc_test IPSET_TOKEN(MTYPE, _gc_test) #define mtype_is_filled IPSET_TOKEN(MTYPE, _is_filled) #define mtype_do_add IPSET_TOKEN(MTYPE, _do_add) #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_do_del IPSET_TOKEN(MTYPE, _do_del) #define mtype_do_list IPSET_TOKEN(MTYPE, _do_list) #define mtype_do_head IPSET_TOKEN(MTYPE, _do_head) #define mtype_adt_elem IPSET_TOKEN(MTYPE, _adt_elem) #define mtype_add_timeout IPSET_TOKEN(MTYPE, _add_timeout) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) #define mtype_memsize IPSET_TOKEN(MTYPE, _memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_elem IPSET_TOKEN(MTYPE, _elem) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_add IPSET_TOKEN(MTYPE, _add) #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct mtype *map = set->data; timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } static void mtype_ext_cleanup(struct ip_set *set) { struct mtype *map = set->data; u32 id; for (id = 0; id < map->elements; id++) if (test_bit(id, map->members)) ip_set_ext_destroy(set, get_ext(set, map, id)); } static void mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); ip_set_free(map); set->data = NULL; } static void mtype_flush(struct ip_set *set) { struct mtype *map = set->data; if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); bitmap_zero(map->members, map->elements); set->elements = 0; set->ext_size = 0; } /* Calculate the actual memory size of the set data */ static size_t mtype_memsize(const struct mtype *map, size_t dsize) { return sizeof(*map) + map->memsize + map->elements * dsize; } static int mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size; nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; nla_nest_end(skb, nested); return 0; nla_put_failure: return -EMSGSIZE; } static int mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct mtype *map = set->data; const struct mtype_adt_elem *e = value; void *x = get_ext(set, map, e->id); int ret = mtype_do_test(e, map, set->dsize); if (ret <= 0) return ret; return ip_set_match_extensions(set, ext, mext, flags, x); } static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct mtype *map = set->data; const struct mtype_adt_elem *e = value; void *x = get_ext(set, map, e->id); int ret = mtype_do_add(e, map, flags, set->dsize); if (ret == IPSET_ADD_FAILED) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(x, set))) { set->elements--; ret = 0; } else if (!(flags & IPSET_FLAG_EXIST)) { set_bit(e->id, map->members); return -IPSET_ERR_EXIST; } /* Element is re-added, cleanup extensions */ ip_set_ext_destroy(set, x); } if (ret > 0) set->elements--; if (SET_WITH_TIMEOUT(set)) #ifdef IP_SET_BITMAP_STORED_TIMEOUT mtype_add_timeout(ext_timeout(x, set), e, ext, set, map, ret); #else ip_set_timeout_set(ext_timeout(x, set), ext->timeout); #endif if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(x, set), ext); if (SET_WITH_COMMENT(set)) ip_set_init_comment(set, ext_comment(x, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(x, set), ext); /* Activate element */ set_bit(e->id, map->members); set->elements++; return 0; } static int mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct mtype *map = set->data; const struct mtype_adt_elem *e = value; void *x = get_ext(set, map, e->id); if (mtype_do_del(e, map)) return -IPSET_ERR_EXIST; ip_set_ext_destroy(set, x); set->elements--; if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(x, set))) return -IPSET_ERR_EXIST; return 0; } #ifndef IP_SET_BITMAP_STORED_TIMEOUT static bool mtype_is_filled(const struct mtype_elem *x) { return true; } #endif static int mtype_list(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb) { struct mtype *map = set->data; struct nlattr *adt, *nested; void *x; u32 id, first = cb->args[IPSET_CB_ARG0]; int ret = 0; adt = nla_nest_start(skb, IPSET_ATTR_ADT); if (!adt) return -EMSGSIZE; /* Extensions may be replaced */ rcu_read_lock(); for (; cb->args[IPSET_CB_ARG0] < map->elements; cb->args[IPSET_CB_ARG0]++) { cond_resched_rcu(); id = cb->args[IPSET_CB_ARG0]; x = get_ext(set, map, id); if (!test_bit(id, map->members) || (SET_WITH_TIMEOUT(set) && #ifdef IP_SET_BITMAP_STORED_TIMEOUT mtype_is_filled(x) && #endif ip_set_timeout_expired(ext_timeout(x, set)))) continue; nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) { if (id == first) { nla_nest_cancel(skb, adt); ret = -EMSGSIZE; goto out; } goto nla_put_failure; } if (mtype_do_list(skb, map, id, set->dsize)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, x, mtype_is_filled(x))) goto nla_put_failure; nla_nest_end(skb, nested); } nla_nest_end(skb, adt); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; goto out; nla_put_failure: nla_nest_cancel(skb, nested); if (unlikely(id == first)) { cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } nla_nest_end(skb, adt); out: rcu_read_unlock(); return ret; } static void mtype_gc(struct timer_list *t) { struct mtype *map = from_timer(map, t, gc); struct ip_set *set = map->set; void *x; u32 id; /* We run parallel with other readers (test element) * but adding/deleting new entries is locked out */ spin_lock_bh(&set->lock); for (id = 0; id < map->elements; id++) if (mtype_gc_test(id, map, set->dsize)) { x = get_ext(set, map, id); if (ip_set_timeout_expired(ext_timeout(x, set))) { clear_bit(id, map->members); ip_set_ext_destroy(set, x); set->elements--; } } spin_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); } static void mtype_cancel_gc(struct ip_set *set) { struct mtype *map = set->data; if (SET_WITH_TIMEOUT(set)) del_timer_sync(&map->gc); } static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, .adt = { [IPSET_ADD] = mtype_add, [IPSET_DEL] = mtype_del, [IPSET_TEST] = mtype_test, }, .destroy = mtype_destroy, .flush = mtype_flush, .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */
91 12 57 85 105 16 37 2 85 86 2 1 7 25 26 26 26 25 25 8 24 25 9 3 6 20 13 16 32 19 18 18 3 3 3 1 3 1 1 1 1 1 91 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 // SPDX-License-Identifier: GPL-2.0+ /* * NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #include <linux/errno.h> #include "nilfs.h" #include "page.h" #include "direct.h" #include "alloc.h" #include "dat.h" static inline __le64 *nilfs_direct_dptrs(const struct nilfs_bmap *direct) { return (__le64 *) ((struct nilfs_direct_node *)direct->b_u.u_data + 1); } static inline __u64 nilfs_direct_get_ptr(const struct nilfs_bmap *direct, __u64 key) { return le64_to_cpu(*(nilfs_direct_dptrs(direct) + key)); } static inline void nilfs_direct_set_ptr(struct nilfs_bmap *direct, __u64 key, __u64 ptr) { *(nilfs_direct_dptrs(direct) + key) = cpu_to_le64(ptr); } static int nilfs_direct_lookup(const struct nilfs_bmap *direct, __u64 key, int level, __u64 *ptrp) { __u64 ptr; if (key > NILFS_DIRECT_KEY_MAX || level != 1) return -ENOENT; ptr = nilfs_direct_get_ptr(direct, key); if (ptr == NILFS_BMAP_INVALID_PTR) return -ENOENT; *ptrp = ptr; return 0; } static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, __u64 key, __u64 *ptrp, unsigned int maxblocks) { struct inode *dat = NULL; __u64 ptr, ptr2; sector_t blocknr; int ret, cnt; if (key > NILFS_DIRECT_KEY_MAX) return -ENOENT; ptr = nilfs_direct_get_ptr(direct, key); if (ptr == NILFS_BMAP_INVALID_PTR) return -ENOENT; if (NILFS_BMAP_USE_VBN(direct)) { dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) goto dat_error; ptr = blocknr; } maxblocks = min_t(unsigned int, maxblocks, NILFS_DIRECT_KEY_MAX - key + 1); for (cnt = 1; cnt < maxblocks && (ptr2 = nilfs_direct_get_ptr(direct, key + cnt)) != NILFS_BMAP_INVALID_PTR; cnt++) { if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) break; } *ptrp = ptr; return cnt; dat_error: if (ret == -ENOENT) ret = -EINVAL; /* Notify bmap layer of metadata corruption */ return ret; } static __u64 nilfs_direct_find_target_v(const struct nilfs_bmap *direct, __u64 key) { __u64 ptr; ptr = nilfs_bmap_find_target_seq(direct, key); if (ptr != NILFS_BMAP_INVALID_PTR) /* sequential access */ return ptr; /* block group */ return nilfs_bmap_find_target_in_group(direct); } static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) { union nilfs_bmap_ptr_req req; struct inode *dat = NULL; struct buffer_head *bh; int ret; if (key > NILFS_DIRECT_KEY_MAX) return -ENOENT; if (nilfs_direct_get_ptr(bmap, key) != NILFS_BMAP_INVALID_PTR) return -EEXIST; if (NILFS_BMAP_USE_VBN(bmap)) { req.bpr_ptr = nilfs_direct_find_target_v(bmap, key); dat = nilfs_bmap_get_dat(bmap); } ret = nilfs_bmap_prepare_alloc_ptr(bmap, &req, dat); if (!ret) { /* ptr must be a pointer to a buffer head. */ bh = (struct buffer_head *)((unsigned long)ptr); set_buffer_nilfs_volatile(bh); nilfs_bmap_commit_alloc_ptr(bmap, &req, dat); nilfs_direct_set_ptr(bmap, key, req.bpr_ptr); if (!nilfs_bmap_dirty(bmap)) nilfs_bmap_set_dirty(bmap); if (NILFS_BMAP_USE_VBN(bmap)) nilfs_bmap_set_target_v(bmap, key, req.bpr_ptr); nilfs_inode_add_blocks(bmap->b_inode, 1); } return ret; } static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key) { union nilfs_bmap_ptr_req req; struct inode *dat; int ret; if (key > NILFS_DIRECT_KEY_MAX || nilfs_direct_get_ptr(bmap, key) == NILFS_BMAP_INVALID_PTR) return -ENOENT; dat = NILFS_BMAP_USE_VBN(bmap) ? nilfs_bmap_get_dat(bmap) : NULL; req.bpr_ptr = nilfs_direct_get_ptr(bmap, key); ret = nilfs_bmap_prepare_end_ptr(bmap, &req, dat); if (!ret) { nilfs_bmap_commit_end_ptr(bmap, &req, dat); nilfs_direct_set_ptr(bmap, key, NILFS_BMAP_INVALID_PTR); nilfs_inode_sub_blocks(bmap->b_inode, 1); } return ret; } static int nilfs_direct_seek_key(const struct nilfs_bmap *direct, __u64 start, __u64 *keyp) { __u64 key; for (key = start; key <= NILFS_DIRECT_KEY_MAX; key++) { if (nilfs_direct_get_ptr(direct, key) != NILFS_BMAP_INVALID_PTR) { *keyp = key; return 0; } } return -ENOENT; } static int nilfs_direct_last_key(const struct nilfs_bmap *direct, __u64 *keyp) { __u64 key, lastkey; lastkey = NILFS_DIRECT_KEY_MAX + 1; for (key = NILFS_DIRECT_KEY_MIN; key <= NILFS_DIRECT_KEY_MAX; key++) if (nilfs_direct_get_ptr(direct, key) != NILFS_BMAP_INVALID_PTR) lastkey = key; if (lastkey == NILFS_DIRECT_KEY_MAX + 1) return -ENOENT; *keyp = lastkey; return 0; } static int nilfs_direct_check_insert(const struct nilfs_bmap *bmap, __u64 key) { return key > NILFS_DIRECT_KEY_MAX; } static int nilfs_direct_gather_data(struct nilfs_bmap *direct, __u64 *keys, __u64 *ptrs, int nitems) { __u64 key; __u64 ptr; int n; if (nitems > NILFS_DIRECT_NBLOCKS) nitems = NILFS_DIRECT_NBLOCKS; n = 0; for (key = 0; key < nitems; key++) { ptr = nilfs_direct_get_ptr(direct, key); if (ptr != NILFS_BMAP_INVALID_PTR) { keys[n] = key; ptrs[n] = ptr; n++; } } return n; } int nilfs_direct_delete_and_convert(struct nilfs_bmap *bmap, __u64 key, __u64 *keys, __u64 *ptrs, int n) { __le64 *dptrs; int ret, i, j; /* no need to allocate any resource for conversion */ /* delete */ ret = bmap->b_ops->bop_delete(bmap, key); if (ret < 0) return ret; /* free resources */ if (bmap->b_ops->bop_clear != NULL) bmap->b_ops->bop_clear(bmap); /* convert */ dptrs = nilfs_direct_dptrs(bmap); for (i = 0, j = 0; i < NILFS_DIRECT_NBLOCKS; i++) { if ((j < n) && (i == keys[j])) { dptrs[i] = (i != key) ? cpu_to_le64(ptrs[j]) : NILFS_BMAP_INVALID_PTR; j++; } else dptrs[i] = NILFS_BMAP_INVALID_PTR; } nilfs_direct_init(bmap); return 0; } static int nilfs_direct_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh) { struct nilfs_palloc_req oldreq, newreq; struct inode *dat; __u64 key; __u64 ptr; int ret; if (!NILFS_BMAP_USE_VBN(bmap)) return 0; dat = nilfs_bmap_get_dat(bmap); key = nilfs_bmap_data_get_key(bmap, bh); ptr = nilfs_direct_get_ptr(bmap, key); if (!buffer_nilfs_volatile(bh)) { oldreq.pr_entry_nr = ptr; newreq.pr_entry_nr = ptr; ret = nilfs_dat_prepare_update(dat, &oldreq, &newreq); if (ret < 0) return ret; nilfs_dat_commit_update(dat, &oldreq, &newreq, bmap->b_ptr_type == NILFS_BMAP_PTR_VS); set_buffer_nilfs_volatile(bh); nilfs_direct_set_ptr(bmap, key, newreq.pr_entry_nr); } else ret = nilfs_dat_mark_dirty(dat, ptr); return ret; } static int nilfs_direct_assign_v(struct nilfs_bmap *direct, __u64 key, __u64 ptr, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct inode *dat = nilfs_bmap_get_dat(direct); union nilfs_bmap_ptr_req req; int ret; req.bpr_ptr = ptr; ret = nilfs_dat_prepare_start(dat, &req.bpr_req); if (!ret) { nilfs_dat_commit_start(dat, &req.bpr_req, blocknr); binfo->bi_v.bi_vblocknr = cpu_to_le64(ptr); binfo->bi_v.bi_blkoff = cpu_to_le64(key); } return ret; } static int nilfs_direct_assign_p(struct nilfs_bmap *direct, __u64 key, __u64 ptr, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { nilfs_direct_set_ptr(direct, key, blocknr); binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = 0; memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } static int nilfs_direct_assign(struct nilfs_bmap *bmap, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { __u64 key; __u64 ptr; key = nilfs_bmap_data_get_key(bmap, *bh); if (unlikely(key > NILFS_DIRECT_KEY_MAX)) { nilfs_crit(bmap->b_inode->i_sb, "%s (ino=%lu): invalid key: %llu", __func__, bmap->b_inode->i_ino, (unsigned long long)key); return -EINVAL; } ptr = nilfs_direct_get_ptr(bmap, key); if (unlikely(ptr == NILFS_BMAP_INVALID_PTR)) { nilfs_crit(bmap->b_inode->i_sb, "%s (ino=%lu): invalid pointer: %llu", __func__, bmap->b_inode->i_ino, (unsigned long long)ptr); return -EINVAL; } return NILFS_BMAP_USE_VBN(bmap) ? nilfs_direct_assign_v(bmap, key, ptr, bh, blocknr, binfo) : nilfs_direct_assign_p(bmap, key, ptr, bh, blocknr, binfo); } static const struct nilfs_bmap_operations nilfs_direct_ops = { .bop_lookup = nilfs_direct_lookup, .bop_lookup_contig = nilfs_direct_lookup_contig, .bop_insert = nilfs_direct_insert, .bop_delete = nilfs_direct_delete, .bop_clear = NULL, .bop_propagate = nilfs_direct_propagate, .bop_lookup_dirty_buffers = NULL, .bop_assign = nilfs_direct_assign, .bop_mark = NULL, .bop_seek_key = nilfs_direct_seek_key, .bop_last_key = nilfs_direct_last_key, .bop_check_insert = nilfs_direct_check_insert, .bop_check_delete = NULL, .bop_gather_data = nilfs_direct_gather_data, }; int nilfs_direct_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_direct_ops; return 0; }
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 // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match AH parameters. */ /* (C) 1999-2000 Yon Uriarte <yon@astaro.de> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/netfilter_ipv4/ipt_ah.h> #include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yon Uriarte <yon@astaro.de>"); MODULE_DESCRIPTION("Xtables: IPv4 IPsec-AH SPI match"); /* Returns 1 if the spi is matched by the range, 0 otherwise */ static inline bool spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) { bool r; pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', min, spi, max); r = (spi >= min && spi <= max) ^ invert; pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct ip_auth_hdr _ahdr; const struct ip_auth_hdr *ah; const struct ipt_ah *ahinfo = par->matchinfo; /* Must not be a fragment. */ if (par->fragoff != 0) return false; ah = skb_header_pointer(skb, par->thoff, sizeof(_ahdr), &_ahdr); if (ah == NULL) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. */ pr_debug("Dropping evil AH tinygram.\n"); par->hotdrop = true; return false; } return spi_match(ahinfo->spis[0], ahinfo->spis[1], ntohl(ah->spi), !!(ahinfo->invflags & IPT_AH_INV_SPI)); } static int ah_mt_check(const struct xt_mtchk_param *par) { const struct ipt_ah *ahinfo = par->matchinfo; /* Must specify no unknown invflags */ if (ahinfo->invflags & ~IPT_AH_INV_MASK) { pr_debug("unknown flags %X\n", ahinfo->invflags); return -EINVAL; } return 0; } static struct xt_match ah_mt_reg __read_mostly = { .name = "ah", .family = NFPROTO_IPV4, .match = ah_mt, .matchsize = sizeof(struct ipt_ah), .proto = IPPROTO_AH, .checkentry = ah_mt_check, .me = THIS_MODULE, }; static int __init ah_mt_init(void) { return xt_register_match(&ah_mt_reg); } static void __exit ah_mt_exit(void) { xt_unregister_match(&ah_mt_reg); } module_init(ah_mt_init); module_exit(ah_mt_exit);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2021 Intel Corporation */ #include <linux/unaligned.h> void eir_create(struct hci_dev *hdev, u8 *data); u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr); u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr); u8 eir_create_per_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr); u8 eir_append_local_name(struct hci_dev *hdev, u8 *eir, u8 ad_len); u8 eir_append_appearance(struct hci_dev *hdev, u8 *ptr, u8 ad_len); u8 eir_append_service_data(u8 *eir, u16 eir_len, u16 uuid, u8 *data, u8 data_len); static inline u16 eir_precalc_len(u8 data_len) { return sizeof(u8) * 2 + data_len; } static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) { eir[eir_len++] = sizeof(type) + data_len; eir[eir_len++] = type; memcpy(&eir[eir_len], data, data_len); eir_len += data_len; return eir_len; } static inline u16 eir_append_le16(u8 *eir, u16 eir_len, u8 type, u16 data) { eir[eir_len++] = sizeof(type) + sizeof(data); eir[eir_len++] = type; put_unaligned_le16(data, &eir[eir_len]); eir_len += sizeof(data); return eir_len; } static inline u16 eir_skb_put_data(struct sk_buff *skb, u8 type, u8 *data, u8 data_len) { u8 *eir; u16 eir_len; eir_len = eir_precalc_len(data_len); eir = skb_put(skb, eir_len); WARN_ON(sizeof(type) + data_len > U8_MAX); eir[0] = sizeof(type) + data_len; eir[1] = type; memcpy(&eir[2], data, data_len); return eir_len; } static inline void *eir_get_data(u8 *eir, size_t eir_len, u8 type, size_t *data_len) { size_t parsed = 0; if (eir_len < 2) return NULL; while (parsed < eir_len - 1) { u8 field_len = eir[0]; if (field_len == 0) break; parsed += field_len + 1; if (parsed > eir_len) break; if (eir[1] != type) { eir += field_len + 1; continue; } /* Zero length data */ if (field_len == 1) return NULL; if (data_len) *data_len = field_len - 1; return &eir[2]; } return NULL; } void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len);
80 14 1 14 10 14 5 5 5 5 5 2 3 7 7 3 5 15 15 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 /* * Performance events x86 architecture code * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * * For licencing details see kernel-base/COPYING */ #include <linux/perf_event.h> #include <linux/capability.h> #include <linux/notifier.h> #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kdebug.h> #include <linux/sched/mm.h> #include <linux/sched/clock.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> #include <linux/nospec.h> #include <linux/static_call.h> #include <asm/apic.h> #include <asm/stacktrace.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/alternative.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/timer.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/unwind.h> #include <asm/uprobes.h> #include <asm/ibt.h> #include "perf_event.h" struct x86_pmu x86_pmu __read_mostly; static struct pmu pmu; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, .pmu = &pmu, }; DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key); DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); DEFINE_STATIC_KEY_FALSE(perf_is_hybrid); /* * This here uses DEFINE_STATIC_CALL_NULL() to get a static_call defined * from just a typename, as opposed to an actual function. */ DEFINE_STATIC_CALL_NULL(x86_pmu_handle_irq, *x86_pmu.handle_irq); DEFINE_STATIC_CALL_NULL(x86_pmu_disable_all, *x86_pmu.disable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); DEFINE_STATIC_CALL_NULL(x86_pmu_set_period, *x86_pmu.set_period); DEFINE_STATIC_CALL_NULL(x86_pmu_update, *x86_pmu.update); DEFINE_STATIC_CALL_NULL(x86_pmu_limit_period, *x86_pmu.limit_period); DEFINE_STATIC_CALL_NULL(x86_pmu_schedule_events, *x86_pmu.schedule_events); DEFINE_STATIC_CALL_NULL(x86_pmu_get_event_constraints, *x86_pmu.get_event_constraints); DEFINE_STATIC_CALL_NULL(x86_pmu_put_event_constraints, *x86_pmu.put_event_constraints); DEFINE_STATIC_CALL_NULL(x86_pmu_start_scheduling, *x86_pmu.start_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_commit_scheduling, *x86_pmu.commit_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_stop_scheduling, *x86_pmu.stop_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_sched_task, *x86_pmu.sched_task); DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx); DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter); /* * This one is magic, it will get called even when PMU init fails (because * there is no PMU), in which case it should simply return NULL. */ DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs); u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; /* * Propagate event elapsed time into the generic event. * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; u64 delta; if (unlikely(!hwc->event_base)) return 0; /* * Careful: an NMI might modify the previous event value. * * Our tactic to handle this is to first atomically read and * exchange a new raw count - then add that new-prev delta * count to the generic event atomically: */ prev_raw_count = local64_read(&hwc->prev_count); do { rdpmcl(hwc->event_base_rdpmc, new_raw_count); } while (!local64_try_cmpxchg(&hwc->prev_count, &prev_raw_count, new_raw_count)); /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); return new_raw_count; } /* * Find and validate any extra registers to set up. */ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) { struct extra_reg *extra_regs = hybrid(event->pmu, extra_regs); struct hw_perf_event_extra *reg; struct extra_reg *er; reg = &event->hw.extra_reg; if (!extra_regs) return 0; for (er = extra_regs; er->msr; er++) { if (er->event != (config & er->config_mask)) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; /* Check if the extra msrs can be safely accessed*/ if (!er->extra_msr_access) return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; reg->reg = er->msr; break; } return 0; } static atomic_t active_events; static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC static inline u64 get_possible_counter_mask(void) { u64 cntr_mask = x86_pmu.cntr_mask64; int i; if (!is_hybrid()) return cntr_mask; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64; return cntr_mask; } static bool reserve_pmc_hardware(void) { u64 cntr_mask = get_possible_counter_mask(); int i, end; for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { if (!reserve_perfctr_nmi(x86_pmu_event_addr(i))) goto perfctr_fail; } for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { if (!reserve_evntsel_nmi(x86_pmu_config_addr(i))) goto eventsel_fail; } return true; eventsel_fail: end = i; for_each_set_bit(i, (unsigned long *)&cntr_mask, end) release_evntsel_nmi(x86_pmu_config_addr(i)); i = X86_PMC_IDX_MAX; perfctr_fail: end = i; for_each_set_bit(i, (unsigned long *)&cntr_mask, end) release_perfctr_nmi(x86_pmu_event_addr(i)); return false; } static void release_pmc_hardware(void) { u64 cntr_mask = get_possible_counter_mask(); int i; for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { release_perfctr_nmi(x86_pmu_event_addr(i)); release_evntsel_nmi(x86_pmu_config_addr(i)); } } #else static bool reserve_pmc_hardware(void) { return true; } static void release_pmc_hardware(void) {} #endif bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask, unsigned long *fixed_cntr_mask) { u64 val, val_fail = -1, val_new= ~0; int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; /* * Check to see if the BIOS enabled any of the counters, if so * complain and bail. */ for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) { reg = x86_pmu_config_addr(i); ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; if (val & ARCH_PERFMON_EVENTSEL_ENABLE) { bios_fail = 1; val_fail = val; reg_fail = reg; } else { reg_safe = i; } } if (*(u64 *)fixed_cntr_mask) { reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) { if (fixed_counter_disabled(i, pmu)) continue; if (val & (0x03ULL << i*4)) { bios_fail = 1; val_fail = val; reg_fail = reg; } } } /* * If all the counters are enabled, the below test will always * fail. The tools will also become useless in this scenario. * Just fail and disable the hardware counters. */ if (reg_safe == -1) { reg = reg_safe; goto msr_fail; } /* * Read the current value, change it and read it back to see if it * matches, this is needed to detect certain hardware emulators * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ reg = x86_pmu_event_addr(reg_safe); if (rdmsrl_safe(reg, &val)) goto msr_fail; val ^= 0xffffUL; ret = wrmsrl_safe(reg, val); ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) goto msr_fail; /* * We still allow the PMU driver to operate: */ if (bios_fail) { pr_cont("Broken BIOS detected, complain to your hardware vendor.\n"); pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); } return true; msr_fail: if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { pr_cont("PMU not available due to virtualization, using software events only.\n"); } else { pr_cont("Broken PMU hardware detected, using software events only.\n"); pr_err("Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); } return false; } static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) { hw_perf_event_destroy(event); /* undo the lbr/bts event accounting */ x86_del_exclusive(x86_lbr_exclusive_lbr); } static inline int x86_pmu_initialized(void) { return x86_pmu.handle_irq != NULL; } static inline int set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) { struct perf_event_attr *attr = &event->attr; unsigned int cache_type, cache_op, cache_result; u64 config, val; config = attr->config; cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hybrid_var(event->pmu, hw_cache_event_ids)[cache_type][cache_op][cache_result]; if (val == 0) return -ENOENT; if (val == -1) return -EINVAL; hwc->config |= val; attr->config1 = hybrid_var(event->pmu, hw_cache_extra_regs)[cache_type][cache_op][cache_result]; return x86_pmu_extra_regs(val, event); } int x86_reserve_hardware(void) { int err = 0; if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) { err = -EBUSY; } else { reserve_ds_buffers(); reserve_lbr_buffers(); } } if (!err) atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } return err; } void x86_release_hardware(void) { if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); release_lbr_buffers(); mutex_unlock(&pmc_reserve_mutex); } } /* * Check if we can create event of a certain type (that no conflicting events * are present). */ int x86_add_exclusive(unsigned int what) { int i; /* * When lbr_pt_coexist we allow PT to coexist with either LBR or BTS. * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) goto fail_unlock; } atomic_inc(&x86_pmu.lbr_exclusive[what]); mutex_unlock(&pmc_reserve_mutex); } out: atomic_inc(&active_events); return 0; fail_unlock: mutex_unlock(&pmc_reserve_mutex); return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&active_events); /* * See the comment in x86_add_exclusive(). */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); } int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; u64 config; if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } if (attr->type == event->pmu->type) return x86_pmu_extra_regs(event->attr.config, event); if (attr->type == PERF_TYPE_HW_CACHE) return set_ext_hw_attr(hwc, event); if (attr->config >= x86_pmu.max_events) return -EINVAL; attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); /* * The generic map: */ config = x86_pmu.event_map(attr->config); if (config == 0) return -ENOENT; if (config == -1LL) return -EINVAL; hwc->config |= config; return 0; } /* * check that branch_sample_type is compatible with * settings needed for precise_ip > 1 which implies * using the LBR to capture ALL taken branches at the * priv levels of the measurement */ static inline int precise_br_compat(struct perf_event *event) { u64 m = event->attr.branch_sample_type; u64 b = 0; /* must capture all branches */ if (!(m & PERF_SAMPLE_BRANCH_ANY)) return 0; m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_user) b |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) b |= PERF_SAMPLE_BRANCH_KERNEL; /* * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86 */ return m == b; } int x86_pmu_max_precise(void) { int precise = 0; /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; if (x86_pmu.pebs_prec_dist) precise++; } return precise; } int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = x86_pmu_max_precise(); if (event->attr.precise_ip > precise) return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; } /* * check that PEBS LBR correction does not conflict with * whatever the user is asking with attr->branch_sample_type */ if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) { u64 *br_type = &event->attr.branch_sample_type; if (has_branch_stack(event)) { if (!precise_br_compat(event)) return -EOPNOTSUPP; /* branch_sample_type is compatible */ } else { /* * user did not specify branch_sample_type * * For PEBS fixups, we capture all * the branches at the priv level of the * event. */ *br_type = PERF_SAMPLE_BRANCH_ANY; if (!event->attr.exclude_user) *br_type |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) *br_type |= PERF_SAMPLE_BRANCH_KERNEL; } } if (branch_sample_call_stack(event)) event->attach_state |= PERF_ATTACH_TASK_DATA; /* * Generate PMC IRQs: * (keep 'enabled' bit clear for now) */ event->hw.config = ARCH_PERFMON_EVENTSEL_INT; /* * Count user and OS events unless requested not to */ if (!event->attr.exclude_user) event->hw.config |= ARCH_PERFMON_EVENTSEL_USR; if (!event->attr.exclude_kernel) event->hw.config |= ARCH_PERFMON_EVENTSEL_OS; if (event->attr.type == event->pmu->type) event->hw.config |= x86_pmu_get_event_config(event); if (event->attr.sample_period && x86_pmu.limit_period) { s64 left = event->attr.sample_period; x86_pmu.limit_period(event, &left); if (left > event->attr.sample_period) return -EINVAL; } /* sample_regs_user never support XMM registers */ if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK)) return -EINVAL; /* * Besides the general purpose registers, XMM registers may * be collected in PEBS on some platforms, e.g. Icelake */ if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) { if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS)) return -EINVAL; if (!event->attr.precise_ip) return -EINVAL; } return x86_setup_perfctr(event); } /* * Setup the hardware configuration for a given attr_type */ static int __x86_pmu_event_init(struct perf_event *event) { int err; if (!x86_pmu_initialized()) return -ENODEV; err = x86_reserve_hardware(); if (err) return err; atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; event->hw.last_cpu = -1; event->hw.last_tag = ~0ULL; /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; event->hw.branch_reg.idx = EXTRA_REG_NONE; return x86_pmu.hw_config(event); } void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { struct hw_perf_event *hwc = &cpuc->events[idx]->hw; u64 val; if (!test_bit(idx, cpuc->active_mask)) continue; rdmsrl(x86_pmu_config_addr(idx), val); if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu_config_addr(idx), val); if (is_counter_pair(hwc)) wrmsrl(x86_pmu_config_addr(idx + 1), 0); } } struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data) { return static_call(x86_pmu_guest_get_msrs)(nr, data); } EXPORT_SYMBOL_GPL(perf_guest_get_msrs); /* * There may be PMI landing after enabled=0. The PMI hitting could be before or * after disable_all. * * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. * It will not be re-enabled in the NMI handler again, because enabled=0. After * handling the NMI, disable_all will be called, which will not change the * state either. If PMI hits after disable_all, the PMU is already disabled * before entering NMI handler. The NMI handler will not change the state * either. * * So either situation is harmless. */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu_initialized()) return; if (!cpuc->enabled) return; cpuc->n_added = 0; cpuc->enabled = 0; barrier(); static_call(x86_pmu_disable_all)(); } void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { struct hw_perf_event *hwc = &cpuc->events[idx]->hw; if (!test_bit(idx, cpuc->active_mask)) continue; __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } } static inline int is_x86_event(struct perf_event *event) { int i; if (!is_hybrid()) return event->pmu == &pmu; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { if (event->pmu == &x86_pmu.hybrid_pmu[i].pmu) return true; } return false; } struct pmu *x86_get_pmu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); /* * All CPUs of the hybrid type have been offline. * The x86_get_pmu() should not be invoked. */ if (WARN_ON_ONCE(!cpuc->pmu)) return &pmu; return cpuc->pmu; } /* * Event scheduler state: * * Assign events iterating over all events and counters, beginning * with events with least weights first. Keep the current iterator * state in struct sched_state. */ struct sched_state { int weight; int event; /* event index */ int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ u64 used; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ #define SCHED_STATES_MAX 2 struct perf_sched { int max_weight; int max_events; int max_gp; int saved_states; struct event_constraint **constraints; struct sched_state state; struct sched_state saved[SCHED_STATES_MAX]; }; /* * Initialize iterator that runs through all events and counters. */ static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, int num, int wmin, int wmax, int gpmax) { int idx; memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; sched->max_gp = gpmax; sched->constraints = constraints; for (idx = 0; idx < num; idx++) { if (constraints[idx]->weight == wmin) break; } sched->state.event = idx; /* start with min weight */ sched->state.weight = wmin; sched->state.unassigned = num; } static void perf_sched_save_state(struct perf_sched *sched) { if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX)) return; sched->saved[sched->saved_states] = sched->state; sched->saved_states++; } static bool perf_sched_restore_state(struct perf_sched *sched) { if (!sched->saved_states) return false; sched->saved_states--; sched->state = sched->saved[sched->saved_states]; /* this assignment didn't work out */ /* XXX broken vs EVENT_PAIR */ sched->state.used &= ~BIT_ULL(sched->state.counter); /* try the next one */ sched->state.counter++; return true; } /* * Select a counter for the current event to schedule. Return true on * success. */ static bool __perf_sched_find_counter(struct perf_sched *sched) { struct event_constraint *c; int idx; if (!sched->state.unassigned) return false; if (sched->state.event >= sched->max_events) return false; c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { u64 mask = BIT_ULL(idx); if (sched->state.used & mask) continue; sched->state.used |= mask; goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { u64 mask = BIT_ULL(idx); if (c->flags & PERF_X86_EVENT_PAIR) mask |= mask << 1; if (sched->state.used & mask) continue; if (sched->state.nr_gp++ >= sched->max_gp) return false; sched->state.used |= mask; goto done; } return false; done: sched->state.counter = idx; if (c->overlap) perf_sched_save_state(sched); return true; } static bool perf_sched_find_counter(struct perf_sched *sched) { while (!__perf_sched_find_counter(sched)) { if (!perf_sched_restore_state(sched)) return false; } return true; } /* * Go through all unassigned events and find the next one to schedule. * Take events with the least weight first. Return true on success. */ static bool perf_sched_next_event(struct perf_sched *sched) { struct event_constraint *c; if (!sched->state.unassigned || !--sched->state.unassigned) return false; do { /* next event */ sched->state.event++; if (sched->state.event >= sched->max_events) { /* next weight */ sched->state.event = 0; sched->state.weight++; if (sched->state.weight > sched->max_weight) return false; } c = sched->constraints[sched->state.event]; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ return true; } /* * Assign a counter for each event. */ int perf_assign_events(struct event_constraint **constraints, int n, int wmin, int wmax, int gpmax, int *assign) { struct perf_sched sched; perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax); do { if (!perf_sched_find_counter(&sched)) break; /* failed */ if (assign) assign[sched.state.event] = sched.state.counter; } while (perf_sched_next_event(&sched)); return sched.state.unassigned; } EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; u64 used_mask = 0; /* * Compute the number of events already present; see x86_pmu_add(), * validate_group() and x86_pmu_commit_txn(). For the former two * cpuc->n_events hasn't been updated yet, while for the latter * cpuc->n_txn contains the number of events added in the current * transaction. */ n0 = cpuc->n_events; if (cpuc->txn_flags & PERF_PMU_TXN_ADD) n0 -= cpuc->n_txn; static_call_cond(x86_pmu_start_scheduling)(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { c = cpuc->event_constraint[i]; /* * Previously scheduled events should have a cached constraint, * while new events should not have one. */ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); /* * Request constraints for new events; or for those events that * have a dynamic constraint -- for those the constraint can * change due to external factors (sibling state, allow_tfa). */ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { c = static_call(x86_pmu_get_event_constraints)(cpuc, i, cpuc->event_list[i]); cpuc->event_constraint[i] = c; } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } /* * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { u64 mask; hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) break; /* constraint still honored */ if (!test_bit(hwc->idx, c->idxmsk)) break; mask = BIT_ULL(hwc->idx); if (is_counter_pair(hwc)) mask |= mask << 1; /* not already used */ if (used_mask & mask) break; used_mask |= mask; if (assign) assign[i] = hwc->idx; } /* slow path */ if (i != n) { int gpmax = x86_pmu_max_num_counters(cpuc->pmu); /* * Do not allow scheduling of more than half the available * generic counters. * * This helps avoid counter starvation of sibling thread by * ensuring at most half the counters cannot be in exclusive * mode. There is no designated counters for the limits. Any * N/2 counters can be used. This helps with events with * specific counter constraints. */ if (is_ht_workaround_enabled() && !cpuc->is_fake && READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; /* * Reduce the amount of available counters to allow fitting * the extra Merge events needed by large increment events. */ if (x86_pmu.flags & PMU_FL_PAIR) { gpmax -= cpuc->n_pair; WARN_ON(gpmax <= 0); } unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } /* * In case of success (unsched = 0), mark events as committed, * so we do not put_constraint() in case new events are added * and fail to be scheduled * * We invoke the lower level commit callback to lock the resource * * We do not need to do all of this in case we are called to * validate an event group (assign == NULL) */ if (!unsched && assign) { for (i = 0; i < n; i++) static_call_cond(x86_pmu_commit_scheduling)(cpuc, i, assign[i]); } else { for (i = n0; i < n; i++) { e = cpuc->event_list[i]; /* * release events that failed scheduling */ static_call_cond(x86_pmu_put_event_constraints)(cpuc, e); cpuc->event_constraint[i] = NULL; } } static_call_cond(x86_pmu_stop_scheduling)(cpuc); return unsched ? -EINVAL : 0; } static int add_nr_metric_event(struct cpu_hw_events *cpuc, struct perf_event *event) { if (is_metric_event(event)) { if (cpuc->n_metric == INTEL_TD_METRIC_NUM) return -EINVAL; cpuc->n_metric++; cpuc->n_txn_metric++; } return 0; } static void del_nr_metric_event(struct cpu_hw_events *cpuc, struct perf_event *event) { if (is_metric_event(event)) cpuc->n_metric--; } static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event, int max_count, int n) { union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap); if (intel_cap.perf_metrics && add_nr_metric_event(cpuc, event)) return -EINVAL; if (n >= max_count + cpuc->n_metric) return -EINVAL; cpuc->event_list[n] = event; if (is_counter_pair(&event->hw)) { cpuc->n_pair++; cpuc->n_txn_pair++; } return 0; } /* * dogrp: true if must collect siblings events (group) * returns total number of events and error code */ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp) { struct perf_event *event; int n, max_count; max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu); /* current number of events already accepted */ n = cpuc->n_events; if (!cpuc->n_events) cpuc->pebs_output = 0; if (!cpuc->is_fake && leader->attr.precise_ip) { /* * For PEBS->PT, if !aux_event, the group leader (PT) went * away, the group was broken down and this singleton event * can't schedule any more. */ if (is_pebs_pt(leader) && !leader->aux_event) return -EINVAL; /* * pebs_output: 0: no PEBS so far, 1: PT, 2: DS */ if (cpuc->pebs_output && cpuc->pebs_output != is_pebs_pt(leader) + 1) return -EINVAL; cpuc->pebs_output = is_pebs_pt(leader) + 1; } if (is_x86_event(leader)) { if (collect_event(cpuc, leader, max_count, n)) return -EINVAL; n++; } if (!dogrp) return n; for_each_sibling_event(event, leader) { if (!is_x86_event(event) || event->state <= PERF_EVENT_STATE_OFF) continue; if (collect_event(cpuc, event, max_count, n)) return -EINVAL; n++; } return n; } static inline void x86_assign_hw_event(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { struct hw_perf_event *hwc = &event->hw; int idx; idx = hwc->idx = cpuc->assign[i]; hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; static_call_cond(x86_pmu_assign)(event, idx); switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: hwc->config_base = 0; hwc->event_base = 0; break; case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: /* All the metric events are mapped onto the fixed counter 3. */ idx = INTEL_PMC_IDX_FIXED_SLOTS; fallthrough; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1: hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED); hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | INTEL_PMC_FIXED_RDPMC_BASE; break; default: hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx); break; } } /** * x86_perf_rdpmc_index - Return PMC counter used for event * @event: the perf_event to which the PMC counter was assigned * * The counter assigned to this performance event may change if interrupts * are enabled. This counter should thus never be used while interrupts are * enabled. Before this function is used to obtain the assigned counter the * event should be checked for validity using, for example, * perf_event_read_local(), within the same interrupt disabled section in * which this counter is planned to be used. * * Return: The index of the performance monitoring counter assigned to * @perf_event. */ int x86_perf_rdpmc_index(struct perf_event *event) { lockdep_assert_irqs_disabled(); return event->hw.event_base_rdpmc; } static inline int match_prev_assignment(struct hw_perf_event *hwc, struct cpu_hw_events *cpuc, int i) { return hwc->idx == cpuc->assign[i] && hwc->last_cpu == smp_processor_id() && hwc->last_tag == cpuc->tags[i]; } static void x86_pmu_start(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; int i, added = cpuc->n_added; if (!x86_pmu_initialized()) return; if (cpuc->enabled) return; if (cpuc->n_added) { int n_running = cpuc->n_events - cpuc->n_added; /* * apply assignment obtained either from * hw_perf_group_sched_in() or x86_pmu_enable() * * step1: save events moving to new counters */ for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; hwc = &event->hw; /* * we can avoid reprogramming counter if: * - assigned same counter as last time * - running on same CPU as last time * - no other event has used the counter since */ if (hwc->idx == -1 || match_prev_assignment(hwc, cpuc, i)) continue; /* * Ensure we don't accidentally enable a stopped * counter simply because we rescheduled. */ if (hwc->state & PERF_HES_STOPPED) hwc->state |= PERF_HES_ARCH; x86_pmu_stop(event, PERF_EF_UPDATE); } /* * step2: reprogram moved events into new counters */ for (i = 0; i < cpuc->n_events; i++) { event = cpuc->event_list[i]; hwc = &event->hw; if (!match_prev_assignment(hwc, cpuc, i)) x86_assign_hw_event(event, cpuc, i); else if (i < n_running) continue; if (hwc->state & PERF_HES_ARCH) continue; /* * if cpuc->enabled = 0, then no wrmsr as * per x86_pmu_enable_event() */ x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; perf_events_lapic_init(); } cpuc->enabled = 1; barrier(); static_call(x86_pmu_enable_all)(added); } DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; if (unlikely(!hwc->event_base)) return 0; /* * If we are way outside a reasonable range then just skip forward: */ if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } /* * Quirk: certain CPUs dont like it if just 1 hw_event is left: */ if (unlikely(left < 2)) left = 2; if (left > x86_pmu.max_period) left = x86_pmu.max_period; static_call_cond(x86_pmu_limit_period)(event, &left); this_cpu_write(pmc_prev_left[idx], left); /* * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ local64_set(&hwc->prev_count, (u64)-left); wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Sign extend the Merge event counter's upper 16 bits since * we currently declare a 48-bit counter width */ if (is_counter_pair(hwc)) wrmsrl(x86_pmu_event_addr(idx + 1), 0xffff); perf_event_update_userpage(event); return ret; } void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, ARCH_PERFMON_EVENTSEL_ENABLE); } /* * Add a single event to the PMU. * * The event is added to the group of enabled events * but only if it can be scheduled with existing events. */ static int x86_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc; int assign[X86_PMC_IDX_MAX]; int n, n0, ret; hwc = &event->hw; n0 = cpuc->n_events; ret = n = collect_events(cpuc, event, false); if (ret < 0) goto out; hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (!(flags & PERF_EF_START)) hwc->state |= PERF_HES_ARCH; /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. * * If commit fails, we'll call ->del() on all events * for which ->add() was called. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) goto out; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); done_collect: /* * Commit the collect_events() state. See x86_pmu_del() and * x86_pmu_*_txn(). */ cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; /* * This is before x86_pmu_enable() will call x86_pmu_start(), * so we enable LBRs before an event needs them etc.. */ static_call_cond(x86_pmu_add)(event); ret = 0; out: return ret; } static void x86_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = event->hw.idx; if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; if (WARN_ON_ONCE(idx == -1)) return; if (flags & PERF_EF_RELOAD) { WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); static_call(x86_pmu_set_period)(event); } event->hw.state = 0; cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); static_call(x86_pmu_enable)(event); perf_event_update_userpage(event); } void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; unsigned long *cntr_mask, *fixed_cntr_mask; struct event_constraint *pebs_constraints; struct cpu_hw_events *cpuc; u64 pebs, debugctl; int cpu, idx; guard(irqsave)(); cpu = smp_processor_id(); cpuc = &per_cpu(cpu_hw_events, cpu); cntr_mask = hybrid(cpuc->pmu, cntr_mask); fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask); pebs_constraints = hybrid(cpuc->pmu, pebs_constraints); if (!*(u64 *)cntr_mask) return; if (x86_pmu.version >= 2) { rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl); rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); if (pebs_constraints) { rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); } if (x86_pmu.lbr_nr) { rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl); } } pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) { rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl); rdmsrl(x86_pmu_event_addr(idx), pmc_count); prev_left = per_cpu(pmc_prev_left[idx], cpu); pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n", cpu, idx, pmc_ctrl); pr_info("CPU#%d: gen-PMC%d count: %016llx\n", cpu, idx, pmc_count); pr_info("CPU#%d: gen-PMC%d left: %016llx\n", cpu, idx, prev_left); } for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) { if (fixed_counter_disabled(idx, cpuc->pmu)) continue; rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", cpu, idx, pmc_count); } } void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; if (test_bit(hwc->idx, cpuc->active_mask)) { static_call(x86_pmu_disable)(event); __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ static_call(x86_pmu_update)(event); hwc->state |= PERF_HES_UPTODATE; } } static void x86_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap); int i; /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. * * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto do_del; __set_bit(event->hw.idx, cpuc->dirty); /* * Not a TXN, therefore cleanup properly. */ x86_pmu_stop(event, PERF_EF_UPDATE); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) break; } if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */ return; /* If we have a newly added event; make sure to decrease n_added. */ if (i >= cpuc->n_events - cpuc->n_added) --cpuc->n_added; static_call_cond(x86_pmu_put_event_constraints)(cpuc, event); /* Delete the array entry. */ while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; if (intel_cap.perf_metrics) del_nr_metric_event(cpuc, event); perf_event_update_userpage(event); do_del: /* * This is after x86_pmu_stop(); so we disable LBRs after any * event can need them etc.. */ static_call_cond(x86_pmu_del)(event); } int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; struct perf_event *event; int idx, handled = 0; u64 val; cpuc = this_cpu_ptr(&cpu_hw_events); /* * Some chipsets need to unmask the LVTPC in a particular spot * inside the nmi handler. As a result, the unmasking was pushed * into all the nmi handlers. * * This generic handler doesn't seem to have any issues where the * unmasking occurs so it was left at the top. */ apic_write(APIC_LVTPC, APIC_DM_NMI); for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { if (!test_bit(idx, cpuc->active_mask)) continue; event = cpuc->events[idx]; val = static_call(x86_pmu_update)(event); if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; /* * event overflow */ handled++; if (!static_call(x86_pmu_set_period)(event)) continue; perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } if (handled) inc_irq_stat(apic_perf_irqs); return handled; } void perf_events_lapic_init(void) { if (!x86_pmu.apic || !x86_pmu_initialized()) return; /* * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); } static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { u64 start_clock; u64 finish_clock; int ret; /* * All PMUs/events that share this PMI handler should make sure to * increment active_events for their events. */ if (!atomic_read(&active_events)) return NMI_DONE; start_clock = sched_clock(); ret = static_call(x86_pmu_handle_irq)(regs); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); return ret; } NOKPROBE_SYMBOL(perf_event_nmi_handler); struct event_constraint emptyconstraint; struct event_constraint unconstrained; static int x86_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) cpuc->kfree_on_online[i] = NULL; if (x86_pmu.cpu_prepare) return x86_pmu.cpu_prepare(cpu); return 0; } static int x86_pmu_dead_cpu(unsigned int cpu) { if (x86_pmu.cpu_dead) x86_pmu.cpu_dead(cpu); return 0; } static int x86_pmu_online_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) { kfree(cpuc->kfree_on_online[i]); cpuc->kfree_on_online[i] = NULL; } return 0; } static int x86_pmu_starting_cpu(unsigned int cpu) { if (x86_pmu.cpu_starting) x86_pmu.cpu_starting(cpu); return 0; } static int x86_pmu_dying_cpu(unsigned int cpu) { if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); return 0; } static void __init pmu_check_apic(void) { if (boot_cpu_has(X86_FEATURE_APIC)) return; x86_pmu.apic = 0; pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); pr_info("no hardware sampling interrupt available.\n"); /* * If we have a PMU initialized but no APIC * interrupts, we cannot sample hardware * events (user-space has to fall back and * sample via a hrtimer based software event): */ pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } static struct attribute_group x86_pmu_format_group __ro_after_init = { .name = "format", .attrs = NULL, }; ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); u64 config = 0; if (pmu_attr->id < x86_pmu.max_events) config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) return sprintf(page, "%s\n", pmu_attr->event_str); return x86_pmu.events_sysfs_show(page, config); } EXPORT_SYMBOL_GPL(events_sysfs_show); ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_ht_attr *pmu_attr = container_of(attr, struct perf_pmu_events_ht_attr, attr); /* * Report conditional events depending on Hyper-Threading. * * This is overly conservative as usually the HT special * handling is not needed if the other CPU thread is idle. * * Note this does not (and cannot) handle the case when thread * siblings are invisible, for example with virtualization * if they are owned by some other guest. The user tool * has to re-read when a thread sibling gets onlined later. */ return sprintf(page, "%s", topology_max_smt_threads() > 1 ? pmu_attr->event_str_ht : pmu_attr->event_str_noht); } ssize_t events_hybrid_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_hybrid_attr *pmu_attr = container_of(attr, struct perf_pmu_events_hybrid_attr, attr); struct x86_hybrid_pmu *pmu; const char *str, *next_str; int i; if (hweight64(pmu_attr->pmu_type) == 1) return sprintf(page, "%s", pmu_attr->event_str); /* * Hybrid PMUs may support the same event name, but with different * event encoding, e.g., the mem-loads event on an Atom PMU has * different event encoding from a Core PMU. * * The event_str includes all event encodings. Each event encoding * is divided by ";". The order of the event encodings must follow * the order of the hybrid PMU index. */ pmu = container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu); str = pmu_attr->event_str; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { if (!(x86_pmu.hybrid_pmu[i].pmu_type & pmu_attr->pmu_type)) continue; if (x86_pmu.hybrid_pmu[i].pmu_type & pmu->pmu_type) { next_str = strchr(str, ';'); if (next_str) return snprintf(page, next_str - str + 1, "%s", str); else return sprintf(page, "%s", str); } str = strchr(str, ';'); str++; } return 0; } EXPORT_SYMBOL_GPL(events_hybrid_sysfs_show); EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); EVENT_ATTR(cache-references, CACHE_REFERENCES ); EVENT_ATTR(cache-misses, CACHE_MISSES ); EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); EVENT_ATTR(branch-misses, BRANCH_MISSES ); EVENT_ATTR(bus-cycles, BUS_CYCLES ); EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); static struct attribute *empty_attrs; static struct attribute *events_attr[] = { EVENT_PTR(CPU_CYCLES), EVENT_PTR(INSTRUCTIONS), EVENT_PTR(CACHE_REFERENCES), EVENT_PTR(CACHE_MISSES), EVENT_PTR(BRANCH_INSTRUCTIONS), EVENT_PTR(BRANCH_MISSES), EVENT_PTR(BUS_CYCLES), EVENT_PTR(STALLED_CYCLES_FRONTEND), EVENT_PTR(STALLED_CYCLES_BACKEND), EVENT_PTR(REF_CPU_CYCLES), NULL, }; /* * Remove all undefined events (x86_pmu.event_map(id) == 0) * out of events_attr attributes. */ static umode_t is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; if (idx >= x86_pmu.max_events) return 0; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; } static struct attribute_group x86_pmu_events_group __ro_after_init = { .name = "events", .attrs = events_attr, .is_visible = is_visible, }; ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) { u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); ssize_t ret; /* * We have whole page size to spend and just little data * to write, so we can safely use sprintf. */ ret = sprintf(page, "event=0x%02llx", event); if (umask) ret += sprintf(page + ret, ",umask=0x%02llx", umask); if (edge) ret += sprintf(page + ret, ",edge"); if (pc) ret += sprintf(page + ret, ",pc"); if (any) ret += sprintf(page + ret, ",any"); if (inv) ret += sprintf(page + ret, ",inv"); if (cmask) ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); ret += sprintf(page + ret, "\n"); return ret; } static struct attribute_group x86_pmu_attr_group; static struct attribute_group x86_pmu_caps_group; static void x86_pmu_static_call_update(void) { static_call_update(x86_pmu_handle_irq, x86_pmu.handle_irq); static_call_update(x86_pmu_disable_all, x86_pmu.disable_all); static_call_update(x86_pmu_enable_all, x86_pmu.enable_all); static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); static_call_update(x86_pmu_assign, x86_pmu.assign); static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); static_call_update(x86_pmu_set_period, x86_pmu.set_period); static_call_update(x86_pmu_update, x86_pmu.update); static_call_update(x86_pmu_limit_period, x86_pmu.limit_period); static_call_update(x86_pmu_schedule_events, x86_pmu.schedule_events); static_call_update(x86_pmu_get_event_constraints, x86_pmu.get_event_constraints); static_call_update(x86_pmu_put_event_constraints, x86_pmu.put_event_constraints); static_call_update(x86_pmu_start_scheduling, x86_pmu.start_scheduling); static_call_update(x86_pmu_commit_scheduling, x86_pmu.commit_scheduling); static_call_update(x86_pmu_stop_scheduling, x86_pmu.stop_scheduling); static_call_update(x86_pmu_sched_task, x86_pmu.sched_task); static_call_update(x86_pmu_swap_task_ctx, x86_pmu.swap_task_ctx); static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs); static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases); static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs); static_call_update(x86_pmu_filter, x86_pmu.filter); } static void _x86_pmu_read(struct perf_event *event) { static_call(x86_pmu_update)(event); } void x86_pmu_show_pmu_cap(struct pmu *pmu) { pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu_num_counters(pmu)); pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask); pr_info("... max period: %016Lx\n", x86_pmu.max_period); pr_info("... fixed-purpose events: %d\n", x86_pmu_num_counters_fixed(pmu)); pr_info("... event mask: %016Lx\n", hybrid(pmu, intel_ctrl)); } static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; int err; pr_info("Performance Events: "); switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: err = intel_pmu_init(); break; case X86_VENDOR_AMD: err = amd_pmu_init(); break; case X86_VENDOR_HYGON: err = amd_pmu_init(); x86_pmu.name = "HYGON"; break; case X86_VENDOR_ZHAOXIN: case X86_VENDOR_CENTAUR: err = zhaoxin_pmu_init(); break; default: err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); err = 0; goto out_bad_pmu; } pmu_check_apic(); /* sanity check that the hardware exists or is emulated */ if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask)) goto out_bad_pmu; pr_cont("%s PMU driver.\n", x86_pmu.name); x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); if (!x86_pmu.intel_ctrl) x86_pmu.intel_ctrl = x86_pmu.cntr_mask64; if (!x86_pmu.config_mask) x86_pmu.config_mask = X86_RAW_EVENT_MASK; perf_events_lapic_init(); register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64, 0, x86_pmu_num_counters(NULL), 0, 0); x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; pmu.attr_update = x86_pmu.attr_update; if (!is_hybrid()) x86_pmu_show_pmu_cap(NULL); if (!x86_pmu.read) x86_pmu.read = _x86_pmu_read; if (!x86_pmu.guest_get_msrs) x86_pmu.guest_get_msrs = (void *)&__static_call_return0; if (!x86_pmu.set_period) x86_pmu.set_period = x86_perf_event_set_period; if (!x86_pmu.update) x86_pmu.update = x86_perf_event_update; x86_pmu_static_call_update(); /* * Install callbacks. Core will call them for each online * cpu. */ err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare", x86_pmu_prepare_cpu, x86_pmu_dead_cpu); if (err) return err; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING, "perf/x86:starting", x86_pmu_starting_cpu, x86_pmu_dying_cpu); if (err) goto out; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online", x86_pmu_online_cpu, NULL); if (err) goto out1; if (!is_hybrid()) { err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); if (err) goto out2; } else { struct x86_hybrid_pmu *hybrid_pmu; int i, j; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { hybrid_pmu = &x86_pmu.hybrid_pmu[i]; hybrid_pmu->pmu = pmu; hybrid_pmu->pmu.type = -1; hybrid_pmu->pmu.attr_update = x86_pmu.attr_update; hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE; err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name, (hybrid_pmu->pmu_type == hybrid_big) ? PERF_TYPE_RAW : -1); if (err) break; } if (i < x86_pmu.num_hybrid_pmus) { for (j = 0; j < i; j++) perf_pmu_unregister(&x86_pmu.hybrid_pmu[j].pmu); pr_warn("Failed to register hybrid PMUs\n"); kfree(x86_pmu.hybrid_pmu); x86_pmu.hybrid_pmu = NULL; x86_pmu.num_hybrid_pmus = 0; goto out2; } } return 0; out2: cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE); out1: cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING); out: cpuhp_remove_state(CPUHP_PERF_X86_PREPARE); out_bad_pmu: memset(&x86_pmu, 0, sizeof(x86_pmu)); return err; } early_initcall(init_hw_perf_events); static void x86_pmu_read(struct perf_event *event) { static_call(x86_pmu_read)(event); } /* * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time * * We only support PERF_PMU_TXN_ADD transactions. Save the * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD * transactions. */ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ cpuc->txn_flags = txn_flags; if (txn_flags & ~PERF_PMU_TXN_ADD) return; perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); __this_cpu_write(cpu_hw_events.n_txn_pair, 0); __this_cpu_write(cpu_hw_events.n_txn_metric, 0); } /* * Stop group events scheduling transaction * Clear the flag and pmu::enable() will perform the * schedulability test. */ static void x86_pmu_cancel_txn(struct pmu *pmu) { unsigned int txn_flags; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ txn_flags = cpuc->txn_flags; cpuc->txn_flags = 0; if (txn_flags & ~PERF_PMU_TXN_ADD) return; /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_pair, __this_cpu_read(cpu_hw_events.n_txn_pair)); __this_cpu_sub(cpu_hw_events.n_metric, __this_cpu_read(cpu_hw_events.n_txn_metric)); perf_pmu_enable(pmu); } /* * Commit group events scheduling transaction * Perform the group schedulability test as a whole * Return 0 if success * * Does not cancel the transaction on failure; expects the caller to do this. */ static int x86_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int assign[X86_PMC_IDX_MAX]; int n, ret; WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { cpuc->txn_flags = 0; return 0; } n = cpuc->n_events; if (!x86_pmu_initialized()) return -EAGAIN; ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) return ret; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } /* * a fake_cpuc is used to validate event groups. Due to * the extra reg logic, we need to also allocate a fake * per_core and per_cpu structure. Otherwise, group events * using extra reg may conflict without the kernel being * able to catch this when the last event gets added to * the group. */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { intel_cpuc_finish(cpuc); kfree(cpuc); } static struct cpu_hw_events *allocate_fake_cpuc(struct pmu *event_pmu) { struct cpu_hw_events *cpuc; int cpu; cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); if (!cpuc) return ERR_PTR(-ENOMEM); cpuc->is_fake = 1; if (is_hybrid()) { struct x86_hybrid_pmu *h_pmu; h_pmu = hybrid_pmu(event_pmu); if (cpumask_empty(&h_pmu->supported_cpus)) goto error; cpu = cpumask_first(&h_pmu->supported_cpus); } else cpu = raw_smp_processor_id(); cpuc->pmu = event_pmu; if (intel_cpuc_prepare(cpuc, cpu)) goto error; return cpuc; error: free_fake_cpuc(cpuc); return ERR_PTR(-ENOMEM); } /* * validate that we can schedule this event */ static int validate_event(struct perf_event *event) { struct cpu_hw_events *fake_cpuc; struct event_constraint *c; int ret = 0; fake_cpuc = allocate_fake_cpuc(event->pmu); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(fake_cpuc, event); free_fake_cpuc(fake_cpuc); return ret; } /* * validate a single event group * * validation include: * - check events are compatible which each other * - events do not compete for the same counter * - number of events <= number of counters * * validation ensures the group can be loaded onto the * PMU if it was the only group available. */ static int validate_group(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct cpu_hw_events *fake_cpuc; int ret = -EINVAL, n; /* * Reject events from different hybrid PMUs. */ if (is_hybrid()) { struct perf_event *sibling; struct pmu *pmu = NULL; if (is_x86_event(leader)) pmu = leader->pmu; for_each_sibling_event(sibling, leader) { if (!is_x86_event(sibling)) continue; if (!pmu) pmu = sibling->pmu; else if (pmu != sibling->pmu) return ret; } } fake_cpuc = allocate_fake_cpuc(event->pmu); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); /* * the event is not yet connected with its * siblings therefore we must first collect * existing siblings, then add the new event * before we can simulate the scheduling */ n = collect_events(fake_cpuc, leader, true); if (n < 0) goto out; fake_cpuc->n_events = n; n = collect_events(fake_cpuc, event, false); if (n < 0) goto out; fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: free_fake_cpuc(fake_cpuc); return ret; } static int x86_pmu_event_init(struct perf_event *event) { struct x86_hybrid_pmu *pmu = NULL; int err; if ((event->attr.type != event->pmu->type) && (event->attr.type != PERF_TYPE_HARDWARE) && (event->attr.type != PERF_TYPE_HW_CACHE)) return -ENOENT; if (is_hybrid() && (event->cpu != -1)) { pmu = hybrid_pmu(event->pmu); if (!cpumask_test_cpu(event->cpu, &pmu->supported_cpus)) return -ENOENT; } err = __x86_pmu_event_init(event); if (!err) { if (event->group_leader != event) err = validate_group(event); else err = validate_event(event); } if (err) { if (event->destroy) event->destroy(event); event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; return err; } void perf_clear_dirty_counters(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; /* Don't need to clear the assigned counter. */ for (i = 0; i < cpuc->n_events; i++) __clear_bit(cpuc->assign[i], cpuc->dirty); if (bitmap_empty(cpuc->dirty, X86_PMC_IDX_MAX)) return; for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) { if (i >= INTEL_PMC_IDX_FIXED) { /* Metrics and fake events don't have corresponding HW counters. */ if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask))) continue; wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0); } else { wrmsrl(x86_pmu_event_addr(i), 0); } } bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX); } static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; /* * This function relies on not being called concurrently in two * tasks in the same mm. Otherwise one task could observe * perf_rdpmc_allowed > 1 and return all the way back to * userspace with CR4.PCE clear while another task is still * doing on_each_cpu_mask() to propagate CR4.PCE. * * For now, this can't happen because all callers hold mmap_lock * for write. If this changes, we'll need a different solution. */ mmap_assert_write_locked(mm); if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1); } static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; if (!(hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) return 0; if (is_metric_idx(hwc->idx)) return INTEL_PMC_FIXED_RDPMC_METRICS + 1; else return hwc->event_base_rdpmc + 1; } static ssize_t get_attr_rdpmc(struct device *cdev, struct device_attribute *attr, char *buf) { return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc); } static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { static DEFINE_MUTEX(rdpmc_mutex); unsigned long val; ssize_t ret; ret = kstrtoul(buf, 0, &val); if (ret) return ret; if (val > 2) return -EINVAL; if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; guard(mutex)(&rdpmc_mutex); if (val != x86_pmu.attr_rdpmc) { /* * Changing into or out of never available or always available, * aka perf-event-bypassing mode. This path is extremely slow, * but only root can trigger it, so it's okay. */ if (val == 0) static_branch_inc(&rdpmc_never_available_key); else if (x86_pmu.attr_rdpmc == 0) static_branch_dec(&rdpmc_never_available_key); if (val == 2) static_branch_inc(&rdpmc_always_available_key); else if (x86_pmu.attr_rdpmc == 2) static_branch_dec(&rdpmc_always_available_key); on_each_cpu(cr4_update_pce, NULL, 1); x86_pmu.attr_rdpmc = val; } return count; } static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc); static struct attribute *x86_pmu_attrs[] = { &dev_attr_rdpmc.attr, NULL, }; static struct attribute_group x86_pmu_attr_group __ro_after_init = { .attrs = x86_pmu_attrs, }; static ssize_t max_precise_show(struct device *cdev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise()); } static DEVICE_ATTR_RO(max_precise); static struct attribute *x86_pmu_caps_attrs[] = { &dev_attr_max_precise.attr, NULL }; static struct attribute_group x86_pmu_caps_group __ro_after_init = { .name = "caps", .attrs = x86_pmu_caps_attrs, }; static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, &x86_pmu_events_group, &x86_pmu_caps_group, NULL, }; static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { static_call_cond(x86_pmu_sched_task)(pmu_ctx, sched_in); } static void x86_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc) { static_call_cond(x86_pmu_swap_task_ctx)(prev_epc, next_epc); } void perf_check_microcode(void) { if (x86_pmu.check_microcode) x86_pmu.check_microcode(); } static int x86_pmu_check_period(struct perf_event *event, u64 value) { if (x86_pmu.check_period && x86_pmu.check_period(event, value)) return -EINVAL; if (value && x86_pmu.limit_period) { s64 left = value; x86_pmu.limit_period(event, &left); if (left > value) return -EINVAL; } return 0; } static int x86_pmu_aux_output_match(struct perf_event *event) { if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT)) return 0; if (x86_pmu.aux_output_match) return x86_pmu.aux_output_match(event); return 0; } static bool x86_pmu_filter(struct pmu *pmu, int cpu) { bool ret = false; static_call_cond(x86_pmu_filter)(pmu, cpu, &ret); return ret; } static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, .attr_groups = x86_pmu_attr_groups, .event_init = x86_pmu_event_init, .event_mapped = x86_pmu_event_mapped, .event_unmapped = x86_pmu_event_unmapped, .add = x86_pmu_add, .del = x86_pmu_del, .start = x86_pmu_start, .stop = x86_pmu_stop, .read = x86_pmu_read, .start_txn = x86_pmu_start_txn, .cancel_txn = x86_pmu_cancel_txn, .commit_txn = x86_pmu_commit_txn, .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .swap_task_ctx = x86_pmu_swap_task_ctx, .check_period = x86_pmu_check_period, .aux_output_match = x86_pmu_aux_output_match, .filter = x86_pmu_filter, }; void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); userpg->pmc_width = x86_pmu.cntval_bits; if (!using_native_sched_clock() || !sched_clock_stable()) return; cyc2ns_read_begin(&data); offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; userpg->time_mult = data.cyc2ns_mul; userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different * time base for the records. */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; userpg->time_zero = offset; } cyc2ns_read_end(); } /* * Determine whether the regs were taken from an irq/exception handler rather * than from perf_arch_fetch_caller_regs(). */ static bool perf_hw_regs(struct pt_regs *regs) { return regs->flags & X86_EFLAGS_FIXED; } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; unsigned long addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } if (perf_callchain_store(entry, regs->ip)) return; if (perf_hw_regs(regs)) unwind_start(&state, current, regs, NULL); else unwind_start(&state, current, NULL, (void *)regs->sp); for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; } } static inline int valid_user_frame(const void __user *fp, unsigned long size) { return __access_ok(fp, size); } static unsigned long get_segment_base(unsigned int segment) { struct desc_struct *desc; unsigned int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; #else return 0; #endif } else { if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; } return get_desc_base(desc); } #ifdef CONFIG_UPROBES /* * Heuristic-based check if uprobe is installed at the function entry. * * Under assumption of user code being compiled with frame pointers, * `push %rbp/%ebp` is a good indicator that we indeed are. * * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. * If we get this wrong, captured stack trace might have one extra bogus * entry, but the rest of stack trace will still be meaningful. */ static bool is_uprobe_at_func_entry(struct pt_regs *regs) { struct arch_uprobe *auprobe; if (!current->utask) return false; auprobe = current->utask->auprobe; if (!auprobe) return false; /* push %rbp/%ebp */ if (auprobe->insn[0] == 0x55) return true; /* endbr64 (64-bit only) */ if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) return true; return false; } #else static bool is_uprobe_at_func_entry(struct pt_regs *regs) { return false; } #endif /* CONFIG_UPROBES */ #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { /* 32-bit process in 64-bit kernel. */ unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; u32 ret_addr; if (user_64bit_mode(regs)) return 0; cs_base = get_segment_base(regs->cs); ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); /* see perf_callchain_user() below for why we do this */ if (is_uprobe_at_func_entry(regs) && !get_user(ret_addr, (const u32 __user *)regs->sp)) perf_callchain_store(entry, ret_addr); while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; if (__get_user(frame.next_frame, &fp->next_frame)) break; if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } pagefault_enable(); return 1; } #else static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { return 0; } #endif void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; const struct stack_frame __user *fp; unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } /* * We don't know what to do with VM86 stacks.. ignore them for now. */ if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); if (!nmi_uaccess_okay()) return; if (perf_callchain_user32(regs, entry)) return; pagefault_disable(); /* * If we are called from uprobe handler, and we are indeed at the very * entry to user function (which is normally a `push %rbp` instruction, * under assumption of application being compiled with frame pointers), * we should read return address from *regs->sp before proceeding * to follow frame pointers, otherwise we'll skip immediate caller * as %rbp is not yet setup. */ if (is_uprobe_at_func_entry(regs) && !get_user(ret_addr, (const unsigned long __user *)regs->sp)) perf_callchain_store(entry, ret_addr); while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; if (__get_user(frame.next_frame, &fp->next_frame)) break; if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, frame.return_address); fp = (void __user *)frame.next_frame; } pagefault_enable(); } /* * Deal with code segment offsets for the various execution modes: * * VM86 - the good olde 16 bit days, where the linear address is * 20 bits and we use regs->ip + 0x10 * regs->cs. * * IA32 - Where we need to look at GDT/LDT segment descriptor tables * to figure out what the 32bit base address is. * * X32 - has TIF_X32 set, but is running in x86_64 * * X86_64 - CS,DS,SS,ES are all zero based. */ static unsigned long code_segment_base(struct pt_regs *regs) { /* * For IA32 we look at the GDT/LDT segment base to convert the * effective IP to a linear address. */ #ifdef CONFIG_X86_32 /* * If we are in VM86 mode, add the segment offset to convert to a * linear address. */ if (regs->flags & X86_VM_MASK) return 0x10 * regs->cs; if (user_mode(regs) && regs->cs != __USER_CS) return get_segment_base(regs->cs); #else if (user_mode(regs) && !user_64bit_mode(regs) && regs->cs != __USER32_CS) return get_segment_base(regs->cs); #endif return 0; } unsigned long perf_instruction_pointer(struct pt_regs *regs) { if (perf_guest_state()) return perf_guest_get_ip(); return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { unsigned int guest_state = perf_guest_state(); int misc = 0; if (guest_state) { if (guest_state & PERF_GUEST_USER) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { if (user_mode(regs)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; } if (regs->flags & PERF_EFLAGS_EXACT) misc |= PERF_RECORD_MISC_EXACT_IP; return misc; } void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { /* This API doesn't currently support enumerating hybrid PMUs. */ if (WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) || !x86_pmu_initialized()) { memset(cap, 0, sizeof(*cap)); return; } /* * Note, hybrid CPU models get tracked as having hybrid PMUs even when * all E-cores are disabled via BIOS. When E-cores are disabled, the * base PMU holds the correct number of counters for P-cores. */ cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu_num_counters(NULL); cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL); cap->bit_width_gp = x86_pmu.cntval_bits; cap->bit_width_fixed = x86_pmu.cntval_bits; cap->events_mask = (unsigned int)x86_pmu.events_maskl; cap->events_mask_len = x86_pmu.events_mask_len; cap->pebs_ept = x86_pmu.pebs_ept; } EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability); u64 perf_get_hw_event_config(int hw_event) { int max = x86_pmu.max_events; if (hw_event < max) return x86_pmu.event_map(array_index_nospec(hw_event, max)); return 0; } EXPORT_SYMBOL_GPL(perf_get_hw_event_config);
