| 3 5 1 1 1 1 1 8 13 1 8 4 2 7 3 10 8 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * Framework for userspace DMA-BUF allocations * * Copyright (C) 2011 Google, Inc. * Copyright (C) 2019 Linaro Ltd. */ #include <linux/cdev.h> #include <linux/device.h> #include <linux/dma-buf.h> #include <linux/dma-heap.h> #include <linux/err.h> #include <linux/list.h> #include <linux/nospec.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/xarray.h> #include <uapi/linux/dma-heap.h> #define DEVNAME "dma_heap" #define NUM_HEAP_MINORS 128 /** * struct dma_heap - represents a dmabuf heap in the system * @name: used for debugging/device-node name * @ops: ops struct for this heap * @priv: private data for this heap * @heap_devt: heap device node * @list: list head connecting to list of heaps * @heap_cdev: heap char device * * Represents a heap of memory from which buffers can be made. */ struct dma_heap { const char *name; const struct dma_heap_ops *ops; void *priv; dev_t heap_devt; struct list_head list; struct cdev heap_cdev; }; static LIST_HEAD(heap_list); static DEFINE_MUTEX(heap_list_lock); static dev_t dma_heap_devt; static struct class *dma_heap_class; static DEFINE_XARRAY_ALLOC(dma_heap_minors); static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, u32 fd_flags, u64 heap_flags) { struct dma_buf *dmabuf; int fd; /* * Allocations from all heaps have to begin * and end on page boundaries. */ len = PAGE_ALIGN(len); if (!len) return -EINVAL; dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); if (IS_ERR(dmabuf)) return PTR_ERR(dmabuf); fd = dma_buf_fd(dmabuf, fd_flags); if (fd < 0) { dma_buf_put(dmabuf); /* just return, as put will call release and that will free */ } return fd; } static int dma_heap_open(struct inode *inode, struct file *file) { struct dma_heap *heap; heap = xa_load(&dma_heap_minors, iminor(inode)); if (!heap) { pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); return -ENODEV; } /* instance data as context */ file->private_data = heap; nonseekable_open(inode, file); return 0; } static long dma_heap_ioctl_allocate(struct file *file, void *data) { struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; int fd; if (heap_allocation->fd) return -EINVAL; if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) return -EINVAL; if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) return -EINVAL; fd = dma_heap_buffer_alloc(heap, heap_allocation->len, heap_allocation->fd_flags, heap_allocation->heap_flags); if (fd < 0) return fd; heap_allocation->fd = fd; return 0; } static unsigned int dma_heap_ioctl_cmds[] = { DMA_HEAP_IOCTL_ALLOC, }; static long dma_heap_ioctl(struct file *file, unsigned int ucmd, unsigned long arg) { char stack_kdata[128]; char *kdata = stack_kdata; unsigned int kcmd; unsigned int in_size, out_size, drv_size, ksize; int nr = _IOC_NR(ucmd); int ret = 0; if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); /* Get the kernel ioctl cmd that matches */ kcmd = dma_heap_ioctl_cmds[nr]; /* Figure out the delta between user cmd size and kernel cmd size */ drv_size = _IOC_SIZE(kcmd); out_size = _IOC_SIZE(ucmd); in_size = out_size; if ((ucmd & kcmd & IOC_IN) == 0) in_size = 0; if ((ucmd & kcmd & IOC_OUT) == 0) out_size = 0; ksize = max(max(in_size, out_size), drv_size); /* If necessary, allocate buffer for ioctl argument */ if (ksize > sizeof(stack_kdata)) { kdata = kmalloc(ksize, GFP_KERNEL); if (!kdata) return -ENOMEM; } if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { ret = -EFAULT; goto err; } /* zero out any difference between the kernel/user structure size */ if (ksize > in_size) memset(kdata + in_size, 0, ksize - in_size); switch (kcmd) { case DMA_HEAP_IOCTL_ALLOC: ret = dma_heap_ioctl_allocate(file, kdata); break; default: ret = -ENOTTY; goto err; } if (copy_to_user((void __user *)arg, kdata, out_size) != 0) ret = -EFAULT; err: if (kdata != stack_kdata) kfree(kdata); return ret; } static const struct