35 35 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_ftp.c: IPVS ftp application module * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: * * Most code here is taken from ip_masq_ftp.c in kernel 2.2. The difference * is that ip_vs_ftp module handles the reverse direction to ip_masq_ftp. * * IP_MASQ_FTP ftp masquerading module * * Version: @(#)ip_masq_ftp.c 0.04 02/05/96 * * Author: Wouter Gadeyne */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #include <linux/gfp.h> #include <net/protocol.h> #include <net/tcp.h> #include <linux/unaligned.h> #include <net/ip_vs.h> #define SERVER_STRING_PASV "227 " #define CLIENT_STRING_PORT "PORT" #define SERVER_STRING_EPSV "229 " #define CLIENT_STRING_EPRT "EPRT" enum { IP_VS_FTP_ACTIVE = 0, IP_VS_FTP_PORT = 0, IP_VS_FTP_PASV, IP_VS_FTP_EPRT, IP_VS_FTP_EPSV, }; /* * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper * First port is set to the default port. */ static unsigned int ports_count = 1; static unsigned short ports[IP_VS_APP_MAX_PORTS] = {21, 0}; module_param_array(ports, ushort, &ports_count, 0444); MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands"); static char *ip_vs_ftp_data_ptr(struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { struct tcphdr *th = (struct tcphdr *)((char *)skb->data + ipvsh->len); if ((th->doff << 2) < sizeof(struct tcphdr)) return NULL; return (char *)th + (th->doff << 2); } static int ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) { /* We use connection tracking for the command connection */ cp->flags |= IP_VS_CONN_F_NFCT; return 0; } static int ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) { return 0; } /* Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started * with the "pattern". <addr,port> is in network order. * Parse extended format depending on ext. In this case addr can be pre-set. */ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, const char *pattern, size_t plen, char skip, bool ext, int mode, union nf_inet_addr *addr, __be16 *port, __u16 af, char **start, char **end) { char *s, c; unsigned char p[6]; char edelim; __u16 hport; int i = 0; if (data_limit - data < plen) { /* check if there is partial match */ if (strncasecmp(data, pattern, data_limit - data) == 0) return -1; else return 0; } if (strncasecmp(data, pattern, plen) != 0) { return 0; } s = data + plen; if (skip) { bool found = false; for (;; s++) { if (s == data_limit) return -1; if (!found) { /* "(" is optional for non-extended format, * so catch the start of IPv4 address */ if (!ext && isdigit(*s)) break; if (*s == skip) found = true; } else if (*s != skip) { break; } } } /* Old IPv4-only format? */ if (!ext) { p[0] = 0; for (data = s; ; data++) { if (data == data_limit) return -1; c = *data; if (isdigit(c)) { p[i] = p[i]*10 + c - '0'; } else if (c == ',' && i < 5) { i++; p[i] = 0; } else { /* unexpected character or terminator */ break; } } if (i != 5) return -1; *start = s; *end = data; addr->ip = get_unaligned((__be32 *) p); *port = get_unaligned((__be16 *) (p + 4)); return 1; } if (s == data_limit) return -1; *start = s; edelim = *s++; if (edelim < 33 || edelim > 126) return -1; if (s == data_limit) return -1; if (*s == edelim) { /* Address family is usually missing for EPSV response */ if (mode != IP_VS_FTP_EPSV) return -1; s++; if (s == data_limit) return -1; /* Then address should be missing too */ if (*s != edelim) return -1; /* Caller can pre-set addr, if needed */ s++; } else { const char *ep; /* We allow address only from same family */ if (af == AF_INET6 && *s != '2') return -1; if (af == AF_INET && *s != '1') return -1; s++; if (s == data_limit) return -1; if (*s != edelim) return -1; s++; if (s == data_limit) return -1; if (af == AF_INET6) { if (in6_pton(s, data_limit - s, (u8 *)addr, edelim, &ep) <= 0) return -1; } else { if (in4_pton(s, data_limit - s, (u8 *)addr, edelim, &ep) <= 0) return -1; } s = (char *) ep; if (s == data_limit) return -1; if (*s != edelim) return -1; s++; } for (hport = 0; ; s++) { if (s == data_limit) return -1; if (!isdigit(*s)) break; hport = hport * 10 + *s - '0'; } if (s == data_limit || !hport || *s != edelim) return -1; s++; *end = s; *port = htons(hport); return 1; } /* Look at outgoing ftp packets to catch the response to a PASV/EPSV command * from the server (inside-to-outside). * When we see one, we build a connection entry with the client address, * client port 0 (unknown at the moment), the server address and the * server port. Mark the current connection entry as a control channel * of the new entry. All this work is just to make the data connection * can be scheduled to the right server later. * * The outgoing packet should be something like * "227 Entering Passive Mode (xxx,xxx,xxx,xxx,ppp,ppp)". * xxx,xxx,xxx,xxx is the server address, ppp,ppp is the server port number. * The extended format for EPSV response provides usually only port: * "229 Entering Extended Passive Mode (|||ppp|)" */ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct sk_buff *skb, int *diff, struct ip_vs_iphdr *ipvsh) { char *data, *data_limit; char *start, *end; union nf_inet_addr from; __be16 port; struct ip_vs_conn *n_cp; char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */ unsigned int buf_len; int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; *diff = 0; /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; /* Linear packets are much easier to deal with. */ if (skb_ensure_writable(skb, skb->len)) return 0; if (cp->app_data == (void *) IP_VS_FTP_PASV) { data = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING_PASV, sizeof(SERVER_STRING_PASV)-1, '(', false, IP_VS_FTP_PASV, &from, &port, cp->af, &start, &end) != 1) return 1; IP_VS_DBG(7, "PASV response (%pI4:%u) -> %pI4:%u detected\n", &from.ip, ntohs(port), &cp->caddr.ip, 0); } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { data = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; /* Usually, data address is not specified but * we support different address, so pre-set it. */ from = cp->daddr; if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING_EPSV, sizeof(SERVER_STRING_EPSV)-1, '(', true, IP_VS_FTP_EPSV, &from, &port, cp->af, &start, &end) != 1) return 1; IP_VS_DBG_BUF(7, "EPSV response (%s:%u) -> %s:%u detected\n", IP_VS_DBG_ADDR(cp->af, &from), ntohs(port), IP_VS_DBG_ADDR(cp->af, &cp->caddr), 0); } else { return 1; } /* Now update or create a connection entry for it */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &from, port, &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &cp->caddr, 0, &cp->vaddr, port, &p); n_cp = ip_vs_conn_new(&p, cp->af, &from, port, IP_VS_CONN_F_NO_CPORT | IP_VS_CONN_F_NFCT, cp->dest, skb->mark); if (!n_cp) return 0; /* add its controller */ ip_vs_control_add(n_cp, cp); } /* Replace the old passive address with the new one */ if (cp->app_data == (void *) IP_VS_FTP_PASV) { from.ip = n_cp->vaddr.ip; port = n_cp->vport; snprintf(buf, sizeof(buf), "%u,%u,%u,%u,%u,%u", ((unsigned char *)&from.ip)[0], ((unsigned char *)&from.ip)[1], ((unsigned char *)&from.ip)[2], ((unsigned char *)&from.ip)[3], ntohs(port) >> 8, ntohs(port) & 0xFF); } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { from = n_cp->vaddr; port = n_cp->vport; /* Only port, client will use VIP for the data connection */ snprintf(buf, sizeof(buf), "|||%u|", ntohs(port)); } else { *buf = 0; } buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); if (ct) { bool mangled; /* If mangling fails this function will return 0 * which will cause the packet to be dropped. * Mangling can only fail under memory pressure, * hopefully it will succeed on the retransmitted * packet. */ mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, ipvsh->len, start - data, end - start, buf, buf_len); if (mangled) { ip_vs_nfct_expect_related(skb, ct, n_cp, ipvsh->protocol, 0, 0); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_UNNECESSARY; /* csum is updated */ ret = 1; } } /* Not setting 'diff' is intentional, otherwise the sequence * would be adjusted twice. */ cp->app_data = (void *) IP_VS_FTP_ACTIVE; ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return ret; } /* Look at incoming ftp packets to catch the PASV/PORT/EPRT/EPSV command * (outside-to-inside). * * The incoming packet having the PORT command should be something like * "PORT xxx,xxx,xxx,xxx,ppp,ppp\n". * xxx,xxx,xxx,xxx is the client address, ppp,ppp is the client port number. * In this case, we create a connection entry using the client address and * port, so that the active ftp data connection from the server can reach * the client. * Extended format: * "EPSV\r\n" when client requests server address from same family * "EPSV 1\r\n" when client requests IPv4 server address * "EPSV 2\r\n" when client requests IPv6 server address * "EPSV ALL\r\n" - not supported * EPRT with specified delimiter (ASCII 33..126), "|" by default: * "EPRT |1|IPv4ADDR|PORT|\r\n" when client provides IPv4 addrport * "EPRT |2|IPv6ADDR|PORT|\r\n" when client provides IPv6 addrport */ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct sk_buff *skb, int *diff, struct ip_vs_iphdr *ipvsh) { char *data, *data_start, *data_limit; char *start, *end; union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; /* no diff required for incoming packets */ *diff = 0; /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; /* Linear packets are much easier to deal with. */ if (skb_ensure_writable(skb, skb->len)) return 0; data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; while (data <= data_limit - 6) { if (cp->af == AF_INET && strncasecmp(data, "PASV\r\n", 6) == 0) { /* Passive mode on */ IP_VS_DBG(7, "got PASV at %td of %td\n", data - data_start, data_limit - data_start); cp->app_data = (void *) IP_VS_FTP_PASV; return 1; } /* EPSV or EPSV<space><net-prt> */ if (strncasecmp(data, "EPSV", 4) == 0 && (data[4] == ' ' || data[4] == '\r')) { if (data[4] == ' ') { char proto = data[5]; if (data > data_limit - 7 || data[6] != '\r') return 1; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && proto == '2') { } else #endif if (cp->af == AF_INET && proto == '1') { } else { return 1; } } /* Extended Passive mode on */ IP_VS_DBG(7, "got EPSV at %td of %td\n", data - data_start, data_limit - data_start); cp->app_data = (void *) IP_VS_FTP_EPSV; return 1; } data++; } /* * To support virtual FTP server, the scenerio is as follows: * FTP client ----> Load Balancer ----> FTP server * First detect the port number in the application data, * then create a new connection entry for the coming data * connection. */ if (cp->af == AF_INET && ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING_PORT, sizeof(CLIENT_STRING_PORT)-1, ' ', false, IP_VS_FTP_PORT, &to, &port, cp->af, &start, &end) == 1) { IP_VS_DBG(7, "PORT %pI4:%u detected\n", &to.ip, ntohs(port)); /* Now update or create a connection entry for it */ IP_VS_DBG(7, "protocol %s %pI4:%u %pI4:%u\n", ip_vs_proto_name(ipvsh->protocol), &to.ip, ntohs(port), &cp->vaddr.ip, ntohs(cp->vport)-1); } else if (ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING_EPRT, sizeof(CLIENT_STRING_EPRT)-1, ' ', true, IP_VS_FTP_EPRT, &to, &port, cp->af, &start, &end) == 1) { IP_VS_DBG_BUF(7, "EPRT %s:%u detected\n", IP_VS_DBG_ADDR(cp->af, &to), ntohs(port)); /* Now update or create a connection entry for it */ IP_VS_DBG_BUF(7, "protocol %s %s:%u %s:%u\n", ip_vs_proto_name(ipvsh->protocol), IP_VS_DBG_ADDR(cp->af, &to), ntohs(port), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport)-1); } else { return 1; } /* Passive mode off */ cp->app_data = (void *) IP_VS_FTP_ACTIVE; { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); if (!n_cp) { n_cp = ip_vs_conn_new(&p, cp->af, &cp->daddr, htons(ntohs(cp->dport)-1), IP_VS_CONN_F_NFCT, cp->dest, skb->mark); if (!n_cp) return 0; /* add its controller */ ip_vs_control_add(n_cp, cp); } } /* * Move tunnel to listen state */ ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return 1; } static struct ip_vs_app ip_vs_ftp = { .name = "ftp", .type = IP_VS_APP_TYPE_FTP, .protocol = IPPROTO_TCP, .module = THIS_MODULE, .incs_list = LIST_HEAD_INIT(ip_vs_ftp.incs_list), .init_conn = ip_vs_ftp_init_conn, .done_conn = ip_vs_ftp_done_conn, .bind_conn = NULL, .unbind_conn = NULL, .pkt_out = ip_vs_ftp_out, .pkt_in = ip_vs_ftp_in, }; /* * per netns ip_vs_ftp initialization */ static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; struct ip_vs_app *app; struct netns_ipvs *ipvs = net_ipvs(net); if (!ipvs) return -ENOENT; app = register_ip_vs_app(ipvs, &ip_vs_ftp); if (IS_ERR(app)) return PTR_ERR(app); for (i = 0; i < ports_count; i++) { if (!ports[i]) continue; ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; } return 0; err_unreg: unregister_ip_vs_app(ipvs, &ip_vs_ftp); return ret; } /* * netns exit */ static void __ip_vs_ftp_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); if (!ipvs) return; unregister_ip_vs_app(ipvs, &ip_vs_ftp); } static struct pernet_operations ip_vs_ftp_ops = { .init = __ip_vs_ftp_init, .exit = __ip_vs_ftp_exit, }; static int __init ip_vs_ftp_init(void) { /* rcu_barrier() is called by netns on error */ return register_pernet_subsys(&ip_vs_ftp_ops); } /* * ip_vs_ftp finish. */ static void __exit ip_vs_ftp_exit(void) { unregister_pernet_subsys(&ip_vs_ftp_ops); /* rcu_barrier() is called by netns */ } module_init(ip_vs_ftp_init); module_exit(ip_vs_ftp_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs ftp helper");
1 1 5 5 3 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; BPDU handling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netfilter_bridge.h> #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/stp.h> #include <linux/unaligned.h> #include "br_private.h" #include "br_private_stp.h" #define STP_HZ 256 #define LLC_RESERVE sizeof(struct llc_pdu_un) static int br_send_bpdu_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } static void br_send_bpdu(struct net_bridge_port *p, const unsigned char *data, int length) { struct sk_buff *skb; skb = dev_alloc_skb(length+LLC_RESERVE); if (!skb) return; skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); __skb_put_data(skb, data, length); llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); skb_reset_mac_header(skb); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(p->dev), NULL, skb, NULL, skb->dev, br_send_bpdu_finish); } static inline void br_set_ticks(unsigned char *dest, int j) { unsigned long ticks = (STP_HZ * j)/ HZ; put_unaligned_be16(ticks, dest); } static inline int br_get_ticks(const unsigned char *src) { unsigned long ticks = get_unaligned_be16(src); return DIV_ROUND_UP(ticks * HZ, STP_HZ); } /* called under bridge lock */ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) { unsigned char buf[35]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_CONFIG; buf[4] = (bpdu->topology_change ? 0x01 : 0) | (bpdu->topology_change_ack ? 0x80 : 0); buf[5] = bpdu->root.prio[0]; buf[6] = bpdu->root.prio[1]; buf[7] = bpdu->root.addr[0]; buf[8] = bpdu->root.addr[1]; buf[9] = bpdu->root.addr[2]; buf[10] = bpdu->root.addr[3]; buf[11] = bpdu->root.addr[4]; buf[12] = bpdu->root.addr[5]; buf[13] = (bpdu->root_path_cost >> 24) & 0xFF; buf[14] = (bpdu->root_path_cost >> 16) & 0xFF; buf[15] = (bpdu->root_path_cost >> 8) & 0xFF; buf[16] = bpdu->root_path_cost & 0xFF; buf[17] = bpdu->bridge_id.prio[0]; buf[18] = bpdu->bridge_id.prio[1]; buf[19] = bpdu->bridge_id.addr[0]; buf[20] = bpdu->bridge_id.addr[1]; buf[21] = bpdu->bridge_id.addr[2]; buf[22] = bpdu->bridge_id.addr[3]; buf[23] = bpdu->bridge_id.addr[4]; buf[24] = bpdu->bridge_id.addr[5]; buf[25] = (bpdu->port_id >> 8) & 0xFF; buf[26] = bpdu->port_id & 0xFF; br_set_ticks(buf+27, bpdu->message_age); br_set_ticks(buf+29, bpdu->max_age); br_set_ticks(buf+31, bpdu->hello_time); br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ void br_send_tcn_bpdu(struct net_bridge_port *p) { unsigned char buf[4]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); p->stp_xstats.tx_tcn++; } /* * Called from llc. * * NO locks, but rcu_read_lock */ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; if (!pskb_may_pull(skb, 4)) goto err; /* compare of protocol id and version */ buf = skb->data; if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; p = br_port_get_check_rcu(dev); if (!p) goto err; br = p->br; spin_lock(&br->lock); if (br->stp_enabled != BR_KERNEL_STP) goto out; if (!(br->dev->flags & IFF_UP)) goto out; if (p->state == BR_STATE_DISABLED) goto out; if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out; if (p->flags & BR_BPDU_GUARD) { br_notice(br, "BPDU received on blocked port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); br_stp_disable_port(p); goto out; } buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; if (!pskb_may_pull(skb, 32)) goto out; buf = skb->data; bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0; bpdu.topology_change_ack = (buf[1] & 0x80) ? 1 : 0; bpdu.root.prio[0] = buf[2]; bpdu.root.prio[1] = buf[3]; bpdu.root.addr[0] = buf[4]; bpdu.root.addr[1] = buf[5]; bpdu.root.addr[2] = buf[6]; bpdu.root.addr[3] = buf[7]; bpdu.root.addr[4] = buf[8]; bpdu.root.addr[5] = buf[9]; bpdu.root_path_cost = (buf[10] << 24) | (buf[11] << 16) | (buf[12] << 8) | buf[13]; bpdu.bridge_id.prio[0] = buf[14]; bpdu.bridge_id.prio[1] = buf[15]; bpdu.bridge_id.addr[0] = buf[16]; bpdu.bridge_id.addr[1] = buf[17]; bpdu.bridge_id.addr[2] = buf[18]; bpdu.bridge_id.addr[3] = buf[19]; bpdu.bridge_id.addr[4] = buf[20]; bpdu.bridge_id.addr[5] = buf[21]; bpdu.port_id = (buf[22] << 8) | buf[23]; bpdu.message_age = br_get_ticks(buf+24); bpdu.max_age = br_get_ticks(buf+26); bpdu.hello_time = br_get_ticks(buf+28); bpdu.forward_delay = br_get_ticks(buf+30); if (bpdu.message_age > bpdu.max_age) { if (net_ratelimit()) br_notice(p->br, "port %u config from %pM" " (message_age %ul > max_age %ul)\n", p->port_no, eth_hdr(skb)->h_source, bpdu.message_age, bpdu.max_age); goto out; } br_received_config_bpdu(p, &bpdu); } else if (buf[0] == BPDU_TYPE_TCN) { br_received_tcn_bpdu(p); } out: spin_unlock(&br->lock); err: kfree_skb(skb); }
1 4 4 4 4 3 3 3 3 3 1 1 6 3 3 5 3 3 3 3 3 2 1 12 12 12 12 7 7 14 14 14 1 2 11 1 1 14 2 21 16 1 1 1 2 1 2 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 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * * Bluetooth HCI UART driver * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky <maxk@qualcomm.com> * Copyright (C) 2004-2005 Marcel Holtmann <marcel@holtmann.org> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/interrupt.h> #include <linux/ptrace.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/signal.h> #include <linux/ioctl.h> #include <linux/skbuff.h> #include <linux/firmware.h> #include <linux/serdev.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include "btintel.h" #include "btbcm.h" #include "hci_uart.h" #define VERSION "2.3" static const struct hci_uart_proto *hup[HCI_UART_MAX_PROTO]; int hci_uart_register_proto(const struct hci_uart_proto *p) { if (p->id >= HCI_UART_MAX_PROTO) return -EINVAL; if (hup[p->id]) return -EEXIST; hup[p->id] = p; BT_INFO("HCI UART protocol %s registered", p->name); return 0; } int hci_uart_unregister_proto(const struct hci_uart_proto *p) { if (p->id >= HCI_UART_MAX_PROTO) return -EINVAL; if (!hup[p->id]) return -EINVAL; hup[p->id] = NULL; return 0; } static const struct hci_uart_proto *hci_uart_get_proto(unsigned int id) { if (id >= HCI_UART_MAX_PROTO) return NULL; return hup[id]; } static inline void hci_uart_tx_complete(struct hci_uart *hu, int pkt_type) { struct hci_dev *hdev = hu->hdev; /* Update HCI stat counters */ switch (pkt_type) { case HCI_COMMAND_PKT: hdev->stat.cmd_tx++; break; case HCI_ACLDATA_PKT: hdev->stat.acl_tx++; break; case HCI_SCODATA_PKT: hdev->stat.sco_tx++; break; } } static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu) { struct sk_buff *skb = hu->tx_skb; if (!skb) { percpu_down_read(&hu->proto_lock); if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) skb = hu->proto->dequeue(hu); percpu_up_read(&hu->proto_lock); } else { hu->tx_skb = NULL; } return skb; } int hci_uart_tx_wakeup(struct hci_uart *hu) { /* This may be called in an IRQ context, so we can't sleep. Therefore * we try to acquire the lock only, and if that fails we assume the * tty is being closed because that is the only time the write lock is * acquired. If, however, at some point in the future the write lock * is also acquired in other situations, then this must be revisited. */ if (!percpu_down_read_trylock(&hu->proto_lock)) return 0; if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) goto no_schedule; set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) goto no_schedule; BT_DBG(""); schedule_work(&hu->write_work); no_schedule: percpu_up_read(&hu->proto_lock); return 0; } EXPORT_SYMBOL_GPL(hci_uart_tx_wakeup); static void hci_uart_write_work(struct work_struct *work) { struct hci_uart *hu = container_of(work, struct hci_uart, write_work); struct tty_struct *tty = hu->tty; struct hci_dev *hdev = hu->hdev; struct sk_buff *skb; /* REVISIT: should we cope with bad skbs or ->write() returning * and error value ? */ restart: clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); while ((skb = hci_uart_dequeue(hu))) { int len; set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); len = tty->ops->write(tty, skb->data, skb->len); hdev->stat.byte_tx += len; skb_pull(skb, len); if (skb->len) { hu->tx_skb = skb; break; } hci_uart_tx_complete(hu, hci_skb_pkt_type(skb)); kfree_skb(skb); } clear_bit(HCI_UART_SENDING, &hu->tx_state); if (test_bit(HCI_UART_TX_WAKEUP, &hu->tx_state)) goto restart; wake_up_bit(&hu->tx_state, HCI_UART_SENDING); } void hci_uart_init_work(struct work_struct *work) { struct hci_uart *hu = container_of(work, struct hci_uart, init_ready); int err; struct hci_dev *hdev; if (!test_and_clear_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return; err = hci_register_dev(hu->hdev); if (err < 0) { BT_ERR("Can't register HCI device"); clear_bit(HCI_UART_PROTO_READY, &hu->flags); hu->proto->close(hu); hdev = hu->hdev; hu->hdev = NULL; hci_free_dev(hdev); return; } set_bit(HCI_UART_REGISTERED, &hu->flags); } int hci_uart_init_ready(struct hci_uart *hu) { if (!test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return -EALREADY; schedule_work(&hu->init_ready); return 0; } int hci_uart_wait_until_sent(struct hci_uart *hu) { return wait_on_bit_timeout(&hu->tx_state, HCI_UART_SENDING, TASK_INTERRUPTIBLE, msecs_to_jiffies(2000)); } /* ------- Interface to HCI layer ------ */ /* Reset device */ static int hci_uart_flush(struct hci_dev *hdev) { struct hci_uart *hu = hci_get_drvdata(hdev); struct tty_struct *tty = hu->tty; BT_DBG("hdev %p tty %p", hdev, tty); if (hu->tx_skb) { kfree_skb(hu->tx_skb); hu->tx_skb = NULL; } /* Flush any pending characters in the driver and discipline. */ tty_ldisc_flush(tty); tty_driver_flush_buffer(tty); percpu_down_read(&hu->proto_lock); if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) hu->proto->flush(hu); percpu_up_read(&hu->proto_lock); return 0; } /* Initialize device */ static int hci_uart_open(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); /* Undo clearing this from hci_uart_close() */ hdev->flush = hci_uart_flush; return 0; } /* Close device */ static int hci_uart_close(struct hci_dev *hdev) { BT_DBG("hdev %p", hdev); hci_uart_flush(hdev); hdev->flush = NULL; return 0; } /* Send frames from HCI layer */ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_uart *hu = hci_get_drvdata(hdev); BT_DBG("%s: type %d len %d", hdev->name, hci_skb_pkt_type(skb), skb->len); percpu_down_read(&hu->proto_lock); if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) { percpu_up_read(&hu->proto_lock); return -EUNATCH; } hu->proto->enqueue(hu, skb); percpu_up_read(&hu->proto_lock); hci_uart_tx_wakeup(hu); return 0; } /* Check the underlying device or tty has flow control support */ bool hci_uart_has_flow_control(struct hci_uart *hu) { /* serdev nodes check if the needed operations are present */ if (hu->serdev) return true; if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset) return true; return false; } /* Flow control or un-flow control the device */ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) { struct tty_struct *tty = hu->tty; struct ktermios ktermios; int status; unsigned int set = 0; unsigned int clear = 0; if (hu->serdev) { serdev_device_set_flow_control(hu->serdev, !enable); serdev_device_set_rts(hu->serdev, !enable); return; } if (enable) { /* Disable hardware flow control */ ktermios = tty->termios; ktermios.c_cflag &= ~CRTSCTS; tty_set_termios(tty, &ktermios); BT_DBG("Disabling hardware flow control: %s", (tty->termios.c_cflag & CRTSCTS) ? "failed" : "success"); /* Clear RTS to prevent the device from sending */ /* Most UARTs need OUT2 to enable interrupts */ status = tty->driver->ops->tiocmget(tty); BT_DBG("Current tiocm 0x%x", status); set &= ~(TIOCM_OUT2 | TIOCM_RTS); clear = ~set; set &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 | TIOCM_OUT2 | TIOCM_LOOP; clear &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 | TIOCM_OUT2 | TIOCM_LOOP; status = tty->driver->ops->tiocmset(tty, set, clear); BT_DBG("Clearing RTS: %s", status ? "failed" : "success"); } else { /* Set RTS to allow the device to send again */ status = tty->driver->ops->tiocmget(tty); BT_DBG("Current tiocm 0x%x", status); set |= (TIOCM_OUT2 | TIOCM_RTS); clear = ~set; set &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 | TIOCM_OUT2 | TIOCM_LOOP; clear &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 | TIOCM_OUT2 | TIOCM_LOOP; status = tty->driver->ops->tiocmset(tty, set, clear); BT_DBG("Setting RTS: %s", status ? "failed" : "success"); /* Re-enable hardware flow control */ ktermios = tty->termios; ktermios.c_cflag |= CRTSCTS; tty_set_termios(tty, &ktermios); BT_DBG("Enabling hardware flow control: %s", !(tty->termios.c_cflag & CRTSCTS) ? "failed" : "success"); } } void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed, unsigned int oper_speed) { hu->init_speed = init_speed; hu->oper_speed = oper_speed; } void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed) { struct tty_struct *tty = hu->tty; struct ktermios ktermios; ktermios = tty->termios; ktermios.c_cflag &= ~CBAUD; tty_termios_encode_baud_rate(&ktermios, speed, speed); /* tty_set_termios() return not checked as it is always 0 */ tty_set_termios(tty, &ktermios); BT_DBG("%s: New tty speeds: %d/%d", hu->hdev->name, tty->termios.c_ispeed, tty->termios.c_ospeed); } static int hci_uart_setup(struct hci_dev *hdev) { struct hci_uart *hu = hci_get_drvdata(hdev); struct hci_rp_read_local_version *ver; struct sk_buff *skb; unsigned int speed; int err; /* Init speed if any */ if (hu->init_speed) speed = hu->init_speed; else if (hu->proto->init_speed) speed = hu->proto->init_speed; else speed = 0; if (speed) hci_uart_set_baudrate(hu, speed); /* Operational speed if any */ if (hu->oper_speed) speed = hu->oper_speed; else if (hu->proto->oper_speed) speed = hu->proto->oper_speed; else speed = 0; if (hu->proto->set_baudrate && speed) { err = hu->proto->set_baudrate(hu, speed); if (!err) hci_uart_set_baudrate(hu, speed); } if (hu->proto->setup) return hu->proto->setup(hu); if (!test_bit(HCI_UART_VND_DETECT, &hu->hdev_flags)) return 0; skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { BT_ERR("%s: Reading local version information failed (%ld)", hdev->name, PTR_ERR(skb)); return 0; } if (skb->len != sizeof(*ver)) { BT_ERR("%s: Event length mismatch for version information", hdev->name); goto done; } ver = (struct hci_rp_read_local_version *)skb->data; switch (le16_to_cpu(ver->manufacturer)) { #ifdef CONFIG_BT_HCIUART_INTEL case 2: hdev->set_bdaddr = btintel_set_bdaddr; btintel_check_bdaddr(hdev); break; #endif #ifdef CONFIG_BT_HCIUART_BCM case 15: hdev->set_bdaddr = btbcm_set_bdaddr; btbcm_check_bdaddr(hdev); break; #endif default: break; } done: kfree_skb(skb); return 0; } /* ------ LDISC part ------ */ /* hci_uart_tty_open * * Called when line discipline changed to HCI_UART. * * Arguments: * tty pointer to tty info structure * Return Value: * 0 if success, otherwise error code */ static int hci_uart_tty_open(struct tty_struct *tty) { struct hci_uart *hu; BT_DBG("tty %p", tty); if (!capable(CAP_NET_ADMIN)) return -EPERM; /* Error if the tty has no write op instead of leaving an exploitable * hole */ if (tty->ops->write == NULL) return -EOPNOTSUPP; hu = kzalloc(sizeof(*hu), GFP_KERNEL); if (!hu) { BT_ERR("Can't allocate control structure"); return -ENFILE; } if (percpu_init_rwsem(&hu->proto_lock)) { BT_ERR("Can't allocate semaphore structure"); kfree(hu); return -ENOMEM; } tty->disc_data = hu; hu->tty = tty; tty->receive_room = 65536; /* disable alignment support by default */ hu->alignment = 1; hu->padding = 0; /* Use serial port speed as oper_speed */ hu->oper_speed = tty->termios.c_ospeed; INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); /* Flush any pending characters in the driver */ tty_driver_flush_buffer(tty); return 0; } /* hci_uart_tty_close() * * Called when the line discipline is changed to something * else, the tty is closed, or the tty detects a hangup. */ static void hci_uart_tty_close(struct tty_struct *tty) { struct hci_uart *hu = tty->disc_data; struct hci_dev *hdev; BT_DBG("tty %p", tty); /* Detach from the tty */ tty->disc_data = NULL; if (!hu) return; hdev = hu->hdev; if (hdev) hci_uart_close(hdev); if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) { percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_READY, &hu->flags); percpu_up_write(&hu->proto_lock); cancel_work_sync(&hu->init_ready); cancel_work_sync(&hu->write_work); if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) hci_unregister_dev(hdev); hci_free_dev(hdev); } hu->proto->close(hu); } clear_bit(HCI_UART_PROTO_SET, &hu->flags); percpu_free_rwsem(&hu->proto_lock); kfree(hu); } /* hci_uart_tty_wakeup() * * Callback for transmit wakeup. Called when low level * device driver can accept more send data. * * Arguments: tty pointer to associated tty instance data * Return Value: None */ static void hci_uart_tty_wakeup(struct tty_struct *tty) { struct hci_uart *hu = tty->disc_data; BT_DBG(""); if (!hu) return; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (tty != hu->tty) return; if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) hci_uart_tx_wakeup(hu); } /* hci_uart_tty_receive() * * Called by tty low level driver when receive data is * available. * * Arguments: tty pointer to tty isntance data * data pointer to received data * flags pointer to flags for data * count count of received data in bytes * * Return Value: None */ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, const u8 *flags, size_t count) { struct hci_uart *hu = tty->disc_data; if (!hu || tty != hu->tty) return; percpu_down_read(&hu->proto_lock); if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) { percpu_up_read(&hu->proto_lock); return; } /* It does not need a lock here as it is already protected by a mutex in * tty caller */ hu->proto->recv(hu, data, count); percpu_up_read(&hu->proto_lock); if (hu->hdev) hu->hdev->stat.byte_rx += count; tty_unthrottle(tty); } static int hci_uart_register_dev(struct hci_uart *hu) { struct hci_dev *hdev; int err; BT_DBG(""); /* Initialize and register HCI device */ hdev = hci_alloc_dev(); if (!hdev) { BT_ERR("Can't allocate HCI device"); return -ENOMEM; } hu->hdev = hdev; hdev->bus = HCI_UART; hci_set_drvdata(hdev, hu); /* Only when vendor specific setup callback is provided, consider * the manufacturer information valid. This avoids filling in the * value for Ericsson when nothing is specified. */ if (hu->proto->setup) hdev->manufacturer = hu->proto->manufacturer; hdev->open = hci_uart_open; hdev->close = hci_uart_close; hdev->flush = hci_uart_flush; hdev->send = hci_uart_send_frame; hdev->setup = hci_uart_setup; SET_HCIDEV_DEV(hdev, hu->tty->dev); if (test_bit(HCI_UART_RAW_DEVICE, &hu->hdev_flags)) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags)) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); /* Only call open() for the protocol after hdev is fully initialized as * open() (or a timer/workqueue it starts) may attempt to reference it. */ err = hu->proto->open(hu); if (err) { hu->hdev = NULL; hci_free_dev(hdev); return err; } if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hu->proto->close(hu); hu->hdev = NULL; hci_free_dev(hdev); return -ENODEV; } set_bit(HCI_UART_REGISTERED, &hu->flags); return 0; } static int hci_uart_set_proto(struct hci_uart *hu, int id) { const struct hci_uart_proto *p; int err; p = hci_uart_get_proto(id); if (!p) return -EPROTONOSUPPORT; hu->proto = p; err = hci_uart_register_dev(hu); if (err) { return err; } set_bit(HCI_UART_PROTO_READY, &hu->flags); return 0; } static int hci_uart_set_flags(struct hci_uart *hu, unsigned long flags) { unsigned long valid_flags = BIT(HCI_UART_RAW_DEVICE) | BIT(HCI_UART_RESET_ON_INIT) | BIT(HCI_UART_INIT_PENDING) | BIT(HCI_UART_EXT_CONFIG) | BIT(HCI_UART_VND_DETECT); if (flags & ~valid_flags) return -EINVAL; hu->hdev_flags = flags; return 0; } /* hci_uart_tty_ioctl() * * Process IOCTL system call for the tty device. * * Arguments: * * tty pointer to tty instance data * cmd IOCTL command code * arg argument for IOCTL call (cmd dependent) * * Return Value: Command dependent */ static int hci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct hci_uart *hu = tty->disc_data; int err = 0; BT_DBG(""); /* Verify the status of the device */ if (!hu) return -EBADF; switch (cmd) { case HCIUARTSETPROTO: if (!test_and_set_bit(HCI_UART_PROTO_SET, &hu->flags)) { err = hci_uart_set_proto(hu, arg); if (err) clear_bit(HCI_UART_PROTO_SET, &hu->flags); } else err = -EBUSY; break; case HCIUARTGETPROTO: if (test_bit(HCI_UART_PROTO_SET, &hu->flags) && test_bit(HCI_UART_PROTO_READY, &hu->flags)) err = hu->proto->id; else err = -EUNATCH; break; case HCIUARTGETDEVICE: if (test_bit(HCI_UART_REGISTERED, &hu->flags)) err = hu->hdev->id; else err = -EUNATCH; break; case HCIUARTSETFLAGS: if (test_bit(HCI_UART_PROTO_SET, &hu->flags)) err = -EBUSY; else err = hci_uart_set_flags(hu, arg); break; case HCIUARTGETFLAGS: err = hu->hdev_flags; break; default: err = n_tty_ioctl_helper(tty, cmd, arg); break; } return err; } /* * We don't provide read/write/poll interface for user space. */ static ssize_t hci_uart_tty_read(struct tty_struct *tty, struct file *file, u8 *buf, size_t nr, void **cookie, unsigned long offset) { return 0; } static ssize_t hci_uart_tty_write(struct tty_struct *tty, struct file *file, const u8 *data, size_t count) { return 0; } static struct tty_ldisc_ops hci_uart_ldisc = { .owner = THIS_MODULE, .num = N_HCI, .name = "n_hci", .open = hci_uart_tty_open, .close = hci_uart_tty_close, .read = hci_uart_tty_read, .write = hci_uart_tty_write, .ioctl = hci_uart_tty_ioctl, .compat_ioctl = hci_uart_tty_ioctl, .receive_buf = hci_uart_tty_receive, .write_wakeup = hci_uart_tty_wakeup, }; static int __init hci_uart_init(void) { int err; BT_INFO("HCI UART driver ver %s", VERSION); /* Register the tty discipline */ err = tty_register_ldisc(&hci_uart_ldisc); if (err) { BT_ERR("HCI line discipline registration failed. (%d)", err); return err; } #ifdef CONFIG_BT_HCIUART_H4 h4_init(); #endif #ifdef CONFIG_BT_HCIUART_BCSP bcsp_init(); #endif #ifdef CONFIG_BT_HCIUART_LL ll_init(); #endif #ifdef CONFIG_BT_HCIUART_ATH3K ath_init(); #endif #ifdef CONFIG_BT_HCIUART_3WIRE h5_init(); #endif #ifdef CONFIG_BT_HCIUART_INTEL intel_init(); #endif #ifdef CONFIG_BT_HCIUART_BCM bcm_init(); #endif #ifdef CONFIG_BT_HCIUART_QCA qca_init(); #endif #ifdef CONFIG_BT_HCIUART_AG6XX ag6xx_init(); #endif #ifdef CONFIG_BT_HCIUART_MRVL mrvl_init(); #endif #ifdef CONFIG_BT_HCIUART_AML aml_init(); #endif return 0; } static void __exit hci_uart_exit(void) { #ifdef CONFIG_BT_HCIUART_H4 h4_deinit(); #endif #ifdef CONFIG_BT_HCIUART_BCSP bcsp_deinit(); #endif #ifdef CONFIG_BT_HCIUART_LL ll_deinit(); #endif #ifdef CONFIG_BT_HCIUART_ATH3K ath_deinit(); #endif #ifdef CONFIG_BT_HCIUART_3WIRE h5_deinit(); #endif #ifdef CONFIG_BT_HCIUART_INTEL intel_deinit(); #endif #ifdef CONFIG_BT_HCIUART_BCM bcm_deinit(); #endif #ifdef CONFIG_BT_HCIUART_QCA qca_deinit(); #endif #ifdef CONFIG_BT_HCIUART_AG6XX ag6xx_deinit(); #endif #ifdef CONFIG_BT_HCIUART_MRVL mrvl_deinit(); #endif #ifdef CONFIG_BT_HCIUART_AML aml_deinit(); #endif tty_unregister_ldisc(&hci_uart_ldisc); } module_init(hci_uart_init); module_exit(hci_uart_exit); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth HCI UART driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_HCI);
35 36 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 // SPDX-License-Identifier: GPL-2.0-or-later // Copyright (c) 2020, Nikolay Aleksandrov <nikolay@nvidia.com> #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include "br_private.h" #include "br_private_mcast_eht.h" static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr); static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src); static struct net_bridge_group_eht_host * br_multicast_eht_host_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct rb_node *node = pg->eht_host_tree.rb_node; while (node) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(node, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static int br_multicast_eht_host_filter_mode(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_host *eht_host; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return MCAST_INCLUDE; return eht_host->filter_mode; } static struct net_bridge_group_eht_set_entry * br_multicast_eht_set_entry_lookup(struct net_bridge_group_eht_set *eht_set, union net_bridge_eht_addr *h_addr) { struct rb_node *node = eht_set->entry_tree.rb_node; while (node) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static struct net_bridge_group_eht_set * br_multicast_eht_set_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node *node = pg->eht_set_tree.rb_node; while (node) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static void __eht_destroy_host(struct net_bridge_group_eht_host *eht_host) { WARN_ON(!hlist_empty(&eht_host->set_entries)); br_multicast_eht_hosts_dec(eht_host->pg); rb_erase(&eht_host->rb_node, &eht_host->pg->eht_host_tree); RB_CLEAR_NODE(&eht_host->rb_node); kfree(eht_host); } static void br_multicast_destroy_eht_set_entry(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set_entry *set_h; set_h = container_of(gc, struct net_bridge_group_eht_set_entry, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&set_h->rb_node)); timer_shutdown_sync(&set_h->timer); kfree(set_h); } static void br_multicast_destroy_eht_set(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set *eht_set; eht_set = container_of(gc, struct net_bridge_group_eht_set, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&eht_set->rb_node)); WARN_ON(!RB_EMPTY_ROOT(&eht_set->entry_tree)); timer_shutdown_sync(&eht_set->timer); kfree(eht_set); } static void __eht_del_set_entry(struct net_bridge_group_eht_set_entry *set_h) { struct net_bridge_group_eht_host *eht_host = set_h->h_parent; union net_bridge_eht_addr zero_addr; rb_erase(&set_h->rb_node, &set_h->eht_set->entry_tree); RB_CLEAR_NODE(&set_h->rb_node); hlist_del_init(&set_h->host_list); memset(&zero_addr, 0, sizeof(zero_addr)); if (memcmp(&set_h->h_addr, &zero_addr, sizeof(zero_addr))) eht_host->num_entries--; hlist_add_head(&set_h->mcast_gc.gc_node, &set_h->br->mcast_gc_list); queue_work(system_long_wq, &set_h->br->mcast_gc_work); if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); } static void br_multicast_del_eht_set(struct net_bridge_group_eht_set *eht_set) { struct net_bridge_group_eht_set_entry *set_h; struct rb_node *node; while ((node = rb_first(&eht_set->entry_tree))) { set_h = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); __eht_del_set_entry(set_h); } rb_erase(&eht_set->rb_node, &eht_set->pg->eht_set_tree); RB_CLEAR_NODE(&eht_set->rb_node); hlist_add_head(&eht_set->mcast_gc.gc_node, &eht_set->br->mcast_gc_list); queue_work(system_long_wq, &eht_set->br->mcast_gc_work); } void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg) { struct net_bridge_group_eht_set *eht_set; struct rb_node *node; while ((node = rb_first(&pg->eht_set_tree))) { eht_set = rb_entry(node, struct net_bridge_group_eht_set, rb_node); br_multicast_del_eht_set(eht_set); } } static void br_multicast_eht_set_entry_expired(struct timer_list *t) { struct net_bridge_group_eht_set_entry *set_h = from_timer(set_h, t, timer); struct net_bridge *br = set_h->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&set_h->rb_node) || timer_pending(&set_h->timer)) goto out; br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); out: spin_unlock(&br->multicast_lock); } static void br_multicast_eht_set_expired(struct timer_list *t) { struct net_bridge_group_eht_set *eht_set = from_timer(eht_set, t, timer); struct net_bridge *br = eht_set->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&eht_set->rb_node) || timer_pending(&eht_set->timer)) goto out; br_multicast_del_eht_set(eht_set); out: spin_unlock(&br->multicast_lock); } static struct net_bridge_group_eht_host * __eht_lookup_create_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, unsigned char filter_mode) { struct rb_node **link = &pg->eht_host_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_host *eht_host; while (*link) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } if (br_multicast_eht_hosts_over_limit(pg)) return NULL; eht_host = kzalloc(sizeof(*eht_host), GFP_ATOMIC); if (!eht_host) return NULL; memcpy(&eht_host->h_addr, h_addr, sizeof(*h_addr)); INIT_HLIST_HEAD(&eht_host->set_entries); eht_host->pg = pg; eht_host->filter_mode = filter_mode; rb_link_node(&eht_host->rb_node, parent, link); rb_insert_color(&eht_host->rb_node, &pg->eht_host_tree); br_multicast_eht_hosts_inc(pg); return eht_host; } static struct net_bridge_group_eht_set_entry * __eht_lookup_create_set_entry(struct net_bridge *br, struct net_bridge_group_eht_set *eht_set, struct net_bridge_group_eht_host *eht_host, bool allow_zero_src) { struct rb_node **link = &eht_set->entry_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set_entry *set_h; while (*link) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(&eht_host->h_addr, &this->h_addr, sizeof(union net_bridge_eht_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } /* always allow auto-created zero entry */ if (!allow_zero_src && eht_host->num_entries >= PG_SRC_ENT_LIMIT) return NULL; set_h = kzalloc(sizeof(*set_h), GFP_ATOMIC); if (!set_h) return NULL; memcpy(&set_h->h_addr, &eht_host->h_addr, sizeof(union net_bridge_eht_addr)); set_h->mcast_gc.destroy = br_multicast_destroy_eht_set_entry; set_h->eht_set = eht_set; set_h->h_parent = eht_host; set_h->br = br; timer_setup(&set_h->timer, br_multicast_eht_set_entry_expired, 0); hlist_add_head(&set_h->host_list, &eht_host->set_entries); rb_link_node(&set_h->rb_node, parent, link); rb_insert_color(&set_h->rb_node, &eht_set->entry_tree); /* we must not count the auto-created zero entry otherwise we won't be * able to track the full list of PG_SRC_ENT_LIMIT entries */ if (!allow_zero_src) eht_host->num_entries++; return set_h; } static struct net_bridge_group_eht_set * __eht_lookup_create_set(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node **link = &pg->eht_set_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set *eht_set; while (*link) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } eht_set = kzalloc(sizeof(*eht_set), GFP_ATOMIC); if (!eht_set) return NULL; memcpy(&eht_set->src_addr, src_addr, sizeof(*src_addr)); eht_set->mcast_gc.destroy = br_multicast_destroy_eht_set; eht_set->pg = pg; eht_set->br = pg->key.port->br; eht_set->entry_tree = RB_ROOT; timer_setup(&eht_set->timer, br_multicast_eht_set_expired, 0); rb_link_node(&eht_set->rb_node, parent, link); rb_insert_color(&eht_set->rb_node, &pg->eht_set_tree); return eht_set; } static void br_multicast_ip_src_to_eht_addr(const struct br_ip *src, union net_bridge_eht_addr *dest) { switch (src->proto) { case htons(ETH_P_IP): dest->ip4 = src->src.ip4; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): memcpy(&dest->ip6, &src->src.ip6, sizeof(struct in6_addr)); break; #endif } } static void br_eht_convert_host_filter_mode(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, int filter_mode) { struct net_bridge_group_eht_host *eht_host; union net_bridge_eht_addr zero_addr; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (eht_host) eht_host->filter_mode = filter_mode; memset(&zero_addr, 0, sizeof(zero_addr)); switch (filter_mode) { case MCAST_INCLUDE: br_multicast_del_eht_set_entry(pg, &zero_addr, h_addr); break; case MCAST_EXCLUDE: br_multicast_create_eht_set_entry(brmctx, pg, &zero_addr, h_addr, MCAST_EXCLUDE, true); break; } } static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct net_bridge *br = pg->key.port->br; struct net_bridge_group_eht_set *eht_set; union net_bridge_eht_addr zero_addr; memset(&zero_addr, 0, sizeof(zero_addr)); if (!allow_zero_src && !memcmp(src_addr, &zero_addr, sizeof(zero_addr))) return; eht_set = __eht_lookup_create_set(pg, src_addr); if (!eht_set) return; eht_host = __eht_lookup_create_host(pg, h_addr, filter_mode); if (!eht_host) goto fail_host; set_h = __eht_lookup_create_set_entry(br, eht_set, eht_host, allow_zero_src); if (!set_h) goto fail_set_entry; mod_timer(&set_h->timer, jiffies + br_multicast_gmi(brmctx)); mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(brmctx)); return; fail_set_entry: if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); fail_host: if (RB_EMPTY_ROOT(&eht_set->entry_tree)) br_multicast_del_eht_set(eht_set); } static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_set *eht_set; bool set_deleted = false; eht_set = br_multicast_eht_set_lookup(pg, src_addr); if (!eht_set) goto out; set_h = br_multicast_eht_set_entry_lookup(eht_set, h_addr); if (!set_h) goto out; __eht_del_set_entry(set_h); if (RB_EMPTY_ROOT(&eht_set->entry_tree)) { br_multicast_del_eht_set(eht_set); set_deleted = true; } out: return set_deleted; } static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct hlist_node *tmp; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return; hlist_for_each_entry_safe(set_h, tmp, &eht_host->set_entries, host_list) br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); } /* create new set entries from reports */ static void __eht_create_set_entries(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int filter_mode) { union net_bridge_eht_addr eht_src_addr; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); br_multicast_create_eht_set_entry(brmctx, pg, &eht_src_addr, h_addr, filter_mode, false); } } /* delete existing set entries and their (S,G) entries if they were the last */ static bool __eht_del_set_entries(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { union net_bridge_eht_addr eht_src_addr; struct net_bridge_group_src *src_ent; bool changed = false; struct br_ip src_ip; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, h_addr)) continue; memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); src_ent = br_multicast_find_group_src(pg, &src_ip); if (!src_ent) continue; br_multicast_del_group_src(src_ent, true); changed = true; } return changed; } static bool br_multicast_eht_allow(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE); break; case MCAST_EXCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; } return changed; } static bool br_multicast_eht_block(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; case MCAST_EXCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE); break; } return changed; } /* flush_entries is true when changing mode */ static bool __eht_inc_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, unsigned char filter_mode, bool to_report) { bool changed = false, flush_entries = to_report; union net_bridge_eht_addr eht_src_addr; if (br_multicast_eht_host_filter_mode(pg, h_addr) != filter_mode) flush_entries = true; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); /* if we're changing mode del host and its entries */ if (flush_entries) br_multicast_del_eht_host(pg, h_addr); __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, filter_mode); /* we can be missing sets only if we've deleted some entries */ if (flush_entries) { struct net_bridge_group_eht_set *eht_set; struct net_bridge_group_src *src_ent; struct hlist_node *tmp; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { br_multicast_ip_src_to_eht_addr(&src_ent->addr, &eht_src_addr); if (!br_multicast_eht_set_lookup(pg, &eht_src_addr)) { br_multicast_del_group_src(src_ent, true); changed = true; continue; } /* this is an optimization for TO_INCLUDE where we lower * the set's timeout to LMQT to catch timeout hosts: * - host A (timing out): set entries X, Y * - host B: set entry Z (new from current TO_INCLUDE) * sends BLOCK Z after LMQT but host A's EHT * entries still exist (unless lowered to LMQT * so they can timeout with the S,Gs) * => we wait another LMQT, when we can just delete the * group immediately */ if (!(src_ent->flags & BR_SGRP_F_SEND) || filter_mode != MCAST_INCLUDE || !to_report) continue; eht_set = br_multicast_eht_set_lookup(pg, &eht_src_addr); if (!eht_set) continue; mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(brmctx)); } } return changed; } static bool br_multicast_eht_inc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_INCLUDE); return changed; } static bool br_multicast_eht_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_EXCLUDE); return changed; } static bool __eht_ip4_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case IGMPV3_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; case IGMPV3_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; } return changed; } #if IS_ENABLED(CONFIG_IPV6) static bool __eht_ip6_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case MLD2_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; case MLD2_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; } return changed; } #endif /* true means an entry was deleted */ bool br_multicast_eht_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool eht_enabled = !!(pg->key.port->flags & BR_MULTICAST_FAST_LEAVE); union net_bridge_eht_addr eht_host_addr; bool changed = false; if (!eht_enabled) goto out; memset(&eht_host_addr, 0, sizeof(eht_host_addr)); memcpy(&eht_host_addr, h_addr, addr_size); if (addr_size == sizeof(__be32)) changed = __eht_ip4_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #if IS_ENABLED(CONFIG_IPV6) else changed = __eht_ip6_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #endif out: return changed; } int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, u32 eht_hosts_limit) { struct net_bridge *br = p->br; if (!eht_hosts_limit) return -EINVAL; spin_lock_bh(&br->multicast_lock); p->multicast_eht_hosts_limit = eht_hosts_limit; spin_unlock_bh(&br->multicast_lock); return 0; }
6 2 136 131 94 3 7 6 2 6 4 2 4 2 6 6 4 2 6 4 2 2 4 3 3 179 22 1 65 47 1 1 18 1 14 1 2 9 8 1 12 9 4 1 13 1 11 1 17 1 34 1 33 1 28 1 27 48 9 72 72 3 13 15 2 25 72 16 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 /* * linux/fs/hfs/super.c * * Copyright (C) 1995-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * This file contains hfs_read_super(), some of the super_ops and * init_hfs_fs() and exit_hfs_fs(). The remaining super_ops are in * inode.c since they deal with inodes. * * Based on the minix file system code, (C) 1991, 1992 by Linus Torvalds */ #include <linux/module.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/nls.h> #include <linux/parser.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/vfs.h> #include "hfs_fs.h" #include "btree.h" static struct kmem_cache *hfs_inode_cachep; MODULE_DESCRIPTION("Apple Macintosh file system support"); MODULE_LICENSE("GPL"); static int hfs_sync_fs(struct super_block *sb, int wait) { hfs_mdb_commit(sb); return 0; } /* * hfs_put_super() * * This is the put_super() entry in the super_operations structure for * HFS filesystems. The purpose is to release the resources * associated with the superblock sb. */ static void hfs_put_super(struct super_block *sb) { cancel_delayed_work_sync(&HFS_SB(sb)->mdb_work); hfs_mdb_close(sb); /* release the MDB's resources */ hfs_mdb_put(sb); } static void flush_mdb(struct work_struct *work) { struct hfs_sb_info *sbi; struct super_block *sb; sbi = container_of(work, struct hfs_sb_info, mdb_work.work); sb = sbi->sb; spin_lock(&sbi->work_lock); sbi->work_queued = 0; spin_unlock(&sbi->work_lock); hfs_mdb_commit(sb); } void hfs_mark_mdb_dirty(struct super_block *sb) { struct hfs_sb_info *sbi = HFS_SB(sb); unsigned long delay; if (sb_rdonly(sb)) return; spin_lock(&sbi->work_lock); if (!sbi->work_queued) { delay = msecs_to_jiffies(dirty_writeback_interval * 10); queue_delayed_work(system_long_wq, &sbi->mdb_work, delay); sbi->work_queued = 1; } spin_unlock(&sbi->work_lock); } /* * hfs_statfs() * * This is the statfs() entry in the super_operations structure for * HFS filesystems. The purpose is to return various data about the * filesystem. * * changed f_files/f_ffree to reflect the fs_ablock/free_ablocks. */ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = HFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = (u32)HFS_SB(sb)->fs_ablocks * HFS_SB(sb)->fs_div; buf->f_bfree = (u32)HFS_SB(sb)->free_ablocks * HFS_SB(sb)->fs_div; buf->f_bavail = buf->f_bfree; buf->f_files = HFS_SB(sb)->fs_ablocks; buf->f_ffree = HFS_SB(sb)->free_ablocks; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = HFS_NAMELEN; return 0; } static int hfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); *flags |= SB_NODIRATIME; if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) return 0; if (!(*flags & SB_RDONLY)) { if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n"); sb->s_flags |= SB_RDONLY; *flags |= SB_RDONLY; } else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) { pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= SB_RDONLY; *flags |= SB_RDONLY; } } return 0; } static int hfs_show_options(struct seq_file *seq, struct dentry *root) { struct hfs_sb_info *sbi = HFS_SB(root->d_sb); if (sbi->s_creator != cpu_to_be32(0x3f3f3f3f)) seq_show_option_n(seq, "creator", (char *)&sbi->s_creator, 4); if (sbi->s_type != cpu_to_be32(0x3f3f3f3f)) seq_show_option_n(seq, "type", (char *)&sbi->s_type, 4); seq_printf(seq, ",uid=%u,gid=%u", from_kuid_munged(&init_user_ns, sbi->s_uid), from_kgid_munged(&init_user_ns, sbi->s_gid)); if (sbi->s_file_umask != 0133) seq_printf(seq, ",file_umask=%o", sbi->s_file_umask); if (sbi->s_dir_umask != 0022) seq_printf(seq, ",dir_umask=%o", sbi->s_dir_umask); if (sbi->part >= 0) seq_printf(seq, ",part=%u", sbi->part); if (sbi->session >= 0) seq_printf(seq, ",session=%u", sbi->session); if (sbi->nls_disk) seq_printf(seq, ",codepage=%s", sbi->nls_disk->charset); if (sbi->nls_io) seq_printf(seq, ",iocharset=%s", sbi->nls_io->charset); if (sbi->s_quiet) seq_printf(seq, ",quiet"); return 0; } static struct inode *hfs_alloc_inode(struct super_block *sb) { struct hfs_inode_info *i; i = alloc_inode_sb(sb, hfs_inode_cachep, GFP_KERNEL); return i ? &i->vfs_inode : NULL; } static void hfs_free_inode(struct inode *inode) { kmem_cache_free(hfs_inode_cachep, HFS_I(inode)); } static const struct super_operations hfs_super_operations = { .alloc_inode = hfs_alloc_inode, .free_inode = hfs_free_inode, .write_inode = hfs_write_inode, .evict_inode = hfs_evict_inode, .put_super = hfs_put_super, .sync_fs = hfs_sync_fs, .statfs = hfs_statfs, .remount_fs = hfs_remount, .show_options = hfs_show_options, }; enum { opt_uid, opt_gid, opt_umask, opt_file_umask, opt_dir_umask, opt_part, opt_session, opt_type, opt_creator, opt_quiet, opt_codepage, opt_iocharset, opt_err }; static const match_table_t tokens = { { opt_uid, "uid=%u" }, { opt_gid, "gid=%u" }, { opt_umask, "umask=%o" }, { opt_file_umask, "file_umask=%o" }, { opt_dir_umask, "dir_umask=%o" }, { opt_part, "part=%u" }, { opt_session, "session=%u" }, { opt_type, "type=%s" }, { opt_creator, "creator=%s" }, { opt_quiet, "quiet" }, { opt_codepage, "codepage=%s" }, { opt_iocharset, "iocharset=%s" }, { opt_err, NULL } }; static inline int match_fourchar(substring_t *arg, u32 *result) { if (arg->to - arg->from != 4) return -EINVAL; memcpy(result, arg->from, 4); return 0; } /* * parse_options() * * adapted from linux/fs/msdos/inode.c written 1992,93 by Werner Almesberger * This function is called by hfs_read_super() to parse the mount options. */ static int parse_options(char *options, struct hfs_sb_info *hsb) { char *p; substring_t args[MAX_OPT_ARGS]; int tmp, token; /* initialize the sb with defaults */ hsb->s_uid = current_uid(); hsb->s_gid = current_gid(); hsb->s_file_umask = 0133; hsb->s_dir_umask = 0022; hsb->s_type = hsb->s_creator = cpu_to_be32(0x3f3f3f3f); /* == '????' */ hsb->s_quiet = 0; hsb->part = -1; hsb->session = -1; if (!options) return 1; while ((p = strsep(&options, ",")) != NULL) { if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case opt_uid: if (match_int(&args[0], &tmp)) { pr_err("uid requires an argument\n"); return 0; } hsb->s_uid = make_kuid(current_user_ns(), (uid_t)tmp); if (!uid_valid(hsb->s_uid)) { pr_err("invalid uid %d\n", tmp); return 0; } break; case opt_gid: if (match_int(&args[0], &tmp)) { pr_err("gid requires an argument\n"); return 0; } hsb->s_gid = make_kgid(current_user_ns(), (gid_t)tmp); if (!gid_valid(hsb->s_gid)) { pr_err("invalid gid %d\n", tmp); return 0; } break; case opt_umask: if (match_octal(&args[0], &tmp)) { pr_err("umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; hsb->s_dir_umask = (umode_t)tmp; break; case opt_file_umask: if (match_octal(&args[0], &tmp)) { pr_err("file_umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; break; case opt_dir_umask: if (match_octal(&args[0], &tmp)) { pr_err("dir_umask requires a value\n"); return 0; } hsb->s_dir_umask = (umode_t)tmp; break; case opt_part: if (match_int(&args[0], &hsb->part)) { pr_err("part requires an argument\n"); return 0; } break; case opt_session: if (match_int(&args[0], &hsb->session)) { pr_err("session requires an argument\n"); return 0; } break; case opt_type: if (match_fourchar(&args[0], &hsb->s_type)) { pr_err("type requires a 4 character value\n"); return 0; } break; case opt_creator: if (match_fourchar(&args[0], &hsb->s_creator)) { pr_err("creator requires a 4 character value\n"); return 0; } break; case opt_quiet: hsb->s_quiet = 1; break; case opt_codepage: if (hsb->nls_disk) { pr_err("unable to change codepage\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_disk = load_nls(p); if (!hsb->nls_disk) { pr_err("unable to load codepage \"%s\"\n", p); kfree(p); return 0; } kfree(p); break; case opt_iocharset: if (hsb->nls_io) { pr_err("unable to change iocharset\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_io = load_nls(p); if (!hsb->nls_io) { pr_err("unable to load iocharset \"%s\"\n", p); kfree(p); return 0; } kfree(p); break; default: return 0; } } if (hsb->nls_disk && !hsb->nls_io) { hsb->nls_io = load_nls_default(); if (!hsb->nls_io) { pr_err("unable to load default iocharset\n"); return 0; } } hsb->s_dir_umask &= 0777; hsb->s_file_umask &= 0577; return 1; } /* * hfs_read_super() * * This is the function that is responsible for mounting an HFS * filesystem. It performs all the tasks necessary to get enough data * from the disk to read the root inode. This includes parsing the * mount options, dealing with Macintosh partitions, reading the * superblock and the allocation bitmap blocks, calling * hfs_btree_init() to get the necessary data about the extents and * catalog B-trees and, finally, reading the root inode into memory. */ static int hfs_fill_super(struct super_block *sb, void *data, int silent) { struct hfs_sb_info *sbi; struct hfs_find_data fd; hfs_cat_rec rec; struct inode *root_inode; int res; sbi = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sbi->sb = sb; sb->s_fs_info = sbi; spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb); res = -EINVAL; if (!parse_options((char *)data, sbi)) { pr_err("unable to parse mount options\n"); goto bail; } sb->s_op = &hfs_super_operations; sb->s_xattr = hfs_xattr_handlers; sb->s_flags |= SB_NODIRATIME; mutex_init(&sbi->bitmap_lock); res = hfs_mdb_get(sb); if (res) { if (!silent) pr_warn("can't find a HFS filesystem on dev %s\n", hfs_mdb_name(sb)); res = -EINVAL; goto bail; } /* try to get the root inode */ res = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); if (res) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } if (res) goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); if (!root_inode) goto bail_no_root; sb->s_d_op = &hfs_dentry_operations; res = -ENOMEM; sb->s_root = d_make_root(root_inode); if (!sb->s_root) goto bail_no_root; /* everything's okay */ return 0; bail_hfs_find: hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail: hfs_mdb_put(sb); return res; } static struct dentry *hfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_bdev(fs_type, flags, dev_name, data, hfs_fill_super); } static struct file_system_type hfs_fs_type = { .owner = THIS_MODULE, .name = "hfs", .mount = hfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("hfs"); static void hfs_init_once(void *p) { struct hfs_inode_info *i = p; inode_init_once(&i->vfs_inode); } static int __init init_hfs_fs(void) { int err; hfs_inode_cachep = kmem_cache_create("hfs_inode_cache", sizeof(struct hfs_inode_info), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfs_init_once); if (!hfs_inode_cachep) return -ENOMEM; err = register_filesystem(&hfs_fs_type); if (err) kmem_cache_destroy(hfs_inode_cachep); return err; } static void __exit exit_hfs_fs(void) { unregister_filesystem(&hfs_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(hfs_inode_cachep); } module_init(init_hfs_fs) module_exit(exit_hfs_fs)
2 2 2 2 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 // SPDX-License-Identifier: GPL-2.0-only /* * Driver for the mt9m111 sensor * * Copyright (C) 2008 Erik Andrén * Copyright (C) 2007 Ilyes Gouta. Based on the m5603x Linux Driver Project. * Copyright (C) 2005 m5603x Linux Driver Project <m5602@x3ng.com.br> * * Portions of code to USB interface and ALi driver software, * Copyright (c) 2006 Willem Duinker * v4l2 interface modeled after the V4L2 driver * for SN9C10x PC Camera Controllers */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "m5602_mt9m111.h" static int mt9m111_s_ctrl(struct v4l2_ctrl *ctrl); static void mt9m111_dump_registers(struct sd *sd); static const unsigned char preinit_mt9m111[][4] = { {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00}, {BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00}, {SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00}, {SENSOR, MT9M111_SC_RESET, MT9M111_RESET | MT9M111_RESTART | MT9M111_ANALOG_STANDBY | MT9M111_CHIP_DISABLE, MT9M111_SHOW_BAD_FRAMES | MT9M111_RESTART_BAD_FRAMES | MT9M111_SYNCHRONIZE_CHANGES}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x3e, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00}, {BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00} }; static const unsigned char init_mt9m111[][4] = { {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00}, {BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00}, {SENSOR, MT9M111_SC_RESET, 0x00, 0x29}, {SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00}, {SENSOR, MT9M111_SC_RESET, 0x00, 0x08}, {SENSOR, MT9M111_PAGE_MAP, 0x00, 0x01}, {SENSOR, MT9M111_CP_OPERATING_MODE_CTL, 0x00, MT9M111_CP_OPERATING_MODE_CTL}, {SENSOR, MT9M111_CP_LENS_CORRECTION_1, 0x04, 0x2a}, {SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_A, 0x00, MT9M111_2D_DEFECT_CORRECTION_ENABLE}, {SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_B, 0x00, MT9M111_2D_DEFECT_CORRECTION_ENABLE}, {SENSOR, MT9M111_CP_LUMA_OFFSET, 0x00, 0x00}, {SENSOR, MT9M111_CP_LUMA_CLIP, 0xff, 0x00}, {SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_A, 0x14, 0x00}, {SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_B, 0x14, 0x00}, {SENSOR, 0xcd, 0x00, 0x0e}, {SENSOR, 0xd0, 0x00, 0x40}, {SENSOR, MT9M111_PAGE_MAP, 0x00, 0x02}, {SENSOR, MT9M111_CC_AUTO_EXPOSURE_PARAMETER_18, 0x00, 0x00}, {SENSOR, MT9M111_CC_AWB_PARAMETER_7, 0xef, 0x03}, {SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00}, {SENSOR, 0x33, 0x03, 0x49}, {SENSOR, 0x34, 0xc0, 0x19}, {SENSOR, 0x3f, 0x20, 0x20}, {SENSOR, 0x40, 0x20, 0x20}, {SENSOR, 0x5a, 0xc0, 0x0a}, {SENSOR, 0x70, 0x7b, 0x0a}, {SENSOR, 0x71, 0xff, 0x00}, {SENSOR, 0x72, 0x19, 0x0e}, {SENSOR, 0x73, 0x18, 0x0f}, {SENSOR, 0x74, 0x57, 0x32}, {SENSOR, 0x75, 0x56, 0x34}, {SENSOR, 0x76, 0x73, 0x35}, {SENSOR, 0x77, 0x30, 0x12}, {SENSOR, 0x78, 0x79, 0x02}, {SENSOR, 0x79, 0x75, 0x06}, {SENSOR, 0x7a, 0x77, 0x0a}, {SENSOR, 0x7b, 0x78, 0x09}, {SENSOR, 0x7c, 0x7d, 0x06}, {SENSOR, 0x7d, 0x31, 0x10}, {SENSOR, 0x7e, 0x00, 0x7e}, {SENSOR, 0x80, 0x59, 0x04}, {SENSOR, 0x81, 0x59, 0x04}, {SENSOR, 0x82, 0x57, 0x0a}, {SENSOR, 0x83, 0x58, 0x0b}, {SENSOR, 0x84, 0x47, 0x0c}, {SENSOR, 0x85, 0x48, 0x0e}, {SENSOR, 0x86, 0x5b, 0x02}, {SENSOR, 0x87, 0x00, 0x5c}, {SENSOR, MT9M111_CONTEXT_CONTROL, 0x00, MT9M111_SEL_CONTEXT_B}, {SENSOR, 0x60, 0x00, 0x80}, {SENSOR, 0x61, 0x00, 0x00}, {SENSOR, 0x62, 0x00, 0x00}, {SENSOR, 0x63, 0x00, 0x00}, {SENSOR, 0x64, 0x00, 0x00}, {SENSOR, MT9M111_SC_ROWSTART, 0x00, 0x0d}, /* 13 */ {SENSOR, MT9M111_SC_COLSTART, 0x00, 0x12}, /* 18 */ {SENSOR, MT9M111_SC_WINDOW_HEIGHT, 0x04, 0x00}, /* 1024 */ {SENSOR, MT9M111_SC_WINDOW_WIDTH, 0x05, 0x10}, /* 1296 */ {SENSOR, MT9M111_SC_HBLANK_CONTEXT_B, 0x01, 0x60}, /* 352 */ {SENSOR, MT9M111_SC_VBLANK_CONTEXT_B, 0x00, 0x11}, /* 17 */ {SENSOR, MT9M111_SC_HBLANK_CONTEXT_A, 0x01, 0x60}, /* 352 */ {SENSOR, MT9M111_SC_VBLANK_CONTEXT_A, 0x00, 0x11}, /* 17 */ {SENSOR, MT9M111_SC_R_MODE_CONTEXT_A, 0x01, 0x0f}, /* 271 */ {SENSOR, 0x30, 0x04, 0x00}, /* Set number of blank rows chosen to 400 */ {SENSOR, MT9M111_SC_SHUTTER_WIDTH, 0x01, 0x90}, }; static const unsigned char start_mt9m111[][4] = { {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00}, {BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00}, {BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00}, {BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00}, }; static struct v4l2_pix_format mt9m111_modes[] = { { 640, 480, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 640 * 480, .bytesperline = 640, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 0 } }; static const struct v4l2_ctrl_ops mt9m111_ctrl_ops = { .s_ctrl = mt9m111_s_ctrl, }; static const struct v4l2_ctrl_config mt9m111_greenbal_cfg = { .ops = &mt9m111_ctrl_ops, .id = M5602_V4L2_CID_GREEN_BALANCE, .name = "Green Balance", .type = V4L2_CTRL_TYPE_INTEGER, .min = 0, .max = 0x7ff, .step = 1, .def = MT9M111_GREEN_GAIN_DEFAULT, .flags = V4L2_CTRL_FLAG_SLIDER, }; int mt9m111_probe(struct sd *sd) { u8 data[2] = {0x00, 0x00}; int i, err; struct gspca_dev *gspca_dev = (struct gspca_dev *)sd; if (force_sensor) { if (force_sensor == MT9M111_SENSOR) { pr_info("Forcing a %s sensor\n", mt9m111.name); goto sensor_found; } /* If we want to force another sensor, don't try to probe this * one */ return -ENODEV; } gspca_dbg(gspca_dev, D_PROBE, "Probing for a mt9m111 sensor\n"); /* Do the preinit */ for (i = 0; i < ARRAY_SIZE(preinit_mt9m111); i++) { if (preinit_mt9m111[i][0] == BRIDGE) { err = m5602_write_bridge(sd, preinit_mt9m111[i][1], preinit_mt9m111[i][2]); } else { data[0] = preinit_mt9m111[i][2]; data[1] = preinit_mt9m111[i][3]; err = m5602_write_sensor(sd, preinit_mt9m111[i][1], data, 2); } if (err < 0) return err; } if (m5602_read_sensor(sd, MT9M111_SC_CHIPVER, data, 2)) return -ENODEV; if ((data[0] == 0x14) && (data[1] == 0x3a)) { pr_info("Detected a mt9m111 sensor\n"); goto sensor_found; } return -ENODEV; sensor_found: sd->gspca_dev.cam.cam_mode = mt9m111_modes; sd->gspca_dev.cam.nmodes = ARRAY_SIZE(mt9m111_modes); return 0; } int mt9m111_init(struct sd *sd) { int i, err = 0; /* Init the sensor */ for (i = 0; i < ARRAY_SIZE(init_mt9m111) && !err; i++) { u8 data[2]; if (init_mt9m111[i][0] == BRIDGE) { err = m5602_write_bridge(sd, init_mt9m111[i][1], init_mt9m111[i][2]); } else { data[0] = init_mt9m111[i][2]; data[1] = init_mt9m111[i][3]; err = m5602_write_sensor(sd, init_mt9m111[i][1], data, 2); } } if (dump_sensor) mt9m111_dump_registers(sd); return 0; } int mt9m111_init_controls(struct sd *sd) { struct v4l2_ctrl_handler *hdl = &sd->gspca_dev.ctrl_handler; sd->gspca_dev.vdev.ctrl_handler = hdl; v4l2_ctrl_handler_init(hdl, 7); sd->auto_white_bal = v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, 0); sd->green_bal = v4l2_ctrl_new_custom(hdl, &mt9m111_greenbal_cfg, NULL); sd->red_bal = v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_RED_BALANCE, 0, 0x7ff, 1, MT9M111_RED_GAIN_DEFAULT); sd->blue_bal = v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_BLUE_BALANCE, 0, 0x7ff, 1, MT9M111_BLUE_GAIN_DEFAULT); v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_GAIN, 0, (INITIAL_MAX_GAIN - 1) * 2 * 2 * 2, 1, MT9M111_DEFAULT_GAIN); sd->hflip = v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_HFLIP, 0, 1, 1, 0); sd->vflip = v4l2_ctrl_new_std(hdl, &mt9m111_ctrl_ops, V4L2_CID_VFLIP, 0, 1, 1, 0); if (hdl->error) { pr_err("Could not initialize controls\n"); return hdl->error; } v4l2_ctrl_auto_cluster(4, &sd->auto_white_bal, 0, false); v4l2_ctrl_cluster(2, &sd->hflip); return 0; } int mt9m111_start(struct sd *sd) { int i, err = 0; u8 data[2]; struct cam *cam = &sd->gspca_dev.cam; struct gspca_dev *gspca_dev = (struct gspca_dev *)sd; int width = cam->cam_mode[sd->gspca_dev.curr_mode].width - 1; int height = cam->cam_mode[sd->gspca_dev.curr_mode].height; for (i = 0; i < ARRAY_SIZE(start_mt9m111) && !err; i++) { if (start_mt9m111[i][0] == BRIDGE) { err = m5602_write_bridge(sd, start_mt9m111[i][1], start_mt9m111[i][2]); } else { data[0] = start_mt9m111[i][2]; data[1] = start_mt9m111[i][3]; err = m5602_write_sensor(sd, start_mt9m111[i][1], data, 2); } } if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, (height >> 8) & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, (height & 0xff)); if (err < 0) return err; for (i = 0; i < 2 && !err; i++) err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 2); if (err < 0) return err; for (i = 0; i < 2 && !err; i++) err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, (width >> 8) & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, width & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 0); if (err < 0) return err; switch (width) { case 640: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for VGA mode\n"); break; case 320: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for QVGA mode\n"); break; } return err; } void mt9m111_disconnect(struct sd *sd) { sd->sensor = NULL; } static int mt9m111_set_hvflip(struct gspca_dev *gspca_dev) { int err; u8 data[2] = {0x00, 0x00}; struct sd *sd = (struct sd *) gspca_dev; int hflip; int vflip; gspca_dbg(gspca_dev, D_CONF, "Set hvflip to %d %d\n", sd->hflip->val, sd->vflip->val); /* The mt9m111 is flipped by default */ hflip = !sd->hflip->val; vflip = !sd->vflip->val; /* Set the correct page map */ err = m5602_write_sensor(sd, MT9M111_PAGE_MAP, data, 2); if (err < 0) return err; data[0] = MT9M111_RMB_OVER_SIZED; if (gspca_dev->pixfmt.width == 640) { data[1] = MT9M111_RMB_ROW_SKIP_2X | MT9M111_RMB_COLUMN_SKIP_2X | (hflip << 1) | vflip; } else { data[1] = MT9M111_RMB_ROW_SKIP_4X | MT9M111_RMB_COLUMN_SKIP_4X | (hflip << 1) | vflip; } err = m5602_write_sensor(sd, MT9M111_SC_R_MODE_CONTEXT_B, data, 2); return err; } static int mt9m111_set_auto_white_balance(struct gspca_dev *gspca_dev, __s32 val) { struct sd *sd = (struct sd *) gspca_dev; int err; u8 data[2]; err = m5602_read_sensor(sd, MT9M111_CP_OPERATING_MODE_CTL, data, 2); if (err < 0) return err; data[1] = ((data[1] & 0xfd) | ((val & 0x01) << 1)); err = m5602_write_sensor(sd, MT9M111_CP_OPERATING_MODE_CTL, data, 2); gspca_dbg(gspca_dev, D_CONF, "Set auto white balance %d\n", val); return err; } static int mt9m111_set_gain(struct gspca_dev *gspca_dev, __s32 val) { int err, tmp; u8 data[2] = {0x00, 0x00}; struct sd *sd = (struct sd *) gspca_dev; /* Set the correct page map */ err = m5602_write_sensor(sd, MT9M111_PAGE_MAP, data, 2); if (err < 0) return err; if (val >= INITIAL_MAX_GAIN * 2 * 2 * 2) return -EINVAL; if ((val >= INITIAL_MAX_GAIN * 2 * 2) && (val < (INITIAL_MAX_GAIN - 1) * 2 * 2 * 2)) tmp = (1 << 10) | (val << 9) | (val << 8) | (val / 8); else if ((val >= INITIAL_MAX_GAIN * 2) && (val < INITIAL_MAX_GAIN * 2 * 2)) tmp = (1 << 9) | (1 << 8) | (val / 4); else if ((val >= INITIAL_MAX_GAIN) && (val < INITIAL_MAX_GAIN * 2)) tmp = (1 << 8) | (val / 2); else tmp = val; data[1] = (tmp & 0xff); data[0] = (tmp & 0xff00) >> 8; gspca_dbg(gspca_dev, D_CONF, "tmp=%d, data[1]=%d, data[0]=%d\n", tmp, data[1], data[0]); err = m5602_write_sensor(sd, MT9M111_SC_GLOBAL_GAIN, data, 2); return err; } static int mt9m111_set_green_balance(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 data[2]; struct sd *sd = (struct sd *) gspca_dev; data[1] = (val & 0xff); data[0] = (val & 0xff00) >> 8; gspca_dbg(gspca_dev, D_CONF, "Set green balance %d\n", val); err = m5602_write_sensor(sd, MT9M111_SC_GREEN_1_GAIN, data, 2); if (err < 0) return err; return m5602_write_sensor(sd, MT9M111_SC_GREEN_2_GAIN, data, 2); } static int mt9m111_set_blue_balance(struct gspca_dev *gspca_dev, __s32 val) { u8 data[2]; struct sd *sd = (struct sd *) gspca_dev; data[1] = (val & 0xff); data[0] = (val & 0xff00) >> 8; gspca_dbg(gspca_dev, D_CONF, "Set blue balance %d\n", val); return m5602_write_sensor(sd, MT9M111_SC_BLUE_GAIN, data, 2); } static int mt9m111_set_red_balance(struct gspca_dev *gspca_dev, __s32 val) { u8 data[2]; struct sd *sd = (struct sd *) gspca_dev; data[1] = (val & 0xff); data[0] = (val & 0xff00) >> 8; gspca_dbg(gspca_dev, D_CONF, "Set red balance %d\n", val); return m5602_write_sensor(sd, MT9M111_SC_RED_GAIN, data, 2); } static int mt9m111_s_ctrl(struct v4l2_ctrl *ctrl) { struct gspca_dev *gspca_dev = container_of(ctrl->handler, struct gspca_dev, ctrl_handler); struct sd *sd = (struct sd *) gspca_dev; int err; if (!gspca_dev->streaming) return 0; switch (ctrl->id) { case V4L2_CID_AUTO_WHITE_BALANCE: err = mt9m111_set_auto_white_balance(gspca_dev, ctrl->val); if (err || ctrl->val) return err; err = mt9m111_set_green_balance(gspca_dev, sd->green_bal->val); if (err) return err; err = mt9m111_set_red_balance(gspca_dev, sd->red_bal->val); if (err) return err; err = mt9m111_set_blue_balance(gspca_dev, sd->blue_bal->val); break; case V4L2_CID_GAIN: err = mt9m111_set_gain(gspca_dev, ctrl->val); break; case V4L2_CID_HFLIP: err = mt9m111_set_hvflip(gspca_dev); break; default: return -EINVAL; } return err; } static void mt9m111_dump_registers(struct sd *sd) { u8 address, value[2] = {0x00, 0x00}; pr_info("Dumping the mt9m111 register state\n"); pr_info("Dumping the mt9m111 sensor core registers\n"); value[1] = MT9M111_SENSOR_CORE; m5602_write_sensor(sd, MT9M111_PAGE_MAP, value, 2); for (address = 0; address < 0xff; address++) { m5602_read_sensor(sd, address, value, 2); pr_info("register 0x%x contains 0x%x%x\n", address, value[0], value[1]); } pr_info("Dumping the mt9m111 color pipeline registers\n"); value[1] = MT9M111_COLORPIPE; m5602_write_sensor(sd, MT9M111_PAGE_MAP, value, 2); for (address = 0; address < 0xff; address++) { m5602_read_sensor(sd, address, value, 2); pr_info("register 0x%x contains 0x%x%x\n", address, value[0], value[1]); } pr_info("Dumping the mt9m111 camera control registers\n"); value[1] = MT9M111_CAMERA_CONTROL; m5602_write_sensor(sd, MT9M111_PAGE_MAP, value, 2); for (address = 0; address < 0xff; address++) { m5602_read_sensor(sd, address, value, 2); pr_info("register 0x%x contains 0x%x%x\n", address, value[0], value[1]); } pr_info("mt9m111 register state dump complete\n"); }
26 4 21 22 6 20 20 6 22 22 22 22 22 22 22 22 21 9 20 25 12 23 23 23 19 11 11 6 26 5 11 26 26 26 20 26 6 6 5 20 5 23 23 23 23 6 20 23 9 9 9 2 2 2 4 4 4 4 3 3 3 3 3 3 3 1 3 1 1 1 1 1 1 1 3 3 2 1428 1399 1 3 3 43 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 // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct work_struct work; struct net_device *dev; u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; bool may_sleep; if (!utn->need_sync) return; /* Drivers which sleep in the callback need to update from * the workqueue, if we come from the tunnel driver's notification. */ may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (!may_sleep) __udp_tunnel_nic_device_sync(dev, utn); if (may_sleep || utn->need_replay) { queue_work(udp_tunnel_nic_workqueue, &utn->work); utn->work_pending = 1; } } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; ASSERT_RTNL(); utn = dev->udp_tunnel_nic; if (!utn) return; utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release rtnl across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) udp_tunnel_get_rx_info(dev); return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) return; list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. */ if (utn->work_pending) return; udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_flush(dev, utn); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL");
4 2 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 #ifndef _NET_FLOW_OFFLOAD_H #define _NET_FLOW_OFFLOAD_H #include <linux/kernel.h> #include <linux/list.h> #include <linux/netlink.h> #include <net/flow_dissector.h> struct flow_match { struct flow_dissector *dissector; void *mask; void *key; }; struct flow_match_meta { struct flow_dissector_key_meta *key, *mask; }; struct flow_match_basic { struct flow_dissector_key_basic *key, *mask; }; struct flow_match_control { struct flow_dissector_key_control *key, *mask; }; struct flow_match_eth_addrs { struct flow_dissector_key_eth_addrs *key, *mask; }; struct flow_match_vlan { struct flow_dissector_key_vlan *key, *mask; }; struct flow_match_arp { struct flow_dissector_key_arp *key, *mask; }; struct flow_match_ipv4_addrs { struct flow_dissector_key_ipv4_addrs *key, *mask; }; struct flow_match_ipv6_addrs { struct flow_dissector_key_ipv6_addrs *key, *mask; }; struct flow_match_ip { struct flow_dissector_key_ip *key, *mask; }; struct flow_match_ports { struct flow_dissector_key_ports *key, *mask; }; struct flow_match_ports_range { struct flow_dissector_key_ports_range *key, *mask; }; struct flow_match_icmp { struct flow_dissector_key_icmp *key, *mask; }; struct flow_match_tcp { struct flow_dissector_key_tcp *key, *mask; }; struct flow_match_ipsec { struct flow_dissector_key_ipsec *key, *mask; }; struct flow_match_mpls { struct flow_dissector_key_mpls *key, *mask; }; struct flow_match_enc_keyid { struct flow_dissector_key_keyid *key, *mask; }; struct flow_match_enc_opts { struct flow_dissector_key_enc_opts *key, *mask; }; struct flow_match_ct { struct flow_dissector_key_ct *key, *mask; }; struct flow_match_pppoe { struct flow_dissector_key_pppoe *key, *mask; }; struct flow_match_l2tpv3 { struct flow_dissector_key_l2tpv3 *key, *mask; }; struct flow_rule; void flow_rule_match_meta(const struct flow_rule *rule, struct flow_match_meta *out); void flow_rule_match_basic(const struct flow_rule *rule, struct flow_match_basic *out); void flow_rule_match_control(const struct flow_rule *rule, struct flow_match_control *out); void flow_rule_match_eth_addrs(const struct flow_rule *rule, struct flow_match_eth_addrs *out); void flow_rule_match_vlan(const struct flow_rule *rule, struct flow_match_vlan *out); void flow_rule_match_cvlan(const struct flow_rule *rule, struct flow_match_vlan *out); void flow_rule_match_arp(const struct flow_rule *rule, struct flow_match_arp *out); void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out); void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out); void flow_rule_match_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_ports(const struct flow_rule *rule, struct flow_match_ports *out); void flow_rule_match_ports_range(const struct flow_rule *rule, struct flow_match_ports_range *out); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out); void flow_rule_match_ipsec(const struct flow_rule *rule, struct flow_match_ipsec *out); void flow_rule_match_icmp(const struct flow_rule *rule, struct flow_match_icmp *out); void flow_rule_match_mpls(const struct flow_rule *rule, struct flow_match_mpls *out); void flow_rule_match_enc_control(const struct flow_rule *rule, struct flow_match_control *out); void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out); void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out); void flow_rule_match_enc_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_enc_ports(const struct flow_rule *rule, struct flow_match_ports *out); void flow_rule_match_enc_keyid(const struct flow_rule *rule, struct flow_match_enc_keyid *out); void flow_rule_match_enc_opts(const struct flow_rule *rule, struct flow_match_enc_opts *out); void flow_rule_match_ct(const struct flow_rule *rule, struct flow_match_ct *out); void flow_rule_match_pppoe(const struct flow_rule *rule, struct flow_match_pppoe *out); void flow_rule_match_l2tpv3(const struct flow_rule *rule, struct flow_match_l2tpv3 *out); enum flow_action_id { FLOW_ACTION_ACCEPT = 0, FLOW_ACTION_DROP, FLOW_ACTION_TRAP, FLOW_ACTION_GOTO, FLOW_ACTION_REDIRECT, FLOW_ACTION_MIRRED, FLOW_ACTION_REDIRECT_INGRESS, FLOW_ACTION_MIRRED_INGRESS, FLOW_ACTION_VLAN_PUSH, FLOW_ACTION_VLAN_POP, FLOW_ACTION_VLAN_MANGLE, FLOW_ACTION_TUNNEL_ENCAP, FLOW_ACTION_TUNNEL_DECAP, FLOW_ACTION_MANGLE, FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, FLOW_ACTION_PTYPE, FLOW_ACTION_PRIORITY, FLOW_ACTION_RX_QUEUE_MAPPING, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, FLOW_ACTION_POLICE, FLOW_ACTION_CT, FLOW_ACTION_CT_METADATA, FLOW_ACTION_MPLS_PUSH, FLOW_ACTION_MPLS_POP, FLOW_ACTION_MPLS_MANGLE, FLOW_ACTION_GATE, FLOW_ACTION_PPPOE_PUSH, FLOW_ACTION_JUMP, FLOW_ACTION_PIPE, FLOW_ACTION_VLAN_PUSH_ETH, FLOW_ACTION_VLAN_POP_ETH, FLOW_ACTION_CONTINUE, NUM_FLOW_ACTIONS, }; /* This is mirroring enum pedit_header_type definition for easy mapping between * tc pedit action. Legacy TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK is mapped to * FLOW_ACT_MANGLE_UNSPEC, which is supported by no driver. */ enum flow_action_mangle_base { FLOW_ACT_MANGLE_UNSPEC = 0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, FLOW_ACT_MANGLE_HDR_TYPE_IP4, FLOW_ACT_MANGLE_HDR_TYPE_IP6, FLOW_ACT_MANGLE_HDR_TYPE_TCP, FLOW_ACT_MANGLE_HDR_TYPE_UDP, }; enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, FLOW_ACTION_HW_STATS_DISABLED_BIT, FLOW_ACTION_HW_STATS_NUM_BITS }; enum flow_action_hw_stats { FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE | FLOW_ACTION_HW_STATS_DELAYED, FLOW_ACTION_HW_STATS_DISABLED = BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), FLOW_ACTION_HW_STATS_DONT_CARE = BIT(FLOW_ACTION_HW_STATS_NUM_BITS) - 1, }; typedef void (*action_destr)(void *priv); struct flow_action_cookie { u32 cookie_len; u8 cookie[]; }; struct flow_action_cookie *flow_action_cookie_create(void *data, unsigned int len, gfp_t gfp); void flow_action_cookie_destroy(struct flow_action_cookie *cookie); struct flow_action_entry { enum flow_action_id id; u32 hw_index; unsigned long cookie; u64 miss_cookie; enum flow_action_hw_stats hw_stats; action_destr destructor; void *destructor_priv; union { u32 chain_index; /* FLOW_ACTION_GOTO */ struct net_device *dev; /* FLOW_ACTION_REDIRECT */ struct { /* FLOW_ACTION_VLAN */ u16 vid; __be16 proto; u8 prio; } vlan; struct { /* FLOW_ACTION_VLAN_PUSH_ETH */ unsigned char dst[ETH_ALEN]; unsigned char src[ETH_ALEN]; } vlan_push_eth; struct { /* FLOW_ACTION_MANGLE */ /* FLOW_ACTION_ADD */ enum flow_action_mangle_base htype; u32 offset; u32 mask; u32 val; } mangle; struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ u16 ptype; /* FLOW_ACTION_PTYPE */ u16 rx_queue; /* FLOW_ACTION_RX_QUEUE_MAPPING */ u32 priority; /* FLOW_ACTION_PRIORITY */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; u32 index; u8 vf; } queue; struct { /* FLOW_ACTION_SAMPLE */ struct psample_group *psample_group; u32 rate; u32 trunc_size; bool truncate; } sample; struct { /* FLOW_ACTION_POLICE */ u32 burst; u64 rate_bytes_ps; u64 peakrate_bytes_ps; u32 avrate; u16 overhead; u64 burst_pkt; u64 rate_pkt_ps; u32 mtu; struct { enum flow_action_id act_id; u32 extval; } exceed, notexceed; } police; struct { /* FLOW_ACTION_CT */ int action; u16 zone; struct nf_flowtable *flow_table; } ct; struct { unsigned long cookie; u32 mark; u32 labels[4]; bool orig_dir; } ct_metadata; struct { /* FLOW_ACTION_MPLS_PUSH */ u32 label; __be16 proto; u8 tc; u8 bos; u8 ttl; } mpls_push; struct { /* FLOW_ACTION_MPLS_POP */ __be16 proto; } mpls_pop; struct { /* FLOW_ACTION_MPLS_MANGLE */ u32 label; u8 tc; u8 bos; u8 ttl; } mpls_mangle; struct { s32 prio; u64 basetime; u64 cycletime; u64 cycletimeext; u32 num_entries; struct action_gate_entry *entries; } gate; struct { /* FLOW_ACTION_PPPOE_PUSH */ u16 sid; } pppoe; }; struct flow_action_cookie *user_cookie; /* user defined action cookie */ }; struct flow_action { unsigned int num_entries; struct flow_action_entry entries[] __counted_by(num_entries); }; static inline bool flow_action_has_entries(const struct flow_action *action) { return action->num_entries; } /** * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * * Return: true if exactly one action is present. */ static inline bool flow_offload_has_one_action(const struct flow_action *action) { return action->num_entries == 1; } static inline bool flow_action_is_last_entry(const struct flow_action *action, const struct flow_action_entry *entry) { return entry == &action->entries[action->num_entries - 1]; } #define flow_action_for_each(__i, __act, __actions) \ for (__i = 0, __act = &(__actions)->entries[0]; \ __i < (__actions)->num_entries; \ __act = &(__actions)->entries[++__i]) static inline bool flow_action_mixed_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack) { const struct flow_action_entry *action_entry; u8 last_hw_stats; int i; if (flow_offload_has_one_action(action)) return true; flow_action_for_each(i, action_entry, action) { if (i && action_entry->hw_stats != last_hw_stats) { NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); return false; } last_hw_stats = action_entry->hw_stats; } return true; } static inline const struct flow_action_entry * flow_action_first_entry_get(const struct flow_action *action) { WARN_ON(!flow_action_has_entries(action)); return &action->entries[0]; } static inline bool __flow_action_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack, bool check_allow_bit, enum flow_action_hw_stats_bit allow_bit) { const struct flow_action_entry *action_entry; if (!flow_action_has_entries(action)) return true; if (!flow_action_mixed_hw_stats_check(action, extack)) return false; action_entry = flow_action_first_entry_get(action); /* Zero is not a legal value for hw_stats, catch anyone passing it */ WARN_ON_ONCE(!action_entry->hw_stats); if (!check_allow_bit && ~action_entry->hw_stats & FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); return false; } else if (check_allow_bit && !(action_entry->hw_stats & BIT(allow_bit))) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support selected HW stats type"); return false; } return true; } static inline bool flow_action_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack, enum flow_action_hw_stats_bit allow_bit) { return __flow_action_hw_stats_check(action, extack, true, allow_bit); } static inline bool flow_action_basic_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack) { return __flow_action_hw_stats_check(action, extack, false, 0); } struct flow_rule { struct flow_match match; struct flow_action action; }; struct flow_rule *flow_rule_alloc(unsigned int num_actions); static inline bool flow_rule_match_key(const struct flow_rule *rule, enum flow_dissector_key_id key) { return dissector_uses_key(rule->match.dissector, key); } /** * flow_rule_is_supp_control_flags() - check for supported control flags * @supp_flags: control flags supported by driver * @ctrl_flags: control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if only supported control flags are set, false otherwise. */ static inline bool flow_rule_is_supp_control_flags(const u32 supp_flags, const u32 ctrl_flags, struct netlink_ext_ack *extack) { if (likely((ctrl_flags & ~supp_flags) == 0)) return true; NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on control.flags %#x", ctrl_flags); return false; } /** * flow_rule_is_supp_enc_control_flags() - check for supported control flags * @supp_enc_flags: encapsulation control flags supported by driver * @enc_ctrl_flags: encapsulation control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if only supported control flags are set, false otherwise. */ static inline bool flow_rule_is_supp_enc_control_flags(const u32 supp_enc_flags, const u32 enc_ctrl_flags, struct netlink_ext_ack *extack) { if (likely((enc_ctrl_flags & ~supp_enc_flags) == 0)) return true; NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on enc_control.flags %#x", enc_ctrl_flags); return false; } /** * flow_rule_has_control_flags() - check for presence of any control flags * @ctrl_flags: control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if control flags are set, false otherwise. */ static inline bool flow_rule_has_control_flags(const u32 ctrl_flags, struct netlink_ext_ack *extack) { return !flow_rule_is_supp_control_flags(0, ctrl_flags, extack); } /** * flow_rule_has_enc_control_flags() - check for presence of any control flags * @enc_ctrl_flags: encapsulation control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if control flags are set, false otherwise. */ static inline bool flow_rule_has_enc_control_flags(const u32 enc_ctrl_flags, struct netlink_ext_ack *extack) { return !flow_rule_is_supp_enc_control_flags(0, enc_ctrl_flags, extack); } /** * flow_rule_match_has_control_flags() - match and check for any control flags * @rule: The flow_rule under evaluation. * @extack: The netlink extended ACK for reporting errors. * * Return: true if control flags are set, false otherwise. */ static inline bool flow_rule_match_has_control_flags(struct flow_rule *rule, struct netlink_ext_ack *extack) { struct flow_match_control match; if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) return false; flow_rule_match_control(rule, &match); return flow_rule_has_control_flags(match.mask->flags, extack); } struct flow_stats { u64 pkts; u64 bytes; u64 drops; u64 lastused; enum flow_action_hw_stats used_hw_stats; bool used_hw_stats_valid; }; static inline void flow_stats_update(struct flow_stats *flow_stats, u64 bytes, u64 pkts, u64 drops, u64 lastused, enum flow_action_hw_stats used_hw_stats) { flow_stats->pkts += pkts; flow_stats->bytes += bytes; flow_stats->drops += drops; flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused); /* The driver should pass value with a maximum of one bit set. * Passing FLOW_ACTION_HW_STATS_ANY is invalid. */ WARN_ON(used_hw_stats == FLOW_ACTION_HW_STATS_ANY); flow_stats->used_hw_stats |= used_hw_stats; flow_stats->used_hw_stats_valid = true; } enum flow_block_command { FLOW_BLOCK_BIND, FLOW_BLOCK_UNBIND, }; enum flow_block_binder_type { FLOW_BLOCK_BINDER_TYPE_UNSPEC, FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, FLOW_BLOCK_BINDER_TYPE_RED_MARK, }; struct flow_block { struct list_head cb_list; }; struct netlink_ext_ack; struct flow_block_offload { enum flow_block_command command; enum flow_block_binder_type binder_type; bool block_shared; bool unlocked_driver_cb; struct net *net; struct flow_block *block; struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; struct Qdisc *sch; struct list_head *cb_list_head; }; enum tc_setup_type; typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); struct flow_block_cb; struct flow_block_indr { struct list_head list; struct net_device *dev; struct Qdisc *sch; enum flow_block_binder_type binder_type; void *data; void *cb_priv; void (*cleanup)(struct flow_block_cb *block_cb); }; struct flow_block_cb { struct list_head driver_list; struct list_head list; flow_setup_cb_t *cb; void *cb_ident; void *cb_priv; void (*release)(void *cb_priv); struct flow_block_indr indr; unsigned int refcnt; }; struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)); struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv), struct flow_block_offload *bo, struct net_device *dev, struct Qdisc *sch, void *data, void *indr_cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)); void flow_block_cb_free(struct flow_block_cb *block_cb); struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, flow_setup_cb_t *cb, void *cb_ident); void *flow_block_cb_priv(struct flow_block_cb *block_cb); void flow_block_cb_incref(struct flow_block_cb *block_cb); unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb); static inline void flow_block_cb_add(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_add_tail(&block_cb->list, &offload->cb_list); } static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_move(&block_cb->list, &offload->cb_list); } static inline void flow_indr_block_cb_remove(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_del(&block_cb->indr.list); list_move(&block_cb->list, &offload->cb_list); } bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); enum flow_cls_command { FLOW_CLS_REPLACE, FLOW_CLS_DESTROY, FLOW_CLS_STATS, FLOW_CLS_TMPLT_CREATE, FLOW_CLS_TMPLT_DESTROY, }; struct flow_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; struct netlink_ext_ack *extack; }; struct flow_cls_offload { struct flow_cls_common_offload common; enum flow_cls_command command; bool use_act_stats; unsigned long cookie; struct flow_rule *rule; struct flow_stats stats; u32 classid; }; enum offload_act_command { FLOW_ACT_REPLACE, FLOW_ACT_DESTROY, FLOW_ACT_STATS, }; struct flow_offload_action { struct netlink_ext_ack *extack; /* NULL in FLOW_ACT_STATS process*/ enum offload_act_command command; enum flow_action_id id; u32 index; unsigned long cookie; struct flow_stats stats; struct flow_action action; }; struct flow_offload_action *offload_action_alloc(unsigned int num_actions); static inline struct flow_rule * flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) { return flow_cmd->rule; } static inline void flow_block_init(struct flow_block *flow_block) { INIT_LIST_HEAD(&flow_block->cb_list); } typedef int flow_indr_block_bind_cb_t(struct net_device *dev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv); void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, void (*release)(void *cb_priv)); int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); bool flow_indr_dev_exists(void); #endif /* _NET_FLOW_OFFLOAD_H */
12893 12309 261 2565 1065 7389 9047 2563 2567 5050 153 39 37 2595 2632 12310 2708 2664 12245 2571 2560 1 2563 2569 2574 2549 1 2568 2567 2575 8474 649 651 652 651 652 651 12334 331 222 680 222 3 3 3 3 3 3 532 12309 8093 534 532 8102 116 3 3 3 3 116 125 3 262 37 239 262 260 2272 3417 260 1 237 37 262 261 1 3551 3439 12309 12331 12334 8241 12300 12304 605 7558 8241 12326 8305 4196 95 12285 12307 560 9972 11598 12291 12346 561 86 11922 3958 11912 11933 2 2 2 2 2 3695 3697 3688 3694 3697 1567 2745 2873 906 2818 2885 1375 1371 1369 86 86 612 935 935 648 322 322 322 169 933 408 408 408 407 408 10 2 406 10 408 407 405 408 10 409 2 2 2 2 10 10 10 2 10 10 10 2 2 2 2 230 229 230 230 3295 843 1123 933 3289 3297 863 75 1265 379 245 145 71 72 70 2268 2272 2268 2558 2268 2560 2561 2276 2277 1697 1702 792 797 986 991 8 8 2271 2274 2272 2275 2277 7 648 651 647 649 650 490 652 649 647 649 651 165 688 649 651 651 490 650 649 651 648 649 648 647 650 652 165 490 487 651 650 651 649 648 645 652 79 79 166 166 490 687 688 116 612 574 44 688 687 687 685 78 651 685 687 78 652 690 687 689 686 686 690 221 221 221 63 222 221 222 222 222 222 5 5 14 11 4 59 58 58 162 59 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 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map __lockdep_map; struct lockdep_map *lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */ static cpumask_var_t wq_online_cpumask; /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1U << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); while (true) { int old, tmp; old = atomic_read(&nna->nr); if (old >= max) return false; tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1); if (tmp == old) return true; } } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) kick_pool(pwq->pool); } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data = *work_data_bits(work); debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be deleted directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Move the linked * barrier work items to the worklist when deleting the grabbed * item. Also keep WORK_STRUCT_INACTIVE in work_data, so that * it doesn't participate in nr_active management in later * pwq_dec_nr_in_flight(). */ if (work_data & WORK_STRUCT_INACTIVE) move_linked_works(work, &pwq->pool->worklist, NULL); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack_noalloc(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq)))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. * * For ordered workqueue, work items must be queued on the newest pwq * for accurate order management. Guaranteed order also guarantees * non-reentrancy. See the comments above unplug_oldest_pwq(). */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void detach_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); unbind_worker(worker); list_del(&worker->node); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); detach_worker(worker); worker->pool = NULL; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void detach_dying_workers(struct list_head *cull_list) { struct worker *worker; list_for_each_entry(worker, cull_list, entry) detach_worker(worker); } static void reap_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); kthread_stop_put(worker->task); kfree(worker); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); /* get an extra task struct reference for later kthread_stop_put() */ get_task_struct(worker->task); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_unbound_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong set_pf_worker() in its self-destruct path. * This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before detach_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); pwq->stats[PWQ_STAT_COMPLETED]++; lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->watchdog_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); /* * The worker is dead and PF_WQ_WORKER is cleared, worker->pool * shouldn't be accessed, reset it to NULL in case otherwise. */ worker->pool = NULL; ida_free(&pool->worker_ida, worker->id); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) pwq->stats[PWQ_STAT_RESCUED]++; } if (!list_empty(&rescuer->scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (unlikely(!wq->lockdep_map)) return; if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(wq->lockdep_map); lock_map_release(wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, (*wq->lockdep_map)), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ if (from_cancel) { unsigned long data = *work_data_bits(work); if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted * soft interrupt processing or prevents ksoftirqd from * running by keeping flipping BH. If the BH work item * runs on a different CPU then this has no effect other * than doing the BH disable/enable dance for nothing. * This is copied from * kernel/softirq.c::tasklet_unlock_spin_wait(). */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { local_bh_disable(); local_bh_enable(); } else { cpu_relax(); } } goto out_destroy; } } wait_for_completion(&barr.done); out_destroy: destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; wq->lockdep_map = &wq->__lockdep_map; lockdep_init_map(wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); /* shut down the timers */ del_timer_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } kfree_rcu(pwq, rcu); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } static void apply_wqattrs_lock(void) { mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * * Calculate the cpumask a workqueue with @attrs should use on @pod. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* calculate possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); /* does @pod have any online CPUs @attrs wants? */ if (!cpumask_intersects(attrs->__pod_cpumask, wq_online_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); /* rescuer needs to respect wq cpumask changes */ if (ctx->wq->rescuer) set_cpus_allowed_ptr(ctx->wq->rescuer->task, unbound_effective_cpumask(ctx->wq)); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update the pwq slot for * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is in the same pod of the CPU being hot[un]plugged. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu) { struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = unbound_wq_update_pwq_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; lockdep_assert_held(&wq_pool_mutex); wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { struct worker_pool __percpu *pools; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool *pool; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) kmem_cache_free(pwq_cache, pwq); } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; if (wq->flags & WQ_UNBOUND) kthread_bind_mask(rescuer->task, unbound_effective_cpumask(wq)); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) { struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_free_wq; } /* * wq_pool_mutex protects the workqueues list, allocations of PWQs, * and the global freeze state. */ apply_wqattrs_lock(); if (alloc_and_link_pwqs(wq) < 0) goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); if (wq_online && init_rescuer(wq) < 0) goto err_unlock_destroy; apply_wqattrs_unlock(); if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; return wq; err_unlock_free_node_nr_active: apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() * completes before calling kfree(wq). */ if (wq->flags & WQ_UNBOUND) { kthread_flush_worker(pwq_release_worker); free_node_nr_active(wq->node_nr_active); } err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_unlock_destroy: apply_wqattrs_unlock(); err_destroy: destroy_workqueue(wq); return NULL; } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; va_start(args, max_active); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq_init_lockdep(wq); return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue); #ifdef CONFIG_LOCKDEP __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...) { struct workqueue_struct *wq; va_list args; va_start(args, lockdep_map); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq->lockdep_map = lockdep_map; return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_lockdep_map); #endif static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & WQ_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); cpumask_set_cpu(cpu, wq_online_cpumask); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); /** * work_on_cpu_safe_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * @key: The lock class key for lock debugging purposes * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) ret = work_on_cpu_key(cpu, fn, arg, key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * * This function can be called from cpuset code to provide a set of isolated * CPUs that should be excluded from wq_unbound_cpumask. */ int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; mutex_lock(&wq_pool_mutex); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); /* Save the current isolated cpumask & export it via sysfs */ if (!ret) cpumask_copy(wq_isolated_cpumask, exclude_cpumask); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { int i; for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) return i; } return -EINVAL; } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { ret = 0; apply_wqattrs_lock(); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); if (!ret) cpumask_copy(wq_requested_unbound_cpumask, cpumask); apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active breaks ordering guarantee. Disallow exposing * ordered workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static unsigned int wq_panic_on_stall; module_param_named(panic_on_stall, wq_panic_on_stall, uint, 0644); /* * Show workers that might prevent the processing of pending work items. * The only candidates are CPU-bound workers in the running state. * Pending work items should be handled by another idle worker * in all other situations. */ static void show_cpu_pool_hog(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (task_is_running(worker->task)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_hogs(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_hog(pool); } rcu_read_unlock(); } static void panic_on_wq_watchdog(void) { static unsigned int wq_stall; if (wq_panic_on_stall) { wq_stall++; BUG_ON(wq_stall >= wq_panic_on_stall); } } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_hogs(); if (lockup_detected) panic_on_wq_watchdog(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_online_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_online_cpumask, cpu_online_mask); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!unbound_wq_update_pwq_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call unbound_wq_update_pwq() on all workqueue * and CPU combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup);
5 5 4 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 // SPDX-License-Identifier: GPL-2.0-only /* * Card-specific functions for the Siano SMS1xxx USB dongle * * Copyright (c) 2008 Michael Krufky <mkrufky@linuxtv.org> */ #include "sms-cards.h" #include "smsir.h" #include <linux/module.h> static struct sms_board sms_boards[] = { [SMS_BOARD_UNKNOWN] = { .name = "Unknown board", .type = SMS_UNKNOWN_TYPE, .default_mode = DEVICE_MODE_NONE, }, [SMS1XXX_BOARD_SIANO_STELLAR] = { .name = "Siano Stellar Digital Receiver", .type = SMS_STELLAR, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_SIANO_NOVA_A] = { .name = "Siano Nova A Digital Receiver", .type = SMS_NOVA_A0, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_SIANO_NOVA_B] = { .name = "Siano Nova B Digital Receiver", .type = SMS_NOVA_B0, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_SIANO_VEGA] = { .name = "Siano Vega Digital Receiver", .type = SMS_VEGA, .default_mode = DEVICE_MODE_CMMB, }, [SMS1XXX_BOARD_HAUPPAUGE_CATAMOUNT] = { .name = "Hauppauge Catamount", .type = SMS_STELLAR, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_STELLAR, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_HAUPPAUGE_OKEMO_A] = { .name = "Hauppauge Okemo-A", .type = SMS_NOVA_A0, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_NOVA_A, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_HAUPPAUGE_OKEMO_B] = { .name = "Hauppauge Okemo-B", .type = SMS_NOVA_B0, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_NOVA_B, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_HAUPPAUGE_WINDHAM] = { .name = "Hauppauge WinTV MiniStick", .type = SMS_NOVA_B0, .fw[DEVICE_MODE_ISDBT_BDA] = SMS_FW_ISDBT_HCW_55XXX, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_HCW_55XXX, .default_mode = DEVICE_MODE_DVBT_BDA, .rc_codes = RC_MAP_HAUPPAUGE, .board_cfg.leds_power = 26, .board_cfg.led0 = 27, .board_cfg.led1 = 28, .board_cfg.ir = 9, .led_power = 26, .led_lo = 27, .led_hi = 28, }, [SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD] = { .name = "Hauppauge WinTV MiniCard", .type = SMS_NOVA_B0, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_HCW_55XXX, .default_mode = DEVICE_MODE_DVBT_BDA, .lna_ctrl = 29, .board_cfg.foreign_lna0_ctrl = 29, .rf_switch = 17, .board_cfg.rf_switch_uhf = 17, }, [SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD_R2] = { .name = "Hauppauge WinTV MiniCard Rev 2", .type = SMS_NOVA_B0, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVBT_HCW_55XXX, .default_mode = DEVICE_MODE_DVBT_BDA, .lna_ctrl = -1, }, [SMS1XXX_BOARD_SIANO_NICE] = { .name = "Siano Nice Digital Receiver", .type = SMS_NOVA_B0, .default_mode = DEVICE_MODE_DVBT_BDA, }, [SMS1XXX_BOARD_SIANO_VENICE] = { .name = "Siano Venice Digital Receiver", .type = SMS_VEGA, .default_mode = DEVICE_MODE_CMMB, }, [SMS1XXX_BOARD_SIANO_STELLAR_ROM] = { .name = "Siano Stellar Digital Receiver ROM", .type = SMS_STELLAR, .default_mode = DEVICE_MODE_DVBT_BDA, .intf_num = 1, }, [SMS1XXX_BOARD_ZTE_DVB_DATA_CARD] = { .name = "ZTE Data Card Digital Receiver", .type = SMS_NOVA_B0, .default_mode = DEVICE_MODE_DVBT_BDA, .intf_num = 5, .mtu = 15792, }, [SMS1XXX_BOARD_ONDA_MDTV_DATA_CARD] = { .name = "ONDA Data Card Digital Receiver", .type = SMS_NOVA_B0, .default_mode = DEVICE_MODE_DVBT_BDA, .intf_num = 6, .mtu = 15792, }, [SMS1XXX_BOARD_SIANO_MING] = { .name = "Siano Ming Digital Receiver", .type = SMS_MING, .default_mode = DEVICE_MODE_CMMB, }, [SMS1XXX_BOARD_SIANO_PELE] = { .name = "Siano Pele Digital Receiver", .type = SMS_PELE, .default_mode = DEVICE_MODE_ISDBT_BDA, }, [SMS1XXX_BOARD_SIANO_RIO] = { .name = "Siano Rio Digital Receiver", .type = SMS_RIO, .default_mode = DEVICE_MODE_ISDBT_BDA, }, [SMS1XXX_BOARD_SIANO_DENVER_1530] = { .name = "Siano Denver (ATSC-M/H) Digital Receiver", .type = SMS_DENVER_1530, .default_mode = DEVICE_MODE_ATSC, .crystal = 2400, }, [SMS1XXX_BOARD_SIANO_DENVER_2160] = { .name = "Siano Denver (TDMB) Digital Receiver", .type = SMS_DENVER_2160, .default_mode = DEVICE_MODE_DAB_TDMB, }, [SMS1XXX_BOARD_PCTV_77E] = { .name = "Hauppauge microStick 77e", .type = SMS_NOVA_B0, .fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVB_NOVA_12MHZ_B0, .default_mode = DEVICE_MODE_DVBT_BDA, }, }; struct sms_board *sms_get_board(unsigned id) { BUG_ON(id >= ARRAY_SIZE(sms_boards)); return &sms_boards[id]; } EXPORT_SYMBOL_GPL(sms_get_board); static inline void sms_gpio_assign_11xx_default_led_config( struct smscore_config_gpio *p_gpio_config) { p_gpio_config->direction = SMS_GPIO_DIRECTION_OUTPUT; p_gpio_config->inputcharacteristics = SMS_GPIO_INPUTCHARACTERISTICS_NORMAL; p_gpio_config->outputdriving = SMS_GPIO_OUTPUTDRIVING_4mA; p_gpio_config->outputslewrate = SMS_GPIO_OUTPUT_SLEW_RATE_0_45_V_NS; p_gpio_config->pullupdown = SMS_GPIO_PULLUPDOWN_NONE; } int sms_board_event(struct smscore_device_t *coredev, enum SMS_BOARD_EVENTS gevent) { struct smscore_config_gpio my_gpio_config; sms_gpio_assign_11xx_default_led_config(&my_gpio_config); switch (gevent) { case BOARD_EVENT_POWER_INIT: /* including hotplug */ break; /* BOARD_EVENT_BIND */ case BOARD_EVENT_POWER_SUSPEND: break; /* BOARD_EVENT_POWER_SUSPEND */ case BOARD_EVENT_POWER_RESUME: break; /* BOARD_EVENT_POWER_RESUME */ case BOARD_EVENT_BIND: break; /* BOARD_EVENT_BIND */ case BOARD_EVENT_SCAN_PROG: break; /* BOARD_EVENT_SCAN_PROG */ case BOARD_EVENT_SCAN_COMP: break; /* BOARD_EVENT_SCAN_COMP */ case BOARD_EVENT_EMERGENCY_WARNING_SIGNAL: break; /* BOARD_EVENT_EMERGENCY_WARNING_SIGNAL */ case BOARD_EVENT_FE_LOCK: break; /* BOARD_EVENT_FE_LOCK */ case BOARD_EVENT_FE_UNLOCK: break; /* BOARD_EVENT_FE_UNLOCK */ case BOARD_EVENT_DEMOD_LOCK: break; /* BOARD_EVENT_DEMOD_LOCK */ case BOARD_EVENT_DEMOD_UNLOCK: break; /* BOARD_EVENT_DEMOD_UNLOCK */ case BOARD_EVENT_RECEPTION_MAX_4: break; /* BOARD_EVENT_RECEPTION_MAX_4 */ case BOARD_EVENT_RECEPTION_3: break; /* BOARD_EVENT_RECEPTION_3 */ case BOARD_EVENT_RECEPTION_2: break; /* BOARD_EVENT_RECEPTION_2 */ case BOARD_EVENT_RECEPTION_1: break; /* BOARD_EVENT_RECEPTION_1 */ case BOARD_EVENT_RECEPTION_LOST_0: break; /* BOARD_EVENT_RECEPTION_LOST_0 */ case BOARD_EVENT_MULTIPLEX_OK: break; /* BOARD_EVENT_MULTIPLEX_OK */ case BOARD_EVENT_MULTIPLEX_ERRORS: break; /* BOARD_EVENT_MULTIPLEX_ERRORS */ default: pr_err("Unknown SMS board event\n"); break; } return 0; } EXPORT_SYMBOL_GPL(sms_board_event); static int sms_set_gpio(struct smscore_device_t *coredev, int pin, int enable) { int lvl, ret; u32 gpio; struct smscore_config_gpio gpioconfig = { .direction = SMS_GPIO_DIRECTION_OUTPUT, .pullupdown = SMS_GPIO_PULLUPDOWN_NONE, .inputcharacteristics = SMS_GPIO_INPUTCHARACTERISTICS_NORMAL, .outputslewrate = SMS_GPIO_OUTPUT_SLEW_RATE_FAST, .outputdriving = SMS_GPIO_OUTPUTDRIVING_S_4mA, }; if (pin == 0) return -EINVAL; if (pin < 0) { /* inverted gpio */ gpio = pin * -1; lvl = enable ? 0 : 1; } else { gpio = pin; lvl = enable ? 1 : 0; } ret = smscore_configure_gpio(coredev, gpio, &gpioconfig); if (ret < 0) return ret; return smscore_set_gpio(coredev, gpio, lvl); } int sms_board_setup(struct smscore_device_t *coredev) { int board_id = smscore_get_board_id(coredev); struct sms_board *board = sms_get_board(board_id); switch (board_id) { case SMS1XXX_BOARD_HAUPPAUGE_WINDHAM: /* turn off all LEDs */ sms_set_gpio(coredev, board->led_power, 0); sms_set_gpio(coredev, board->led_hi, 0); sms_set_gpio(coredev, board->led_lo, 0); break; case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD_R2: case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD: /* turn off LNA */ sms_set_gpio(coredev, board->lna_ctrl, 0); break; } return 0; } EXPORT_SYMBOL_GPL(sms_board_setup); int sms_board_power(struct smscore_device_t *coredev, int onoff) { int board_id = smscore_get_board_id(coredev); struct sms_board *board = sms_get_board(board_id); switch (board_id) { case SMS1XXX_BOARD_HAUPPAUGE_WINDHAM: /* power LED */ sms_set_gpio(coredev, board->led_power, onoff ? 1 : 0); break; case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD_R2: case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD: /* LNA */ if (!onoff) sms_set_gpio(coredev, board->lna_ctrl, 0); break; } return 0; } EXPORT_SYMBOL_GPL(sms_board_power); int sms_board_led_feedback(struct smscore_device_t *coredev, int led) { int board_id = smscore_get_board_id(coredev); struct sms_board *board = sms_get_board(board_id); /* don't touch GPIO if LEDs are already set */ if (smscore_led_state(coredev, -1) == led) return 0; switch (board_id) { case SMS1XXX_BOARD_HAUPPAUGE_WINDHAM: sms_set_gpio(coredev, board->led_lo, (led & SMS_LED_LO) ? 1 : 0); sms_set_gpio(coredev, board->led_hi, (led & SMS_LED_HI) ? 1 : 0); smscore_led_state(coredev, led); break; } return 0; } EXPORT_SYMBOL_GPL(sms_board_led_feedback); int sms_board_lna_control(struct smscore_device_t *coredev, int onoff) { int board_id = smscore_get_board_id(coredev); struct sms_board *board = sms_get_board(board_id); pr_debug("%s: LNA %s\n", __func__, onoff ? "enabled" : "disabled"); switch (board_id) { case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD_R2: case SMS1XXX_BOARD_HAUPPAUGE_TIGER_MINICARD: sms_set_gpio(coredev, board->rf_switch, onoff ? 1 : 0); return sms_set_gpio(coredev, board->lna_ctrl, onoff ? 1 : 0); } return -EINVAL; } EXPORT_SYMBOL_GPL(sms_board_lna_control); int sms_board_load_modules(int id) { request_module("smsdvb"); return 0; } EXPORT_SYMBOL_GPL(sms_board_load_modules);
117 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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tlb #if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TLB_H #include <linux/mm_types.h> #include <linux/tracepoint.h> #define TLB_FLUSH_REASON \ EM( TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" ) \ EM( TLB_REMOTE_SHOOTDOWN, "remote shootdown" ) \ EM( TLB_LOCAL_SHOOTDOWN, "local shootdown" ) \ EM( TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" ) \ EMe( TLB_REMOTE_SEND_IPI, "remote ipi send" ) /* * First define the enums in TLB_FLUSH_REASON to be exported to userspace * via TRACE_DEFINE_ENUM(). */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); TLB_FLUSH_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } TRACE_EVENT(tlb_flush, TP_PROTO(int reason, unsigned long pages), TP_ARGS(reason, pages), TP_STRUCT__entry( __field( int, reason) __field(unsigned long, pages) ), TP_fast_assign( __entry->reason = reason; __entry->pages = pages; ), TP_printk("pages:%ld reason:%s (%d)", __entry->pages, __print_symbolic(__entry->reason, TLB_FLUSH_REASON), __entry->reason) ); #endif /* _TRACE_TLB_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
56 42 42 41 42 42 933 891 43 895 896 895 1423 1425 13 32 56 94 38 49 32 56 54 55 38 38 50 44 44 44 6 2 2 4 5 41 41 2 2 1 12 12 12 12 12 92 61 1 56 13 13 2 2 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 // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/bug.h> #include <net/page_pool/helpers.h> #include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #include <net/xdp_sock_drv.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_free(&mem_id_pool, xa->mem.id); kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; int type = mem->type; int id = mem->id; /* Reset mem info to defaults */ mem->id = 0; mem->type = 0; if (id == 0) return; if (type == MEM_TYPE_PAGE_POOL) { xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } xdp_unreg_mem_model(&xdp_rxq->mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->napi_id = napi_id; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (!__is_supported_mem_type(type)) return ERR_PTR(-EOPNOTSUPP); mem->type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ return NULL; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) return ERR_PTR(ret); } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return ERR_PTR(-ENOMEM); mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } mem->id = id; xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_free(&mem_id_pool, mem->id); mem->id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem); mutex_unlock(&mem_id_lock); return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return ERR_PTR(errno); } int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); return 0; } EXPORT_SYMBOL_GPL(xdp_reg_mem_model); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); if (trace_mem_connect_enabled() && xdp_alloc) trace_mem_connect(xdp_alloc, xdp_rxq); return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp) { struct page *page; switch (mem->type) { case MEM_TYPE_PAGE_POOL: page = virt_to_head_page(data); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as mem->type knows this a page_pool page */ page_pool_put_full_page(page->pp, page, napi_direct); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(data); break; case MEM_TYPE_PAGE_ORDER0: page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ xsk_buff_free(xdp); break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); break; } } void xdp_return_frame(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; int i; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { struct page *page = skb_frag_page(&sinfo->frags[i]); __xdp_return(page_address(page), &xdpf->mem, false, NULL); } out: __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; int i; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { struct page *page = skb_frag_page(&sinfo->frags[i]); __xdp_return(page_address(page), &xdpf->mem, true, NULL); } out: __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); /* XDP bulk APIs introduce a defer/flush mechanism to return * pages belonging to the same xdp_mem_allocator object * (identified via the mem.id field) in bulk to optimize * I-cache and D-cache. * The bulk queue size is set to 16 to be aligned to how * XDP_REDIRECT bulking works. The bulk is flushed when * it is full or when mem.id changes. * xdp_frame_bulk is usually stored/allocated on the function * call-stack to avoid locking penalties. */ void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) { struct xdp_mem_allocator *xa = bq->xa; if (unlikely(!xa || !bq->count)) return; page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count); /* bq->xa is not cleared to save lookup, if mem.id same in next bulk */ bq->count = 0; } EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk); /* Must be called with rcu_read_lock held */ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq) { struct xdp_mem_info *mem = &xdpf->mem; struct xdp_mem_allocator *xa; if (mem->type != MEM_TYPE_PAGE_POOL) { xdp_return_frame(xdpf); return; } xa = bq->xa; if (unlikely(!xa)) { xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); bq->count = 0; bq->xa = xa; } if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); if (unlikely(mem->id != xa->mem.id)) { xdp_flush_frame_bulk(bq); bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); } if (unlikely(xdp_frame_has_frags(xdpf))) { struct skb_shared_info *sinfo; int i; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; bq->q[bq->count++] = skb_frag_address(frag); if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); } } bq->q[bq->count++] = xdpf->data; } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); void xdp_return_buff(struct xdp_buff *xdp) { struct skb_shared_info *sinfo; int i; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); for (i = 0; i < sinfo->nr_frags; i++) { struct page *page = skb_frag_page(&sinfo->frags[i]); __xdp_return(page_address(page), &xdp->rxq->mem, true, xdp); } out: __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } EXPORT_SYMBOL_GPL(xdp_return_buff); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); /* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */ void xdp_warn(const char *msg, const char *func, const int line) { WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; u8 nr_frags; /* xdp frags frame */ if (unlikely(xdp_frame_has_frags(xdpf))) nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; /* Memory size backing xdp_frame data already have reserved * room for build_skb to place skb_shared_info in tailroom. */ frame_size = xdpf->frame_sz; hard_start = xdpf->data - headroom; skb = build_skb_around(skb, hard_start, frame_size); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); if (unlikely(xdp_frame_has_frags(xdpf))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, nr_frags * xdpf->frame_sz, xdp_frame_is_frag_pfmemalloc(xdpf)); /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) * - HW RX hash (skb_set_hash) * - RX ring dev queue index (skb_record_rx_queue) */ if (xdpf->mem.type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ xdp_scrub_frame(xdpf); return skb; } EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) { unsigned int headroom, totalsize; struct xdp_frame *nxdpf; struct page *page; void *addr; headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; if (unlikely(totalsize > PAGE_SIZE)) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); memcpy(addr, xdpf, totalsize); nxdpf = addr; nxdpf->data = addr + headroom; nxdpf->frame_sz = PAGE_SIZE; nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; nxdpf->mem.id = 0; return nxdpf; } __bpf_kfunc_start_defs(); /** * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp. * @ctx: XDP context pointer. * @timestamp: Return value pointer. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc * * ``-ENODATA`` : means no RX-timestamp available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. * @rss_type: Return value pointer for RSS type. * * The RSS hash type (@rss_type) specifies what portion of packet headers NIC * hardware used when calculating RSS hash value. The RSS type can be decoded * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag * @ctx: XDP context pointer. * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) * * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** * and should be used as follows: * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` * * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. * Driver is expected to provide those in **host byte order (usually LE)**, * so the bpf program should not perform byte conversion. * According to 802.1Q standard, *VLAN TCI (Tag control information)* * is a bit field that contains: * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, * *Drop eligible indicator (DEI)* - 1 bit, * *Priority code point (PCP)* - 3 bits. * For detailed meaning of DEI and PCP, please refer to other sources. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc * * ``-ENODATA`` : VLAN tag was not stripped or is not available */ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { return -EOPNOTSUPP; } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, .set = &xdp_metadata_kfunc_ids, }; BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted) #define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC u32 bpf_xdp_metadata_kfunc_id(int id) { /* xdp_metadata_kfunc_ids is sorted and can't be used */ return xdp_metadata_kfunc_ids_unsorted[id]; } bool bpf_dev_bound_kfunc_id(u32 btf_id) { return btf_id_set8_contains(&xdp_metadata_kfunc_ids, btf_id); } static int __init xdp_metadata_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { val &= NETDEV_XDP_ACT_MASK; if (dev->xdp_features == val) return; dev->xdp_features = val; if (dev->reg_state == NETREG_REGISTERED) call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); } EXPORT_SYMBOL_GPL(xdp_set_features_flag); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); if (support_sg) val |= NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target(struct net_device *dev) { xdp_features_t val = dev->xdp_features; val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
10 51 21 21 6 2 3 3 1 1 3 1 17 2 20 8 7 34 30 22 1 8 2 4 1 4 2 1 4 3 1 1 2 68 1 5 1 1 1 1 34 6 5 1 30 1 1 2 2 30 31 48 1 7 1 2 5 5 2 3 3 3 2 1 2 2 2 1 4 4 4 1 1 3 2 24 14 4 7 5 8 2 5 27 3 1 1 3 3 2 2 2 1 175 176 1 74 108 13 28 30 42 1 10 11 2 10 10 10 1 1 1 2 8 19 1 2 1 3 1 11 4 3 2 1 1 3 1 2 1 6 5 2 2 2 5 2 1 1 1 1 3 5 1 7 4 1 3 2 2 1 3 4 15 2 1 1 9 13 11 3 1 2 1 1 1 1 1 1 1 1 1 1 2 5 12 8 11 69 68 1 2 3 26 38 19 16 1 2 2 1 2 17 18 1 19 18 19 19 19 131 129 114 19 3 1 2 3 1 2 1 1 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 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 // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2021, Red Hat. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <net/sock.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" #define MIN_INFO_OPTLEN_SIZE 16 #define MIN_FULL_INFO_OPTLEN_SIZE 40 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { msk_owned_by_me(msk); if (likely(!__mptcp_check_fallback(msk))) return NULL; return msk->first; } static u32 sockopt_seq_reset(const struct sock *sk) { sock_owned_by_me(sk); /* Highbits contain state. Allows to distinguish sockopt_seq * of listener and established: * s0 = new_listener() * sockopt(s0) - seq is 1 * s1 = accept(s0) - s1 inherits seq 1 if listener sk (s0) * sockopt(s0) - seq increments to 2 on s0 * sockopt(s1) // seq increments to 2 on s1 (different option) * new ssk completes join, inherits options from s0 // seq 2 * Needs sync from mptcp join logic, but ssk->seq == msk->seq * * Set High order bits to sk_state so ssk->seq == msk->seq test * will fail. */ return (u32)sk->sk_state << 24u; } static void sockopt_seq_inc(struct mptcp_sock *msk) { u32 seq = (msk->setsockopt_seq + 1) & 0x00ffffff; msk->setsockopt_seq = sockopt_seq_reset((struct sock *)msk) + seq; } static int mptcp_get_int_option(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen, int *val) { if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(val, optval, sizeof(*val))) return -EFAULT; return 0; } static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; lock_sock(sk); sockopt_seq_inc(msk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); switch (optname) { case SO_DEBUG: sock_valbool_flag(ssk, SOCK_DBG, !!val); break; case SO_KEEPALIVE: if (ssk->sk_prot->keepalive) ssk->sk_prot->keepalive(ssk, !!val); sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val); break; case SO_PRIORITY: WRITE_ONCE(ssk->sk_priority, val); break; case SO_SNDBUF: case SO_SNDBUFFORCE: ssk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; break; case SO_RCVBUF: case SO_RCVBUFFORCE: ssk->sk_userlocks |= SOCK_RCVBUF_LOCK; WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; case SO_INCOMING_CPU: WRITE_ONCE(ssk->sk_incoming_cpu, val); break; } subflow->setsockopt_seq = msk->setsockopt_seq; unlock_sock_fast(ssk, slow); } release_sock(sk); } static int mptcp_sol_socket_intval(struct mptcp_sock *msk, int optname, int val) { sockptr_t optval = KERNEL_SOCKPTR(&val); struct sock *sk = (struct sock *)msk; int ret; ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, sizeof(val)); if (ret) return ret; mptcp_sol_socket_sync_intval(msk, optname, val); return 0; } static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val) { struct sock *sk = (struct sock *)msk; WRITE_ONCE(sk->sk_incoming_cpu, val); mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val); } static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val) { sockptr_t optval = KERNEL_SOCKPTR(&val); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; int ret; ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, sizeof(val)); if (ret) return ret; lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); sock_set_timestamp(sk, optname, !!val); unlock_sock_fast(ssk, slow); } release_sock(sk); return 0; } static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { int val, ret; ret = mptcp_get_int_option(msk, optval, optlen, &val); if (ret) return ret; switch (optname) { case SO_KEEPALIVE: case SO_DEBUG: case SO_MARK: case SO_PRIORITY: case SO_SNDBUF: case SO_SNDBUFFORCE: case SO_RCVBUF: case SO_RCVBUFFORCE: return mptcp_sol_socket_intval(msk, optname, val); case SO_INCOMING_CPU: mptcp_so_incoming_cpu(msk, val); return 0; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; } static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct so_timestamping timestamping; int ret; if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(&timestamping, optval, sizeof(timestamping))) return -EFAULT; } else if (optlen == sizeof(int)) { memset(&timestamping, 0, sizeof(timestamping)); if (copy_from_sockptr(&timestamping.flags, optval, sizeof(int))) return -EFAULT; } else { return -EINVAL; } ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, KERNEL_SOCKPTR(&timestamping), sizeof(timestamping)); if (ret) return ret; lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); sock_set_timestamping(sk, optname, timestamping); unlock_sock_fast(ssk, slow); } release_sock(sk); return 0; } static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct linger ling; sockptr_t kopt; int ret; if (optlen < sizeof(ling)) return -EINVAL; if (copy_from_sockptr(&ling, optval, sizeof(ling))) return -EFAULT; kopt = KERNEL_SOCKPTR(&ling); ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, SO_LINGER, kopt, sizeof(ling)); if (ret) return ret; lock_sock(sk); sockopt_seq_inc(msk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); if (!ling.l_onoff) { sock_reset_flag(ssk, SOCK_LINGER); } else { ssk->sk_lingertime = sk->sk_lingertime; sock_set_flag(ssk, SOCK_LINGER); } subflow->setsockopt_seq = msk->setsockopt_seq; unlock_sock_fast(ssk, slow); } release_sock(sk); return 0; } static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; struct sock *ssk; int ret; switch (optname) { case SO_REUSEPORT: case SO_REUSEADDR: case SO_BINDTODEVICE: case SO_BINDTOIFINDEX: lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { release_sock(sk); return PTR_ERR(ssk); } ret = sk_setsockopt(ssk, SOL_SOCKET, optname, optval, optlen); if (ret == 0) { if (optname == SO_REUSEPORT) sk->sk_reuseport = ssk->sk_reuseport; else if (optname == SO_REUSEADDR) sk->sk_reuse = ssk->sk_reuse; else if (optname == SO_BINDTODEVICE) sk->sk_bound_dev_if = ssk->sk_bound_dev_if; else if (optname == SO_BINDTOIFINDEX) sk->sk_bound_dev_if = ssk->sk_bound_dev_if; } release_sock(sk); return ret; case SO_KEEPALIVE: case SO_PRIORITY: case SO_SNDBUF: case SO_SNDBUFFORCE: case SO_RCVBUF: case SO_RCVBUFFORCE: case SO_MARK: case SO_INCOMING_CPU: case SO_DEBUG: case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_timestamping(msk, optname, optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); case SO_RCVLOWAT: case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: case SO_BUSY_POLL: case SO_PREFER_BUSY_POLL: case SO_BUSY_POLL_BUDGET: /* No need to copy: only relevant for msk */ return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); case SO_NO_CHECK: case SO_DONTROUTE: case SO_BROADCAST: case SO_BSDCOMPAT: case SO_PASSCRED: case SO_PASSPIDFD: case SO_PASSSEC: case SO_RXQ_OVFL: case SO_WIFI_STATUS: case SO_NOFCS: case SO_SELECT_ERR_QUEUE: return 0; } /* SO_OOBINLINE is not supported, let's avoid the related mess * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF, * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER, * we must be careful with subflows * * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks * explicitly the sk_protocol field * * SO_PEEK_OFF is unsupported, as it is for plain TCP * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows * SO_CNX_ADVICE is currently unsupported, could possibly be relevant, * but likely needs careful design * * SO_ZEROCOPY is currently unsupported, TODO in sndmsg * SO_TXTIME is currently unsupported */ return -EOPNOTSUPP; } static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; int ret = -EOPNOTSUPP; struct sock *ssk; switch (optname) { case IPV6_V6ONLY: case IPV6_TRANSPARENT: case IPV6_FREEBIND: lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { release_sock(sk); return PTR_ERR(ssk); } ret = tcp_setsockopt(ssk, SOL_IPV6, optname, optval, optlen); if (ret != 0) { release_sock(sk); return ret; } sockopt_seq_inc(msk); switch (optname) { case IPV6_V6ONLY: sk->sk_ipv6only = ssk->sk_ipv6only; break; case IPV6_TRANSPARENT: inet_assign_bit(TRANSPARENT, sk, inet_test_bit(TRANSPARENT, ssk)); break; case IPV6_FREEBIND: inet_assign_bit(FREEBIND, sk, inet_test_bit(FREEBIND, ssk)); break; } release_sock(sk); break; } return ret; } static bool mptcp_supported_sockopt(int level, int optname) { if (level == SOL_IP) { switch (optname) { /* should work fine */ case IP_FREEBIND: case IP_TRANSPARENT: case IP_BIND_ADDRESS_NO_PORT: case IP_LOCAL_PORT_RANGE: /* the following are control cmsg related */ case IP_PKTINFO: case IP_RECVTTL: case IP_RECVTOS: case IP_RECVOPTS: case IP_RETOPTS: case IP_PASSSEC: case IP_RECVORIGDSTADDR: case IP_CHECKSUM: case IP_RECVFRAGSIZE: /* common stuff that need some love */ case IP_TOS: case IP_TTL: case IP_MTU_DISCOVER: case IP_RECVERR: /* possibly less common may deserve some love */ case IP_MINTTL: /* the following is apparently a no-op for plain TCP */ case IP_RECVERR_RFC4884: return true; } /* IP_OPTIONS is not supported, needs subflow care */ /* IP_HDRINCL, IP_NODEFRAG are not supported, RAW specific */ /* IP_MULTICAST_TTL, IP_MULTICAST_LOOP, IP_UNICAST_IF, * IP_ADD_MEMBERSHIP, IP_ADD_SOURCE_MEMBERSHIP, IP_DROP_MEMBERSHIP, * IP_DROP_SOURCE_MEMBERSHIP, IP_BLOCK_SOURCE, IP_UNBLOCK_SOURCE, * MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP MCAST_JOIN_SOURCE_GROUP, * MCAST_LEAVE_SOURCE_GROUP, MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE, * MCAST_MSFILTER, IP_MULTICAST_ALL are not supported, better not deal * with mcast stuff */ /* IP_IPSEC_POLICY, IP_XFRM_POLICY are nut supported, unrelated here */ return false; } if (level == SOL_IPV6) { switch (optname) { case IPV6_V6ONLY: /* the following are control cmsg related */ case IPV6_RECVPKTINFO: case IPV6_2292PKTINFO: case IPV6_RECVHOPLIMIT: case IPV6_2292HOPLIMIT: case IPV6_RECVRTHDR: case IPV6_2292RTHDR: case IPV6_RECVHOPOPTS: case IPV6_2292HOPOPTS: case IPV6_RECVDSTOPTS: case IPV6_2292DSTOPTS: case IPV6_RECVTCLASS: case IPV6_FLOWINFO: case IPV6_RECVPATHMTU: case IPV6_RECVORIGDSTADDR: case IPV6_RECVFRAGSIZE: /* the following ones need some love but are quite common */ case IPV6_TCLASS: case IPV6_TRANSPARENT: case IPV6_FREEBIND: case IPV6_PKTINFO: case IPV6_2292PKTOPTIONS: case IPV6_UNICAST_HOPS: case IPV6_MTU_DISCOVER: case IPV6_MTU: case IPV6_RECVERR: case IPV6_FLOWINFO_SEND: case IPV6_FLOWLABEL_MGR: case IPV6_MINHOPCOUNT: case IPV6_DONTFRAG: case IPV6_AUTOFLOWLABEL: /* the following one is a no-op for plain TCP */ case IPV6_RECVERR_RFC4884: return true; } /* IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, IPV6_RTHDR, IPV6_DSTOPTS are * not supported */ /* IPV6_MULTICAST_HOPS, IPV6_MULTICAST_LOOP, IPV6_UNICAST_IF, * IPV6_MULTICAST_IF, IPV6_ADDRFORM, * IPV6_ADD_MEMBERSHIP, IPV6_DROP_MEMBERSHIP, IPV6_JOIN_ANYCAST, * IPV6_LEAVE_ANYCAST, IPV6_MULTICAST_ALL, MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP, * MCAST_JOIN_SOURCE_GROUP, MCAST_LEAVE_SOURCE_GROUP, * MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE, MCAST_MSFILTER * are not supported better not deal with mcast */ /* IPV6_ROUTER_ALERT, IPV6_ROUTER_ALERT_ISOLATE are not supported, since are evil */ /* IPV6_IPSEC_POLICY, IPV6_XFRM_POLICY are not supported */ /* IPV6_ADDR_PREFERENCES is not supported, we must be careful with subflows */ return false; } if (level == SOL_TCP) { switch (optname) { /* the following are no-op or should work just fine */ case TCP_THIN_DUPACK: case TCP_DEFER_ACCEPT: /* the following need some love */ case TCP_MAXSEG: case TCP_NODELAY: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_CONGESTION: case TCP_CORK: case TCP_KEEPIDLE: case TCP_KEEPINTVL: case TCP_KEEPCNT: case TCP_SYNCNT: case TCP_SAVE_SYN: case TCP_LINGER2: case TCP_WINDOW_CLAMP: case TCP_QUICKACK: case TCP_USER_TIMEOUT: case TCP_TIMESTAMP: case TCP_NOTSENT_LOWAT: case TCP_TX_DELAY: case TCP_INQ: case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: return true; } /* TCP_MD5SIG, TCP_MD5SIG_EXT are not supported, MD5 is not compatible with MPTCP */ /* TCP_REPAIR, TCP_REPAIR_QUEUE, TCP_QUEUE_SEQ, TCP_REPAIR_OPTIONS, * TCP_REPAIR_WINDOW are not supported, better avoid this mess */ } return false; } static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; char name[TCP_CA_NAME_MAX]; bool cap_net_admin; int ret; if (optlen < 1) return -EINVAL; ret = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX - 1, optlen)); if (ret < 0) return -EFAULT; name[ret] = 0; cap_net_admin = ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN); ret = 0; lock_sock(sk); sockopt_seq_inc(msk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err; lock_sock(ssk); err = tcp_set_congestion_control(ssk, name, true, cap_net_admin); if (err < 0 && ret == 0) ret = err; subflow->setsockopt_seq = msk->setsockopt_seq; release_sock(ssk); } if (ret == 0) strscpy(msk->ca_name, name, sizeof(msk->ca_name)); release_sock(sk); return ret; } static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max, int (*set_val)(struct sock *, int), int *msk_val, int val) { struct mptcp_subflow_context *subflow; int err = 0; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int ret; lock_sock(ssk); ret = set_val(ssk, val); err = err ? : ret; release_sock(ssk); } if (!err) { *msk_val = val; sockopt_seq_inc(msk); } return err; } static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; sockopt_seq_inc(msk); msk->cork = !!val; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); __tcp_sock_set_cork(ssk, !!val); release_sock(ssk); } if (!val) mptcp_check_and_set_pending(sk); return 0; } static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; sockopt_seq_inc(msk); msk->nodelay = !!val; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); __tcp_sock_set_nodelay(ssk, !!val); release_sock(ssk); } if (val) mptcp_check_and_set_pending(sk); return 0; } static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; struct sock *ssk; int err; err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen); if (err != 0) return err; lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { release_sock(sk); return PTR_ERR(ssk); } switch (optname) { case IP_FREEBIND: inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); break; case IP_TRANSPARENT: inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); break; case IP_BIND_ADDRESS_NO_PORT: inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); break; case IP_LOCAL_PORT_RANGE: WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range)); break; default: release_sock(sk); WARN_ON_ONCE(1); return -EOPNOTSUPP; } sockopt_seq_inc(msk); release_sock(sk); return 0; } static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; int err, val; err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen); if (err != 0) return err; lock_sock(sk); sockopt_seq_inc(msk); val = READ_ONCE(inet_sk(sk)->tos); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(ssk); __ip_sock_set_tos(ssk, val); unlock_sock_fast(ssk, slow); } release_sock(sk); return 0; } static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { switch (optname) { case IP_FREEBIND: case IP_TRANSPARENT: case IP_BIND_ADDRESS_NO_PORT: case IP_LOCAL_PORT_RANGE: return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen); case IP_TOS: return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen); } return -EOPNOTSUPP; } static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; struct sock *ssk; int ret; /* Limit to first subflow, before the connection establishment */ lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { ret = PTR_ERR(ssk); goto unlock; } ret = tcp_setsockopt(ssk, level, optname, optval, optlen); unlock: release_sock(sk); return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = (void *)msk; int ret, val; switch (optname) { case TCP_ULP: return -EOPNOTSUPP; case TCP_CONGESTION: return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen); case TCP_DEFER_ACCEPT: /* See tcp.c: TCP_DEFER_ACCEPT does not fail */ mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); return 0; case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: return mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); } ret = mptcp_get_int_option(msk, optval, optlen, &val); if (ret) return ret; lock_sock(sk); switch (optname) { case TCP_INQ: if (val < 0 || val > 1) ret = -EINVAL; else msk->recvmsg_inq = !!val; break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(msk->notsent_lowat, val); mptcp_write_space(sk); break; case TCP_CORK: ret = __mptcp_setsockopt_sol_tcp_cork(msk, val); break; case TCP_NODELAY: ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val); break; case TCP_KEEPIDLE: ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE, &tcp_sock_set_keepidle_locked, &msk->keepalive_idle, val); break; case TCP_KEEPINTVL: ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL, &tcp_sock_set_keepintvl, &msk->keepalive_intvl, val); break; case TCP_KEEPCNT: ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT, &tcp_sock_set_keepcnt, &msk->keepalive_cnt, val); break; default: ret = -ENOPROTOOPT; } release_sock(sk); return ret; } int mptcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; pr_debug("msk=%p\n", msk); if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); if (!mptcp_supported_sockopt(level, optname)) return -ENOPROTOOPT; /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the * MPTCP-level socket to configure the subflows until the subflow * is in TCP fallback, when TCP socket options are passed through * to the one remaining subflow. */ lock_sock(sk); ssk = __mptcp_tcp_fallback(msk); release_sock(sk); if (ssk) return tcp_setsockopt(ssk, level, optname, optval, optlen); if (level == SOL_IP) return mptcp_setsockopt_v4(msk, optname, optval, optlen); if (level == SOL_IPV6) return mptcp_setsockopt_v6(msk, optname, optval, optlen); if (level == SOL_TCP) return mptcp_setsockopt_sol_tcp(msk, optname, optval, optlen); return -EOPNOTSUPP; } static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = (struct sock *)msk; struct sock *ssk; int ret; lock_sock(sk); ssk = msk->first; if (ssk) { ret = tcp_getsockopt(ssk, level, optname, optval, optlen); goto out; } ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { ret = PTR_ERR(ssk); goto out; } ret = tcp_getsockopt(ssk, level, optname, optval, optlen); out: release_sock(sk); return ret; } void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { struct sock *sk = (struct sock *)msk; u32 flags = 0; bool slow; u32 now; memset(info, 0, sizeof(*info)); info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); if (inet_sk_state_load(sk) == TCP_LISTEN) return; /* The following limits only make sense for the in-kernel PM */ if (mptcp_pm_is_kernel(msk)) { info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk); info->mptcpi_add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk); info->mptcpi_add_addr_accepted_max = mptcp_pm_get_add_addr_accept_max(msk); info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk); } if (__mptcp_check_fallback(msk)) flags |= MPTCP_INFO_FLAG_FALLBACK; if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; slow = lock_sock_fast(sk); info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); info->mptcpi_token = msk->token; info->mptcpi_write_seq = msk->write_seq; info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits; info->mptcpi_bytes_sent = msk->bytes_sent; info->mptcpi_bytes_received = msk->bytes_received; info->mptcpi_bytes_retrans = msk->bytes_retrans; info->mptcpi_subflows_total = info->mptcpi_subflows + __mptcp_has_initial_subflow(msk); now = tcp_jiffies32; info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent); info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv); unlock_sock_fast(sk, slow); mptcp_data_lock(sk); info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv); info->mptcpi_snd_una = msk->snd_una; info->mptcpi_rcv_nxt = msk->ack_seq; info->mptcpi_bytes_acked = msk->bytes_acked; mptcp_data_unlock(sk); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { struct mptcp_info m_info; int len; if (get_user(len, optlen)) return -EFAULT; /* When used only to check if a fallback to TCP happened. */ if (len == 0) return 0; len = min_t(unsigned int, len, sizeof(struct mptcp_info)); mptcp_diag_fill_info(msk, &m_info); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &m_info, len)) return -EFAULT; return 0; } static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, char __user *optval, u32 copied, int __user *optlen) { u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd)); if (copied) copied += sfd->size_subflow_data; else copied = copylen; if (put_user(copied, optlen)) return -EFAULT; if (copy_to_user(optval, sfd, copylen)) return -EFAULT; return 0; } static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, char __user *optval, int __user *optlen) { int len, copylen; if (get_user(len, optlen)) return -EFAULT; /* if mptcp_subflow_data size is changed, need to adjust * this function to deal with programs using old version. */ BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE); if (len < MIN_INFO_OPTLEN_SIZE) return -EINVAL; memset(sfd, 0, sizeof(*sfd)); copylen = min_t(unsigned int, len, sizeof(*sfd)); if (copy_from_user(sfd, optval, copylen)) return -EFAULT; /* size_subflow_data is u32, but len is signed */ if (sfd->size_subflow_data > INT_MAX || sfd->size_user > INT_MAX) return -EINVAL; if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE || sfd->size_subflow_data > len) return -EINVAL; if (sfd->num_subflows || sfd->size_kernel) return -EINVAL; return len - sfd->size_subflow_data; } static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; unsigned int sfcount = 0, copied = 0; struct mptcp_subflow_data sfd; char __user *infoptr; int len; len = mptcp_get_subflow_data(&sfd, optval, optlen); if (len < 0) return len; sfd.size_kernel = sizeof(struct tcp_info); sfd.size_user = min_t(unsigned int, sfd.size_user, sizeof(struct tcp_info)); infoptr = optval + sfd.size_subflow_data; lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); ++sfcount; if (len && len >= sfd.size_user) { struct tcp_info info; tcp_get_info(ssk, &info); if (copy_to_user(infoptr, &info, sfd.size_user)) { release_sock(sk); return -EFAULT; } infoptr += sfd.size_user; copied += sfd.size_user; len -= sfd.size_user; } } release_sock(sk); sfd.num_subflows = sfcount; if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) return -EFAULT; return 0; } static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a) { const struct inet_sock *inet = inet_sk(sk); memset(a, 0, sizeof(*a)); if (sk->sk_family == AF_INET) { a->sin_local.sin_family = AF_INET; a->sin_local.sin_port = inet->inet_sport; a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr; if (!a->sin_local.sin_addr.s_addr) a->sin_local.sin_addr.s_addr = inet->inet_saddr; a->sin_remote.sin_family = AF_INET; a->sin_remote.sin_port = inet->inet_dport; a->sin_remote.sin_addr.s_addr = inet->inet_daddr; #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); if (WARN_ON_ONCE(!np)) return; a->sin6_local.sin6_family = AF_INET6; a->sin6_local.sin6_port = inet->inet_sport; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) a->sin6_local.sin6_addr = np->saddr; else a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr; a->sin6_remote.sin6_family = AF_INET6; a->sin6_remote.sin6_port = inet->inet_dport; a->sin6_remote.sin6_addr = sk->sk_v6_daddr; #endif } } static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; unsigned int sfcount = 0, copied = 0; struct mptcp_subflow_data sfd; char __user *addrptr; int len; len = mptcp_get_subflow_data(&sfd, optval, optlen); if (len < 0) return len; sfd.size_kernel = sizeof(struct mptcp_subflow_addrs); sfd.size_user = min_t(unsigned int, sfd.size_user, sizeof(struct mptcp_subflow_addrs)); addrptr = optval + sfd.size_subflow_data; lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); ++sfcount; if (len && len >= sfd.size_user) { struct mptcp_subflow_addrs a; mptcp_get_sub_addrs(ssk, &a); if (copy_to_user(addrptr, &a, sfd.size_user)) { release_sock(sk); return -EFAULT; } addrptr += sfd.size_user; copied += sfd.size_user; len -= sfd.size_user; } } release_sock(sk); sfd.num_subflows = sfcount; if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) return -EFAULT; return 0; } static int mptcp_get_full_info(struct mptcp_full_info *mfi, char __user *optval, int __user *optlen) { int len; BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) != MIN_FULL_INFO_OPTLEN_SIZE); if (get_user(len, optlen)) return -EFAULT; if (len < MIN_FULL_INFO_OPTLEN_SIZE) return -EINVAL; memset(mfi, 0, sizeof(*mfi)); if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE)) return -EFAULT; if (mfi->size_tcpinfo_kernel || mfi->size_sfinfo_kernel || mfi->num_subflows) return -EINVAL; if (mfi->size_sfinfo_user > INT_MAX || mfi->size_tcpinfo_user > INT_MAX) return -EINVAL; return len - MIN_FULL_INFO_OPTLEN_SIZE; } static int mptcp_put_full_info(struct mptcp_full_info *mfi, char __user *optval, u32 copylen, int __user *optlen) { copylen += MIN_FULL_INFO_OPTLEN_SIZE; if (put_user(copylen, optlen)) return -EFAULT; if (copy_to_user(optval, mfi, copylen)) return -EFAULT; return 0; } static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { unsigned int sfcount = 0, copylen = 0; struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; void __user *tcpinfoptr, *sfinfoptr; struct mptcp_full_info mfi; int len; len = mptcp_get_full_info(&mfi, optval, optlen); if (len < 0) return len; /* don't bother filling the mptcp info if there is not enough * user-space-provided storage */ if (len > 0) { mptcp_diag_fill_info(msk, &mfi.mptcp_info); copylen += min_t(unsigned int, len, sizeof(struct mptcp_info)); } mfi.size_tcpinfo_kernel = sizeof(struct tcp_info); mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user, sizeof(struct tcp_info)); sfinfoptr = u64_to_user_ptr(mfi.subflow_info); mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info); mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user, sizeof(struct mptcp_subflow_info)); tcpinfoptr = u64_to_user_ptr(mfi.tcp_info); lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct mptcp_subflow_info sfinfo; struct tcp_info tcp_info; if (sfcount++ >= mfi.size_arrays_user) continue; /* fetch addr/tcp_info only if the user space buffers * are wide enough */ memset(&sfinfo, 0, sizeof(sfinfo)); sfinfo.id = subflow->subflow_id; if (mfi.size_sfinfo_user > offsetof(struct mptcp_subflow_info, addrs)) mptcp_get_sub_addrs(ssk, &sfinfo.addrs); if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user)) goto fail_release; if (mfi.size_tcpinfo_user) { tcp_get_info(ssk, &tcp_info); if (copy_to_user(tcpinfoptr, &tcp_info, mfi.size_tcpinfo_user)) goto fail_release; } tcpinfoptr += mfi.size_tcpinfo_user; sfinfoptr += mfi.size_sfinfo_user; } release_sock(sk); mfi.num_subflows = sfcount; if (mptcp_put_full_info(&mfi, optval, copylen, optlen)) return -EFAULT; return 0; fail_release: release_sock(sk); return -EFAULT; } static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval, int __user *optlen, int val) { int len; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, len, sizeof(int)); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; } return 0; } static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { struct sock *sk = (void *)msk; switch (optname) { case TCP_ULP: case TCP_CONGESTION: case TCP_INFO: case TCP_CC_INFO: case TCP_DEFER_ACCEPT: case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); case TCP_INQ: return mptcp_put_int_option(msk, optval, optlen, msk->recvmsg_inq); case TCP_CORK: return mptcp_put_int_option(msk, optval, optlen, msk->cork); case TCP_NODELAY: return mptcp_put_int_option(msk, optval, optlen, msk->nodelay); case TCP_KEEPIDLE: return mptcp_put_int_option(msk, optval, optlen, msk->keepalive_idle ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ); case TCP_KEEPINTVL: return mptcp_put_int_option(msk, optval, optlen, msk->keepalive_intvl ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ); case TCP_KEEPCNT: return mptcp_put_int_option(msk, optval, optlen, msk->keepalive_cnt ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes)); case TCP_NOTSENT_LOWAT: return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); case TCP_IS_MPTCP: return mptcp_put_int_option(msk, optval, optlen, 1); } return -EOPNOTSUPP; } static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { struct sock *sk = (void *)msk; switch (optname) { case IP_TOS: return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos)); case IP_BIND_ADDRESS_NO_PORT: return mptcp_put_int_option(msk, optval, optlen, inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); case IP_LOCAL_PORT_RANGE: return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->local_port_range)); } return -EOPNOTSUPP; } static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { switch (optname) { case MPTCP_INFO: return mptcp_getsockopt_info(msk, optval, optlen); case MPTCP_FULL_INFO: return mptcp_getsockopt_full_info(msk, optval, optlen); case MPTCP_TCPINFO: return mptcp_getsockopt_tcpinfo(msk, optval, optlen); case MPTCP_SUBFLOW_ADDRS: return mptcp_getsockopt_subflow_addrs(msk, optval, optlen); } return -EOPNOTSUPP; } int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; pr_debug("msk=%p\n", msk); /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the * MPTCP-level socket to configure the subflows until the subflow * is in TCP fallback, when socket options are passed through * to the one remaining subflow. */ lock_sock(sk); ssk = __mptcp_tcp_fallback(msk); release_sock(sk); if (ssk) return tcp_getsockopt(ssk, level, optname, optval, option); if (level == SOL_IP) return mptcp_getsockopt_v4(msk, optname, optval, option); if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); if (level == SOL_MPTCP) return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option); return -EOPNOTSUPP; } static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) { static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK; struct sock *sk = (struct sock *)msk; if (ssk->sk_prot->keepalive) { if (sock_flag(sk, SOCK_KEEPOPEN)) ssk->sk_prot->keepalive(ssk, 1); else ssk->sk_prot->keepalive(ssk, 0); } ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; ssk->sk_incoming_cpu = sk->sk_incoming_cpu; ssk->sk_ipv6only = sk->sk_ipv6only; __ip_sock_set_tos(ssk, inet_sk(sk)->tos); if (sk->sk_userlocks & tx_rx_locks) { ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) { WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); } if (sock_flag(sk, SOCK_LINGER)) { ssk->sk_lingertime = sk->sk_lingertime; sock_set_flag(ssk, SOCK_LINGER); } else { sock_reset_flag(ssk, SOCK_LINGER); } if (sk->sk_mark != ssk->sk_mark) { ssk->sk_mark = sk->sk_mark; sk_dst_reset(ssk); } sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG)); if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops) tcp_set_congestion_control(ssk, msk->ca_name, false, true); __tcp_sock_set_cork(ssk, !!msk->cork); __tcp_sock_set_nodelay(ssk, !!msk->nodelay); tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle); tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl); tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt); inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range)); } void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); msk_owned_by_me(msk); ssk->sk_rcvlowat = 0; /* subflows must ignore any latency-related settings: will not affect * the user-space - only the msk is relevant - but will foul the * mptcp scheduler */ tcp_sk(ssk)->notsent_lowat = UINT_MAX; if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { sync_socket_options(msk, ssk); subflow->setsockopt_seq = msk->setsockopt_seq; } } /* unfortunately this is different enough from the tcp version so * that we can't factor it out */ int mptcp_set_rcvlowat(struct sock *sk, int val) { struct mptcp_subflow_context *subflow; int space, cap; /* bpf can land here with a wrong sk type */ if (sk->sk_protocol == IPPROTO_TCP) return -EINVAL; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ if (mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; space = mptcp_space_from_win(sk, val); if (space <= sk->sk_rcvbuf) return 0; /* propagate the rcvbuf changes to all the subflows */ WRITE_ONCE(sk->sk_rcvbuf, space); mptcp_for_each_subflow(mptcp_sk(sk), subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, space); WRITE_ONCE(tcp_sk(ssk)->window_clamp, val); unlock_sock_fast(ssk, slow); } return 0; }
159 10 158 140 133 1 10 35 36 34 36 30 36 5 34 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 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/termios.h> #include <linux/tty.h> #include <linux/export.h> #include "tty.h" /* * Routine which returns the baud rate of the tty * * Note that the baud_table needs to be kept in sync with the * include/asm/termbits.h file. */ static const speed_t baud_table[] = { 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, 9600, 19200, 38400, 57600, 115200, 230400, 460800, #ifdef __sparc__ 76800, 153600, 307200, 614400, 921600, 500000, 576000, 1000000, 1152000, 1500000, 2000000 #else 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000, 2500000, 3000000, 3500000, 4000000 #endif }; static const tcflag_t baud_bits[] = { B0, B50, B75, B110, B134, B150, B200, B300, B600, B1200, B1800, B2400, B4800, B9600, B19200, B38400, B57600, B115200, B230400, B460800, #ifdef __sparc__ B76800, B153600, B307200, B614400, B921600, B500000, B576000, B1000000, B1152000, B1500000, B2000000 #else B500000, B576000, B921600, B1000000, B1152000, B1500000, B2000000, B2500000, B3000000, B3500000, B4000000 #endif }; static int n_baud_table = ARRAY_SIZE(baud_table); /** * tty_termios_baud_rate * @termios: termios structure * * Convert termios baud rate data into a speed. This should be called * with the termios lock held if this termios is a terminal termios * structure. Device drivers can call this function but should use * ->c_[io]speed directly as they are updated. * * Locking: none */ speed_t tty_termios_baud_rate(const struct ktermios *termios) { unsigned int cbaud; cbaud = termios->c_cflag & CBAUD; /* Magic token for arbitrary speed via c_ispeed/c_ospeed */ if (cbaud == BOTHER) return termios->c_ospeed; if (cbaud & CBAUDEX) { cbaud &= ~CBAUDEX; cbaud += 15; } return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); /** * tty_termios_input_baud_rate * @termios: termios structure * * Convert termios baud rate data into a speed. This should be called * with the termios lock held if this termios is a terminal termios * structure. Device drivers can call this function but should use * ->c_[io]speed directly as they are updated. * * Locking: none */ speed_t tty_termios_input_baud_rate(const struct ktermios *termios) { unsigned int cbaud = (termios->c_cflag >> IBSHIFT) & CBAUD; if (cbaud == B0) return tty_termios_baud_rate(termios); /* Magic token for arbitrary speed via c_ispeed */ if (cbaud == BOTHER) return termios->c_ispeed; if (cbaud & CBAUDEX) { cbaud &= ~CBAUDEX; cbaud += 15; } return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_input_baud_rate); /** * tty_termios_encode_baud_rate * @termios: ktermios structure holding user requested state * @ibaud: input speed * @obaud: output speed * * Encode the speeds set into the passed termios structure. This is * used as a library helper for drivers so that they can report back * the actual speed selected when it differs from the speed requested * * For maximal back compatibility with legacy SYS5/POSIX *nix behaviour * we need to carefully set the bits when the user does not get the * desired speed. We allow small margins and preserve as much of possible * of the input intent to keep compatibility. * * Locking: Caller should hold termios lock. This is already held * when calling this function from the driver termios handler. * * The ifdefs deal with platforms whose owners have yet to update them * and will all go away once this is done. */ void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud) { int i = 0; int ifound = -1, ofound = -1; int iclose = ibaud/50, oclose = obaud/50; int ibinput = 0; if (obaud == 0) /* CD dropped */ ibaud = 0; /* Clear ibaud to be sure */ termios->c_ispeed = ibaud; termios->c_ospeed = obaud; if (((termios->c_cflag >> IBSHIFT) & CBAUD) != B0) ibinput = 1; /* An input speed was specified */ /* If the user asked for a precise weird speed give a precise weird * answer. If they asked for a Bfoo speed they may have problems * digesting non-exact replies so fuzz a bit. */ if ((termios->c_cflag & CBAUD) == BOTHER) { oclose = 0; if (!ibinput) iclose = 0; } if (((termios->c_cflag >> IBSHIFT) & CBAUD) == BOTHER) iclose = 0; termios->c_cflag &= ~CBAUD; termios->c_cflag &= ~(CBAUD << IBSHIFT); /* * Our goal is to find a close match to the standard baud rate * returned. Walk the baud rate table and if we get a very close * match then report back the speed as a POSIX Bxxxx value by * preference */ do { if (obaud - oclose <= baud_table[i] && obaud + oclose >= baud_table[i]) { termios->c_cflag |= baud_bits[i]; ofound = i; } if (ibaud - iclose <= baud_table[i] && ibaud + iclose >= baud_table[i]) { /* For the case input == output don't set IBAUD bits * if the user didn't do so. */ if (ofound == i && !ibinput) { ifound = i; } else { ifound = i; termios->c_cflag |= (baud_bits[i] << IBSHIFT); } } } while (++i < n_baud_table); /* If we found no match then use BOTHER. */ if (ofound == -1) termios->c_cflag |= BOTHER; /* Set exact input bits only if the input and output differ or the * user already did. */ if (ifound == -1 && (ibaud != obaud || ibinput)) termios->c_cflag |= (BOTHER << IBSHIFT); } EXPORT_SYMBOL_GPL(tty_termios_encode_baud_rate); /** * tty_encode_baud_rate - set baud rate of the tty * @tty: terminal device * @ibaud: input baud rate * @obaud: output baud rate * * Update the current termios data for the tty with the new speed * settings. The caller must hold the termios_rwsem for the tty in * question. */ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, speed_t obaud) { tty_termios_encode_baud_rate(&tty->termios, ibaud, obaud); } EXPORT_SYMBOL_GPL(tty_encode_baud_rate);