file_operations dma_heap_fops = { .owner = THIS_MODULE, .open = dma_heap_open, .unlocked_ioctl = dma_heap_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = dma_heap_ioctl, #endif }; /** * dma_heap_get_drvdata - get per-heap driver data * @heap: DMA-Heap to retrieve private data for * * Returns: * The per-heap data for the heap. */ void *dma_heap_get_drvdata(struct dma_heap *heap) { return heap->priv; } /** * dma_heap_get_name - get heap name * @heap: DMA-Heap to retrieve the name of * * Returns: * The char* for the heap name. */ const char *dma_heap_get_name(struct dma_heap *heap) { return heap->name; } /** * dma_heap_add - adds a heap to dmabuf heaps * @exp_info: information needed to register this heap */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; struct device *dev_ret; unsigned int minor; int ret; if (!exp_info->name || !strcmp(exp_info->name, "")) { pr_err("dma_heap: Cannot add heap without a name\n"); return ERR_PTR(-EINVAL); } if (!exp_info->ops || !exp_info->ops->allocate) { pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); return ERR_PTR(-EINVAL); } heap = kzalloc(sizeof(*heap), GFP_KERNEL); if (!heap) return ERR_PTR(-ENOMEM); heap->name = exp_info->name; heap->ops = exp_info->ops; heap->priv = exp_info->priv; /* Find unused minor number */ ret = xa_alloc(&dma_heap_minors, &minor, heap, XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); if (ret < 0) { pr_err("dma_heap: Unable to get minor number for heap\n"); err_ret = ERR_PTR(ret); goto err0; } /* Create device */ heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); cdev_init(&heap->heap_cdev, &dma_heap_fops); ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); if (ret < 0) { pr_err("dma_heap: Unable to add char device\n"); err_ret = ERR_PTR(ret); goto err1; } dev_ret = device_create(dma_heap_class, NULL, heap->heap_devt, NULL, heap->name); if (IS_ERR(dev_ret)) { pr_err("dma_heap: Unable to create device\n"); err_ret = ERR_CAST(dev_ret); goto err2; } mutex_lock(&heap_list_lock); /* check the name is unique */ list_for_each_entry(h, &heap_list, list) { if (!strcmp(h->name, exp_info->name)) { mutex_unlock(&heap_list_lock); pr_err("dma_heap: Already registered heap named %s\n", exp_info->name); err_ret = ERR_PTR(-EINVAL); goto err3; } } /* Add heap to the list */ list_add(&heap->list, &heap_list); mutex_unlock(&heap_list_lock); return heap; err3: device_destroy(dma_heap_class, heap->heap_devt); err2: cdev_del(&heap->heap_cdev); err1: xa_erase(&dma_heap_minors, minor); err0: kfree(heap); return err_ret; } static char *dma_heap_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); } static int dma_heap_init(void) { int ret; ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); if (ret) return ret; dma_heap_class = class_create(DEVNAME); if (IS_ERR(dma_heap_class)) { unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); return PTR_ERR(dma_heap_class); } dma_heap_class->devnode = dma_heap_devnode; return 0; } subsys_initcall(dma_heap_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * DSA tagging protocol handling * * Copyright (c) 2008-2009 Marvell Semiconductor * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> */ #include <linux/netdevice.h> #include <linux/ptp_classify.h> #include <linux/skbuff.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include "tag.h" #include "user.h" static LIST_HEAD(dsa_tag_drivers_list); static DEFINE_MUTEX(dsa_tag_drivers_lock); /* Determine if we should defer delivery of skb until we have a rx timestamp. * * Called from dsa_switch_rcv. For now, this will only work if tagging is * enabled on the switch. Normally the MAC driver would retrieve the hardware * timestamp when it reads the packet out of the hardware. However in a DSA * switch, the DSA driver owning the interface to which the packet is * delivered is never notified unless we do so here. */ static bool dsa_skb_defer_rx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; unsigned