19 19 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 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 // SPDX-License-Identifier: ISC /* * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/ctype.h> #include "core.h" #include "htc.h" #include "debug.h" #include "wmi.h" #include "wmi-tlv.h" #include "mac.h" #include "testmode.h" #include "wmi-ops.h" #include "p2p.h" #include "hw.h" #include "hif.h" #include "txrx.h" #define ATH10K_WMI_BARRIER_ECHO_ID 0xBA991E9 #define ATH10K_WMI_BARRIER_TIMEOUT_HZ (3 * HZ) #define ATH10K_WMI_DFS_CONF_TIMEOUT_HZ (HZ / 6) /* MAIN WMI cmd track */ static struct wmi_cmd_map wmi_cmd_map = { .init_cmdid = WMI_INIT_CMDID, .start_scan_cmdid = WMI_START_SCAN_CMDID, .stop_scan_cmdid = WMI_STOP_SCAN_CMDID, .scan_chan_list_cmdid = WMI_SCAN_CHAN_LIST_CMDID, .scan_sch_prio_tbl_cmdid = WMI_SCAN_SCH_PRIO_TBL_CMDID, .scan_prob_req_oui_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_regdomain_cmdid = WMI_PDEV_SET_REGDOMAIN_CMDID, .pdev_set_channel_cmdid = WMI_PDEV_SET_CHANNEL_CMDID, .pdev_set_param_cmdid = WMI_PDEV_SET_PARAM_CMDID, .pdev_pktlog_enable_cmdid = WMI_PDEV_PKTLOG_ENABLE_CMDID, .pdev_pktlog_disable_cmdid = WMI_PDEV_PKTLOG_DISABLE_CMDID, .pdev_set_wmm_params_cmdid = WMI_PDEV_SET_WMM_PARAMS_CMDID, .pdev_set_ht_cap_ie_cmdid = WMI_PDEV_SET_HT_CAP_IE_CMDID, .pdev_set_vht_cap_ie_cmdid = WMI_PDEV_SET_VHT_CAP_IE_CMDID, .pdev_set_dscp_tid_map_cmdid = WMI_PDEV_SET_DSCP_TID_MAP_CMDID, .pdev_set_quiet_mode_cmdid = WMI_PDEV_SET_QUIET_MODE_CMDID, .pdev_green_ap_ps_enable_cmdid = WMI_PDEV_GREEN_AP_PS_ENABLE_CMDID, .pdev_get_tpc_config_cmdid = WMI_PDEV_GET_TPC_CONFIG_CMDID, .pdev_set_base_macaddr_cmdid = WMI_PDEV_SET_BASE_MACADDR_CMDID, .vdev_create_cmdid = WMI_VDEV_CREATE_CMDID, .vdev_delete_cmdid = WMI_VDEV_DELETE_CMDID, .vdev_start_request_cmdid = WMI_VDEV_START_REQUEST_CMDID, .vdev_restart_request_cmdid = WMI_VDEV_RESTART_REQUEST_CMDID, .vdev_up_cmdid = WMI_VDEV_UP_CMDID, .vdev_stop_cmdid = WMI_VDEV_STOP_CMDID, .vdev_down_cmdid = WMI_VDEV_DOWN_CMDID, .vdev_set_param_cmdid = WMI_VDEV_SET_PARAM_CMDID, .vdev_install_key_cmdid = WMI_VDEV_INSTALL_KEY_CMDID, .peer_create_cmdid = WMI_PEER_CREATE_CMDID, .peer_delete_cmdid = WMI_PEER_DELETE_CMDID, .peer_flush_tids_cmdid = WMI_PEER_FLUSH_TIDS_CMDID, .peer_set_param_cmdid = WMI_PEER_SET_PARAM_CMDID, .peer_assoc_cmdid = WMI_PEER_ASSOC_CMDID, .peer_add_wds_entry_cmdid = WMI_PEER_ADD_WDS_ENTRY_CMDID, .peer_remove_wds_entry_cmdid = WMI_PEER_REMOVE_WDS_ENTRY_CMDID, .peer_mcast_group_cmdid = WMI_PEER_MCAST_GROUP_CMDID, .bcn_tx_cmdid = WMI_BCN_TX_CMDID, .pdev_send_bcn_cmdid = WMI_PDEV_SEND_BCN_CMDID, .bcn_tmpl_cmdid = WMI_BCN_TMPL_CMDID, .bcn_filter_rx_cmdid = WMI_BCN_FILTER_RX_CMDID, .prb_req_filter_rx_cmdid = WMI_PRB_REQ_FILTER_RX_CMDID, .mgmt_tx_cmdid = WMI_MGMT_TX_CMDID, .prb_tmpl_cmdid = WMI_PRB_TMPL_CMDID, .addba_clear_resp_cmdid = WMI_ADDBA_CLEAR_RESP_CMDID, .addba_send_cmdid = WMI_ADDBA_SEND_CMDID, .addba_status_cmdid = WMI_ADDBA_STATUS_CMDID, .delba_send_cmdid = WMI_DELBA_SEND_CMDID, .addba_set_resp_cmdid = WMI_ADDBA_SET_RESP_CMDID, .send_singleamsdu_cmdid = WMI_SEND_SINGLEAMSDU_CMDID, .sta_powersave_mode_cmdid = WMI_STA_POWERSAVE_MODE_CMDID, .sta_powersave_param_cmdid = WMI_STA_POWERSAVE_PARAM_CMDID, .sta_mimo_ps_mode_cmdid = WMI_STA_MIMO_PS_MODE_CMDID, .pdev_dfs_enable_cmdid = WMI_PDEV_DFS_ENABLE_CMDID, .pdev_dfs_disable_cmdid = WMI_PDEV_DFS_DISABLE_CMDID, .roam_scan_mode = WMI_ROAM_SCAN_MODE, .roam_scan_rssi_threshold = WMI_ROAM_SCAN_RSSI_THRESHOLD, .roam_scan_period = WMI_ROAM_SCAN_PERIOD, .roam_scan_rssi_change_threshold = WMI_ROAM_SCAN_RSSI_CHANGE_THRESHOLD, .roam_ap_profile = WMI_ROAM_AP_PROFILE, .ofl_scan_add_ap_profile = WMI_ROAM_AP_PROFILE, .ofl_scan_remove_ap_profile = WMI_OFL_SCAN_REMOVE_AP_PROFILE, .ofl_scan_period = WMI_OFL_SCAN_PERIOD, .p2p_dev_set_device_info = WMI_P2P_DEV_SET_DEVICE_INFO, .p2p_dev_set_discoverability = WMI_P2P_DEV_SET_DISCOVERABILITY, .p2p_go_set_beacon_ie = WMI_P2P_GO_SET_BEACON_IE, .p2p_go_set_probe_resp_ie = WMI_P2P_GO_SET_PROBE_RESP_IE, .p2p_set_vendor_ie_data_cmdid = WMI_P2P_SET_VENDOR_IE_DATA_CMDID, .ap_ps_peer_param_cmdid = WMI_AP_PS_PEER_PARAM_CMDID, .ap_ps_peer_uapsd_coex_cmdid = WMI_AP_PS_PEER_UAPSD_COEX_CMDID, .peer_rate_retry_sched_cmdid = WMI_PEER_RATE_RETRY_SCHED_CMDID, .wlan_profile_trigger_cmdid = WMI_WLAN_PROFILE_TRIGGER_CMDID, .wlan_profile_set_hist_intvl_cmdid = WMI_WLAN_PROFILE_SET_HIST_INTVL_CMDID, .wlan_profile_get_profile_data_cmdid = WMI_WLAN_PROFILE_GET_PROFILE_DATA_CMDID, .wlan_profile_enable_profile_id_cmdid = WMI_WLAN_PROFILE_ENABLE_PROFILE_ID_CMDID, .wlan_profile_list_profile_id_cmdid = WMI_WLAN_PROFILE_LIST_PROFILE_ID_CMDID, .pdev_suspend_cmdid = WMI_PDEV_SUSPEND_CMDID, .pdev_resume_cmdid = WMI_PDEV_RESUME_CMDID, .add_bcn_filter_cmdid = WMI_ADD_BCN_FILTER_CMDID, .rmv_bcn_filter_cmdid = WMI_RMV_BCN_FILTER_CMDID, .wow_add_wake_pattern_cmdid = WMI_WOW_ADD_WAKE_PATTERN_CMDID, .wow_del_wake_pattern_cmdid = WMI_WOW_DEL_WAKE_PATTERN_CMDID, .wow_enable_disable_wake_event_cmdid = WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID, .wow_enable_cmdid = WMI_WOW_ENABLE_CMDID, .wow_hostwakeup_from_sleep_cmdid = WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID, .rtt_measreq_cmdid = WMI_RTT_MEASREQ_CMDID, .rtt_tsf_cmdid = WMI_RTT_TSF_CMDID, .vdev_spectral_scan_configure_cmdid = WMI_VDEV_SPECTRAL_SCAN_CONFIGURE_CMDID, .vdev_spectral_scan_enable_cmdid = WMI_VDEV_SPECTRAL_SCAN_ENABLE_CMDID, .request_stats_cmdid = WMI_REQUEST_STATS_CMDID, .set_arp_ns_offload_cmdid = WMI_SET_ARP_NS_OFFLOAD_CMDID, .network_list_offload_config_cmdid = WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID, .gtk_offload_cmdid = WMI_GTK_OFFLOAD_CMDID, .csa_offload_enable_cmdid = WMI_CSA_OFFLOAD_ENABLE_CMDID, .csa_offload_chanswitch_cmdid = WMI_CSA_OFFLOAD_CHANSWITCH_CMDID, .chatter_set_mode_cmdid = WMI_CHATTER_SET_MODE_CMDID, .peer_tid_addba_cmdid = WMI_PEER_TID_ADDBA_CMDID, .peer_tid_delba_cmdid = WMI_PEER_TID_DELBA_CMDID, .sta_dtim_ps_method_cmdid = WMI_STA_DTIM_PS_METHOD_CMDID, .sta_uapsd_auto_trig_cmdid = WMI_STA_UAPSD_AUTO_TRIG_CMDID, .sta_keepalive_cmd = WMI_STA_KEEPALIVE_CMD, .echo_cmdid = WMI_ECHO_CMDID, .pdev_utf_cmdid = WMI_PDEV_UTF_CMDID, .dbglog_cfg_cmdid = WMI_DBGLOG_CFG_CMDID, .pdev_qvit_cmdid = WMI_PDEV_QVIT_CMDID, .pdev_ftm_intg_cmdid = WMI_PDEV_FTM_INTG_CMDID, .vdev_set_keepalive_cmdid = WMI_VDEV_SET_KEEPALIVE_CMDID, .vdev_get_keepalive_cmdid = WMI_VDEV_GET_KEEPALIVE_CMDID, .force_fw_hang_cmdid = WMI_FORCE_FW_HANG_CMDID, .gpio_config_cmdid = WMI_GPIO_CONFIG_CMDID, .gpio_output_cmdid = WMI_GPIO_OUTPUT_CMDID, .pdev_get_temperature_cmdid = WMI_CMD_UNSUPPORTED, .pdev_enable_adaptive_cca_cmdid = WMI_CMD_UNSUPPORTED, .scan_update_request_cmdid = WMI_CMD_UNSUPPORTED, .vdev_standby_response_cmdid = WMI_CMD_UNSUPPORTED, .vdev_resume_response_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_add_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_evict_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_restore_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_print_all_peers_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_update_wds_entry_cmdid = WMI_CMD_UNSUPPORTED, .peer_add_proxy_sta_entry_cmdid = WMI_CMD_UNSUPPORTED, .rtt_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .oem_req_cmdid = WMI_CMD_UNSUPPORTED, .nan_cmdid = WMI_CMD_UNSUPPORTED, .vdev_ratemask_cmdid = WMI_CMD_UNSUPPORTED, .qboost_cfg_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_enable_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_set_rx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_tx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_train_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_node_config_ops_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_antenna_switch_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_ctl_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_mimogain_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_chainmsk_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_fips_cmdid = WMI_CMD_UNSUPPORTED, .tt_set_conf_cmdid = WMI_CMD_UNSUPPORTED, .fwtest_cmdid = WMI_CMD_UNSUPPORTED, .vdev_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .peer_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_cck_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_ofdm_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_reserve_ast_entry_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_nfcal_power_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ast_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_dscp_tid_map_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_filter_neighbor_rx_packets_cmdid = WMI_CMD_UNSUPPORTED, .mu_cal_start_cmdid = WMI_CMD_UNSUPPORTED, .set_cca_params_cmdid = WMI_CMD_UNSUPPORTED, .pdev_bss_chan_info_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_table_cmdid = WMI_CMD_UNSUPPORTED, .radar_found_cmdid = WMI_CMD_UNSUPPORTED, }; /* 10.X WMI cmd track */ static struct wmi_cmd_map wmi_10x_cmd_map = { .init_cmdid = WMI_10X_INIT_CMDID, .start_scan_cmdid = WMI_10X_START_SCAN_CMDID, .stop_scan_cmdid = WMI_10X_STOP_SCAN_CMDID, .scan_chan_list_cmdid = WMI_10X_SCAN_CHAN_LIST_CMDID, .scan_sch_prio_tbl_cmdid = WMI_CMD_UNSUPPORTED, .scan_prob_req_oui_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_regdomain_cmdid = WMI_10X_PDEV_SET_REGDOMAIN_CMDID, .pdev_set_channel_cmdid = WMI_10X_PDEV_SET_CHANNEL_CMDID, .pdev_set_param_cmdid = WMI_10X_PDEV_SET_PARAM_CMDID, .pdev_pktlog_enable_cmdid = WMI_10X_PDEV_PKTLOG_ENABLE_CMDID, .pdev_pktlog_disable_cmdid = WMI_10X_PDEV_PKTLOG_DISABLE_CMDID, .pdev_set_wmm_params_cmdid = WMI_10X_PDEV_SET_WMM_PARAMS_CMDID, .pdev_set_ht_cap_ie_cmdid = WMI_10X_PDEV_SET_HT_CAP_IE_CMDID, .pdev_set_vht_cap_ie_cmdid = WMI_10X_PDEV_SET_VHT_CAP_IE_CMDID, .pdev_set_dscp_tid_map_cmdid = WMI_10X_PDEV_SET_DSCP_TID_MAP_CMDID, .pdev_set_quiet_mode_cmdid = WMI_10X_PDEV_SET_QUIET_MODE_CMDID, .pdev_green_ap_ps_enable_cmdid = WMI_10X_PDEV_GREEN_AP_PS_ENABLE_CMDID, .pdev_get_tpc_config_cmdid = WMI_10X_PDEV_GET_TPC_CONFIG_CMDID, .pdev_set_base_macaddr_cmdid = WMI_10X_PDEV_SET_BASE_MACADDR_CMDID, .vdev_create_cmdid = WMI_10X_VDEV_CREATE_CMDID, .vdev_delete_cmdid = WMI_10X_VDEV_DELETE_CMDID, .vdev_start_request_cmdid = WMI_10X_VDEV_START_REQUEST_CMDID, .vdev_restart_request_cmdid = WMI_10X_VDEV_RESTART_REQUEST_CMDID, .vdev_up_cmdid = WMI_10X_VDEV_UP_CMDID, .vdev_stop_cmdid = WMI_10X_VDEV_STOP_CMDID, .vdev_down_cmdid = WMI_10X_VDEV_DOWN_CMDID, .vdev_set_param_cmdid = WMI_10X_VDEV_SET_PARAM_CMDID, .vdev_install_key_cmdid = WMI_10X_VDEV_INSTALL_KEY_CMDID, .peer_create_cmdid = WMI_10X_PEER_CREATE_CMDID, .peer_delete_cmdid = WMI_10X_PEER_DELETE_CMDID, .peer_flush_tids_cmdid = WMI_10X_PEER_FLUSH_TIDS_CMDID, .peer_set_param_cmdid = WMI_10X_PEER_SET_PARAM_CMDID, .peer_assoc_cmdid = WMI_10X_PEER_ASSOC_CMDID, .peer_add_wds_entry_cmdid = WMI_10X_PEER_ADD_WDS_ENTRY_CMDID, .peer_remove_wds_entry_cmdid = WMI_10X_PEER_REMOVE_WDS_ENTRY_CMDID, .peer_mcast_group_cmdid = WMI_10X_PEER_MCAST_GROUP_CMDID, .bcn_tx_cmdid = WMI_10X_BCN_TX_CMDID, .pdev_send_bcn_cmdid = WMI_10X_PDEV_SEND_BCN_CMDID, .bcn_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .bcn_filter_rx_cmdid = WMI_10X_BCN_FILTER_RX_CMDID, .prb_req_filter_rx_cmdid = WMI_10X_PRB_REQ_FILTER_RX_CMDID, .mgmt_tx_cmdid = WMI_10X_MGMT_TX_CMDID, .prb_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .addba_clear_resp_cmdid = WMI_10X_ADDBA_CLEAR_RESP_CMDID, .addba_send_cmdid = WMI_10X_ADDBA_SEND_CMDID, .addba_status_cmdid = WMI_10X_ADDBA_STATUS_CMDID, .delba_send_cmdid = WMI_10X_DELBA_SEND_CMDID, .addba_set_resp_cmdid = WMI_10X_ADDBA_SET_RESP_CMDID, .send_singleamsdu_cmdid = WMI_10X_SEND_SINGLEAMSDU_CMDID, .sta_powersave_mode_cmdid = WMI_10X_STA_POWERSAVE_MODE_CMDID, .sta_powersave_param_cmdid = WMI_10X_STA_POWERSAVE_PARAM_CMDID, .sta_mimo_ps_mode_cmdid = WMI_10X_STA_MIMO_PS_MODE_CMDID, .pdev_dfs_enable_cmdid = WMI_10X_PDEV_DFS_ENABLE_CMDID, .pdev_dfs_disable_cmdid = WMI_10X_PDEV_DFS_DISABLE_CMDID, .roam_scan_mode = WMI_10X_ROAM_SCAN_MODE, .roam_scan_rssi_threshold = WMI_10X_ROAM_SCAN_RSSI_THRESHOLD, .roam_scan_period = WMI_10X_ROAM_SCAN_PERIOD, .roam_scan_rssi_change_threshold = WMI_10X_ROAM_SCAN_RSSI_CHANGE_THRESHOLD, .roam_ap_profile = WMI_10X_ROAM_AP_PROFILE, .ofl_scan_add_ap_profile = WMI_10X_OFL_SCAN_ADD_AP_PROFILE, .ofl_scan_remove_ap_profile = WMI_10X_OFL_SCAN_REMOVE_AP_PROFILE, .ofl_scan_period = WMI_10X_OFL_SCAN_PERIOD, .p2p_dev_set_device_info = WMI_10X_P2P_DEV_SET_DEVICE_INFO, .p2p_dev_set_discoverability = WMI_10X_P2P_DEV_SET_DISCOVERABILITY, .p2p_go_set_beacon_ie = WMI_10X_P2P_GO_SET_BEACON_IE, .p2p_go_set_probe_resp_ie = WMI_10X_P2P_GO_SET_PROBE_RESP_IE, .p2p_set_vendor_ie_data_cmdid = WMI_CMD_UNSUPPORTED, .ap_ps_peer_param_cmdid = WMI_10X_AP_PS_PEER_PARAM_CMDID, .ap_ps_peer_uapsd_coex_cmdid = WMI_CMD_UNSUPPORTED, .peer_rate_retry_sched_cmdid = WMI_10X_PEER_RATE_RETRY_SCHED_CMDID, .wlan_profile_trigger_cmdid = WMI_10X_WLAN_PROFILE_TRIGGER_CMDID, .wlan_profile_set_hist_intvl_cmdid = WMI_10X_WLAN_PROFILE_SET_HIST_INTVL_CMDID, .wlan_profile_get_profile_data_cmdid = WMI_10X_WLAN_PROFILE_GET_PROFILE_DATA_CMDID, .wlan_profile_enable_profile_id_cmdid = WMI_10X_WLAN_PROFILE_ENABLE_PROFILE_ID_CMDID, .wlan_profile_list_profile_id_cmdid = WMI_10X_WLAN_PROFILE_LIST_PROFILE_ID_CMDID, .pdev_suspend_cmdid = WMI_10X_PDEV_SUSPEND_CMDID, .pdev_resume_cmdid = WMI_10X_PDEV_RESUME_CMDID, .add_bcn_filter_cmdid = WMI_10X_ADD_BCN_FILTER_CMDID, .rmv_bcn_filter_cmdid = WMI_10X_RMV_BCN_FILTER_CMDID, .wow_add_wake_pattern_cmdid = WMI_10X_WOW_ADD_WAKE_PATTERN_CMDID, .wow_del_wake_pattern_cmdid = WMI_10X_WOW_DEL_WAKE_PATTERN_CMDID, .wow_enable_disable_wake_event_cmdid = WMI_10X_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID, .wow_enable_cmdid = WMI_10X_WOW_ENABLE_CMDID, .wow_hostwakeup_from_sleep_cmdid = WMI_10X_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID, .rtt_measreq_cmdid = WMI_10X_RTT_MEASREQ_CMDID, .rtt_tsf_cmdid = WMI_10X_RTT_TSF_CMDID, .vdev_spectral_scan_configure_cmdid = WMI_10X_VDEV_SPECTRAL_SCAN_CONFIGURE_CMDID, .vdev_spectral_scan_enable_cmdid = WMI_10X_VDEV_SPECTRAL_SCAN_ENABLE_CMDID, .request_stats_cmdid = WMI_10X_REQUEST_STATS_CMDID, .set_arp_ns_offload_cmdid = WMI_CMD_UNSUPPORTED, .network_list_offload_config_cmdid = WMI_CMD_UNSUPPORTED, .gtk_offload_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_enable_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_chanswitch_cmdid = WMI_CMD_UNSUPPORTED, .chatter_set_mode_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_addba_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_delba_cmdid = WMI_CMD_UNSUPPORTED, .sta_dtim_ps_method_cmdid = WMI_CMD_UNSUPPORTED, .sta_uapsd_auto_trig_cmdid = WMI_CMD_UNSUPPORTED, .sta_keepalive_cmd = WMI_CMD_UNSUPPORTED, .echo_cmdid = WMI_10X_ECHO_CMDID, .pdev_utf_cmdid = WMI_10X_PDEV_UTF_CMDID, .dbglog_cfg_cmdid = WMI_10X_DBGLOG_CFG_CMDID, .pdev_qvit_cmdid = WMI_10X_PDEV_QVIT_CMDID, .pdev_ftm_intg_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .force_fw_hang_cmdid = WMI_CMD_UNSUPPORTED, .gpio_config_cmdid = WMI_10X_GPIO_CONFIG_CMDID, .gpio_output_cmdid = WMI_10X_GPIO_OUTPUT_CMDID, .pdev_get_temperature_cmdid = WMI_CMD_UNSUPPORTED, .pdev_enable_adaptive_cca_cmdid = WMI_CMD_UNSUPPORTED, .scan_update_request_cmdid = WMI_CMD_UNSUPPORTED, .vdev_standby_response_cmdid = WMI_CMD_UNSUPPORTED, .vdev_resume_response_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_add_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_evict_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_restore_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_print_all_peers_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_update_wds_entry_cmdid = WMI_CMD_UNSUPPORTED, .peer_add_proxy_sta_entry_cmdid = WMI_CMD_UNSUPPORTED, .rtt_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .oem_req_cmdid = WMI_CMD_UNSUPPORTED, .nan_cmdid = WMI_CMD_UNSUPPORTED, .vdev_ratemask_cmdid = WMI_CMD_UNSUPPORTED, .qboost_cfg_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_enable_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_set_rx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_tx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_train_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_node_config_ops_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_antenna_switch_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_ctl_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_mimogain_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_chainmsk_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_fips_cmdid = WMI_CMD_UNSUPPORTED, .tt_set_conf_cmdid = WMI_CMD_UNSUPPORTED, .fwtest_cmdid = WMI_CMD_UNSUPPORTED, .vdev_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .peer_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_cck_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_ofdm_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_reserve_ast_entry_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_nfcal_power_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ast_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_dscp_tid_map_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_filter_neighbor_rx_packets_cmdid = WMI_CMD_UNSUPPORTED, .mu_cal_start_cmdid = WMI_CMD_UNSUPPORTED, .set_cca_params_cmdid = WMI_CMD_UNSUPPORTED, .pdev_bss_chan_info_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_table_cmdid = WMI_CMD_UNSUPPORTED, .radar_found_cmdid = WMI_CMD_UNSUPPORTED, }; /* 10.2.4 WMI cmd track */ static struct wmi_cmd_map wmi_10_2_4_cmd_map = { .init_cmdid = WMI_10_2_INIT_CMDID, .start_scan_cmdid = WMI_10_2_START_SCAN_CMDID, .stop_scan_cmdid = WMI_10_2_STOP_SCAN_CMDID, .scan_chan_list_cmdid = WMI_10_2_SCAN_CHAN_LIST_CMDID, .scan_sch_prio_tbl_cmdid = WMI_CMD_UNSUPPORTED, .scan_prob_req_oui_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_regdomain_cmdid = WMI_10_2_PDEV_SET_REGDOMAIN_CMDID, .pdev_set_channel_cmdid = WMI_10_2_PDEV_SET_CHANNEL_CMDID, .pdev_set_param_cmdid = WMI_10_2_PDEV_SET_PARAM_CMDID, .pdev_pktlog_enable_cmdid = WMI_10_2_PDEV_PKTLOG_ENABLE_CMDID, .pdev_pktlog_disable_cmdid = WMI_10_2_PDEV_PKTLOG_DISABLE_CMDID, .pdev_set_wmm_params_cmdid = WMI_10_2_PDEV_SET_WMM_PARAMS_CMDID, .pdev_set_ht_cap_ie_cmdid = WMI_10_2_PDEV_SET_HT_CAP_IE_CMDID, .pdev_set_vht_cap_ie_cmdid = WMI_10_2_PDEV_SET_VHT_CAP_IE_CMDID, .pdev_set_quiet_mode_cmdid = WMI_10_2_PDEV_SET_QUIET_MODE_CMDID, .pdev_green_ap_ps_enable_cmdid = WMI_10_2_PDEV_GREEN_AP_PS_ENABLE_CMDID, .pdev_get_tpc_config_cmdid = WMI_10_2_PDEV_GET_TPC_CONFIG_CMDID, .pdev_set_base_macaddr_cmdid = WMI_10_2_PDEV_SET_BASE_MACADDR_CMDID, .vdev_create_cmdid = WMI_10_2_VDEV_CREATE_CMDID, .vdev_delete_cmdid = WMI_10_2_VDEV_DELETE_CMDID, .vdev_start_request_cmdid = WMI_10_2_VDEV_START_REQUEST_CMDID, .vdev_restart_request_cmdid = WMI_10_2_VDEV_RESTART_REQUEST_CMDID, .vdev_up_cmdid = WMI_10_2_VDEV_UP_CMDID, .vdev_stop_cmdid = WMI_10_2_VDEV_STOP_CMDID, .vdev_down_cmdid = WMI_10_2_VDEV_DOWN_CMDID, .vdev_set_param_cmdid = WMI_10_2_VDEV_SET_PARAM_CMDID, .vdev_install_key_cmdid = WMI_10_2_VDEV_INSTALL_KEY_CMDID, .peer_create_cmdid = WMI_10_2_PEER_CREATE_CMDID, .peer_delete_cmdid = WMI_10_2_PEER_DELETE_CMDID, .peer_flush_tids_cmdid = WMI_10_2_PEER_FLUSH_TIDS_CMDID, .peer_set_param_cmdid = WMI_10_2_PEER_SET_PARAM_CMDID, .peer_assoc_cmdid = WMI_10_2_PEER_ASSOC_CMDID, .peer_add_wds_entry_cmdid = WMI_10_2_PEER_ADD_WDS_ENTRY_CMDID, .peer_remove_wds_entry_cmdid = WMI_10_2_PEER_REMOVE_WDS_ENTRY_CMDID, .peer_mcast_group_cmdid = WMI_10_2_PEER_MCAST_GROUP_CMDID, .bcn_tx_cmdid = WMI_10_2_BCN_TX_CMDID, .pdev_send_bcn_cmdid = WMI_10_2_PDEV_SEND_BCN_CMDID, .bcn_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .bcn_filter_rx_cmdid = WMI_10_2_BCN_FILTER_RX_CMDID, .prb_req_filter_rx_cmdid = WMI_10_2_PRB_REQ_FILTER_RX_CMDID, .mgmt_tx_cmdid = WMI_10_2_MGMT_TX_CMDID, .prb_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .addba_clear_resp_cmdid = WMI_10_2_ADDBA_CLEAR_RESP_CMDID, .addba_send_cmdid = WMI_10_2_ADDBA_SEND_CMDID, .addba_status_cmdid = WMI_10_2_ADDBA_STATUS_CMDID, .delba_send_cmdid = WMI_10_2_DELBA_SEND_CMDID, .addba_set_resp_cmdid = WMI_10_2_ADDBA_SET_RESP_CMDID, .send_singleamsdu_cmdid = WMI_10_2_SEND_SINGLEAMSDU_CMDID, .sta_powersave_mode_cmdid = WMI_10_2_STA_POWERSAVE_MODE_CMDID, .sta_powersave_param_cmdid = WMI_10_2_STA_POWERSAVE_PARAM_CMDID, .sta_mimo_ps_mode_cmdid = WMI_10_2_STA_MIMO_PS_MODE_CMDID, .pdev_dfs_enable_cmdid = WMI_10_2_PDEV_DFS_ENABLE_CMDID, .pdev_dfs_disable_cmdid = WMI_10_2_PDEV_DFS_DISABLE_CMDID, .roam_scan_mode = WMI_10_2_ROAM_SCAN_MODE, .roam_scan_rssi_threshold = WMI_10_2_ROAM_SCAN_RSSI_THRESHOLD, .roam_scan_period = WMI_10_2_ROAM_SCAN_PERIOD, .roam_scan_rssi_change_threshold = WMI_10_2_ROAM_SCAN_RSSI_CHANGE_THRESHOLD, .roam_ap_profile = WMI_10_2_ROAM_AP_PROFILE, .ofl_scan_add_ap_profile = WMI_10_2_OFL_SCAN_ADD_AP_PROFILE, .ofl_scan_remove_ap_profile = WMI_10_2_OFL_SCAN_REMOVE_AP_PROFILE, .ofl_scan_period = WMI_10_2_OFL_SCAN_PERIOD, .p2p_dev_set_device_info = WMI_10_2_P2P_DEV_SET_DEVICE_INFO, .p2p_dev_set_discoverability = WMI_10_2_P2P_DEV_SET_DISCOVERABILITY, .p2p_go_set_beacon_ie = WMI_10_2_P2P_GO_SET_BEACON_IE, .p2p_go_set_probe_resp_ie = WMI_10_2_P2P_GO_SET_PROBE_RESP_IE, .p2p_set_vendor_ie_data_cmdid = WMI_CMD_UNSUPPORTED, .ap_ps_peer_param_cmdid = WMI_10_2_AP_PS_PEER_PARAM_CMDID, .ap_ps_peer_uapsd_coex_cmdid = WMI_CMD_UNSUPPORTED, .peer_rate_retry_sched_cmdid = WMI_10_2_PEER_RATE_RETRY_SCHED_CMDID, .wlan_profile_trigger_cmdid = WMI_10_2_WLAN_PROFILE_TRIGGER_CMDID, .wlan_profile_set_hist_intvl_cmdid = WMI_10_2_WLAN_PROFILE_SET_HIST_INTVL_CMDID, .wlan_profile_get_profile_data_cmdid = WMI_10_2_WLAN_PROFILE_GET_PROFILE_DATA_CMDID, .wlan_profile_enable_profile_id_cmdid = WMI_10_2_WLAN_PROFILE_ENABLE_PROFILE_ID_CMDID, .wlan_profile_list_profile_id_cmdid = WMI_10_2_WLAN_PROFILE_LIST_PROFILE_ID_CMDID, .pdev_suspend_cmdid = WMI_10_2_PDEV_SUSPEND_CMDID, .pdev_resume_cmdid = WMI_10_2_PDEV_RESUME_CMDID, .add_bcn_filter_cmdid = WMI_10_2_ADD_BCN_FILTER_CMDID, .rmv_bcn_filter_cmdid = WMI_10_2_RMV_BCN_FILTER_CMDID, .wow_add_wake_pattern_cmdid = WMI_10_2_WOW_ADD_WAKE_PATTERN_CMDID, .wow_del_wake_pattern_cmdid = WMI_10_2_WOW_DEL_WAKE_PATTERN_CMDID, .wow_enable_disable_wake_event_cmdid = WMI_10_2_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID, .wow_enable_cmdid = WMI_10_2_WOW_ENABLE_CMDID, .wow_hostwakeup_from_sleep_cmdid = WMI_10_2_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID, .rtt_measreq_cmdid = WMI_10_2_RTT_MEASREQ_CMDID, .rtt_tsf_cmdid = WMI_10_2_RTT_TSF_CMDID, .vdev_spectral_scan_configure_cmdid = WMI_10_2_VDEV_SPECTRAL_SCAN_CONFIGURE_CMDID, .vdev_spectral_scan_enable_cmdid = WMI_10_2_VDEV_SPECTRAL_SCAN_ENABLE_CMDID, .request_stats_cmdid = WMI_10_2_REQUEST_STATS_CMDID, .set_arp_ns_offload_cmdid = WMI_CMD_UNSUPPORTED, .network_list_offload_config_cmdid = WMI_CMD_UNSUPPORTED, .gtk_offload_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_enable_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_chanswitch_cmdid = WMI_CMD_UNSUPPORTED, .chatter_set_mode_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_addba_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_delba_cmdid = WMI_CMD_UNSUPPORTED, .sta_dtim_ps_method_cmdid = WMI_CMD_UNSUPPORTED, .sta_uapsd_auto_trig_cmdid = WMI_CMD_UNSUPPORTED, .sta_keepalive_cmd = WMI_CMD_UNSUPPORTED, .echo_cmdid = WMI_10_2_ECHO_CMDID, .pdev_utf_cmdid = WMI_10_2_PDEV_UTF_CMDID, .dbglog_cfg_cmdid = WMI_10_2_DBGLOG_CFG_CMDID, .pdev_qvit_cmdid = WMI_10_2_PDEV_QVIT_CMDID, .pdev_ftm_intg_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .force_fw_hang_cmdid = WMI_CMD_UNSUPPORTED, .gpio_config_cmdid = WMI_10_2_GPIO_CONFIG_CMDID, .gpio_output_cmdid = WMI_10_2_GPIO_OUTPUT_CMDID, .pdev_get_temperature_cmdid = WMI_10_2_PDEV_GET_TEMPERATURE_CMDID, .pdev_enable_adaptive_cca_cmdid = WMI_10_2_SET_CCA_PARAMS, .scan_update_request_cmdid = WMI_CMD_UNSUPPORTED, .vdev_standby_response_cmdid = WMI_CMD_UNSUPPORTED, .vdev_resume_response_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_add_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_evict_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_restore_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_print_all_peers_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_update_wds_entry_cmdid = WMI_CMD_UNSUPPORTED, .peer_add_proxy_sta_entry_cmdid = WMI_CMD_UNSUPPORTED, .rtt_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .oem_req_cmdid = WMI_CMD_UNSUPPORTED, .nan_cmdid = WMI_CMD_UNSUPPORTED, .vdev_ratemask_cmdid = WMI_CMD_UNSUPPORTED, .qboost_cfg_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_enable_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_set_rx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_tx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_train_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_node_config_ops_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_antenna_switch_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_ctl_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_mimogain_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_chainmsk_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_fips_cmdid = WMI_CMD_UNSUPPORTED, .tt_set_conf_cmdid = WMI_CMD_UNSUPPORTED, .fwtest_cmdid = WMI_CMD_UNSUPPORTED, .vdev_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .peer_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_cck_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_ofdm_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_reserve_ast_entry_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_nfcal_power_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ast_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_dscp_tid_map_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_info_cmdid = WMI_CMD_UNSUPPORTED, .vdev_filter_neighbor_rx_packets_cmdid = WMI_CMD_UNSUPPORTED, .mu_cal_start_cmdid = WMI_CMD_UNSUPPORTED, .set_cca_params_cmdid = WMI_CMD_UNSUPPORTED, .pdev_bss_chan_info_request_cmdid = WMI_10_2_PDEV_BSS_CHAN_INFO_REQUEST_CMDID, .pdev_get_tpc_table_cmdid = WMI_CMD_UNSUPPORTED, .radar_found_cmdid = WMI_CMD_UNSUPPORTED, .set_bb_timing_cmdid = WMI_10_2_PDEV_SET_BB_TIMING_CONFIG_CMDID, }; /* 10.4 WMI cmd track */ static struct wmi_cmd_map wmi_10_4_cmd_map = { .init_cmdid = WMI_10_4_INIT_CMDID, .start_scan_cmdid = WMI_10_4_START_SCAN_CMDID, .stop_scan_cmdid = WMI_10_4_STOP_SCAN_CMDID, .scan_chan_list_cmdid = WMI_10_4_SCAN_CHAN_LIST_CMDID, .scan_sch_prio_tbl_cmdid = WMI_10_4_SCAN_SCH_PRIO_TBL_CMDID, .scan_prob_req_oui_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_regdomain_cmdid = WMI_10_4_PDEV_SET_REGDOMAIN_CMDID, .pdev_set_channel_cmdid = WMI_10_4_PDEV_SET_CHANNEL_CMDID, .pdev_set_param_cmdid = WMI_10_4_PDEV_SET_PARAM_CMDID, .pdev_pktlog_enable_cmdid = WMI_10_4_PDEV_PKTLOG_ENABLE_CMDID, .pdev_pktlog_disable_cmdid = WMI_10_4_PDEV_PKTLOG_DISABLE_CMDID, .pdev_set_wmm_params_cmdid = WMI_10_4_PDEV_SET_WMM_PARAMS_CMDID, .pdev_set_ht_cap_ie_cmdid = WMI_10_4_PDEV_SET_HT_CAP_IE_CMDID, .pdev_set_vht_cap_ie_cmdid = WMI_10_4_PDEV_SET_VHT_CAP_IE_CMDID, .pdev_set_dscp_tid_map_cmdid = WMI_10_4_PDEV_SET_DSCP_TID_MAP_CMDID, .pdev_set_quiet_mode_cmdid = WMI_10_4_PDEV_SET_QUIET_MODE_CMDID, .pdev_green_ap_ps_enable_cmdid = WMI_10_4_PDEV_GREEN_AP_PS_ENABLE_CMDID, .pdev_get_tpc_config_cmdid = WMI_10_4_PDEV_GET_TPC_CONFIG_CMDID, .pdev_set_base_macaddr_cmdid = WMI_10_4_PDEV_SET_BASE_MACADDR_CMDID, .vdev_create_cmdid = WMI_10_4_VDEV_CREATE_CMDID, .vdev_delete_cmdid = WMI_10_4_VDEV_DELETE_CMDID, .vdev_start_request_cmdid = WMI_10_4_VDEV_START_REQUEST_CMDID, .vdev_restart_request_cmdid = WMI_10_4_VDEV_RESTART_REQUEST_CMDID, .vdev_up_cmdid = WMI_10_4_VDEV_UP_CMDID, .vdev_stop_cmdid = WMI_10_4_VDEV_STOP_CMDID, .vdev_down_cmdid = WMI_10_4_VDEV_DOWN_CMDID, .vdev_set_param_cmdid = WMI_10_4_VDEV_SET_PARAM_CMDID, .vdev_install_key_cmdid = WMI_10_4_VDEV_INSTALL_KEY_CMDID, .peer_create_cmdid = WMI_10_4_PEER_CREATE_CMDID, .peer_delete_cmdid = WMI_10_4_PEER_DELETE_CMDID, .peer_flush_tids_cmdid = WMI_10_4_PEER_FLUSH_TIDS_CMDID, .peer_set_param_cmdid = WMI_10_4_PEER_SET_PARAM_CMDID, .peer_assoc_cmdid = WMI_10_4_PEER_ASSOC_CMDID, .peer_add_wds_entry_cmdid = WMI_10_4_PEER_ADD_WDS_ENTRY_CMDID, .peer_remove_wds_entry_cmdid = WMI_10_4_PEER_REMOVE_WDS_ENTRY_CMDID, .peer_mcast_group_cmdid = WMI_10_4_PEER_MCAST_GROUP_CMDID, .bcn_tx_cmdid = WMI_10_4_BCN_TX_CMDID, .pdev_send_bcn_cmdid = WMI_10_4_PDEV_SEND_BCN_CMDID, .bcn_tmpl_cmdid = WMI_10_4_BCN_PRB_TMPL_CMDID, .bcn_filter_rx_cmdid = WMI_10_4_BCN_FILTER_RX_CMDID, .prb_req_filter_rx_cmdid = WMI_10_4_PRB_REQ_FILTER_RX_CMDID, .mgmt_tx_cmdid = WMI_10_4_MGMT_TX_CMDID, .prb_tmpl_cmdid = WMI_10_4_PRB_TMPL_CMDID, .addba_clear_resp_cmdid = WMI_10_4_ADDBA_CLEAR_RESP_CMDID, .addba_send_cmdid = WMI_10_4_ADDBA_SEND_CMDID, .addba_status_cmdid = WMI_10_4_ADDBA_STATUS_CMDID, .delba_send_cmdid = WMI_10_4_DELBA_SEND_CMDID, .addba_set_resp_cmdid = WMI_10_4_ADDBA_SET_RESP_CMDID, .send_singleamsdu_cmdid = WMI_10_4_SEND_SINGLEAMSDU_CMDID, .sta_powersave_mode_cmdid = WMI_10_4_STA_POWERSAVE_MODE_CMDID, .sta_powersave_param_cmdid = WMI_10_4_STA_POWERSAVE_PARAM_CMDID, .sta_mimo_ps_mode_cmdid = WMI_10_4_STA_MIMO_PS_MODE_CMDID, .pdev_dfs_enable_cmdid = WMI_10_4_PDEV_DFS_ENABLE_CMDID, .pdev_dfs_disable_cmdid = WMI_10_4_PDEV_DFS_DISABLE_CMDID, .roam_scan_mode = WMI_10_4_ROAM_SCAN_MODE, .roam_scan_rssi_threshold = WMI_10_4_ROAM_SCAN_RSSI_THRESHOLD, .roam_scan_period = WMI_10_4_ROAM_SCAN_PERIOD, .roam_scan_rssi_change_threshold = WMI_10_4_ROAM_SCAN_RSSI_CHANGE_THRESHOLD, .roam_ap_profile = WMI_10_4_ROAM_AP_PROFILE, .ofl_scan_add_ap_profile = WMI_10_4_OFL_SCAN_ADD_AP_PROFILE, .ofl_scan_remove_ap_profile = WMI_10_4_OFL_SCAN_REMOVE_AP_PROFILE, .ofl_scan_period = WMI_10_4_OFL_SCAN_PERIOD, .p2p_dev_set_device_info = WMI_10_4_P2P_DEV_SET_DEVICE_INFO, .p2p_dev_set_discoverability = WMI_10_4_P2P_DEV_SET_DISCOVERABILITY, .p2p_go_set_beacon_ie = WMI_10_4_P2P_GO_SET_BEACON_IE, .p2p_go_set_probe_resp_ie = WMI_10_4_P2P_GO_SET_PROBE_RESP_IE, .p2p_set_vendor_ie_data_cmdid = WMI_10_4_P2P_SET_VENDOR_IE_DATA_CMDID, .ap_ps_peer_param_cmdid = WMI_10_4_AP_PS_PEER_PARAM_CMDID, .ap_ps_peer_uapsd_coex_cmdid = WMI_10_4_AP_PS_PEER_UAPSD_COEX_CMDID, .peer_rate_retry_sched_cmdid = WMI_10_4_PEER_RATE_RETRY_SCHED_CMDID, .wlan_profile_trigger_cmdid = WMI_10_4_WLAN_PROFILE_TRIGGER_CMDID, .wlan_profile_set_hist_intvl_cmdid = WMI_10_4_WLAN_PROFILE_SET_HIST_INTVL_CMDID, .wlan_profile_get_profile_data_cmdid = WMI_10_4_WLAN_PROFILE_GET_PROFILE_DATA_CMDID, .wlan_profile_enable_profile_id_cmdid = WMI_10_4_WLAN_PROFILE_ENABLE_PROFILE_ID_CMDID, .wlan_profile_list_profile_id_cmdid = WMI_10_4_WLAN_PROFILE_LIST_PROFILE_ID_CMDID, .pdev_suspend_cmdid = WMI_10_4_PDEV_SUSPEND_CMDID, .pdev_resume_cmdid = WMI_10_4_PDEV_RESUME_CMDID, .add_bcn_filter_cmdid = WMI_10_4_ADD_BCN_FILTER_CMDID, .rmv_bcn_filter_cmdid = WMI_10_4_RMV_BCN_FILTER_CMDID, .wow_add_wake_pattern_cmdid = WMI_10_4_WOW_ADD_WAKE_PATTERN_CMDID, .wow_del_wake_pattern_cmdid = WMI_10_4_WOW_DEL_WAKE_PATTERN_CMDID, .wow_enable_disable_wake_event_cmdid = WMI_10_4_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID, .wow_enable_cmdid = WMI_10_4_WOW_ENABLE_CMDID, .wow_hostwakeup_from_sleep_cmdid = WMI_10_4_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID, .rtt_measreq_cmdid = WMI_10_4_RTT_MEASREQ_CMDID, .rtt_tsf_cmdid = WMI_10_4_RTT_TSF_CMDID, .vdev_spectral_scan_configure_cmdid = WMI_10_4_VDEV_SPECTRAL_SCAN_CONFIGURE_CMDID, .vdev_spectral_scan_enable_cmdid = WMI_10_4_VDEV_SPECTRAL_SCAN_ENABLE_CMDID, .request_stats_cmdid = WMI_10_4_REQUEST_STATS_CMDID, .set_arp_ns_offload_cmdid = WMI_CMD_UNSUPPORTED, .network_list_offload_config_cmdid = WMI_CMD_UNSUPPORTED, .gtk_offload_cmdid = WMI_10_4_GTK_OFFLOAD_CMDID, .csa_offload_enable_cmdid = WMI_10_4_CSA_OFFLOAD_ENABLE_CMDID, .csa_offload_chanswitch_cmdid = WMI_10_4_CSA_OFFLOAD_CHANSWITCH_CMDID, .chatter_set_mode_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_addba_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_delba_cmdid = WMI_CMD_UNSUPPORTED, .sta_dtim_ps_method_cmdid = WMI_CMD_UNSUPPORTED, .sta_uapsd_auto_trig_cmdid = WMI_CMD_UNSUPPORTED, .sta_keepalive_cmd = WMI_CMD_UNSUPPORTED, .echo_cmdid = WMI_10_4_ECHO_CMDID, .pdev_utf_cmdid = WMI_10_4_PDEV_UTF_CMDID, .dbglog_cfg_cmdid = WMI_10_4_DBGLOG_CFG_CMDID, .pdev_qvit_cmdid = WMI_10_4_PDEV_QVIT_CMDID, .pdev_ftm_intg_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_keepalive_cmdid = WMI_10_4_VDEV_SET_KEEPALIVE_CMDID, .vdev_get_keepalive_cmdid = WMI_10_4_VDEV_GET_KEEPALIVE_CMDID, .force_fw_hang_cmdid = WMI_10_4_FORCE_FW_HANG_CMDID, .gpio_config_cmdid = WMI_10_4_GPIO_CONFIG_CMDID, .gpio_output_cmdid = WMI_10_4_GPIO_OUTPUT_CMDID, .pdev_get_temperature_cmdid = WMI_10_4_PDEV_GET_TEMPERATURE_CMDID, .vdev_set_wmm_params_cmdid = WMI_CMD_UNSUPPORTED, .adaptive_qcs_cmdid = WMI_CMD_UNSUPPORTED, .scan_update_request_cmdid = WMI_10_4_SCAN_UPDATE_REQUEST_CMDID, .vdev_standby_response_cmdid = WMI_10_4_VDEV_STANDBY_RESPONSE_CMDID, .vdev_resume_response_cmdid = WMI_10_4_VDEV_RESUME_RESPONSE_CMDID, .wlan_peer_caching_add_peer_cmdid = WMI_10_4_WLAN_PEER_CACHING_ADD_PEER_CMDID, .wlan_peer_caching_evict_peer_cmdid = WMI_10_4_WLAN_PEER_CACHING_EVICT_PEER_CMDID, .wlan_peer_caching_restore_peer_cmdid = WMI_10_4_WLAN_PEER_CACHING_RESTORE_PEER_CMDID, .wlan_peer_caching_print_all_peers_info_cmdid = WMI_10_4_WLAN_PEER_CACHING_PRINT_ALL_PEERS_INFO_CMDID, .peer_update_wds_entry_cmdid = WMI_10_4_PEER_UPDATE_WDS_ENTRY_CMDID, .peer_add_proxy_sta_entry_cmdid = WMI_10_4_PEER_ADD_PROXY_STA_ENTRY_CMDID, .rtt_keepalive_cmdid = WMI_10_4_RTT_KEEPALIVE_CMDID, .oem_req_cmdid = WMI_10_4_OEM_REQ_CMDID, .nan_cmdid = WMI_10_4_NAN_CMDID, .vdev_ratemask_cmdid = WMI_10_4_VDEV_RATEMASK_CMDID, .qboost_cfg_cmdid = WMI_10_4_QBOOST_CFG_CMDID, .pdev_smart_ant_enable_cmdid = WMI_10_4_PDEV_SMART_ANT_ENABLE_CMDID, .pdev_smart_ant_set_rx_antenna_cmdid = WMI_10_4_PDEV_SMART_ANT_SET_RX_ANTENNA_CMDID, .peer_smart_ant_set_tx_antenna_cmdid = WMI_10_4_PEER_SMART_ANT_SET_TX_ANTENNA_CMDID, .peer_smart_ant_set_train_info_cmdid = WMI_10_4_PEER_SMART_ANT_SET_TRAIN_INFO_CMDID, .peer_smart_ant_set_node_config_ops_cmdid = WMI_10_4_PEER_SMART_ANT_SET_NODE_CONFIG_OPS_CMDID, .pdev_set_antenna_switch_table_cmdid = WMI_10_4_PDEV_SET_ANTENNA_SWITCH_TABLE_CMDID, .pdev_set_ctl_table_cmdid = WMI_10_4_PDEV_SET_CTL_TABLE_CMDID, .pdev_set_mimogain_table_cmdid = WMI_10_4_PDEV_SET_MIMOGAIN_TABLE_CMDID, .pdev_ratepwr_table_cmdid = WMI_10_4_PDEV_RATEPWR_TABLE_CMDID, .pdev_ratepwr_chainmsk_table_cmdid = WMI_10_4_PDEV_RATEPWR_CHAINMSK_TABLE_CMDID, .pdev_fips_cmdid = WMI_10_4_PDEV_FIPS_CMDID, .tt_set_conf_cmdid = WMI_10_4_TT_SET_CONF_CMDID, .fwtest_cmdid = WMI_10_4_FWTEST_CMDID, .vdev_atf_request_cmdid = WMI_10_4_VDEV_ATF_REQUEST_CMDID, .peer_atf_request_cmdid = WMI_10_4_PEER_ATF_REQUEST_CMDID, .pdev_get_ani_cck_config_cmdid = WMI_10_4_PDEV_GET_ANI_CCK_CONFIG_CMDID, .pdev_get_ani_ofdm_config_cmdid = WMI_10_4_PDEV_GET_ANI_OFDM_CONFIG_CMDID, .pdev_reserve_ast_entry_cmdid = WMI_10_4_PDEV_RESERVE_AST_ENTRY_CMDID, .pdev_get_nfcal_power_cmdid = WMI_10_4_PDEV_GET_NFCAL_POWER_CMDID, .pdev_get_tpc_cmdid = WMI_10_4_PDEV_GET_TPC_CMDID, .pdev_get_ast_info_cmdid = WMI_10_4_PDEV_GET_AST_INFO_CMDID, .vdev_set_dscp_tid_map_cmdid = WMI_10_4_VDEV_SET_DSCP_TID_MAP_CMDID, .pdev_get_info_cmdid = WMI_10_4_PDEV_GET_INFO_CMDID, .vdev_get_info_cmdid = WMI_10_4_VDEV_GET_INFO_CMDID, .vdev_filter_neighbor_rx_packets_cmdid = WMI_10_4_VDEV_FILTER_NEIGHBOR_RX_PACKETS_CMDID, .mu_cal_start_cmdid = WMI_10_4_MU_CAL_START_CMDID, .set_cca_params_cmdid = WMI_10_4_SET_CCA_PARAMS_CMDID, .pdev_bss_chan_info_request_cmdid = WMI_10_4_PDEV_BSS_CHAN_INFO_REQUEST_CMDID, .ext_resource_cfg_cmdid = WMI_10_4_EXT_RESOURCE_CFG_CMDID, .vdev_set_ie_cmdid = WMI_10_4_VDEV_SET_IE_CMDID, .set_lteu_config_cmdid = WMI_10_4_SET_LTEU_CONFIG_CMDID, .atf_ssid_grouping_request_cmdid = WMI_10_4_ATF_SSID_GROUPING_REQUEST_CMDID, .peer_atf_ext_request_cmdid = WMI_10_4_PEER_ATF_EXT_REQUEST_CMDID, .set_periodic_channel_stats_cfg_cmdid = WMI_10_4_SET_PERIODIC_CHANNEL_STATS_CONFIG, .peer_bwf_request_cmdid = WMI_10_4_PEER_BWF_REQUEST_CMDID, .btcoex_cfg_cmdid = WMI_10_4_BTCOEX_CFG_CMDID, .peer_tx_mu_txmit_count_cmdid = WMI_10_4_PEER_TX_MU_TXMIT_COUNT_CMDID, .peer_tx_mu_txmit_rstcnt_cmdid = WMI_10_4_PEER_TX_MU_TXMIT_RSTCNT_CMDID, .peer_gid_userpos_list_cmdid = WMI_10_4_PEER_GID_USERPOS_LIST_CMDID, .pdev_check_cal_version_cmdid = WMI_10_4_PDEV_CHECK_CAL_VERSION_CMDID, .coex_version_cfg_cmid = WMI_10_4_COEX_VERSION_CFG_CMID, .pdev_get_rx_filter_cmdid = WMI_10_4_PDEV_GET_RX_FILTER_CMDID, .pdev_extended_nss_cfg_cmdid = WMI_10_4_PDEV_EXTENDED_NSS_CFG_CMDID, .vdev_set_scan_nac_rssi_cmdid = WMI_10_4_VDEV_SET_SCAN_NAC_RSSI_CMDID, .prog_gpio_band_select_cmdid = WMI_10_4_PROG_GPIO_BAND_SELECT_CMDID, .config_smart_logging_cmdid = WMI_10_4_CONFIG_SMART_LOGGING_CMDID, .debug_fatal_condition_cmdid = WMI_10_4_DEBUG_FATAL_CONDITION_CMDID, .get_tsf_timer_cmdid = WMI_10_4_GET_TSF_TIMER_CMDID, .pdev_get_tpc_table_cmdid = WMI_10_4_PDEV_GET_TPC_TABLE_CMDID, .vdev_sifs_trigger_time_cmdid = WMI_10_4_VDEV_SIFS_TRIGGER_TIME_CMDID, .pdev_wds_entry_list_cmdid = WMI_10_4_PDEV_WDS_ENTRY_LIST_CMDID, .tdls_set_state_cmdid = WMI_10_4_TDLS_SET_STATE_CMDID, .tdls_peer_update_cmdid = WMI_10_4_TDLS_PEER_UPDATE_CMDID, .tdls_set_offchan_mode_cmdid = WMI_10_4_TDLS_SET_OFFCHAN_MODE_CMDID, .radar_found_cmdid = WMI_10_4_RADAR_FOUND_CMDID, .per_peer_per_tid_config_cmdid = WMI_10_4_PER_PEER_PER_TID_CONFIG_CMDID, }; static struct wmi_peer_param_map wmi_peer_param_map = { .smps_state = WMI_PEER_SMPS_STATE, .ampdu = WMI_PEER_AMPDU, .authorize = WMI_PEER_AUTHORIZE, .chan_width = WMI_PEER_CHAN_WIDTH, .nss = WMI_PEER_NSS, .use_4addr = WMI_PEER_USE_4ADDR, .use_fixed_power = WMI_PEER_USE_FIXED_PWR, .debug = WMI_PEER_DEBUG, .phymode = WMI_PEER_PHYMODE, .dummy_var = WMI_PEER_DUMMY_VAR, }; /* MAIN WMI VDEV param map */ static struct wmi_vdev_param_map wmi_vdev_param_map = { .rts_threshold = WMI_VDEV_PARAM_RTS_THRESHOLD, .fragmentation_threshold = WMI_VDEV_PARAM_FRAGMENTATION_THRESHOLD, .beacon_interval = WMI_VDEV_PARAM_BEACON_INTERVAL, .listen_interval = WMI_VDEV_PARAM_LISTEN_INTERVAL, .multicast_rate = WMI_VDEV_PARAM_MULTICAST_RATE, .mgmt_tx_rate = WMI_VDEV_PARAM_MGMT_TX_RATE, .slot_time = WMI_VDEV_PARAM_SLOT_TIME, .preamble = WMI_VDEV_PARAM_PREAMBLE, .swba_time = WMI_VDEV_PARAM_SWBA_TIME, .wmi_vdev_stats_update_period = WMI_VDEV_STATS_UPDATE_PERIOD, .wmi_vdev_pwrsave_ageout_time = WMI_VDEV_PWRSAVE_AGEOUT_TIME, .wmi_vdev_host_swba_interval = WMI_VDEV_HOST_SWBA_INTERVAL, .dtim_period = WMI_VDEV_PARAM_DTIM_PERIOD, .wmi_vdev_oc_scheduler_air_time_limit = WMI_VDEV_OC_SCHEDULER_AIR_TIME_LIMIT, .wds = WMI_VDEV_PARAM_WDS, .atim_window = WMI_VDEV_PARAM_ATIM_WINDOW, .bmiss_count_max = WMI_VDEV_PARAM_BMISS_COUNT_MAX, .bmiss_first_bcnt = WMI_VDEV_PARAM_BMISS_FIRST_BCNT, .bmiss_final_bcnt = WMI_VDEV_PARAM_BMISS_FINAL_BCNT, .feature_wmm = WMI_VDEV_PARAM_FEATURE_WMM, .chwidth = WMI_VDEV_PARAM_CHWIDTH, .chextoffset = WMI_VDEV_PARAM_CHEXTOFFSET, .disable_htprotection = WMI_VDEV_PARAM_DISABLE_HTPROTECTION, .sta_quickkickout = WMI_VDEV_PARAM_STA_QUICKKICKOUT, .mgmt_rate = WMI_VDEV_PARAM_MGMT_RATE, .protection_mode = WMI_VDEV_PARAM_PROTECTION_MODE, .fixed_rate = WMI_VDEV_PARAM_FIXED_RATE, .sgi = WMI_VDEV_PARAM_SGI, .ldpc = WMI_VDEV_PARAM_LDPC, .tx_stbc = WMI_VDEV_PARAM_TX_STBC, .rx_stbc = WMI_VDEV_PARAM_RX_STBC, .intra_bss_fwd = WMI_VDEV_PARAM_INTRA_BSS_FWD, .def_keyid = WMI_VDEV_PARAM_DEF_KEYID, .nss = WMI_VDEV_PARAM_NSS, .bcast_data_rate = WMI_VDEV_PARAM_BCAST_DATA_RATE, .mcast_data_rate = WMI_VDEV_PARAM_MCAST_DATA_RATE, .mcast_indicate = WMI_VDEV_PARAM_MCAST_INDICATE, .dhcp_indicate = WMI_VDEV_PARAM_DHCP_INDICATE, .unknown_dest_indicate = WMI_VDEV_PARAM_UNKNOWN_DEST_INDICATE, .ap_keepalive_min_idle_inactive_time_secs = WMI_VDEV_PARAM_AP_KEEPALIVE_MIN_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_idle_inactive_time_secs = WMI_VDEV_PARAM_AP_KEEPALIVE_MAX_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_unresponsive_time_secs = WMI_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS, .ap_enable_nawds = WMI_VDEV_PARAM_AP_ENABLE_NAWDS, .mcast2ucast_set = WMI_VDEV_PARAM_UNSUPPORTED, .enable_rtscts = WMI_VDEV_PARAM_ENABLE_RTSCTS, .txbf = WMI_VDEV_PARAM_TXBF, .packet_powersave = WMI_VDEV_PARAM_PACKET_POWERSAVE, .drop_unencry = WMI_VDEV_PARAM_DROP_UNENCRY, .tx_encap_type = WMI_VDEV_PARAM_TX_ENCAP_TYPE, .ap_detect_out_of_sync_sleeping_sta_time_secs = WMI_VDEV_PARAM_UNSUPPORTED, .rc_num_retries = WMI_VDEV_PARAM_UNSUPPORTED, .cabq_maxdur = WMI_VDEV_PARAM_UNSUPPORTED, .mfptest_set = WMI_VDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_VDEV_PARAM_UNSUPPORTED, .vht_sgimask = WMI_VDEV_PARAM_UNSUPPORTED, .vht80_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_enable = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_tgt_bmiss_num = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_bmiss_sample_cycle = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_slop_step = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_init_slop = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_pause = WMI_VDEV_PARAM_UNSUPPORTED, .proxy_sta = WMI_VDEV_PARAM_UNSUPPORTED, .meru_vc = WMI_VDEV_PARAM_UNSUPPORTED, .rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED, .bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED, .rtt_responder_role = WMI_VDEV_PARAM_UNSUPPORTED, }; /* 10.X WMI VDEV param map */ static struct wmi_vdev_param_map wmi_10x_vdev_param_map = { .rts_threshold = WMI_10X_VDEV_PARAM_RTS_THRESHOLD, .fragmentation_threshold = WMI_10X_VDEV_PARAM_FRAGMENTATION_THRESHOLD, .beacon_interval = WMI_10X_VDEV_PARAM_BEACON_INTERVAL, .listen_interval = WMI_10X_VDEV_PARAM_LISTEN_INTERVAL, .multicast_rate = WMI_10X_VDEV_PARAM_MULTICAST_RATE, .mgmt_tx_rate = WMI_10X_VDEV_PARAM_MGMT_TX_RATE, .slot_time = WMI_10X_VDEV_PARAM_SLOT_TIME, .preamble = WMI_10X_VDEV_PARAM_PREAMBLE, .swba_time = WMI_10X_VDEV_PARAM_SWBA_TIME, .wmi_vdev_stats_update_period = WMI_10X_VDEV_STATS_UPDATE_PERIOD, .wmi_vdev_pwrsave_ageout_time = WMI_10X_VDEV_PWRSAVE_AGEOUT_TIME, .wmi_vdev_host_swba_interval = WMI_10X_VDEV_HOST_SWBA_INTERVAL, .dtim_period = WMI_10X_VDEV_PARAM_DTIM_PERIOD, .wmi_vdev_oc_scheduler_air_time_limit = WMI_10X_VDEV_OC_SCHEDULER_AIR_TIME_LIMIT, .wds = WMI_10X_VDEV_PARAM_WDS, .atim_window = WMI_10X_VDEV_PARAM_ATIM_WINDOW, .bmiss_count_max = WMI_10X_VDEV_PARAM_BMISS_COUNT_MAX, .bmiss_first_bcnt = WMI_VDEV_PARAM_UNSUPPORTED, .bmiss_final_bcnt = WMI_VDEV_PARAM_UNSUPPORTED, .feature_wmm = WMI_10X_VDEV_PARAM_FEATURE_WMM, .chwidth = WMI_10X_VDEV_PARAM_CHWIDTH, .chextoffset = WMI_10X_VDEV_PARAM_CHEXTOFFSET, .disable_htprotection = WMI_10X_VDEV_PARAM_DISABLE_HTPROTECTION, .sta_quickkickout = WMI_10X_VDEV_PARAM_STA_QUICKKICKOUT, .mgmt_rate = WMI_10X_VDEV_PARAM_MGMT_RATE, .protection_mode = WMI_10X_VDEV_PARAM_PROTECTION_MODE, .fixed_rate = WMI_10X_VDEV_PARAM_FIXED_RATE, .sgi = WMI_10X_VDEV_PARAM_SGI, .ldpc = WMI_10X_VDEV_PARAM_LDPC, .tx_stbc = WMI_10X_VDEV_PARAM_TX_STBC, .rx_stbc = WMI_10X_VDEV_PARAM_RX_STBC, .intra_bss_fwd = WMI_10X_VDEV_PARAM_INTRA_BSS_FWD, .def_keyid = WMI_10X_VDEV_PARAM_DEF_KEYID, .nss = WMI_10X_VDEV_PARAM_NSS, .bcast_data_rate = WMI_10X_VDEV_PARAM_BCAST_DATA_RATE, .mcast_data_rate = WMI_10X_VDEV_PARAM_MCAST_DATA_RATE, .mcast_indicate = WMI_10X_VDEV_PARAM_MCAST_INDICATE, .dhcp_indicate = WMI_10X_VDEV_PARAM_DHCP_INDICATE, .unknown_dest_indicate = WMI_10X_VDEV_PARAM_UNKNOWN_DEST_INDICATE, .ap_keepalive_min_idle_inactive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MIN_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_idle_inactive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MAX_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_unresponsive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS, .ap_enable_nawds = WMI_10X_VDEV_PARAM_AP_ENABLE_NAWDS, .mcast2ucast_set = WMI_10X_VDEV_PARAM_MCAST2UCAST_SET, .enable_rtscts = WMI_10X_VDEV_PARAM_ENABLE_RTSCTS, .txbf = WMI_VDEV_PARAM_UNSUPPORTED, .packet_powersave = WMI_VDEV_PARAM_UNSUPPORTED, .drop_unencry = WMI_VDEV_PARAM_UNSUPPORTED, .tx_encap_type = WMI_VDEV_PARAM_UNSUPPORTED, .ap_detect_out_of_sync_sleeping_sta_time_secs = WMI_10X_VDEV_PARAM_AP_DETECT_OUT_OF_SYNC_SLEEPING_STA_TIME_SECS, .rc_num_retries = WMI_VDEV_PARAM_UNSUPPORTED, .cabq_maxdur = WMI_VDEV_PARAM_UNSUPPORTED, .mfptest_set = WMI_VDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_VDEV_PARAM_UNSUPPORTED, .vht_sgimask = WMI_VDEV_PARAM_UNSUPPORTED, .vht80_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_enable = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_tgt_bmiss_num = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_bmiss_sample_cycle = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_slop_step = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_init_slop = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_pause = WMI_VDEV_PARAM_UNSUPPORTED, .proxy_sta = WMI_VDEV_PARAM_UNSUPPORTED, .meru_vc = WMI_VDEV_PARAM_UNSUPPORTED, .rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED, .bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED, .rtt_responder_role = WMI_VDEV_PARAM_UNSUPPORTED, }; static struct wmi_vdev_param_map wmi_10_2_4_vdev_param_map = { .rts_threshold = WMI_10X_VDEV_PARAM_RTS_THRESHOLD, .fragmentation_threshold = WMI_10X_VDEV_PARAM_FRAGMENTATION_THRESHOLD, .beacon_interval = WMI_10X_VDEV_PARAM_BEACON_INTERVAL, .listen_interval = WMI_10X_VDEV_PARAM_LISTEN_INTERVAL, .multicast_rate = WMI_10X_VDEV_PARAM_MULTICAST_RATE, .mgmt_tx_rate = WMI_10X_VDEV_PARAM_MGMT_TX_RATE, .slot_time = WMI_10X_VDEV_PARAM_SLOT_TIME, .preamble = WMI_10X_VDEV_PARAM_PREAMBLE, .swba_time = WMI_10X_VDEV_PARAM_SWBA_TIME, .wmi_vdev_stats_update_period = WMI_10X_VDEV_STATS_UPDATE_PERIOD, .wmi_vdev_pwrsave_ageout_time = WMI_10X_VDEV_PWRSAVE_AGEOUT_TIME, .wmi_vdev_host_swba_interval = WMI_10X_VDEV_HOST_SWBA_INTERVAL, .dtim_period = WMI_10X_VDEV_PARAM_DTIM_PERIOD, .wmi_vdev_oc_scheduler_air_time_limit = WMI_10X_VDEV_OC_SCHEDULER_AIR_TIME_LIMIT, .wds = WMI_10X_VDEV_PARAM_WDS, .atim_window = WMI_10X_VDEV_PARAM_ATIM_WINDOW, .bmiss_count_max = WMI_10X_VDEV_PARAM_BMISS_COUNT_MAX, .bmiss_first_bcnt = WMI_VDEV_PARAM_UNSUPPORTED, .bmiss_final_bcnt = WMI_VDEV_PARAM_UNSUPPORTED, .feature_wmm = WMI_10X_VDEV_PARAM_FEATURE_WMM, .chwidth = WMI_10X_VDEV_PARAM_CHWIDTH, .chextoffset = WMI_10X_VDEV_PARAM_CHEXTOFFSET, .disable_htprotection = WMI_10X_VDEV_PARAM_DISABLE_HTPROTECTION, .sta_quickkickout = WMI_10X_VDEV_PARAM_STA_QUICKKICKOUT, .mgmt_rate = WMI_10X_VDEV_PARAM_MGMT_RATE, .protection_mode = WMI_10X_VDEV_PARAM_PROTECTION_MODE, .fixed_rate = WMI_10X_VDEV_PARAM_FIXED_RATE, .sgi = WMI_10X_VDEV_PARAM_SGI, .ldpc = WMI_10X_VDEV_PARAM_LDPC, .tx_stbc = WMI_10X_VDEV_PARAM_TX_STBC, .rx_stbc = WMI_10X_VDEV_PARAM_RX_STBC, .intra_bss_fwd = WMI_10X_VDEV_PARAM_INTRA_BSS_FWD, .def_keyid = WMI_10X_VDEV_PARAM_DEF_KEYID, .nss = WMI_10X_VDEV_PARAM_NSS, .bcast_data_rate = WMI_10X_VDEV_PARAM_BCAST_DATA_RATE, .mcast_data_rate = WMI_10X_VDEV_PARAM_MCAST_DATA_RATE, .mcast_indicate = WMI_10X_VDEV_PARAM_MCAST_INDICATE, .dhcp_indicate = WMI_10X_VDEV_PARAM_DHCP_INDICATE, .unknown_dest_indicate = WMI_10X_VDEV_PARAM_UNKNOWN_DEST_INDICATE, .ap_keepalive_min_idle_inactive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MIN_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_idle_inactive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MAX_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_unresponsive_time_secs = WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS, .ap_enable_nawds = WMI_10X_VDEV_PARAM_AP_ENABLE_NAWDS, .mcast2ucast_set = WMI_10X_VDEV_PARAM_MCAST2UCAST_SET, .enable_rtscts = WMI_10X_VDEV_PARAM_ENABLE_RTSCTS, .txbf = WMI_VDEV_PARAM_UNSUPPORTED, .packet_powersave = WMI_VDEV_PARAM_UNSUPPORTED, .drop_unencry = WMI_VDEV_PARAM_UNSUPPORTED, .tx_encap_type = WMI_VDEV_PARAM_UNSUPPORTED, .ap_detect_out_of_sync_sleeping_sta_time_secs = WMI_10X_VDEV_PARAM_AP_DETECT_OUT_OF_SYNC_SLEEPING_STA_TIME_SECS, .rc_num_retries = WMI_VDEV_PARAM_UNSUPPORTED, .cabq_maxdur = WMI_VDEV_PARAM_UNSUPPORTED, .mfptest_set = WMI_VDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_VDEV_PARAM_UNSUPPORTED, .vht_sgimask = WMI_VDEV_PARAM_UNSUPPORTED, .vht80_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_enable = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_tgt_bmiss_num = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_bmiss_sample_cycle = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_slop_step = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_init_slop = WMI_VDEV_PARAM_UNSUPPORTED, .early_rx_adjust_pause = WMI_VDEV_PARAM_UNSUPPORTED, .proxy_sta = WMI_VDEV_PARAM_UNSUPPORTED, .meru_vc = WMI_VDEV_PARAM_UNSUPPORTED, .rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED, .bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED, .disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED, .rtt_responder_role = WMI_VDEV_PARAM_UNSUPPORTED, }; static struct wmi_vdev_param_map wmi_10_4_vdev_param_map = { .rts_threshold = WMI_10_4_VDEV_PARAM_RTS_THRESHOLD, .fragmentation_threshold = WMI_10_4_VDEV_PARAM_FRAGMENTATION_THRESHOLD, .beacon_interval = WMI_10_4_VDEV_PARAM_BEACON_INTERVAL, .listen_interval = WMI_10_4_VDEV_PARAM_LISTEN_INTERVAL, .multicast_rate = WMI_10_4_VDEV_PARAM_MULTICAST_RATE, .mgmt_tx_rate = WMI_10_4_VDEV_PARAM_MGMT_TX_RATE, .slot_time = WMI_10_4_VDEV_PARAM_SLOT_TIME, .preamble = WMI_10_4_VDEV_PARAM_PREAMBLE, .swba_time = WMI_10_4_VDEV_PARAM_SWBA_TIME, .wmi_vdev_stats_update_period = WMI_10_4_VDEV_STATS_UPDATE_PERIOD, .wmi_vdev_pwrsave_ageout_time = WMI_10_4_VDEV_PWRSAVE_AGEOUT_TIME, .wmi_vdev_host_swba_interval = WMI_10_4_VDEV_HOST_SWBA_INTERVAL, .dtim_period = WMI_10_4_VDEV_PARAM_DTIM_PERIOD, .wmi_vdev_oc_scheduler_air_time_limit = WMI_10_4_VDEV_OC_SCHEDULER_AIR_TIME_LIMIT, .wds = WMI_10_4_VDEV_PARAM_WDS, .atim_window = WMI_10_4_VDEV_PARAM_ATIM_WINDOW, .bmiss_count_max = WMI_10_4_VDEV_PARAM_BMISS_COUNT_MAX, .bmiss_first_bcnt = WMI_10_4_VDEV_PARAM_BMISS_FIRST_BCNT, .bmiss_final_bcnt = WMI_10_4_VDEV_PARAM_BMISS_FINAL_BCNT, .feature_wmm = WMI_10_4_VDEV_PARAM_FEATURE_WMM, .chwidth = WMI_10_4_VDEV_PARAM_CHWIDTH, .chextoffset = WMI_10_4_VDEV_PARAM_CHEXTOFFSET, .disable_htprotection = WMI_10_4_VDEV_PARAM_DISABLE_HTPROTECTION, .sta_quickkickout = WMI_10_4_VDEV_PARAM_STA_QUICKKICKOUT, .mgmt_rate = WMI_10_4_VDEV_PARAM_MGMT_RATE, .protection_mode = WMI_10_4_VDEV_PARAM_PROTECTION_MODE, .fixed_rate = WMI_10_4_VDEV_PARAM_FIXED_RATE, .sgi = WMI_10_4_VDEV_PARAM_SGI, .ldpc = WMI_10_4_VDEV_PARAM_LDPC, .tx_stbc = WMI_10_4_VDEV_PARAM_TX_STBC, .rx_stbc = WMI_10_4_VDEV_PARAM_RX_STBC, .intra_bss_fwd = WMI_10_4_VDEV_PARAM_INTRA_BSS_FWD, .def_keyid = WMI_10_4_VDEV_PARAM_DEF_KEYID, .nss = WMI_10_4_VDEV_PARAM_NSS, .bcast_data_rate = WMI_10_4_VDEV_PARAM_BCAST_DATA_RATE, .mcast_data_rate = WMI_10_4_VDEV_PARAM_MCAST_DATA_RATE, .mcast_indicate = WMI_10_4_VDEV_PARAM_MCAST_INDICATE, .dhcp_indicate = WMI_10_4_VDEV_PARAM_DHCP_INDICATE, .unknown_dest_indicate = WMI_10_4_VDEV_PARAM_UNKNOWN_DEST_INDICATE, .ap_keepalive_min_idle_inactive_time_secs = WMI_10_4_VDEV_PARAM_AP_KEEPALIVE_MIN_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_idle_inactive_time_secs = WMI_10_4_VDEV_PARAM_AP_KEEPALIVE_MAX_IDLE_INACTIVE_TIME_SECS, .ap_keepalive_max_unresponsive_time_secs = WMI_10_4_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS, .ap_enable_nawds = WMI_10_4_VDEV_PARAM_AP_ENABLE_NAWDS, .mcast2ucast_set = WMI_10_4_VDEV_PARAM_MCAST2UCAST_SET, .enable_rtscts = WMI_10_4_VDEV_PARAM_ENABLE_RTSCTS, .txbf = WMI_10_4_VDEV_PARAM_TXBF, .packet_powersave = WMI_10_4_VDEV_PARAM_PACKET_POWERSAVE, .drop_unencry = WMI_10_4_VDEV_PARAM_DROP_UNENCRY, .tx_encap_type = WMI_10_4_VDEV_PARAM_TX_ENCAP_TYPE, .ap_detect_out_of_sync_sleeping_sta_time_secs = WMI_10_4_VDEV_PARAM_AP_DETECT_OUT_OF_SYNC_SLEEPING_STA_TIME_SECS, .rc_num_retries = WMI_10_4_VDEV_PARAM_RC_NUM_RETRIES, .cabq_maxdur = WMI_10_4_VDEV_PARAM_CABQ_MAXDUR, .mfptest_set = WMI_10_4_VDEV_PARAM_MFPTEST_SET, .rts_fixed_rate = WMI_10_4_VDEV_PARAM_RTS_FIXED_RATE, .vht_sgimask = WMI_10_4_VDEV_PARAM_VHT_SGIMASK, .vht80_ratemask = WMI_10_4_VDEV_PARAM_VHT80_RATEMASK, .early_rx_adjust_enable = WMI_10_4_VDEV_PARAM_EARLY_RX_ADJUST_ENABLE, .early_rx_tgt_bmiss_num = WMI_10_4_VDEV_PARAM_EARLY_RX_TGT_BMISS_NUM, .early_rx_bmiss_sample_cycle = WMI_10_4_VDEV_PARAM_EARLY_RX_BMISS_SAMPLE_CYCLE, .early_rx_slop_step = WMI_10_4_VDEV_PARAM_EARLY_RX_SLOP_STEP, .early_rx_init_slop = WMI_10_4_VDEV_PARAM_EARLY_RX_INIT_SLOP, .early_rx_adjust_pause = WMI_10_4_VDEV_PARAM_EARLY_RX_ADJUST_PAUSE, .proxy_sta = WMI_10_4_VDEV_PARAM_PROXY_STA, .meru_vc = WMI_10_4_VDEV_PARAM_MERU_VC, .rx_decap_type = WMI_10_4_VDEV_PARAM_RX_DECAP_TYPE, .bw_nss_ratemask = WMI_10_4_VDEV_PARAM_BW_NSS_RATEMASK, .inc_tsf = WMI_10_4_VDEV_PARAM_TSF_INCREMENT, .dec_tsf = WMI_10_4_VDEV_PARAM_TSF_DECREMENT, .disable_4addr_src_lrn = WMI_10_4_VDEV_PARAM_DISABLE_4_ADDR_SRC_LRN, .rtt_responder_role = WMI_10_4_VDEV_PARAM_ENABLE_DISABLE_RTT_RESPONDER_ROLE, }; static struct wmi_pdev_param_map wmi_pdev_param_map = { .tx_chain_mask = WMI_PDEV_PARAM_TX_CHAIN_MASK, .rx_chain_mask = WMI_PDEV_PARAM_RX_CHAIN_MASK, .txpower_limit2g = WMI_PDEV_PARAM_TXPOWER_LIMIT2G, .txpower_limit5g = WMI_PDEV_PARAM_TXPOWER_LIMIT5G, .txpower_scale = WMI_PDEV_PARAM_TXPOWER_SCALE, .beacon_gen_mode = WMI_PDEV_PARAM_BEACON_GEN_MODE, .beacon_tx_mode = WMI_PDEV_PARAM_BEACON_TX_MODE, .resmgr_offchan_mode = WMI_PDEV_PARAM_RESMGR_OFFCHAN_MODE, .protection_mode = WMI_PDEV_PARAM_PROTECTION_MODE, .dynamic_bw = WMI_PDEV_PARAM_DYNAMIC_BW, .non_agg_sw_retry_th = WMI_PDEV_PARAM_NON_AGG_SW_RETRY_TH, .agg_sw_retry_th = WMI_PDEV_PARAM_AGG_SW_RETRY_TH, .sta_kickout_th = WMI_PDEV_PARAM_STA_KICKOUT_TH, .ac_aggrsize_scaling = WMI_PDEV_PARAM_AC_AGGRSIZE_SCALING, .ltr_enable = WMI_PDEV_PARAM_LTR_ENABLE, .ltr_ac_latency_be = WMI_PDEV_PARAM_LTR_AC_LATENCY_BE, .ltr_ac_latency_bk = WMI_PDEV_PARAM_LTR_AC_LATENCY_BK, .ltr_ac_latency_vi = WMI_PDEV_PARAM_LTR_AC_LATENCY_VI, .ltr_ac_latency_vo = WMI_PDEV_PARAM_LTR_AC_LATENCY_VO, .ltr_ac_latency_timeout = WMI_PDEV_PARAM_LTR_AC_LATENCY_TIMEOUT, .ltr_sleep_override = WMI_PDEV_PARAM_LTR_SLEEP_OVERRIDE, .ltr_rx_override = WMI_PDEV_PARAM_LTR_RX_OVERRIDE, .ltr_tx_activity_timeout = WMI_PDEV_PARAM_LTR_TX_ACTIVITY_TIMEOUT, .l1ss_enable = WMI_PDEV_PARAM_L1SS_ENABLE, .dsleep_enable = WMI_PDEV_PARAM_DSLEEP_ENABLE, .pcielp_txbuf_flush = WMI_PDEV_PARAM_PCIELP_TXBUF_FLUSH, .pcielp_txbuf_watermark = WMI_PDEV_PARAM_PCIELP_TXBUF_TMO_EN, .pcielp_txbuf_tmo_en = WMI_PDEV_PARAM_PCIELP_TXBUF_TMO_EN, .pcielp_txbuf_tmo_value = WMI_PDEV_PARAM_PCIELP_TXBUF_TMO_VALUE, .pdev_stats_update_period = WMI_PDEV_PARAM_PDEV_STATS_UPDATE_PERIOD, .vdev_stats_update_period = WMI_PDEV_PARAM_VDEV_STATS_UPDATE_PERIOD, .peer_stats_update_period = WMI_PDEV_PARAM_PEER_STATS_UPDATE_PERIOD, .bcnflt_stats_update_period = WMI_PDEV_PARAM_BCNFLT_STATS_UPDATE_PERIOD, .pmf_qos = WMI_PDEV_PARAM_PMF_QOS, .arp_ac_override = WMI_PDEV_PARAM_ARP_AC_OVERRIDE, .dcs = WMI_PDEV_PARAM_DCS, .ani_enable = WMI_PDEV_PARAM_ANI_ENABLE, .ani_poll_period = WMI_PDEV_PARAM_ANI_POLL_PERIOD, .ani_listen_period = WMI_PDEV_PARAM_ANI_LISTEN_PERIOD, .ani_ofdm_level = WMI_PDEV_PARAM_ANI_OFDM_LEVEL, .ani_cck_level = WMI_PDEV_PARAM_ANI_CCK_LEVEL, .dyntxchain = WMI_PDEV_PARAM_DYNTXCHAIN, .proxy_sta = WMI_PDEV_PARAM_PROXY_STA, .idle_ps_config = WMI_PDEV_PARAM_IDLE_PS_CONFIG, .power_gating_sleep = WMI_PDEV_PARAM_POWER_GATING_SLEEP, .fast_channel_reset = WMI_PDEV_PARAM_UNSUPPORTED, .burst_dur = WMI_PDEV_PARAM_UNSUPPORTED, .burst_enable = WMI_PDEV_PARAM_UNSUPPORTED, .cal_period = WMI_PDEV_PARAM_UNSUPPORTED, .aggr_burst = WMI_PDEV_PARAM_UNSUPPORTED, .rx_decap_mode = WMI_PDEV_PARAM_UNSUPPORTED, .smart_antenna_default_antenna = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_override = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_tid = WMI_PDEV_PARAM_UNSUPPORTED, .antenna_gain = WMI_PDEV_PARAM_UNSUPPORTED, .rx_filter = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_to_ucast_tid = WMI_PDEV_PARAM_UNSUPPORTED, .proxy_sta_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .remove_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .peer_sta_ps_statechg_enable = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_ac_override = WMI_PDEV_PARAM_UNSUPPORTED, .block_interbss = WMI_PDEV_PARAM_UNSUPPORTED, .set_disable_reset_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_msdu_ttl_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_ppdu_duration_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .txbf_sound_period_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_promisc_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_burst_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .en_stats = WMI_PDEV_PARAM_UNSUPPORTED, .mu_group_policy = WMI_PDEV_PARAM_UNSUPPORTED, .noise_detection = WMI_PDEV_PARAM_UNSUPPORTED, .noise_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .dpd_enable = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_bcast_echo = WMI_PDEV_PARAM_UNSUPPORTED, .atf_strict_sch = WMI_PDEV_PARAM_UNSUPPORTED, .atf_sched_duration = WMI_PDEV_PARAM_UNSUPPORTED, .ant_plzn = WMI_PDEV_PARAM_UNSUPPORTED, .mgmt_retry_limit = WMI_PDEV_PARAM_UNSUPPORTED, .sensitivity_level = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_2g = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_5g = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_amsdu = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_ampdu = WMI_PDEV_PARAM_UNSUPPORTED, .cca_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_PDEV_PARAM_UNSUPPORTED, .pdev_reset = WMI_PDEV_PARAM_UNSUPPORTED, .wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED, .arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED, .arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED, .enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED, }; static struct wmi_pdev_param_map wmi_10x_pdev_param_map = { .tx_chain_mask = WMI_10X_PDEV_PARAM_TX_CHAIN_MASK, .rx_chain_mask = WMI_10X_PDEV_PARAM_RX_CHAIN_MASK, .txpower_limit2g = WMI_10X_PDEV_PARAM_TXPOWER_LIMIT2G, .txpower_limit5g = WMI_10X_PDEV_PARAM_TXPOWER_LIMIT5G, .txpower_scale = WMI_10X_PDEV_PARAM_TXPOWER_SCALE, .beacon_gen_mode = WMI_10X_PDEV_PARAM_BEACON_GEN_MODE, .beacon_tx_mode = WMI_10X_PDEV_PARAM_BEACON_TX_MODE, .resmgr_offchan_mode = WMI_10X_PDEV_PARAM_RESMGR_OFFCHAN_MODE, .protection_mode = WMI_10X_PDEV_PARAM_PROTECTION_MODE, .dynamic_bw = WMI_10X_PDEV_PARAM_DYNAMIC_BW, .non_agg_sw_retry_th = WMI_10X_PDEV_PARAM_NON_AGG_SW_RETRY_TH, .agg_sw_retry_th = WMI_10X_PDEV_PARAM_AGG_SW_RETRY_TH, .sta_kickout_th = WMI_10X_PDEV_PARAM_STA_KICKOUT_TH, .ac_aggrsize_scaling = WMI_10X_PDEV_PARAM_AC_AGGRSIZE_SCALING, .ltr_enable = WMI_10X_PDEV_PARAM_LTR_ENABLE, .ltr_ac_latency_be = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_BE, .ltr_ac_latency_bk = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_BK, .ltr_ac_latency_vi = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_VI, .ltr_ac_latency_vo = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_VO, .ltr_ac_latency_timeout = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_TIMEOUT, .ltr_sleep_override = WMI_10X_PDEV_PARAM_LTR_SLEEP_OVERRIDE, .ltr_rx_override = WMI_10X_PDEV_PARAM_LTR_RX_OVERRIDE, .ltr_tx_activity_timeout = WMI_10X_PDEV_PARAM_LTR_TX_ACTIVITY_TIMEOUT, .l1ss_enable = WMI_10X_PDEV_PARAM_L1SS_ENABLE, .dsleep_enable = WMI_10X_PDEV_PARAM_DSLEEP_ENABLE, .pcielp_txbuf_flush = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_watermark = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_tmo_en = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_tmo_value = WMI_PDEV_PARAM_UNSUPPORTED, .pdev_stats_update_period = WMI_10X_PDEV_PARAM_PDEV_STATS_UPDATE_PERIOD, .vdev_stats_update_period = WMI_10X_PDEV_PARAM_VDEV_STATS_UPDATE_PERIOD, .peer_stats_update_period = WMI_10X_PDEV_PARAM_PEER_STATS_UPDATE_PERIOD, .bcnflt_stats_update_period = WMI_10X_PDEV_PARAM_BCNFLT_STATS_UPDATE_PERIOD, .pmf_qos = WMI_10X_PDEV_PARAM_PMF_QOS, .arp_ac_override = WMI_10X_PDEV_PARAM_ARPDHCP_AC_OVERRIDE, .dcs = WMI_10X_PDEV_PARAM_DCS, .ani_enable = WMI_10X_PDEV_PARAM_ANI_ENABLE, .ani_poll_period = WMI_10X_PDEV_PARAM_ANI_POLL_PERIOD, .ani_listen_period = WMI_10X_PDEV_PARAM_ANI_LISTEN_PERIOD, .ani_ofdm_level = WMI_10X_PDEV_PARAM_ANI_OFDM_LEVEL, .ani_cck_level = WMI_10X_PDEV_PARAM_ANI_CCK_LEVEL, .dyntxchain = WMI_10X_PDEV_PARAM_DYNTXCHAIN, .proxy_sta = WMI_PDEV_PARAM_UNSUPPORTED, .idle_ps_config = WMI_PDEV_PARAM_UNSUPPORTED, .power_gating_sleep = WMI_PDEV_PARAM_UNSUPPORTED, .fast_channel_reset = WMI_10X_PDEV_PARAM_FAST_CHANNEL_RESET, .burst_dur = WMI_10X_PDEV_PARAM_BURST_DUR, .burst_enable = WMI_10X_PDEV_PARAM_BURST_ENABLE, .cal_period = WMI_10X_PDEV_PARAM_CAL_PERIOD, .aggr_burst = WMI_PDEV_PARAM_UNSUPPORTED, .rx_decap_mode = WMI_PDEV_PARAM_UNSUPPORTED, .smart_antenna_default_antenna = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_override = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_tid = WMI_PDEV_PARAM_UNSUPPORTED, .antenna_gain = WMI_PDEV_PARAM_UNSUPPORTED, .rx_filter = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_to_ucast_tid = WMI_PDEV_PARAM_UNSUPPORTED, .proxy_sta_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .remove_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .peer_sta_ps_statechg_enable = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_ac_override = WMI_PDEV_PARAM_UNSUPPORTED, .block_interbss = WMI_PDEV_PARAM_UNSUPPORTED, .set_disable_reset_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_msdu_ttl_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_ppdu_duration_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .txbf_sound_period_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_promisc_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_burst_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .en_stats = WMI_PDEV_PARAM_UNSUPPORTED, .mu_group_policy = WMI_PDEV_PARAM_UNSUPPORTED, .noise_detection = WMI_PDEV_PARAM_UNSUPPORTED, .noise_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .dpd_enable = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_bcast_echo = WMI_PDEV_PARAM_UNSUPPORTED, .atf_strict_sch = WMI_PDEV_PARAM_UNSUPPORTED, .atf_sched_duration = WMI_PDEV_PARAM_UNSUPPORTED, .ant_plzn = WMI_PDEV_PARAM_UNSUPPORTED, .mgmt_retry_limit = WMI_PDEV_PARAM_UNSUPPORTED, .sensitivity_level = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_2g = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_5g = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_amsdu = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_ampdu = WMI_PDEV_PARAM_UNSUPPORTED, .cca_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_PDEV_PARAM_UNSUPPORTED, .pdev_reset = WMI_PDEV_PARAM_UNSUPPORTED, .wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED, .arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED, .arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED, .enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED, }; static struct wmi_pdev_param_map wmi_10_2_4_pdev_param_map = { .tx_chain_mask = WMI_10X_PDEV_PARAM_TX_CHAIN_MASK, .rx_chain_mask = WMI_10X_PDEV_PARAM_RX_CHAIN_MASK, .txpower_limit2g = WMI_10X_PDEV_PARAM_TXPOWER_LIMIT2G, .txpower_limit5g = WMI_10X_PDEV_PARAM_TXPOWER_LIMIT5G, .txpower_scale = WMI_10X_PDEV_PARAM_TXPOWER_SCALE, .beacon_gen_mode = WMI_10X_PDEV_PARAM_BEACON_GEN_MODE, .beacon_tx_mode = WMI_10X_PDEV_PARAM_BEACON_TX_MODE, .resmgr_offchan_mode = WMI_10X_PDEV_PARAM_RESMGR_OFFCHAN_MODE, .protection_mode = WMI_10X_PDEV_PARAM_PROTECTION_MODE, .dynamic_bw = WMI_10X_PDEV_PARAM_DYNAMIC_BW, .non_agg_sw_retry_th = WMI_10X_PDEV_PARAM_NON_AGG_SW_RETRY_TH, .agg_sw_retry_th = WMI_10X_PDEV_PARAM_AGG_SW_RETRY_TH, .sta_kickout_th = WMI_10X_PDEV_PARAM_STA_KICKOUT_TH, .ac_aggrsize_scaling = WMI_10X_PDEV_PARAM_AC_AGGRSIZE_SCALING, .ltr_enable = WMI_10X_PDEV_PARAM_LTR_ENABLE, .ltr_ac_latency_be = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_BE, .ltr_ac_latency_bk = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_BK, .ltr_ac_latency_vi = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_VI, .ltr_ac_latency_vo = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_VO, .ltr_ac_latency_timeout = WMI_10X_PDEV_PARAM_LTR_AC_LATENCY_TIMEOUT, .ltr_sleep_override = WMI_10X_PDEV_PARAM_LTR_SLEEP_OVERRIDE, .ltr_rx_override = WMI_10X_PDEV_PARAM_LTR_RX_OVERRIDE, .ltr_tx_activity_timeout = WMI_10X_PDEV_PARAM_LTR_TX_ACTIVITY_TIMEOUT, .l1ss_enable = WMI_10X_PDEV_PARAM_L1SS_ENABLE, .dsleep_enable = WMI_10X_PDEV_PARAM_DSLEEP_ENABLE, .pcielp_txbuf_flush = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_watermark = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_tmo_en = WMI_PDEV_PARAM_UNSUPPORTED, .pcielp_txbuf_tmo_value = WMI_PDEV_PARAM_UNSUPPORTED, .pdev_stats_update_period = WMI_10X_PDEV_PARAM_PDEV_STATS_UPDATE_PERIOD, .vdev_stats_update_period = WMI_10X_PDEV_PARAM_VDEV_STATS_UPDATE_PERIOD, .peer_stats_update_period = WMI_10X_PDEV_PARAM_PEER_STATS_UPDATE_PERIOD, .bcnflt_stats_update_period = WMI_10X_PDEV_PARAM_BCNFLT_STATS_UPDATE_PERIOD, .pmf_qos = WMI_10X_PDEV_PARAM_PMF_QOS, .arp_ac_override = WMI_10X_PDEV_PARAM_ARPDHCP_AC_OVERRIDE, .dcs = WMI_10X_PDEV_PARAM_DCS, .ani_enable = WMI_10X_PDEV_PARAM_ANI_ENABLE, .ani_poll_period = WMI_10X_PDEV_PARAM_ANI_POLL_PERIOD, .ani_listen_period = WMI_10X_PDEV_PARAM_ANI_LISTEN_PERIOD, .ani_ofdm_level = WMI_10X_PDEV_PARAM_ANI_OFDM_LEVEL, .ani_cck_level = WMI_10X_PDEV_PARAM_ANI_CCK_LEVEL, .dyntxchain = WMI_10X_PDEV_PARAM_DYNTXCHAIN, .proxy_sta = WMI_PDEV_PARAM_UNSUPPORTED, .idle_ps_config = WMI_PDEV_PARAM_UNSUPPORTED, .power_gating_sleep = WMI_PDEV_PARAM_UNSUPPORTED, .fast_channel_reset = WMI_10X_PDEV_PARAM_FAST_CHANNEL_RESET, .burst_dur = WMI_10X_PDEV_PARAM_BURST_DUR, .burst_enable = WMI_10X_PDEV_PARAM_BURST_ENABLE, .cal_period = WMI_10X_PDEV_PARAM_CAL_PERIOD, .aggr_burst = WMI_PDEV_PARAM_UNSUPPORTED, .rx_decap_mode = WMI_PDEV_PARAM_UNSUPPORTED, .smart_antenna_default_antenna = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_override = WMI_PDEV_PARAM_UNSUPPORTED, .igmpmld_tid = WMI_PDEV_PARAM_UNSUPPORTED, .antenna_gain = WMI_PDEV_PARAM_UNSUPPORTED, .rx_filter = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_to_ucast_tid = WMI_PDEV_PARAM_UNSUPPORTED, .proxy_sta_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_mode = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .remove_mcast2ucast_buffer = WMI_PDEV_PARAM_UNSUPPORTED, .peer_sta_ps_statechg_enable = WMI_10X_PDEV_PARAM_PEER_STA_PS_STATECHG_ENABLE, .igmpmld_ac_override = WMI_PDEV_PARAM_UNSUPPORTED, .block_interbss = WMI_PDEV_PARAM_UNSUPPORTED, .set_disable_reset_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_msdu_ttl_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_ppdu_duration_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .txbf_sound_period_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_promisc_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .set_burst_mode_cmdid = WMI_PDEV_PARAM_UNSUPPORTED, .en_stats = WMI_PDEV_PARAM_UNSUPPORTED, .mu_group_policy = WMI_PDEV_PARAM_UNSUPPORTED, .noise_detection = WMI_PDEV_PARAM_UNSUPPORTED, .noise_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .dpd_enable = WMI_PDEV_PARAM_UNSUPPORTED, .set_mcast_bcast_echo = WMI_PDEV_PARAM_UNSUPPORTED, .atf_strict_sch = WMI_PDEV_PARAM_UNSUPPORTED, .atf_sched_duration = WMI_PDEV_PARAM_UNSUPPORTED, .ant_plzn = WMI_PDEV_PARAM_UNSUPPORTED, .mgmt_retry_limit = WMI_PDEV_PARAM_UNSUPPORTED, .sensitivity_level = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_2g = WMI_PDEV_PARAM_UNSUPPORTED, .signed_txpower_5g = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_amsdu = WMI_PDEV_PARAM_UNSUPPORTED, .enable_per_tid_ampdu = WMI_PDEV_PARAM_UNSUPPORTED, .cca_threshold = WMI_PDEV_PARAM_UNSUPPORTED, .rts_fixed_rate = WMI_PDEV_PARAM_UNSUPPORTED, .pdev_reset = WMI_10X_PDEV_PARAM_PDEV_RESET, .wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED, .arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED, .arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED, .enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED, }; /* firmware 10.2 specific mappings */ static struct wmi_cmd_map wmi_10_2_cmd_map = { .init_cmdid = WMI_10_2_INIT_CMDID, .start_scan_cmdid = WMI_10_2_START_SCAN_CMDID, .stop_scan_cmdid = WMI_10_2_STOP_SCAN_CMDID, .scan_chan_list_cmdid = WMI_10_2_SCAN_CHAN_LIST_CMDID, .scan_sch_prio_tbl_cmdid = WMI_CMD_UNSUPPORTED, .scan_prob_req_oui_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_regdomain_cmdid = WMI_10_2_PDEV_SET_REGDOMAIN_CMDID, .pdev_set_channel_cmdid = WMI_10_2_PDEV_SET_CHANNEL_CMDID, .pdev_set_param_cmdid = WMI_10_2_PDEV_SET_PARAM_CMDID, .pdev_pktlog_enable_cmdid = WMI_10_2_PDEV_PKTLOG_ENABLE_CMDID, .pdev_pktlog_disable_cmdid = WMI_10_2_PDEV_PKTLOG_DISABLE_CMDID, .pdev_set_wmm_params_cmdid = WMI_10_2_PDEV_SET_WMM_PARAMS_CMDID, .pdev_set_ht_cap_ie_cmdid = WMI_10_2_PDEV_SET_HT_CAP_IE_CMDID, .pdev_set_vht_cap_ie_cmdid = WMI_10_2_PDEV_SET_VHT_CAP_IE_CMDID, .pdev_set_quiet_mode_cmdid = WMI_10_2_PDEV_SET_QUIET_MODE_CMDID, .pdev_green_ap_ps_enable_cmdid = WMI_10_2_PDEV_GREEN_AP_PS_ENABLE_CMDID, .pdev_get_tpc_config_cmdid = WMI_10_2_PDEV_GET_TPC_CONFIG_CMDID, .pdev_set_base_macaddr_cmdid = WMI_10_2_PDEV_SET_BASE_MACADDR_CMDID, .vdev_create_cmdid = WMI_10_2_VDEV_CREATE_CMDID, .vdev_delete_cmdid = WMI_10_2_VDEV_DELETE_CMDID, .vdev_start_request_cmdid = WMI_10_2_VDEV_START_REQUEST_CMDID, .vdev_restart_request_cmdid = WMI_10_2_VDEV_RESTART_REQUEST_CMDID, .vdev_up_cmdid = WMI_10_2_VDEV_UP_CMDID, .vdev_stop_cmdid = WMI_10_2_VDEV_STOP_CMDID, .vdev_down_cmdid = WMI_10_2_VDEV_DOWN_CMDID, .vdev_set_param_cmdid = WMI_10_2_VDEV_SET_PARAM_CMDID, .vdev_install_key_cmdid = WMI_10_2_VDEV_INSTALL_KEY_CMDID, .peer_create_cmdid = WMI_10_2_PEER_CREATE_CMDID, .peer_delete_cmdid = WMI_10_2_PEER_DELETE_CMDID, .peer_flush_tids_cmdid = WMI_10_2_PEER_FLUSH_TIDS_CMDID, .peer_set_param_cmdid = WMI_10_2_PEER_SET_PARAM_CMDID, .peer_assoc_cmdid = WMI_10_2_PEER_ASSOC_CMDID, .peer_add_wds_entry_cmdid = WMI_10_2_PEER_ADD_WDS_ENTRY_CMDID, .peer_remove_wds_entry_cmdid = WMI_10_2_PEER_REMOVE_WDS_ENTRY_CMDID, .peer_mcast_group_cmdid = WMI_10_2_PEER_MCAST_GROUP_CMDID, .bcn_tx_cmdid = WMI_10_2_BCN_TX_CMDID, .pdev_send_bcn_cmdid = WMI_10_2_PDEV_SEND_BCN_CMDID, .bcn_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .bcn_filter_rx_cmdid = WMI_10_2_BCN_FILTER_RX_CMDID, .prb_req_filter_rx_cmdid = WMI_10_2_PRB_REQ_FILTER_RX_CMDID, .mgmt_tx_cmdid = WMI_10_2_MGMT_TX_CMDID, .prb_tmpl_cmdid = WMI_CMD_UNSUPPORTED, .addba_clear_resp_cmdid = WMI_10_2_ADDBA_CLEAR_RESP_CMDID, .addba_send_cmdid = WMI_10_2_ADDBA_SEND_CMDID, .addba_status_cmdid = WMI_10_2_ADDBA_STATUS_CMDID, .delba_send_cmdid = WMI_10_2_DELBA_SEND_CMDID, .addba_set_resp_cmdid = WMI_10_2_ADDBA_SET_RESP_CMDID, .send_singleamsdu_cmdid = WMI_10_2_SEND_SINGLEAMSDU_CMDID, .sta_powersave_mode_cmdid = WMI_10_2_STA_POWERSAVE_MODE_CMDID, .sta_powersave_param_cmdid = WMI_10_2_STA_POWERSAVE_PARAM_CMDID, .sta_mimo_ps_mode_cmdid = WMI_10_2_STA_MIMO_PS_MODE_CMDID, .pdev_dfs_enable_cmdid = WMI_10_2_PDEV_DFS_ENABLE_CMDID, .pdev_dfs_disable_cmdid = WMI_10_2_PDEV_DFS_DISABLE_CMDID, .roam_scan_mode = WMI_10_2_ROAM_SCAN_MODE, .roam_scan_rssi_threshold = WMI_10_2_ROAM_SCAN_RSSI_THRESHOLD, .roam_scan_period = WMI_10_2_ROAM_SCAN_PERIOD, .roam_scan_rssi_change_threshold = WMI_10_2_ROAM_SCAN_RSSI_CHANGE_THRESHOLD, .roam_ap_profile = WMI_10_2_ROAM_AP_PROFILE, .ofl_scan_add_ap_profile = WMI_10_2_OFL_SCAN_ADD_AP_PROFILE, .ofl_scan_remove_ap_profile = WMI_10_2_OFL_SCAN_REMOVE_AP_PROFILE, .ofl_scan_period = WMI_10_2_OFL_SCAN_PERIOD, .p2p_dev_set_device_info = WMI_10_2_P2P_DEV_SET_DEVICE_INFO, .p2p_dev_set_discoverability = WMI_10_2_P2P_DEV_SET_DISCOVERABILITY, .p2p_go_set_beacon_ie = WMI_10_2_P2P_GO_SET_BEACON_IE, .p2p_go_set_probe_resp_ie = WMI_10_2_P2P_GO_SET_PROBE_RESP_IE, .p2p_set_vendor_ie_data_cmdid = WMI_CMD_UNSUPPORTED, .ap_ps_peer_param_cmdid = WMI_10_2_AP_PS_PEER_PARAM_CMDID, .ap_ps_peer_uapsd_coex_cmdid = WMI_CMD_UNSUPPORTED, .peer_rate_retry_sched_cmdid = WMI_10_2_PEER_RATE_RETRY_SCHED_CMDID, .wlan_profile_trigger_cmdid = WMI_10_2_WLAN_PROFILE_TRIGGER_CMDID, .wlan_profile_set_hist_intvl_cmdid = WMI_10_2_WLAN_PROFILE_SET_HIST_INTVL_CMDID, .wlan_profile_get_profile_data_cmdid = WMI_10_2_WLAN_PROFILE_GET_PROFILE_DATA_CMDID, .wlan_profile_enable_profile_id_cmdid = WMI_10_2_WLAN_PROFILE_ENABLE_PROFILE_ID_CMDID, .wlan_profile_list_profile_id_cmdid = WMI_10_2_WLAN_PROFILE_LIST_PROFILE_ID_CMDID, .pdev_suspend_cmdid = WMI_10_2_PDEV_SUSPEND_CMDID, .pdev_resume_cmdid = WMI_10_2_PDEV_RESUME_CMDID, .add_bcn_filter_cmdid = WMI_10_2_ADD_BCN_FILTER_CMDID, .rmv_bcn_filter_cmdid = WMI_10_2_RMV_BCN_FILTER_CMDID, .wow_add_wake_pattern_cmdid = WMI_10_2_WOW_ADD_WAKE_PATTERN_CMDID, .wow_del_wake_pattern_cmdid = WMI_10_2_WOW_DEL_WAKE_PATTERN_CMDID, .wow_enable_disable_wake_event_cmdid = WMI_10_2_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID, .wow_enable_cmdid = WMI_10_2_WOW_ENABLE_CMDID, .wow_hostwakeup_from_sleep_cmdid = WMI_10_2_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID, .rtt_measreq_cmdid = WMI_10_2_RTT_MEASREQ_CMDID, .rtt_tsf_cmdid = WMI_10_2_RTT_TSF_CMDID, .vdev_spectral_scan_configure_cmdid = WMI_10_2_VDEV_SPECTRAL_SCAN_CONFIGURE_CMDID, .vdev_spectral_scan_enable_cmdid = WMI_10_2_VDEV_SPECTRAL_SCAN_ENABLE_CMDID, .request_stats_cmdid = WMI_10_2_REQUEST_STATS_CMDID, .set_arp_ns_offload_cmdid = WMI_CMD_UNSUPPORTED, .network_list_offload_config_cmdid = WMI_CMD_UNSUPPORTED, .gtk_offload_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_enable_cmdid = WMI_CMD_UNSUPPORTED, .csa_offload_chanswitch_cmdid = WMI_CMD_UNSUPPORTED, .chatter_set_mode_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_addba_cmdid = WMI_CMD_UNSUPPORTED, .peer_tid_delba_cmdid = WMI_CMD_UNSUPPORTED, .sta_dtim_ps_method_cmdid = WMI_CMD_UNSUPPORTED, .sta_uapsd_auto_trig_cmdid = WMI_CMD_UNSUPPORTED, .sta_keepalive_cmd = WMI_CMD_UNSUPPORTED, .echo_cmdid = WMI_10_2_ECHO_CMDID, .pdev_utf_cmdid = WMI_10_2_PDEV_UTF_CMDID, .dbglog_cfg_cmdid = WMI_10_2_DBGLOG_CFG_CMDID, .pdev_qvit_cmdid = WMI_10_2_PDEV_QVIT_CMDID, .pdev_ftm_intg_cmdid = WMI_CMD_UNSUPPORTED, .vdev_set_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .vdev_get_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .force_fw_hang_cmdid = WMI_CMD_UNSUPPORTED, .gpio_config_cmdid = WMI_10_2_GPIO_CONFIG_CMDID, .gpio_output_cmdid = WMI_10_2_GPIO_OUTPUT_CMDID, .pdev_get_temperature_cmdid = WMI_CMD_UNSUPPORTED, .pdev_enable_adaptive_cca_cmdid = WMI_CMD_UNSUPPORTED, .scan_update_request_cmdid = WMI_CMD_UNSUPPORTED, .vdev_standby_response_cmdid = WMI_CMD_UNSUPPORTED, .vdev_resume_response_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_add_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_evict_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_restore_peer_cmdid = WMI_CMD_UNSUPPORTED, .wlan_peer_caching_print_all_peers_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_update_wds_entry_cmdid = WMI_CMD_UNSUPPORTED, .peer_add_proxy_sta_entry_cmdid = WMI_CMD_UNSUPPORTED, .rtt_keepalive_cmdid = WMI_CMD_UNSUPPORTED, .oem_req_cmdid = WMI_CMD_UNSUPPORTED, .nan_cmdid = WMI_CMD_UNSUPPORTED, .vdev_ratemask_cmdid = WMI_CMD_UNSUPPORTED, .qboost_cfg_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_enable_cmdid = WMI_CMD_UNSUPPORTED, .pdev_smart_ant_set_rx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_tx_antenna_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_train_info_cmdid = WMI_CMD_UNSUPPORTED, .peer_smart_ant_set_node_config_ops_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_antenna_switch_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_ctl_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_set_mimogain_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_ratepwr_chainmsk_table_cmdid = WMI_CMD_UNSUPPORTED, .pdev_fips_cmdid = WMI_CMD_UNSUPPORTED, .tt_set_conf_cmdid = WMI_CMD_UNSUPPORTED, .fwtest_cmdid = WMI_CMD_UNSUPPORTED, .vdev_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .peer_atf_request_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_cck_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_ani_ofdm_config_cmdid = WMI_CMD_UNSUPPORTED, .pdev_reserve_ast_entry_cmdid = WMI_CMD_UNSUPPORTED, .pdev_get_tpc_table_cmdid = WMI_CMD_UNSUPPORTED, .radar_found_cmdid = WMI_CMD_UNSUPPORTED, }; static struct wmi_pdev_param_map wmi_10_4_pdev_param_map = { .tx_chain_mask = WMI_10_4_PDEV_PARAM_TX_CHAIN_MASK, .rx_chain_mask = WMI_10_4_PDEV_PARAM_RX_CHAIN_MASK, .txpower_limit2g = WMI_10_4_PDEV_PARAM_TXPOWER_LIMIT2G, .txpower_limit5g = WMI_10_4_PDEV_PARAM_TXPOWER_LIMIT5G, .txpower_scale = WMI_10_4_PDEV_PARAM_TXPOWER_SCALE, .beacon_gen_mode = WMI_10_4_PDEV_PARAM_BEACON_GEN_MODE, .beacon_tx_mode = WMI_10_4_PDEV_PARAM_BEACON_TX_MODE, .resmgr_offchan_mode = WMI_10_4_PDEV_PARAM_RESMGR_OFFCHAN_MODE, .protection_mode = WMI_10_4_PDEV_PARAM_PROTECTION_MODE, .dynamic_bw = WMI_10_4_PDEV_PARAM_DYNAMIC_BW, .non_agg_sw_retry_th = WMI_10_4_PDEV_PARAM_NON_AGG_SW_RETRY_TH, .agg_sw_retry_th = WMI_10_4_PDEV_PARAM_AGG_SW_RETRY_TH, .sta_kickout_th = WMI_10_4_PDEV_PARAM_STA_KICKOUT_TH, .ac_aggrsize_scaling = WMI_10_4_PDEV_PARAM_AC_AGGRSIZE_SCALING, .ltr_enable = WMI_10_4_PDEV_PARAM_LTR_ENABLE, .ltr_ac_latency_be = WMI_10_4_PDEV_PARAM_LTR_AC_LATENCY_BE, .ltr_ac_latency_bk = WMI_10_4_PDEV_PARAM_LTR_AC_LATENCY_BK, .ltr_ac_latency_vi = WMI_10_4_PDEV_PARAM_LTR_AC_LATENCY_VI, .ltr_ac_latency_vo = WMI_10_4_PDEV_PARAM_LTR_AC_LATENCY_VO, .ltr_ac_latency_timeout = WMI_10_4_PDEV_PARAM_LTR_AC_LATENCY_TIMEOUT, .ltr_sleep_override = WMI_10_4_PDEV_PARAM_LTR_SLEEP_OVERRIDE, .ltr_rx_override = WMI_10_4_PDEV_PARAM_LTR_RX_OVERRIDE, .ltr_tx_activity_timeout = WMI_10_4_PDEV_PARAM_LTR_TX_ACTIVITY_TIMEOUT, .l1ss_enable = WMI_10_4_PDEV_PARAM_L1SS_ENABLE, .dsleep_enable = WMI_10_4_PDEV_PARAM_DSLEEP_ENABLE, .pcielp_txbuf_flush = WMI_10_4_PDEV_PARAM_PCIELP_TXBUF_FLUSH, .pcielp_txbuf_watermark = WMI_10_4_PDEV_PARAM_PCIELP_TXBUF_WATERMARK, .pcielp_txbuf_tmo_en = WMI_10_4_PDEV_PARAM_PCIELP_TXBUF_TMO_EN, .pcielp_txbuf_tmo_value = WMI_10_4_PDEV_PARAM_PCIELP_TXBUF_TMO_VALUE, .pdev_stats_update_period = WMI_10_4_PDEV_PARAM_PDEV_STATS_UPDATE_PERIOD, .vdev_stats_update_period = WMI_10_4_PDEV_PARAM_VDEV_STATS_UPDATE_PERIOD, .peer_stats_update_period = WMI_10_4_PDEV_PARAM_PEER_STATS_UPDATE_PERIOD, .bcnflt_stats_update_period = WMI_10_4_PDEV_PARAM_BCNFLT_STATS_UPDATE_PERIOD, .pmf_qos = WMI_10_4_PDEV_PARAM_PMF_QOS, .arp_ac_override = WMI_10_4_PDEV_PARAM_ARP_AC_OVERRIDE, .dcs = WMI_10_4_PDEV_PARAM_DCS, .ani_enable = WMI_10_4_PDEV_PARAM_ANI_ENABLE, .ani_poll_period = WMI_10_4_PDEV_PARAM_ANI_POLL_PERIOD, .ani_listen_period = WMI_10_4_PDEV_PARAM_ANI_LISTEN_PERIOD, .ani_ofdm_level = WMI_10_4_PDEV_PARAM_ANI_OFDM_LEVEL, .ani_cck_level = WMI_10_4_PDEV_PARAM_ANI_CCK_LEVEL, .dyntxchain = WMI_10_4_PDEV_PARAM_DYNTXCHAIN, .proxy_sta = WMI_10_4_PDEV_PARAM_PROXY_STA, .idle_ps_config = WMI_10_4_PDEV_PARAM_IDLE_PS_CONFIG, .power_gating_sleep = WMI_10_4_PDEV_PARAM_POWER_GATING_SLEEP, .fast_channel_reset = WMI_10_4_PDEV_PARAM_FAST_CHANNEL_RESET, .burst_dur = WMI_10_4_PDEV_PARAM_BURST_DUR, .burst_enable = WMI_10_4_PDEV_PARAM_BURST_ENABLE, .cal_period = WMI_10_4_PDEV_PARAM_CAL_PERIOD, .aggr_burst = WMI_10_4_PDEV_PARAM_AGGR_BURST, .rx_decap_mode = WMI_10_4_PDEV_PARAM_RX_DECAP_MODE, .smart_antenna_default_antenna = WMI_10_4_PDEV_PARAM_SMART_ANTENNA_DEFAULT_ANTENNA, .igmpmld_override = WMI_10_4_PDEV_PARAM_IGMPMLD_OVERRIDE, .igmpmld_tid = WMI_10_4_PDEV_PARAM_IGMPMLD_TID, .antenna_gain = WMI_10_4_PDEV_PARAM_ANTENNA_GAIN, .rx_filter = WMI_10_4_PDEV_PARAM_RX_FILTER, .set_mcast_to_ucast_tid = WMI_10_4_PDEV_SET_MCAST_TO_UCAST_TID, .proxy_sta_mode = WMI_10_4_PDEV_PARAM_PROXY_STA_MODE, .set_mcast2ucast_mode = WMI_10_4_PDEV_PARAM_SET_MCAST2UCAST_MODE, .set_mcast2ucast_buffer = WMI_10_4_PDEV_PARAM_SET_MCAST2UCAST_BUFFER, .remove_mcast2ucast_buffer = WMI_10_4_PDEV_PARAM_REMOVE_MCAST2UCAST_BUFFER, .peer_sta_ps_statechg_enable = WMI_10_4_PDEV_PEER_STA_PS_STATECHG_ENABLE, .igmpmld_ac_override = WMI_10_4_PDEV_PARAM_IGMPMLD_AC_OVERRIDE, .block_interbss = WMI_10_4_PDEV_PARAM_BLOCK_INTERBSS, .set_disable_reset_cmdid = WMI_10_4_PDEV_PARAM_SET_DISABLE_RESET_CMDID, .set_msdu_ttl_cmdid = WMI_10_4_PDEV_PARAM_SET_MSDU_TTL_CMDID, .set_ppdu_duration_cmdid = WMI_10_4_PDEV_PARAM_SET_PPDU_DURATION_CMDID, .txbf_sound_period_cmdid = WMI_10_4_PDEV_PARAM_TXBF_SOUND_PERIOD_CMDID, .set_promisc_mode_cmdid = WMI_10_4_PDEV_PARAM_SET_PROMISC_MODE_CMDID, .set_burst_mode_cmdid = WMI_10_4_PDEV_PARAM_SET_BURST_MODE_CMDID, .en_stats = WMI_10_4_PDEV_PARAM_EN_STATS, .mu_group_policy = WMI_10_4_PDEV_PARAM_MU_GROUP_POLICY, .noise_detection = WMI_10_4_PDEV_PARAM_NOISE_DETECTION, .noise_threshold = WMI_10_4_PDEV_PARAM_NOISE_THRESHOLD, .dpd_enable = WMI_10_4_PDEV_PARAM_DPD_ENABLE, .set_mcast_bcast_echo = WMI_10_4_PDEV_PARAM_SET_MCAST_BCAST_ECHO, .atf_strict_sch = WMI_10_4_PDEV_PARAM_ATF_STRICT_SCH, .atf_sched_duration = WMI_10_4_PDEV_PARAM_ATF_SCHED_DURATION, .ant_plzn = WMI_10_4_PDEV_PARAM_ANT_PLZN, .mgmt_retry_limit = WMI_10_4_PDEV_PARAM_MGMT_RETRY_LIMIT, .sensitivity_level = WMI_10_4_PDEV_PARAM_SENSITIVITY_LEVEL, .signed_txpower_2g = WMI_10_4_PDEV_PARAM_SIGNED_TXPOWER_2G, .signed_txpower_5g = WMI_10_4_PDEV_PARAM_SIGNED_TXPOWER_5G, .enable_per_tid_amsdu = WMI_10_4_PDEV_PARAM_ENABLE_PER_TID_AMSDU, .enable_per_tid_ampdu = WMI_10_4_PDEV_PARAM_ENABLE_PER_TID_AMPDU, .cca_threshold = WMI_10_4_PDEV_PARAM_CCA_THRESHOLD, .rts_fixed_rate = WMI_10_4_PDEV_PARAM_RTS_FIXED_RATE, .pdev_reset = WMI_10_4_PDEV_PARAM_PDEV_RESET, .wapi_mbssid_offset = WMI_10_4_PDEV_PARAM_WAPI_MBSSID_OFFSET, .arp_srcaddr = WMI_10_4_PDEV_PARAM_ARP_SRCADDR, .arp_dstaddr = WMI_10_4_PDEV_PARAM_ARP_DSTADDR, .enable_btcoex = WMI_10_4_PDEV_PARAM_ENABLE_BTCOEX, }; static const u8 wmi_key_cipher_suites[] = { [WMI_CIPHER_NONE] = WMI_CIPHER_NONE, [WMI_CIPHER_WEP] = WMI_CIPHER_WEP, [WMI_CIPHER_TKIP] = WMI_CIPHER_TKIP, [WMI_CIPHER_AES_OCB] = WMI_CIPHER_AES_OCB, [WMI_CIPHER_AES_CCM] = WMI_CIPHER_AES_CCM, [WMI_CIPHER_WAPI] = WMI_CIPHER_WAPI, [WMI_CIPHER_CKIP] = WMI_CIPHER_CKIP, [WMI_CIPHER_AES_CMAC] = WMI_CIPHER_AES_CMAC, [WMI_CIPHER_AES_GCM] = WMI_CIPHER_AES_GCM, }; static const u8 wmi_tlv_key_cipher_suites[] = { [WMI_CIPHER_NONE] = WMI_TLV_CIPHER_NONE, [WMI_CIPHER_WEP] = WMI_TLV_CIPHER_WEP, [WMI_CIPHER_TKIP] = WMI_TLV_CIPHER_TKIP, [WMI_CIPHER_AES_OCB] = WMI_TLV_CIPHER_AES_OCB, [WMI_CIPHER_AES_CCM] = WMI_TLV_CIPHER_AES_CCM, [WMI_CIPHER_WAPI] = WMI_TLV_CIPHER_WAPI, [WMI_CIPHER_CKIP] = WMI_TLV_CIPHER_CKIP, [WMI_CIPHER_AES_CMAC] = WMI_TLV_CIPHER_AES_CMAC, [WMI_CIPHER_AES_GCM] = WMI_TLV_CIPHER_AES_GCM, }; static const struct wmi_peer_flags_map wmi_peer_flags_map = { .auth = WMI_PEER_AUTH, .qos = WMI_PEER_QOS, .need_ptk_4_way = WMI_PEER_NEED_PTK_4_WAY, .need_gtk_2_way = WMI_PEER_NEED_GTK_2_WAY, .apsd = WMI_PEER_APSD, .ht = WMI_PEER_HT, .bw40 = WMI_PEER_40MHZ, .stbc = WMI_PEER_STBC, .ldbc = WMI_PEER_LDPC, .dyn_mimops = WMI_PEER_DYN_MIMOPS, .static_mimops = WMI_PEER_STATIC_MIMOPS, .spatial_mux = WMI_PEER_SPATIAL_MUX, .vht = WMI_PEER_VHT, .bw80 = WMI_PEER_80MHZ, .vht_2g = WMI_PEER_VHT_2G, .pmf = WMI_PEER_PMF, .bw160 = WMI_PEER_160MHZ, }; static const struct wmi_peer_flags_map wmi_10x_peer_flags_map = { .auth = WMI_10X_PEER_AUTH, .qos = WMI_10X_PEER_QOS, .need_ptk_4_way = WMI_10X_PEER_NEED_PTK_4_WAY, .need_gtk_2_way = WMI_10X_PEER_NEED_GTK_2_WAY, .apsd = WMI_10X_PEER_APSD, .ht = WMI_10X_PEER_HT, .bw40 = WMI_10X_PEER_40MHZ, .stbc = WMI_10X_PEER_STBC, .ldbc = WMI_10X_PEER_LDPC, .dyn_mimops = WMI_10X_PEER_DYN_MIMOPS, .static_mimops = WMI_10X_PEER_STATIC_MIMOPS, .spatial_mux = WMI_10X_PEER_SPATIAL_MUX, .vht = WMI_10X_PEER_VHT, .bw80 = WMI_10X_PEER_80MHZ, .bw160 = WMI_10X_PEER_160MHZ, }; static const struct wmi_peer_flags_map wmi_10_2_peer_flags_map = { .auth = WMI_10_2_PEER_AUTH, .qos = WMI_10_2_PEER_QOS, .need_ptk_4_way = WMI_10_2_PEER_NEED_PTK_4_WAY, .need_gtk_2_way = WMI_10_2_PEER_NEED_GTK_2_WAY, .apsd = WMI_10_2_PEER_APSD, .ht = WMI_10_2_PEER_HT, .bw40 = WMI_10_2_PEER_40MHZ, .stbc = WMI_10_2_PEER_STBC, .ldbc = WMI_10_2_PEER_LDPC, .dyn_mimops = WMI_10_2_PEER_DYN_MIMOPS, .static_mimops = WMI_10_2_PEER_STATIC_MIMOPS, .spatial_mux = WMI_10_2_PEER_SPATIAL_MUX, .vht = WMI_10_2_PEER_VHT, .bw80 = WMI_10_2_PEER_80MHZ, .vht_2g = WMI_10_2_PEER_VHT_2G, .pmf = WMI_10_2_PEER_PMF, .bw160 = WMI_10_2_PEER_160MHZ, }; void ath10k_wmi_put_wmi_channel(struct ath10k *ar, struct wmi_channel *ch, const struct wmi_channel_arg *arg) { u32 flags = 0; struct ieee80211_channel *chan = NULL; memset(ch, 0, sizeof(*ch)); if (arg->passive) flags |= WMI_CHAN_FLAG_PASSIVE; if (arg->allow_ibss) flags |= WMI_CHAN_FLAG_ADHOC_ALLOWED; if (arg->allow_ht) flags |= WMI_CHAN_FLAG_ALLOW_HT; if (arg->allow_vht) flags |= WMI_CHAN_FLAG_ALLOW_VHT; if (arg->ht40plus) flags |= WMI_CHAN_FLAG_HT40_PLUS; if (arg->chan_radar) flags |= WMI_CHAN_FLAG_DFS; ch->band_center_freq2 = 0; ch->mhz = __cpu_to_le32(arg->freq); ch->band_center_freq1 = __cpu_to_le32(arg->band_center_freq1); if (arg->mode == MODE_11AC_VHT80_80) { ch->band_center_freq2 = __cpu_to_le32(arg->band_center_freq2); chan = ieee80211_get_channel(ar->hw->wiphy, arg->band_center_freq2 - 10); } if (arg->mode == MODE_11AC_VHT160) { u32 band_center_freq1; u32 band_center_freq2; if (arg->freq > arg->band_center_freq1) { band_center_freq1 = arg->band_center_freq1 + 40; band_center_freq2 = arg->band_center_freq1 - 40; } else { band_center_freq1 = arg->band_center_freq1 - 40; band_center_freq2 = arg->band_center_freq1 + 40; } ch->band_center_freq1 = __cpu_to_le32(band_center_freq1); /* Minus 10 to get a defined 5G channel frequency*/ chan = ieee80211_get_channel(ar->hw->wiphy, band_center_freq2 - 10); /* The center frequency of the entire VHT160 */ ch->band_center_freq2 = __cpu_to_le32(arg->band_center_freq1); } if (chan && chan->flags & IEEE80211_CHAN_RADAR) flags |= WMI_CHAN_FLAG_DFS_CFREQ2; ch->min_power = arg->min_power; ch->max_power = arg->max_power; ch->reg_power = arg->max_reg_power; ch->antenna_max = arg->max_antenna_gain; ch->max_tx_power = arg->max_power; /* mode & flags share storage */ ch->mode = arg->mode; ch->flags |= __cpu_to_le32(flags); } int ath10k_wmi_wait_for_service_ready(struct ath10k *ar) { unsigned long time_left, i; time_left = wait_for_completion_timeout(&ar->wmi.service_ready, WMI_SERVICE_READY_TIMEOUT_HZ); if (!time_left) { /* Sometimes the PCI HIF doesn't receive interrupt * for the service ready message even if the buffer * was completed. PCIe sniffer shows that it's * because the corresponding CE ring doesn't fires * it. Workaround here by polling CE rings once. */ ath10k_warn(ar, "failed to receive service ready completion, polling..\n"); for (i = 0; i < CE_COUNT; i++) ath10k_hif_send_complete_check(ar, i, 1); time_left = wait_for_completion_timeout(&ar->wmi.service_ready, WMI_SERVICE_READY_TIMEOUT_HZ); if (!time_left) { ath10k_warn(ar, "polling timed out\n"); return -ETIMEDOUT; } ath10k_warn(ar, "service ready completion received, continuing normally\n"); } return 0; } int ath10k_wmi_wait_for_unified_ready(struct ath10k *ar) { unsigned long time_left; time_left = wait_for_completion_timeout(&ar->wmi.unified_ready, WMI_UNIFIED_READY_TIMEOUT_HZ); if (!time_left) return -ETIMEDOUT; return 0; } struct sk_buff *ath10k_wmi_alloc_skb(struct ath10k *ar, u32 len) { struct sk_buff *skb; u32 round_len = roundup(len, 4); skb = ath10k_htc_alloc_skb(ar, WMI_SKB_HEADROOM + round_len); if (!skb) return NULL; skb_reserve(skb, WMI_SKB_HEADROOM); if (!IS_ALIGNED((unsigned long)skb->data, 4)) ath10k_warn(ar, "Unaligned WMI skb\n"); skb_put(skb, round_len); memset(skb->data, 0, round_len); return skb; } static void ath10k_wmi_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb) { dev_kfree_skb(skb); } int ath10k_wmi_cmd_send_nowait(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id) { struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(skb); struct wmi_cmd_hdr *cmd_hdr; int ret; u32 cmd = 0; if (skb_push(skb, sizeof(struct wmi_cmd_hdr)) == NULL) return -ENOMEM; cmd |= SM(cmd_id, WMI_CMD_HDR_CMD_ID); cmd_hdr = (struct wmi_cmd_hdr *)skb->data; cmd_hdr->cmd_id = __cpu_to_le32(cmd); memset(skb_cb, 0, sizeof(*skb_cb)); trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len); ret = ath10k_htc_send(&ar->htc, ar->wmi.eid, skb); if (ret) goto err_pull; return 0; err_pull: skb_pull(skb, sizeof(struct wmi_cmd_hdr)); return ret; } static void ath10k_wmi_tx_beacon_nowait(struct ath10k_vif *arvif) { struct ath10k *ar = arvif->ar; struct ath10k_skb_cb *cb; struct sk_buff *bcn; bool dtim_zero; bool deliver_cab; int ret; spin_lock_bh(&ar->data_lock); bcn = arvif->beacon; if (!bcn) goto unlock; cb = ATH10K_SKB_CB(bcn); switch (arvif->beacon_state) { case ATH10K_BEACON_SENDING: case ATH10K_BEACON_SENT: break; case ATH10K_BEACON_SCHEDULED: arvif->beacon_state = ATH10K_BEACON_SENDING; spin_unlock_bh(&ar->data_lock); dtim_zero = !!(cb->flags & ATH10K_SKB_F_DTIM_ZERO); deliver_cab = !!