int type; if (!ds->ops->port_rxtstamp) return false; if (skb_headroom(skb) < ETH_HLEN) return false; __skb_push(skb, ETH_HLEN); type = ptp_classify_raw(skb); __skb_pull(skb, ETH_HLEN); if (type == PTP_CLASS_NONE) return false; return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); } static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; struct dsa_user_priv *p; if (unlikely(!cpu_dp)) { kfree_skb(skb); return 0; } skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) return 0; if (md_dst && md_dst->type == METADATA_HW_PORT_MUX) { unsigned int port = md_dst->u.port_info.port_id; skb_dst_drop(skb); if (!skb_has_extensions(skb)) skb->slow_gro = 0; skb->dev = dsa_conduit_find_user(dev, 0, port); if (likely(skb->dev)) { dsa_default_offload_fwd_mark(skb); nskb = skb; } } else { nskb = cpu_dp->rcv(skb, dev); } if (!nskb) { kfree_skb(skb); return 0; } skb = nskb; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); if (unlikely(!dsa_user_dev_check(skb->dev))) { /* Packet is to be injected directly on an upper * device, e.g. a team/bond, so skip all DSA-port * specific actions. */ netif_rx(skb); return 0; } p = netdev_priv(skb->dev); if (unlikely(cpu_dp->ds->untag_bridge_pvid || cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; } skb = nskb; } dev_sw_netstats_rx_add(skb->dev, skb->len + ETH_HLEN); if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; gro_cells_receive(&p->gcells, skb); return 0; } struct packet_type dsa_pack_type __read_mostly = { .type = cpu_to_be16(ETH_P_XDSA), .func = dsa_switch_rcv, }; static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, struct module *owner) { dsa_tag_driver->owner = owner; mutex_lock(&dsa_tag_drivers_lock); list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); mutex_unlock(&dsa_tag_drivers_lock); } void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count, struct module *owner) { unsigned int i; for (i = 0; i < count; i++) dsa_tag_driver_register(dsa_tag_driver_array[i], owner); } static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) { mutex_lock(&dsa_tag_drivers_lock); list_del(&dsa_tag_driver->list); mutex_unlock(&dsa_tag_drivers_lock); } EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count) { unsigned int i; for (i = 0; i < count; i++) dsa_tag_driver_unregister(dsa_tag_driver_array[i]); } EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) { return ops->name; }; /* Function takes a reference on the module owning the tagger, * so dsa_tag_driver_put must be called afterwards. */ const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name) { const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); struct dsa_tag_driver *dsa_tag_driver; request_module("%s%s", DSA_TAG_DRIVER_ALIAS, name); mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { const struct dsa_device_ops *tmp = dsa_tag_driver->ops; if (strcmp(name, tmp->name)) continue; if (!try_module_get(dsa_tag_driver->owner)) break; ops = tmp; break; } mutex_unlock(&dsa_tag_drivers_lock); return ops; } const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol) { struct dsa_tag_driver *dsa_tag_driver; const struct dsa_device_ops *ops; bool found = false; request_module("%sid-%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { ops = dsa_tag_driver->ops; if (ops->proto == tag_protocol) { found = true; break; } } if (found) { if (!try_module_get(dsa_tag_driver->owner)) ops = ERR_PTR(-ENOPROTOOPT); } else { ops = ERR_PTR(-ENOPROTOOPT); } mutex_unlock(&dsa_tag_drivers_lock); return ops; } void dsa_tag_driver_put(const struct dsa_device_ops *ops) { struct dsa_tag_driver *dsa_tag_driver; mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { if (dsa_tag_driver->ops == ops) { module_put(dsa_tag_driver->owner); break; } } mutex_unlock(&dsa_tag_drivers_lock); } |