(cb->flags & ATH10K_SKB_F_DELIVER_CAB); ret = ath10k_wmi_beacon_send_ref_nowait(arvif->ar, arvif->vdev_id, bcn->data, bcn->len, cb->paddr, dtim_zero, deliver_cab); spin_lock_bh(&ar->data_lock); if (ret == 0) arvif->beacon_state = ATH10K_BEACON_SENT; else arvif->beacon_state = ATH10K_BEACON_SCHEDULED; } unlock: spin_unlock_bh(&ar->data_lock); } static void ath10k_wmi_tx_beacons_iter(void *data, u8 *mac, struct ieee80211_vif *vif) { struct ath10k_vif *arvif = (void *)vif->drv_priv; ath10k_wmi_tx_beacon_nowait(arvif); } static void ath10k_wmi_tx_beacons_nowait(struct ath10k *ar) { ieee80211_iterate_active_interfaces_atomic(ar->hw, ATH10K_ITER_NORMAL_FLAGS, ath10k_wmi_tx_beacons_iter, NULL); } static void ath10k_wmi_op_ep_tx_credits(struct ath10k *ar) { /* try to send pending beacons first. they take priority */ ath10k_wmi_tx_beacons_nowait(ar); wake_up(&ar->wmi.tx_credits_wq); } int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id) { int ret = -EOPNOTSUPP; might_sleep(); if (cmd_id == WMI_CMD_UNSUPPORTED) { ath10k_warn(ar, "wmi command %d is not supported by firmware\n", cmd_id); return ret; } wait_event_timeout(ar->wmi.tx_credits_wq, ({ /* try to send pending beacons first. they take priority */ ath10k_wmi_tx_beacons_nowait(ar); ret = ath10k_wmi_cmd_send_nowait(ar, skb, cmd_id); if (ret && test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) ret = -ESHUTDOWN; (ret != -EAGAIN); }), 3 * HZ); if (ret) dev_kfree_skb_any(skb); if (ret == -EAGAIN) { ath10k_warn(ar, "wmi command %d timeout, restarting hardware\n", cmd_id); ath10k_core_start_recovery(ar); } return ret; } static struct sk_buff * ath10k_wmi_op_gen_mgmt_tx(struct ath10k *ar, struct sk_buff *msdu) { struct ath10k_skb_cb *cb = ATH10K_SKB_CB(msdu); struct ath10k_vif *arvif; struct wmi_mgmt_tx_cmd *cmd; struct ieee80211_hdr *hdr; struct sk_buff *skb; int len; u32 vdev_id; u32 buf_len = msdu->len; u16 fc; const u8 *peer_addr; hdr = (struct ieee80211_hdr *)msdu->data; fc = le16_to_cpu(hdr->frame_control); if (cb->vif) { arvif = (void *)cb->vif->drv_priv; vdev_id = arvif->vdev_id; } else { vdev_id = 0; } if (WARN_ON_ONCE(!ieee80211_is_mgmt(hdr->frame_control))) return ERR_PTR(-EINVAL); len = sizeof(cmd->hdr) + msdu->len; if ((ieee80211_is_action(hdr->frame_control) || ieee80211_is_deauth(hdr->frame_control) || ieee80211_is_disassoc(hdr->frame_control)) && ieee80211_has_protected(hdr->frame_control)) { peer_addr = hdr->addr1; if (is_multicast_ether_addr(peer_addr)) { len += sizeof(struct ieee80211_mmie_16); buf_len += sizeof(struct ieee80211_mmie_16); } else { if (cb->ucast_cipher == WLAN_CIPHER_SUITE_GCMP || cb->ucast_cipher == WLAN_CIPHER_SUITE_GCMP_256) { len += IEEE80211_GCMP_MIC_LEN; buf_len += IEEE80211_GCMP_MIC_LEN; } else { len += IEEE80211_CCMP_MIC_LEN; buf_len += IEEE80211_CCMP_MIC_LEN; } } } len = round_up(len, 4); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_mgmt_tx_cmd *)skb->data; cmd->hdr.vdev_id = __cpu_to_le32(vdev_id); cmd->hdr.tx_rate = 0; cmd->hdr.tx_power = 0; cmd->hdr.buf_len = __cpu_to_le32(buf_len); ether_addr_copy(cmd->hdr.peer_macaddr.addr, ieee80211_get_DA(hdr)); memcpy(cmd->buf, msdu->data, msdu->len); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt tx skb %pK len %d ftype %02x stype %02x\n", msdu, skb->len, fc & IEEE80211_FCTL_FTYPE, fc & IEEE80211_FCTL_STYPE); trace_ath10k_tx_hdr(ar, skb->data, skb->len); trace_ath10k_tx_payload(ar, skb->data, skb->len); return skb; } static void ath10k_wmi_event_scan_started(struct ath10k *ar) { lockdep_assert_held(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: ath10k_warn(ar, "received scan started event in an invalid scan state: %s (%d)\n", ath10k_scan_state_str(ar->scan.state), ar->scan.state); break; case ATH10K_SCAN_STARTING: ar->scan.state = ATH10K_SCAN_RUNNING; if (ar->scan.is_roc) ieee80211_ready_on_channel(ar->hw); complete(&ar->scan.started); break; } } static void ath10k_wmi_event_scan_start_failed(struct ath10k *ar) { lockdep_assert_held(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: ath10k_warn(ar, "received scan start failed event in an invalid scan state: %s (%d)\n", ath10k_scan_state_str(ar->scan.state), ar->scan.state); break; case ATH10K_SCAN_STARTING: complete(&ar->scan.started); __ath10k_scan_finish(ar); break; } } static void ath10k_wmi_event_scan_completed(struct ath10k *ar) { lockdep_assert_held(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_STARTING: /* One suspected reason scan can be completed while starting is * if firmware fails to deliver all scan events to the host, * e.g. when transport pipe is full. This has been observed * with spectral scan phyerr events starving wmi transport * pipe. In such case the "scan completed" event should be (and * is) ignored by the host as it may be just firmware's scan * state machine recovering. */ ath10k_warn(ar, "received scan completed event in an invalid scan state: %s (%d)\n", ath10k_scan_state_str(ar->scan.state), ar->scan.state); break; case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: __ath10k_scan_finish(ar); break; } } static void ath10k_wmi_event_scan_bss_chan(struct ath10k *ar) { lockdep_assert_held(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_STARTING: ath10k_warn(ar, "received scan bss chan event in an invalid scan state: %s (%d)\n", ath10k_scan_state_str(ar->scan.state), ar->scan.state); break; case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: ar->scan_channel = NULL; break; } } static void ath10k_wmi_event_scan_foreign_chan(struct ath10k *ar, u32 freq) { lockdep_assert_held(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_STARTING: ath10k_warn(ar, "received scan foreign chan event in an invalid scan state: %s (%d)\n", ath10k_scan_state_str(ar->scan.state), ar->scan.state); break; case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: ar->scan_channel = ieee80211_get_channel(ar->hw->wiphy, freq); if (ar->scan.is_roc && ar->scan.roc_freq == freq) complete(&ar->scan.on_channel); break; } } static const char * ath10k_wmi_event_scan_type_str(enum wmi_scan_event_type type, enum wmi_scan_completion_reason reason) { switch (type) { case WMI_SCAN_EVENT_STARTED: return "started"; case WMI_SCAN_EVENT_COMPLETED: switch (reason) { case WMI_SCAN_REASON_COMPLETED: return "completed"; case WMI_SCAN_REASON_CANCELLED: return "completed [cancelled]"; case WMI_SCAN_REASON_PREEMPTED: return "completed [preempted]"; case WMI_SCAN_REASON_TIMEDOUT: return "completed [timedout]"; case WMI_SCAN_REASON_INTERNAL_FAILURE: return "completed [internal err]"; case WMI_SCAN_REASON_MAX: break; } return "completed [unknown]"; case WMI_SCAN_EVENT_BSS_CHANNEL: return "bss channel"; case WMI_SCAN_EVENT_FOREIGN_CHANNEL: return "foreign channel"; case WMI_SCAN_EVENT_DEQUEUED: return "dequeued"; case WMI_SCAN_EVENT_PREEMPTED: return "preempted"; case WMI_SCAN_EVENT_START_FAILED: return "start failed"; case WMI_SCAN_EVENT_RESTARTED: return "restarted"; case WMI_SCAN_EVENT_FOREIGN_CHANNEL_EXIT: return "foreign channel exit"; default: return "unknown"; } } static int ath10k_wmi_op_pull_scan_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_scan_ev_arg *arg) { struct wmi_scan_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->event_type = ev->event_type; arg->reason = ev->reason; arg->channel_freq = ev->channel_freq; arg->scan_req_id = ev->scan_req_id; arg->scan_id = ev->scan_id; arg->vdev_id = ev->vdev_id; return 0; } int ath10k_wmi_event_scan(struct ath10k *ar, struct sk_buff *skb) { struct wmi_scan_ev_arg arg = {}; enum wmi_scan_event_type event_type; enum wmi_scan_completion_reason reason; u32 freq; u32 req_id; u32 scan_id; u32 vdev_id; int ret; ret = ath10k_wmi_pull_scan(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse scan event: %d\n", ret); return ret; } event_type = __le32_to_cpu(arg.event_type); reason = __le32_to_cpu(arg.reason); freq = __le32_to_cpu(arg.channel_freq); req_id = __le32_to_cpu(arg.scan_req_id); scan_id = __le32_to_cpu(arg.scan_id); vdev_id = __le32_to_cpu(arg.vdev_id); spin_lock_bh(&ar->data_lock); ath10k_dbg(ar, ATH10K_DBG_WMI, "scan event %s type %d reason %d freq %d req_id %d scan_id %d vdev_id %d state %s (%d)\n", ath10k_wmi_event_scan_type_str(event_type, reason), event_type, reason, freq, req_id, scan_id, vdev_id, ath10k_scan_state_str(ar->scan.state), ar->scan.state); switch (event_type) { case WMI_SCAN_EVENT_STARTED: ath10k_wmi_event_scan_started(ar); break; case WMI_SCAN_EVENT_COMPLETED: ath10k_wmi_event_scan_completed(ar); break; case WMI_SCAN_EVENT_BSS_CHANNEL: ath10k_wmi_event_scan_bss_chan(ar); break; case WMI_SCAN_EVENT_FOREIGN_CHANNEL: ath10k_wmi_event_scan_foreign_chan(ar, freq); break; case WMI_SCAN_EVENT_START_FAILED: ath10k_warn(ar, "received scan start failure event\n"); ath10k_wmi_event_scan_start_failed(ar); break; case WMI_SCAN_EVENT_DEQUEUED: case WMI_SCAN_EVENT_PREEMPTED: case WMI_SCAN_EVENT_RESTARTED: case WMI_SCAN_EVENT_FOREIGN_CHANNEL_EXIT: default: break; } spin_unlock_bh(&ar->data_lock); return 0; } /* If keys are configured, HW decrypts all frames * with protected bit set. Mark such frames as decrypted. */ static void ath10k_wmi_handle_wep_reauth(struct ath10k *ar, struct sk_buff *skb, struct ieee80211_rx_status *status) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; unsigned int hdrlen; bool peer_key; u8 *addr, keyidx; if (!ieee80211_is_auth(hdr->frame_control) || !ieee80211_has_protected(hdr->frame_control)) return; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < (hdrlen + IEEE80211_WEP_IV_LEN)) return; keyidx = skb->data[hdrlen + (IEEE80211_WEP_IV_LEN - 1)] >> WEP_KEYID_SHIFT; addr = ieee80211_get_SA(hdr); spin_lock_bh(&ar->data_lock); peer_key = ath10k_mac_is_peer_wep_key_set(ar, addr, keyidx); spin_unlock_bh(&ar->data_lock); if (peer_key) { ath10k_dbg(ar, ATH10K_DBG_MAC, "mac wep key present for peer %pM\n", addr); status->flag |= RX_FLAG_DECRYPTED; } } static int ath10k_wmi_op_pull_mgmt_rx_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_mgmt_rx_ev_arg *arg) { struct wmi_mgmt_rx_event_v1 *ev_v1; struct wmi_mgmt_rx_event_v2 *ev_v2; struct wmi_mgmt_rx_hdr_v1 *ev_hdr; struct wmi_mgmt_rx_ext_info *ext_info; size_t pull_len; u32 msdu_len; u32 len; if (test_bit(ATH10K_FW_FEATURE_EXT_WMI_MGMT_RX, ar->running_fw->fw_file.fw_features)) { ev_v2 = (struct wmi_mgmt_rx_event_v2 *)skb->data; ev_hdr = &ev_v2->hdr.v1; pull_len = sizeof(*ev_v2); } else { ev_v1 = (struct wmi_mgmt_rx_event_v1 *)skb->data; ev_hdr = &ev_v1->hdr; pull_len = sizeof(*ev_v1); } if (skb->len < pull_len) return -EPROTO; skb_pull(skb, pull_len); arg->channel = ev_hdr->channel; arg->buf_len = ev_hdr->buf_len; arg->status = ev_hdr->status; arg->snr = ev_hdr->snr; arg->phy_mode = ev_hdr->phy_mode; arg->rate = ev_hdr->rate; msdu_len = __le32_to_cpu(arg->buf_len); if (skb->len < msdu_len) return -EPROTO; if (le32_to_cpu(arg->status) & WMI_RX_STATUS_EXT_INFO) { len = ALIGN(le32_to_cpu(arg->buf_len), 4); ext_info = (struct wmi_mgmt_rx_ext_info *)(skb->data + len); memcpy(&arg->ext_info, ext_info, sizeof(struct wmi_mgmt_rx_ext_info)); } /* the WMI buffer might've ended up being padded to 4 bytes due to HTC * trailer with credit update. Trim the excess garbage. */ skb_trim(skb, msdu_len); return 0; } static int ath10k_wmi_10_4_op_pull_mgmt_rx_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_mgmt_rx_ev_arg *arg) { struct wmi_10_4_mgmt_rx_event *ev; struct wmi_10_4_mgmt_rx_hdr *ev_hdr; size_t pull_len; u32 msdu_len; struct wmi_mgmt_rx_ext_info *ext_info; u32 len; ev = (struct wmi_10_4_mgmt_rx_event *)skb->data; ev_hdr = &ev->hdr; pull_len = sizeof(*ev); if (skb->len < pull_len) return -EPROTO; skb_pull(skb, pull_len); arg->channel = ev_hdr->channel; arg->buf_len = ev_hdr->buf_len; arg->status = ev_hdr->status; arg->snr = ev_hdr->snr; arg->phy_mode = ev_hdr->phy_mode; arg->rate = ev_hdr->rate; msdu_len = __le32_to_cpu(arg->buf_len); if (skb->len < msdu_len) return -EPROTO; if (le32_to_cpu(arg->status) & WMI_RX_STATUS_EXT_INFO) { len = ALIGN(le32_to_cpu(arg->buf_len), 4); ext_info = (struct wmi_mgmt_rx_ext_info *)(skb->data + len); memcpy(&arg->ext_info, ext_info, sizeof(struct wmi_mgmt_rx_ext_info)); } /* Make sure bytes added for padding are removed. */ skb_trim(skb, msdu_len); return 0; } static bool ath10k_wmi_rx_is_decrypted(struct ath10k *ar, struct ieee80211_hdr *hdr) { if (!ieee80211_has_protected(hdr->frame_control)) return false; /* FW delivers WEP Shared Auth frame with Protected Bit set and * encrypted payload. However in case of PMF it delivers decrypted * frames with Protected Bit set. */ if (ieee80211_is_auth(hdr->frame_control)) return false; /* qca99x0 based FW delivers broadcast or multicast management frames * (ex: group privacy action frames in mesh) as encrypted payload. */ if (is_multicast_ether_addr(ieee80211_get_DA(hdr)) && ar->hw_params.sw_decrypt_mcast_mgmt) return false; return true; } static int wmi_process_mgmt_tx_comp(struct ath10k *ar, struct mgmt_tx_compl_params *param) { struct ath10k_mgmt_tx_pkt_addr *pkt_addr; struct ath10k_wmi *wmi = &ar->wmi; struct ieee80211_tx_info *info; struct sk_buff *msdu; int ret; spin_lock_bh(&ar->data_lock); pkt_addr = idr_find(&wmi->mgmt_pending_tx, param->desc_id); if (!pkt_addr) { ath10k_warn(ar, "received mgmt tx completion for invalid msdu_id: %d\n", param->desc_id); ret = -ENOENT; goto out; } msdu = pkt_addr->vaddr; dma_unmap_single(ar->dev, pkt_addr->paddr, msdu->len, DMA_TO_DEVICE); info = IEEE80211_SKB_CB(msdu); kfree(pkt_addr); if (param->status) { info->flags &= ~IEEE80211_TX_STAT_ACK; } else { info->flags |= IEEE80211_TX_STAT_ACK; info->status.ack_signal = ATH10K_DEFAULT_NOISE_FLOOR + param->ack_rssi; info->status.flags |= IEEE80211_TX_STATUS_ACK_SIGNAL_VALID; } ieee80211_tx_status_irqsafe(ar->hw, msdu); ret = 0; out: idr_remove(&wmi->mgmt_pending_tx, param->desc_id); spin_unlock_bh(&ar->data_lock); return ret; } int ath10k_wmi_event_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb) { struct wmi_tlv_mgmt_tx_compl_ev_arg arg; struct mgmt_tx_compl_params param; int ret; ret = ath10k_wmi_pull_mgmt_tx_compl(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse mgmt comp event: %d\n", ret); return ret; } memset(&param, 0, sizeof(struct mgmt_tx_compl_params)); param.desc_id = __le32_to_cpu(arg.desc_id); param.status = __le32_to_cpu(arg.status); if (test_bit(WMI_SERVICE_TX_DATA_ACK_RSSI, ar->wmi.svc_map)) param.ack_rssi = __le32_to_cpu(arg.ack_rssi); wmi_process_mgmt_tx_comp(ar, &param); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tlv evnt mgmt tx completion\n"); return 0; } int ath10k_wmi_event_mgmt_tx_bundle_compl(struct ath10k *ar, struct sk_buff *skb) { struct wmi_tlv_mgmt_tx_bundle_compl_ev_arg arg; struct mgmt_tx_compl_params param; u32 num_reports; int i, ret; ret = ath10k_wmi_pull_mgmt_tx_bundle_compl(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse bundle mgmt compl event: %d\n", ret); return ret; } num_reports = __le32_to_cpu(arg.num_reports); for (i = 0; i < num_reports; i++) { memset(&param, 0, sizeof(struct mgmt_tx_compl_params)); param.desc_id = __le32_to_cpu(arg.desc_ids[i]); param.status = __le32_to_cpu(arg.desc_ids[i]); if (test_bit(WMI_SERVICE_TX_DATA_ACK_RSSI, ar->wmi.svc_map)) param.ack_rssi = __le32_to_cpu(arg.ack_rssi[i]); wmi_process_mgmt_tx_comp(ar, &param); } ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tlv event bundle mgmt tx completion\n"); return 0; } int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb) { struct wmi_mgmt_rx_ev_arg arg = {}; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr; struct ieee80211_supported_band *sband; u32 rx_status; u32 channel; u32 phy_mode; u32 snr, rssi; u32 rate; u16 fc; int ret, i; ret = ath10k_wmi_pull_mgmt_rx(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse mgmt rx event: %d\n", ret); dev_kfree_skb(skb); return ret; } channel = __le32_to_cpu(arg.channel); rx_status = __le32_to_cpu(arg.status); snr = __le32_to_cpu(arg.snr); phy_mode = __le32_to_cpu(arg.phy_mode); rate = __le32_to_cpu(arg.rate); memset(status, 0, sizeof(*status)); ath10k_dbg(ar, ATH10K_DBG_MGMT, "event mgmt rx status %08x\n", rx_status); if ((test_bit(ATH10K_CAC_RUNNING, &ar->dev_flags)) || (rx_status & (WMI_RX_STATUS_ERR_DECRYPT | WMI_RX_STATUS_ERR_KEY_CACHE_MISS | WMI_RX_STATUS_ERR_CRC))) { dev_kfree_skb(skb); return 0; } if (rx_status & WMI_RX_STATUS_ERR_MIC) status->flag |= RX_FLAG_MMIC_ERROR; if (rx_status & WMI_RX_STATUS_EXT_INFO) { status->mactime = __le64_to_cpu(arg.ext_info.rx_mac_timestamp); status->flag |= RX_FLAG_MACTIME_END; } /* Hardware can Rx CCK rates on 5GHz. In that case phy_mode is set to * MODE_11B. This means phy_mode is not a reliable source for the band * of mgmt rx. */ if (channel >= 1 && channel <= 14) { status->band = NL80211_BAND_2GHZ; } else if (channel >= 36 && channel <= ATH10K_MAX_5G_CHAN) { status->band = NL80211_BAND_5GHZ; } else { /* Shouldn't happen unless list of advertised channels to * mac80211 has been changed. */ WARN_ON_ONCE(1); dev_kfree_skb(skb); return 0; } if (phy_mode == MODE_11B && status->band == NL80211_BAND_5GHZ) ath10k_dbg(ar, ATH10K_DBG_MGMT, "wmi mgmt rx 11b (CCK) on 5GHz\n"); sband = &ar->mac.sbands[status->band]; status->freq = ieee80211_channel_to_frequency(channel, status->band); status->signal = snr + ATH10K_DEFAULT_NOISE_FLOOR; BUILD_BUG_ON(ARRAY_SIZE(status->chain_signal) != ARRAY_SIZE(arg.rssi)); for (i = 0; i < ARRAY_SIZE(status->chain_signal); i++) { status->chains &= ~BIT(i); rssi = __le32_to_cpu(arg.rssi[i]); ath10k_dbg(ar, ATH10K_DBG_MGMT, "mgmt rssi[%d]:%d\n", i, arg.rssi[i]); if (rssi != ATH10K_INVALID_RSSI && rssi != 0) { status->chain_signal[i] = ATH10K_DEFAULT_NOISE_FLOOR + rssi; status->chains |= BIT(i); } } status->rate_idx = ath10k_mac_bitrate_to_idx(sband, rate / 100); hdr = (struct ieee80211_hdr *)skb->data; fc = le16_to_cpu(hdr->frame_control); /* Firmware is guaranteed to report all essential management frames via * WMI while it can deliver some extra via HTT. Since there can be * duplicates split the reporting wrt monitor/sniffing. */ status->flag |= RX_FLAG_SKIP_MONITOR; ath10k_wmi_handle_wep_reauth(ar, skb, status); if (ath10k_wmi_rx_is_decrypted(ar, hdr)) { status->flag |= RX_FLAG_DECRYPTED; if (!ieee80211_is_action(hdr->frame_control) && !ieee80211_is_deauth(hdr->frame_control) && !ieee80211_is_disassoc(hdr->frame_control)) { status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED; hdr->frame_control = __cpu_to_le16(fc & ~IEEE80211_FCTL_PROTECTED); } } if (ieee80211_is_beacon(hdr->frame_control)) ath10k_mac_handle_beacon(ar, skb); if (ieee80211_is_beacon(hdr->frame_control) || ieee80211_is_probe_resp(hdr->frame_control)) status->boottime_ns = ktime_get_boottime_ns(); ath10k_dbg(ar, ATH10K_DBG_MGMT, "event mgmt rx skb %pK len %d ftype %02x stype %02x\n", skb, skb->len, fc & IEEE80211_FCTL_FTYPE, fc & IEEE80211_FCTL_STYPE); ath10k_dbg(ar, ATH10K_DBG_MGMT, "event mgmt rx freq %d band %d snr %d, rate_idx %d\n", status->freq, status->band, status->signal, status->rate_idx); ieee80211_rx_ni(ar->hw, skb); return 0; } static int freq_to_idx(struct ath10k *ar, int freq) { struct ieee80211_supported_band *sband; int band, ch, idx = 0; for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) { sband = ar->hw->wiphy->bands[band]; if (!sband) continue; for (ch = 0; ch < sband->n_channels; ch++, idx++) if (sband->channels[ch].center_freq == freq) goto exit; } exit: return idx; } static int ath10k_wmi_op_pull_ch_info_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_ch_info_ev_arg *arg) { struct wmi_chan_info_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->err_code = ev->err_code; arg->freq = ev->freq; arg->cmd_flags = ev->cmd_flags; arg->noise_floor = ev->noise_floor; arg->rx_clear_count = ev->rx_clear_count; arg->cycle_count = ev->cycle_count; return 0; } static int ath10k_wmi_10_4_op_pull_ch_info_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_ch_info_ev_arg *arg) { struct wmi_10_4_chan_info_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->err_code = ev->err_code; arg->freq = ev->freq; arg->cmd_flags = ev->cmd_flags; arg->noise_floor = ev->noise_floor; arg->rx_clear_count = ev->rx_clear_count; arg->cycle_count = ev->cycle_count; arg->chan_tx_pwr_range = ev->chan_tx_pwr_range; arg->chan_tx_pwr_tp = ev->chan_tx_pwr_tp; arg->rx_frame_count = ev->rx_frame_count; return 0; } /* * Handle the channel info event for firmware which only sends one * chan_info event per scanned channel. */ static void ath10k_wmi_event_chan_info_unpaired(struct ath10k *ar, struct chan_info_params *params) { struct survey_info *survey; int idx; if (params->cmd_flags & WMI_CHAN_INFO_FLAG_COMPLETE) { ath10k_dbg(ar, ATH10K_DBG_WMI, "chan info report completed\n"); return; } idx = freq_to_idx(ar, params->freq); if (idx >= ARRAY_SIZE(ar->survey)) { ath10k_warn(ar, "chan info: invalid frequency %d (idx %d out of bounds)\n", params->freq, idx); return; } survey = &ar->survey[idx]; if (!params->mac_clk_mhz) return; memset(survey, 0, sizeof(*survey)); survey->noise = params->noise_floor; survey->time = (params->cycle_count / params->mac_clk_mhz) / 1000; survey->time_busy = (params->rx_clear_count / params->mac_clk_mhz) / 1000; survey->filled |= SURVEY_INFO_NOISE_DBM | SURVEY_INFO_TIME | SURVEY_INFO_TIME_BUSY; } /* * Handle the channel info event for firmware which sends chan_info * event in pairs(start and stop events) for every scanned channel. */ static void ath10k_wmi_event_chan_info_paired(struct ath10k *ar, struct chan_info_params *params) { struct survey_info *survey; int idx; idx = freq_to_idx(ar, params->freq); if (idx >= ARRAY_SIZE(ar->survey)) { ath10k_warn(ar, "chan info: invalid frequency %d (idx %d out of bounds)\n", params->freq, idx); return; } if (params->cmd_flags & WMI_CHAN_INFO_FLAG_COMPLETE) { if (ar->ch_info_can_report_survey) { survey = &ar->survey[idx]; survey->noise = params->noise_floor; survey->filled = SURVEY_INFO_NOISE_DBM; ath10k_hw_fill_survey_time(ar, survey, params->cycle_count, params->rx_clear_count, ar->survey_last_cycle_count, ar->survey_last_rx_clear_count); } ar->ch_info_can_report_survey = false; } else { ar->ch_info_can_report_survey = true; } if (!(params->cmd_flags & WMI_CHAN_INFO_FLAG_PRE_COMPLETE)) { ar->survey_last_rx_clear_count = params->rx_clear_count; ar->survey_last_cycle_count = params->cycle_count; } } void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb) { struct chan_info_params ch_info_param; struct wmi_ch_info_ev_arg arg = {}; int ret; ret = ath10k_wmi_pull_ch_info(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse chan info event: %d\n", ret); return; } ch_info_param.err_code = __le32_to_cpu(arg.err_code); ch_info_param.freq = __le32_to_cpu(arg.freq); ch_info_param.cmd_flags = __le32_to_cpu(arg.cmd_flags); ch_info_param.noise_floor = __le32_to_cpu(arg.noise_floor); ch_info_param.rx_clear_count = __le32_to_cpu(arg.rx_clear_count); ch_info_param.cycle_count = __le32_to_cpu(arg.cycle_count); ch_info_param.mac_clk_mhz = __le32_to_cpu(arg.mac_clk_mhz); ath10k_dbg(ar, ATH10K_DBG_WMI, "chan info err_code %d freq %d cmd_flags %d noise_floor %d rx_clear_count %d cycle_count %d\n", ch_info_param.err_code, ch_info_param.freq, ch_info_param.cmd_flags, ch_info_param.noise_floor, ch_info_param.rx_clear_count, ch_info_param.cycle_count); spin_lock_bh(&ar->data_lock); switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_STARTING: ath10k_dbg(ar, ATH10K_DBG_WMI, "received chan info event without a scan request, ignoring\n"); goto exit; case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: break; } if (test_bit(ATH10K_FW_FEATURE_SINGLE_CHAN_INFO_PER_CHANNEL, ar->running_fw->fw_file.fw_features)) ath10k_wmi_event_chan_info_unpaired(ar, &ch_info_param); else ath10k_wmi_event_chan_info_paired(ar, &ch_info_param); exit: spin_unlock_bh(&ar->data_lock); } void ath10k_wmi_event_echo(struct ath10k *ar, struct sk_buff *skb) { struct wmi_echo_ev_arg arg = {}; int ret; ret = ath10k_wmi_pull_echo_ev(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse echo: %d\n", ret); return; } ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event echo value 0x%08x\n", le32_to_cpu(arg.value)); if (le32_to_cpu(arg.value) == ATH10K_WMI_BARRIER_ECHO_ID) complete(&ar->wmi.barrier); } int ath10k_wmi_event_debug_mesg(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event debug mesg len %d\n", skb->len); trace_ath10k_wmi_dbglog(ar, skb->data, skb->len); return 0; } void ath10k_wmi_pull_pdev_stats_base(const struct wmi_pdev_stats_base *src, struct ath10k_fw_stats_pdev *dst) { dst->ch_noise_floor = __le32_to_cpu(src->chan_nf); dst->tx_frame_count = __le32_to_cpu(src->tx_frame_count); dst->rx_frame_count = __le32_to_cpu(src->rx_frame_count); dst->rx_clear_count = __le32_to_cpu(src->rx_clear_count); dst->cycle_count = __le32_to_cpu(src->cycle_count); dst->phy_err_count = __le32_to_cpu(src->phy_err_count); dst->chan_tx_power = __le32_to_cpu(src->chan_tx_pwr); } void ath10k_wmi_pull_pdev_stats_tx(const struct wmi_pdev_stats_tx *src, struct ath10k_fw_stats_pdev *dst) { dst->comp_queued = __le32_to_cpu(src->comp_queued); dst->comp_delivered = __le32_to_cpu(src->comp_delivered); dst->msdu_enqued = __le32_to_cpu(src->msdu_enqued); dst->mpdu_enqued = __le32_to_cpu(src->mpdu_enqued); dst->wmm_drop = __le32_to_cpu(src->wmm_drop); dst->local_enqued = __le32_to_cpu(src->local_enqued); dst->local_freed = __le32_to_cpu(src->local_freed); dst->hw_queued = __le32_to_cpu(src->hw_queued); dst->hw_reaped = __le32_to_cpu(src->hw_reaped); dst->underrun = __le32_to_cpu(src->underrun); dst->tx_abort = __le32_to_cpu(src->tx_abort); dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued); dst->tx_ko = __le32_to_cpu(src->tx_ko); dst->data_rc = __le32_to_cpu(src->data_rc); dst->self_triggers = __le32_to_cpu(src->self_triggers); dst->sw_retry_failure = __le32_to_cpu(src->sw_retry_failure); dst->illgl_rate_phy_err = __le32_to_cpu(src->illgl_rate_phy_err); dst->pdev_cont_xretry = __le32_to_cpu(src->pdev_cont_xretry); dst->pdev_tx_timeout = __le32_to_cpu(src->pdev_tx_timeout); dst->pdev_resets = __le32_to_cpu(src->pdev_resets); dst->phy_underrun = __le32_to_cpu(src->phy_underrun); dst->txop_ovf = __le32_to_cpu(src->txop_ovf); } static void ath10k_wmi_10_4_pull_pdev_stats_tx(const struct wmi_10_4_pdev_stats_tx *src, struct ath10k_fw_stats_pdev *dst) { dst->comp_queued = __le32_to_cpu(src->comp_queued); dst->comp_delivered = __le32_to_cpu(src->comp_delivered); dst->msdu_enqued = __le32_to_cpu(src->msdu_enqued); dst->mpdu_enqued = __le32_to_cpu(src->mpdu_enqued); dst->wmm_drop = __le32_to_cpu(src->wmm_drop); dst->local_enqued = __le32_to_cpu(src->local_enqued); dst->local_freed = __le32_to_cpu(src->local_freed); dst->hw_queued = __le32_to_cpu(src->hw_queued); dst->hw_reaped = __le32_to_cpu(src->hw_reaped); dst->underrun = __le32_to_cpu(src->underrun); dst->tx_abort = __le32_to_cpu(src->tx_abort); dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued); dst->tx_ko = __le32_to_cpu(src->tx_ko); dst->data_rc = __le32_to_cpu(src->data_rc); dst->self_triggers = __le32_to_cpu(src->self_triggers); dst->sw_retry_failure = __le32_to_cpu(src->sw_retry_failure); dst->illgl_rate_phy_err = __le32_to_cpu(src->illgl_rate_phy_err); dst->pdev_cont_xretry = __le32_to_cpu(src->pdev_cont_xretry); dst->pdev_tx_timeout = __le32_to_cpu(src->pdev_tx_timeout); dst->pdev_resets = __le32_to_cpu(src->pdev_resets); dst->phy_underrun = __le32_to_cpu(src->phy_underrun); dst->txop_ovf = __le32_to_cpu(src->txop_ovf); dst->hw_paused = __le32_to_cpu(src->hw_paused); dst->seq_posted = __le32_to_cpu(src->seq_posted); dst->seq_failed_queueing = __le32_to_cpu(src->seq_failed_queueing); dst->seq_completed = __le32_to_cpu(src->seq_completed); dst->seq_restarted = __le32_to_cpu(src->seq_restarted); dst->mu_seq_posted = __le32_to_cpu(src->mu_seq_posted); dst->mpdus_sw_flush = __le32_to_cpu(src->mpdus_sw_flush); dst->mpdus_hw_filter = __le32_to_cpu(src->mpdus_hw_filter); dst->mpdus_truncated = __le32_to_cpu(src->mpdus_truncated); dst->mpdus_ack_failed = __le32_to_cpu(src->mpdus_ack_failed); dst->mpdus_hw_filter = __le32_to_cpu(src->mpdus_hw_filter); dst->mpdus_expired = __le32_to_cpu(src->mpdus_expired); } void ath10k_wmi_pull_pdev_stats_rx(const struct wmi_pdev_stats_rx *src, struct ath10k_fw_stats_pdev *dst) { dst->mid_ppdu_route_change = __le32_to_cpu(src->mid_ppdu_route_change); dst->status_rcvd = __le32_to_cpu(src->status_rcvd); dst->r0_frags = __le32_to_cpu(src->r0_frags); dst->r1_frags = __le32_to_cpu(src->r1_frags); dst->r2_frags = __le32_to_cpu(src->r2_frags); dst->r3_frags = __le32_to_cpu(src->r3_frags); dst->htt_msdus = __le32_to_cpu(src->htt_msdus); dst->htt_mpdus = __le32_to_cpu(src->htt_mpdus); dst->loc_msdus = __le32_to_cpu(src->loc_msdus); dst->loc_mpdus = __le32_to_cpu(src->loc_mpdus); dst->oversize_amsdu = __le32_to_cpu(src->oversize_amsdu); dst->phy_errs = __le32_to_cpu(src->phy_errs); dst->phy_err_drop = __le32_to_cpu(src->phy_err_drop); dst->mpdu_errs = __le32_to_cpu(src->mpdu_errs); } void ath10k_wmi_pull_pdev_stats_extra(const struct wmi_pdev_stats_extra *src, struct ath10k_fw_stats_pdev *dst) { dst->ack_rx_bad = __le32_to_cpu(src->ack_rx_bad); dst->rts_bad = __le32_to_cpu(src->rts_bad); dst->rts_good = __le32_to_cpu(src->rts_good); dst->fcs_bad = __le32_to_cpu(src->fcs_bad); dst->no_beacons = __le32_to_cpu(src->no_beacons); dst->mib_int_count = __le32_to_cpu(src->mib_int_count); } void ath10k_wmi_pull_peer_stats(const struct wmi_peer_stats *src, struct ath10k_fw_stats_peer *dst) { ether_addr_copy(dst->peer_macaddr, src->peer_macaddr.addr); dst->peer_rssi = __le32_to_cpu(src->peer_rssi); dst->peer_tx_rate = __le32_to_cpu(src->peer_tx_rate); } static void ath10k_wmi_10_4_pull_peer_stats(const struct wmi_10_4_peer_stats *src, struct ath10k_fw_stats_peer *dst) { ether_addr_copy(dst->peer_macaddr, src->peer_macaddr.addr); dst->peer_rssi = __le32_to_cpu(src->peer_rssi); dst->peer_tx_rate = __le32_to_cpu(src->peer_tx_rate); dst->peer_rx_rate = __le32_to_cpu(src->peer_rx_rate); } static void ath10k_wmi_10_4_pull_vdev_stats(const struct wmi_vdev_stats_extd *src, struct ath10k_fw_stats_vdev_extd *dst) { dst->vdev_id = __le32_to_cpu(src->vdev_id); dst->ppdu_aggr_cnt = __le32_to_cpu(src->ppdu_aggr_cnt); dst->ppdu_noack = __le32_to_cpu(src->ppdu_noack); dst->mpdu_queued = __le32_to_cpu(src->mpdu_queued); dst->ppdu_nonaggr_cnt = __le32_to_cpu(src->ppdu_nonaggr_cnt); dst->mpdu_sw_requeued = __le32_to_cpu(src->mpdu_sw_requeued); dst->mpdu_suc_retry = __le32_to_cpu(src->mpdu_suc_retry); dst->mpdu_suc_multitry = __le32_to_cpu(src->mpdu_suc_multitry); dst->mpdu_fail_retry = __le32_to_cpu(src->mpdu_fail_retry); dst->tx_ftm_suc = __le32_to_cpu(src->tx_ftm_suc); dst->tx_ftm_suc_retry = __le32_to_cpu(src->tx_ftm_suc_retry); dst->tx_ftm_fail = __le32_to_cpu(src->tx_ftm_fail); dst->rx_ftmr_cnt = __le32_to_cpu(src->rx_ftmr_cnt); dst->rx_ftmr_dup_cnt = __le32_to_cpu(src->rx_ftmr_dup_cnt); dst->rx_iftmr_cnt = __le32_to_cpu(src->rx_iftmr_cnt); dst->rx_iftmr_dup_cnt = __le32_to_cpu(src->rx_iftmr_dup_cnt); } static int ath10k_wmi_main_op_pull_fw_stats(struct ath10k *ar, struct sk_buff *skb, struct ath10k_fw_stats *stats) { const struct wmi_stats_event *ev = (void *)skb->data; u32 num_pdev_stats, num_peer_stats; int i; if (!skb_pull(skb, sizeof(*ev))) return -EPROTO; num_pdev_stats = __le32_to_cpu(ev->num_pdev_stats); num_peer_stats = __le32_to_cpu(ev->num_peer_stats); for (i = 0; i < num_pdev_stats; i++) { const struct wmi_pdev_stats *src; struct ath10k_fw_stats_pdev *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_pdev_stats_base(&src->base, dst); ath10k_wmi_pull_pdev_stats_tx(&src->tx, dst); ath10k_wmi_pull_pdev_stats_rx(&src->rx, dst); list_add_tail(&dst->list, &stats->pdevs); } /* fw doesn't implement vdev stats */ for (i = 0; i < num_peer_stats; i++) { const struct wmi_peer_stats *src; struct ath10k_fw_stats_peer *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_peer_stats(src, dst); list_add_tail(&dst->list, &stats->peers); } return 0; } static int ath10k_wmi_10x_op_pull_fw_stats(struct ath10k *ar, struct sk_buff *skb, struct ath10k_fw_stats *stats) { const struct wmi_stats_event *ev = (void *)skb->data; u32 num_pdev_stats, num_peer_stats; int i; if (!skb_pull(skb, sizeof(*ev))) return -EPROTO; num_pdev_stats = __le32_to_cpu(ev->num_pdev_stats); num_peer_stats = __le32_to_cpu(ev->num_peer_stats); for (i = 0; i < num_pdev_stats; i++) { const struct wmi_10x_pdev_stats *src; struct ath10k_fw_stats_pdev *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_pdev_stats_base(&src->base, dst); ath10k_wmi_pull_pdev_stats_tx(&src->tx, dst); ath10k_wmi_pull_pdev_stats_rx(&src->rx, dst); ath10k_wmi_pull_pdev_stats_extra(&src->extra, dst); list_add_tail(&dst->list, &stats->pdevs); } /* fw doesn't implement vdev stats */ for (i = 0; i < num_peer_stats; i++) { const struct wmi_10x_peer_stats *src; struct ath10k_fw_stats_peer *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_peer_stats(&src->old, dst); dst->peer_rx_rate = __le32_to_cpu(src->peer_rx_rate); list_add_tail(&dst->list, &stats->peers); } return 0; } static int ath10k_wmi_10_2_op_pull_fw_stats(struct ath10k *ar, struct sk_buff *skb, struct ath10k_fw_stats *stats) { const struct wmi_10_2_stats_event *ev = (void *)skb->data; u32 num_pdev_stats; u32 num_pdev_ext_stats; u32 num_peer_stats; int i; if (!skb_pull(skb, sizeof(*ev))) return -EPROTO; num_pdev_stats = __le32_to_cpu(ev->num_pdev_stats); num_pdev_ext_stats = __le32_to_cpu(ev->num_pdev_ext_stats); num_peer_stats = __le32_to_cpu(ev->num_peer_stats); for (i = 0; i < num_pdev_stats; i++) { const struct wmi_10_2_pdev_stats *src; struct ath10k_fw_stats_pdev *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_pdev_stats_base(&src->base, dst); ath10k_wmi_pull_pdev_stats_tx(&src->tx, dst); ath10k_wmi_pull_pdev_stats_rx(&src->rx, dst); ath10k_wmi_pull_pdev_stats_extra(&src->extra, dst); /* FIXME: expose 10.2 specific values */ list_add_tail(&dst->list, &stats->pdevs); } for (i = 0; i < num_pdev_ext_stats; i++) { const struct wmi_10_2_pdev_ext_stats *src; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; /* FIXME: expose values to userspace * * Note: Even though this loop seems to do nothing it is * required to parse following sub-structures properly. */ } /* fw doesn't implement vdev stats */ for (i = 0; i < num_peer_stats; i++) { const struct wmi_10_2_peer_stats *src; struct ath10k_fw_stats_peer *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_peer_stats(&src->old, dst); dst->peer_rx_rate = __le32_to_cpu(src->peer_rx_rate); /* FIXME: expose 10.2 specific values */ list_add_tail(&dst->list, &stats->peers); } return 0; } static int ath10k_wmi_10_2_4_op_pull_fw_stats(struct ath10k *ar, struct sk_buff *skb, struct ath10k_fw_stats *stats) { const struct wmi_10_2_stats_event *ev = (void *)skb->data; u32 num_pdev_stats; u32 num_pdev_ext_stats; u32 num_peer_stats; int i; if (!skb_pull(skb, sizeof(*ev))) return -EPROTO; num_pdev_stats = __le32_to_cpu(ev->num_pdev_stats); num_pdev_ext_stats = __le32_to_cpu(ev->num_pdev_ext_stats); num_peer_stats = __le32_to_cpu(ev->num_peer_stats); for (i = 0; i < num_pdev_stats; i++) { const struct wmi_10_2_pdev_stats *src; struct ath10k_fw_stats_pdev *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_pdev_stats_base(&src->base, dst); ath10k_wmi_pull_pdev_stats_tx(&src->tx, dst); ath10k_wmi_pull_pdev_stats_rx(&src->rx, dst); ath10k_wmi_pull_pdev_stats_extra(&src->extra, dst); /* FIXME: expose 10.2 specific values */ list_add_tail(&dst->list, &stats->pdevs); } for (i = 0; i < num_pdev_ext_stats; i++) { const struct wmi_10_2_pdev_ext_stats *src; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; /* FIXME: expose values to userspace * * Note: Even though this loop seems to do nothing it is * required to parse following sub-structures properly. */ } /* fw doesn't implement vdev stats */ for (i = 0; i < num_peer_stats; i++) { const struct wmi_10_2_4_ext_peer_stats *src; struct ath10k_fw_stats_peer *dst; int stats_len; if (test_bit(WMI_SERVICE_PEER_STATS, ar->wmi.svc_map)) stats_len = sizeof(struct wmi_10_2_4_ext_peer_stats); else stats_len = sizeof(struct wmi_10_2_4_peer_stats); src = (void *)skb->data; if (!skb_pull(skb, stats_len)) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_peer_stats(&src->common.old, dst); dst->peer_rx_rate = __le32_to_cpu(src->common.peer_rx_rate); if (ath10k_peer_stats_enabled(ar)) dst->rx_duration = __le32_to_cpu(src->rx_duration); /* FIXME: expose 10.2 specific values */ list_add_tail(&dst->list, &stats->peers); } return 0; } static int ath10k_wmi_10_4_op_pull_fw_stats(struct ath10k *ar, struct sk_buff *skb, struct ath10k_fw_stats *stats) { const struct wmi_10_2_stats_event *ev = (void *)skb->data; u32 num_pdev_stats; u32 num_pdev_ext_stats; u32 num_vdev_stats; u32 num_peer_stats; u32 num_bcnflt_stats; u32 stats_id; int i; if (!skb_pull(skb, sizeof(*ev))) return -EPROTO; num_pdev_stats = __le32_to_cpu(ev->num_pdev_stats); num_pdev_ext_stats = __le32_to_cpu(ev->num_pdev_ext_stats); num_vdev_stats = __le32_to_cpu(ev->num_vdev_stats); num_peer_stats = __le32_to_cpu(ev->num_peer_stats); num_bcnflt_stats = __le32_to_cpu(ev->num_bcnflt_stats); stats_id = __le32_to_cpu(ev->stats_id); for (i = 0; i < num_pdev_stats; i++) { const struct wmi_10_4_pdev_stats *src; struct ath10k_fw_stats_pdev *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_pull_pdev_stats_base(&src->base, dst); ath10k_wmi_10_4_pull_pdev_stats_tx(&src->tx, dst); ath10k_wmi_pull_pdev_stats_rx(&src->rx, dst); dst->rx_ovfl_errs = __le32_to_cpu(src->rx_ovfl_errs); ath10k_wmi_pull_pdev_stats_extra(&src->extra, dst); list_add_tail(&dst->list, &stats->pdevs); } for (i = 0; i < num_pdev_ext_stats; i++) { const struct wmi_10_2_pdev_ext_stats *src; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; /* FIXME: expose values to userspace * * Note: Even though this loop seems to do nothing it is * required to parse following sub-structures properly. */ } for (i = 0; i < num_vdev_stats; i++) { const struct wmi_vdev_stats *src; /* Ignore vdev stats here as it has only vdev id. Actual vdev * stats will be retrieved from vdev extended stats. */ src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; } for (i = 0; i < num_peer_stats; i++) { const struct wmi_10_4_peer_stats *src; struct ath10k_fw_stats_peer *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_10_4_pull_peer_stats(src, dst); list_add_tail(&dst->list, &stats->peers); } for (i = 0; i < num_bcnflt_stats; i++) { const struct wmi_10_4_bss_bcn_filter_stats *src; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; /* FIXME: expose values to userspace * * Note: Even though this loop seems to do nothing it is * required to parse following sub-structures properly. */ } if (stats_id & WMI_10_4_STAT_PEER_EXTD) { stats->extended = true; for (i = 0; i < num_peer_stats; i++) { const struct wmi_10_4_peer_extd_stats *src; struct ath10k_fw_extd_stats_peer *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ether_addr_copy(dst->peer_macaddr, src->peer_macaddr.addr); dst->rx_duration = __le32_to_cpu(src->rx_duration); list_add_tail(&dst->list, &stats->peers_extd); } } if (stats_id & WMI_10_4_STAT_VDEV_EXTD) { for (i = 0; i < num_vdev_stats; i++) { const struct wmi_vdev_stats_extd *src; struct ath10k_fw_stats_vdev_extd *dst; src = (void *)skb->data; if (!skb_pull(skb, sizeof(*src))) return -EPROTO; dst = kzalloc(sizeof(*dst), GFP_ATOMIC); if (!dst) continue; ath10k_wmi_10_4_pull_vdev_stats(src, dst); list_add_tail(&dst->list, &stats->vdevs); } } return 0; } void ath10k_wmi_event_update_stats(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_UPDATE_STATS_EVENTID\n"); ath10k_debug_fw_stats_process(ar, skb); } static int ath10k_wmi_op_pull_vdev_start_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_vdev_start_ev_arg *arg) { struct wmi_vdev_start_response_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->vdev_id = ev->vdev_id; arg->req_id = ev->req_id; arg->resp_type = ev->resp_type; arg->status = ev->status; return 0; } void ath10k_wmi_event_vdev_start_resp(struct ath10k *ar, struct sk_buff *skb) { struct wmi_vdev_start_ev_arg arg = {}; int ret; u32 status; ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_START_RESP_EVENTID\n"); ar->last_wmi_vdev_start_status = 0; ret = ath10k_wmi_pull_vdev_start(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse vdev start event: %d\n", ret); ar->last_wmi_vdev_start_status = ret; goto out; } status = __le32_to_cpu(arg.status); if (WARN_ON_ONCE(status)) { ath10k_warn(ar, "vdev-start-response reports status error: %d (%s)\n", status, (status == WMI_VDEV_START_CHAN_INVALID) ? "chan-invalid" : "unknown"); /* Setup is done one way or another though, so we should still * do the completion, so don't return here. */ ar->last_wmi_vdev_start_status = -EINVAL; } out: complete(&ar->vdev_setup_done); } void ath10k_wmi_event_vdev_stopped(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_STOPPED_EVENTID\n"); complete(&ar->vdev_setup_done); } static int ath10k_wmi_op_pull_peer_kick_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_peer_kick_ev_arg *arg) { struct wmi_peer_sta_kickout_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->mac_addr = ev->peer_macaddr.addr; return 0; } void ath10k_wmi_event_peer_sta_kickout(struct ath10k *ar, struct sk_buff *skb) { struct wmi_peer_kick_ev_arg arg = {}; struct ieee80211_sta *sta; int ret; ret = ath10k_wmi_pull_peer_kick(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse peer kickout event: %d\n", ret); return; } ath10k_dbg(ar, ATH10K_DBG_STA, "wmi event peer sta kickout %pM\n", arg.mac_addr); rcu_read_lock(); sta = ieee80211_find_sta_by_ifaddr(ar->hw, arg.mac_addr, NULL); if (!sta) { ath10k_warn(ar, "Spurious quick kickout for STA %pM\n", arg.mac_addr); goto exit; } ieee80211_report_low_ack(sta, 10); exit: rcu_read_unlock(); } /* * FIXME * * We don't report to mac80211 sleep state of connected * stations. Due to this mac80211 can't fill in TIM IE * correctly. * * I know of no way of getting nullfunc frames that contain * sleep transition from connected stations - these do not * seem to be sent from the target to the host. There also * doesn't seem to be a dedicated event for that. So the * only way left to do this would be to read tim_bitmap * during SWBA. * * We could probably try using tim_bitmap from SWBA to tell * mac80211 which stations are asleep and which are not. The * problem here is calling mac80211 functions so many times * could take too long and make us miss the time to submit * the beacon to the target. * * So as a workaround we try to extend the TIM IE if there * is unicast buffered for stations with aid > 7 and fill it * in ourselves. */ static void ath10k_wmi_update_tim(struct ath10k *ar, struct ath10k_vif *arvif, struct sk_buff *bcn, const struct wmi_tim_info_arg *tim_info) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)bcn->data; struct ieee80211_tim_ie *tim; u8 *ies, *ie; u8 ie_len, pvm_len; __le32 t; u32 v, tim_len; /* When FW reports 0 in tim_len, ensure at least first byte * in tim_bitmap is considered for pvm calculation. */ tim_len = tim_info->tim_len ? __le32_to_cpu(tim_info->tim_len) : 1; /* if next SWBA has no tim_changed the tim_bitmap is garbage. * we must copy the bitmap upon change and reuse it later */ if (__le32_to_cpu(tim_info->tim_changed)) { int i; if (sizeof(arvif->u.ap.tim_bitmap) < tim_len) { ath10k_warn(ar, "SWBA TIM field is too big (%u), truncated it to %zu", tim_len, sizeof(arvif->u.ap.tim_bitmap)); tim_len = sizeof(arvif->u.ap.tim_bitmap); } for (i = 0; i < tim_len; i++) { t = tim_info->tim_bitmap[i / 4]; v = __le32_to_cpu(t); arvif->u.ap.tim_bitmap[i] = (v >> ((i % 4) * 8)) & 0xFF; } /* FW reports either length 0 or length based on max supported * station. so we calculate this on our own */ arvif->u.ap.tim_len = 0; for (i = 0; i < tim_len; i++) if (arvif->u.ap.tim_bitmap[i]) arvif->u.ap.tim_len = i; arvif->u.ap.tim_len++; } ies = bcn->data; ies += ieee80211_hdrlen(hdr->frame_control); ies += 12; /* fixed parameters */ ie = (u8 *)cfg80211_find_ie(WLAN_EID_TIM, ies, (u8 *)skb_tail_pointer(bcn) - ies); if (!ie) { if (arvif->vdev_type != WMI_VDEV_TYPE_IBSS) ath10k_warn(ar, "no tim ie found;\n"); return; } tim = (void *)ie + 2; ie_len = ie[1]; pvm_len = ie_len - 3; /* exclude dtim count, dtim period, bmap ctl */ if (pvm_len < arvif->u.ap.tim_len) { int expand_size = tim_len - pvm_len; int move_size = skb_tail_pointer(bcn) - (ie + 2 + ie_len); void *next_ie = ie + 2 + ie_len; if (skb_put(bcn, expand_size)) { memmove(next_ie + expand_size, next_ie, move_size); ie[1] += expand_size; ie_len += expand_size; pvm_len += expand_size; } else { ath10k_warn(ar, "tim expansion failed\n"); } } if (pvm_len > tim_len) { ath10k_warn(ar, "tim pvm length is too great (%d)\n", pvm_len); return; } tim->bitmap_ctrl = !!__le32_to_cpu(tim_info->tim_mcast); memcpy(tim->virtual_map, arvif->u.ap.tim_bitmap, pvm_len); if (tim->dtim_count == 0) { ATH10K_SKB_CB(bcn)->flags |= ATH10K_SKB_F_DTIM_ZERO; if (__le32_to_cpu(tim_info->tim_mcast) == 1) ATH10K_SKB_CB(bcn)->flags |= ATH10K_SKB_F_DELIVER_CAB; } ath10k_dbg(ar, ATH10K_DBG_MGMT, "dtim %d/%d mcast %d pvmlen %d\n", tim->dtim_count, tim->dtim_period, tim->bitmap_ctrl, pvm_len); } static void ath10k_wmi_update_noa(struct ath10k *ar, struct ath10k_vif *arvif, struct sk_buff *bcn, const struct wmi_p2p_noa_info *noa) { if (!arvif->vif->p2p) return; ath10k_dbg(ar, ATH10K_DBG_MGMT, "noa changed: %d\n", noa->changed); if (noa->changed & WMI_P2P_NOA_CHANGED_BIT) ath10k_p2p_noa_update(arvif, noa); if (arvif->u.ap.noa_data) if (!pskb_expand_head(bcn, 0, arvif->u.ap.noa_len, GFP_ATOMIC)) skb_put_data(bcn, arvif->u.ap.noa_data, arvif->u.ap.noa_len); } static int ath10k_wmi_op_pull_swba_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_swba_ev_arg *arg) { struct wmi_host_swba_event *ev = (void *)skb->data; u32 map; size_t i; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->vdev_map = ev->vdev_map; for (i = 0, map = __le32_to_cpu(ev->vdev_map); map; map >>= 1) { if (!(map & BIT(0))) continue; /* If this happens there were some changes in firmware and * ath10k should update the max size of tim_info array. */ if (WARN_ON_ONCE(i == ARRAY_SIZE(arg->tim_info))) break; if (__le32_to_cpu(ev->bcn_info[i].tim_info.tim_len) > sizeof(ev->bcn_info[i].tim_info.tim_bitmap)) { ath10k_warn(ar, "refusing to parse invalid swba structure\n"); return -EPROTO; } arg->tim_info[i].tim_len = ev->bcn_info[i].tim_info.tim_len; arg->tim_info[i].tim_mcast = ev->bcn_info[i].tim_info.tim_mcast; arg->tim_info[i].tim_bitmap = ev->bcn_info[i].tim_info.tim_bitmap; arg->tim_info[i].tim_changed = ev->bcn_info[i].tim_info.tim_changed; arg->tim_info[i].tim_num_ps_pending = ev->bcn_info[i].tim_info.tim_num_ps_pending; arg->noa_info[i] = &ev->bcn_info[i].p2p_noa_info; i++; } return 0; } static int ath10k_wmi_10_2_4_op_pull_swba_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_swba_ev_arg *arg) { struct wmi_10_2_4_host_swba_event *ev = (void *)skb->data; u32 map; size_t i; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->vdev_map = ev->vdev_map; for (i = 0, map = __le32_to_cpu(ev->vdev_map); map; map >>= 1) { if (!(map & BIT(0))) continue; /* If this happens there were some changes in firmware and * ath10k should update the max size of tim_info array. */ if (WARN_ON_ONCE(i == ARRAY_SIZE(arg->tim_info))) break; if (__le32_to_cpu(ev->bcn_info[i].tim_info.tim_len) > sizeof(ev->bcn_info[i].tim_info.tim_bitmap)) { ath10k_warn(ar, "refusing to parse invalid swba structure\n"); return -EPROTO; } arg->tim_info[i].tim_len = ev->bcn_info[i].tim_info.tim_len; arg->tim_info[i].tim_mcast = ev->bcn_info[i].tim_info.tim_mcast; arg->tim_info[i].tim_bitmap = ev->bcn_info[i].tim_info.tim_bitmap; arg->tim_info[i].tim_changed = ev->bcn_info[i].tim_info.tim_changed; arg->tim_info[i].tim_num_ps_pending = ev->bcn_info[i].tim_info.tim_num_ps_pending; i++; } return 0; } static int ath10k_wmi_10_4_op_pull_swba_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_swba_ev_arg *arg) { struct wmi_10_4_host_swba_event *ev = (void *)skb->data; u32 map, tim_len; size_t i; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->vdev_map = ev->vdev_map; for (i = 0, map = __le32_to_cpu(ev->vdev_map); map; map >>= 1) { if (!(map & BIT(0))) continue; /* If this happens there were some changes in firmware and * ath10k should update the max size of tim_info array. */ if (WARN_ON_ONCE(i == ARRAY_SIZE(arg->tim_info))) break; if (__le32_to_cpu(ev->bcn_info[i].tim_info.tim_len) > sizeof(ev->bcn_info[i].tim_info.tim_bitmap)) { ath10k_warn(ar, "refusing to parse invalid swba structure\n"); return -EPROTO; } tim_len = __le32_to_cpu(ev->bcn_info[i].tim_info.tim_len); if (tim_len) { /* Exclude 4 byte guard length */ tim_len -= 4; arg->tim_info[i].tim_len = __cpu_to_le32(tim_len); } else { arg->tim_info[i].tim_len = 0; } arg->tim_info[i].tim_mcast = ev->bcn_info[i].tim_info.tim_mcast; arg->tim_info[i].tim_bitmap = ev->bcn_info[i].tim_info.tim_bitmap; arg->tim_info[i].tim_changed = ev->bcn_info[i].tim_info.tim_changed; arg->tim_info[i].tim_num_ps_pending = ev->bcn_info[i].tim_info.tim_num_ps_pending; /* 10.4 firmware doesn't have p2p support. notice of absence * info can be ignored for now. */ i++; } return 0; } static enum wmi_txbf_conf ath10k_wmi_10_4_txbf_conf_scheme(struct ath10k *ar) { return WMI_TXBF_CONF_BEFORE_ASSOC; } void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb) { struct wmi_swba_ev_arg arg = {}; u32 map; int i = -1; const struct wmi_tim_info_arg *tim_info; const struct wmi_p2p_noa_info *noa_info; struct ath10k_vif *arvif; struct sk_buff *bcn; dma_addr_t paddr; int ret, vdev_id = 0; ret = ath10k_wmi_pull_swba(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse swba event: %d\n", ret); return; } map = __le32_to_cpu(arg.vdev_map); ath10k_dbg(ar, ATH10K_DBG_MGMT, "mgmt swba vdev_map 0x%x\n", map); for (; map; map >>= 1, vdev_id++) { if (!(map & 0x1)) continue; i++; if (i >= WMI_MAX_AP_VDEV) { ath10k_warn(ar, "swba has corrupted vdev map\n"); break; } tim_info = &arg.tim_info[i]; noa_info = arg.noa_info[i]; ath10k_dbg(ar, ATH10K_DBG_MGMT, "mgmt event bcn_info %d tim_len %d mcast %d changed %d num_ps_pending %d bitmap 0x%08x%08x%08x%08x\n", i, __le32_to_cpu(tim_info->tim_len), __le32_to_cpu(tim_info->tim_mcast), __le32_to_cpu(tim_info->tim_changed), __le32_to_cpu(tim_info->tim_num_ps_pending), __le32_to_cpu(tim_info->tim_bitmap[3]), __le32_to_cpu(tim_info->tim_bitmap[2]), __le32_to_cpu(tim_info->tim_bitmap[1]), __le32_to_cpu(tim_info->tim_bitmap[0])); /* TODO: Only first 4 word from tim_bitmap is dumped. * Extend debug code to dump full tim_bitmap. */ arvif = ath10k_get_arvif(ar, vdev_id); if (arvif == NULL) { ath10k_warn(ar, "no vif for vdev_id %d found\n", vdev_id); continue; } /* mac80211 would have already asked us to stop beaconing and * bring the vdev down, so continue in that case */ if (!arvif->is_up) continue; /* There are no completions for beacons so wait for next SWBA * before telling mac80211 to decrement CSA counter * * Once CSA counter is completed stop sending beacons until * actual channel switch is done */ if (arvif->vif->bss_conf.csa_active && ieee80211_beacon_cntdwn_is_complete(arvif->vif, 0)) { ieee80211_csa_finish(arvif->vif, 0); continue; } bcn = ieee80211_beacon_get(ar->hw, arvif->vif, 0); if (!bcn) { ath10k_warn(ar, "could not get mac80211 beacon\n"); continue; } ath10k_tx_h_seq_no(arvif->vif, bcn); ath10k_wmi_update_tim(ar, arvif, bcn, tim_info); ath10k_wmi_update_noa(ar, arvif, bcn, noa_info); spin_lock_bh(&ar->data_lock); if (arvif->beacon) { switch (arvif->beacon_state) { case ATH10K_BEACON_SENT: break; case ATH10K_BEACON_SCHEDULED: ath10k_warn(ar, "SWBA overrun on vdev %d, skipped old beacon\n", arvif->vdev_id); break; case ATH10K_BEACON_SENDING: ath10k_warn(ar, "SWBA overrun on vdev %d, skipped new beacon\n", arvif->vdev_id); dev_kfree_skb(bcn); goto skip; } ath10k_mac_vif_beacon_free(arvif); } if (!arvif->beacon_buf) { paddr = dma_map_single(arvif->ar->dev, bcn->data, bcn->len, DMA_TO_DEVICE); ret = dma_mapping_error(arvif->ar->dev, paddr); if (ret) { ath10k_warn(ar, "failed to map beacon: %d\n", ret); dev_kfree_skb_any(bcn); goto skip; } ATH10K_SKB_CB(bcn)->paddr = paddr; } else { if (bcn->len > IEEE80211_MAX_FRAME_LEN) { ath10k_warn(ar, "trimming beacon %d -> %d bytes!\n", bcn->len, IEEE80211_MAX_FRAME_LEN); skb_trim(bcn, IEEE80211_MAX_FRAME_LEN); } memcpy(arvif->beacon_buf, bcn->data, bcn->len); ATH10K_SKB_CB(bcn)->paddr = arvif->beacon_paddr; } arvif->beacon = bcn; arvif->beacon_state = ATH10K_BEACON_SCHEDULED; trace_ath10k_tx_hdr(ar, bcn->data, bcn->len); trace_ath10k_tx_payload(ar, bcn->data, bcn->len); skip: spin_unlock_bh(&ar->data_lock); } ath10k_wmi_tx_beacons_nowait(ar); } void ath10k_wmi_event_tbttoffset_update(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_TBTTOFFSET_UPDATE_EVENTID\n"); } static void ath10k_radar_detected(struct ath10k *ar) { ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs radar detected\n"); ATH10K_DFS_STAT_INC(ar, radar_detected); /* Control radar events reporting in debugfs file * dfs_block_radar_events */ if (ar->dfs_block_radar_events) ath10k_info(ar, "DFS Radar detected, but ignored as requested\n"); else ieee80211_radar_detected(ar->hw, NULL); } static void ath10k_radar_confirmation_work(struct work_struct *work) { struct ath10k *ar = container_of(work, struct ath10k, radar_confirmation_work); struct ath10k_radar_found_info radar_info; int ret, time_left; reinit_completion(&ar->wmi.radar_confirm); spin_lock_bh(&ar->data_lock); memcpy(&radar_info, &ar->last_radar_info, sizeof(radar_info)); spin_unlock_bh(&ar->data_lock); ret = ath10k_wmi_report_radar_found(ar, &radar_info); if (ret) { ath10k_warn(ar, "failed to send radar found %d\n", ret); goto wait_complete; } time_left = wait_for_completion_timeout(&ar->wmi.radar_confirm, ATH10K_WMI_DFS_CONF_TIMEOUT_HZ); if (time_left) { /* DFS Confirmation status event received and * necessary action completed. */ goto wait_complete; } else { /* DFS Confirmation event not received from FW.Considering this * as real radar. */ ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs confirmation not received from fw, considering as radar\n"); goto radar_detected; } radar_detected: ath10k_radar_detected(ar); /* Reset state to allow sending confirmation on consecutive radar * detections, unless radar confirmation is disabled/stopped. */ wait_complete: spin_lock_bh(&ar->data_lock); if (ar->radar_conf_state != ATH10K_RADAR_CONFIRMATION_STOPPED) ar->radar_conf_state = ATH10K_RADAR_CONFIRMATION_IDLE; spin_unlock_bh(&ar->data_lock); } static void ath10k_dfs_radar_report(struct ath10k *ar, struct wmi_phyerr_ev_arg *phyerr, const struct phyerr_radar_report *rr, u64 tsf) { u32 reg0, reg1, tsf32l; struct ieee80211_channel *ch; struct pulse_event pe; struct radar_detector_specs rs; u64 tsf64; u8 rssi, width; struct ath10k_radar_found_info *radar_info; reg0 = __le32_to_cpu(rr->reg0); reg1 = __le32_to_cpu(rr->reg1); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi phyerr radar report chirp %d max_width %d agc_total_gain %d pulse_delta_diff %d\n", MS(reg0, RADAR_REPORT_REG0_PULSE_IS_CHIRP), MS(reg0, RADAR_REPORT_REG0_PULSE_IS_MAX_WIDTH), MS(reg0, RADAR_REPORT_REG0_AGC_TOTAL_GAIN), MS(reg0, RADAR_REPORT_REG0_PULSE_DELTA_DIFF)); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi phyerr radar report pulse_delta_pean %d pulse_sidx %d fft_valid %d agc_mb_gain %d subchan_mask %d\n", MS(reg0, RADAR_REPORT_REG0_PULSE_DELTA_PEAK), MS(reg0, RADAR_REPORT_REG0_PULSE_SIDX), MS(reg1, RADAR_REPORT_REG1_PULSE_SRCH_FFT_VALID), MS(reg1, RADAR_REPORT_REG1_PULSE_AGC_MB_GAIN), MS(reg1, RADAR_REPORT_REG1_PULSE_SUBCHAN_MASK)); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi phyerr radar report pulse_tsf_offset 0x%X pulse_dur: %d\n", MS(reg1, RADAR_REPORT_REG1_PULSE_TSF_OFFSET), MS(reg1, RADAR_REPORT_REG1_PULSE_DUR)); if (!ar->dfs_detector) return; spin_lock_bh(&ar->data_lock); ch = ar->rx_channel; /* fetch target operating channel during channel change */ if (!ch) ch = ar->tgt_oper_chan; spin_unlock_bh(&ar->data_lock); if (!ch) { ath10k_warn(ar, "failed to derive channel for radar pulse, treating as radar\n"); goto radar_detected; } /* report event to DFS pattern detector */ tsf32l = phyerr->tsf_timestamp; tsf64 = tsf & (~0xFFFFFFFFULL); tsf64 |= tsf32l; width = MS(reg1, RADAR_REPORT_REG1_PULSE_DUR); rssi = phyerr->rssi_combined; /* hardware store this as 8 bit signed value, * set to zero if negative number */ if (rssi & 0x80) rssi = 0; pe.ts = tsf64; pe.freq = ch->center_freq; pe.width = width; pe.rssi = rssi; pe.chirp = (MS(reg0, RADAR_REPORT_REG0_PULSE_IS_CHIRP) != 0); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs add pulse freq: %d, width: %d, rssi %d, tsf: %llX\n", pe.freq, pe.width, pe.rssi, pe.ts); ATH10K_DFS_STAT_INC(ar, pulses_detected); if (!ar->dfs_detector->add_pulse(ar->dfs_detector, &pe, &rs)) { ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs no pulse pattern detected, yet\n"); return; } if ((test_bit(WMI_SERVICE_HOST_DFS_CHECK_SUPPORT, ar->wmi.svc_map)) && ar->dfs_detector->region == NL80211_DFS_FCC) { /* Consecutive radar indications need not be * sent to the firmware until we get confirmation * for the previous detected radar. */ spin_lock_bh(&ar->data_lock); if (ar->radar_conf_state != ATH10K_RADAR_CONFIRMATION_IDLE) { spin_unlock_bh(&ar->data_lock); return; } ar->radar_conf_state = ATH10K_RADAR_CONFIRMATION_INPROGRESS; radar_info = &ar->last_radar_info; radar_info->pri_min = rs.pri_min; radar_info->pri_max = rs.pri_max; radar_info->width_min = rs.width_min; radar_info->width_max = rs.width_max; /*TODO Find sidx_min and sidx_max */ radar_info->sidx_min = MS(reg0, RADAR_REPORT_REG0_PULSE_SIDX); radar_info->sidx_max = MS(reg0, RADAR_REPORT_REG0_PULSE_SIDX); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "sending wmi radar found cmd pri_min %d pri_max %d width_min %d width_max %d sidx_min %d sidx_max %d\n", radar_info->pri_min, radar_info->pri_max, radar_info->width_min, radar_info->width_max, radar_info->sidx_min, radar_info->sidx_max); ieee80211_queue_work(ar->hw, &ar->radar_confirmation_work); spin_unlock_bh(&ar->data_lock); return; } radar_detected: ath10k_radar_detected(ar); } static int ath10k_dfs_fft_report(struct ath10k *ar, struct wmi_phyerr_ev_arg *phyerr, const struct phyerr_fft_report *fftr, u64 tsf) { u32 reg0, reg1; u8 rssi, peak_mag; reg0 = __le32_to_cpu(fftr->reg0); reg1 = __le32_to_cpu(fftr->reg1); rssi = phyerr->rssi_combined; ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi phyerr fft report total_gain_db %d base_pwr_db %d fft_chn_idx %d peak_sidx %d\n", MS(reg0, SEARCH_FFT_REPORT_REG0_TOTAL_GAIN_DB), MS(reg0, SEARCH_FFT_REPORT_REG0_BASE_PWR_DB), MS(reg0, SEARCH_FFT_REPORT_REG0_FFT_CHN_IDX), MS(reg0, SEARCH_FFT_REPORT_REG0_PEAK_SIDX)); ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi phyerr fft report rel_pwr_db %d avgpwr_db %d peak_mag %d num_store_bin %d\n", MS(reg1, SEARCH_FFT_REPORT_REG1_RELPWR_DB), MS(reg1, SEARCH_FFT_REPORT_REG1_AVGPWR_DB), MS(reg1, SEARCH_FFT_REPORT_REG1_PEAK_MAG), MS(reg1, SEARCH_FFT_REPORT_REG1_NUM_STR_BINS_IB)); peak_mag = MS(reg1, SEARCH_FFT_REPORT_REG1_PEAK_MAG); /* false event detection */ if (rssi == DFS_RSSI_POSSIBLY_FALSE && peak_mag < 2 * DFS_PEAK_MAG_THOLD_POSSIBLY_FALSE) { ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs false pulse detected\n"); ATH10K_DFS_STAT_INC(ar, pulses_discarded); return -EINVAL; } return 0; } void ath10k_wmi_event_dfs(struct ath10k *ar, struct wmi_phyerr_ev_arg *phyerr, u64 tsf) { int buf_len, tlv_len, res, i = 0; const struct phyerr_tlv *tlv; const struct phyerr_radar_report *rr; const struct phyerr_fft_report *fftr; const u8 *tlv_buf; buf_len = phyerr->buf_len; ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi event dfs err_code %d rssi %d tsfl 0x%X tsf64 0x%llX len %d\n", phyerr->phy_err_code, phyerr->rssi_combined, phyerr->tsf_timestamp, tsf, buf_len); /* Skip event if DFS disabled */ if (!IS_ENABLED(CONFIG_ATH10K_DFS_CERTIFIED)) return; ATH10K_DFS_STAT_INC(ar, pulses_total); while (i < buf_len) { if (i + sizeof(*tlv) > buf_len) { ath10k_warn(ar, "too short buf for tlv header (%d)\n", i); return; } tlv = (struct phyerr_tlv *)&phyerr->buf[i]; tlv_len = __le16_to_cpu(tlv->len); tlv_buf = &phyerr->buf[i + sizeof(*tlv)]; ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "wmi event dfs tlv_len %d tlv_tag 0x%02X tlv_sig 0x%02X\n", tlv_len, tlv->tag, tlv->sig); switch (tlv->tag) { case PHYERR_TLV_TAG_RADAR_PULSE_SUMMARY: if (i + sizeof(*tlv) + sizeof(*rr) > buf_len) { ath10k_warn(ar, "too short radar pulse summary (%d)\n", i); return; } rr = (struct phyerr_radar_report *)tlv_buf; ath10k_dfs_radar_report(ar, phyerr, rr, tsf); break; case PHYERR_TLV_TAG_SEARCH_FFT_REPORT: if (i + sizeof(*tlv) + sizeof(*fftr) > buf_len) { ath10k_warn(ar, "too short fft report (%d)\n", i); return; } fftr = (struct phyerr_fft_report *)tlv_buf; res = ath10k_dfs_fft_report(ar, phyerr, fftr, tsf); if (res) return; break; } i += sizeof(*tlv) + tlv_len; } } void ath10k_wmi_event_spectral_scan(struct ath10k *ar, struct wmi_phyerr_ev_arg *phyerr, u64 tsf) { int buf_len, tlv_len, res, i = 0; struct phyerr_tlv *tlv; const void *tlv_buf; const struct phyerr_fft_report *fftr; size_t fftr_len; buf_len = phyerr->buf_len; while (i < buf_len) { if (i + sizeof(*tlv) > buf_len) { ath10k_warn(ar, "failed to parse phyerr tlv header at byte %d\n", i); return; } tlv = (struct phyerr_tlv *)&phyerr->buf[i]; tlv_len = __le16_to_cpu(tlv->len); tlv_buf = &phyerr->buf[i + sizeof(*tlv)]; if (i + sizeof(*tlv) + tlv_len > buf_len) { ath10k_warn(ar, "failed to parse phyerr tlv payload at byte %d\n", i); return; } switch (tlv->tag) { case PHYERR_TLV_TAG_SEARCH_FFT_REPORT: if (sizeof(*fftr) > tlv_len) { ath10k_warn(ar, "failed to parse fft report at byte %d\n", i); return; } fftr_len = tlv_len - sizeof(*fftr); fftr = tlv_buf; res = ath10k_spectral_process_fft(ar, phyerr, fftr, fftr_len, tsf); if (res < 0) { ath10k_dbg(ar, ATH10K_DBG_WMI, "failed to process fft report: %d\n", res); return; } break; } i += sizeof(*tlv) + tlv_len; } } static int ath10k_wmi_op_pull_phyerr_ev_hdr(struct ath10k *ar, struct sk_buff *skb, struct wmi_phyerr_hdr_arg *arg) { struct wmi_phyerr_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; arg->num_phyerrs = __le32_to_cpu(ev->num_phyerrs); arg->tsf_l32 = __le32_to_cpu(ev->tsf_l32); arg->tsf_u32 = __le32_to_cpu(ev->tsf_u32); arg->buf_len = skb->len - sizeof(*ev); arg->phyerrs = ev->phyerrs; return 0; } static int ath10k_wmi_10_4_op_pull_phyerr_ev_hdr(struct ath10k *ar, struct sk_buff *skb, struct wmi_phyerr_hdr_arg *arg) { struct wmi_10_4_phyerr_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; /* 10.4 firmware always reports only one phyerr */ arg->num_phyerrs = 1; arg->tsf_l32 = __le32_to_cpu(ev->tsf_l32); arg->tsf_u32 = __le32_to_cpu(ev->tsf_u32); arg->buf_len = skb->len; arg->phyerrs = skb->data; return 0; } int ath10k_wmi_op_pull_phyerr_ev(struct ath10k *ar, const void *phyerr_buf, int left_len, struct wmi_phyerr_ev_arg *arg) { const struct wmi_phyerr *phyerr = phyerr_buf; int i; if (left_len < sizeof(*phyerr)) { ath10k_warn(ar, "wrong phyerr event head len %d (need: >=%zd)\n", left_len, sizeof(*phyerr)); return -EINVAL; } arg->tsf_timestamp = __le32_to_cpu(phyerr->tsf_timestamp); arg->freq1 = __le16_to_cpu(phyerr->freq1); arg->freq2 = __le16_to_cpu(phyerr->freq2); arg->rssi_combined = phyerr->rssi_combined; arg->chan_width_mhz = phyerr->chan_width_mhz; arg->buf_len = __le32_to_cpu(phyerr->buf_len); arg->buf = phyerr->buf; arg->hdr_len = sizeof(*phyerr); for (i = 0; i < 4; i++) arg->nf_chains[i] = __le16_to_cpu(phyerr->nf_chains[i]); switch (phyerr->phy_err_code) { case PHY_ERROR_GEN_SPECTRAL_SCAN: arg->phy_err_code = PHY_ERROR_SPECTRAL_SCAN; break; case PHY_ERROR_GEN_FALSE_RADAR_EXT: arg->phy_err_code = PHY_ERROR_FALSE_RADAR_EXT; break; case PHY_ERROR_GEN_RADAR: arg->phy_err_code = PHY_ERROR_RADAR; break; default: arg->phy_err_code = PHY_ERROR_UNKNOWN; break; } return 0; } static int ath10k_wmi_10_4_op_pull_phyerr_ev(struct ath10k *ar, const void *phyerr_buf, int left_len, struct wmi_phyerr_ev_arg *arg) { const struct wmi_10_4_phyerr_event *phyerr = phyerr_buf; u32 phy_err_mask; int i; if (left_len < sizeof(*phyerr)) { ath10k_warn(ar, "wrong phyerr event head len %d (need: >=%zd)\n", left_len, sizeof(*phyerr)); return -EINVAL; } arg->tsf_timestamp = __le32_to_cpu(phyerr->tsf_timestamp); arg->freq1 = __le16_to_cpu(phyerr->freq1); arg->freq2 = __le16_to_cpu(phyerr->freq2); arg->rssi_combined = phyerr->rssi_combined; arg->chan_width_mhz = phyerr->chan_width_mhz; arg->buf_len = __le32_to_cpu(phyerr->buf_len); arg->buf = phyerr->buf; arg->hdr_len = sizeof(*phyerr); for (i = 0; i < 4; i++) arg->nf_chains[i] = __le16_to_cpu(phyerr->nf_chains[i]); phy_err_mask = __le32_to_cpu(phyerr->phy_err_mask[0]); if (phy_err_mask & PHY_ERROR_10_4_SPECTRAL_SCAN_MASK) arg->phy_err_code = PHY_ERROR_SPECTRAL_SCAN; else if (phy_err_mask & PHY_ERROR_10_4_RADAR_MASK) arg->phy_err_code = PHY_ERROR_RADAR; else arg->phy_err_code = PHY_ERROR_UNKNOWN; return 0; } void ath10k_wmi_event_phyerr(struct ath10k *ar, struct sk_buff *skb) { struct wmi_phyerr_hdr_arg hdr_arg = {}; struct wmi_phyerr_ev_arg phyerr_arg = {}; const void *phyerr; u32 count, i, buf_len, phy_err_code; u64 tsf; int left_len, ret; ATH10K_DFS_STAT_INC(ar, phy_errors); ret = ath10k_wmi_pull_phyerr_hdr(ar, skb, &hdr_arg); if (ret) { ath10k_warn(ar, "failed to parse phyerr event hdr: %d\n", ret); return; } /* Check number of included events */ count = hdr_arg.num_phyerrs; left_len = hdr_arg.buf_len; tsf = hdr_arg.tsf_u32; tsf <<= 32; tsf |= hdr_arg.tsf_l32; ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event phyerr count %d tsf64 0x%llX\n", count, tsf); phyerr = hdr_arg.phyerrs; for (i = 0; i < count; i++) { ret = ath10k_wmi_pull_phyerr(ar, phyerr, left_len, &phyerr_arg); if (ret) { ath10k_warn(ar, "failed to parse phyerr event (%d)\n", i); return; } left_len -= phyerr_arg.hdr_len; buf_len = phyerr_arg.buf_len; phy_err_code = phyerr_arg.phy_err_code; if (left_len < buf_len) { ath10k_warn(ar, "single event (%d) wrong buf len\n", i); return; } left_len -= buf_len; switch (phy_err_code) { case PHY_ERROR_RADAR: ath10k_wmi_event_dfs(ar, &phyerr_arg, tsf); break; case PHY_ERROR_SPECTRAL_SCAN: ath10k_wmi_event_spectral_scan(ar, &phyerr_arg, tsf); break; case PHY_ERROR_FALSE_RADAR_EXT: ath10k_wmi_event_dfs(ar, &phyerr_arg, tsf); ath10k_wmi_event_spectral_scan(ar, &phyerr_arg, tsf); break; default: break; } phyerr = phyerr + phyerr_arg.hdr_len + buf_len; } } static int ath10k_wmi_10_4_op_pull_dfs_status_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_dfs_status_ev_arg *arg) { struct wmi_dfs_status_ev_arg *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; arg->status = ev->status; return 0; } static void ath10k_wmi_event_dfs_status_check(struct ath10k *ar, struct sk_buff *skb) { struct wmi_dfs_status_ev_arg status_arg = {}; int ret; ret = ath10k_wmi_pull_dfs_status(ar, skb, &status_arg); if (ret) { ath10k_warn(ar, "failed to parse dfs status event: %d\n", ret); return; } ath10k_dbg(ar, ATH10K_DBG_REGULATORY, "dfs status event received from fw: %d\n", status_arg.status); /* Even in case of radar detection failure we follow the same * behaviour as if radar is detected i.e to switch to a different * channel. */ if (status_arg.status == WMI_HW_RADAR_DETECTED || status_arg.status == WMI_RADAR_DETECTION_FAIL) ath10k_radar_detected(ar); complete(&ar->wmi.radar_confirm); } void ath10k_wmi_event_roam(struct ath10k *ar, struct sk_buff *skb) { struct wmi_roam_ev_arg arg = {}; int ret; u32 vdev_id; u32 reason; s32 rssi; ret = ath10k_wmi_pull_roam_ev(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse roam event: %d\n", ret); return; } vdev_id = __le32_to_cpu(arg.vdev_id); reason = __le32_to_cpu(arg.reason); rssi = __le32_to_cpu(arg.rssi); rssi += WMI_SPECTRAL_NOISE_FLOOR_REF_DEFAULT; ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi roam event vdev %u reason 0x%08x rssi %d\n", vdev_id, reason, rssi); if (reason >= WMI_ROAM_REASON_MAX) ath10k_warn(ar, "ignoring unknown roam event reason %d on vdev %i\n", reason, vdev_id); switch (reason) { case WMI_ROAM_REASON_BEACON_MISS: ath10k_mac_handle_beacon_miss(ar, vdev_id); break; case WMI_ROAM_REASON_BETTER_AP: case WMI_ROAM_REASON_LOW_RSSI: case WMI_ROAM_REASON_SUITABLE_AP_FOUND: case WMI_ROAM_REASON_HO_FAILED: ath10k_warn(ar, "ignoring not implemented roam event reason %d on vdev %i\n", reason, vdev_id); break; } } void ath10k_wmi_event_profile_match(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_PROFILE_MATCH\n"); } void ath10k_wmi_event_debug_print(struct ath10k *ar, struct sk_buff *skb) { char buf[101], c; int i; for (i = 0; i < sizeof(buf) - 1; i++) { if (i >= skb->len) break; c = skb->data[i]; if (c == '\0') break; if (isascii(c) && isprint(c)) buf[i] = c; else buf[i] = '.'; } if (i == sizeof(buf) - 1) ath10k_warn(ar, "wmi debug print truncated: %d\n", skb->len); /* for some reason the debug prints end with \n, remove that */ if (skb->data[i - 1] == '\n') i--; /* the last byte is always reserved for the null character */ buf[i] = '\0'; ath10k_dbg(ar, ATH10K_DBG_WMI_PRINT, "wmi print '%s'\n", buf); } void ath10k_wmi_event_pdev_qvit(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_PDEV_QVIT_EVENTID\n"); } void ath10k_wmi_event_wlan_profile_data(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_WLAN_PROFILE_DATA_EVENTID\n"); } void ath10k_wmi_event_rtt_measurement_report(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_RTT_MEASUREMENT_REPORT_EVENTID\n"); } void ath10k_wmi_event_tsf_measurement_report(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_TSF_MEASUREMENT_REPORT_EVENTID\n"); } void ath10k_wmi_event_rtt_error_report(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_RTT_ERROR_REPORT_EVENTID\n"); } void ath10k_wmi_event_wow_wakeup_host(struct ath10k *ar, struct sk_buff *skb) { struct wmi_wow_ev_arg ev = {}; int ret; complete(&ar->wow.wakeup_completed); ret = ath10k_wmi_pull_wow_event(ar, skb, &ev); if (ret) { ath10k_warn(ar, "failed to parse wow wakeup event: %d\n", ret); return; } ath10k_dbg(ar, ATH10K_DBG_WMI, "wow wakeup host reason %s\n", wow_reason(ev.wake_reason)); } void ath10k_wmi_event_dcs_interference(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_DCS_INTERFERENCE_EVENTID\n"); } static u8 ath10k_tpc_config_get_rate(struct ath10k *ar, struct wmi_pdev_tpc_config_event *ev, u32 rate_idx, u32 num_chains, u32 rate_code, u8 type) { u8 tpc, num_streams, preamble, ch, stm_idx; num_streams = ATH10K_HW_NSS(rate_code); preamble = ATH10K_HW_PREAMBLE(rate_code); ch = num_chains - 1; tpc = min_t(u8, ev->rates_array[rate_idx], ev->max_reg_allow_pow[ch]); if (__le32_to_cpu(ev->num_tx_chain) <= 1) goto out; if (preamble == WMI_RATE_PREAMBLE_CCK) goto out; stm_idx = num_streams - 1; if (num_chains <= num_streams) goto out; switch (type) { case WMI_TPC_TABLE_TYPE_STBC: tpc = min_t(u8, tpc, ev->max_reg_allow_pow_agstbc[ch - 1][stm_idx]); break; case WMI_TPC_TABLE_TYPE_TXBF: tpc = min_t(u8, tpc, ev->max_reg_allow_pow_agtxbf[ch - 1][stm_idx]); break; case WMI_TPC_TABLE_TYPE_CDD: tpc = min_t(u8, tpc, ev->max_reg_allow_pow_agcdd[ch - 1][stm_idx]); break; default: ath10k_warn(ar, "unknown wmi tpc table type: %d\n", type); tpc = 0; break; } out: return tpc; } static void ath10k_tpc_config_disp_tables(struct ath10k *ar, struct wmi_pdev_tpc_config_event *ev, struct ath10k_tpc_stats *tpc_stats, u8 *rate_code, u16 *pream_table, u8 type) { u32 i, j, pream_idx, flags; u8 tpc[WMI_TPC_TX_N_CHAIN]; char tpc_value[WMI_TPC_TX_N_CHAIN * WMI_TPC_BUF_SIZE]; char buff[WMI_TPC_BUF_SIZE]; flags = __le32_to_cpu(ev->flags); switch (type) { case WMI_TPC_TABLE_TYPE_CDD: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_CDD)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "CDD not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; case WMI_TPC_TABLE_TYPE_STBC: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_STBC)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "STBC not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; case WMI_TPC_TABLE_TYPE_TXBF: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_TXBF)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "TXBF not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; default: ath10k_dbg(ar, ATH10K_DBG_WMI, "invalid table type in wmi tpc event: %d\n", type); return; } pream_idx = 0; for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++; for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_tpc_config_get_rate(ar, ev, i, j + 1, rate_code[i], type); snprintf(buff, sizeof(buff), "%8d ", tpc[j]); strlcat(tpc_value, buff, sizeof(tpc_value)); } tpc_stats->tpc_table[type].pream_idx[i] = pream_idx; tpc_stats->tpc_table[type].rate_code[i] = rate_code[i]; memcpy(tpc_stats->tpc_table[type].tpc_value[i], tpc_value, sizeof(tpc_value)); } } void ath10k_wmi_tpc_config_get_rate_code(u8 *rate_code, u16 *pream_table, u32 num_tx_chain) { u32 i, j, pream_idx; u8 rate_idx; /* Create the rate code table based on the chains supported */ rate_idx = 0; pream_idx = 0; /* Fill CCK rate code */ for (i = 0; i < 4; i++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(i, 0, WMI_RATE_PREAMBLE_CCK); rate_idx++; } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill OFDM rate code */ for (i = 0; i < 8; i++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(i, 0, WMI_RATE_PREAMBLE_OFDM); rate_idx++; } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill HT20 rate code */ for (i = 0; i < num_tx_chain; i++) { for (j = 0; j < 8; j++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(j, i, WMI_RATE_PREAMBLE_HT); rate_idx++; } } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill HT40 rate code */ for (i = 0; i < num_tx_chain; i++) { for (j = 0; j < 8; j++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(j, i, WMI_RATE_PREAMBLE_HT); rate_idx++; } } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill VHT20 rate code */ for (i = 0; i < num_tx_chain; i++) { for (j = 0; j < 10; j++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(j, i, WMI_RATE_PREAMBLE_VHT); rate_idx++; } } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill VHT40 rate code */ for (i = 0; i < num_tx_chain; i++) { for (j = 0; j < 10; j++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(j, i, WMI_RATE_PREAMBLE_VHT); rate_idx++; } } pream_table[pream_idx] = rate_idx; pream_idx++; /* Fill VHT80 rate code */ for (i = 0; i < num_tx_chain; i++) { for (j = 0; j < 10; j++) { rate_code[rate_idx] = ATH10K_HW_RATECODE(j, i, WMI_RATE_PREAMBLE_VHT); rate_idx++; } } pream_table[pream_idx] = rate_idx; pream_idx++; rate_code[rate_idx++] = ATH10K_HW_RATECODE(0, 0, WMI_RATE_PREAMBLE_CCK); rate_code[rate_idx++] = ATH10K_HW_RATECODE(0, 0, WMI_RATE_PREAMBLE_OFDM); rate_code[rate_idx++] = ATH10K_HW_RATECODE(0, 0, WMI_RATE_PREAMBLE_CCK); rate_code[rate_idx++] = ATH10K_HW_RATECODE(0, 0, WMI_RATE_PREAMBLE_OFDM); rate_code[rate_idx++] = ATH10K_HW_RATECODE(0, 0, WMI_RATE_PREAMBLE_OFDM); pream_table[pream_idx] = ATH10K_TPC_PREAM_TABLE_END; } void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) { u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_config_event *ev; struct ath10k_tpc_stats *tpc_stats; ev = (struct wmi_pdev_tpc_config_event *)skb->data; num_tx_chain = __le32_to_cpu(ev->num_tx_chain); if (num_tx_chain > WMI_TPC_TX_N_CHAIN) { ath10k_warn(ar, "number of tx chain is %d greater than TPC configured tx chain %d\n", num_tx_chain, WMI_TPC_TX_N_CHAIN); return; } rate_max = __le32_to_cpu(ev->rate_max); if (rate_max > WMI_TPC_RATE_MAX) { ath10k_warn(ar, "number of rate is %d greater than TPC configured rate %d\n", rate_max, WMI_TPC_RATE_MAX); rate_max = WMI_TPC_RATE_MAX; } tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return; ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table, num_tx_chain); tpc_stats->chan_freq = __le32_to_cpu(ev->chan_freq); tpc_stats->phy_mode = __le32_to_cpu(ev->phy_mode); tpc_stats->ctl = __le32_to_cpu(ev->ctl); tpc_stats->reg_domain = __le32_to_cpu(ev->reg_domain); tpc_stats->twice_antenna_gain = a_sle32_to_cpu(ev->twice_antenna_gain); tpc_stats->twice_antenna_reduction = __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); tpc_stats->num_tx_chain = num_tx_chain; tpc_stats->rate_max = rate_max; ath10k_tpc_config_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_CDD); ath10k_tpc_config_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_STBC); ath10k_tpc_config_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_TXBF); ath10k_debug_tpc_stats_process(ar, tpc_stats); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event tpc config channel %d mode %d ctl %d regd %d gain %d %d limit %d max_power %d tx_chanins %d rates %d\n", __le32_to_cpu(ev->chan_freq), __le32_to_cpu(ev->phy_mode), __le32_to_cpu(ev->ctl), __le32_to_cpu(ev->reg_domain), a_sle32_to_cpu(ev->twice_antenna_gain), __le32_to_cpu(ev->twice_antenna_reduction), __le32_to_cpu(ev->power_limit), __le32_to_cpu(ev->twice_max_rd_power) / 2, __le32_to_cpu(ev->num_tx_chain), __le32_to_cpu(ev->rate_max)); } static u8 ath10k_wmi_tpc_final_get_rate(struct ath10k *ar, struct wmi_pdev_tpc_final_table_event *ev, u32 rate_idx, u32 num_chains, u32 rate_code, u8 type, u32 pream_idx) { u8 tpc, num_streams, preamble, ch, stm_idx; s8 pow_agcdd, pow_agstbc, pow_agtxbf; int pream; num_streams = ATH10K_HW_NSS(rate_code); preamble = ATH10K_HW_PREAMBLE(rate_code); ch = num_chains - 1; stm_idx = num_streams - 1; pream = -1; if (__le32_to_cpu(ev->chan_freq) <= 2483) { switch (pream_idx) { case WMI_TPC_PREAM_2GHZ_CCK: pream = 0; break; case WMI_TPC_PREAM_2GHZ_OFDM: pream = 1; break; case WMI_TPC_PREAM_2GHZ_HT20: case WMI_TPC_PREAM_2GHZ_VHT20: pream = 2; break; case WMI_TPC_PREAM_2GHZ_HT40: case WMI_TPC_PREAM_2GHZ_VHT40: pream = 3; break; case WMI_TPC_PREAM_2GHZ_VHT80: pream = 4; break; default: pream = -1; break; } } if (__le32_to_cpu(ev->chan_freq) >= 5180) { switch (pream_idx) { case WMI_TPC_PREAM_5GHZ_OFDM: pream = 0; break; case WMI_TPC_PREAM_5GHZ_HT20: case WMI_TPC_PREAM_5GHZ_VHT20: pream = 1; break; case WMI_TPC_PREAM_5GHZ_HT40: case WMI_TPC_PREAM_5GHZ_VHT40: pream = 2; break; case WMI_TPC_PREAM_5GHZ_VHT80: pream = 3; break; case WMI_TPC_PREAM_5GHZ_HTCUP: pream = 4; break; default: pream = -1; break; } } if (pream == -1) { ath10k_warn(ar, "unknown wmi tpc final index and frequency: %u, %u\n", pream_idx, __le32_to_cpu(ev->chan_freq)); tpc = 0; goto out; } if (pream == 4) tpc = min_t(u8, ev->rates_array[rate_idx], ev->max_reg_allow_pow[ch]); else tpc = min_t(u8, min_t(u8, ev->rates_array[rate_idx], ev->max_reg_allow_pow[ch]), ev->ctl_power_table[0][pream][stm_idx]); if (__le32_to_cpu(ev->num_tx_chain) <= 1) goto out; if (preamble == WMI_RATE_PREAMBLE_CCK) goto out; if (num_chains <= num_streams) goto out; switch (type) { case WMI_TPC_TABLE_TYPE_STBC: pow_agstbc = ev->max_reg_allow_pow_agstbc[ch - 1][stm_idx]; if (pream == 4) tpc = min_t(u8, tpc, pow_agstbc); else tpc = min_t(u8, min_t(u8, tpc, pow_agstbc), ev->ctl_power_table[0][pream][stm_idx]); break; case WMI_TPC_TABLE_TYPE_TXBF: pow_agtxbf = ev->max_reg_allow_pow_agtxbf[ch - 1][stm_idx]; if (pream == 4) tpc = min_t(u8, tpc, pow_agtxbf); else tpc = min_t(u8, min_t(u8, tpc, pow_agtxbf), ev->ctl_power_table[1][pream][stm_idx]); break; case WMI_TPC_TABLE_TYPE_CDD: pow_agcdd = ev->max_reg_allow_pow_agcdd[ch - 1][stm_idx]; if (pream == 4) tpc = min_t(u8, tpc, pow_agcdd); else tpc = min_t(u8, min_t(u8, tpc, pow_agcdd), ev->ctl_power_table[0][pream][stm_idx]); break; default: ath10k_warn(ar, "unknown wmi tpc final table type: %d\n", type); tpc = 0; break; } out: return tpc; } static void ath10k_wmi_tpc_stats_final_disp_tables(struct ath10k *ar, struct wmi_pdev_tpc_final_table_event *ev, struct ath10k_tpc_stats_final *tpc_stats, u8 *rate_code, u16 *pream_table, u8 type) { u32 i, j, pream_idx, flags; u8 tpc[WMI_TPC_TX_N_CHAIN]; char tpc_value[WMI_TPC_TX_N_CHAIN * WMI_TPC_BUF_SIZE]; char buff[WMI_TPC_BUF_SIZE]; flags = __le32_to_cpu(ev->flags); switch (type) { case WMI_TPC_TABLE_TYPE_CDD: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_CDD)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "CDD not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; case WMI_TPC_TABLE_TYPE_STBC: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_STBC)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "STBC not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; case WMI_TPC_TABLE_TYPE_TXBF: if (!(flags & WMI_TPC_CONFIG_EVENT_FLAG_TABLE_TXBF)) { ath10k_dbg(ar, ATH10K_DBG_WMI, "TXBF not supported\n"); tpc_stats->flag[type] = ATH10K_TPC_TABLE_TYPE_FLAG; return; } break; default: ath10k_dbg(ar, ATH10K_DBG_WMI, "invalid table type in wmi tpc event: %d\n", type); return; } pream_idx = 0; for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++; for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_wmi_tpc_final_get_rate(ar, ev, i, j + 1, rate_code[i], type, pream_idx); snprintf(buff, sizeof(buff), "%8d ", tpc[j]); strlcat(tpc_value, buff, sizeof(tpc_value)); } tpc_stats->tpc_table_final[type].pream_idx[i] = pream_idx; tpc_stats->tpc_table_final[type].rate_code[i] = rate_code[i]; memcpy(tpc_stats->tpc_table_final[type].tpc_value[i], tpc_value, sizeof(tpc_value)); } } void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) { u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_FINAL_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_final_table_event *ev; struct ath10k_tpc_stats_final *tpc_stats; ev = (struct wmi_pdev_tpc_final_table_event *)skb->data; num_tx_chain = __le32_to_cpu(ev->num_tx_chain); if (num_tx_chain > WMI_TPC_TX_N_CHAIN) { ath10k_warn(ar, "number of tx chain is %d greater than TPC final configured tx chain %d\n", num_tx_chain, WMI_TPC_TX_N_CHAIN); return; } rate_max = __le32_to_cpu(ev->rate_max); if (rate_max > WMI_TPC_FINAL_RATE_MAX) { ath10k_warn(ar, "number of rate is %d greater than TPC final configured rate %d\n", rate_max, WMI_TPC_FINAL_RATE_MAX); rate_max = WMI_TPC_FINAL_RATE_MAX; } tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return; ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table, num_tx_chain); tpc_stats->chan_freq = __le32_to_cpu(ev->chan_freq); tpc_stats->phy_mode = __le32_to_cpu(ev->phy_mode); tpc_stats->ctl = __le32_to_cpu(ev->ctl); tpc_stats->reg_domain = __le32_to_cpu(ev->reg_domain); tpc_stats->twice_antenna_gain = a_sle32_to_cpu(ev->twice_antenna_gain); tpc_stats->twice_antenna_reduction = __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); tpc_stats->num_tx_chain = num_tx_chain; tpc_stats->rate_max = rate_max; ath10k_wmi_tpc_stats_final_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_CDD); ath10k_wmi_tpc_stats_final_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_STBC); ath10k_wmi_tpc_stats_final_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, WMI_TPC_TABLE_TYPE_TXBF); ath10k_debug_tpc_stats_final_process(ar, tpc_stats); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event tpc final table channel %d mode %d ctl %d regd %d gain %d %d limit %d max_power %d tx_chanins %d rates %d\n", __le32_to_cpu(ev->chan_freq), __le32_to_cpu(ev->phy_mode), __le32_to_cpu(ev->ctl), __le32_to_cpu(ev->reg_domain), a_sle32_to_cpu(ev->twice_antenna_gain), __le32_to_cpu(ev->twice_antenna_reduction), __le32_to_cpu(ev->power_limit), __le32_to_cpu(ev->twice_max_rd_power) / 2, __le32_to_cpu(ev->num_tx_chain), __le32_to_cpu(ev->rate_max)); } static void ath10k_wmi_handle_tdls_peer_event(struct ath10k *ar, struct sk_buff *skb) { struct wmi_tdls_peer_event *ev; struct ath10k_peer *peer; struct ath10k_vif *arvif; int vdev_id; int peer_status; int peer_reason; u8 reason; if (skb->len < sizeof(*ev)) { ath10k_err(ar, "received tdls peer event with invalid size (%d bytes)\n", skb->len); return; } ev = (struct wmi_tdls_peer_event *)skb->data; vdev_id = __le32_to_cpu(ev->vdev_id); peer_status = __le32_to_cpu(ev->peer_status); peer_reason = __le32_to_cpu(ev->peer_reason); spin_lock_bh(&ar->data_lock); peer = ath10k_peer_find(ar, vdev_id, ev->peer_macaddr.addr); spin_unlock_bh(&ar->data_lock); if (!peer) { ath10k_warn(ar, "failed to find peer entry for %pM\n", ev->peer_macaddr.addr); return; } switch (peer_status) { case WMI_TDLS_SHOULD_TEARDOWN: switch (peer_reason) { case WMI_TDLS_TEARDOWN_REASON_PTR_TIMEOUT: case WMI_TDLS_TEARDOWN_REASON_NO_RESPONSE: case WMI_TDLS_TEARDOWN_REASON_RSSI: reason = WLAN_REASON_TDLS_TEARDOWN_UNREACHABLE; break; default: reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; break; } arvif = ath10k_get_arvif(ar, vdev_id); if (!arvif) { ath10k_warn(ar, "received tdls peer event for invalid vdev id %u\n", vdev_id); return; } ieee80211_tdls_oper_request(arvif->vif, ev->peer_macaddr.addr, NL80211_TDLS_TEARDOWN, reason, GFP_ATOMIC); ath10k_dbg(ar, ATH10K_DBG_WMI, "received tdls teardown event for peer %pM reason %u\n", ev->peer_macaddr.addr, peer_reason); break; default: ath10k_dbg(ar, ATH10K_DBG_WMI, "received unknown tdls peer event %u\n", peer_status); break; } } static void ath10k_wmi_event_peer_sta_ps_state_chg(struct ath10k *ar, struct sk_buff *skb) { struct wmi_peer_sta_ps_state_chg_event *ev; struct ieee80211_sta *sta; struct ath10k_sta *arsta; u8 peer_addr[ETH_ALEN]; lockdep_assert_held(&ar->data_lock); ev = (struct wmi_peer_sta_ps_state_chg_event *)skb->data; ether_addr_copy(peer_addr, ev->peer_macaddr.addr); rcu_read_lock(); sta = ieee80211_find_sta_by_ifaddr(ar->hw, peer_addr, NULL); if (!sta) { ath10k_warn(ar, "failed to find station entry %pM\n", peer_addr); goto exit; } arsta = (struct ath10k_sta *)sta->drv_priv; arsta->peer_ps_state = __le32_to_cpu(ev->peer_ps_state); exit: rcu_read_unlock(); } void ath10k_wmi_event_pdev_ftm_intg(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_PDEV_FTM_INTG_EVENTID\n"); } void ath10k_wmi_event_gtk_offload_status(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_GTK_OFFLOAD_STATUS_EVENTID\n"); } void ath10k_wmi_event_gtk_rekey_fail(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_GTK_REKEY_FAIL_EVENTID\n"); } void ath10k_wmi_event_delba_complete(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_TX_DELBA_COMPLETE_EVENTID\n"); } void ath10k_wmi_event_addba_complete(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_TX_ADDBA_COMPLETE_EVENTID\n"); } void ath10k_wmi_event_vdev_install_key_complete(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_INSTALL_KEY_COMPLETE_EVENTID\n"); } void ath10k_wmi_event_inst_rssi_stats(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_INST_RSSI_STATS_EVENTID\n"); } void ath10k_wmi_event_vdev_standby_req(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_STANDBY_REQ_EVENTID\n"); } void ath10k_wmi_event_vdev_resume_req(struct ath10k *ar, struct sk_buff *skb) { ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_RESUME_REQ_EVENTID\n"); } static int ath10k_wmi_alloc_chunk(struct ath10k *ar, u32 req_id, u32 num_units, u32 unit_len) { dma_addr_t paddr; u32 pool_size; int idx = ar->wmi.num_mem_chunks; void *vaddr; pool_size = num_units * round_up(unit_len, 4); vaddr = dma_alloc_coherent(ar->dev, pool_size, &paddr, GFP_KERNEL); if (!vaddr) return -ENOMEM; ar->wmi.mem_chunks[idx].vaddr = vaddr; ar->wmi.mem_chunks[idx].paddr = paddr; ar->wmi.mem_chunks[idx].len = pool_size; ar->wmi.mem_chunks[idx].req_id = req_id; ar->wmi.num_mem_chunks++; return num_units; } static int ath10k_wmi_alloc_host_mem(struct ath10k *ar, u32 req_id, u32 num_units, u32 unit_len) { int ret; while (num_units) { ret = ath10k_wmi_alloc_chunk(ar, req_id, num_units, unit_len); if (ret < 0) return ret; num_units -= ret; } return 0; } static bool ath10k_wmi_is_host_mem_allocated(struct ath10k *ar, const struct wlan_host_mem_req **mem_reqs, u32 num_mem_reqs) { u32 req_id, num_units, unit_size, num_unit_info; u32 pool_size; int i, j; bool found; if (ar->wmi.num_mem_chunks != num_mem_reqs) return false; for (i = 0; i < num_mem_reqs; ++i) { req_id = __le32_to_cpu(mem_reqs[i]->req_id); num_units = __le32_to_cpu(mem_reqs[i]->num_units); unit_size = __le32_to_cpu(mem_reqs[i]->unit_size); num_unit_info = __le32_to_cpu(mem_reqs[i]->num_unit_info); if (num_unit_info & NUM_UNITS_IS_NUM_ACTIVE_PEERS) { if (ar->num_active_peers) num_units = ar->num_active_peers + 1; else num_units = ar->max_num_peers + 1; } else if (num_unit_info & NUM_UNITS_IS_NUM_PEERS) { num_units = ar->max_num_peers + 1; } else if (num_unit_info & NUM_UNITS_IS_NUM_VDEVS) { num_units = ar->max_num_vdevs + 1; } found = false; for (j = 0; j < ar->wmi.num_mem_chunks; j++) { if (ar->wmi.mem_chunks[j].req_id == req_id) { pool_size = num_units * round_up(unit_size, 4); if (ar->wmi.mem_chunks[j].len == pool_size) { found = true; break; } } } if (!found) return false; } return true; } static int ath10k_wmi_main_op_pull_svc_rdy_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_svc_rdy_ev_arg *arg) { struct wmi_service_ready_event *ev; size_t i, n; if (skb->len < sizeof(*ev)) return -EPROTO; ev = (void *)skb->data; skb_pull(skb, sizeof(*ev)); arg->min_tx_power = ev->hw_min_tx_power; arg->max_tx_power = ev->hw_max_tx_power; arg->ht_cap = ev->ht_cap_info; arg->vht_cap = ev->vht_cap_info; arg->vht_supp_mcs = ev->vht_supp_mcs; arg->sw_ver0 = ev->sw_version; arg->sw_ver1 = ev->sw_version_1; arg->phy_capab = ev->phy_capability; arg->num_rf_chains = ev->num_rf_chains; arg->eeprom_rd = ev->hal_reg_capabilities.eeprom_rd; arg->low_2ghz_chan = ev->hal_reg_capabilities.low_2ghz_chan; arg->high_2ghz_chan = ev->hal_reg_capabilities.high_2ghz_chan; arg->low_5ghz_chan = ev->hal_reg_capabilities.low_5ghz_chan; arg->high_5ghz_chan = ev->hal_reg_capabilities.high_5ghz_chan; arg->num_mem_reqs = ev->num_mem_reqs; arg->service_map = ev->wmi_service_bitmap; arg->service_map_len = sizeof(ev->wmi_service_bitmap); n = min_t(size_t, __le32_to_cpu(arg->num_mem_reqs), ARRAY_SIZE(arg->mem_reqs)); for (i = 0; i < n; i++) arg->mem_reqs[i] = &ev->mem_reqs[i]; if (skb->len < __le32_to_cpu(arg->num_mem_reqs) * sizeof(arg->mem_reqs[0])) return -EPROTO; return 0; } static int ath10k_wmi_10x_op_pull_svc_rdy_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_svc_rdy_ev_arg *arg) { struct wmi_10x_service_ready_event *ev; int i, n; if (skb->len < sizeof(*ev)) return -EPROTO; ev = (void *)skb->data; skb_pull(skb, sizeof(*ev)); arg->min_tx_power = ev->hw_min_tx_power; arg->max_tx_power = ev->hw_max_tx_power; arg->ht_cap = ev->ht_cap_info; arg->vht_cap = ev->vht_cap_info; arg->vht_supp_mcs = ev->vht_supp_mcs; arg->sw_ver0 = ev->sw_version; arg->phy_capab = ev->phy_capability; arg->num_rf_chains = ev->num_rf_chains; arg->eeprom_rd = ev->hal_reg_capabilities.eeprom_rd; arg->low_2ghz_chan = ev->hal_reg_capabilities.low_2ghz_chan; arg->high_2ghz_chan = ev->hal_reg_capabilities.high_2ghz_chan; arg->low_5ghz_chan = ev->hal_reg_capabilities.low_5ghz_chan; arg->high_5ghz_chan = ev->hal_reg_capabilities.high_5ghz_chan; arg->num_mem_reqs = ev->num_mem_reqs; arg->service_map = ev->wmi_service_bitmap; arg->service_map_len = sizeof(ev->wmi_service_bitmap); /* Deliberately skipping ev->sys_cap_info as WMI and WMI-TLV have * different values. We would need a translation to handle that, * but as we don't currently need anything from sys_cap_info from * WMI interface (only from WMI-TLV) safest it to skip it. */ n = min_t(size_t, __le32_to_cpu(arg->num_mem_reqs), ARRAY_SIZE(arg->mem_reqs)); for (i = 0; i < n; i++) arg->mem_reqs[i] = &ev->mem_reqs[i]; if (skb->len < __le32_to_cpu(arg->num_mem_reqs) * sizeof(arg->mem_reqs[0])) return -EPROTO; return 0; } static void ath10k_wmi_event_service_ready_work(struct work_struct *work) { struct ath10k *ar = container_of(work, struct ath10k, svc_rdy_work); struct sk_buff *skb = ar->svc_rdy_skb; struct wmi_svc_rdy_ev_arg arg = {}; u32 num_units, req_id, unit_size, num_mem_reqs, num_unit_info, i; int ret; bool allocated; if (!skb) { ath10k_warn(ar, "invalid service ready event skb\n"); return; } ret = ath10k_wmi_pull_svc_rdy(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse service ready: %d\n", ret); return; } ath10k_wmi_map_svc(ar, arg.service_map, ar->wmi.svc_map, arg.service_map_len); ar->hw_min_tx_power = __le32_to_cpu(arg.min_tx_power); ar->hw_max_tx_power = __le32_to_cpu(arg.max_tx_power); ar->ht_cap_info = __le32_to_cpu(arg.ht_cap); ar->vht_cap_info = __le32_to_cpu(arg.vht_cap); ar->vht_supp_mcs = __le32_to_cpu(arg.vht_supp_mcs); ar->fw_version_major = (__le32_to_cpu(arg.sw_ver0) & 0xff000000) >> 24; ar->fw_version_minor = (__le32_to_cpu(arg.sw_ver0) & 0x00ffffff); ar->fw_version_release = (__le32_to_cpu(arg.sw_ver1) & 0xffff0000) >> 16; ar->fw_version_build = (__le32_to_cpu(arg.sw_ver1) & 0x0000ffff); ar->phy_capability = __le32_to_cpu(arg.phy_capab); ar->num_rf_chains = __le32_to_cpu(arg.num_rf_chains); ar->hw_eeprom_rd = __le32_to_cpu(arg.eeprom_rd); ar->low_2ghz_chan = __le32_to_cpu(arg.low_2ghz_chan); ar->high_2ghz_chan = __le32_to_cpu(arg.high_2ghz_chan); ar->low_5ghz_chan = __le32_to_cpu(arg.low_5ghz_chan); ar->high_5ghz_chan = __le32_to_cpu(arg.high_5ghz_chan); ar->sys_cap_info = __le32_to_cpu(arg.sys_cap_info); ath10k_dbg_dump(ar, ATH10K_DBG_WMI, NULL, "wmi svc: ", arg.service_map, arg.service_map_len); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi sys_cap_info 0x%x\n", ar->sys_cap_info); if (ar->num_rf_chains > ar->max_spatial_stream) { ath10k_warn(ar, "hardware advertises support for more spatial streams than it should (%d > %d)\n", ar->num_rf_chains, ar->max_spatial_stream); ar->num_rf_chains = ar->max_spatial_stream; } if (!ar->cfg_tx_chainmask) { ar->cfg_tx_chainmask = (1 << ar->num_rf_chains) - 1; ar->cfg_rx_chainmask = (1 << ar->num_rf_chains) - 1; } if (strlen(ar->hw->wiphy->fw_version) == 0) { snprintf(ar->hw->wiphy->fw_version, sizeof(ar->hw->wiphy->fw_version), "%u.%u.%u.%u", ar->fw_version_major, ar->fw_version_minor, ar->fw_version_release, ar->fw_version_build); } num_mem_reqs = __le32_to_cpu(arg.num_mem_reqs); if (num_mem_reqs > WMI_MAX_MEM_REQS) { ath10k_warn(ar, "requested memory chunks number (%d) exceeds the limit\n", num_mem_reqs); return; } if (test_bit(WMI_SERVICE_PEER_CACHING, ar->wmi.svc_map)) { if (test_bit(ATH10K_FW_FEATURE_PEER_FLOW_CONTROL, ar->running_fw->fw_file.fw_features)) ar->num_active_peers = TARGET_10_4_QCACHE_ACTIVE_PEERS_PFC + ar->max_num_vdevs; else ar->num_active_peers = TARGET_10_4_QCACHE_ACTIVE_PEERS + ar->max_num_vdevs; ar->max_num_peers = TARGET_10_4_NUM_QCACHE_PEERS_MAX + ar->max_num_vdevs; ar->num_tids = ar->num_active_peers * 2; ar->max_num_stations = TARGET_10_4_NUM_QCACHE_PEERS_MAX; } /* TODO: Adjust max peer count for cases like WMI_SERVICE_RATECTRL_CACHE * and WMI_SERVICE_IRAM_TIDS, etc. */ allocated = ath10k_wmi_is_host_mem_allocated(ar, arg.mem_reqs, num_mem_reqs); if (allocated) goto skip_mem_alloc; /* Either this event is received during boot time or there is a change * in memory requirement from firmware when compared to last request. * Free any old memory and do a fresh allocation based on the current * memory requirement. */ ath10k_wmi_free_host_mem(ar); for (i = 0; i < num_mem_reqs; ++i) { req_id = __le32_to_cpu(arg.mem_reqs[i]->req_id); num_units = __le32_to_cpu(arg.mem_reqs[i]->num_units); unit_size = __le32_to_cpu(arg.mem_reqs[i]->unit_size); num_unit_info = __le32_to_cpu(arg.mem_reqs[i]->num_unit_info); if (num_unit_info & NUM_UNITS_IS_NUM_ACTIVE_PEERS) { if (ar->num_active_peers) num_units = ar->num_active_peers + 1; else num_units = ar->max_num_peers + 1; } else if (num_unit_info & NUM_UNITS_IS_NUM_PEERS) { /* number of units to allocate is number of * peers, 1 extra for self peer on target * this needs to be tied, host and target * can get out of sync */ num_units = ar->max_num_peers + 1; } else if (num_unit_info & NUM_UNITS_IS_NUM_VDEVS) { num_units = ar->max_num_vdevs + 1; } ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mem_req_id %d num_units %d num_unit_info %d unit size %d actual units %d\n", req_id, __le32_to_cpu(arg.mem_reqs[i]->num_units), num_unit_info, unit_size, num_units); ret = ath10k_wmi_alloc_host_mem(ar, req_id, num_units, unit_size); if (ret) return; } skip_mem_alloc: ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event service ready min_tx_power 0x%08x max_tx_power 0x%08x ht_cap 0x%08x vht_cap 0x%08x vht_supp_mcs 0x%08x sw_ver0 0x%08x sw_ver1 0x%08x fw_build 0x%08x phy_capab 0x%08x num_rf_chains 0x%08x eeprom_rd 0x%08x low_2ghz_chan %d high_2ghz_chan %d low_5ghz_chan %d high_5ghz_chan %d num_mem_reqs 0x%08x\n", __le32_to_cpu(arg.min_tx_power), __le32_to_cpu(arg.max_tx_power), __le32_to_cpu(arg.ht_cap), __le32_to_cpu(arg.vht_cap), __le32_to_cpu(arg.vht_supp_mcs), __le32_to_cpu(arg.sw_ver0), __le32_to_cpu(arg.sw_ver1), __le32_to_cpu(arg.fw_build), __le32_to_cpu(arg.phy_capab), __le32_to_cpu(arg.num_rf_chains), __le32_to_cpu(arg.eeprom_rd), __le32_to_cpu(arg.low_2ghz_chan), __le32_to_cpu(arg.high_2ghz_chan), __le32_to_cpu(arg.low_5ghz_chan), __le32_to_cpu(arg.high_5ghz_chan), __le32_to_cpu(arg.num_mem_reqs)); dev_kfree_skb(skb); ar->svc_rdy_skb = NULL; complete(&ar->wmi.service_ready); } void ath10k_wmi_event_service_ready(struct ath10k *ar, struct sk_buff *skb) { ar->svc_rdy_skb = skb; queue_work(ar->workqueue_aux, &ar->svc_rdy_work); } static int ath10k_wmi_op_pull_rdy_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_rdy_ev_arg *arg) { struct wmi_ready_event *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->sw_version = ev->sw_version; arg->abi_version = ev->abi_version; arg->status = ev->status; arg->mac_addr = ev->mac_addr.addr; return 0; } static int ath10k_wmi_op_pull_roam_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_roam_ev_arg *arg) { struct wmi_roam_ev *ev = (void *)skb->data; if (skb->len < sizeof(*ev)) return -EPROTO; skb_pull(skb, sizeof(*ev)); arg->vdev_id = ev->vdev_id; arg->reason = ev->reason; return 0; } static int ath10k_wmi_op_pull_echo_ev(struct ath10k *ar, struct sk_buff *skb, struct wmi_echo_ev_arg *arg) { struct wmi_echo_event *ev = (void *)skb->data; arg->value = ev->value; return 0; } int ath10k_wmi_event_ready(struct ath10k *ar, struct sk_buff *skb) { struct wmi_rdy_ev_arg arg = {}; int ret; ret = ath10k_wmi_pull_rdy(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse ready event: %d\n", ret); return ret; } ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event ready sw_version 0x%08x abi_version %u mac_addr %pM status %d\n", __le32_to_cpu(arg.sw_version), __le32_to_cpu(arg.abi_version), arg.mac_addr, __le32_to_cpu(arg.status)); if (is_zero_ether_addr(ar->mac_addr)) ether_addr_copy(ar->mac_addr, arg.mac_addr); complete(&ar->wmi.unified_ready); return 0; } void ath10k_wmi_event_service_available(struct ath10k *ar, struct sk_buff *skb) { int ret; struct wmi_svc_avail_ev_arg arg = {}; ret = ath10k_wmi_pull_svc_avail(ar, skb, &arg); if (ret) { ath10k_warn(ar, "failed to parse service available event: %d\n", ret); } /* * Initialization of "arg.service_map_ext_valid" to ZERO is necessary * for the below logic to work. */ if (arg.service_map_ext_valid) ath10k_wmi_map_svc_ext(ar, arg.service_map_ext, ar->wmi.svc_map, __le32_to_cpu(arg.service_map_ext_len)); } static int ath10k_wmi_event_temperature(struct ath10k *ar, struct sk_buff *skb) { const struct wmi_pdev_temperature_event *ev; ev = (struct wmi_pdev_temperature_event *)skb->data; if (WARN_ON(skb->len < sizeof(*ev))) return -EPROTO; ath10k_thermal_event_temperature(ar, __le32_to_cpu(ev->temperature)); return 0; } static int ath10k_wmi_event_pdev_bss_chan_info(struct ath10k *ar, struct sk_buff *skb) { struct wmi_pdev_bss_chan_info_event *ev; struct survey_info *survey; u64 busy, total, tx, rx, rx_bss; u32 freq, noise_floor; u32 cc_freq_hz = ar->hw_params.channel_counters_freq_hz; int idx; ev = (struct wmi_pdev_bss_chan_info_event *)skb->data; if (WARN_ON(skb->len < sizeof(*ev))) return -EPROTO; freq = __le32_to_cpu(ev->freq); noise_floor = __le32_to_cpu(ev->noise_floor); busy = __le64_to_cpu(ev->cycle_busy); total = __le64_to_cpu(ev->cycle_total); tx = __le64_to_cpu(ev->cycle_tx); rx = __le64_to_cpu(ev->cycle_rx); rx_bss = __le64_to_cpu(ev->cycle_rx_bss); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi event pdev bss chan info:\n freq: %d noise: %d cycle: busy %llu total %llu tx %llu rx %llu rx_bss %llu\n", freq, noise_floor, busy, total, tx, rx, rx_bss); spin_lock_bh(&ar->data_lock); idx = freq_to_idx(ar, freq); if (idx >= ARRAY_SIZE(ar->survey)) { ath10k_warn(ar, "bss chan info: invalid frequency %d (idx %d out of bounds)\n", freq, idx); goto exit; } survey = &ar->survey[idx]; survey->noise = noise_floor; survey->time = div_u64(total, cc_freq_hz); survey->time_busy = div_u64(busy, cc_freq_hz); survey->time_rx = div_u64(rx_bss, cc_freq_hz); survey->time_tx = div_u64(tx, cc_freq_hz); survey->filled |= (SURVEY_INFO_NOISE_DBM | SURVEY_INFO_TIME | SURVEY_INFO_TIME_BUSY | SURVEY_INFO_TIME_RX | SURVEY_INFO_TIME_TX); exit: spin_unlock_bh(&ar->data_lock); complete(&ar->bss_survey_done); return 0; } static inline void ath10k_wmi_queue_set_coverage_class_work(struct ath10k *ar) { if (ar->hw_params.hw_ops->set_coverage_class) { spin_lock_bh(&ar->data_lock); /* This call only ensures that the modified coverage class * persists in case the firmware sets the registers back to * their default value. So calling it is only necessary if the * coverage class has a non-zero value. */ if (ar->fw_coverage.coverage_class) queue_work(ar->workqueue, &ar->set_coverage_class_work); spin_unlock_bh(&ar->data_lock); } } static void ath10k_wmi_op_rx(struct ath10k *ar, struct sk_buff *skb) { struct wmi_cmd_hdr *cmd_hdr; enum wmi_event_id id; cmd_hdr = (struct wmi_cmd_hdr *)skb->data; id = MS(__le32_to_cpu(cmd_hdr->cmd_id), WMI_CMD_HDR_CMD_ID); if (skb_pull(skb, sizeof(struct wmi_cmd_hdr)) == NULL) goto out; trace_ath10k_wmi_event(ar, id, skb->data, skb->len); switch (id) { case WMI_MGMT_RX_EVENTID: ath10k_wmi_event_mgmt_rx(ar, skb); /* mgmt_rx() owns the skb now! */ return; case WMI_SCAN_EVENTID: ath10k_wmi_event_scan(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_CHAN_INFO_EVENTID: ath10k_wmi_event_chan_info(ar, skb); break; case WMI_ECHO_EVENTID: ath10k_wmi_event_echo(ar, skb); break; case WMI_DEBUG_MESG_EVENTID: ath10k_wmi_event_debug_mesg(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_UPDATE_STATS_EVENTID: ath10k_wmi_event_update_stats(ar, skb); break; case WMI_VDEV_START_RESP_EVENTID: ath10k_wmi_event_vdev_start_resp(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_VDEV_STOPPED_EVENTID: ath10k_wmi_event_vdev_stopped(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_PEER_STA_KICKOUT_EVENTID: ath10k_wmi_event_peer_sta_kickout(ar, skb); break; case WMI_HOST_SWBA_EVENTID: ath10k_wmi_event_host_swba(ar, skb); break; case WMI_TBTTOFFSET_UPDATE_EVENTID: ath10k_wmi_event_tbttoffset_update(ar, skb); break; case WMI_PHYERR_EVENTID: ath10k_wmi_event_phyerr(ar, skb); break; case WMI_ROAM_EVENTID: ath10k_wmi_event_roam(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_PROFILE_MATCH: ath10k_wmi_event_profile_match(ar, skb); break; case WMI_DEBUG_PRINT_EVENTID: ath10k_wmi_event_debug_print(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_PDEV_QVIT_EVENTID: ath10k_wmi_event_pdev_qvit(ar, skb); break; case WMI_WLAN_PROFILE_DATA_EVENTID: ath10k_wmi_event_wlan_profile_data(ar, skb); break; case WMI_RTT_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_rtt_measurement_report(ar, skb); break; case WMI_TSF_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_tsf_measurement_report(ar, skb); break; case WMI_RTT_ERROR_REPORT_EVENTID: ath10k_wmi_event_rtt_error_report(ar, skb); break; case WMI_WOW_WAKEUP_HOST_EVENTID: ath10k_wmi_event_wow_wakeup_host(ar, skb); break; case WMI_DCS_INTERFERENCE_EVENTID: ath10k_wmi_event_dcs_interference(ar, skb); break; case WMI_PDEV_TPC_CONFIG_EVENTID: ath10k_wmi_event_pdev_tpc_config(ar, skb); break; case WMI_PDEV_FTM_INTG_EVENTID: ath10k_wmi_event_pdev_ftm_intg(ar, skb); break; case WMI_GTK_OFFLOAD_STATUS_EVENTID: ath10k_wmi_event_gtk_offload_status(ar, skb); break; case WMI_GTK_REKEY_FAIL_EVENTID: ath10k_wmi_event_gtk_rekey_fail(ar, skb); break; case WMI_TX_DELBA_COMPLETE_EVENTID: ath10k_wmi_event_delba_complete(ar, skb); break; case WMI_TX_ADDBA_COMPLETE_EVENTID: ath10k_wmi_event_addba_complete(ar, skb); break; case WMI_VDEV_INSTALL_KEY_COMPLETE_EVENTID: ath10k_wmi_event_vdev_install_key_complete(ar, skb); break; case WMI_SERVICE_READY_EVENTID: ath10k_wmi_event_service_ready(ar, skb); return; case WMI_READY_EVENTID: ath10k_wmi_event_ready(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_SERVICE_AVAILABLE_EVENTID: ath10k_wmi_event_service_available(ar, skb); break; default: ath10k_warn(ar, "Unknown eventid: %d\n", id); break; } out: dev_kfree_skb(skb); } static void ath10k_wmi_10_1_op_rx(struct ath10k *ar, struct sk_buff *skb) { struct wmi_cmd_hdr *cmd_hdr; enum wmi_10x_event_id id; bool consumed; cmd_hdr = (struct wmi_cmd_hdr *)skb->data; id = MS(__le32_to_cpu(cmd_hdr->cmd_id), WMI_CMD_HDR_CMD_ID); if (skb_pull(skb, sizeof(struct wmi_cmd_hdr)) == NULL) goto out; trace_ath10k_wmi_event(ar, id, skb->data, skb->len); consumed = ath10k_tm_event_wmi(ar, id, skb); /* Ready event must be handled normally also in UTF mode so that we * know the UTF firmware has booted, others we are just bypass WMI * events to testmode. */ if (consumed && id != WMI_10X_READY_EVENTID) { ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi testmode consumed 0x%x\n", id); goto out; } switch (id) { case WMI_10X_MGMT_RX_EVENTID: ath10k_wmi_event_mgmt_rx(ar, skb); /* mgmt_rx() owns the skb now! */ return; case WMI_10X_SCAN_EVENTID: ath10k_wmi_event_scan(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_CHAN_INFO_EVENTID: ath10k_wmi_event_chan_info(ar, skb); break; case WMI_10X_ECHO_EVENTID: ath10k_wmi_event_echo(ar, skb); break; case WMI_10X_DEBUG_MESG_EVENTID: ath10k_wmi_event_debug_mesg(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_UPDATE_STATS_EVENTID: ath10k_wmi_event_update_stats(ar, skb); break; case WMI_10X_VDEV_START_RESP_EVENTID: ath10k_wmi_event_vdev_start_resp(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_VDEV_STOPPED_EVENTID: ath10k_wmi_event_vdev_stopped(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_PEER_STA_KICKOUT_EVENTID: ath10k_wmi_event_peer_sta_kickout(ar, skb); break; case WMI_10X_HOST_SWBA_EVENTID: ath10k_wmi_event_host_swba(ar, skb); break; case WMI_10X_TBTTOFFSET_UPDATE_EVENTID: ath10k_wmi_event_tbttoffset_update(ar, skb); break; case WMI_10X_PHYERR_EVENTID: ath10k_wmi_event_phyerr(ar, skb); break; case WMI_10X_ROAM_EVENTID: ath10k_wmi_event_roam(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_PROFILE_MATCH: ath10k_wmi_event_profile_match(ar, skb); break; case WMI_10X_DEBUG_PRINT_EVENTID: ath10k_wmi_event_debug_print(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_PDEV_QVIT_EVENTID: ath10k_wmi_event_pdev_qvit(ar, skb); break; case WMI_10X_WLAN_PROFILE_DATA_EVENTID: ath10k_wmi_event_wlan_profile_data(ar, skb); break; case WMI_10X_RTT_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_rtt_measurement_report(ar, skb); break; case WMI_10X_TSF_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_tsf_measurement_report(ar, skb); break; case WMI_10X_RTT_ERROR_REPORT_EVENTID: ath10k_wmi_event_rtt_error_report(ar, skb); break; case WMI_10X_WOW_WAKEUP_HOST_EVENTID: ath10k_wmi_event_wow_wakeup_host(ar, skb); break; case WMI_10X_DCS_INTERFERENCE_EVENTID: ath10k_wmi_event_dcs_interference(ar, skb); break; case WMI_10X_PDEV_TPC_CONFIG_EVENTID: ath10k_wmi_event_pdev_tpc_config(ar, skb); break; case WMI_10X_INST_RSSI_STATS_EVENTID: ath10k_wmi_event_inst_rssi_stats(ar, skb); break; case WMI_10X_VDEV_STANDBY_REQ_EVENTID: ath10k_wmi_event_vdev_standby_req(ar, skb); break; case WMI_10X_VDEV_RESUME_REQ_EVENTID: ath10k_wmi_event_vdev_resume_req(ar, skb); break; case WMI_10X_SERVICE_READY_EVENTID: ath10k_wmi_event_service_ready(ar, skb); return; case WMI_10X_READY_EVENTID: ath10k_wmi_event_ready(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10X_PDEV_UTF_EVENTID: /* ignore utf events */ break; default: ath10k_warn(ar, "Unknown eventid: %d\n", id); break; } out: dev_kfree_skb(skb); } static void ath10k_wmi_10_2_op_rx(struct ath10k *ar, struct sk_buff *skb) { struct wmi_cmd_hdr *cmd_hdr; enum wmi_10_2_event_id id; bool consumed; cmd_hdr = (struct wmi_cmd_hdr *)skb->data; id = MS(__le32_to_cpu(cmd_hdr->cmd_id), WMI_CMD_HDR_CMD_ID); if (skb_pull(skb, sizeof(struct wmi_cmd_hdr)) == NULL) goto out; trace_ath10k_wmi_event(ar, id, skb->data, skb->len); consumed = ath10k_tm_event_wmi(ar, id, skb); /* Ready event must be handled normally also in UTF mode so that we * know the UTF firmware has booted, others we are just bypass WMI * events to testmode. */ if (consumed && id != WMI_10_2_READY_EVENTID) { ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi testmode consumed 0x%x\n", id); goto out; } switch (id) { case WMI_10_2_MGMT_RX_EVENTID: ath10k_wmi_event_mgmt_rx(ar, skb); /* mgmt_rx() owns the skb now! */ return; case WMI_10_2_SCAN_EVENTID: ath10k_wmi_event_scan(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_CHAN_INFO_EVENTID: ath10k_wmi_event_chan_info(ar, skb); break; case WMI_10_2_ECHO_EVENTID: ath10k_wmi_event_echo(ar, skb); break; case WMI_10_2_DEBUG_MESG_EVENTID: ath10k_wmi_event_debug_mesg(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_UPDATE_STATS_EVENTID: ath10k_wmi_event_update_stats(ar, skb); break; case WMI_10_2_VDEV_START_RESP_EVENTID: ath10k_wmi_event_vdev_start_resp(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_VDEV_STOPPED_EVENTID: ath10k_wmi_event_vdev_stopped(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_PEER_STA_KICKOUT_EVENTID: ath10k_wmi_event_peer_sta_kickout(ar, skb); break; case WMI_10_2_HOST_SWBA_EVENTID: ath10k_wmi_event_host_swba(ar, skb); break; case WMI_10_2_TBTTOFFSET_UPDATE_EVENTID: ath10k_wmi_event_tbttoffset_update(ar, skb); break; case WMI_10_2_PHYERR_EVENTID: ath10k_wmi_event_phyerr(ar, skb); break; case WMI_10_2_ROAM_EVENTID: ath10k_wmi_event_roam(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_PROFILE_MATCH: ath10k_wmi_event_profile_match(ar, skb); break; case WMI_10_2_DEBUG_PRINT_EVENTID: ath10k_wmi_event_debug_print(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_PDEV_QVIT_EVENTID: ath10k_wmi_event_pdev_qvit(ar, skb); break; case WMI_10_2_WLAN_PROFILE_DATA_EVENTID: ath10k_wmi_event_wlan_profile_data(ar, skb); break; case WMI_10_2_RTT_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_rtt_measurement_report(ar, skb); break; case WMI_10_2_TSF_MEASUREMENT_REPORT_EVENTID: ath10k_wmi_event_tsf_measurement_report(ar, skb); break; case WMI_10_2_RTT_ERROR_REPORT_EVENTID: ath10k_wmi_event_rtt_error_report(ar, skb); break; case WMI_10_2_WOW_WAKEUP_HOST_EVENTID: ath10k_wmi_event_wow_wakeup_host(ar, skb); break; case WMI_10_2_DCS_INTERFERENCE_EVENTID: ath10k_wmi_event_dcs_interference(ar, skb); break; case WMI_10_2_PDEV_TPC_CONFIG_EVENTID: ath10k_wmi_event_pdev_tpc_config(ar, skb); break; case WMI_10_2_INST_RSSI_STATS_EVENTID: ath10k_wmi_event_inst_rssi_stats(ar, skb); break; case WMI_10_2_VDEV_STANDBY_REQ_EVENTID: ath10k_wmi_event_vdev_standby_req(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_VDEV_RESUME_REQ_EVENTID: ath10k_wmi_event_vdev_resume_req(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_SERVICE_READY_EVENTID: ath10k_wmi_event_service_ready(ar, skb); return; case WMI_10_2_READY_EVENTID: ath10k_wmi_event_ready(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_2_PDEV_TEMPERATURE_EVENTID: ath10k_wmi_event_temperature(ar, skb); break; case WMI_10_2_PDEV_BSS_CHAN_INFO_EVENTID: ath10k_wmi_event_pdev_bss_chan_info(ar, skb); break; case WMI_10_2_RTT_KEEPALIVE_EVENTID: case WMI_10_2_GPIO_INPUT_EVENTID: case WMI_10_2_PEER_RATECODE_LIST_EVENTID: case WMI_10_2_GENERIC_BUFFER_EVENTID: case WMI_10_2_MCAST_BUF_RELEASE_EVENTID: case WMI_10_2_MCAST_LIST_AGEOUT_EVENTID: case WMI_10_2_WDS_PEER_EVENTID: ath10k_dbg(ar, ATH10K_DBG_WMI, "received event id %d not implemented\n", id); break; case WMI_10_2_PEER_STA_PS_STATECHG_EVENTID: ath10k_wmi_event_peer_sta_ps_state_chg(ar, skb); break; default: ath10k_warn(ar, "Unknown eventid: %d\n", id); break; } out: dev_kfree_skb(skb); } static void ath10k_wmi_10_4_op_rx(struct ath10k *ar, struct sk_buff *skb) { struct wmi_cmd_hdr *cmd_hdr; enum wmi_10_4_event_id id; bool consumed; cmd_hdr = (struct wmi_cmd_hdr *)skb->data; id = MS(__le32_to_cpu(cmd_hdr->cmd_id), WMI_CMD_HDR_CMD_ID); if (!skb_pull(skb, sizeof(struct wmi_cmd_hdr))) goto out; trace_ath10k_wmi_event(ar, id, skb->data, skb->len); consumed = ath10k_tm_event_wmi(ar, id, skb); /* Ready event must be handled normally also in UTF mode so that we * know the UTF firmware has booted, others we are just bypass WMI * events to testmode. */ if (consumed && id != WMI_10_4_READY_EVENTID) { ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi testmode consumed 0x%x\n", id); goto out; } switch (id) { case WMI_10_4_MGMT_RX_EVENTID: ath10k_wmi_event_mgmt_rx(ar, skb); /* mgmt_rx() owns the skb now! */ return; case WMI_10_4_ECHO_EVENTID: ath10k_wmi_event_echo(ar, skb); break; case WMI_10_4_DEBUG_MESG_EVENTID: ath10k_wmi_event_debug_mesg(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_SERVICE_READY_EVENTID: ath10k_wmi_event_service_ready(ar, skb); return; case WMI_10_4_SCAN_EVENTID: ath10k_wmi_event_scan(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_CHAN_INFO_EVENTID: ath10k_wmi_event_chan_info(ar, skb); break; case WMI_10_4_PHYERR_EVENTID: ath10k_wmi_event_phyerr(ar, skb); break; case WMI_10_4_READY_EVENTID: ath10k_wmi_event_ready(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_PEER_STA_KICKOUT_EVENTID: ath10k_wmi_event_peer_sta_kickout(ar, skb); break; case WMI_10_4_ROAM_EVENTID: ath10k_wmi_event_roam(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_HOST_SWBA_EVENTID: ath10k_wmi_event_host_swba(ar, skb); break; case WMI_10_4_TBTTOFFSET_UPDATE_EVENTID: ath10k_wmi_event_tbttoffset_update(ar, skb); break; case WMI_10_4_DEBUG_PRINT_EVENTID: ath10k_wmi_event_debug_print(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_VDEV_START_RESP_EVENTID: ath10k_wmi_event_vdev_start_resp(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_VDEV_STOPPED_EVENTID: ath10k_wmi_event_vdev_stopped(ar, skb); ath10k_wmi_queue_set_coverage_class_work(ar); break; case WMI_10_4_WOW_WAKEUP_HOST_EVENTID: case WMI_10_4_PEER_RATECODE_LIST_EVENTID: case WMI_10_4_WDS_PEER_EVENTID: case WMI_10_4_DEBUG_FATAL_CONDITION_EVENTID: ath10k_dbg(ar, ATH10K_DBG_WMI, "received event id %d not implemented\n", id); break; case WMI_10_4_UPDATE_STATS_EVENTID: ath10k_wmi_event_update_stats(ar, skb); break; case WMI_10_4_PDEV_TEMPERATURE_EVENTID: ath10k_wmi_event_temperature(ar, skb); break; case WMI_10_4_PDEV_BSS_CHAN_INFO_EVENTID: ath10k_wmi_event_pdev_bss_chan_info(ar, skb); break; case WMI_10_4_PDEV_TPC_CONFIG_EVENTID: ath10k_wmi_event_pdev_tpc_config(ar, skb); break; case WMI_10_4_TDLS_PEER_EVENTID: ath10k_wmi_handle_tdls_peer_event(ar, skb); break; case WMI_10_4_PDEV_TPC_TABLE_EVENTID: ath10k_wmi_event_tpc_final_table(ar, skb); break; case WMI_10_4_DFS_STATUS_CHECK_EVENTID: ath10k_wmi_event_dfs_status_check(ar, skb); break; case WMI_10_4_PEER_STA_PS_STATECHG_EVENTID: ath10k_wmi_event_peer_sta_ps_state_chg(ar, skb); break; default: ath10k_warn(ar, "Unknown eventid: %d\n", id); break; } out: dev_kfree_skb(skb); } static void ath10k_wmi_process_rx(struct ath10k *ar, struct sk_buff *skb) { int ret; ret = ath10k_wmi_rx(ar, skb); if (ret) ath10k_warn(ar, "failed to process wmi rx: %d\n", ret); } int ath10k_wmi_connect(struct ath10k *ar) { int status; struct ath10k_htc_svc_conn_req conn_req; struct ath10k_htc_svc_conn_resp conn_resp; memset(&ar->wmi.svc_map, 0, sizeof(ar->wmi.svc_map)); memset(&conn_req, 0, sizeof(conn_req)); memset(&conn_resp, 0, sizeof(conn_resp)); /* these fields are the same for all service endpoints */ conn_req.ep_ops.ep_tx_complete = ath10k_wmi_htc_tx_complete; conn_req.ep_ops.ep_rx_complete = ath10k_wmi_process_rx; conn_req.ep_ops.ep_tx_credits = ath10k_wmi_op_ep_tx_credits; /* connect to control service */ conn_req.service_id = ATH10K_HTC_SVC_ID_WMI_CONTROL; status = ath10k_htc_connect_service(&ar->htc, &conn_req, &conn_resp); if (status) { ath10k_warn(ar, "failed to connect to WMI CONTROL service status: %d\n", status); return status; } ar->wmi.eid = conn_resp.eid; return 0; } static struct sk_buff * ath10k_wmi_op_gen_pdev_set_base_macaddr(struct ath10k *ar, const u8 macaddr[ETH_ALEN]) { struct wmi_pdev_set_base_macaddr_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_base_macaddr_cmd *)skb->data; ether_addr_copy(cmd->mac_addr.addr, macaddr); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev basemac %pM\n", macaddr); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pdev_set_rd(struct ath10k *ar, u16 rd, u16 rd2g, u16 rd5g, u16 ctl2g, u16 ctl5g, enum wmi_dfs_region dfs_reg) { struct wmi_pdev_set_regdomain_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_regdomain_cmd *)skb->data; cmd->reg_domain = __cpu_to_le32(rd); cmd->reg_domain_2G = __cpu_to_le32(rd2g); cmd->reg_domain_5G = __cpu_to_le32(rd5g); cmd->conformance_test_limit_2G = __cpu_to_le32(ctl2g); cmd->conformance_test_limit_5G = __cpu_to_le32(ctl5g); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev regdomain rd %x rd2g %x rd5g %x ctl2g %x ctl5g %x\n", rd, rd2g, rd5g, ctl2g, ctl5g); return skb; } static struct sk_buff * ath10k_wmi_10x_op_gen_pdev_set_rd(struct ath10k *ar, u16 rd, u16 rd2g, u16 rd5g, u16 ctl2g, u16 ctl5g, enum wmi_dfs_region dfs_reg) { struct wmi_pdev_set_regdomain_cmd_10x *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_regdomain_cmd_10x *)skb->data; cmd->reg_domain = __cpu_to_le32(rd); cmd->reg_domain_2G = __cpu_to_le32(rd2g); cmd->reg_domain_5G = __cpu_to_le32(rd5g); cmd->conformance_test_limit_2G = __cpu_to_le32(ctl2g); cmd->conformance_test_limit_5G = __cpu_to_le32(ctl5g); cmd->dfs_domain = __cpu_to_le32(dfs_reg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev regdomain rd %x rd2g %x rd5g %x ctl2g %x ctl5g %x dfs_region %x\n", rd, rd2g, rd5g, ctl2g, ctl5g, dfs_reg); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pdev_suspend(struct ath10k *ar, u32 suspend_opt) { struct wmi_pdev_suspend_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_suspend_cmd *)skb->data; cmd->suspend_opt = __cpu_to_le32(suspend_opt); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pdev_resume(struct ath10k *ar) { struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, 0); if (!skb) return ERR_PTR(-ENOMEM); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pdev_set_param(struct ath10k *ar, u32 id, u32 value) { struct wmi_pdev_set_param_cmd *cmd; struct sk_buff *skb; if (id == WMI_PDEV_PARAM_UNSUPPORTED) { ath10k_warn(ar, "pdev param %d not supported by firmware\n", id); return ERR_PTR(-EOPNOTSUPP); } skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_param_cmd *)skb->data; cmd->param_id = __cpu_to_le32(id); cmd->param_value = __cpu_to_le32(value); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev set param %d value %d\n", id, value); return skb; } void ath10k_wmi_put_host_mem_chunks(struct ath10k *ar, struct wmi_host_mem_chunks *chunks) { struct host_memory_chunk *chunk; int i; chunks->count = __cpu_to_le32(ar->wmi.num_mem_chunks); for (i = 0; i < ar->wmi.num_mem_chunks; i++) { chunk = &chunks->items[i]; chunk->ptr = __cpu_to_le32(ar->wmi.mem_chunks[i].paddr); chunk->size = __cpu_to_le32(ar->wmi.mem_chunks[i].len); chunk->req_id = __cpu_to_le32(ar->wmi.mem_chunks[i].req_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi chunk %d len %d requested, addr 0x%llx\n", i, ar->wmi.mem_chunks[i].len, (unsigned long long)ar->wmi.mem_chunks[i].paddr); } } static struct sk_buff *ath10k_wmi_op_gen_init(struct ath10k *ar) { struct wmi_init_cmd *cmd; struct sk_buff *buf; struct wmi_resource_config config = {}; u32 val; config.num_vdevs = __cpu_to_le32(TARGET_NUM_VDEVS); config.num_peers = __cpu_to_le32(TARGET_NUM_PEERS); config.num_offload_peers = __cpu_to_le32(TARGET_NUM_OFFLOAD_PEERS); config.num_offload_reorder_bufs = __cpu_to_le32(TARGET_NUM_OFFLOAD_REORDER_BUFS); config.num_peer_keys = __cpu_to_le32(TARGET_NUM_PEER_KEYS); config.num_tids = __cpu_to_le32(TARGET_NUM_TIDS); config.ast_skid_limit = __cpu_to_le32(TARGET_AST_SKID_LIMIT); config.tx_chain_mask = __cpu_to_le32(TARGET_TX_CHAIN_MASK); config.rx_chain_mask = __cpu_to_le32(TARGET_RX_CHAIN_MASK); config.rx_timeout_pri_vo = __cpu_to_le32(TARGET_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_vi = __cpu_to_le32(TARGET_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_be = __cpu_to_le32(TARGET_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_bk = __cpu_to_le32(TARGET_RX_TIMEOUT_HI_PRI); config.rx_decap_mode = __cpu_to_le32(ar->wmi.rx_decap_mode); config.scan_max_pending_reqs = __cpu_to_le32(TARGET_SCAN_MAX_PENDING_REQS); config.bmiss_offload_max_vdev = __cpu_to_le32(TARGET_BMISS_OFFLOAD_MAX_VDEV); config.roam_offload_max_vdev = __cpu_to_le32(TARGET_ROAM_OFFLOAD_MAX_VDEV); config.roam_offload_max_ap_profiles = __cpu_to_le32(TARGET_ROAM_OFFLOAD_MAX_AP_PROFILES); config.num_mcast_groups = __cpu_to_le32(TARGET_NUM_MCAST_GROUPS); config.num_mcast_table_elems = __cpu_to_le32(TARGET_NUM_MCAST_TABLE_ELEMS); config.mcast2ucast_mode = __cpu_to_le32(TARGET_MCAST2UCAST_MODE); config.tx_dbg_log_size = __cpu_to_le32(TARGET_TX_DBG_LOG_SIZE); config.num_wds_entries = __cpu_to_le32(TARGET_NUM_WDS_ENTRIES); config.dma_burst_size = __cpu_to_le32(TARGET_DMA_BURST_SIZE); config.mac_aggr_delim = __cpu_to_le32(TARGET_MAC_AGGR_DELIM); val = TARGET_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK; config.rx_skip_defrag_timeout_dup_detection_check = __cpu_to_le32(val); config.vow_config = __cpu_to_le32(TARGET_VOW_CONFIG); config.gtk_offload_max_vdev = __cpu_to_le32(TARGET_GTK_OFFLOAD_MAX_VDEV); config.num_msdu_desc = __cpu_to_le32(TARGET_NUM_MSDU_DESC); config.max_frag_entries = __cpu_to_le32(TARGET_MAX_FRAG_ENTRIES); buf = ath10k_wmi_alloc_skb(ar, struct_size(cmd, mem_chunks.items, ar->wmi.num_mem_chunks)); if (!buf) return ERR_PTR(-ENOMEM); cmd = (struct wmi_init_cmd *)buf->data; memcpy(&cmd->resource_config, &config, sizeof(config)); ath10k_wmi_put_host_mem_chunks(ar, &cmd->mem_chunks); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi init\n"); return buf; } static struct sk_buff *ath10k_wmi_10_1_op_gen_init(struct ath10k *ar) { struct wmi_init_cmd_10x *cmd; struct sk_buff *buf; struct wmi_resource_config_10x config = {}; u32 val; config.num_vdevs = __cpu_to_le32(TARGET_10X_NUM_VDEVS); config.num_peers = __cpu_to_le32(TARGET_10X_NUM_PEERS); config.num_peer_keys = __cpu_to_le32(TARGET_10X_NUM_PEER_KEYS); config.num_tids = __cpu_to_le32(TARGET_10X_NUM_TIDS); config.ast_skid_limit = __cpu_to_le32(TARGET_10X_AST_SKID_LIMIT); config.tx_chain_mask = __cpu_to_le32(TARGET_10X_TX_CHAIN_MASK); config.rx_chain_mask = __cpu_to_le32(TARGET_10X_RX_CHAIN_MASK); config.rx_timeout_pri_vo = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_vi = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_be = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_bk = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_HI_PRI); config.rx_decap_mode = __cpu_to_le32(ar->wmi.rx_decap_mode); config.scan_max_pending_reqs = __cpu_to_le32(TARGET_10X_SCAN_MAX_PENDING_REQS); config.bmiss_offload_max_vdev = __cpu_to_le32(TARGET_10X_BMISS_OFFLOAD_MAX_VDEV); config.roam_offload_max_vdev = __cpu_to_le32(TARGET_10X_ROAM_OFFLOAD_MAX_VDEV); config.roam_offload_max_ap_profiles = __cpu_to_le32(TARGET_10X_ROAM_OFFLOAD_MAX_AP_PROFILES); config.num_mcast_groups = __cpu_to_le32(TARGET_10X_NUM_MCAST_GROUPS); config.num_mcast_table_elems = __cpu_to_le32(TARGET_10X_NUM_MCAST_TABLE_ELEMS); config.mcast2ucast_mode = __cpu_to_le32(TARGET_10X_MCAST2UCAST_MODE); config.tx_dbg_log_size = __cpu_to_le32(TARGET_10X_TX_DBG_LOG_SIZE); config.num_wds_entries = __cpu_to_le32(TARGET_10X_NUM_WDS_ENTRIES); config.dma_burst_size = __cpu_to_le32(TARGET_10X_DMA_BURST_SIZE); config.mac_aggr_delim = __cpu_to_le32(TARGET_10X_MAC_AGGR_DELIM); val = TARGET_10X_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK; config.rx_skip_defrag_timeout_dup_detection_check = __cpu_to_le32(val); config.vow_config = __cpu_to_le32(TARGET_10X_VOW_CONFIG); config.num_msdu_desc = __cpu_to_le32(TARGET_10X_NUM_MSDU_DESC); config.max_frag_entries = __cpu_to_le32(TARGET_10X_MAX_FRAG_ENTRIES); buf = ath10k_wmi_alloc_skb(ar, struct_size(cmd, mem_chunks.items, ar->wmi.num_mem_chunks)); if (!buf) return ERR_PTR(-ENOMEM); cmd = (struct wmi_init_cmd_10x *)buf->data; memcpy(&cmd->resource_config, &config, sizeof(config)); ath10k_wmi_put_host_mem_chunks(ar, &cmd->mem_chunks); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi init 10x\n"); return buf; } static struct sk_buff *ath10k_wmi_10_2_op_gen_init(struct ath10k *ar) { struct wmi_init_cmd_10_2 *cmd; struct sk_buff *buf; struct wmi_resource_config_10x config = {}; u32 val, features; config.num_vdevs = __cpu_to_le32(TARGET_10X_NUM_VDEVS); config.num_peer_keys = __cpu_to_le32(TARGET_10X_NUM_PEER_KEYS); if (ath10k_peer_stats_enabled(ar)) { config.num_peers = __cpu_to_le32(TARGET_10X_TX_STATS_NUM_PEERS); config.num_tids = __cpu_to_le32(TARGET_10X_TX_STATS_NUM_TIDS); } else { config.num_peers = __cpu_to_le32(TARGET_10X_NUM_PEERS); config.num_tids = __cpu_to_le32(TARGET_10X_NUM_TIDS); } config.ast_skid_limit = __cpu_to_le32(TARGET_10X_AST_SKID_LIMIT); config.tx_chain_mask = __cpu_to_le32(TARGET_10X_TX_CHAIN_MASK); config.rx_chain_mask = __cpu_to_le32(TARGET_10X_RX_CHAIN_MASK); config.rx_timeout_pri_vo = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_vi = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_be = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri_bk = __cpu_to_le32(TARGET_10X_RX_TIMEOUT_HI_PRI); config.rx_decap_mode = __cpu_to_le32(ar->wmi.rx_decap_mode); config.scan_max_pending_reqs = __cpu_to_le32(TARGET_10X_SCAN_MAX_PENDING_REQS); config.bmiss_offload_max_vdev = __cpu_to_le32(TARGET_10X_BMISS_OFFLOAD_MAX_VDEV); config.roam_offload_max_vdev = __cpu_to_le32(TARGET_10X_ROAM_OFFLOAD_MAX_VDEV); config.roam_offload_max_ap_profiles = __cpu_to_le32(TARGET_10X_ROAM_OFFLOAD_MAX_AP_PROFILES); config.num_mcast_groups = __cpu_to_le32(TARGET_10X_NUM_MCAST_GROUPS); config.num_mcast_table_elems = __cpu_to_le32(TARGET_10X_NUM_MCAST_TABLE_ELEMS); config.mcast2ucast_mode = __cpu_to_le32(TARGET_10X_MCAST2UCAST_MODE); config.tx_dbg_log_size = __cpu_to_le32(TARGET_10X_TX_DBG_LOG_SIZE); config.num_wds_entries = __cpu_to_le32(TARGET_10X_NUM_WDS_ENTRIES); config.dma_burst_size = __cpu_to_le32(TARGET_10_2_DMA_BURST_SIZE); config.mac_aggr_delim = __cpu_to_le32(TARGET_10X_MAC_AGGR_DELIM); val = TARGET_10X_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK; config.rx_skip_defrag_timeout_dup_detection_check = __cpu_to_le32(val); config.vow_config = __cpu_to_le32(TARGET_10X_VOW_CONFIG); config.num_msdu_desc = __cpu_to_le32(TARGET_10X_NUM_MSDU_DESC); config.max_frag_entries = __cpu_to_le32(TARGET_10X_MAX_FRAG_ENTRIES); buf = ath10k_wmi_alloc_skb(ar, struct_size(cmd, mem_chunks.items, ar->wmi.num_mem_chunks)); if (!buf) return ERR_PTR(-ENOMEM); cmd = (struct wmi_init_cmd_10_2 *)buf->data; features = WMI_10_2_RX_BATCH_MODE; if (test_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags) && test_bit(WMI_SERVICE_COEX_GPIO, ar->wmi.svc_map)) features |= WMI_10_2_COEX_GPIO; if (ath10k_peer_stats_enabled(ar)) features |= WMI_10_2_PEER_STATS; if (test_bit(WMI_SERVICE_BSS_CHANNEL_INFO_64, ar->wmi.svc_map)) features |= WMI_10_2_BSS_CHAN_INFO; cmd->resource_config.feature_mask = __cpu_to_le32(features); memcpy(&cmd->resource_config.common, &config, sizeof(config)); ath10k_wmi_put_host_mem_chunks(ar, &cmd->mem_chunks); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi init 10.2\n"); return buf; } static struct sk_buff *ath10k_wmi_10_4_op_gen_init(struct ath10k *ar) { struct wmi_init_cmd_10_4 *cmd; struct sk_buff *buf; struct wmi_resource_config_10_4 config = {}; config.num_vdevs = __cpu_to_le32(ar->max_num_vdevs); config.num_peers = __cpu_to_le32(ar->max_num_peers); config.num_active_peers = __cpu_to_le32(ar->num_active_peers); config.num_tids = __cpu_to_le32(ar->num_tids); config.num_offload_peers = __cpu_to_le32(TARGET_10_4_NUM_OFFLOAD_PEERS); config.num_offload_reorder_buffs = __cpu_to_le32(TARGET_10_4_NUM_OFFLOAD_REORDER_BUFFS); config.num_peer_keys = __cpu_to_le32(TARGET_10_4_NUM_PEER_KEYS); config.ast_skid_limit = __cpu_to_le32(TARGET_10_4_AST_SKID_LIMIT); config.tx_chain_mask = __cpu_to_le32(ar->hw_params.tx_chain_mask); config.rx_chain_mask = __cpu_to_le32(ar->hw_params.rx_chain_mask); config.rx_timeout_pri[0] = __cpu_to_le32(TARGET_10_4_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri[1] = __cpu_to_le32(TARGET_10_4_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri[2] = __cpu_to_le32(TARGET_10_4_RX_TIMEOUT_LO_PRI); config.rx_timeout_pri[3] = __cpu_to_le32(TARGET_10_4_RX_TIMEOUT_HI_PRI); config.rx_decap_mode = __cpu_to_le32(ar->wmi.rx_decap_mode); config.scan_max_pending_req = __cpu_to_le32(TARGET_10_4_SCAN_MAX_REQS); config.bmiss_offload_max_vdev = __cpu_to_le32(TARGET_10_4_BMISS_OFFLOAD_MAX_VDEV); config.roam_offload_max_vdev = __cpu_to_le32(TARGET_10_4_ROAM_OFFLOAD_MAX_VDEV); config.roam_offload_max_ap_profiles = __cpu_to_le32(TARGET_10_4_ROAM_OFFLOAD_MAX_PROFILES); config.num_mcast_groups = __cpu_to_le32(TARGET_10_4_NUM_MCAST_GROUPS); config.num_mcast_table_elems = __cpu_to_le32(TARGET_10_4_NUM_MCAST_TABLE_ELEMS); config.mcast2ucast_mode = __cpu_to_le32(TARGET_10_4_MCAST2UCAST_MODE); config.tx_dbg_log_size = __cpu_to_le32(TARGET_10_4_TX_DBG_LOG_SIZE); config.num_wds_entries = __cpu_to_le32(TARGET_10_4_NUM_WDS_ENTRIES); config.dma_burst_size = __cpu_to_le32(TARGET_10_4_DMA_BURST_SIZE); config.mac_aggr_delim = __cpu_to_le32(TARGET_10_4_MAC_AGGR_DELIM); config.rx_skip_defrag_timeout_dup_detection_check = __cpu_to_le32(TARGET_10_4_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK); config.vow_config = __cpu_to_le32(TARGET_10_4_VOW_CONFIG); config.gtk_offload_max_vdev = __cpu_to_le32(TARGET_10_4_GTK_OFFLOAD_MAX_VDEV); config.num_msdu_desc = __cpu_to_le32(ar->htt.max_num_pending_tx); config.max_frag_entries = __cpu_to_le32(TARGET_10_4_11AC_TX_MAX_FRAGS); config.max_peer_ext_stats = __cpu_to_le32(TARGET_10_4_MAX_PEER_EXT_STATS); config.smart_ant_cap = __cpu_to_le32(TARGET_10_4_SMART_ANT_CAP); config.bk_minfree = __cpu_to_le32(TARGET_10_4_BK_MIN_FREE); config.be_minfree = __cpu_to_le32(TARGET_10_4_BE_MIN_FREE); config.vi_minfree = __cpu_to_le32(TARGET_10_4_VI_MIN_FREE); config.vo_minfree = __cpu_to_le32(TARGET_10_4_VO_MIN_FREE); config.rx_batchmode = __cpu_to_le32(TARGET_10_4_RX_BATCH_MODE); config.tt_support = __cpu_to_le32(TARGET_10_4_THERMAL_THROTTLING_CONFIG); config.atf_config = __cpu_to_le32(TARGET_10_4_ATF_CONFIG); config.iphdr_pad_config = __cpu_to_le32(TARGET_10_4_IPHDR_PAD_CONFIG); config.qwrap_config = __cpu_to_le32(TARGET_10_4_QWRAP_CONFIG); buf = ath10k_wmi_alloc_skb(ar, struct_size(cmd, mem_chunks.items, ar->wmi.num_mem_chunks)); if (!buf) return ERR_PTR(-ENOMEM); cmd = (struct wmi_init_cmd_10_4 *)buf->data; memcpy(&cmd->resource_config, &config, sizeof(config)); ath10k_wmi_put_host_mem_chunks(ar, &cmd->mem_chunks); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi init 10.4\n"); return buf; } int ath10k_wmi_start_scan_verify(const struct wmi_start_scan_arg *arg) { if (arg->ie_len > WLAN_SCAN_PARAMS_MAX_IE_LEN) return -EINVAL; if (arg->n_channels > ARRAY_SIZE(arg->channels)) return -EINVAL; if (arg->n_ssids > WLAN_SCAN_PARAMS_MAX_SSID) return -EINVAL; if (arg->n_bssids > WLAN_SCAN_PARAMS_MAX_BSSID) return -EINVAL; return 0; } static size_t ath10k_wmi_start_scan_tlvs_len(const struct wmi_start_scan_arg *arg) { int len = 0; if (arg->ie_len) { len += sizeof(struct wmi_ie_data); len += roundup(arg->ie_len, 4); } if (arg->n_channels) { len += sizeof(struct wmi_chan_list); len += sizeof(__le32) * arg->n_channels; } if (arg->n_ssids) { len += sizeof(struct wmi_ssid_list); len += sizeof(struct wmi_ssid) * arg->n_ssids; } if (arg->n_bssids) { len += sizeof(struct wmi_bssid_list); len += sizeof(struct wmi_mac_addr) * arg->n_bssids; } return len; } void ath10k_wmi_put_start_scan_common(struct wmi_start_scan_common *cmn, const struct wmi_start_scan_arg *arg) { u32 scan_id; u32 scan_req_id; scan_id = WMI_HOST_SCAN_REQ_ID_PREFIX; scan_id |= arg->scan_id; scan_req_id = WMI_HOST_SCAN_REQUESTOR_ID_PREFIX; scan_req_id |= arg->scan_req_id; cmn->scan_id = __cpu_to_le32(scan_id); cmn->scan_req_id = __cpu_to_le32(scan_req_id); cmn->vdev_id = __cpu_to_le32(arg->vdev_id); cmn->scan_priority = __cpu_to_le32(arg->scan_priority); cmn->notify_scan_events = __cpu_to_le32(arg->notify_scan_events); cmn->dwell_time_active = __cpu_to_le32(arg->dwell_time_active); cmn->dwell_time_passive = __cpu_to_le32(arg->dwell_time_passive); cmn->min_rest_time = __cpu_to_le32(arg->min_rest_time); cmn->max_rest_time = __cpu_to_le32(arg->max_rest_time); cmn->repeat_probe_time = __cpu_to_le32(arg->repeat_probe_time); cmn->probe_spacing_time = __cpu_to_le32(arg->probe_spacing_time); cmn->idle_time = __cpu_to_le32(arg->idle_time); cmn->max_scan_time = __cpu_to_le32(arg->max_scan_time); cmn->probe_delay = __cpu_to_le32(arg->probe_delay); cmn->scan_ctrl_flags = __cpu_to_le32(arg->scan_ctrl_flags); } static void ath10k_wmi_put_start_scan_tlvs(u8 *tlvs, const struct wmi_start_scan_arg *arg) { struct wmi_ie_data *ie; struct wmi_chan_list *channels; struct wmi_ssid_list *ssids; struct wmi_bssid_list *bssids; void *ptr = tlvs; int i; if (arg->n_channels) { channels = ptr; channels->tag = __cpu_to_le32(WMI_CHAN_LIST_TAG); channels->num_chan = __cpu_to_le32(arg->n_channels); for (i = 0; i < arg->n_channels; i++) channels->channel_list[i].freq = __cpu_to_le16(arg->channels[i]); ptr += sizeof(*channels); ptr += sizeof(__le32) * arg->n_channels; } if (arg->n_ssids) { ssids = ptr; ssids->tag = __cpu_to_le32(WMI_SSID_LIST_TAG); ssids->num_ssids = __cpu_to_le32(arg->n_ssids); for (i = 0; i < arg->n_ssids; i++) { ssids->ssids[i].ssid_len = __cpu_to_le32(arg->ssids[i].len); memcpy(&ssids->ssids[i].ssid, arg->ssids[i].ssid, arg->ssids[i].len); } ptr += sizeof(*ssids); ptr += sizeof(struct wmi_ssid) * arg->n_ssids; } if (arg->n_bssids) { bssids = ptr; bssids->tag = __cpu_to_le32(WMI_BSSID_LIST_TAG); bssids->num_bssid = __cpu_to_le32(arg->n_bssids); for (i = 0; i < arg->n_bssids; i++) ether_addr_copy(bssids->bssid_list[i].addr, arg->bssids[i].bssid); ptr += sizeof(*bssids); ptr += sizeof(struct wmi_mac_addr) * arg->n_bssids; } if (arg->ie_len) { ie = ptr; ie->tag = __cpu_to_le32(WMI_IE_TAG); ie->ie_len = __cpu_to_le32(arg->ie_len); memcpy(ie->ie_data, arg->ie, arg->ie_len); ptr += sizeof(*ie); ptr += roundup(arg->ie_len, 4); } } static struct sk_buff * ath10k_wmi_op_gen_start_scan(struct ath10k *ar, const struct wmi_start_scan_arg *arg) { struct wmi_start_scan_cmd *cmd; struct sk_buff *skb; size_t len; int ret; ret = ath10k_wmi_start_scan_verify(arg); if (ret) return ERR_PTR(ret); len = sizeof(*cmd) + ath10k_wmi_start_scan_tlvs_len(arg); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_start_scan_cmd *)skb->data; ath10k_wmi_put_start_scan_common(&cmd->common, arg); ath10k_wmi_put_start_scan_tlvs(cmd->tlvs, arg); cmd->burst_duration_ms = __cpu_to_le32(0); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi start scan\n"); return skb; } static struct sk_buff * ath10k_wmi_10x_op_gen_start_scan(struct ath10k *ar, const struct wmi_start_scan_arg *arg) { struct wmi_10x_start_scan_cmd *cmd; struct sk_buff *skb; size_t len; int ret; ret = ath10k_wmi_start_scan_verify(arg); if (ret) return ERR_PTR(ret); len = sizeof(*cmd) + ath10k_wmi_start_scan_tlvs_len(arg); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_10x_start_scan_cmd *)skb->data; ath10k_wmi_put_start_scan_common(&cmd->common, arg); ath10k_wmi_put_start_scan_tlvs(cmd->tlvs, arg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi 10x start scan\n"); return skb; } void ath10k_wmi_start_scan_init(struct ath10k *ar, struct wmi_start_scan_arg *arg) { /* setup commonly used values */ arg->scan_req_id = 1; arg->scan_priority = WMI_SCAN_PRIORITY_LOW; arg->dwell_time_active = 50; arg->dwell_time_passive = 150; arg->min_rest_time = 50; arg->max_rest_time = 500; arg->repeat_probe_time = 0; arg->probe_spacing_time = 0; arg->idle_time = 0; arg->max_scan_time = 20000; arg->probe_delay = 5; arg->notify_scan_events = WMI_SCAN_EVENT_STARTED | WMI_SCAN_EVENT_COMPLETED | WMI_SCAN_EVENT_BSS_CHANNEL | WMI_SCAN_EVENT_FOREIGN_CHANNEL | WMI_SCAN_EVENT_FOREIGN_CHANNEL_EXIT | WMI_SCAN_EVENT_DEQUEUED; arg->scan_ctrl_flags |= WMI_SCAN_CHAN_STAT_EVENT; arg->n_bssids = 1; arg->bssids[0].bssid = "\xFF\xFF\xFF\xFF\xFF\xFF"; } static struct sk_buff * ath10k_wmi_op_gen_stop_scan(struct ath10k *ar, const struct wmi_stop_scan_arg *arg) { struct wmi_stop_scan_cmd *cmd; struct sk_buff *skb; u32 scan_id; u32 req_id; if (arg->req_id > 0xFFF) return ERR_PTR(-EINVAL); if (arg->req_type == WMI_SCAN_STOP_ONE && arg->u.scan_id > 0xFFF) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); scan_id = arg->u.scan_id; scan_id |= WMI_HOST_SCAN_REQ_ID_PREFIX; req_id = arg->req_id; req_id |= WMI_HOST_SCAN_REQUESTOR_ID_PREFIX; cmd = (struct wmi_stop_scan_cmd *)skb->data; cmd->req_type = __cpu_to_le32(arg->req_type); cmd->vdev_id = __cpu_to_le32(arg->u.vdev_id); cmd->scan_id = __cpu_to_le32(scan_id); cmd->scan_req_id = __cpu_to_le32(req_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi stop scan reqid %d req_type %d vdev/scan_id %d\n", arg->req_id, arg->req_type, arg->u.scan_id); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_create(struct ath10k *ar, u32 vdev_id, enum wmi_vdev_type type, enum wmi_vdev_subtype subtype, const u8 macaddr[ETH_ALEN]) { struct wmi_vdev_create_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_create_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->vdev_type = __cpu_to_le32(type); cmd->vdev_subtype = __cpu_to_le32(subtype); ether_addr_copy(cmd->vdev_macaddr.addr, macaddr); ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI vdev create: id %d type %d subtype %d macaddr %pM\n", vdev_id, type, subtype, macaddr); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_delete(struct ath10k *ar, u32 vdev_id) { struct wmi_vdev_delete_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_delete_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI vdev delete id %d\n", vdev_id); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_start(struct ath10k *ar, const struct wmi_vdev_start_request_arg *arg, bool restart) { struct wmi_vdev_start_request_cmd *cmd; struct sk_buff *skb; const char *cmdname; u32 flags = 0; if (WARN_ON(arg->hidden_ssid && !arg->ssid)) return ERR_PTR(-EINVAL); if (WARN_ON(arg->ssid_len > sizeof(cmd->ssid.ssid))) return ERR_PTR(-EINVAL); if (restart) cmdname = "restart"; else cmdname = "start"; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); if (arg->hidden_ssid) flags |= WMI_VDEV_START_HIDDEN_SSID; if (arg->pmf_enabled) flags |= WMI_VDEV_START_PMF_ENABLED; cmd = (struct wmi_vdev_start_request_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(arg->vdev_id); cmd->disable_hw_ack = __cpu_to_le32(arg->disable_hw_ack); cmd->beacon_interval = __cpu_to_le32(arg->bcn_intval); cmd->dtim_period = __cpu_to_le32(arg->dtim_period); cmd->flags = __cpu_to_le32(flags); cmd->bcn_tx_rate = __cpu_to_le32(arg->bcn_tx_rate); cmd->bcn_tx_power = __cpu_to_le32(arg->bcn_tx_power); if (arg->ssid) { cmd->ssid.ssid_len = __cpu_to_le32(arg->ssid_len); memcpy(cmd->ssid.ssid, arg->ssid, arg->ssid_len); } ath10k_wmi_put_wmi_channel(ar, &cmd->chan, &arg->channel); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi vdev %s id 0x%x flags: 0x%0X, freq %d, mode %d, ch_flags: 0x%0X, max_power: %d\n", cmdname, arg->vdev_id, flags, arg->channel.freq, arg->channel.mode, cmd->chan.flags, arg->channel.max_power); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_stop(struct ath10k *ar, u32 vdev_id) { struct wmi_vdev_stop_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_stop_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi vdev stop id 0x%x\n", vdev_id); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_up(struct ath10k *ar, u32 vdev_id, u32 aid, const u8 *bssid) { struct wmi_vdev_up_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_up_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->vdev_assoc_id = __cpu_to_le32(aid); ether_addr_copy(cmd->vdev_bssid.addr, bssid); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt vdev up id 0x%x assoc id %d bssid %pM\n", vdev_id, aid, bssid); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_down(struct ath10k *ar, u32 vdev_id) { struct wmi_vdev_down_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_down_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt vdev down id 0x%x\n", vdev_id); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_set_param(struct ath10k *ar, u32 vdev_id, u32 param_id, u32 param_value) { struct wmi_vdev_set_param_cmd *cmd; struct sk_buff *skb; if (param_id == WMI_VDEV_PARAM_UNSUPPORTED) { ath10k_dbg(ar, ATH10K_DBG_WMI, "vdev param %d not supported by firmware\n", param_id); return ERR_PTR(-EOPNOTSUPP); } skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_set_param_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->param_id = __cpu_to_le32(param_id); cmd->param_value = __cpu_to_le32(param_value); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi vdev id 0x%x set param %d value %d\n", vdev_id, param_id, param_value); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_install_key(struct ath10k *ar, const struct wmi_vdev_install_key_arg *arg) { struct wmi_vdev_install_key_cmd *cmd; struct sk_buff *skb; if (arg->key_cipher == WMI_CIPHER_NONE && arg->key_data != NULL) return ERR_PTR(-EINVAL); if (arg->key_cipher != WMI_CIPHER_NONE && arg->key_data == NULL) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd) + arg->key_len); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_install_key_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(arg->vdev_id); cmd->key_idx = __cpu_to_le32(arg->key_idx); cmd->key_flags = __cpu_to_le32(arg->key_flags); cmd->key_cipher = __cpu_to_le32(arg->key_cipher); cmd->key_len = __cpu_to_le32(arg->key_len); cmd->key_txmic_len = __cpu_to_le32(arg->key_txmic_len); cmd->key_rxmic_len = __cpu_to_le32(arg->key_rxmic_len); if (arg->macaddr) ether_addr_copy(cmd->peer_macaddr.addr, arg->macaddr); if (arg->key_data) memcpy(cmd->key_data, arg->key_data, arg->key_len); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi vdev install key idx %d cipher %d len %d\n", arg->key_idx, arg->key_cipher, arg->key_len); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_spectral_conf(struct ath10k *ar, const struct wmi_vdev_spectral_conf_arg *arg) { struct wmi_vdev_spectral_conf_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_spectral_conf_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(arg->vdev_id); cmd->scan_count = __cpu_to_le32(arg->scan_count); cmd->scan_period = __cpu_to_le32(arg->scan_period); cmd->scan_priority = __cpu_to_le32(arg->scan_priority); cmd->scan_fft_size = __cpu_to_le32(arg->scan_fft_size); cmd->scan_gc_ena = __cpu_to_le32(arg->scan_gc_ena); cmd->scan_restart_ena = __cpu_to_le32(arg->scan_restart_ena); cmd->scan_noise_floor_ref = __cpu_to_le32(arg->scan_noise_floor_ref); cmd->scan_init_delay = __cpu_to_le32(arg->scan_init_delay); cmd->scan_nb_tone_thr = __cpu_to_le32(arg->scan_nb_tone_thr); cmd->scan_str_bin_thr = __cpu_to_le32(arg->scan_str_bin_thr); cmd->scan_wb_rpt_mode = __cpu_to_le32(arg->scan_wb_rpt_mode); cmd->scan_rssi_rpt_mode = __cpu_to_le32(arg->scan_rssi_rpt_mode); cmd->scan_rssi_thr = __cpu_to_le32(arg->scan_rssi_thr); cmd->scan_pwr_format = __cpu_to_le32(arg->scan_pwr_format); cmd->scan_rpt_mode = __cpu_to_le32(arg->scan_rpt_mode); cmd->scan_bin_scale = __cpu_to_le32(arg->scan_bin_scale); cmd->scan_dbm_adj = __cpu_to_le32(arg->scan_dbm_adj); cmd->scan_chn_mask = __cpu_to_le32(arg->scan_chn_mask); return skb; } static struct sk_buff * ath10k_wmi_op_gen_vdev_spectral_enable(struct ath10k *ar, u32 vdev_id, u32 trigger, u32 enable) { struct wmi_vdev_spectral_enable_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_vdev_spectral_enable_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->trigger_cmd = __cpu_to_le32(trigger); cmd->enable_cmd = __cpu_to_le32(enable); return skb; } static struct sk_buff * ath10k_wmi_op_gen_peer_create(struct ath10k *ar, u32 vdev_id, const u8 peer_addr[ETH_ALEN], enum wmi_peer_type peer_type) { struct wmi_peer_create_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_peer_create_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, peer_addr); cmd->peer_type = __cpu_to_le32(peer_type); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer create vdev_id %d peer_addr %pM\n", vdev_id, peer_addr); return skb; } static struct sk_buff * ath10k_wmi_op_gen_peer_delete(struct ath10k *ar, u32 vdev_id, const u8 peer_addr[ETH_ALEN]) { struct wmi_peer_delete_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_peer_delete_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, peer_addr); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer delete vdev_id %d peer_addr %pM\n", vdev_id, peer_addr); return skb; } static struct sk_buff * ath10k_wmi_op_gen_peer_flush(struct ath10k *ar, u32 vdev_id, const u8 peer_addr[ETH_ALEN], u32 tid_bitmap) { struct wmi_peer_flush_tids_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_peer_flush_tids_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->peer_tid_bitmap = __cpu_to_le32(tid_bitmap); ether_addr_copy(cmd->peer_macaddr.addr, peer_addr); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer flush vdev_id %d peer_addr %pM tids %08x\n", vdev_id, peer_addr, tid_bitmap); return skb; } static struct sk_buff * ath10k_wmi_op_gen_peer_set_param(struct ath10k *ar, u32 vdev_id, const u8 *peer_addr, enum wmi_peer_param param_id, u32 param_value) { struct wmi_peer_set_param_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_peer_set_param_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->param_id = __cpu_to_le32(param_id); cmd->param_value = __cpu_to_le32(param_value); ether_addr_copy(cmd->peer_macaddr.addr, peer_addr); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi vdev %d peer 0x%pM set param %d value %d\n", vdev_id, peer_addr, param_id, param_value); return skb; } static struct sk_buff *ath10k_wmi_op_gen_gpio_config(struct ath10k *ar, u32 gpio_num, u32 input, u32 pull_type, u32 intr_mode) { struct wmi_gpio_config_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_gpio_config_cmd *)skb->data; cmd->pull_type = __cpu_to_le32(pull_type); cmd->gpio_num = __cpu_to_le32(gpio_num); cmd->input = __cpu_to_le32(input); cmd->intr_mode = __cpu_to_le32(intr_mode); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi gpio_config gpio_num 0x%08x input 0x%08x pull_type 0x%08x intr_mode 0x%08x\n", gpio_num, input, pull_type, intr_mode); return skb; } static struct sk_buff *ath10k_wmi_op_gen_gpio_output(struct ath10k *ar, u32 gpio_num, u32 set) { struct wmi_gpio_output_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_gpio_output_cmd *)skb->data; cmd->gpio_num = __cpu_to_le32(gpio_num); cmd->set = __cpu_to_le32(set); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi gpio_output gpio_num 0x%08x set 0x%08x\n", gpio_num, set); return skb; } static struct sk_buff * ath10k_wmi_op_gen_set_psmode(struct ath10k *ar, u32 vdev_id, enum wmi_sta_ps_mode psmode) { struct wmi_sta_powersave_mode_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_sta_powersave_mode_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->sta_ps_mode = __cpu_to_le32(psmode); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi set powersave id 0x%x mode %d\n", vdev_id, psmode); return skb; } static struct sk_buff * ath10k_wmi_op_gen_set_sta_ps(struct ath10k *ar, u32 vdev_id, enum wmi_sta_powersave_param param_id, u32 value) { struct wmi_sta_powersave_param_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_sta_powersave_param_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->param_id = __cpu_to_le32(param_id); cmd->param_value = __cpu_to_le32(value); ath10k_dbg(ar, ATH10K_DBG_STA, "wmi sta ps param vdev_id 0x%x param %d value %d\n", vdev_id, param_id, value); return skb; } static struct sk_buff * ath10k_wmi_op_gen_set_ap_ps(struct ath10k *ar, u32 vdev_id, const u8 *mac, enum wmi_ap_ps_peer_param param_id, u32 value) { struct wmi_ap_ps_peer_cmd *cmd; struct sk_buff *skb; if (!mac) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_ap_ps_peer_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->param_id = __cpu_to_le32(param_id); cmd->param_value = __cpu_to_le32(value); ether_addr_copy(cmd->peer_macaddr.addr, mac); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi ap ps param vdev_id 0x%X param %d value %d mac_addr %pM\n", vdev_id, param_id, value, mac); return skb; } static struct sk_buff * ath10k_wmi_op_gen_scan_chan_list(struct ath10k *ar, const struct wmi_scan_chan_list_arg *arg) { struct wmi_scan_chan_list_cmd *cmd; struct sk_buff *skb; struct wmi_channel_arg *ch; struct wmi_channel *ci; int i; skb = ath10k_wmi_alloc_skb(ar, struct_size(cmd, chan_info, arg->n_channels)); if (!skb) return ERR_PTR(-EINVAL); cmd = (struct wmi_scan_chan_list_cmd *)skb->data; cmd->num_scan_chans = __cpu_to_le32(arg->n_channels); for (i = 0; i < arg->n_channels; i++) { ch = &arg->channels[i]; ci = &cmd->chan_info[i]; ath10k_wmi_put_wmi_channel(ar, ci, ch); } return skb; } static void ath10k_wmi_peer_assoc_fill(struct ath10k *ar, void *buf, const struct wmi_peer_assoc_complete_arg *arg) { struct wmi_common_peer_assoc_complete_cmd *cmd = buf; cmd->vdev_id = __cpu_to_le32(arg->vdev_id); cmd->peer_new_assoc = __cpu_to_le32(arg->peer_reassoc ? 0 : 1); cmd->peer_associd = __cpu_to_le32(arg->peer_aid); cmd->peer_flags = __cpu_to_le32(arg->peer_flags); cmd->peer_caps = __cpu_to_le32(arg->peer_caps); cmd->peer_listen_intval = __cpu_to_le32(arg->peer_listen_intval); cmd->peer_ht_caps = __cpu_to_le32(arg->peer_ht_caps); cmd->peer_max_mpdu = __cpu_to_le32(arg->peer_max_mpdu); cmd->peer_mpdu_density = __cpu_to_le32(arg->peer_mpdu_density); cmd->peer_rate_caps = __cpu_to_le32(arg->peer_rate_caps); cmd->peer_nss = __cpu_to_le32(arg->peer_num_spatial_streams); cmd->peer_vht_caps = __cpu_to_le32(arg->peer_vht_caps); cmd->peer_phymode = __cpu_to_le32(arg->peer_phymode); ether_addr_copy(cmd->peer_macaddr.addr, arg->addr); cmd->peer_legacy_rates.num_rates = __cpu_to_le32(arg->peer_legacy_rates.num_rates); memcpy(cmd->peer_legacy_rates.rates, arg->peer_legacy_rates.rates, arg->peer_legacy_rates.num_rates); cmd->peer_ht_rates.num_rates = __cpu_to_le32(arg->peer_ht_rates.num_rates); memcpy(cmd->peer_ht_rates.rates, arg->peer_ht_rates.rates, arg->peer_ht_rates.num_rates); cmd->peer_vht_rates.rx_max_rate = __cpu_to_le32(arg->peer_vht_rates.rx_max_rate); cmd->peer_vht_rates.rx_mcs_set = __cpu_to_le32(arg->peer_vht_rates.rx_mcs_set); cmd->peer_vht_rates.tx_max_rate = __cpu_to_le32(arg->peer_vht_rates.tx_max_rate); cmd->peer_vht_rates.tx_mcs_set = __cpu_to_le32(arg->peer_vht_rates.tx_mcs_set); } static void ath10k_wmi_peer_assoc_fill_main(struct ath10k *ar, void *buf, const struct wmi_peer_assoc_complete_arg *arg) { struct wmi_main_peer_assoc_complete_cmd *cmd = buf; ath10k_wmi_peer_assoc_fill(ar, buf, arg); memset(cmd->peer_ht_info, 0, sizeof(cmd->peer_ht_info)); } static void ath10k_wmi_peer_assoc_fill_10_1(struct ath10k *ar, void *buf, const struct wmi_peer_assoc_complete_arg *arg) { ath10k_wmi_peer_assoc_fill(ar, buf, arg); } static void ath10k_wmi_peer_assoc_fill_10_2(struct ath10k *ar, void *buf, const struct wmi_peer_assoc_complete_arg *arg) { struct wmi_10_2_peer_assoc_complete_cmd *cmd = buf; int max_mcs, max_nss; u32 info0; /* TODO: Is using max values okay with firmware? */ max_mcs = 0xf; max_nss = 0xf; info0 = SM(max_mcs, WMI_PEER_ASSOC_INFO0_MAX_MCS_IDX) | SM(max_nss, WMI_PEER_ASSOC_INFO0_MAX_NSS); ath10k_wmi_peer_assoc_fill(ar, buf, arg); cmd->info0 = __cpu_to_le32(info0); } static void ath10k_wmi_peer_assoc_fill_10_4(struct ath10k *ar, void *buf, const struct wmi_peer_assoc_complete_arg *arg) { struct wmi_10_4_peer_assoc_complete_cmd *cmd = buf; ath10k_wmi_peer_assoc_fill_10_2(ar, buf, arg); cmd->peer_bw_rxnss_override = __cpu_to_le32(arg->peer_bw_rxnss_override); } static int ath10k_wmi_peer_assoc_check_arg(const struct wmi_peer_assoc_complete_arg *arg) { if (arg->peer_mpdu_density > 16) return -EINVAL; if (arg->peer_legacy_rates.num_rates > MAX_SUPPORTED_RATES) return -EINVAL; if (arg->peer_ht_rates.num_rates > MAX_SUPPORTED_RATES) return -EINVAL; return 0; } static struct sk_buff * ath10k_wmi_op_gen_peer_assoc(struct ath10k *ar, const struct wmi_peer_assoc_complete_arg *arg) { size_t len = sizeof(struct wmi_main_peer_assoc_complete_cmd); struct sk_buff *skb; int ret; ret = ath10k_wmi_peer_assoc_check_arg(arg); if (ret) return ERR_PTR(ret); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); ath10k_wmi_peer_assoc_fill_main(ar, skb->data, arg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer assoc vdev %d addr %pM (%s)\n", arg->vdev_id, arg->addr, arg->peer_reassoc ? "reassociate" : "new"); return skb; } static struct sk_buff * ath10k_wmi_10_1_op_gen_peer_assoc(struct ath10k *ar, const struct wmi_peer_assoc_complete_arg *arg) { size_t len = sizeof(struct wmi_10_1_peer_assoc_complete_cmd); struct sk_buff *skb; int ret; ret = ath10k_wmi_peer_assoc_check_arg(arg); if (ret) return ERR_PTR(ret); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); ath10k_wmi_peer_assoc_fill_10_1(ar, skb->data, arg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer assoc vdev %d addr %pM (%s)\n", arg->vdev_id, arg->addr, arg->peer_reassoc ? "reassociate" : "new"); return skb; } static struct sk_buff * ath10k_wmi_10_2_op_gen_peer_assoc(struct ath10k *ar, const struct wmi_peer_assoc_complete_arg *arg) { size_t len = sizeof(struct wmi_10_2_peer_assoc_complete_cmd); struct sk_buff *skb; int ret; ret = ath10k_wmi_peer_assoc_check_arg(arg); if (ret) return ERR_PTR(ret); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); ath10k_wmi_peer_assoc_fill_10_2(ar, skb->data, arg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer assoc vdev %d addr %pM (%s)\n", arg->vdev_id, arg->addr, arg->peer_reassoc ? "reassociate" : "new"); return skb; } static struct sk_buff * ath10k_wmi_10_4_op_gen_peer_assoc(struct ath10k *ar, const struct wmi_peer_assoc_complete_arg *arg) { size_t len = sizeof(struct wmi_10_4_peer_assoc_complete_cmd); struct sk_buff *skb; int ret; ret = ath10k_wmi_peer_assoc_check_arg(arg); if (ret) return ERR_PTR(ret); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); ath10k_wmi_peer_assoc_fill_10_4(ar, skb->data, arg); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi peer assoc vdev %d addr %pM (%s)\n", arg->vdev_id, arg->addr, arg->peer_reassoc ? "reassociate" : "new"); return skb; } static struct sk_buff * ath10k_wmi_10_2_op_gen_pdev_get_temperature(struct ath10k *ar) { struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, 0); if (!skb) return ERR_PTR(-ENOMEM); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev get temperature\n"); return skb; } static struct sk_buff * ath10k_wmi_10_2_op_gen_pdev_bss_chan_info(struct ath10k *ar, enum wmi_bss_survey_req_type type) { struct wmi_pdev_chan_info_req_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_chan_info_req_cmd *)skb->data; cmd->type = __cpu_to_le32(type); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev bss info request type %d\n", type); return skb; } /* This function assumes the beacon is already DMA mapped */ static struct sk_buff * ath10k_wmi_op_gen_beacon_dma(struct ath10k *ar, u32 vdev_id, const void *bcn, size_t bcn_len, u32 bcn_paddr, bool dtim_zero, bool deliver_cab) { struct wmi_bcn_tx_ref_cmd *cmd; struct sk_buff *skb; struct ieee80211_hdr *hdr; u16 fc; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); hdr = (struct ieee80211_hdr *)bcn; fc = le16_to_cpu(hdr->frame_control); cmd = (struct wmi_bcn_tx_ref_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->data_len = __cpu_to_le32(bcn_len); cmd->data_ptr = __cpu_to_le32(bcn_paddr); cmd->msdu_id = 0; cmd->frame_control = __cpu_to_le32(fc); cmd->flags = 0; cmd->antenna_mask = __cpu_to_le32(WMI_BCN_TX_REF_DEF_ANTENNA); if (dtim_zero) cmd->flags |= __cpu_to_le32(WMI_BCN_TX_REF_FLAG_DTIM_ZERO); if (deliver_cab) cmd->flags |= __cpu_to_le32(WMI_BCN_TX_REF_FLAG_DELIVER_CAB); return skb; } void ath10k_wmi_set_wmm_param(struct wmi_wmm_params *params, const struct wmi_wmm_params_arg *arg) { params->cwmin = __cpu_to_le32(arg->cwmin); params->cwmax = __cpu_to_le32(arg->cwmax); params->aifs = __cpu_to_le32(arg->aifs); params->txop = __cpu_to_le32(arg->txop); params->acm = __cpu_to_le32(arg->acm); params->no_ack = __cpu_to_le32(arg->no_ack); } static struct sk_buff * ath10k_wmi_op_gen_pdev_set_wmm(struct ath10k *ar, const struct wmi_wmm_params_all_arg *arg) { struct wmi_pdev_set_wmm_params *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_wmm_params *)skb->data; ath10k_wmi_set_wmm_param(&cmd->ac_be, &arg->ac_be); ath10k_wmi_set_wmm_param(&cmd->ac_bk, &arg->ac_bk); ath10k_wmi_set_wmm_param(&cmd->ac_vi, &arg->ac_vi); ath10k_wmi_set_wmm_param(&cmd->ac_vo, &arg->ac_vo); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev set wmm params\n"); return skb; } static struct sk_buff * ath10k_wmi_op_gen_request_stats(struct ath10k *ar, u32 stats_mask) { struct wmi_request_stats_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_request_stats_cmd *)skb->data; cmd->stats_id = __cpu_to_le32(stats_mask); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi request stats 0x%08x\n", stats_mask); return skb; } static struct sk_buff * ath10k_wmi_op_gen_force_fw_hang(struct ath10k *ar, enum wmi_force_fw_hang_type type, u32 delay_ms) { struct wmi_force_fw_hang_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_force_fw_hang_cmd *)skb->data; cmd->type = __cpu_to_le32(type); cmd->delay_ms = __cpu_to_le32(delay_ms); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi force fw hang %d delay %d\n", type, delay_ms); return skb; } static struct sk_buff * ath10k_wmi_op_gen_dbglog_cfg(struct ath10k *ar, u64 module_enable, u32 log_level) { struct wmi_dbglog_cfg_cmd *cmd; struct sk_buff *skb; u32 cfg; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_dbglog_cfg_cmd *)skb->data; if (module_enable) { cfg = SM(log_level, ATH10K_DBGLOG_CFG_LOG_LVL); } else { /* set back defaults, all modules with WARN level */ cfg = SM(ATH10K_DBGLOG_LEVEL_WARN, ATH10K_DBGLOG_CFG_LOG_LVL); module_enable = ~0; } cmd->module_enable = __cpu_to_le32(module_enable); cmd->module_valid = __cpu_to_le32(~0); cmd->config_enable = __cpu_to_le32(cfg); cmd->config_valid = __cpu_to_le32(ATH10K_DBGLOG_CFG_LOG_LVL_MASK); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi dbglog cfg modules %08x %08x config %08x %08x\n", __le32_to_cpu(cmd->module_enable), __le32_to_cpu(cmd->module_valid), __le32_to_cpu(cmd->config_enable), __le32_to_cpu(cmd->config_valid)); return skb; } static struct sk_buff * ath10k_wmi_10_4_op_gen_dbglog_cfg(struct ath10k *ar, u64 module_enable, u32 log_level) { struct wmi_10_4_dbglog_cfg_cmd *cmd; struct sk_buff *skb; u32 cfg; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_10_4_dbglog_cfg_cmd *)skb->data; if (module_enable) { cfg = SM(log_level, ATH10K_DBGLOG_CFG_LOG_LVL); } else { /* set back defaults, all modules with WARN level */ cfg = SM(ATH10K_DBGLOG_LEVEL_WARN, ATH10K_DBGLOG_CFG_LOG_LVL); module_enable = ~0; } cmd->module_enable = __cpu_to_le64(module_enable); cmd->module_valid = __cpu_to_le64(~0); cmd->config_enable = __cpu_to_le32(cfg); cmd->config_valid = __cpu_to_le32(ATH10K_DBGLOG_CFG_LOG_LVL_MASK); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi dbglog cfg modules 0x%016llx 0x%016llx config %08x %08x\n", __le64_to_cpu(cmd->module_enable), __le64_to_cpu(cmd->module_valid), __le32_to_cpu(cmd->config_enable), __le32_to_cpu(cmd->config_valid)); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pktlog_enable(struct ath10k *ar, u32 ev_bitmap) { struct wmi_pdev_pktlog_enable_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); ev_bitmap &= ATH10K_PKTLOG_ANY; cmd = (struct wmi_pdev_pktlog_enable_cmd *)skb->data; cmd->ev_bitmap = __cpu_to_le32(ev_bitmap); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi enable pktlog filter 0x%08x\n", ev_bitmap); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pktlog_disable(struct ath10k *ar) { struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, 0); if (!skb) return ERR_PTR(-ENOMEM); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi disable pktlog\n"); return skb; } static struct sk_buff * ath10k_wmi_op_gen_pdev_set_quiet_mode(struct ath10k *ar, u32 period, u32 duration, u32 next_offset, u32 enabled) { struct wmi_pdev_set_quiet_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_quiet_cmd *)skb->data; cmd->period = __cpu_to_le32(period); cmd->duration = __cpu_to_le32(duration); cmd->next_start = __cpu_to_le32(next_offset); cmd->enabled = __cpu_to_le32(enabled); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi quiet param: period %u duration %u enabled %d\n", period, duration, enabled); return skb; } static struct sk_buff * ath10k_wmi_op_gen_addba_clear_resp(struct ath10k *ar, u32 vdev_id, const u8 *mac) { struct wmi_addba_clear_resp_cmd *cmd; struct sk_buff *skb; if (!mac) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_addba_clear_resp_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, mac); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi addba clear resp vdev_id 0x%X mac_addr %pM\n", vdev_id, mac); return skb; } static struct sk_buff * ath10k_wmi_op_gen_addba_send(struct ath10k *ar, u32 vdev_id, const u8 *mac, u32 tid, u32 buf_size) { struct wmi_addba_send_cmd *cmd; struct sk_buff *skb; if (!mac) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_addba_send_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, mac); cmd->tid = __cpu_to_le32(tid); cmd->buffersize = __cpu_to_le32(buf_size); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi addba send vdev_id 0x%X mac_addr %pM tid %u bufsize %u\n", vdev_id, mac, tid, buf_size); return skb; } static struct sk_buff * ath10k_wmi_op_gen_addba_set_resp(struct ath10k *ar, u32 vdev_id, const u8 *mac, u32 tid, u32 status) { struct wmi_addba_setresponse_cmd *cmd; struct sk_buff *skb; if (!mac) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_addba_setresponse_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, mac); cmd->tid = __cpu_to_le32(tid); cmd->statuscode = __cpu_to_le32(status); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi addba set resp vdev_id 0x%X mac_addr %pM tid %u status %u\n", vdev_id, mac, tid, status); return skb; } static struct sk_buff * ath10k_wmi_op_gen_delba_send(struct ath10k *ar, u32 vdev_id, const u8 *mac, u32 tid, u32 initiator, u32 reason) { struct wmi_delba_send_cmd *cmd; struct sk_buff *skb; if (!mac) return ERR_PTR(-EINVAL); skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_delba_send_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, mac); cmd->tid = __cpu_to_le32(tid); cmd->initiator = __cpu_to_le32(initiator); cmd->reasoncode = __cpu_to_le32(reason); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi delba send vdev_id 0x%X mac_addr %pM tid %u initiator %u reason %u\n", vdev_id, mac, tid, initiator, reason); return skb; } static struct sk_buff * ath10k_wmi_10_2_4_op_gen_pdev_get_tpc_config(struct ath10k *ar, u32 param) { struct wmi_pdev_get_tpc_config_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_get_tpc_config_cmd *)skb->data; cmd->param = __cpu_to_le32(param); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev get tpc config param %d\n", param); return skb; } static void ath10k_wmi_fw_pdev_base_stats_fill(const struct ath10k_fw_stats_pdev *pdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s\n", "ath10k PDEV stats"); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Channel noise floor", pdev->ch_noise_floor); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "Channel TX power", pdev->chan_tx_power); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "TX frame count", pdev->tx_frame_count); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "RX frame count", pdev->rx_frame_count); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "RX clear count", pdev->rx_clear_count); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "Cycle count", pdev->cycle_count); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "PHY error count", pdev->phy_err_count); *length = len; } static void ath10k_wmi_fw_pdev_extra_stats_fill(const struct ath10k_fw_stats_pdev *pdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "RTS bad count", pdev->rts_bad); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "RTS good count", pdev->rts_good); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "FCS bad count", pdev->fcs_bad); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "No beacon count", pdev->no_beacons); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "MIB int count", pdev->mib_int_count); len += scnprintf(buf + len, buf_len - len, "\n"); *length = len; } static void ath10k_wmi_fw_pdev_tx_stats_fill(const struct ath10k_fw_stats_pdev *pdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "\n%30s\n", "ath10k PDEV TX stats"); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "HTT cookies queued", pdev->comp_queued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "HTT cookies disp.", pdev->comp_delivered); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MSDU queued", pdev->msdu_enqued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDU queued", pdev->mpdu_enqued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MSDUs dropped", pdev->wmm_drop); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Local enqued", pdev->local_enqued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Local freed", pdev->local_freed); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "HW queued", pdev->hw_queued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PPDUs reaped", pdev->hw_reaped); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Num underruns", pdev->underrun); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PPDUs cleaned", pdev->tx_abort); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs requeued", pdev->mpdus_requeued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Excessive retries", pdev->tx_ko); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "HW rate", pdev->data_rc); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Sched self triggers", pdev->self_triggers); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Dropped due to SW retries", pdev->sw_retry_failure); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Illegal rate phy errors", pdev->illgl_rate_phy_err); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Pdev continuous xretry", pdev->pdev_cont_xretry); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "TX timeout", pdev->pdev_tx_timeout); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PDEV resets", pdev->pdev_resets); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PHY underrun", pdev->phy_underrun); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDU is more than txop limit", pdev->txop_ovf); *length = len; } static void ath10k_wmi_fw_pdev_rx_stats_fill(const struct ath10k_fw_stats_pdev *pdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "\n%30s\n", "ath10k PDEV RX stats"); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Mid PPDU route change", pdev->mid_ppdu_route_change); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Tot. number of statuses", pdev->status_rcvd); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Extra frags on rings 0", pdev->r0_frags); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Extra frags on rings 1", pdev->r1_frags); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Extra frags on rings 2", pdev->r2_frags); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Extra frags on rings 3", pdev->r3_frags); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MSDUs delivered to HTT", pdev->htt_msdus); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs delivered to HTT", pdev->htt_mpdus); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MSDUs delivered to stack", pdev->loc_msdus); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs delivered to stack", pdev->loc_mpdus); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Oversized AMSDUs", pdev->oversize_amsdu); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PHY errors", pdev->phy_errs); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PHY errors drops", pdev->phy_err_drop); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDU errors (FCS, MIC, ENC)", pdev->mpdu_errs); *length = len; } static void ath10k_wmi_fw_vdev_stats_fill(const struct ath10k_fw_stats_vdev *vdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; int i; len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "vdev id", vdev->vdev_id); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "beacon snr", vdev->beacon_snr); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "data snr", vdev->data_snr); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num rx frames", vdev->num_rx_frames); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num rts fail", vdev->num_rts_fail); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num rts success", vdev->num_rts_success); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num rx err", vdev->num_rx_err); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num rx discard", vdev->num_rx_discard); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "num tx not acked", vdev->num_tx_not_acked); for (i = 0 ; i < ARRAY_SIZE(vdev->num_tx_frames); i++) len += scnprintf(buf + len, buf_len - len, "%25s [%02d] %u\n", "num tx frames", i, vdev->num_tx_frames[i]); for (i = 0 ; i < ARRAY_SIZE(vdev->num_tx_frames_retries); i++) len += scnprintf(buf + len, buf_len - len, "%25s [%02d] %u\n", "num tx frames retries", i, vdev->num_tx_frames_retries[i]); for (i = 0 ; i < ARRAY_SIZE(vdev->num_tx_frames_failures); i++) len += scnprintf(buf + len, buf_len - len, "%25s [%02d] %u\n", "num tx frames failures", i, vdev->num_tx_frames_failures[i]); for (i = 0 ; i < ARRAY_SIZE(vdev->tx_rate_history); i++) len += scnprintf(buf + len, buf_len - len, "%25s [%02d] 0x%08x\n", "tx rate history", i, vdev->tx_rate_history[i]); for (i = 0 ; i < ARRAY_SIZE(vdev->beacon_rssi_history); i++) len += scnprintf(buf + len, buf_len - len, "%25s [%02d] %u\n", "beacon rssi history", i, vdev->beacon_rssi_history[i]); len += scnprintf(buf + len, buf_len - len, "\n"); *length = len; } static void ath10k_wmi_fw_peer_stats_fill(const struct ath10k_fw_stats_peer *peer, char *buf, u32 *length, bool extended_peer) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "%30s %pM\n", "Peer MAC address", peer->peer_macaddr); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "Peer RSSI", peer->peer_rssi); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "Peer TX rate", peer->peer_tx_rate); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "Peer RX rate", peer->peer_rx_rate); if (!extended_peer) len += scnprintf(buf + len, buf_len - len, "%30s %llu\n", "Peer RX duration", peer->rx_duration); len += scnprintf(buf + len, buf_len - len, "\n"); *length = len; } static void ath10k_wmi_fw_extd_peer_stats_fill(const struct ath10k_fw_extd_stats_peer *peer, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; len += scnprintf(buf + len, buf_len - len, "%30s %pM\n", "Peer MAC address", peer->peer_macaddr); len += scnprintf(buf + len, buf_len - len, "%30s %llu\n", "Peer RX duration", peer->rx_duration); } void ath10k_wmi_main_op_fw_stats_fill(struct ath10k *ar, struct ath10k_fw_stats *fw_stats, char *buf) { u32 len = 0; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; const struct ath10k_fw_stats_pdev *pdev; const struct ath10k_fw_stats_vdev *vdev; const struct ath10k_fw_stats_peer *peer; size_t num_peers; size_t num_vdevs; spin_lock_bh(&ar->data_lock); pdev = list_first_entry_or_null(&fw_stats->pdevs, struct ath10k_fw_stats_pdev, list); if (!pdev) { ath10k_warn(ar, "failed to get pdev stats\n"); goto unlock; } num_peers = list_count_nodes(&fw_stats->peers); num_vdevs = list_count_nodes(&fw_stats->vdevs); ath10k_wmi_fw_pdev_base_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_tx_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_rx_stats_fill(pdev, buf, &len); len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k VDEV stats", num_vdevs); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(vdev, &fw_stats->vdevs, list) { ath10k_wmi_fw_vdev_stats_fill(vdev, buf, &len); } len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k PEER stats", num_peers); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(peer, &fw_stats->peers, list) { ath10k_wmi_fw_peer_stats_fill(peer, buf, &len, fw_stats->extended); } unlock: spin_unlock_bh(&ar->data_lock); if (len >= buf_len) buf[len - 1] = 0; else buf[len] = 0; } void ath10k_wmi_10x_op_fw_stats_fill(struct ath10k *ar, struct ath10k_fw_stats *fw_stats, char *buf) { unsigned int len = 0; unsigned int buf_len = ATH10K_FW_STATS_BUF_SIZE; const struct ath10k_fw_stats_pdev *pdev; const struct ath10k_fw_stats_vdev *vdev; const struct ath10k_fw_stats_peer *peer; size_t num_peers; size_t num_vdevs; spin_lock_bh(&ar->data_lock); pdev = list_first_entry_or_null(&fw_stats->pdevs, struct ath10k_fw_stats_pdev, list); if (!pdev) { ath10k_warn(ar, "failed to get pdev stats\n"); goto unlock; } num_peers = list_count_nodes(&fw_stats->peers); num_vdevs = list_count_nodes(&fw_stats->vdevs); ath10k_wmi_fw_pdev_base_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_extra_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_tx_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_rx_stats_fill(pdev, buf, &len); len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k VDEV stats", num_vdevs); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(vdev, &fw_stats->vdevs, list) { ath10k_wmi_fw_vdev_stats_fill(vdev, buf, &len); } len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k PEER stats", num_peers); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(peer, &fw_stats->peers, list) { ath10k_wmi_fw_peer_stats_fill(peer, buf, &len, fw_stats->extended); } unlock: spin_unlock_bh(&ar->data_lock); if (len >= buf_len) buf[len - 1] = 0; else buf[len] = 0; } static struct sk_buff * ath10k_wmi_op_gen_pdev_enable_adaptive_cca(struct ath10k *ar, u8 enable, u32 detect_level, u32 detect_margin) { struct wmi_pdev_set_adaptive_cca_params *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_set_adaptive_cca_params *)skb->data; cmd->enable = __cpu_to_le32(enable); cmd->cca_detect_level = __cpu_to_le32(detect_level); cmd->cca_detect_margin = __cpu_to_le32(detect_margin); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev set adaptive cca params enable:%d detection level:%d detection margin:%d\n", enable, detect_level, detect_margin); return skb; } static void ath10k_wmi_fw_vdev_stats_extd_fill(const struct ath10k_fw_stats_vdev_extd *vdev, char *buf, u32 *length) { u32 len = *length; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; u32 val; len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "vdev id", vdev->vdev_id); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "ppdu aggr count", vdev->ppdu_aggr_cnt); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "ppdu noack", vdev->ppdu_noack); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "mpdu queued", vdev->mpdu_queued); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "ppdu nonaggr count", vdev->ppdu_nonaggr_cnt); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "mpdu sw requeued", vdev->mpdu_sw_requeued); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "mpdu success retry", vdev->mpdu_suc_retry); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "mpdu success multitry", vdev->mpdu_suc_multitry); len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "mpdu fail retry", vdev->mpdu_fail_retry); val = vdev->tx_ftm_suc; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "tx ftm success", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->tx_ftm_suc_retry; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "tx ftm success retry", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->tx_ftm_fail; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "tx ftm fail", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->rx_ftmr_cnt; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "rx ftm request count", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->rx_ftmr_dup_cnt; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "rx ftm request dup count", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->rx_iftmr_cnt; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "rx initial ftm req count", MS(val, WMI_VDEV_STATS_FTM_COUNT)); val = vdev->rx_iftmr_dup_cnt; if (val & WMI_VDEV_STATS_FTM_COUNT_VALID) len += scnprintf(buf + len, buf_len - len, "%30s %u\n", "rx initial ftm req dup cnt", MS(val, WMI_VDEV_STATS_FTM_COUNT)); len += scnprintf(buf + len, buf_len - len, "\n"); *length = len; } void ath10k_wmi_10_4_op_fw_stats_fill(struct ath10k *ar, struct ath10k_fw_stats *fw_stats, char *buf) { u32 len = 0; u32 buf_len = ATH10K_FW_STATS_BUF_SIZE; const struct ath10k_fw_stats_pdev *pdev; const struct ath10k_fw_stats_vdev_extd *vdev; const struct ath10k_fw_stats_peer *peer; const struct ath10k_fw_extd_stats_peer *extd_peer; size_t num_peers; size_t num_vdevs; spin_lock_bh(&ar->data_lock); pdev = list_first_entry_or_null(&fw_stats->pdevs, struct ath10k_fw_stats_pdev, list); if (!pdev) { ath10k_warn(ar, "failed to get pdev stats\n"); goto unlock; } num_peers = list_count_nodes(&fw_stats->peers); num_vdevs = list_count_nodes(&fw_stats->vdevs); ath10k_wmi_fw_pdev_base_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_extra_stats_fill(pdev, buf, &len); ath10k_wmi_fw_pdev_tx_stats_fill(pdev, buf, &len); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "HW paused", pdev->hw_paused); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Seqs posted", pdev->seq_posted); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Seqs failed queueing", pdev->seq_failed_queueing); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Seqs completed", pdev->seq_completed); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Seqs restarted", pdev->seq_restarted); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MU Seqs posted", pdev->mu_seq_posted); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs SW flushed", pdev->mpdus_sw_flush); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs HW filtered", pdev->mpdus_hw_filter); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs truncated", pdev->mpdus_truncated); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs receive no ACK", pdev->mpdus_ack_failed); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "MPDUs expired", pdev->mpdus_expired); ath10k_wmi_fw_pdev_rx_stats_fill(pdev, buf, &len); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Num Rx Overflow errors", pdev->rx_ovfl_errs); len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k VDEV stats", num_vdevs); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(vdev, &fw_stats->vdevs, list) { ath10k_wmi_fw_vdev_stats_extd_fill(vdev, buf, &len); } len += scnprintf(buf + len, buf_len - len, "\n"); len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n", "ath10k PEER stats", num_peers); len += scnprintf(buf + len, buf_len - len, "%30s\n\n", "================="); list_for_each_entry(peer, &fw_stats->peers, list) { ath10k_wmi_fw_peer_stats_fill(peer, buf, &len, fw_stats->extended); } if (fw_stats->extended) { list_for_each_entry(extd_peer, &fw_stats->peers_extd, list) { ath10k_wmi_fw_extd_peer_stats_fill(extd_peer, buf, &len); } } unlock: spin_unlock_bh(&ar->data_lock); if (len >= buf_len) buf[len - 1] = 0; else buf[len] = 0; } int ath10k_wmi_op_get_vdev_subtype(struct ath10k *ar, enum wmi_vdev_subtype subtype) { switch (subtype) { case WMI_VDEV_SUBTYPE_NONE: return WMI_VDEV_SUBTYPE_LEGACY_NONE; case WMI_VDEV_SUBTYPE_P2P_DEVICE: return WMI_VDEV_SUBTYPE_LEGACY_P2P_DEV; case WMI_VDEV_SUBTYPE_P2P_CLIENT: return WMI_VDEV_SUBTYPE_LEGACY_P2P_CLI; case WMI_VDEV_SUBTYPE_P2P_GO: return WMI_VDEV_SUBTYPE_LEGACY_P2P_GO; case WMI_VDEV_SUBTYPE_PROXY_STA: return WMI_VDEV_SUBTYPE_LEGACY_PROXY_STA; case WMI_VDEV_SUBTYPE_MESH_11S: case WMI_VDEV_SUBTYPE_MESH_NON_11S: return -EOPNOTSUPP; } return -EOPNOTSUPP; } static int ath10k_wmi_10_2_4_op_get_vdev_subtype(struct ath10k *ar, enum wmi_vdev_subtype subtype) { switch (subtype) { case WMI_VDEV_SUBTYPE_NONE: return WMI_VDEV_SUBTYPE_10_2_4_NONE; case WMI_VDEV_SUBTYPE_P2P_DEVICE: return WMI_VDEV_SUBTYPE_10_2_4_P2P_DEV; case WMI_VDEV_SUBTYPE_P2P_CLIENT: return WMI_VDEV_SUBTYPE_10_2_4_P2P_CLI; case WMI_VDEV_SUBTYPE_P2P_GO: return WMI_VDEV_SUBTYPE_10_2_4_P2P_GO; case WMI_VDEV_SUBTYPE_PROXY_STA: return WMI_VDEV_SUBTYPE_10_2_4_PROXY_STA; case WMI_VDEV_SUBTYPE_MESH_11S: return WMI_VDEV_SUBTYPE_10_2_4_MESH_11S; case WMI_VDEV_SUBTYPE_MESH_NON_11S: return -EOPNOTSUPP; } return -EOPNOTSUPP; } static int ath10k_wmi_10_4_op_get_vdev_subtype(struct ath10k *ar, enum wmi_vdev_subtype subtype) { switch (subtype) { case WMI_VDEV_SUBTYPE_NONE: return WMI_VDEV_SUBTYPE_10_4_NONE; case WMI_VDEV_SUBTYPE_P2P_DEVICE: return WMI_VDEV_SUBTYPE_10_4_P2P_DEV; case WMI_VDEV_SUBTYPE_P2P_CLIENT: return WMI_VDEV_SUBTYPE_10_4_P2P_CLI; case WMI_VDEV_SUBTYPE_P2P_GO: return WMI_VDEV_SUBTYPE_10_4_P2P_GO; case WMI_VDEV_SUBTYPE_PROXY_STA: return WMI_VDEV_SUBTYPE_10_4_PROXY_STA; case WMI_VDEV_SUBTYPE_MESH_11S: return WMI_VDEV_SUBTYPE_10_4_MESH_11S; case WMI_VDEV_SUBTYPE_MESH_NON_11S: return WMI_VDEV_SUBTYPE_10_4_MESH_NON_11S; } return -EOPNOTSUPP; } static struct sk_buff * ath10k_wmi_10_4_ext_resource_config(struct ath10k *ar, enum wmi_host_platform_type type, u32 fw_feature_bitmap) { struct wmi_ext_resource_config_10_4_cmd *cmd; struct sk_buff *skb; u32 num_tdls_sleep_sta = 0; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); if (test_bit(WMI_SERVICE_TDLS_UAPSD_SLEEP_STA, ar->wmi.svc_map)) num_tdls_sleep_sta = TARGET_10_4_NUM_TDLS_SLEEP_STA; cmd = (struct wmi_ext_resource_config_10_4_cmd *)skb->data; cmd->host_platform_config = __cpu_to_le32(type); cmd->fw_feature_bitmap = __cpu_to_le32(fw_feature_bitmap); cmd->wlan_gpio_priority = __cpu_to_le32(ar->coex_gpio_pin); cmd->coex_version = __cpu_to_le32(WMI_NO_COEX_VERSION_SUPPORT); cmd->coex_gpio_pin1 = __cpu_to_le32(-1); cmd->coex_gpio_pin2 = __cpu_to_le32(-1); cmd->coex_gpio_pin3 = __cpu_to_le32(-1); cmd->num_tdls_vdevs = __cpu_to_le32(TARGET_10_4_NUM_TDLS_VDEVS); cmd->num_tdls_conn_table_entries = __cpu_to_le32(20); cmd->max_tdls_concurrent_sleep_sta = __cpu_to_le32(num_tdls_sleep_sta); cmd->max_tdls_concurrent_buffer_sta = __cpu_to_le32(TARGET_10_4_NUM_TDLS_BUFFER_STA); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi ext resource config host type %d firmware feature bitmap %08x\n", type, fw_feature_bitmap); return skb; } static struct sk_buff * ath10k_wmi_10_4_gen_update_fw_tdls_state(struct ath10k *ar, u32 vdev_id, enum wmi_tdls_state state) { struct wmi_10_4_tdls_set_state_cmd *cmd; struct sk_buff *skb; u32 options = 0; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); if (test_bit(WMI_SERVICE_TDLS_EXPLICIT_MODE_ONLY, ar->wmi.svc_map) && state == WMI_TDLS_ENABLE_ACTIVE) state = WMI_TDLS_ENABLE_PASSIVE; if (test_bit(WMI_SERVICE_TDLS_UAPSD_BUFFER_STA, ar->wmi.svc_map)) options |= WMI_TDLS_BUFFER_STA_EN; cmd = (struct wmi_10_4_tdls_set_state_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(vdev_id); cmd->state = __cpu_to_le32(state); cmd->notification_interval_ms = __cpu_to_le32(5000); cmd->tx_discovery_threshold = __cpu_to_le32(100); cmd->tx_teardown_threshold = __cpu_to_le32(5); cmd->rssi_teardown_threshold = __cpu_to_le32(-75); cmd->rssi_delta = __cpu_to_le32(-20); cmd->tdls_options = __cpu_to_le32(options); cmd->tdls_peer_traffic_ind_window = __cpu_to_le32(2); cmd->tdls_peer_traffic_response_timeout_ms = __cpu_to_le32(5000); cmd->tdls_puapsd_mask = __cpu_to_le32(0xf); cmd->tdls_puapsd_inactivity_time_ms = __cpu_to_le32(0); cmd->tdls_puapsd_rx_frame_threshold = __cpu_to_le32(10); cmd->teardown_notification_ms = __cpu_to_le32(10); cmd->tdls_peer_kickout_threshold = __cpu_to_le32(96); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi update fw tdls state %d for vdev %i\n", state, vdev_id); return skb; } static u32 ath10k_wmi_prepare_peer_qos(u8 uapsd_queues, u8 sp) { u32 peer_qos = 0; if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) peer_qos |= WMI_TDLS_PEER_QOS_AC_VO; if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) peer_qos |= WMI_TDLS_PEER_QOS_AC_VI; if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) peer_qos |= WMI_TDLS_PEER_QOS_AC_BK; if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) peer_qos |= WMI_TDLS_PEER_QOS_AC_BE; peer_qos |= SM(sp, WMI_TDLS_PEER_SP); return peer_qos; } static struct sk_buff * ath10k_wmi_10_4_op_gen_pdev_get_tpc_table_cmdid(struct ath10k *ar, u32 param) { struct wmi_pdev_get_tpc_table_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_get_tpc_table_cmd *)skb->data; cmd->param = __cpu_to_le32(param); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev get tpc table param:%d\n", param); return skb; } static struct sk_buff * ath10k_wmi_10_4_gen_tdls_peer_update(struct ath10k *ar, const struct wmi_tdls_peer_update_cmd_arg *arg, const struct wmi_tdls_peer_capab_arg *cap, const struct wmi_channel_arg *chan_arg) { struct wmi_10_4_tdls_peer_update_cmd *cmd; struct wmi_tdls_peer_capabilities *peer_cap; struct wmi_channel *chan; struct sk_buff *skb; u32 peer_qos; int len, chan_len; int i; /* tdls peer update cmd has place holder for one channel*/ chan_len = cap->peer_chan_len ? (cap->peer_chan_len - 1) : 0; len = sizeof(*cmd) + chan_len * sizeof(*chan); skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_10_4_tdls_peer_update_cmd *)skb->data; cmd->vdev_id = __cpu_to_le32(arg->vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, arg->addr); cmd->peer_state = __cpu_to_le32(arg->peer_state); peer_qos = ath10k_wmi_prepare_peer_qos(cap->peer_uapsd_queues, cap->peer_max_sp); peer_cap = &cmd->peer_capab; peer_cap->peer_qos = __cpu_to_le32(peer_qos); peer_cap->buff_sta_support = __cpu_to_le32(cap->buff_sta_support); peer_cap->off_chan_support = __cpu_to_le32(cap->off_chan_support); peer_cap->peer_curr_operclass = __cpu_to_le32(cap->peer_curr_operclass); peer_cap->self_curr_operclass = __cpu_to_le32(cap->self_curr_operclass); peer_cap->peer_chan_len = __cpu_to_le32(cap->peer_chan_len); peer_cap->peer_operclass_len = __cpu_to_le32(cap->peer_operclass_len); for (i = 0; i < WMI_TDLS_MAX_SUPP_OPER_CLASSES; i++) peer_cap->peer_operclass[i] = cap->peer_operclass[i]; peer_cap->is_peer_responder = __cpu_to_le32(cap->is_peer_responder); peer_cap->pref_offchan_num = __cpu_to_le32(cap->pref_offchan_num); peer_cap->pref_offchan_bw = __cpu_to_le32(cap->pref_offchan_bw); for (i = 0; i < cap->peer_chan_len; i++) { chan = (struct wmi_channel *)&peer_cap->peer_chan_list[i]; ath10k_wmi_put_wmi_channel(ar, chan, &chan_arg[i]); } ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tdls peer update vdev %i state %d n_chans %u\n", arg->vdev_id, arg->peer_state, cap->peer_chan_len); return skb; } static struct sk_buff * ath10k_wmi_10_4_gen_radar_found(struct ath10k *ar, const struct ath10k_radar_found_info *arg) { struct wmi_radar_found_info *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_radar_found_info *)skb->data; cmd->pri_min = __cpu_to_le32(arg->pri_min); cmd->pri_max = __cpu_to_le32(arg->pri_max); cmd->width_min = __cpu_to_le32(arg->width_min); cmd->width_max = __cpu_to_le32(arg->width_max); cmd->sidx_min = __cpu_to_le32(arg->sidx_min); cmd->sidx_max = __cpu_to_le32(arg->sidx_max); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi radar found pri_min %d pri_max %d width_min %d width_max %d sidx_min %d sidx_max %d\n", arg->pri_min, arg->pri_max, arg->width_min, arg->width_max, arg->sidx_min, arg->sidx_max); return skb; } static struct sk_buff * ath10k_wmi_10_4_gen_per_peer_per_tid_cfg(struct ath10k *ar, const struct wmi_per_peer_per_tid_cfg_arg *arg) { struct wmi_peer_per_tid_cfg_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); memset(skb->data, 0, sizeof(*cmd)); cmd = (struct wmi_peer_per_tid_cfg_cmd *)skb->data; cmd->vdev_id = cpu_to_le32(arg->vdev_id); ether_addr_copy(cmd->peer_macaddr.addr, arg->peer_macaddr.addr); cmd->tid = cpu_to_le32(arg->tid); cmd->ack_policy = cpu_to_le32(arg->ack_policy); cmd->aggr_control = cpu_to_le32(arg->aggr_control); cmd->rate_control = cpu_to_le32(arg->rate_ctrl); cmd->retry_count = cpu_to_le32(arg->retry_count); cmd->rcode_flags = cpu_to_le32(arg->rcode_flags); cmd->ext_tid_cfg_bitmap = cpu_to_le32(arg->ext_tid_cfg_bitmap); cmd->rtscts_ctrl = cpu_to_le32(arg->rtscts_ctrl); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi noack tid %d vdev id %d ack_policy %d aggr %u rate_ctrl %u rcflag %u retry_count %d rtscts %d ext_tid_cfg_bitmap %d mac_addr %pM\n", arg->tid, arg->vdev_id, arg->ack_policy, arg->aggr_control, arg->rate_ctrl, arg->rcode_flags, arg->retry_count, arg->rtscts_ctrl, arg->ext_tid_cfg_bitmap, arg->peer_macaddr.addr); return skb; } static struct sk_buff * ath10k_wmi_op_gen_echo(struct ath10k *ar, u32 value) { struct wmi_echo_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_echo_cmd *)skb->data; cmd->value = cpu_to_le32(value); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi echo value 0x%08x\n", value); return skb; } int ath10k_wmi_barrier(struct ath10k *ar) { int ret; int time_left; spin_lock_bh(&ar->data_lock); reinit_completion(&ar->wmi.barrier); spin_unlock_bh(&ar->data_lock); ret = ath10k_wmi_echo(ar, ATH10K_WMI_BARRIER_ECHO_ID); if (ret) { ath10k_warn(ar, "failed to submit wmi echo: %d\n", ret); return ret; } time_left = wait_for_completion_timeout(&ar->wmi.barrier, ATH10K_WMI_BARRIER_TIMEOUT_HZ); if (!time_left) return -ETIMEDOUT; return 0; } static struct sk_buff * ath10k_wmi_10_2_4_op_gen_bb_timing(struct ath10k *ar, const struct wmi_bb_timing_cfg_arg *arg) { struct wmi_pdev_bb_timing_cfg_cmd *cmd; struct sk_buff *skb; skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd)); if (!skb) return ERR_PTR(-ENOMEM); cmd = (struct wmi_pdev_bb_timing_cfg_cmd *)skb->data; cmd->bb_tx_timing = __cpu_to_le32(arg->bb_tx_timing); cmd->bb_xpa_timing = __cpu_to_le32(arg->bb_xpa_timing); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi pdev bb_tx_timing 0x%x bb_xpa_timing 0x%x\n", arg->bb_tx_timing, arg->bb_xpa_timing); return skb; } static const struct wmi_ops wmi_ops = { .rx = ath10k_wmi_op_rx, .map_svc = wmi_main_svc_map, .pull_scan = ath10k_wmi_op_pull_scan_ev, .pull_mgmt_rx = ath10k_wmi_op_pull_mgmt_rx_ev, .pull_ch_info = ath10k_wmi_op_pull_ch_info_ev, .pull_vdev_start = ath10k_wmi_op_pull_vdev_start_ev, .pull_peer_kick = ath10k_wmi_op_pull_peer_kick_ev, .pull_swba = ath10k_wmi_op_pull_swba_ev, .pull_phyerr_hdr = ath10k_wmi_op_pull_phyerr_ev_hdr, .pull_phyerr = ath10k_wmi_op_pull_phyerr_ev, .pull_svc_rdy = ath10k_wmi_main_op_pull_svc_rdy_ev, .pull_rdy = ath10k_wmi_op_pull_rdy_ev, .pull_fw_stats = ath10k_wmi_main_op_pull_fw_stats, .pull_roam_ev = ath10k_wmi_op_pull_roam_ev, .pull_echo_ev = ath10k_wmi_op_pull_echo_ev, .gen_pdev_suspend = ath10k_wmi_op_gen_pdev_suspend, .gen_pdev_resume = ath10k_wmi_op_gen_pdev_resume, .gen_pdev_set_rd = ath10k_wmi_op_gen_pdev_set_rd, .gen_pdev_set_param = ath10k_wmi_op_gen_pdev_set_param, .gen_init = ath10k_wmi_op_gen_init, .gen_start_scan = ath10k_wmi_op_gen_start_scan, .gen_stop_scan = ath10k_wmi_op_gen_stop_scan, .gen_vdev_create = ath10k_wmi_op_gen_vdev_create, .gen_vdev_delete = ath10k_wmi_op_gen_vdev_delete, .gen_vdev_start = ath10k_wmi_op_gen_vdev_start, .gen_vdev_stop = ath10k_wmi_op_gen_vdev_stop, .gen_vdev_up = ath10k_wmi_op_gen_vdev_up, .gen_vdev_down = ath10k_wmi_op_gen_vdev_down, .gen_vdev_set_param = ath10k_wmi_op_gen_vdev_set_param, .gen_vdev_install_key = ath10k_wmi_op_gen_vdev_install_key, .gen_vdev_spectral_conf = ath10k_wmi_op_gen_vdev_spectral_conf, .gen_vdev_spectral_enable = ath10k_wmi_op_gen_vdev_spectral_enable, /* .gen_vdev_wmm_conf not implemented */ .gen_peer_create = ath10k_wmi_op_gen_peer_create, .gen_peer_delete = ath10k_wmi_op_gen_peer_delete, .gen_peer_flush = ath10k_wmi_op_gen_peer_flush, .gen_peer_set_param = ath10k_wmi_op_gen_peer_set_param, .gen_peer_assoc = ath10k_wmi_op_gen_peer_assoc, .gen_set_psmode = ath10k_wmi_op_gen_set_psmode, .gen_set_sta_ps = ath10k_wmi_op_gen_set_sta_ps, .gen_set_ap_ps = ath10k_wmi_op_gen_set_ap_ps, .gen_scan_chan_list = ath10k_wmi_op_gen_scan_chan_list, .gen_beacon_dma = ath10k_wmi_op_gen_beacon_dma, .gen_pdev_set_wmm = ath10k_wmi_op_gen_pdev_set_wmm, .gen_request_stats = ath10k_wmi_op_gen_request_stats, .gen_force_fw_hang = ath10k_wmi_op_gen_force_fw_hang, .gen_mgmt_tx = ath10k_wmi_op_gen_mgmt_tx, .gen_dbglog_cfg = ath10k_wmi_op_gen_dbglog_cfg, .gen_pktlog_enable = ath10k_wmi_op_gen_pktlog_enable, .gen_pktlog_disable = ath10k_wmi_op_gen_pktlog_disable, .gen_pdev_set_quiet_mode = ath10k_wmi_op_gen_pdev_set_quiet_mode, /* .gen_pdev_get_temperature not implemented */ .gen_addba_clear_resp = ath10k_wmi_op_gen_addba_clear_resp, .gen_addba_send = ath10k_wmi_op_gen_addba_send, .gen_addba_set_resp = ath10k_wmi_op_gen_addba_set_resp, .gen_delba_send = ath10k_wmi_op_gen_delba_send, .fw_stats_fill = ath10k_wmi_main_op_fw_stats_fill, .get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype, .gen_echo = ath10k_wmi_op_gen_echo, .gen_gpio_config = ath10k_wmi_op_gen_gpio_config, .gen_gpio_output = ath10k_wmi_op_gen_gpio_output, /* .gen_bcn_tmpl not implemented */ /* .gen_prb_tmpl not implemented */ /* .gen_p2p_go_bcn_ie not implemented */ /* .gen_adaptive_qcs not implemented */ /* .gen_pdev_enable_adaptive_cca not implemented */ }; static const struct wmi_ops wmi_10_1_ops = { .rx = ath10k_wmi_10_1_op_rx, .map_svc = wmi_10x_svc_map, .pull_svc_rdy = ath10k_wmi_10x_op_pull_svc_rdy_ev, .pull_fw_stats = ath10k_wmi_10x_op_pull_fw_stats, .gen_init = ath10k_wmi_10_1_op_gen_init, .gen_pdev_set_rd = ath10k_wmi_10x_op_gen_pdev_set_rd, .gen_start_scan = ath10k_wmi_10x_op_gen_start_scan, .gen_peer_assoc = ath10k_wmi_10_1_op_gen_peer_assoc, /* .gen_pdev_get_temperature not implemented */ /* shared with main branch */ .pull_scan = ath10k_wmi_op_pull_scan_ev, .pull_mgmt_rx = ath10k_wmi_op_pull_mgmt_rx_ev, .pull_ch_info = ath10k_wmi_op_pull_ch_info_ev, .pull_vdev_start = ath10k_wmi_op_pull_vdev_start_ev, .pull_peer_kick = ath10k_wmi_op_pull_peer_kick_ev, .pull_swba = ath10k_wmi_op_pull_swba_ev, .pull_phyerr_hdr = ath10k_wmi_op_pull_phyerr_ev_hdr, .pull_phyerr = ath10k_wmi_op_pull_phyerr_ev, .pull_rdy = ath10k_wmi_op_pull_rdy_ev, .pull_roam_ev = ath10k_wmi_op_pull_roam_ev, .pull_echo_ev = ath10k_wmi_op_pull_echo_ev, .gen_pdev_suspend = ath10k_wmi_op_gen_pdev_suspend, .gen_pdev_resume = ath10k_wmi_op_gen_pdev_resume, .gen_pdev_set_param = ath10k_wmi_op_gen_pdev_set_param, .gen_stop_scan = ath10k_wmi_op_gen_stop_scan, .gen_vdev_create = ath10k_wmi_op_gen_vdev_create, .gen_vdev_delete = ath10k_wmi_op_gen_vdev_delete, .gen_vdev_start = ath10k_wmi_op_gen_vdev_start, .gen_vdev_stop = ath10k_wmi_op_gen_vdev_stop, .gen_vdev_up = ath10k_wmi_op_gen_vdev_up, .gen_vdev_down = ath10k_wmi_op_gen_vdev_down, .gen_vdev_set_param = ath10k_wmi_op_gen_vdev_set_param, .gen_vdev_install_key = ath10k_wmi_op_gen_vdev_install_key, .gen_vdev_spectral_conf = ath10k_wmi_op_gen_vdev_spectral_conf, .gen_vdev_spectral_enable = ath10k_wmi_op_gen_vdev_spectral_enable, /* .gen_vdev_wmm_conf not implemented */ .gen_peer_create = ath10k_wmi_op_gen_peer_create, .gen_peer_delete = ath10k_wmi_op_gen_peer_delete, .gen_peer_flush = ath10k_wmi_op_gen_peer_flush, .gen_peer_set_param = ath10k_wmi_op_gen_peer_set_param, .gen_set_psmode = ath10k_wmi_op_gen_set_psmode, .gen_set_sta_ps = ath10k_wmi_op_gen_set_sta_ps, .gen_set_ap_ps = ath10k_wmi_op_gen_set_ap_ps, .gen_scan_chan_list = ath10k_wmi_op_gen_scan_chan_list, .gen_beacon_dma = ath10k_wmi_op_gen_beacon_dma, .gen_pdev_set_wmm = ath10k_wmi_op_gen_pdev_set_wmm, .gen_request_stats = ath10k_wmi_op_gen_request_stats, .gen_force_fw_hang = ath10k_wmi_op_gen_force_fw_hang, .gen_mgmt_tx = ath10k_wmi_op_gen_mgmt_tx, .gen_dbglog_cfg = ath10k_wmi_op_gen_dbglog_cfg, .gen_pktlog_enable = ath10k_wmi_op_gen_pktlog_enable, .gen_pktlog_disable = ath10k_wmi_op_gen_pktlog_disable, .gen_pdev_set_quiet_mode = ath10k_wmi_op_gen_pdev_set_quiet_mode, .gen_addba_clear_resp = ath10k_wmi_op_gen_addba_clear_resp, .gen_addba_send = ath10k_wmi_op_gen_addba_send, .gen_addba_set_resp = ath10k_wmi_op_gen_addba_set_resp, .gen_delba_send = ath10k_wmi_op_gen_delba_send, .fw_stats_fill = ath10k_wmi_10x_op_fw_stats_fill, .get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype, .gen_echo = ath10k_wmi_op_gen_echo, .gen_gpio_config = ath10k_wmi_op_gen_gpio_config, .gen_gpio_output = ath10k_wmi_op_gen_gpio_output, /* .gen_bcn_tmpl not implemented */ /* .gen_prb_tmpl not implemented */ /* .gen_p2p_go_bcn_ie not implemented */ /* .gen_adaptive_qcs not implemented */ /* .gen_pdev_enable_adaptive_cca not implemented */ }; static const struct wmi_ops wmi_10_2_ops = { .rx = ath10k_wmi_10_2_op_rx, .pull_fw_stats = ath10k_wmi_10_2_op_pull_fw_stats, .gen_init = ath10k_wmi_10_2_op_gen_init, .gen_peer_assoc = ath10k_wmi_10_2_op_gen_peer_assoc, /* .gen_pdev_get_temperature not implemented */ /* shared with 10.1 */ .map_svc = wmi_10x_svc_map, .pull_svc_rdy = ath10k_wmi_10x_op_pull_svc_rdy_ev, .gen_pdev_set_rd = ath10k_wmi_10x_op_gen_pdev_set_rd, .gen_start_scan = ath10k_wmi_10x_op_gen_start_scan, .gen_echo = ath10k_wmi_op_gen_echo, .pull_scan = ath10k_wmi_op_pull_scan_ev, .pull_mgmt_rx = ath10k_wmi_op_pull_mgmt_rx_ev, .pull_ch_info = ath10k_wmi_op_pull_ch_info_ev, .pull_vdev_start = ath10k_wmi_op_pull_vdev_start_ev, .pull_peer_kick = ath10k_wmi_op_pull_peer_kick_ev, .pull_swba = ath10k_wmi_op_pull_swba_ev, .pull_phyerr_hdr = ath10k_wmi_op_pull_phyerr_ev_hdr, .pull_phyerr = ath10k_wmi_op_pull_phyerr_ev, .pull_rdy = ath10k_wmi_op_pull_rdy_ev, .pull_roam_ev = ath10k_wmi_op_pull_roam_ev, .pull_echo_ev = ath10k_wmi_op_pull_echo_ev, .gen_pdev_suspend = ath10k_wmi_op_gen_pdev_suspend, .gen_pdev_resume = ath10k_wmi_op_gen_pdev_resume, .gen_pdev_set_param = ath10k_wmi_op_gen_pdev_set_param, .gen_stop_scan = ath10k_wmi_op_gen_stop_scan, .gen_vdev_create = ath10k_wmi_op_gen_vdev_create, .gen_vdev_delete = ath10k_wmi_op_gen_vdev_delete, .gen_vdev_start = ath10k_wmi_op_gen_vdev_start, .gen_vdev_stop = ath10k_wmi_op_gen_vdev_stop, .gen_vdev_up = ath10k_wmi_op_gen_vdev_up, .gen_vdev_down = ath10k_wmi_op_gen_vdev_down, .gen_vdev_set_param = ath10k_wmi_op_gen_vdev_set_param, .gen_vdev_install_key = ath10k_wmi_op_gen_vdev_install_key, .gen_vdev_spectral_conf = ath10k_wmi_op_gen_vdev_spectral_conf, .gen_vdev_spectral_enable = ath10k_wmi_op_gen_vdev_spectral_enable, /* .gen_vdev_wmm_conf not implemented */ .gen_peer_create = ath10k_wmi_op_gen_peer_create, .gen_peer_delete = ath10k_wmi_op_gen_peer_delete, .gen_peer_flush = ath10k_wmi_op_gen_peer_flush, .gen_pdev_set_base_macaddr = ath10k_wmi_op_gen_pdev_set_base_macaddr, .gen_peer_set_param = ath10k_wmi_op_gen_peer_set_param, .gen_set_psmode = ath10k_wmi_op_gen_set_psmode, .gen_set_sta_ps = ath10k_wmi_op_gen_set_sta_ps, .gen_set_ap_ps = ath10k_wmi_op_gen_set_ap_ps, .gen_scan_chan_list = ath10k_wmi_op_gen_scan_chan_list, .gen_beacon_dma = ath10k_wmi_op_gen_beacon_dma, .gen_pdev_set_wmm = ath10k_wmi_op_gen_pdev_set_wmm, .gen_request_stats = ath10k_wmi_op_gen_request_stats, .gen_force_fw_hang = ath10k_wmi_op_gen_force_fw_hang, .gen_mgmt_tx = ath10k_wmi_op_gen_mgmt_tx, .gen_dbglog_cfg = ath10k_wmi_op_gen_dbglog_cfg, .gen_pktlog_enable = ath10k_wmi_op_gen_pktlog_enable, .gen_pktlog_disable = ath10k_wmi_op_gen_pktlog_disable, .gen_pdev_set_quiet_mode = ath10k_wmi_op_gen_pdev_set_quiet_mode, .gen_addba_clear_resp = ath10k_wmi_op_gen_addba_clear_resp, .gen_addba_send = ath10k_wmi_op_gen_addba_send, .gen_addba_set_resp = ath10k_wmi_op_gen_addba_set_resp, .gen_delba_send = ath10k_wmi_op_gen_delba_send, .fw_stats_fill = ath10k_wmi_10x_op_fw_stats_fill, .get_vdev_subtype = ath10k_wmi_op_get_vdev_subtype, .gen_gpio_config = ath10k_wmi_op_gen_gpio_config, .gen_gpio_output = ath10k_wmi_op_gen_gpio_output, /* .gen_pdev_enable_adaptive_cca not implemented */ }; static const struct wmi_ops wmi_10_2_4_ops = { .rx = ath10k_wmi_10_2_op_rx, .pull_fw_stats = ath10k_wmi_10_2_4_op_pull_fw_stats, .gen_init = ath10k_wmi_10_2_op_gen_init, .gen_peer_assoc = ath10k_wmi_10_2_op_gen_peer_assoc, .gen_pdev_get_temperature = ath10k_wmi_10_2_op_gen_pdev_get_temperature, .gen_pdev_bss_chan_info_req = ath10k_wmi_10_2_op_gen_pdev_bss_chan_info, /* shared with 10.1 */ .map_svc = wmi_10x_svc_map, .pull_svc_rdy = ath10k_wmi_10x_op_pull_svc_rdy_ev, .gen_pdev_set_rd = ath10k_wmi_10x_op_gen_pdev_set_rd, .gen_start_scan = ath10k_wmi_10x_op_gen_start_scan, .gen_echo = ath10k_wmi_op_gen_echo, .pull_scan = ath10k_wmi_op_pull_scan_ev, .pull_mgmt_rx = ath10k_wmi_op_pull_mgmt_rx_ev, .pull_ch_info = ath10k_wmi_op_pull_ch_info_ev, .pull_vdev_start = ath10k_wmi_op_pull_vdev_start_ev, .pull_peer_kick = ath10k_wmi_op_pull_peer_kick_ev, .pull_swba = ath10k_wmi_10_2_4_op_pull_swba_ev, .pull_phyerr_hdr = ath10k_wmi_op_pull_phyerr_ev_hdr, .pull_phyerr = ath10k_wmi_op_pull_phyerr_ev, .pull_rdy = ath10k_wmi_op_pull_rdy_ev, .pull_roam_ev = ath10k_wmi_op_pull_roam_ev, .pull_echo_ev = ath10k_wmi_op_pull_echo_ev, .gen_pdev_suspend = ath10k_wmi_op_gen_pdev_suspend, .gen_pdev_resume = ath10k_wmi_op_gen_pdev_resume, .gen_pdev_set_param = ath10k_wmi_op_gen_pdev_set_param, .gen_stop_scan = ath10k_wmi_op_gen_stop_scan, .gen_vdev_create = ath10k_wmi_op_gen_vdev_create, .gen_vdev_delete = ath10k_wmi_op_gen_vdev_delete, .gen_vdev_start = ath10k_wmi_op_gen_vdev_start, .gen_vdev_stop = ath10k_wmi_op_gen_vdev_stop, .gen_vdev_up = ath10k_wmi_op_gen_vdev_up, .gen_vdev_down = ath10k_wmi_op_gen_vdev_down, .gen_vdev_set_param = ath10k_wmi_op_gen_vdev_set_param, .gen_vdev_install_key = ath10k_wmi_op_gen_vdev_install_key, .gen_vdev_spectral_conf = ath10k_wmi_op_gen_vdev_spectral_conf, .gen_vdev_spectral_enable = ath10k_wmi_op_gen_vdev_spectral_enable, .gen_peer_create = ath10k_wmi_op_gen_peer_create, .gen_peer_delete = ath10k_wmi_op_gen_peer_delete, .gen_peer_flush = ath10k_wmi_op_gen_peer_flush, .gen_peer_set_param = ath10k_wmi_op_gen_peer_set_param, .gen_set_psmode = ath10k_wmi_op_gen_set_psmode, .gen_set_sta_ps = ath10k_wmi_op_gen_set_sta_ps, .gen_set_ap_ps = ath10k_wmi_op_gen_set_ap_ps, .gen_scan_chan_list = ath10k_wmi_op_gen_scan_chan_list, .gen_beacon_dma = ath10k_wmi_op_gen_beacon_dma, .gen_pdev_set_wmm = ath10k_wmi_op_gen_pdev_set_wmm, .gen_request_stats = ath10k_wmi_op_gen_request_stats, .gen_force_fw_hang = ath10k_wmi_op_gen_force_fw_hang, .gen_mgmt_tx = ath10k_wmi_op_gen_mgmt_tx, .gen_dbglog_cfg = ath10k_wmi_op_gen_dbglog_cfg, .gen_pktlog_enable = ath10k_wmi_op_gen_pktlog_enable, .gen_pktlog_disable = ath10k_wmi_op_gen_pktlog_disable, .gen_pdev_set_quiet_mode = ath10k_wmi_op_gen_pdev_set_quiet_mode, .gen_addba_clear_resp = ath10k_wmi_op_gen_addba_clear_resp, .gen_addba_send = ath10k_wmi_op_gen_addba_send, .gen_addba_set_resp = ath10k_wmi_op_gen_addba_set_resp, .gen_delba_send = ath10k_wmi_op_gen_delba_send, .gen_pdev_get_tpc_config = ath10k_wmi_10_2_4_op_gen_pdev_get_tpc_config, .fw_stats_fill = ath10k_wmi_10x_op_fw_stats_fill, .gen_pdev_enable_adaptive_cca = ath10k_wmi_op_gen_pdev_enable_adaptive_cca, .get_vdev_subtype = ath10k_wmi_10_2_4_op_get_vdev_subtype, .gen_bb_timing = ath10k_wmi_10_2_4_op_gen_bb_timing, .gen_gpio_config = ath10k_wmi_op_gen_gpio_config, .gen_gpio_output = ath10k_wmi_op_gen_gpio_output, /* .gen_bcn_tmpl not implemented */ /* .gen_prb_tmpl not implemented */ /* .gen_p2p_go_bcn_ie not implemented */ /* .gen_adaptive_qcs not implemented */ }; static const struct wmi_ops wmi_10_4_ops = { .rx = ath10k_wmi_10_4_op_rx, .map_svc = wmi_10_4_svc_map, .pull_fw_stats = ath10k_wmi_10_4_op_pull_fw_stats, .pull_scan = ath10k_wmi_op_pull_scan_ev, .pull_mgmt_rx = ath10k_wmi_10_4_op_pull_mgmt_rx_ev, .pull_ch_info = ath10k_wmi_10_4_op_pull_ch_info_ev, .pull_vdev_start = ath10k_wmi_op_pull_vdev_start_ev, .pull_peer_kick = ath10k_wmi_op_pull_peer_kick_ev, .pull_swba = ath10k_wmi_10_4_op_pull_swba_ev, .pull_phyerr_hdr = ath10k_wmi_10_4_op_pull_phyerr_ev_hdr, .pull_phyerr = ath10k_wmi_10_4_op_pull_phyerr_ev, .pull_svc_rdy = ath10k_wmi_main_op_pull_svc_rdy_ev, .pull_rdy = ath10k_wmi_op_pull_rdy_ev, .pull_roam_ev = ath10k_wmi_op_pull_roam_ev, .pull_dfs_status_ev = ath10k_wmi_10_4_op_pull_dfs_status_ev, .get_txbf_conf_scheme = ath10k_wmi_10_4_txbf_conf_scheme, .gen_pdev_suspend = ath10k_wmi_op_gen_pdev_suspend, .gen_pdev_resume = ath10k_wmi_op_gen_pdev_resume, .gen_pdev_set_base_macaddr = ath10k_wmi_op_gen_pdev_set_base_macaddr, .gen_pdev_set_rd = ath10k_wmi_10x_op_gen_pdev_set_rd, .gen_pdev_set_param = ath10k_wmi_op_gen_pdev_set_param, .gen_init = ath10k_wmi_10_4_op_gen_init, .gen_start_scan = ath10k_wmi_op_gen_start_scan, .gen_stop_scan = ath10k_wmi_op_gen_stop_scan, .gen_vdev_create = ath10k_wmi_op_gen_vdev_create, .gen_vdev_delete = ath10k_wmi_op_gen_vdev_delete, .gen_vdev_start = ath10k_wmi_op_gen_vdev_start, .gen_vdev_stop = ath10k_wmi_op_gen_vdev_stop, .gen_vdev_up = ath10k_wmi_op_gen_vdev_up, .gen_vdev_down = ath10k_wmi_op_gen_vdev_down, .gen_vdev_set_param = ath10k_wmi_op_gen_vdev_set_param, .gen_vdev_install_key = ath10k_wmi_op_gen_vdev_install_key, .gen_vdev_spectral_conf = ath10k_wmi_op_gen_vdev_spectral_conf, .gen_vdev_spectral_enable = ath10k_wmi_op_gen_vdev_spectral_enable, .gen_peer_create = ath10k_wmi_op_gen_peer_create, .gen_peer_delete = ath10k_wmi_op_gen_peer_delete, .gen_peer_flush = ath10k_wmi_op_gen_peer_flush, .gen_peer_set_param = ath10k_wmi_op_gen_peer_set_param, .gen_peer_assoc = ath10k_wmi_10_4_op_gen_peer_assoc, .gen_set_psmode = ath10k_wmi_op_gen_set_psmode, .gen_set_sta_ps = ath10k_wmi_op_gen_set_sta_ps, .gen_set_ap_ps = ath10k_wmi_op_gen_set_ap_ps, .gen_scan_chan_list = ath10k_wmi_op_gen_scan_chan_list, .gen_beacon_dma = ath10k_wmi_op_gen_beacon_dma, .gen_pdev_set_wmm = ath10k_wmi_op_gen_pdev_set_wmm, .gen_force_fw_hang = ath10k_wmi_op_gen_force_fw_hang, .gen_mgmt_tx = ath10k_wmi_op_gen_mgmt_tx, .gen_dbglog_cfg = ath10k_wmi_10_4_op_gen_dbglog_cfg, .gen_pktlog_enable = ath10k_wmi_op_gen_pktlog_enable, .gen_pktlog_disable = ath10k_wmi_op_gen_pktlog_disable, .gen_pdev_set_quiet_mode = ath10k_wmi_op_gen_pdev_set_quiet_mode, .gen_addba_clear_resp = ath10k_wmi_op_gen_addba_clear_resp, .gen_addba_send = ath10k_wmi_op_gen_addba_send, .gen_addba_set_resp = ath10k_wmi_op_gen_addba_set_resp, .gen_delba_send = ath10k_wmi_op_gen_delba_send, .fw_stats_fill = ath10k_wmi_10_4_op_fw_stats_fill, .ext_resource_config = ath10k_wmi_10_4_ext_resource_config, .gen_update_fw_tdls_state = ath10k_wmi_10_4_gen_update_fw_tdls_state, .gen_tdls_peer_update = ath10k_wmi_10_4_gen_tdls_peer_update, .gen_pdev_get_tpc_table_cmdid = ath10k_wmi_10_4_op_gen_pdev_get_tpc_table_cmdid, .gen_radar_found = ath10k_wmi_10_4_gen_radar_found, .gen_per_peer_per_tid_cfg = ath10k_wmi_10_4_gen_per_peer_per_tid_cfg, /* shared with 10.2 */ .pull_echo_ev = ath10k_wmi_op_pull_echo_ev, .gen_request_stats = ath10k_wmi_op_gen_request_stats, .gen_pdev_get_temperature = ath10k_wmi_10_2_op_gen_pdev_get_temperature, .get_vdev_subtype = ath10k_wmi_10_4_op_get_vdev_subtype, .gen_pdev_bss_chan_info_req = ath10k_wmi_10_2_op_gen_pdev_bss_chan_info, .gen_echo = ath10k_wmi_op_gen_echo, .gen_pdev_get_tpc_config = ath10k_wmi_10_2_4_op_gen_pdev_get_tpc_config, .gen_gpio_config = ath10k_wmi_op_gen_gpio_config, .gen_gpio_output = ath10k_wmi_op_gen_gpio_output, }; int ath10k_wmi_attach(struct ath10k *ar) { switch (ar->running_fw->fw_file.wmi_op_version) { case ATH10K_FW_WMI_OP_VERSION_10_4: ar->wmi.ops = &wmi_10_4_ops; ar->wmi.cmd = &wmi_10_4_cmd_map; ar->wmi.vdev_param = &wmi_10_4_vdev_param_map; ar->wmi.pdev_param = &wmi_10_4_pdev_param_map; ar->wmi.peer_param = &wmi_peer_param_map; ar->wmi.peer_flags = &wmi_10_2_peer_flags_map; ar->wmi_key_cipher = wmi_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_10_2_4: ar->wmi.cmd = &wmi_10_2_4_cmd_map; ar->wmi.ops = &wmi_10_2_4_ops; ar->wmi.vdev_param = &wmi_10_2_4_vdev_param_map; ar->wmi.pdev_param = &wmi_10_2_4_pdev_param_map; ar->wmi.peer_param = &wmi_peer_param_map; ar->wmi.peer_flags = &wmi_10_2_peer_flags_map; ar->wmi_key_cipher = wmi_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_10_2: ar->wmi.cmd = &wmi_10_2_cmd_map; ar->wmi.ops = &wmi_10_2_ops; ar->wmi.vdev_param = &wmi_10x_vdev_param_map; ar->wmi.pdev_param = &wmi_10x_pdev_param_map; ar->wmi.peer_param = &wmi_peer_param_map; ar->wmi.peer_flags = &wmi_10_2_peer_flags_map; ar->wmi_key_cipher = wmi_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_10_1: ar->wmi.cmd = &wmi_10x_cmd_map; ar->wmi.ops = &wmi_10_1_ops; ar->wmi.vdev_param = &wmi_10x_vdev_param_map; ar->wmi.pdev_param = &wmi_10x_pdev_param_map; ar->wmi.peer_param = &wmi_peer_param_map; ar->wmi.peer_flags = &wmi_10x_peer_flags_map; ar->wmi_key_cipher = wmi_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_MAIN: ar->wmi.cmd = &wmi_cmd_map; ar->wmi.ops = &wmi_ops; ar->wmi.vdev_param = &wmi_vdev_param_map; ar->wmi.pdev_param = &wmi_pdev_param_map; ar->wmi.peer_param = &wmi_peer_param_map; ar->wmi.peer_flags = &wmi_peer_flags_map; ar->wmi_key_cipher = wmi_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_TLV: ath10k_wmi_tlv_attach(ar); ar->wmi_key_cipher = wmi_tlv_key_cipher_suites; break; case ATH10K_FW_WMI_OP_VERSION_UNSET: case ATH10K_FW_WMI_OP_VERSION_MAX: ath10k_err(ar, "unsupported WMI op version: %d\n", ar->running_fw->fw_file.wmi_op_version); return -EINVAL; } init_completion(&ar->wmi.service_ready); init_completion(&ar->wmi.unified_ready); init_completion(&ar->wmi.barrier); init_completion(&ar->wmi.radar_confirm); INIT_WORK(&ar->svc_rdy_work, ath10k_wmi_event_service_ready_work); INIT_WORK(&ar->radar_confirmation_work, ath10k_radar_confirmation_work); if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF, ar->running_fw->fw_file.fw_features)) { idr_init(&ar->wmi.mgmt_pending_tx); } return 0; } void ath10k_wmi_free_host_mem(struct ath10k *ar) { int i; /* free the host memory chunks requested by firmware */ for (i = 0; i < ar->wmi.num_mem_chunks; i++) { dma_free_coherent(ar->dev, ar->wmi.mem_chunks[i].len, ar->wmi.mem_chunks[i].vaddr, ar->wmi.mem_chunks[i].paddr); } ar->wmi.num_mem_chunks = 0; } static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr, void *ctx) { struct ath10k_mgmt_tx_pkt_addr *pkt_addr = ptr; struct ath10k *ar = ctx; struct sk_buff *msdu; ath10k_dbg(ar, ATH10K_DBG_WMI, "force cleanup mgmt msdu_id %u\n", msdu_id); msdu = pkt_addr->vaddr; dma_unmap_single(ar->dev, pkt_addr->paddr, msdu->len, DMA_TO_DEVICE); ieee80211_free_txskb(ar->hw, msdu); kfree(pkt_addr); return 0; } void ath10k_wmi_detach(struct ath10k *ar) { if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF, ar->running_fw->fw_file.fw_features)) { spin_lock_bh(&ar->data_lock); idr_for_each(&ar->wmi.mgmt_pending_tx, ath10k_wmi_mgmt_tx_clean_up_pending, ar); idr_destroy(&ar->wmi.mgmt_pending_tx); spin_unlock_bh(&ar->data_lock); } cancel_work_sync(&ar->svc_rdy_work); dev_kfree_skb(ar->svc_rdy_skb); }
35 35 35 35 35 35 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 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/rculist.h> #include <net/caif/cfpkt.h> #include <net/caif/cfmuxl.h> #include <net/caif/cfsrvl.h> #include <net/caif/cffrml.h> #define container_obj(layr) container_of(layr, struct cfmuxl, layer) #define CAIF_CTRL_CHANNEL 0 #define UP_CACHE_SIZE 8 #define DN_CACHE_SIZE 8 struct cfmuxl { struct cflayer layer; struct list_head srvl_list; struct list_head frml_list; struct cflayer *up_cache[UP_CACHE_SIZE]; struct cflayer *dn_cache[DN_CACHE_SIZE]; /* * Set when inserting or removing downwards layers. */ spinlock_t transmit_lock; /* * Set when inserting or removing upwards layers. */ spinlock_t receive_lock; }; static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt); static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid); static struct cflayer *get_up(struct cfmuxl *muxl, u16 id); struct cflayer *cfmuxl_create(void) { struct cfmuxl *this = kzalloc(sizeof(struct cfmuxl), GFP_ATOMIC); if (!this) return NULL; this->layer.receive = cfmuxl_receive; this->layer.transmit = cfmuxl_transmit; this->layer.ctrlcmd = cfmuxl_ctrlcmd; INIT_LIST_HEAD(&this->srvl_list); INIT_LIST_HEAD(&this->frml_list); spin_lock_init(&this->transmit_lock); spin_lock_init(&this->receive_lock); snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "mux"); return &this->layer; } int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *dn, u8 phyid) { struct cfmuxl *muxl = (struct cfmuxl *) layr; spin_lock_bh(&muxl->transmit_lock); list_add_rcu(&dn->node, &muxl->frml_list); spin_unlock_bh(&muxl->transmit_lock); return 0; } static struct cflayer *get_from_id(struct list_head *list, u16 id) { struct cflayer *lyr; list_for_each_entry_rcu(lyr, list, node) { if (lyr->id == id) return lyr; } return NULL; } int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *old; spin_lock_bh(&muxl->receive_lock); /* Two entries with same id is wrong, so remove old layer from mux */ old = get_from_id(&muxl->srvl_list, linkid); if (old != NULL) list_del_rcu(&old->node); list_add_rcu(&up->node, &muxl->srvl_list); spin_unlock_bh(&muxl->receive_lock); return 0; } struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *dn; int idx = phyid % DN_CACHE_SIZE; spin_lock_bh(&muxl->transmit_lock); RCU_INIT_POINTER(muxl->dn_cache[idx], NULL); dn = get_from_id(&muxl->frml_list, phyid); if (dn == NULL) goto out; list_del_rcu(&dn->node); caif_assert(dn != NULL); out: spin_unlock_bh(&muxl->transmit_lock); return dn; } static struct cflayer *get_up(struct cfmuxl *muxl, u16 id) { struct cflayer *up; int idx = id % UP_CACHE_SIZE; up = rcu_dereference(muxl->up_cache[idx]); if (up == NULL || up->id != id) { spin_lock_bh(&muxl->receive_lock); up = get_from_id(&muxl->srvl_list, id); rcu_assign_pointer(muxl->up_cache[idx], up); spin_unlock_bh(&muxl->receive_lock); } return up; } static struct cflayer *get_dn(struct cfmuxl *muxl, struct dev_info *dev_info) { struct cflayer *dn; int idx = dev_info->id % DN_CACHE_SIZE; dn = rcu_dereference(muxl->dn_cache[idx]); if (dn == NULL || dn->id != dev_info->id) { spin_lock_bh(&muxl->transmit_lock); dn = get_from_id(&muxl->frml_list, dev_info->id); rcu_assign_pointer(muxl->dn_cache[idx], dn); spin_unlock_bh(&muxl->transmit_lock); } return dn; } struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id) { struct cflayer *up; struct cfmuxl *muxl = container_obj(layr); int idx = id % UP_CACHE_SIZE; if (id == 0) { pr_warn("Trying to remove control layer\n"); return NULL; } spin_lock_bh(&muxl->receive_lock); up = get_from_id(&muxl->srvl_list, id); if (up == NULL) goto out; RCU_INIT_POINTER(muxl->up_cache[idx], NULL); list_del_rcu(&up->node); out: spin_unlock_bh(&muxl->receive_lock); return up; } static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt) { int ret; struct cfmuxl *muxl = container_obj(layr); u8 id; struct cflayer *up; if (cfpkt_extr_head(pkt, &id, 1) < 0) { pr_err("erroneous Caif Packet\n"); cfpkt_destroy(pkt); return -EPROTO; } rcu_read_lock(); up = get_up(muxl, id); if (up == NULL) { pr_debug("Received data on unknown link ID = %d (0x%x)" " up == NULL", id, id); cfpkt_destroy(pkt); /* * Don't return ERROR, since modem misbehaves and sends out * flow on before linksetup response. */ rcu_read_unlock(); return /* CFGLU_EPROT; */ 0; } /* We can't hold rcu_lock during receive, so take a ref count instead */ cfsrvl_get(up); rcu_read_unlock(); ret = up->receive(up, pkt); cfsrvl_put(up); return ret; } static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt) { struct cfmuxl *muxl = container_obj(layr); int err; u8 linkid; struct cflayer *dn; struct caif_payload_info *info = cfpkt_info(pkt); BUG_ON(!info); rcu_read_lock(); dn = get_dn(muxl, info->dev_info); if (dn == NULL) { pr_debug("Send data on unknown phy ID = %d (0x%x)\n", info->dev_info->id, info->dev_info->id); rcu_read_unlock(); cfpkt_destroy(pkt); return -ENOTCONN; } info->hdr_len += 1; linkid = info->channel_id; cfpkt_add_head(pkt, &linkid, 1); /* We can't hold rcu_lock during receive, so take a ref count instead */ cffrml_hold(dn); rcu_read_unlock(); err = dn->transmit(dn, pkt); cffrml_put(dn); return err; } static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *layer; rcu_read_lock(); list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && layer->id != 0) cfmuxl_remove_uplayer(layr, layer->id); /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); } } rcu_read_unlock(); }
20 23 21 7 16 2 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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H #include <linux/icmpv6.h> #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/inet_frag.h> enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP6_DEFRAG_CONNTRACK_OUT, __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, }; /* * Equivalent of ipv4 struct ip */ struct frag_queue { struct inet_frag_queue q; int iif; __u16 nhoffset; u8 ecn; }; #if IS_ENABLED(CONFIG_IPV6) static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); const struct frag_v6_compare_key *key = a; q->key.v6 = *key; fq->ecn = 0; } static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v6, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline int ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v6_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static inline void ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; struct sk_buff *head; rcu_read_lock(); /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(fq->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; fq->q.flags |= INET_FRAG_DROP; inet_frag_kill(&fq->q); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&fq->q); if (!head) goto out; head->dev = dev; spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); goto out_rcu_unlock; out: spin_unlock(&fq->q.lock); out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } /* Check if the upper layer header is truncated in the first fragment. */ static inline bool ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) { u8 nexthdr = *nexthdrp; __be16 frag_off; int offset; offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); if (offset < 0 || (frag_off & htons(IP6_OFFSET))) return false; switch (nexthdr) { case NEXTHDR_TCP: offset += sizeof(struct tcphdr); break; case NEXTHDR_UDP: offset += sizeof(struct udphdr); break; case NEXTHDR_ICMP: offset += sizeof(struct icmp6hdr); break; default: offset += 1; } if (offset > skb->len) return true; return false; } #endif #endif
3 1 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 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 // SPDX-License-Identifier: GPL-2.0 /* * QNX6 file system, Linux implementation. * * Version : 1.0.0 * * History : * * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release. * */ #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/crc32.h> #include "qnx6.h" static void qnx6_mmi_copy_sb(struct qnx6_super_block *qsb, struct qnx6_mmi_super_block *sb) { qsb->sb_magic = sb->sb_magic; qsb->sb_checksum = sb->sb_checksum; qsb->sb_serial = sb->sb_serial; qsb->sb_blocksize = sb->sb_blocksize; qsb->sb_num_inodes = sb->sb_num_inodes; qsb->sb_free_inodes = sb->sb_free_inodes; qsb->sb_num_blocks = sb->sb_num_blocks; qsb->sb_free_blocks = sb->sb_free_blocks; /* the rest of the superblock is the same */ memcpy(&qsb->Inode, &sb->Inode, sizeof(sb->Inode)); memcpy(&qsb->Bitmap, &sb->Bitmap, sizeof(sb->Bitmap)); memcpy(&qsb->Longfile, &sb->Longfile, sizeof(sb->Longfile)); } struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent) { struct buffer_head *bh1, *bh2 = NULL; struct qnx6_mmi_super_block *sb1, *sb2; struct qnx6_super_block *qsb = NULL; struct qnx6_sb_info *sbi; __u64 offset; /* Check the superblock signatures start with the first superblock */ bh1 = sb_bread(s, 0); if (!bh1) { pr_err("Unable to read first mmi superblock\n"); return NULL; } sb1 = (struct qnx6_mmi_super_block *)bh1->b_data; sbi = QNX6_SB(s); if (fs32_to_cpu(sbi, sb1->sb_magic) != QNX6_SUPER_MAGIC) { if (!silent) { pr_err("wrong signature (magic) in superblock #1.\n"); goto out; } } /* checksum check - start at byte 8 and end at byte 512 */ if (fs32_to_cpu(sbi, sb1->sb_checksum) != crc32_be(0, (char *)(bh1->b_data + 8), 504)) { pr_err("superblock #1 checksum error\n"); goto out; } /* calculate second superblock blocknumber */ offset = fs32_to_cpu(sbi, sb1->sb_num_blocks) + QNX6_SUPERBLOCK_AREA / fs32_to_cpu(sbi, sb1->sb_blocksize); /* set new blocksize */ if (!sb_set_blocksize(s, fs32_to_cpu(sbi, sb1->sb_blocksize))) { pr_err("unable to set blocksize\n"); goto out; } /* blocksize invalidates bh - pull it back in */ brelse(bh1); bh1 = sb_bread(s, 0); if (!bh1) goto out; sb1 = (struct qnx6_mmi_super_block *)bh1->b_data; /* read second superblock */ bh2 = sb_bread(s, offset); if (!bh2) { pr_err("unable to read the second superblock\n"); goto out; } sb2 = (struct qnx6_mmi_super_block *)bh2->b_data; if (fs32_to_cpu(sbi, sb2->sb_magic) != QNX6_SUPER_MAGIC) { if (!silent) pr_err("wrong signature (magic) in superblock #2.\n"); goto out; } /* checksum check - start at byte 8 and end at byte 512 */ if (fs32_to_cpu(sbi, sb2->sb_checksum) != crc32_be(0, (char *)(bh2->b_data + 8), 504)) { pr_err("superblock #1 checksum error\n"); goto out; } qsb = kmalloc(sizeof(*qsb), GFP_KERNEL); if (!qsb) { pr_err("unable to allocate memory.\n"); goto out; } if (fs64_to_cpu(sbi, sb1->sb_serial) > fs64_to_cpu(sbi, sb2->sb_serial)) { /* superblock #1 active */ qnx6_mmi_copy_sb(qsb, sb1); #ifdef CONFIG_QNX6FS_DEBUG qnx6_superblock_debug(qsb, s); #endif memcpy(bh1->b_data, qsb, sizeof(struct qnx6_super_block)); sbi->sb_buf = bh1; sbi->sb = (struct qnx6_super_block *)bh1->b_data; brelse(bh2); pr_info("superblock #1 active\n"); } else { /* superblock #2 active */ qnx6_mmi_copy_sb(qsb, sb2); #ifdef CONFIG_QNX6FS_DEBUG qnx6_superblock_debug(qsb, s); #endif memcpy(bh2->b_data, qsb, sizeof(struct qnx6_super_block)); sbi->sb_buf = bh2; sbi->sb = (struct qnx6_super_block *)bh2->b_data; brelse(bh1); pr_info("superblock #2 active\n"); } kfree(qsb); /* offset for mmi_fs is just SUPERBLOCK_AREA bytes */ sbi->s_blks_off = QNX6_SUPERBLOCK_AREA / s->s_blocksize; /* success */ return sbi->sb; out: if (bh1 != NULL) brelse(bh1); if (bh2 != NULL) brelse(bh2); return NULL; }
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 // SPDX-License-Identifier: GPL-2.0 /* * thermal_helpers.c - helper functions to handle thermal devices * * Copyright (C) 2016 Eduardo Valentin <edubezval@gmail.com> * * Highly based on original thermal_core.c * Copyright (C) 2008 Intel Corp * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com> * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/sysfs.h> #include "thermal_core.h" #include "thermal_trace.h" int get_tz_trend(struct thermal_zone_device *tz, const struct thermal_trip *trip) { enum thermal_trend trend; if (tz->emul_temperature || !tz->ops.get_trend || tz->ops.get_trend(tz, trip, &trend)) { if (tz->temperature > tz->last_temperature) trend = THERMAL_TREND_RAISING; else if (tz->temperature < tz->last_temperature) trend = THERMAL_TREND_DROPPING; else trend = THERMAL_TREND_STABLE; } return trend; } static bool thermal_instance_present(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev, const struct thermal_trip *trip) { struct thermal_instance *ti; list_for_each_entry(ti, &tz->thermal_instances, tz_node) { if (ti->trip == trip && ti->cdev == cdev) return true; } return false; } bool thermal_trip_is_bound_to_cdev(struct thermal_zone_device *tz, const struct thermal_trip *trip, struct thermal_cooling_device *cdev) { bool ret; mutex_lock(&tz->lock); mutex_lock(&cdev->lock); ret = thermal_instance_present(tz, cdev, trip); mutex_unlock(&cdev->lock); mutex_unlock(&tz->lock); return ret; } EXPORT_SYMBOL_GPL(thermal_trip_is_bound_to_cdev); /** * __thermal_zone_get_temp() - returns the temperature of a thermal zone * @tz: a valid pointer to a struct thermal_zone_device * @temp: a valid pointer to where to store the resulting temperature. * * When a valid thermal zone reference is passed, it will fetch its * temperature and fill @temp. * * Both tz and tz->ops must be valid pointers when calling this function, * and the tz->ops.get_temp callback must be provided. * The function must be called under tz->lock. * * Return: On success returns 0, an error code otherwise */ int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp) { const struct thermal_trip_desc *td; int crit_temp = INT_MAX; int ret = -EINVAL; lockdep_assert_held(&tz->lock); ret = tz->ops.get_temp(tz, temp); if (IS_ENABLED(CONFIG_THERMAL_EMULATION) && tz->emul_temperature) { for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; if (trip->type == THERMAL_TRIP_CRITICAL) { crit_temp = trip->temperature; break; } } /* * Only allow emulating a temperature when the real temperature * is below the critical temperature so that the emulation code * cannot hide critical conditions. */ if (!ret && *temp < crit_temp) *temp = tz->emul_temperature; } if (ret) dev_dbg(&tz->device, "Failed to get temperature: %d\n", ret); return ret; } /** * thermal_zone_get_temp() - returns the temperature of a thermal zone * @tz: a valid pointer to a struct thermal_zone_device * @temp: a valid pointer to where to store the resulting temperature. * * When a valid thermal zone reference is passed, it will fetch its * temperature and fill @temp. * * Return: On success returns 0, an error code otherwise */ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp) { int ret; if (IS_ERR_OR_NULL(tz)) return -EINVAL; mutex_lock(&tz->lock); if (!tz->ops.get_temp) { ret = -EINVAL; goto unlock; } ret = __thermal_zone_get_temp(tz, temp); if (!ret && *temp <= THERMAL_TEMP_INVALID) ret = -ENODATA; unlock: mutex_unlock(&tz->lock); return ret; } EXPORT_SYMBOL_GPL(thermal_zone_get_temp); static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int state) { int ret; /* * No check is needed for the ops->set_cur_state as the * registering function checked the ops are correctly set */ ret = cdev->ops->set_cur_state(cdev, state); if (ret) return ret; thermal_notify_cdev_state_update(cdev, state); thermal_cooling_device_stats_update(cdev, state); thermal_debug_cdev_state_update(cdev, state); return 0; } void __thermal_cdev_update(struct thermal_cooling_device *cdev) { struct thermal_instance *instance; unsigned long target = 0; /* Make sure cdev enters the deepest cooling state */ list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) { if (instance->target == THERMAL_NO_TARGET) continue; if (instance->target > target) target = instance->target; } thermal_cdev_set_cur_state(cdev, target); trace_cdev_update(cdev, target); dev_dbg(&cdev->device, "set to state %lu\n", target); } /** * thermal_cdev_update - update cooling device state if needed * @cdev: pointer to struct thermal_cooling_device * * Update the cooling device state if there is a need. */ void thermal_cdev_update(struct thermal_cooling_device *cdev) { mutex_lock(&cdev->lock); if (!cdev->updated) { __thermal_cdev_update(cdev); cdev->updated = true; } mutex_unlock(&cdev->lock); } /** * thermal_zone_get_slope - return the slope attribute of the thermal zone * @tz: thermal zone device with the slope attribute * * Return: If the thermal zone device has a slope attribute, return it, else * return 1. */ int thermal_zone_get_slope(struct thermal_zone_device *tz) { if (tz && tz->tzp) return tz->tzp->slope; return 1; } EXPORT_SYMBOL_GPL(thermal_zone_get_slope); /** * thermal_zone_get_offset - return the offset attribute of the thermal zone * @tz: thermal zone device with the offset attribute * * Return: If the thermal zone device has a offset attribute, return it, else * return 0. */ int thermal_zone_get_offset(struct thermal_zone_device *tz) { if (tz && tz->tzp) return tz->tzp->offset; return 0; } EXPORT_SYMBOL_GPL(thermal_zone_get_offset);
15 16 10 9 1 10 10 9 3 10 4 7 10 1 9 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 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2014 Nicira, Inc. */ #include <linux/etherdevice.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <net/net_namespace.h> #include <linux/module.h> #include "datapath.h" #include "vport.h" #include "vport-internal_dev.h" static LIST_HEAD(vport_ops_list); /* Protected by RCU read lock for reading, ovs_mutex for writing. */ static struct hlist_head *dev_table; #define VPORT_HASH_BUCKETS 1024 /** * ovs_vport_init - initialize vport subsystem * * Called at module load time to initialize the vport subsystem. */ int ovs_vport_init(void) { dev_table = kcalloc(VPORT_HASH_BUCKETS, sizeof(struct hlist_head), GFP_KERNEL); if (!dev_table) return -ENOMEM; return 0; } /** * ovs_vport_exit - shutdown vport subsystem * * Called at module exit time to shutdown the vport subsystem. */ void ovs_vport_exit(void) { kfree(dev_table); } static struct hlist_head *hash_bucket(const struct net *net, const char *name) { unsigned int hash = jhash(name, strlen(name), (unsigned long) net); return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)]; } int __ovs_vport_ops_register(struct vport_ops *ops) { int err = -EEXIST; struct vport_ops *o; ovs_lock(); list_for_each_entry(o, &vport_ops_list, list) if (ops->type == o->type) goto errout; list_add_tail(&ops->list, &vport_ops_list); err = 0; errout: ovs_unlock(); return err; } EXPORT_SYMBOL_GPL(__ovs_vport_ops_register); void ovs_vport_ops_unregister(struct vport_ops *ops) { ovs_lock(); list_del(&ops->list); ovs_unlock(); } EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister); /** * ovs_vport_locate - find a port that has already been created * * @net: network namespace * @name: name of port to find * * Must be called with ovs or RCU read lock. */ struct vport *ovs_vport_locate(const struct net *net, const char *name) { struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node, lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; return NULL; } /** * ovs_vport_alloc - allocate and initialize new vport * * @priv_size: Size of private data area to allocate. * @ops: vport device ops * @parms: information about new vport. * * Allocate and initialize a new vport defined by @ops. The vport will contain * a private data area of size @priv_size that can be accessed using * vport_priv(). Some parameters of the vport will be initialized from @parms. * @vports that are no longer needed should be released with * vport_free(). */ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, const struct vport_parms *parms) { struct vport *vport; size_t alloc_size; int err; alloc_size = sizeof(struct vport); if (priv_size) { alloc_size = ALIGN(alloc_size, VPORT_ALIGN); alloc_size += priv_size; } vport = kzalloc(alloc_size, GFP_KERNEL); if (!vport) return ERR_PTR(-ENOMEM); vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); if (!vport->upcall_stats) { err = -ENOMEM; goto err_kfree_vport; } vport->dp = parms->dp; vport->port_no = parms->port_no; vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) { err = -EINVAL; goto err_free_percpu; } return vport; err_free_percpu: free_percpu(vport->upcall_stats); err_kfree_vport: kfree(vport); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(ovs_vport_alloc); /** * ovs_vport_free - uninitialize and free vport * * @vport: vport to free * * Frees a vport allocated with vport_alloc() when it is no longer needed. * * The caller must ensure that an RCU grace period has passed since the last * time @vport was in a datapath. */ void ovs_vport_free(struct vport *vport) { /* vport is freed from RCU callback or error path, Therefore * it is safe to use raw dereference. */ kfree(rcu_dereference_raw(vport->upcall_portids)); free_percpu(vport->upcall_stats); kfree(vport); } EXPORT_SYMBOL_GPL(ovs_vport_free); static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms) { struct vport_ops *ops; list_for_each_entry(ops, &vport_ops_list, list) if (ops->type == parms->type) return ops; return NULL; } /** * ovs_vport_add - add vport device (for kernel callers) * * @parms: Information about new vport. * * Creates a new vport with the specified configuration (which is dependent on * device type). ovs_mutex must be held. */ struct vport *ovs_vport_add(const struct vport_parms *parms) { struct vport_ops *ops; struct vport *vport; ops = ovs_vport_lookup(parms); if (ops) { struct hlist_head *bucket; if (!try_module_get(ops->owner)) return ERR_PTR(-EAFNOSUPPORT); vport = ops->create(parms); if (IS_ERR(vport)) { module_put(ops->owner); return vport; } bucket = hash_bucket(ovs_dp_get_net(vport->dp), ovs_vport_name(vport)); hlist_add_head_rcu(&vport->hash_node, bucket); return vport; } /* Unlock to attempt module load and return -EAGAIN if load * was successful as we need to restart the port addition * workflow. */ ovs_unlock(); request_module("vport-type-%d", parms->type); ovs_lock(); if (!ovs_vport_lookup(parms)) return ERR_PTR(-EAFNOSUPPORT); else return ERR_PTR(-EAGAIN); } /** * ovs_vport_set_options - modify existing vport device (for kernel callers) * * @vport: vport to modify. * @options: New configuration. * * Modifies an existing device with the specified configuration (which is * dependent on device type). ovs_mutex must be held. */ int ovs_vport_set_options(struct vport *vport, struct nlattr *options) { if (!vport->ops->set_options) return -EOPNOTSUPP; return vport->ops->set_options(vport, options); } /** * ovs_vport_del - delete existing vport device * * @vport: vport to delete. * * Detaches @vport from its datapath and destroys it. ovs_mutex must * be held. */ void ovs_vport_del(struct vport *vport) { hlist_del_rcu(&vport->hash_node); module_put(vport->ops->owner); vport->ops->destroy(vport); } /** * ovs_vport_get_stats - retrieve device stats * * @vport: vport from which to retrieve the stats * @stats: location to store stats * * Retrieves transmit, receive, and error stats for the given device. * * Must be called with ovs_mutex or rcu_read_lock. */ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) { const struct rtnl_link_stats64 *dev_stats; struct rtnl_link_stats64 temp; dev_stats = dev_get_stats(vport->dev, &temp); stats->rx_errors = dev_stats->rx_errors; stats->tx_errors = dev_stats->tx_errors; stats->tx_dropped = dev_stats->tx_dropped; stats->rx_dropped = dev_stats->rx_dropped; stats->rx_bytes = dev_stats->rx_bytes; stats->rx_packets = dev_stats->rx_packets; stats->tx_bytes = dev_stats->tx_bytes; stats->tx_packets = dev_stats->tx_packets; } /** * ovs_vport_get_upcall_stats - retrieve upcall stats * * @vport: vport from which to retrieve the stats. * @skb: sk_buff where upcall stats should be appended. * * Retrieves upcall stats for the given device. * * Must be called with ovs_mutex or rcu_read_lock. */ int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) { struct nlattr *nla; int i; __u64 tx_success = 0; __u64 tx_fail = 0; for_each_possible_cpu(i) { const struct vport_upcall_stats_percpu *stats; unsigned int start; stats = per_cpu_ptr(vport->upcall_stats, i); do { start = u64_stats_fetch_begin(&stats->syncp); tx_success += u64_stats_read(&stats->n_success); tx_fail += u64_stats_read(&stats->n_fail); } while (u64_stats_fetch_retry(&stats->syncp, start)); } nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); if (!nla) return -EMSGSIZE; if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_SUCCESS, tx_success, OVS_VPORT_ATTR_PAD)) { nla_nest_cancel(skb, nla); return -EMSGSIZE; } if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_FAIL, tx_fail, OVS_VPORT_ATTR_PAD)) { nla_nest_cancel(skb, nla); return -EMSGSIZE; } nla_nest_end(skb, nla); return 0; } /** * ovs_vport_get_options - retrieve device options * * @vport: vport from which to retrieve the options. * @skb: sk_buff where options should be appended. * * Retrieves the configuration of the given device, appending an * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested * vport-specific attributes to @skb. * * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another * negative error code if a real error occurred. If an error occurs, @skb is * left unmodified. * * Must be called with ovs_mutex or rcu_read_lock. */ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) { struct nlattr *nla; int err; if (!vport->ops->get_options) return 0; nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_OPTIONS); if (!nla) return -EMSGSIZE; err = vport->ops->get_options(vport, skb); if (err) { nla_nest_cancel(skb, nla); return err; } nla_nest_end(skb, nla); return 0; } /** * ovs_vport_set_upcall_portids - set upcall portids of @vport. * * @vport: vport to modify. * @ids: new configuration, an array of port ids. * * Sets the vport's upcall_portids to @ids. * * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed * as an array of U32. * * Must be called with ovs_mutex. */ int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids) { struct vport_portids *old, *vport_portids; if (!nla_len(ids) || nla_len(ids) % sizeof(u32)) return -EINVAL; old = ovsl_dereference(vport->upcall_portids); vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids), GFP_KERNEL); if (!vport_portids) return -ENOMEM; vport_portids->n_ids = nla_len(ids) / sizeof(u32); vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids); nla_memcpy(vport_portids->ids, ids, nla_len(ids)); rcu_assign_pointer(vport->upcall_portids, vport_portids); if (old) kfree_rcu(old, rcu); return 0; } /** * ovs_vport_get_upcall_portids - get the upcall_portids of @vport. * * @vport: vport from which to retrieve the portids. * @skb: sk_buff where portids should be appended. * * Retrieves the configuration of the given vport, appending the * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall * portids to @skb. * * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room. * If an error occurs, @skb is left unmodified. Must be called with * ovs_mutex or rcu_read_lock. */ int ovs_vport_get_upcall_portids(const struct vport *vport, struct sk_buff *skb) { struct vport_portids *ids; ids = rcu_dereference_ovsl(vport->upcall_portids); if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS) return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->n_ids * sizeof(u32), (void *)ids->ids); else return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]); } /** * ovs_vport_find_upcall_portid - find the upcall portid to send upcall. * * @vport: vport from which the missed packet is received. * @skb: skb that the missed packet was received. * * Uses the skb_get_hash() to select the upcall portid to send the * upcall. * * Returns the portid of the target socket. Must be called with rcu_read_lock. */ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) { struct vport_portids *ids; u32 ids_index; u32 hash; ids = rcu_dereference(vport->upcall_portids); /* If there is only one portid, select it in the fast-path. */ if (ids->n_ids == 1) return ids->ids[0]; hash = skb_get_hash(skb); ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids); return ids->ids[ids_index]; } /** * ovs_vport_receive - pass up received packet to the datapath for processing * * @vport: vport that received the packet * @skb: skb that was received * @tun_info: tunnel (if any) that carried packet * * Must be called with rcu_read_lock. The packet cannot be shared and * skb->data should point to the Ethernet header. */ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, const struct ip_tunnel_info *tun_info) { struct sw_flow_key key; int error; OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; OVS_CB(skb)->cutlen = 0; OVS_CB(skb)->probability = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { u32 mark; mark = skb->mark; skb_scrub_packet(skb, true); skb->mark = mark; tun_info = NULL; } /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { kfree_skb(skb); return error; } ovs_dp_process_packet(skb, &key); return 0; } static int packet_length(const struct sk_buff *skb, struct net_device *dev) { int length = skb->len - dev->hard_header_len; if (!skb_vlan_tag_present(skb) && eth_type_vlan(skb->protocol)) length -= VLAN_HLEN; /* Don't subtract for multiple VLAN tags. Most (all?) drivers allow * (ETH_LEN + VLAN_HLEN) in addition to the mtu value, but almost none * account for 802.1ad. e.g. is_skb_forwardable(). */ return length > 0 ? length : 0; } void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto) { int mtu = vport->dev->mtu; switch (vport->dev->type) { case ARPHRD_NONE: if (mac_proto == MAC_PROTO_ETHERNET) { skb_reset_network_header(skb); skb_reset_mac_len(skb); skb->protocol = htons(ETH_P_TEB); } else if (mac_proto != MAC_PROTO_NONE) { WARN_ON_ONCE(1); goto drop; } break; case ARPHRD_ETHER: if (mac_proto != MAC_PROTO_ETHERNET) goto drop; break; default: goto drop; } if (unlikely(packet_length(skb, vport->dev) > mtu && !skb_is_gso(skb))) { vport->dev->stats.tx_errors++; if (vport->dev->flags & IFF_UP) net_warn_ratelimited("%s: dropped over-mtu packet: " "%d > %d\n", vport->dev->name, packet_length(skb, vport->dev), mtu); goto drop; } skb->dev = vport->dev; skb_clear_tstamp(skb); vport->ops->send(skb); return; drop: kfree_skb(skb); }
227 17 151 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 /* * linux/fs/ext4/xattr_security.c * Handler for storing security labels as extended attributes. */ #include <linux/string.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/slab.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" static int ext4_xattr_security_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name, buffer, size); } static int ext4_xattr_security_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name, value, size, flags); } static int ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { const struct xattr *xattr; handle_t *handle = fs_info; int err = 0; for (xattr = xattr_array; xattr->name != NULL; xattr++) { err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY, xattr->name, xattr->value, xattr->value_len, XATTR_CREATE); if (err < 0) break; } return err; } int ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, const struct qstr *qstr) { return security_inode_init_security(inode, dir, qstr, &ext4_initxattrs, handle); } const struct xattr_handler ext4_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = ext4_xattr_security_get, .set = ext4_xattr_security_set, };
6 8 29 3 7 1 15 1 9 1 21 4 8 14 1 21 2 1 1 2 21 7 14 29 20 29 22 20 1 3 2 2 2 2 2 2 6 5 2 3 3 1 1 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 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * algif_aead: User-space interface for AEAD algorithms * * Copyright (C) 2014, Stephan Mueller <smueller@chronox.de> * * This file provides the user-space API for AEAD ciphers. * * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is * filled by user space with the data submitted via sendmsg (maybe with * MSG_SPLICE_PAGES). Filling up the TX SGL does not cause a crypto operation * -- the data will only be tracked by the kernel. Upon receipt of one recvmsg * call, the caller must provide a buffer which is tracked with the RX SGL. * * During the processing of the recvmsg operation, the cipher request is * allocated and prepared. As part of the recvmsg operation, the processed * TX buffers are extracted from the TX SGL into a separate SGL. * * After the completion of the crypto operation, the RX SGL and the cipher * request is released. The extracted TX SGL parts are released together with * the RX SGL release. */ #include <crypto/internal/aead.h> #include <crypto/scatterwalk.h> #include <crypto/if_alg.h> #include <crypto/skcipher.h> #include <crypto/null.h> #include <linux/init.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/net.h> #include <net/sock.h> struct aead_tfm { struct crypto_aead *aead; struct crypto_sync_skcipher *null_tfm; }; static inline bool aead_sufficient_data(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct aead_tfm *aeadc = pask->private; struct crypto_aead *tfm = aeadc->aead; unsigned int as = crypto_aead_authsize(tfm); /* * The minimum amount of memory needed for an AEAD cipher is * the AAD and in case of decryption the tag. */ return ctx->used >= ctx->aead_assoclen + (ctx->enc ? 0 : as); } static int aead_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct aead_tfm *aeadc = pask->private; struct crypto_aead *tfm = aeadc->aead; unsigned int ivsize = crypto_aead_ivsize(tfm); return af_alg_sendmsg(sock, msg, size, ivsize); } static int crypto_aead_copy_sgl(struct crypto_sync_skcipher *null_tfm, struct scatterlist *src, struct scatterlist *dst, unsigned int len) { SYNC_SKCIPHER_REQUEST_ON_STACK(skreq, null_tfm); skcipher_request_set_sync_tfm(skreq, null_tfm); skcipher_request_set_callback(skreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); skcipher_request_set_crypt(skreq, src, dst, len, NULL); return crypto_skcipher_encrypt(skreq); } static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct aead_tfm *aeadc = pask->private; struct crypto_aead *tfm = aeadc->aead; struct crypto_sync_skcipher *null_tfm = aeadc->null_tfm; unsigned int i, as = crypto_aead_authsize(tfm); struct af_alg_async_req *areq; struct af_alg_tsgl *tsgl, *tmp; struct scatterlist *rsgl_src, *tsgl_src = NULL; int err = 0; size_t used = 0; /* [in] TX bufs to be en/decrypted */ size_t outlen = 0; /* [out] RX bufs produced by kernel */ size_t usedpages = 0; /* [in] RX bufs to be used from user */ size_t processed = 0; /* [in] TX bufs to be consumed */ if (!ctx->init || ctx->more) { err = af_alg_wait_for_data(sk, flags, 0); if (err) return err; } /* * Data length provided by caller via sendmsg that has not yet been * processed. */ used = ctx->used; /* * Make sure sufficient data is present -- note, the same check is also * present in sendmsg. The checks in sendmsg shall provide an * information to the data sender that something is wrong, but they are * irrelevant to maintain the kernel integrity. We need this check * here too in case user space decides to not honor the error message * in sendmsg and still call recvmsg. This check here protects the * kernel integrity. */ if (!aead_sufficient_data(sk)) return -EINVAL; /* * Calculate the minimum output buffer size holding the result of the * cipher operation. When encrypting data, the receiving buffer is * larger by the tag length compared to the input buffer as the * encryption operation generates the tag. For decryption, the input * buffer provides the tag which is consumed resulting in only the * plaintext without a buffer for the tag returned to the caller. */ if (ctx->enc) outlen = used + as; else outlen = used - as; /* * The cipher operation input data is reduced by the associated data * length as this data is processed separately later on. */ used -= ctx->aead_assoclen; /* Allocate cipher request for current operation. */ areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) + crypto_aead_reqsize(tfm)); if (IS_ERR(areq)) return PTR_ERR(areq); /* convert iovecs of output buffers into RX SGL */ err = af_alg_get_rsgl(sk, msg, flags, areq, outlen, &usedpages); if (err) goto free; /* * Ensure output buffer is sufficiently large. If the caller provides * less buffer space, only use the relative required input size. This * allows AIO operation where the caller sent all data to be processed * and the AIO operation performs the operation on the different chunks * of the input data. */ if (usedpages < outlen) { size_t less = outlen - usedpages; if (used < less) { err = -EINVAL; goto free; } used -= less; outlen -= less; } processed = used + ctx->aead_assoclen; list_for_each_entry_safe(tsgl, tmp, &ctx->tsgl_list, list) { for (i = 0; i < tsgl->cur; i++) { struct scatterlist *process_sg = tsgl->sg + i; if (!(process_sg->length) || !sg_page(process_sg)) continue; tsgl_src = process_sg; break; } if (tsgl_src) break; } if (processed && !tsgl_src) { err = -EFAULT; goto free; } /* * Copy of AAD from source to destination * * The AAD is copied to the destination buffer without change. Even * when user space uses an in-place cipher operation, the kernel * will copy the data as it does not see whether such in-place operation * is initiated. * * To ensure efficiency, the following implementation ensure that the * ciphers are invoked to perform a crypto operation in-place. This * is achieved by memory management specified as follows. */ /* Use the RX SGL as source (and destination) for crypto op. */ rsgl_src = areq->first_rsgl.sgl.sgt.sgl; if (ctx->enc) { /* * Encryption operation - The in-place cipher operation is * achieved by the following operation: * * TX SGL: AAD || PT * | | * | copy | * v v * RX SGL: AAD || PT || Tag */ err = crypto_aead_copy_sgl(null_tfm, tsgl_src, areq->first_rsgl.sgl.sgt.sgl, processed); if (err) goto free; af_alg_pull_tsgl(sk, processed, NULL, 0); } else { /* * Decryption operation - To achieve an in-place cipher * operation, the following SGL structure is used: * * TX SGL: AAD || CT || Tag * | | ^ * | copy | | Create SGL link. * v v | * RX SGL: AAD || CT ----+ */ /* Copy AAD || CT to RX SGL buffer for in-place operation. */ err = crypto_aead_copy_sgl(null_tfm, tsgl_src, areq->first_rsgl.sgl.sgt.sgl, outlen); if (err) goto free; /* Create TX SGL for tag and chain it to RX SGL. */ areq->tsgl_entries = af_alg_count_tsgl(sk, processed, processed - as); if (!areq->tsgl_entries) areq->tsgl_entries = 1; areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), areq->tsgl_entries), GFP_KERNEL); if (!areq->tsgl) { err = -ENOMEM; goto free; } sg_init_table(areq->tsgl, areq->tsgl_entries); /* Release TX SGL, except for tag data and reassign tag data. */ af_alg_pull_tsgl(sk, processed, areq->tsgl, processed - as); /* chain the areq TX SGL holding the tag with RX SGL */ if (usedpages) { /* RX SGL present */ struct af_alg_sgl *sgl_prev = &areq->last_rsgl->sgl; struct scatterlist *sg = sgl_prev->sgt.sgl; sg_unmark_end(sg + sgl_prev->sgt.nents - 1); sg_chain(sg, sgl_prev->sgt.nents + 1, areq->tsgl); } else /* no RX SGL present (e.g. authentication only) */ rsgl_src = areq->tsgl; } /* Initialize the crypto operation */ aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src, areq->first_rsgl.sgl.sgt.sgl, used, ctx->iv); aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen); aead_request_set_tfm(&areq->cra_u.aead_req, tfm); if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) { /* AIO operation */ sock_hold(sk); areq->iocb = msg->msg_iocb; /* Remember output size that will be generated. */ areq->outlen = outlen; aead_request_set_callback(&areq->cra_u.aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, af_alg_async_cb, areq); err = ctx->enc ? crypto_aead_encrypt(&areq->cra_u.aead_req) : crypto_aead_decrypt(&areq->cra_u.aead_req); /* AIO operation in progress */ if (err == -EINPROGRESS) return -EIOCBQUEUED; sock_put(sk); } else { /* Synchronous operation */ aead_request_set_callback(&areq->cra_u.aead_req, CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &ctx->wait); err = crypto_wait_req(ctx->enc ? crypto_aead_encrypt(&areq->cra_u.aead_req) : crypto_aead_decrypt(&areq->cra_u.aead_req), &ctx->wait); } free: af_alg_free_resources(areq); return err ? err : outlen; } static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; int ret = 0; lock_sock(sk); while (msg_data_left(msg)) { int err = _aead_recvmsg(sock, msg, ignored, flags); /* * This error covers -EIOCBQUEUED which implies that we can * only handle one AIO request. If the caller wants to have * multiple AIO requests in parallel, he must make multiple * separate AIO calls. * * Also return the error if no data has been processed so far. */ if (err <= 0) { if (err == -EIOCBQUEUED || err == -EBADMSG || !ret) ret = err; goto out; } ret += err; } out: af_alg_wmem_wakeup(sk); release_sock(sk); return ret; } static struct proto_ops algif_aead_ops = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = aead_sendmsg, .recvmsg = aead_recvmsg, .poll = af_alg_poll, }; static int aead_check_key(struct socket *sock) { int err = 0; struct sock *psk; struct alg_sock *pask; struct aead_tfm *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); lock_sock(sk); if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY) goto unlock; atomic_dec(&pask->nokey_refcnt); atomic_set(&ask->nokey_refcnt, 0); err = 0; unlock: release_sock(psk); unlock_child: release_sock(sk); return err; } static int aead_sendmsg_nokey(struct socket *sock, struct msghdr *msg, size_t size) { int err; err = aead_check_key(sock); if (err) return err; return aead_sendmsg(sock, msg, size); } static int aead_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { int err; err = aead_check_key(sock); if (err) return err; return aead_recvmsg(sock, msg, ignored, flags); } static struct proto_ops algif_aead_ops_nokey = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = aead_sendmsg_nokey, .recvmsg = aead_recvmsg_nokey, .poll = af_alg_poll, }; static void *aead_bind(const char *name, u32 type, u32 mask) { struct aead_tfm *tfm; struct crypto_aead *aead; struct crypto_sync_skcipher *null_tfm; tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); if (!tfm) return ERR_PTR(-ENOMEM); aead = crypto_alloc_aead(name, type, mask); if (IS_ERR(aead)) { kfree(tfm); return ERR_CAST(aead); } null_tfm = crypto_get_default_null_skcipher(); if (IS_ERR(null_tfm)) { crypto_free_aead(aead); kfree(tfm); return ERR_CAST(null_tfm); } tfm->aead = aead; tfm->null_tfm = null_tfm; return tfm; } static void aead_release(void *private) { struct aead_tfm *tfm = private; crypto_free_aead(tfm->aead); crypto_put_default_null_skcipher(); kfree(tfm); } static int aead_setauthsize(void *private, unsigned int authsize) { struct aead_tfm *tfm = private; return crypto_aead_setauthsize(tfm->aead, authsize); } static int aead_setkey(void *private, const u8 *key, unsigned int keylen) { struct aead_tfm *tfm = private; return crypto_aead_setkey(tfm->aead, key, keylen); } static void aead_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct aead_tfm *aeadc = pask->private; struct crypto_aead *tfm = aeadc->aead; unsigned int ivlen = crypto_aead_ivsize(tfm); af_alg_pull_tsgl(sk, ctx->used, NULL, 0); sock_kzfree_s(sk, ctx->iv, ivlen); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } static int aead_accept_parent_nokey(void *private, struct sock *sk) { struct af_alg_ctx *ctx; struct alg_sock *ask = alg_sk(sk); struct aead_tfm *tfm = private; struct crypto_aead *aead = tfm->aead; unsigned int len = sizeof(*ctx); unsigned int ivlen = crypto_aead_ivsize(aead); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; memset(ctx, 0, len); ctx->iv = sock_kmalloc(sk, ivlen, GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } memset(ctx->iv, 0, ivlen); INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; crypto_init_wait(&ctx->wait); ask->private = ctx; sk->sk_destruct = aead_sock_destruct; return 0; } static int aead_accept_parent(void *private, struct sock *sk) { struct aead_tfm *tfm = private; if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return aead_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_aead = { .bind = aead_bind, .release = aead_release, .setkey = aead_setkey, .setauthsize = aead_setauthsize, .accept = aead_accept_parent, .accept_nokey = aead_accept_parent_nokey, .ops = &algif_aead_ops, .ops_nokey = &algif_aead_ops_nokey, .name = "aead", .owner = THIS_MODULE }; static int __init algif_aead_init(void) { return af_alg_register_type(&algif_type_aead); } static void __exit algif_aead_exit(void) { int err = af_alg_unregister_type(&algif_type_aead); BUG_ON(err); } module_init(algif_aead_init); module_exit(algif_aead_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>"); MODULE_DESCRIPTION("AEAD kernel crypto API user space interface");
12 99 101 39 7 7 5 102 10 42 33 102 72 19 17 101 58 34 1 89 89 13 13 9 129 98 77 97 17 19 85 85 63 45 9 11 6 2 50 2 48 33 48 46 6 90 66 25 17 9 5 20 82 10 90 8 14 14 36 12 24 2 34 34 29 3 2 1 10 17 7 21 1 7 42 35 7 35 35 35 21 21 15 26 9 14 10 7 1 4 4 4 1 3 24 10 103 105 33 20 54 1 19 34 34 34 40 3 6 48 49 48 49 4 15 20 4 31 31 10 17 1 3 31 31 31 33 9 10 10 10 10 2 50 34 6 23 8 5 4 22 3 23 2 18 10 1 11 3 1 4 3 107 2 105 105 102 1 100 37 26 2 60 61 9 7 1 6 277 281 33 33 33 33 33 64 23 41 2 21 23 42 1 1 44 27 25 90 69 21 9 9 9 122 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 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/rculist.h> #include <linux/err.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) { return hash_32((__force u32)key ^ (__force u32)remote, IP_TNL_HASH_BITS); } static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, const unsigned long *flags, __be32 key) { if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options Tunnel hash table: We require exact key match i.e. if a key is present in packet it will match only tunnel with the same key; if it is not present, it will match only keyless tunnel. All keysless packets, if not matched configured keyless tunnels will match fallback tunnel. Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; struct net_device *ndev; unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hash = ip_tunnel_hash(key, 0); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) continue; if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(itn->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; ndev = READ_ONCE(itn->fb_tunnel_dev); if (ndev && ndev->flags & IFF_UP) return netdev_priv(ndev); return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); ip_tunnel_flags_copy(flags, parms->i_flags); hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } return t; } static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; struct net_device *dev; char name[IFNAMSIZ]; err = -E2BIG; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strscpy(name, parms->name, IFNAMSIZ); } else { if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; strcpy(name, ops->kind); strcat(name, "%d"); } ASSERT_RTNL(); dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup); if (!dev) { err = -ENOMEM; goto failed; } dev_net_set(dev, net); dev->rtnl_link_ops = ops; tunnel = netdev_priv(dev); tunnel->parms = *parms; tunnel->net = net; err = register_netdevice(dev); if (err) goto failed_free; return dev; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *iph; int hlen = LL_MAX_HEADER; int mtu = ETH_DATA_LEN; int t_hlen = tunnel->hlen + sizeof(struct iphdr); iph = &tunnel->parms.iph; /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { struct flowi4 fl4; struct rtable *rt; ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, iph->tos & INET_DSCP_MASK, dev_net(dev), tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; return mtu; } static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; int t_hlen; int mtu; int err; dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); mtu = ip_tunnel_bind_dev(dev); err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) dev->max_mtu -= dev->hard_header_len; ip_tunnel_add(itn, nt); return nt; err_dev_set_mtu: unregister_netdevice(dev); return ERR_PTR(err); } void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info) { const struct iphdr *iph = ip_hdr(skb); const struct udphdr *udph; if (iph->protocol != IPPROTO_UDP) return; udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2)); info->encap.sport = udph->source; info->encap.dport = udph->dest; } EXPORT_SYMBOL(ip_tunnel_md_udp_encap); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { DEV_STATS_INC(tunnel->dev, multicast); skb->pkt_type = PACKET_BROADCAST; } #endif if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } iph = (struct iphdr *)(skb->head + nh); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_rcv); int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip_tunnel_encap_add_ops); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip_tunnel_encap_del_ops); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, const struct iphdr *inner_iph, int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size; int mtu; tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6; __be32 daddr; rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } #endif return 0; } static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) { /* we must cap headroom to some upperlimit, else pskb_expand_head * will overflow header offsets in skb_headers_offset_update(). */ static const unsigned int max_allowed = 512; if (headroom > max_allowed) headroom = max_allowed; if (headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, headroom); } void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto tx_error; key = &tun_info->key; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); inner_iph = (const struct iphdr *)skb_inner_network_header(skb); tos = key->tos; if (tos == 1) { if (skb->protocol == htons(ETH_P_IP)) tos = inner_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) tunnel_hlen = ip_encap_hlen(&tun_info->encap); if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0) goto tx_error; use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { ip_rt_put(rt); goto tx_error; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; else ttl = ip4_dst_hoplimit(&rt->dst); } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: DEV_STATS_INC(dev, tx_errors); goto kfree; tx_dropped: DEV_STATS_INC(dev, tx_dropped); kfree: kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info = NULL; const struct iphdr *inner_iph; unsigned int max_headroom; /* The extra header space needed */ struct rtable *rt = NULL; /* Route to the other host */ __be16 payload_protocol; bool use_cache = false; struct flowi4 fl4; bool md = false; bool connected; u8 tos, ttl; __be32 dst; __be16 df; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); payload_protocol = skb_protocol(skb, true); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (!skb_dst(skb)) { DEV_STATS_INC(dev, tx_fifo_errors); goto tx_error; } tun_info = skb_tunnel_info(skb); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && ip_tunnel_info_af(tun_info) == AF_INET && tun_info->key.u.ipv4.dst) { dst = tun_info->key.u.ipv4.dst; md = true; connected = true; } else if (payload_protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; if (!md) connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (payload_protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (payload_protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, dev_net(dev), READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) goto tx_error; if (connected && md) { use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); } else { rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : NULL; } if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); else if (!md && connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } df = tnl_params->frag_off; if (payload_protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off & htons(IP_DF)); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (payload_protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { __dev_addr_set(dev, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) WRITE_ONCE(dev->mtu, mtu); } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); struct net *net = t->net; struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } t = ip_tunnel_find(itn, p, itn->type); if (cmd == SIOCADDTUNNEL) { if (!t) { t = ip_tunnel_create(net, itn, p); err = PTR_ERR_OR_ZERO(t); break; } err = -EEXIST; break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) { err = -EINVAL; break; } t = netdev_priv(dev); } } if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true, 0); } else { err = -ENOENT; } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) goto done; dev = t->dev; } unregister_netdevice(dev); err = 0; break; default: err = -EINVAL; } done: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, const void __user *data) { struct ip_tunnel_parm p; if (copy_from_user(&p, data, sizeof(p))) return false; strscpy(kp->name, p.name); kp->link = p.link; ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); kp->i_key = p.i_key; kp->o_key = p.o_key; memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); return true; } EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) { struct ip_tunnel_parm p; if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || !ip_tunnel_flags_is_be16_compat(kp->o_flags)) return false; memset(&p, 0, sizeof(p)); strscpy(p.name, kp->name); p.link = kp->link; p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); p.i_key = kp->i_key; p.o_key = kp->o_key; memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); return !copy_to_user(data, &p, sizeof(p)); } EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct ip_tunnel_parm_kern p; int err; if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) max_mtu -= dev->hard_header_len; if (new_mtu < ETH_MIN_MTU) return -EINVAL; if (new_mtu > max_mtu) { if (strict) return -EINVAL; new_mtu = max_mtu; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) { return __ip_tunnel_change_mtu(dev, new_mtu, true); } EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_net *itn; itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_dellink); struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { const struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; for (i = 0; i < IP_TNL_HASH_SIZE; i++) INIT_HLIST_HEAD(&itn->tunnels[i]); if (!ops || !net_has_fallback_tunnels(net)) { struct ip_tunnel_net *it_init_net; it_init_net = net_generic(&init_net, ip_tnl_net_id); itn->type = it_init_net->type; itn->fb_tunnel_dev = NULL; return 0; } memset(&parms, 0, sizeof(parms)); if (devname) strscpy(parms.name, devname, IFNAMSIZ); rtnl_lock(); itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->netns_local = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; } rtnl_unlock(); return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev); } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, struct list_head *head, struct rtnl_link_ops *ops) { struct net_device *dev, *aux; int h; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == ops) unregister_netdevice_queue(dev, head); for (h = 0; h < IP_TNL_HASH_SIZE; h++) { struct ip_tunnel *t; struct hlist_node *n; struct hlist_head *thead = &itn->tunnels[h]; hlist_for_each_entry_safe(t, n, thead, hash_node) /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } } void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, struct rtnl_link_ops *ops, struct list_head *dev_to_kill) { struct ip_tunnel_net *itn; struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); ip_tunnel_destroy(net, itn, dev_to_kill, ops); } } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct net *net = dev_net(dev); struct ip_tunnel_net *itn; int mtu; int err; nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); if (nt->collect_md) { if (rtnl_dereference(itn->collect_md_tun)) return -EEXIST; } else { if (ip_tunnel_find(itn, p, dev->type)) return -EEXIST; } nt->net = net; nt->parms = *p; nt->fwmark = fwmark; err = register_netdevice(dev); if (err) goto err_register_netdevice; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); if (dev->type == ARPHRD_ETHER) max -= dev->hard_header_len; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; ip_tunnel_add(itn, nt); return 0; err_dev_set_mtu: unregister_netdevice(dev); err_register_netdevice: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); if (dev == itn->fb_tunnel_dev) return -EINVAL; t = ip_tunnel_find(itn, p, dev->type); if (t) { if (t->dev != dev) return -EEXIST; } else { t = tunnel; if (dev->type != ARPHRD_ETHER) { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags ^ nflags) & (IFF_POINTOPOINT | IFF_BROADCAST)) return -EINVAL; } } ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; int err; dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) return err; err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); return err; } tunnel->dev = dev; tunnel->net = dev_net(dev); strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; if (tunnel->collect_md) netif_keep_dst(dev); netdev_lockdep_set_classes(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); ip_tunnel_del(itn, netdev_priv(dev)); if (itn->fb_tunnel_dev == dev) WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); /* Do least required initialization, rest of init is done in tunnel_init call */ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) { struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->ip_tnl_net_id = net_id; } EXPORT_SYMBOL_GPL(ip_tunnel_setup); MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL");
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 // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright (C) Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk) * Copyright (C) Joerg Reuter DL1BKE (jreuter@yaina.de) */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/spinlock.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <net/tcp_states.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> static void ax25_ds_timeout(struct timer_list *); /* * Add DAMA slave timeout timer to timer list. * Unlike the connection based timers the timeout function gets * triggered every second. Please note that NET_AX25_DAMA_SLAVE_TIMEOUT * (aka /proc/sys/net/ax25/{dev}/dama_slave_timeout) is still in * 1/10th of a second. */ void ax25_ds_setup_timer(ax25_dev *ax25_dev) { timer_setup(&ax25_dev->dama.slave_timer, ax25_ds_timeout, 0); } void ax25_ds_del_timer(ax25_dev *ax25_dev) { if (ax25_dev) del_timer(&ax25_dev->dama.slave_timer); } void ax25_ds_set_timer(ax25_dev *ax25_dev) { if (ax25_dev == NULL) /* paranoia */ return; ax25_dev->dama.slave_timeout = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_DS_TIMEOUT]) / 10; mod_timer(&ax25_dev->dama.slave_timer, jiffies + HZ); } /* * DAMA Slave Timeout * Silently discard all (slave) connections in case our master forgot us... */ static void ax25_ds_timeout(struct timer_list *t) { ax25_dev *ax25_dev = from_timer(ax25_dev, t, dama.slave_timer); ax25_cb *ax25; if (ax25_dev == NULL || !ax25_dev->dama.slave) return; /* Yikes! */ if (!ax25_dev->dama.slave_timeout || --ax25_dev->dama.slave_timeout) { ax25_ds_set_timer(ax25_dev); return; } spin_lock(&ax25_list_lock); ax25_for_each(ax25, &ax25_list) { if (ax25->ax25_dev != ax25_dev || !(ax25->condition & AX25_COND_DAMA_MODE)) continue; ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); ax25_disconnect(ax25, ETIMEDOUT); } spin_unlock(&ax25_list_lock); ax25_dev_dama_off(ax25_dev); } void ax25_ds_heartbeat_expiry(ax25_cb *ax25) { struct sock *sk=ax25->sk; if (sk) bh_lock_sock(sk); switch (ax25->state) { case AX25_STATE_0: case AX25_STATE_2: /* Magic here: If we listen() and a new link dies before it is accepted() it isn't 'dead' so doesn't get removed. */ if (!sk || sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { if (sk) { sock_hold(sk); ax25_destroy_socket(ax25); bh_unlock_sock(sk); /* Ungrab socket and destroy it */ sock_put(sk); } else ax25_destroy_socket(ax25); return; } break; case AX25_STATE_3: /* * Check the state of the receive buffer. */ if (sk != NULL) { if (atomic_read(&sk->sk_rmem_alloc) < (sk->sk_rcvbuf >> 1) && (ax25->condition & AX25_COND_OWN_RX_BUSY)) { ax25->condition &= ~AX25_COND_OWN_RX_BUSY; ax25->condition &= ~AX25_COND_ACK_PENDING; break; } } break; } if (sk) bh_unlock_sock(sk); ax25_start_heartbeat(ax25); } /* dl1bke 960114: T3 works much like the IDLE timeout, but * gets reloaded with every frame for this * connection. */ void ax25_ds_t3timer_expiry(ax25_cb *ax25) { ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); ax25_dama_off(ax25); ax25_disconnect(ax25, ETIMEDOUT); } /* dl1bke 960228: close the connection when IDLE expires. * unlike T3 this timer gets reloaded only on * I frames. */ void ax25_ds_idletimer_expiry(ax25_cb *ax25) { ax25_clear_queues(ax25); ax25->n2count = 0; ax25->state = AX25_STATE_2; ax25_calculate_t1(ax25); ax25_start_t1timer(ax25); ax25_stop_t3timer(ax25); if (ax25->sk != NULL) { bh_lock_sock(ax25->sk); ax25->sk->sk_state = TCP_CLOSE; ax25->sk->sk_err = 0; ax25->sk->sk_shutdown |= SEND_SHUTDOWN; if (!sock_flag(ax25->sk, SOCK_DEAD)) { ax25->sk->sk_state_change(ax25->sk); sock_set_flag(ax25->sk, SOCK_DEAD); } bh_unlock_sock(ax25->sk); } } /* dl1bke 960114: The DAMA protocol requires to send data and SABM/DISC * within the poll of any connected channel. Remember * that we are not allowed to send anything unless we * get polled by the Master. * * Thus we'll have to do parts of our T1 handling in * ax25_enquiry_response(). */ void ax25_ds_t1_timeout(ax25_cb *ax25) { switch (ax25->state) { case AX25_STATE_1: if (ax25->n2count == ax25->n2) { if (ax25->modulus == AX25_MODULUS) { ax25_disconnect(ax25, ETIMEDOUT); return; } else { ax25->modulus = AX25_MODULUS; ax25->window = ax25->ax25_dev->values[AX25_VALUES_WINDOW]; ax25->n2count = 0; ax25_send_control(ax25, AX25_SABM, AX25_POLLOFF, AX25_COMMAND); } } else { ax25->n2count++; if (ax25->modulus == AX25_MODULUS) ax25_send_control(ax25, AX25_SABM, AX25_POLLOFF, AX25_COMMAND); else ax25_send_control(ax25, AX25_SABME, AX25_POLLOFF, AX25_COMMAND); } break; case AX25_STATE_2: if (ax25->n2count == ax25->n2) { ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); if (!sock_flag(ax25->sk, SOCK_DESTROY)) ax25_disconnect(ax25, ETIMEDOUT); return; } else { ax25->n2count++; } break; case AX25_STATE_3: if (ax25->n2count == ax25->n2) { ax25_send_control(ax25, AX25_DM, AX25_POLLON, AX25_RESPONSE); ax25_disconnect(ax25, ETIMEDOUT); return; } else { ax25->n2count++; } break; } ax25_calculate_t1(ax25); ax25_start_t1timer(ax25); }
32 8 23 4 5 5 5 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 #ifndef __LINUX_MROUTE_BASE_H #define __LINUX_MROUTE_BASE_H #include <linux/netdevice.h> #include <linux/rhashtable-types.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> /** * struct vif_device - interface representor for multicast routing * @dev: network device being used * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing * @pkt_out: statistic; packets egressing * @rate_limit: Traffic shaping (NI) * @threshold: TTL threshold * @flags: Control flags * @link: Physical interface index * @dev_parent_id: device parent id * @local: Local address * @remote: Remote address for tunnels */ struct vif_device { struct net_device __rcu *dev; netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; unsigned char threshold; unsigned short flags; int link; /* Currently only used by ipmr */ struct netdev_phys_item_id dev_parent_id; __be32 local, remote; }; struct vif_entry_notifier_info { struct fib_notifier_info info; struct net_device *dev; unsigned short vif_index; unsigned short vif_flags; u32 tb_id; }; static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, unsigned int *ipmr_seq) { struct vif_entry_notifier_info info = { .info = { .family = family, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; ASSERT_RTNL(); (*ipmr_seq)++; return call_fib_notifiers(net, event_type, &info.info); } #ifndef MAXVIFS /* This one is nasty; value is defined in uapi using different symbols for * mroute and morute6 but both map into same 32. */ #define MAXVIFS 32 #endif /* Note: This helper is deprecated. */ #define VIF_EXISTS(_mrt, _idx) (!!rcu_access_pointer((_mrt)->vif_table[_idx].dev)) /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), MFC_OFFLOAD = BIT(1), }; /** * struct mr_mfc - common multicast routing entries * @mnode: rhashtable list * @mfc_parent: source interface (iif) * @mfc_flags: entry flags * @expires: unresolved entry expire time * @unresolved: unresolved cached skbs * @last_assert: time of last assert * @minvif: minimum VIF id * @maxvif: maximum VIF id * @bytes: bytes that have passed for this entry * @pkt: packets that have passed for this entry * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction * @free: Operation used for freeing an entry under RCU */ struct mr_mfc { struct rhlist_head mnode; unsigned short mfc_parent; int mfc_flags; union { struct { unsigned long expires; struct sk_buff_head unresolved; } unres; struct { unsigned long last_assert; int minvif; int maxvif; unsigned long bytes; unsigned long pkt; unsigned long wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; } res; } mfc_un; struct list_head list; struct rcu_head rcu; void (*free)(struct rcu_head *head); }; static inline void mr_cache_put(struct mr_mfc *c) { if (refcount_dec_and_test(&c->mfc_un.res.refcount)) call_rcu(&c->rcu, c->free); } static inline void mr_cache_hold(struct mr_mfc *c) { refcount_inc(&c->mfc_un.res.refcount); } struct mfc_entry_notifier_info { struct fib_notifier_info info; struct mr_mfc *mfc; u32 tb_id; }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .mfc = mfc, .tb_id = tb_id }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, unsigned int *ipmr_seq) { struct mfc_entry_notifier_info info = { .info = { .family = family, }, .mfc = mfc, .tb_id = tb_id }; ASSERT_RTNL(); (*ipmr_seq)++; return call_fib_notifiers(net, event_type, &info.info); } struct mr_table; /** * struct mr_table_ops - callbacks and info for protocol-specific ops * @rht_params: parameters for accessing the MFC hash * @cmparg_any: a hash key to be used for matching on (*,*) routes */ struct mr_table_ops { const struct rhashtable_params *rht_params; void *cmparg_any; }; /** * struct mr_table - a multicast routing table * @list: entry within a list of multicast routing tables * @net: net where this table belongs * @ops: protocol specific operations * @id: identifier of the table * @mroute_sk: socket associated with the table * @ipmr_expire_timer: timer for handling unresolved routes * @mfc_unres_queue: list of unresolved MFC entries * @vif_table: array containing all possible vifs * @mfc_hash: Hash table of all resolved routes for easy lookup * @mfc_cache_list: list of resovled routes for possible traversal * @maxvif: Identifier of highest value vif currently in use * @cache_resolve_queue_len: current size of unresolved queue * @mroute_do_assert: Whether to inform userspace on wrong ingress * @mroute_do_pim: Whether to receive IGMP PIMv1 * @mroute_reg_vif_num: PIM-device vif index */ struct mr_table { struct list_head list; possible_net_t net; struct mr_table_ops ops; u32 id; struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; struct vif_device vif_table[MAXVIFS]; struct rhltable mfc_hash; struct list_head mfc_cache_list; int maxvif; atomic_t cache_resolve_queue_len; bool mroute_do_assert; bool mroute_do_pim; bool mroute_do_wrvifwhole; int mroute_reg_vif_num; }; #ifdef CONFIG_IP_MROUTE_COMMON void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask); struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, void (*expire_func)(struct timer_list *t), void (*table_set)(struct mr_table *mrt, struct net *net)); /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent); void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi); void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, struct netlink_callback *cb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask) { } static inline void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) { return NULL; } static inline void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) { return NULL; } static inline struct mr_mfc *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) { return NULL; } static inline int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm) { return -EINVAL; } static inline int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack) { return -EINVAL; } #endif static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg) { return mr_mfc_find_parent(mrt, hasharg, -1); } #ifdef CONFIG_PROC_FS struct mr_vif_iter { struct seq_net_private p; struct mr_table *mrt; int ct; }; struct mr_mfc_iter { struct seq_net_private p; struct mr_table *mrt; struct list_head *cache; /* Lock protecting the mr_table's unresolved queue */ spinlock_t *lock; }; #ifdef CONFIG_IP_MROUTE_COMMON void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos); void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return *pos ? mr_vif_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos); void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { struct mr_mfc_iter *it = seq->private; it->mrt = mrt; it->cache = NULL; it->lock = lock; return *pos ? mr_mfc_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(it->lock); else if (it->cache == &mrt->mfc_cache_list) rcu_read_unlock(); } #else static inline void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) { return NULL; } static inline void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos) { return NULL; } static inline void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { return NULL; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { } #endif #endif #endif
2 10 10 5 1 1 1 1 1 2 2 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 // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/btf_ids.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> /* * bpf_arena is a sparsely populated shared memory region between bpf program and * user space process. * * For example on x86-64 the values could be: * user_vm_start 7f7d26200000 // picked by mmap() * kern_vm_start ffffc90001e69000 // picked by get_vm_area() * For user space all pointers within the arena are normal 8-byte addresses. * In this example 7f7d26200000 is the address of the first page (pgoff=0). * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr * (u32)7f7d26200000 -> 26200000 * hence * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb * kernel memory region. * * BPF JITs generate the following code to access arena: * mov eax, eax // eax has lower 32-bit of user pointer * mov word ptr [rax + r12 + off], bx * where r12 == kern_vm_start and off is s16. * Hence allocate 4Gb + GUARD_SZ/2 on each side. * * Initially kernel vm_area and user vma are not populated. * User space can fault-in any address which will insert the page * into kernel and user vma. * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc * which will insert it into kernel vm_area. * The later fault-in from user space will populate that page into user vma. */ /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ #define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8) #define KERN_VM_SZ (SZ_4G + GUARD_SZ) struct bpf_arena { struct bpf_map map; u64 user_vm_start; u64 user_vm_end; struct vm_struct *kern_vm; struct maple_tree mt; struct list_head vma_list; struct mutex lock; }; u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) { return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0; } u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) { return arena ? arena->user_vm_start : 0; } static long arena_map_peek_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags) { return -EOPNOTSUPP; } static long arena_map_pop_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static long arena_map_delete_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -EOPNOTSUPP; } static long compute_pgoff(struct bpf_arena *arena, long uaddr) { return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT; } static struct bpf_map *arena_map_alloc(union bpf_attr *attr) { struct vm_struct *kern_vm; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_arena *arena; u64 vm_range; int err = -ENOMEM; if (attr->key_size || attr->value_size || attr->max_entries == 0 || /* BPF_F_MMAPABLE must be set */ !(attr->map_flags & BPF_F_MMAPABLE) || /* No unsupported flags present */ (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV))) return ERR_PTR(-EINVAL); if (attr->map_extra & ~PAGE_MASK) /* If non-zero the map_extra is an expected user VMA start address */ return ERR_PTR(-EINVAL); vm_range = (u64)attr->max_entries * PAGE_SIZE; if (vm_range > SZ_4G) return ERR_PTR(-E2BIG); if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) /* user vma must not cross 32-bit boundary */ return ERR_PTR(-ERANGE); kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP); if (!kern_vm) return ERR_PTR(-ENOMEM); arena = bpf_map_area_alloc(sizeof(*arena), numa_node); if (!arena) goto err; arena->kern_vm = kern_vm; arena->user_vm_start = attr->map_extra; if (arena->user_vm_start) arena->user_vm_end = arena->user_vm_start + vm_range; INIT_LIST_HEAD(&arena->vma_list); bpf_map_init_from_attr(&arena->map, attr); mt_init_flags(&arena->mt, MT_FLAGS_ALLOC_RANGE); mutex_init(&arena->lock); return &arena->map; err: free_vm_area(kern_vm); return ERR_PTR(err); } static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data) { struct page *page; pte_t pte; pte = ptep_get(ptep); if (!pte_present(pte)) /* sanity check */ return 0; page = pte_page(pte); /* * We do not update pte here: * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug * 2. TLB flushing is batched or deferred. Even if we clear pte, * the TLB entries can stick around and continue to permit access to * the freed page. So it all relies on 1. */ __free_page(page); return 0; } static void arena_map_free(struct bpf_map *map) { struct bpf_arena *arena = container_of(map, struct bpf_arena, map); /* * Check that user vma-s are not around when bpf map is freed. * mmap() holds vm_file which holds bpf_map refcnt. * munmap() must have happened on vma followed by arena_vm_close() * which would clear arena->vma_list. */ if (WARN_ON_ONCE(!list_empty(&arena->vma_list))) return; /* * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area(). * It unmaps everything from vmalloc area and clears pgtables. * Call apply_to_existing_page_range() first to find populated ptes and * free those pages. */ apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena), KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL); free_vm_area(arena->kern_vm); mtree_destroy(&arena->mt); bpf_map_area_free(arena); } static void *arena_map_lookup_elem(struct bpf_map *map, void *key) { return ERR_PTR(-EINVAL); } static long arena_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return 0; } static u64 arena_map_mem_usage(const struct bpf_map *map) { return 0; } struct vma_list { struct vm_area_struct *vma; struct list_head head; atomic_t mmap_count; }; static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) { struct vma_list *vml; vml = kmalloc(sizeof(*vml), GFP_KERNEL); if (!vml) return -ENOMEM; atomic_set(&vml->mmap_count, 1); vma->vm_private_data = vml; vml->vma = vma; list_add(&vml->head, &arena->vma_list); return 0; } static void arena_vm_open(struct vm_area_struct *vma) { struct vma_list *vml = vma->vm_private_data; atomic_inc(&vml->mmap_count); } static void arena_vm_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); struct vma_list *vml = vma->vm_private_data; if (!atomic_dec_and_test(&vml->mmap_count)) return; guard(mutex)(&arena->lock); /* update link list under lock */ list_del(&vml->head); vma->vm_private_data = NULL; kfree(vml); } #define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */ static vm_fault_t arena_vm_fault(struct vm_fault *vmf) { struct bpf_map *map = vmf->vma->vm_file->private_data; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); struct page *page; long kbase, kaddr; int ret; kbase = bpf_arena_get_kern_vm_start(arena); kaddr = kbase + (u32)(vmf->address); guard(mutex)(&arena->lock); page = vmalloc_to_page((void *)kaddr); if (page) /* already have a page vmap-ed */ goto out; if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT) /* User space requested to segfault when page is not allocated by bpf prog */ return VM_FAULT_SIGSEGV; ret = mtree_insert(&arena->mt, vmf->pgoff, MT_ENTRY, GFP_KERNEL); if (ret) return VM_FAULT_SIGSEGV; /* Account into memcg of the process that created bpf_arena */ ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page); if (ret) { mtree_erase(&arena->mt, vmf->pgoff); return VM_FAULT_SIGSEGV; } ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page); if (ret) { mtree_erase(&arena->mt, vmf->pgoff); __free_page(page); return VM_FAULT_SIGSEGV; } out: page_ref_add(page, 1); vmf->page = page; return 0; } static const struct vm_operations_struct arena_vm_ops = { .open = arena_vm_open, .close = arena_vm_close, .fault = arena_vm_fault, }; static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct bpf_map *map = filp->private_data; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); long ret; if (pgoff) return -EINVAL; if (len > SZ_4G) return -E2BIG; /* if user_vm_start was specified at arena creation time */ if (arena->user_vm_start) { if (len > arena->user_vm_end - arena->user_vm_start) return -E2BIG; if (len != arena->user_vm_end - arena->user_vm_start) return -EINVAL; if (addr != arena->user_vm_start) return -EINVAL; } ret = mm_get_unmapped_area(current->mm, filp, addr, len * 2, 0, flags); if (IS_ERR_VALUE(ret)) return ret; if ((ret >> 32) == ((ret + len - 1) >> 32)) return ret; if (WARN_ON_ONCE(arena->user_vm_start)) /* checks at map creation time should prevent this */ return -EFAULT; return round_up(ret, SZ_4G); } static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_arena *arena = container_of(map, struct bpf_arena, map); guard(mutex)(&arena->lock); if (arena->user_vm_start && arena->user_vm_start != vma->vm_start) /* * If map_extra was not specified at arena creation time then * 1st user process can do mmap(NULL, ...) to pick user_vm_start * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..); * or * specify addr in map_extra and * use the same addr later with mmap(addr, MAP_FIXED..); */ return -EBUSY; if (arena->user_vm_end && arena->user_vm_end != vma->vm_end) /* all user processes must have the same size of mmap-ed region */ return -EBUSY; /* Earlier checks should prevent this */ if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff)) return -EFAULT; if (remember_vma(arena, vma)) return -ENOMEM; arena->user_vm_start = vma->vm_start; arena->user_vm_end = vma->vm_end; /* * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid * potential change of user_vm_start. */ vm_flags_set(vma, VM_DONTEXPAND); vma->vm_ops = &arena_vm_ops; return 0; } static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) { struct bpf_arena *arena = container_of(map, struct bpf_arena, map); if ((u64)off > arena->user_vm_end - arena->user_vm_start) return -ERANGE; *imm = (unsigned long)arena->user_vm_start; return 0; } BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena) const struct bpf_map_ops arena_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = arena_map_alloc, .map_free = arena_map_free, .map_direct_value_addr = arena_map_direct_value_addr, .map_mmap = arena_map_mmap, .map_get_unmapped_area = arena_get_unmapped_area, .map_get_next_key = arena_map_get_next_key, .map_push_elem = arena_map_push_elem, .map_peek_elem = arena_map_peek_elem, .map_pop_elem = arena_map_pop_elem, .map_lookup_elem = arena_map_lookup_elem, .map_update_elem = arena_map_update_elem, .map_delete_elem = arena_map_delete_elem, .map_check_btf = arena_map_check_btf, .map_mem_usage = arena_map_mem_usage, .map_btf_id = &bpf_arena_map_btf_ids[0], }; static u64 clear_lo32(u64 val) { return val & ~(u64)~0U; } /* * Allocate pages and vmap them into kernel vmalloc area. * Later the pages will be mmaped into user space vma. */ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id) { /* user_vm_end/start are fixed before bpf prog runs */ long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena); struct page **pages; long pgoff = 0; u32 uaddr32; int ret, i; if (page_cnt > page_cnt_max) return 0; if (uaddr) { if (uaddr & ~PAGE_MASK) return 0; pgoff = compute_pgoff(arena, uaddr); if (pgoff > page_cnt_max - page_cnt) /* requested address will be outside of user VMA */ return 0; } /* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */ pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); if (!pages) return 0; guard(mutex)(&arena->lock); if (uaddr) ret = mtree_insert_range(&arena->mt, pgoff, pgoff + page_cnt - 1, MT_ENTRY, GFP_KERNEL); else ret = mtree_alloc_range(&arena->mt, &pgoff, MT_ENTRY, page_cnt, 0, page_cnt_max - 1, GFP_KERNEL); if (ret) goto out_free_pages; ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO, node_id, page_cnt, pages); if (ret) goto out; uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); /* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1 * will not overflow 32-bit. Lower 32-bit need to represent * contiguous user address range. * Map these pages at kern_vm_start base. * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow * lower 32-bit and it's ok. */ ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); if (ret) { for (i = 0; i < page_cnt; i++) __free_page(pages[i]); goto out; } kvfree(pages); return clear_lo32(arena->user_vm_start) + uaddr32; out: mtree_erase(&arena->mt, pgoff); out_free_pages: kvfree(pages); return 0; } /* * If page is present in vmalloc area, unmap it from vmalloc area, * unmap it from all user space vma-s, * and free it. */ static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) { struct vma_list *vml; list_for_each_entry(vml, &arena->vma_list, head) zap_page_range_single(vml->vma, uaddr, PAGE_SIZE * page_cnt, NULL); } static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) { u64 full_uaddr, uaddr_end; long kaddr, pgoff, i; struct page *page; /* only aligned lower 32-bit are relevant */ uaddr = (u32)uaddr; uaddr &= PAGE_MASK; full_uaddr = clear_lo32(arena->user_vm_start) + uaddr; uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT)); if (full_uaddr >= uaddr_end) return; page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT; guard(mutex)(&arena->lock); pgoff = compute_pgoff(arena, uaddr); /* clear range */ mtree_store_range(&arena->mt, pgoff, pgoff + page_cnt - 1, NULL, GFP_KERNEL); if (page_cnt > 1) /* bulk zap if multiple pages being freed */ zap_pages(arena, full_uaddr, page_cnt); kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr; for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) { page = vmalloc_to_page((void *)kaddr); if (!page) continue; if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ /* Optimization for the common case of page_cnt==1: * If page wasn't mapped into some user vma there * is no need to call zap_pages which is slow. When * page_cnt is big it's faster to do the batched zap. */ zap_pages(arena, full_uaddr, 1); vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); __free_page(page); } } __bpf_kfunc_start_defs(); __bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt, int node_id, u64 flags) { struct bpf_map *map = p__map; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt) return NULL; return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id); } __bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt) { struct bpf_map *map = p__map; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign) return; arena_free_pages(arena, (long)ptr__ign, page_cnt); } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(arena_kfuncs) BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) BTF_KFUNCS_END(arena_kfuncs) static const struct btf_kfunc_id_set common_kfunc_set = { .owner = THIS_MODULE, .set = &arena_kfuncs, }; static int __init kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); } late_initcall(kfunc_init);
3 2 1 1426 310 1420 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 // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> /* for ipv4 options. */ #include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_flow_table.h> struct nft_flow_offload { struct nft_flowtable *flowtable; }; static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) { if (dst_xfrm(dst)) return FLOW_OFFLOAD_XMIT_XFRM; return FLOW_OFFLOAD_XMIT_NEIGH; } static void nft_default_forward_path(struct nf_flow_route *route, struct dst_entry *dst_cache, enum ip_conntrack_dir dir) { route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; route->tuple[dir].dst = dst_cache; route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } static bool nft_is_valid_ether_device(const struct net_device *dev) { if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return false; return true; } static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, enum ip_conntrack_dir dir, u8 *ha, struct net_device_path_stack *stack) { const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; struct net_device *dev = dst_cache->dev; struct neighbour *n; u8 nud_state; if (!nft_is_valid_ether_device(dev)) goto out; n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; read_lock_bh(&n->lock); nud_state = n->nud_state; ether_addr_copy(ha, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; out: return dev_fill_forward_path(dev, ha, stack); } struct nft_forward_info { const struct net_device *indev; const struct net_device *outdev; const struct net_device *hw_outdev; struct id { __u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps; u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; enum flow_offload_xmit_type xmit_type; }; static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) { const struct net_device_path *path; int i; memcpy(info->h_dest, ha, ETH_ALEN); for (i = 0; i < stack->num_paths; i++) { path = &stack->path[i]; switch (path->type) { case DEV_PATH_ETHERNET: case DEV_PATH_DSA: case DEV_PATH_VLAN: case DEV_PATH_PPPOE: info->indev = path->dev; if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); if (path->type == DEV_PATH_ETHERNET) break; if (path->type == DEV_PATH_DSA) { i = stack->num_paths; break; } /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { info->indev = NULL; break; } if (!info->outdev) info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_UNTAG_HW: info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: info->num_encaps--; break; case DEV_PATH_BR_VLAN_KEEP: break; } info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; default: info->indev = NULL; break; } } if (!info->outdev) info->outdev = info->indev; info->hw_outdev = info->indev; if (nf_flowtable_hw_offload(flowtable) && nft_is_valid_ether_device(info->indev)) info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; } static bool nft_flowtable_find_dev(const struct net_device *dev, struct nft_flowtable *ft) { struct nft_hook *hook; bool found = false; list_for_each_entry_rcu(hook, &ft->hook_list, list) { if (hook->ops.dev != dev) continue; found = true; break; } return found; } static void nft_dev_forward_path(struct nf_flow_route *route, const struct nf_conn *ct, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { const struct dst_entry *dst = route->tuple[dir].dst; struct net_device_path_stack stack; struct nft_forward_info info = {}; unsigned char ha[ETH_ALEN]; int i; if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; route->tuple[!dir].in.ifindex = info.indev->ifindex; for (i = 0; i < info.num_encaps; i++) { route->tuple[!dir].in.encap[i].id = info.encap[i].id; route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; } route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.outdev->ifindex; route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; route->tuple[dir].xmit_type = info.xmit_type; } } static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK; fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } if (!dst_hold_safe(this_dst)) return -ENOENT; nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); if (!other_dst) { dst_release(this_dst); return -ENOENT; } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { nft_dev_forward_path(route, ct, dir, ft); nft_dev_forward_path(route, ct, !dir, ft); } return 0; } static bool nft_flow_offload_skip(struct sk_buff *skb, int family) { if (skb_sec_path(skb)) return true; if (family == NFPROTO_IPV4) { const struct ip_options *opt; opt = &(IPCB(skb)->opt); if (unlikely(opt->optlen)) return true; } return false; } static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; int ret; if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt))) goto out; ct = nf_ct_get(pkt->skb, &ctinfo); if (!ct) goto out; switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst || !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if (ct->status & IPS_NAT_MASK) goto out; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) goto out; break; } #endif default: goto out; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) goto out; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) goto out; dir = CTINFO2DIR(ctinfo); if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); if (!flow) goto err_flow_alloc; flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; return; err_flow_add: flow_offload_free(flow); err_flow_alloc: dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); out: regs->verdict.code = NFT_BREAK; } static int nft_flow_offload_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, hook_mask); } static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, }; static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_flow_offload *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_flowtable *flowtable; if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); if (!nft_use_inc(&flowtable->use)) return -EMFILE; priv->flowtable = flowtable; return nf_ct_netns_get(ctx->net, ctx->family); } static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); } static void nft_flow_offload_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_flow_offload *priv = nft_expr_priv(expr); nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, ctx->family); } static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_flow_offload_type; static const struct nft_expr_ops nft_flow_offload_ops = { .type = &nft_flow_offload_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, .activate = nft_flow_offload_activate, .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_DOWN) return NOTIFY_DONE; nf_flow_table_cleanup(dev); return NOTIFY_DONE; } static struct notifier_block flow_offload_netdev_notifier = { .notifier_call = flow_offload_netdev_event, }; static int __init nft_flow_offload_module_init(void) { int err; err = register_netdevice_notifier(&flow_offload_netdev_notifier); if (err) goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) goto register_expr; return 0; register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); err: return err; } static void __exit nft_flow_offload_module_exit(void) { nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); } module_init(nft_flow_offload_module_init); module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); MODULE_DESCRIPTION("nftables hardware flow offload module");
1 1 1 1 1 1 1 1 1 1 1 1 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 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 // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct rss_req_info { struct ethnl_req_info base; u32 rss_context; }; struct rss_reply_data { struct ethnl_reply_data base; bool no_key_fields; u32 indir_size; u32 hkey_size; u32 hfunc; u32 input_xfrm; u32 *indir_table; u8 *hkey; }; #define RSS_REQINFO(__req_base) \ container_of(__req_base, struct rss_req_info, base) #define RSS_REPDATA(__reply_base) \ container_of(__reply_base, struct rss_reply_data, base) const struct nla_policy ethnl_rss_get_policy[] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, [ETHTOOL_A_RSS_START_CONTEXT] = { .type = NLA_U32 }, }; static int rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rss_req_info *request = RSS_REQINFO(req_info); if (tb[ETHTOOL_A_RSS_CONTEXT]) request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { NL_SET_BAD_ATTR(extack, tb[ETHTOOL_A_RSS_START_CONTEXT]); return -EINVAL; } return 0; } static int rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, struct rss_reply_data *data, const struct genl_info *info) { struct ethtool_rxfh_param rxfh = {}; const struct ethtool_ops *ops; u32 total_size, indir_bytes; u8 *rss_config; int ret; ops = dev->ethtool_ops; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->indir_size = 0; data->hkey_size = 0; if (ops->get_rxfh_indir_size) data->indir_size = ops->get_rxfh_indir_size(dev); if (ops->get_rxfh_key_size) data->hkey_size = ops->get_rxfh_key_size(dev); indir_bytes = data->indir_size * sizeof(u32); total_size = indir_bytes + data->hkey_size; rss_config = kzalloc(total_size, GFP_KERNEL); if (!rss_config) { ret = -ENOMEM; goto out_ops; } if (data->indir_size) data->indir_table = (u32 *)rss_config; if (data->hkey_size) data->hkey = rss_config + indir_bytes; rxfh.indir_size = data->indir_size; rxfh.indir = data->indir_table; rxfh.key_size = data->hkey_size; rxfh.key = data->hkey; ret = ops->get_rxfh(dev, &rxfh); if (ret) goto out_ops; data->hfunc = rxfh.hfunc; data->input_xfrm = rxfh.input_xfrm; out_ops: ethnl_ops_complete(dev); return ret; } static int rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, struct rss_reply_data *data, const struct genl_info *info) { struct ethtool_rxfh_context *ctx; u32 total_size, indir_bytes; u8 *rss_config; ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); if (!ctx) return -ENOENT; data->indir_size = ctx->indir_size; data->hkey_size = ctx->key_size; data->hfunc = ctx->hfunc; data->input_xfrm = ctx->input_xfrm; indir_bytes = data->indir_size * sizeof(u32); total_size = indir_bytes + data->hkey_size; rss_config = kzalloc(total_size, GFP_KERNEL); if (!rss_config) return -ENOMEM; data->indir_table = (u32 *)rss_config; memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes); if (data->hkey_size) { data->hkey = rss_config + indir_bytes; memcpy(data->hkey, ethtool_rxfh_context_key(ctx), data->hkey_size); } return 0; } static int rss_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct rss_reply_data *data = RSS_REPDATA(reply_base); struct rss_req_info *request = RSS_REQINFO(req_base); struct net_device *dev = reply_base->dev; const struct ethtool_ops *ops; ops = dev->ethtool_ops; if (!ops->get_rxfh) return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ if (request->rss_context) { if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) return -EOPNOTSUPP; data->no_key_fields = !ops->rxfh_per_ctx_key; return rss_prepare_ctx(request, dev, data, info); } return rss_prepare_get(request, dev, data, info); } static int rss_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); int len; len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */ nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ return len; } static int rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); struct rss_req_info *request = RSS_REQINFO(req_base); if (request->rss_context && nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) return -EMSGSIZE; if ((data->indir_size && nla_put(skb, ETHTOOL_A_RSS_INDIR, sizeof(u32) * data->indir_size, data->indir_table))) return -EMSGSIZE; if (data->no_key_fields) return 0; if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || (data->input_xfrm && nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || (data->hkey_size && nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; return 0; } static void rss_cleanup_data(struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); kfree(data->indir_table); } struct rss_nl_dump_ctx { unsigned long ifindex; unsigned long ctx_idx; /* User wants to only dump contexts from given ifindex */ unsigned int match_ifindex; unsigned int start_ctx; }; static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb) { NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx); return (struct rss_nl_dump_ctx *)cb->ctx; } int ethnl_rss_dump_start(struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; int ret; /* Filtering by context not supported */ if (tb[ETHTOOL_A_RSS_CONTEXT]) { NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); return -EINVAL; } if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { ctx->start_ctx = nla_get_u32(tb[ETHTOOL_A_RSS_START_CONTEXT]); ctx->ctx_idx = ctx->start_ctx; } ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_RSS_HEADER], sock_net(cb->skb->sk), cb->extack, false); if (req_info.dev) { ctx->match_ifindex = req_info.dev->ifindex; ctx->ifindex = ctx->match_ifindex; ethnl_parse_header_dev_put(&req_info); req_info.dev = NULL; } return ret; } static int rss_dump_one_ctx(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, u32 rss_context) { const struct genl_info *info = genl_info_dump(cb); struct rss_reply_data data = {}; struct rss_req_info req = {}; void *ehdr; int ret; req.rss_context = rss_context; ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_RSS_GET_REPLY); if (!ehdr) return -EMSGSIZE; ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_RSS_HEADER); if (ret < 0) goto err_cancel; /* Context 0 is not currently storred or cached in the XArray */ if (!rss_context) ret = rss_prepare_get(&req, dev, &data, info); else ret = rss_prepare_ctx(&req, dev, &data, info); if (ret) goto err_cancel; ret = rss_fill_reply(skb, &req.base, &data.base); if (ret) goto err_cleanup; genlmsg_end(skb, ehdr); rss_cleanup_data(&data.base); return 0; err_cleanup: rss_cleanup_data(&data.base); err_cancel: genlmsg_cancel(skb, ehdr); return ret; } static int rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); int ret; if (!dev->ethtool_ops->get_rxfh) return 0; if (!ctx->ctx_idx) { ret = rss_dump_one_ctx(skb, cb, dev, 0); if (ret) return ret; ctx->ctx_idx++; } for (; xa_find(&dev->ethtool->rss_ctx, &ctx->ctx_idx, ULONG_MAX, XA_PRESENT); ctx->ctx_idx++) { ret = rss_dump_one_ctx(skb, cb, dev, ctx->ctx_idx); if (ret) return ret; } ctx->ctx_idx = ctx->start_ctx; return 0; } int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); struct net *net = sock_net(skb->sk); struct net_device *dev; int ret = 0; rtnl_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex) break; ret = rss_dump_one_dev(skb, cb, dev); if (ret) break; } rtnl_unlock(); return ret; } const struct ethnl_request_ops ethnl_rss_request_ops = { .request_cmd = ETHTOOL_MSG_RSS_GET, .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, .hdr_attr = ETHTOOL_A_RSS_HEADER, .req_info_size = sizeof(struct rss_req_info), .reply_data_size = sizeof(struct rss_reply_data), .parse_request = rss_parse_request, .prepare_data = rss_prepare_data, .reply_size = rss_reply_size, .fill_reply = rss_fill_reply, .cleanup_data = rss_cleanup_data, };
1 5 1 5 5 4 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 // SPDX-License-Identifier: GPL-2.0-only #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <asm/string.h> #include <linux/kmod.h> #include <linux/sysctl.h> #include <net/ip_vs.h> /* IPVS pe list */ static LIST_HEAD(ip_vs_pe); /* semaphore for IPVS PEs. */ static DEFINE_MUTEX(ip_vs_pe_mutex); /* Get pe in the pe list by name */ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name) { struct ip_vs_pe *pe; IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__, pe_name); rcu_read_lock(); list_for_each_entry_rcu(pe, &ip_vs_pe, n_list) { /* Test and get the modules atomically */ if (pe->module && !try_module_get(pe->module)) { /* This pe is just deleted */ continue; } if (strcmp(pe_name, pe->name)==0) { /* HIT */ rcu_read_unlock(); return pe; } module_put(pe->module); } rcu_read_unlock(); return NULL; } /* Lookup pe and try to load it if it doesn't exist */ struct ip_vs_pe *ip_vs_pe_getbyname(const char *name) { struct ip_vs_pe *pe; /* Search for the pe by name */ pe = __ip_vs_pe_getbyname(name); /* If pe not found, load the module and search again */ if (!pe) { request_module("ip_vs_pe_%s", name); pe = __ip_vs_pe_getbyname(name); } return pe; } /* Register a pe in the pe list */ int register_ip_vs_pe(struct ip_vs_pe *pe) { struct ip_vs_pe *tmp; /* increase the module use count */ if (!ip_vs_use_count_inc()) return -ENOENT; mutex_lock(&ip_vs_pe_mutex); /* Make sure that the pe with this name doesn't exist * in the pe list. */ list_for_each_entry(tmp, &ip_vs_pe, n_list) { if (strcmp(tmp->name, pe->name) == 0) { mutex_unlock(&ip_vs_pe_mutex); ip_vs_use_count_dec(); pr_err("%s(): [%s] pe already existed " "in the system\n", __func__, pe->name); return -EINVAL; } } /* Add it into the d-linked pe list */ list_add_rcu(&pe->n_list, &ip_vs_pe); mutex_unlock(&ip_vs_pe_mutex); pr_info("[%s] pe registered.\n", pe->name); return 0; } EXPORT_SYMBOL_GPL(register_ip_vs_pe); /* Unregister a pe from the pe list */ int unregister_ip_vs_pe(struct ip_vs_pe *pe) { mutex_lock(&ip_vs_pe_mutex); /* Remove it from the d-linked pe list */ list_del_rcu(&pe->n_list); mutex_unlock(&ip_vs_pe_mutex); /* decrease the module use count */ ip_vs_use_count_dec(); pr_info("[%s] pe unregistered.\n", pe->name); return 0; } EXPORT_SYMBOL_GPL(unregister_ip_vs_pe);
16190 4218 105 41 34 12 2 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 /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; ino_t ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf; /* Size of read buffer. */ size_t readbuf_size; /* Buffer for writing. */ char *write_buf; /* Size of write buffer. */ size_t writebuf_size; /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** Function prototypes. **********/ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */
247 7 238 7 7 7 315 245 243 72 3 1 68 160 160 160 160 159 159 160 160 160 60 4 56 1 55 50 6 50 231 79 79 119 3 110 11 122 3 118 3 107 11 2 16 9 8 1 1 6 10 6 7 7 4 6 5 8 3 7 3 7 2 9 8 17 17 102 95 7 97 4 102 102 130 9 105 1 122 102 19 18 102 122 127 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 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2006 IBM Corporation * * Author: Serge Hallyn <serue@us.ibm.com> * * Jun 2006 - namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> */ #include <linux/slab.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/init_task.h> #include <linux/mnt_namespace.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> #include <linux/time_namespace.h> #include <linux/fs_struct.h> #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/syscalls.h> #include <linux/cgroup.h> #include <linux/perf_event.h> static struct kmem_cache *nsproxy_cachep; struct nsproxy init_nsproxy = { .count = REFCOUNT_INIT(1), .uts_ns = &init_uts_ns, #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) .ipc_ns = &init_ipc_ns, #endif .mnt_ns = NULL, .pid_ns_for_children = &init_pid_ns, #ifdef CONFIG_NET .net_ns = &init_net, #endif #ifdef CONFIG_CGROUPS .cgroup_ns = &init_cgroup_ns, #endif #ifdef CONFIG_TIME_NS .time_ns = &init_time_ns, .time_ns_for_children = &init_time_ns, #endif }; static inline struct nsproxy *create_nsproxy(void) { struct nsproxy *nsproxy; nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL); if (nsproxy) refcount_set(&nsproxy->count, 1); return nsproxy; } /* * Create new nsproxy and all of its the associated namespaces. * Return the newly created nsproxy. Do not attach this to the task, * leave it to the caller to do proper locking and attach it to task. */ static struct nsproxy *create_new_namespaces(unsigned long flags, struct task_struct *tsk, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct nsproxy *new_nsp; int err; new_nsp = create_nsproxy(); if (!new_nsp) return ERR_PTR(-ENOMEM); new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs); if (IS_ERR(new_nsp->mnt_ns)) { err = PTR_ERR(new_nsp->mnt_ns); goto out_ns; } new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns); if (IS_ERR(new_nsp->uts_ns)) { err = PTR_ERR(new_nsp->uts_ns); goto out_uts; } new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns); if (IS_ERR(new_nsp->ipc_ns)) { err = PTR_ERR(new_nsp->ipc_ns); goto out_ipc; } new_nsp->pid_ns_for_children = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children); if (IS_ERR(new_nsp->pid_ns_for_children)) { err = PTR_ERR(new_nsp->pid_ns_for_children); goto out_pid; } new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns, tsk->nsproxy->cgroup_ns); if (IS_ERR(new_nsp->cgroup_ns)) { err = PTR_ERR(new_nsp->cgroup_ns); goto out_cgroup; } new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); goto out_net; } new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns, tsk->nsproxy->time_ns_for_children); if (IS_ERR(new_nsp->time_ns_for_children)) { err = PTR_ERR(new_nsp->time_ns_for_children); goto out_time; } new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns); return new_nsp; out_time: put_net(new_nsp->net_ns); out_net: put_cgroup_ns(new_nsp->cgroup_ns); out_cgroup: if (new_nsp->pid_ns_for_children) put_pid_ns(new_nsp->pid_ns_for_children); out_pid: if (new_nsp->ipc_ns) put_ipc_ns(new_nsp->ipc_ns); out_ipc: if (new_nsp->uts_ns) put_uts_ns(new_nsp->uts_ns); out_uts: if (new_nsp->mnt_ns) put_mnt_ns(new_nsp->mnt_ns); out_ns: kmem_cache_free(nsproxy_cachep, new_nsp); return ERR_PTR(err); } /* * called from clone. This now handles copy for nsproxy and all * namespaces therein. */ int copy_namespaces(unsigned long flags, struct task_struct *tsk) { struct nsproxy *old_ns = tsk->nsproxy; struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); struct nsproxy *new_ns; if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWPID | CLONE_NEWNET | CLONE_NEWCGROUP | CLONE_NEWTIME)))) { if ((flags & CLONE_VM) || likely(old_ns->time_ns_for_children == old_ns->time_ns)) { get_nsproxy(old_ns); return 0; } } else if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; /* * CLONE_NEWIPC must detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. In clone parlance, CLONE_SYSVSEM * means share undolist with parent, so we must forbid using * it along with CLONE_NEWIPC. */ if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) == (CLONE_NEWIPC | CLONE_SYSVSEM)) return -EINVAL; new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs); if (IS_ERR(new_ns)) return PTR_ERR(new_ns); if ((flags & CLONE_VM) == 0) timens_on_fork(new_ns, tsk); tsk->nsproxy = new_ns; return 0; } void free_nsproxy(struct nsproxy *ns) { if (ns->mnt_ns) put_mnt_ns(ns->mnt_ns); if (ns->uts_ns) put_uts_ns(ns->uts_ns); if (ns->ipc_ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns_for_children) put_pid_ns(ns->pid_ns_for_children); if (ns->time_ns) put_time_ns(ns->time_ns); if (ns->time_ns_for_children) put_time_ns(ns->time_ns_for_children); put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } /* * Called from unshare. Unshare all the namespaces part of nsproxy. * On success, returns the new nsproxy. */ int unshare_nsproxy_namespaces(unsigned long unshare_flags, struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs) { struct user_namespace *user_ns; int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP | CLONE_NEWTIME))) return 0; user_ns = new_cred ? new_cred->user_ns : current_user_ns(); if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; *new_nsp = create_new_namespaces(unshare_flags, current, user_ns, new_fs ? new_fs : current->fs); if (IS_ERR(*new_nsp)) { err = PTR_ERR(*new_nsp); goto out; } out: return err; } void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) { struct nsproxy *ns; might_sleep(); task_lock(p); ns = p->nsproxy; p->nsproxy = new; task_unlock(p); if (ns) put_nsproxy(ns); } void exit_task_namespaces(struct task_struct *p) { switch_task_namespaces(p, NULL); } int exec_task_namespaces(void) { struct task_struct *tsk = current; struct nsproxy *new; if (tsk->nsproxy->time_ns_for_children == tsk->nsproxy->time_ns) return 0; new = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs); if (IS_ERR(new)) return PTR_ERR(new); timens_on_fork(new, tsk); switch_task_namespaces(tsk, new); return 0; } static int check_setns_flags(unsigned long flags) { if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWCGROUP))) return -EINVAL; #ifndef CONFIG_USER_NS if (flags & CLONE_NEWUSER) return -EINVAL; #endif #ifndef CONFIG_PID_NS if (flags & CLONE_NEWPID) return -EINVAL; #endif #ifndef CONFIG_UTS_NS if (flags & CLONE_NEWUTS) return -EINVAL; #endif #ifndef CONFIG_IPC_NS if (flags & CLONE_NEWIPC) return -EINVAL; #endif #ifndef CONFIG_CGROUPS if (flags & CLONE_NEWCGROUP) return -EINVAL; #endif #ifndef CONFIG_NET_NS if (flags & CLONE_NEWNET) return -EINVAL; #endif #ifndef CONFIG_TIME_NS if (flags & CLONE_NEWTIME) return -EINVAL; #endif return 0; } static void put_nsset(struct nsset *nsset) { unsigned flags = nsset->flags; if (flags & CLONE_NEWUSER) put_cred(nsset_cred(nsset)); /* * We only created a temporary copy if we attached to more than just * the mount namespace. */ if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) free_fs_struct(nsset->fs); if (nsset->nsproxy) free_nsproxy(nsset->nsproxy); } static int prepare_nsset(unsigned flags, struct nsset *nsset) { struct task_struct *me = current; nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs); if (IS_ERR(nsset->nsproxy)) return PTR_ERR(nsset->nsproxy); if (flags & CLONE_NEWUSER) nsset->cred = prepare_creds(); else nsset->cred = current_cred(); if (!nsset->cred) goto out; /* Only create a temporary copy of fs_struct if we really need to. */ if (flags == CLONE_NEWNS) { nsset->fs = me->fs; } else if (flags & CLONE_NEWNS) { nsset->fs = copy_fs_struct(me->fs); if (!nsset->fs) goto out; } nsset->flags = flags; return 0; out: put_nsset(nsset); return -ENOMEM; } static inline int validate_ns(struct nsset *nsset, struct ns_common *ns) { return ns->ops->install(nsset, ns); } /* * This is the inverse operation to unshare(). * Ordering is equivalent to the standard ordering used everywhere else * during unshare and process creation. The switch to the new set of * namespaces occurs at the point of no return after installation of * all requested namespaces was successful in commit_nsset(). */ static int validate_nsset(struct nsset *nsset, struct pid *pid) { int ret = 0; unsigned flags = nsset->flags; struct user_namespace *user_ns = NULL; struct pid_namespace *pid_ns = NULL; struct nsproxy *nsp; struct task_struct *tsk; /* Take a "snapshot" of the target task's namespaces. */ rcu_read_lock(); tsk = pid_task(pid, PIDTYPE_PID); if (!tsk) { rcu_read_unlock(); return -ESRCH; } if (!ptrace_may_access(tsk, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); return -EPERM; } task_lock(tsk); nsp = tsk->nsproxy; if (nsp) get_nsproxy(nsp); task_unlock(tsk); if (!nsp) { rcu_read_unlock(); return -ESRCH; } #ifdef CONFIG_PID_NS if (flags & CLONE_NEWPID) { pid_ns = task_active_pid_ns(tsk); if (unlikely(!pid_ns)) { rcu_read_unlock(); ret = -ESRCH; goto out; } get_pid_ns(pid_ns); } #endif #ifdef CONFIG_USER_NS if (flags & CLONE_NEWUSER) user_ns = get_user_ns(__task_cred(tsk)->user_ns); #endif rcu_read_unlock(); /* * Install requested namespaces. The caller will have * verified earlier that the requested namespaces are * supported on this kernel. We don't report errors here * if a namespace is requested that isn't supported. */ #ifdef CONFIG_USER_NS if (flags & CLONE_NEWUSER) { ret = validate_ns(nsset, &user_ns->ns); if (ret) goto out; } #endif if (flags & CLONE_NEWNS) { ret = validate_ns(nsset, from_mnt_ns(nsp->mnt_ns)); if (ret) goto out; } #ifdef CONFIG_UTS_NS if (flags & CLONE_NEWUTS) { ret = validate_ns(nsset, &nsp->uts_ns->ns); if (ret) goto out; } #endif #ifdef CONFIG_IPC_NS if (flags & CLONE_NEWIPC) { ret = validate_ns(nsset, &nsp->ipc_ns->ns); if (ret) goto out; } #endif #ifdef CONFIG_PID_NS if (flags & CLONE_NEWPID) { ret = validate_ns(nsset, &pid_ns->ns); if (ret) goto out; } #endif #ifdef CONFIG_CGROUPS if (flags & CLONE_NEWCGROUP) { ret = validate_ns(nsset, &nsp->cgroup_ns->ns); if (ret) goto out; } #endif #ifdef CONFIG_NET_NS if (flags & CLONE_NEWNET) { ret = validate_ns(nsset, &nsp->net_ns->ns); if (ret) goto out; } #endif #ifdef CONFIG_TIME_NS if (flags & CLONE_NEWTIME) { ret = validate_ns(nsset, &nsp->time_ns->ns); if (ret) goto out; } #endif out: if (pid_ns) put_pid_ns(pid_ns); if (nsp) put_nsproxy(nsp); put_user_ns(user_ns); return ret; } /* * This is the point of no return. There are just a few namespaces * that do some actual work here and it's sufficiently minimal that * a separate ns_common operation seems unnecessary for now. * Unshare is doing the same thing. If we'll end up needing to do * more in a given namespace or a helper here is ultimately not * exported anymore a simple commit handler for each namespace * should be added to ns_common. */ static void commit_nsset(struct nsset *nsset) { unsigned flags = nsset->flags; struct task_struct *me = current; #ifdef CONFIG_USER_NS if (flags & CLONE_NEWUSER) { /* transfer ownership */ commit_creds(nsset_cred(nsset)); nsset->cred = NULL; } #endif /* We only need to commit if we have used a temporary fs_struct. */ if ((flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) { set_fs_root(me->fs, &nsset->fs->root); set_fs_pwd(me->fs, &nsset->fs->pwd); } #ifdef CONFIG_IPC_NS if (flags & CLONE_NEWIPC) exit_sem(me); #endif #ifdef CONFIG_TIME_NS if (flags & CLONE_NEWTIME) timens_commit(me, nsset->nsproxy->time_ns); #endif /* transfer ownership */ switch_task_namespaces(me, nsset->nsproxy); nsset->nsproxy = NULL; } SYSCALL_DEFINE2(setns, int, fd, int, flags) { struct fd f = fdget(fd); struct ns_common *ns = NULL; struct nsset nsset = {}; int err = 0; if (!fd_file(f)) return -EBADF; if (proc_ns_file(fd_file(f))) { ns = get_proc_ns(file_inode(fd_file(f))); if (flags && (ns->ops->type != flags)) err = -EINVAL; flags = ns->ops->type; } else if (!IS_ERR(pidfd_pid(fd_file(f)))) { err = check_setns_flags(flags); } else { err = -EINVAL; } if (err) goto out; err = prepare_nsset(flags, &nsset); if (err) goto out; if (proc_ns_file(fd_file(f))) err = validate_ns(&nsset, ns); else err = validate_nsset(&nsset, pidfd_pid(fd_file(f))); if (!err) { commit_nsset(&nsset); perf_event_namespaces(current); } put_nsset(&nsset); out: fdput(f); return err; } int __init nsproxy_cache_init(void) { nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC|SLAB_ACCOUNT); return 0; }
5 26 17 23 19 17 23 12 99 14 13 13 13 13 13 15 27 20 12 12 12 12 12 29 29 29 27 29 29 29 29 39 39 39 23 16 16 23 23 10 13 37 1 36 2 12 12 12 7 5 5 7 12 12 12 12 12 5 7 12 12 3 3 3 2 19 19 14 14 7 7 3 12 12 12 12 12 12 81 81 82 71 12 7 7 11 12 1383 1395 29 26 82 83 1423 1428 67 66 1 15 27 27 27 12 27 35 35 35 35 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle firewalling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> * Bart De Schuymer <bdschuym@pandora.be> * * Lennert dedicates this file to Kerstin Wurdinger. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/netfilter_bridge.h> #include <uapi/linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_arp.h> #include <linux/in_route.h> #include <linux/rculist.h> #include <linux/inetdevice.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/dst_metadata.h> #include <net/route.h> #include <net/netfilter/br_netfilter.h> #include <net/netns/generic.h> #include <net/inet_dscp.h> #include <linux/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif static unsigned int brnf_net_id __read_mostly; struct brnf_net { bool enabled; #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_hdr; #endif /* default value is 1 */ int call_iptables; int call_ip6tables; int call_arptables; /* default value is 0 */ int filter_vlan_tagged; int filter_pppoe_tagged; int pass_vlan_indev; }; #define IS_IP(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) #define IS_IPV6(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) #define IS_ARP(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) static inline __be16 vlan_proto(const struct sk_buff *skb) { if (skb_vlan_tag_present(skb)) return skb->protocol; else if (skb->protocol == htons(ETH_P_8021Q)) return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; else return 0; } static inline bool is_vlan_ip(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_IP) && brnet->filter_vlan_tagged; } static inline bool is_vlan_ipv6(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_IPV6) && brnet->filter_vlan_tagged; } static inline bool is_vlan_arp(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_ARP) && brnet->filter_vlan_tagged; } static inline __be16 pppoe_proto(const struct sk_buff *skb) { return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + sizeof(struct pppoe_hdr))); } static inline bool is_pppoe_ip(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return skb->protocol == htons(ETH_P_PPP_SES) && pppoe_proto(skb) == htons(PPP_IP) && brnet->filter_pppoe_tagged; } static inline bool is_pppoe_ipv6(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return skb->protocol == htons(ETH_P_PPP_SES) && pppoe_proto(skb) == htons(PPP_IPV6) && brnet->filter_pppoe_tagged; } /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) struct brnf_frag_data { local_lock_t bh_lock; char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; u8 size; u16 vlan_tci; __be16 vlan_proto; }; static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; static void nf_bridge_info_free(struct sk_buff *skb) { skb_ext_del(skb, SKB_EXT_BRIDGE_NF); } static inline struct net_device *bridge_parent(const struct net_device *dev) { struct net_bridge_port *port; port = br_port_get_rcu(dev); return port ? port->br->dev : NULL; } static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) { return skb_ext_add(skb, SKB_EXT_BRIDGE_NF); } unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) { switch (skb->protocol) { case __cpu_to_be16(ETH_P_8021Q): return VLAN_HLEN; case __cpu_to_be16(ETH_P_PPP_SES): return PPPOE_SES_HLEN; default: return 0; } } static inline void nf_bridge_pull_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); skb_pull(skb, len); skb->network_header += len; } static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); skb_pull_rcsum(skb, len); skb->network_header += len; } /* When handing a packet over to the IP layer * check whether we have a skb that is in the * expected format */ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) { const struct iphdr *iph; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto inhdr_error; iph = ip_hdr(skb); /* Basic sanity checks */ if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; if (!pskb_may_pull(skb, iph->ihl*4)) goto inhdr_error; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto csum_error; len = skb_ip_totlen(skb); if (skb->len < len) { __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; if (pskb_trim_rcsum(skb, len)) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); goto drop; } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); /* We should really parse IP options here but until * somebody who actually uses IP options complains to * us we'll just silently ignore the options because * we're lazy! */ return 0; csum_error: __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: return -1; } void nf_bridge_update_protocol(struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); switch (nf_bridge->orig_proto) { case BRNF_PROTO_8021Q: skb->protocol = htons(ETH_P_8021Q); break; case BRNF_PROTO_PPPOE: skb->protocol = htons(ETH_P_PPP_SES); break; case BRNF_PROTO_UNCHANGED: break; } } /* Obtain the correct destination MAC address, while preserving the original * source MAC address. If we already know this address, we just copy it. If we * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb) { struct neighbour *neigh; struct dst_entry *dst; skb->dev = bridge_parent(skb->dev); if (!skb->dev) goto free_skb; dst = skb_dst(skb); neigh = dst_neigh_lookup_skb(dst, skb); if (neigh) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { struct net_device *br_indev; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { neigh_release(neigh); goto free_skb; } neigh_hh_bridge(&neigh->hh, skb); skb->dev = br_indev; ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and * protocol number. */ skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ ret = READ_ONCE(neigh->output)(neigh, skb); } neigh_release(neigh); return ret; } free_skb: kfree_skb(skb); return 0; } static inline bool br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, const struct nf_bridge_info *nf_bridge) { return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge * port group as it was received on. We can still bridge * the packet. * 2. The packet was DNAT'ed to a different device, either * a non-bridged device or another bridge port group. * The packet will need to be routed. * * The correct way of distinguishing between these two cases is to * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * * Let's first consider the case that ip_route_input() succeeds: * * If the output device equals the logical bridge device the packet * came in on, we can consider this bridging. The corresponding MAC * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will * later be passed up to the IP stack to be routed. For a redirected * packet, ip_route_input() will give back the localhost as output device, * which differs from the bridge device. * * Let's now consider the case that ip_route_input() fails: * * This can be because the destination address is martian, in which case * the packet will be dropped. * If IP forwarding is disabled, ip_route_input() will fail, while * ip_route_output_key() can return success. The source * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care * if IP forwarding is enabled. If the output device equals the logical bridge * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev, *br_indev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { kfree_skb(skb); return 0; } nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a * martian destination or due to the fact that * forwarding is disabled. For most martian packets, * ip_route_output_key() will fail. It won't fail for 2 types of * martian destinations: loopback destinations and destination * 0.0.0.0. In both cases the packet will be dropped because the * destination is the loopback device and not the bridge. */ if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) goto free_skb; rt = ip_route_output(net, iph->daddr, 0, iph->tos & INET_DSCP_MASK, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (rt->dst.dev == dev) { skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); goto bridged_dnat; } ip_rt_put(rt); } free_skb: kfree_skb(skb); return 0; } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge); return 0; } ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; } skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); } skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_handle_frame_finish); return 0; } static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev, const struct net *net) { struct net_device *vlan, *br; struct brnf_net *brnet = net_generic(net, brnf_net_id); br = bridge_parent(dev); if (brnet->pass_vlan_indev == 0 || !skb_vlan_tag_present(skb)) return br; vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto, skb_vlan_tag_get(skb) & VLAN_VID_MASK); return vlan ? vlan : br; } /* Some common code for IPv4/IPv6 */ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; } nf_bridge->in_prerouting = 1; nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) nf_bridge->orig_proto = BRNF_PROTO_8021Q; else if (skb->protocol == htons(ETH_P_PPP_SES)) nf_bridge->orig_proto = BRNF_PROTO_PPPOE; /* Must drop socket now because of tproxy. */ skb_orphan(skb); return skb->dev; } /* Direct IPv6 traffic to br_nf_pre_routing_ipv6. * Replicate the checks that IPv4 does on packet reception. * Set skb->dev to the bridge device (i.e. parent of the * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ static unsigned int br_nf_pre_routing(void *priv, struct sk_buff *skb,