| 12 12 12 13 10 11 7 8 13 13 13 13 13 4 13 12 115 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 2 2 2 4 4 4 4 10 2 2 2 2 2 2 2 7 7 2 1 1 7 6 4 1 3 11 11 11 5 5 5 10 10 10 4 4 4 5 5 7 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Media entity * * Copyright (C) 2010 Nokia Corporation * * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com> * Sakari Ailus <sakari.ailus@iki.fi> */ #include <linux/bitmap.h> #include <linux/list.h> #include <linux/property.h> #include <linux/slab.h> #include <media/media-entity.h> #include <media/media-device.h> static inline const char *intf_type(struct media_interface *intf) { switch (intf->type) { case MEDIA_INTF_T_DVB_FE: return "dvb-frontend"; case MEDIA_INTF_T_DVB_DEMUX: return "dvb-demux"; case MEDIA_INTF_T_DVB_DVR: return "dvb-dvr"; case MEDIA_INTF_T_DVB_CA: return "dvb-ca"; case MEDIA_INTF_T_DVB_NET: return "dvb-net"; case MEDIA_INTF_T_V4L_VIDEO: return "v4l-video"; case MEDIA_INTF_T_V4L_VBI: return "v4l-vbi"; case MEDIA_INTF_T_V4L_RADIO: return "v4l-radio"; case MEDIA_INTF_T_V4L_SUBDEV: return "v4l-subdev"; case MEDIA_INTF_T_V4L_SWRADIO: return "v4l-swradio"; case MEDIA_INTF_T_V4L_TOUCH: return "v4l-touch"; default: return "unknown-intf"; } }; static inline const char *link_type_name(struct media_link *link) { switch (link->flags & MEDIA_LNK_FL_LINK_TYPE) { case MEDIA_LNK_FL_DATA_LINK: return "data"; case MEDIA_LNK_FL_INTERFACE_LINK: return "interface"; case MEDIA_LNK_FL_ANCILLARY_LINK: return "ancillary"; default: return "unknown"; } } __must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, struct media_device *mdev) { int idx_max; idx_max = ALIGN(mdev->entity_internal_idx_max + 1, BITS_PER_LONG); ent_enum->bmap = bitmap_zalloc(idx_max, GFP_KERNEL); if (!ent_enum->bmap) return -ENOMEM; ent_enum->idx_max = idx_max; return 0; } EXPORT_SYMBOL_GPL(media_entity_enum_init); void media_entity_enum_cleanup(struct media_entity_enum *ent_enum) { bitmap_free(ent_enum->bmap); } EXPORT_SYMBOL_GPL(media_entity_enum_cleanup); /** * dev_dbg_obj - Prints in debug mode a change on some object * * @event_name: Name of the event to report. Could be __func__ * @gobj: Pointer to the object * * Enabled only if DEBUG or CONFIG_DYNAMIC_DEBUG. Otherwise, it * won't produce any code. */ static void dev_dbg_obj(const char *event_name, struct media_gobj *gobj) { #if defined(DEBUG) || defined (CONFIG_DYNAMIC_DEBUG) switch (media_type(gobj)) { case MEDIA_GRAPH_ENTITY: dev_dbg(gobj->mdev->dev, "%s id %u: entity '%s'\n", event_name, media_id(gobj), gobj_to_entity(gobj)->name); break; case MEDIA_GRAPH_LINK: { struct media_link *link = gobj_to_link(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s link id %u ==> id %u\n", event_name, media_id(gobj), link_type_name(link), media_id(link->gobj0), media_id(link->gobj1)); break; } case MEDIA_GRAPH_PAD: { struct media_pad *pad = gobj_to_pad(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s%spad '%s':%d\n", event_name, media_id(gobj), pad->flags & MEDIA_PAD_FL_SINK ? "sink " : "", pad->flags & MEDIA_PAD_FL_SOURCE ? "source " : "", pad->entity->name, pad->index); break; } case MEDIA_GRAPH_INTF_DEVNODE: { struct media_interface *intf = gobj_to_intf(gobj); struct media_intf_devnode *devnode = intf_to_devnode(intf); dev_dbg(gobj->mdev->dev, "%s id %u: intf_devnode %s - major: %d, minor: %d\n", event_name, media_id(gobj), intf_type(intf), devnode->major, devnode->minor); break; } } #endif } void media_gobj_create(struct media_device *mdev, enum media_gobj_type type, struct media_gobj *gobj) { BUG_ON(!mdev); gobj->mdev = mdev; /* Create a per-type unique object ID */ gobj->id = media_gobj_gen_id(type, ++mdev->id); switch (type) { case MEDIA_GRAPH_ENTITY: list_add_tail(&gobj->list, &mdev->entities); break; case MEDIA_GRAPH_PAD: list_add_tail(&gobj->list, &mdev->pads); break; case MEDIA_GRAPH_LINK: list_add_tail(&gobj->list, &mdev->links); break; case MEDIA_GRAPH_INTF_DEVNODE: list_add_tail(&gobj->list, &mdev->interfaces); break; } mdev->topology_version++; dev_dbg_obj(__func__, gobj); } void media_gobj_destroy(struct media_gobj *gobj) { /* Do nothing if the object is not linked. */ if (gobj->mdev == NULL) return; dev_dbg_obj(__func__, gobj); gobj->mdev->topology_version++; /* Remove the object from mdev list */ list_del(&gobj->list); gobj->mdev = NULL; } /* * TODO: Get rid of this. */ #define MEDIA_ENTITY_MAX_PADS 512 int media_entity_pads_init(struct media_entity *entity, u16 num_pads, struct media_pad *pads) { struct media_device *mdev = entity->graph_obj.mdev; struct media_pad *iter; unsigned int i = 0; int ret = 0; if (num_pads >= MEDIA_ENTITY_MAX_PADS) return -E2BIG; entity->num_pads = num_pads; entity->pads = pads; if (mdev) mutex_lock(&mdev->graph_mutex); media_entity_for_each_pad(entity, iter) { iter->entity = entity; iter->index = i++; if (hweight32(iter->flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != 1) { ret = -EINVAL; break; } if (mdev) media_gobj_create(mdev, MEDIA_GRAPH_PAD, &iter->graph_obj); } if (ret && mdev) { media_entity_for_each_pad(entity, iter) media_gobj_destroy(&iter->graph_obj); } if (mdev) mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_pads_init); /* ----------------------------------------------------------------------------- * Graph traversal */ /** * media_entity_has_pad_interdep - Check interdependency between two pads * * @entity: The entity * @pad0: The first pad index * @pad1: The second pad index * * This function checks the interdependency inside the entity between @pad0 * and @pad1. If two pads are interdependent they are part of the same pipeline * and enabling one of the pads means that the other pad will become "locked" * and doesn't allow configuration changes. * * This function uses the &media_entity_operations.has_pad_interdep() operation * to check the dependency inside the entity between @pad0 and @pad1. If the * has_pad_interdep operation is not implemented, all pads of the entity are * considered to be interdependent. * * One of @pad0 and @pad1 must be a sink pad and the other one a source pad. * The function returns false if both pads are sinks or sources. * * The caller must hold entity->graph_obj.mdev->mutex. * * Return: true if the pads are connected internally and false otherwise. */ static bool media_entity_has_pad_interdep(struct media_entity *entity, unsigned int pad0, unsigned int pad1) { if (pad0 >= entity->num_pads || pad1 >= entity->num_pads) return false; if (entity->pads[pad0].flags & entity->pads[pad1].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) return false; if (!entity->ops || !entity->ops->has_pad_interdep) return true; return entity->ops->has_pad_interdep(entity, pad0, pad1); } static struct media_entity * media_entity_other(struct media_entity *entity, struct media_link *link) { if (link->source->entity == entity) return link->sink->entity; else return link->source->entity; } /* push an entity to traversal stack */ static void stack_push(struct media_graph *graph, struct media_entity *entity) { if (graph->top == MEDIA_ENTITY_ENUM_MAX_DEPTH - 1) { WARN_ON(1); return; } graph->top++; graph->stack[graph->top].link = entity->links.next; graph->stack[graph->top].entity = entity; } static struct media_entity *stack_pop(struct media_graph *graph) { struct media_entity *entity; entity = graph->stack[graph->top].entity; graph->top--; return entity; } #define link_top(en) ((en)->stack[(en)->top].link) #define stack_top(en) ((en)->stack[(en)->top].entity) /** * media_graph_walk_init - Allocate resources for graph walk * @graph: Media graph structure that will be used to walk the graph * @mdev: Media device * * Reserve resources for graph walk in media device's current * state. The memory must be released using * media_graph_walk_cleanup(). * * Returns error on failure, zero on success. */ __must_check int media_graph_walk_init( struct media_graph *graph, struct media_device *mdev) { return media_entity_enum_init(&graph->ent_enum, mdev); } EXPORT_SYMBOL_GPL(media_graph_walk_init); /** * media_graph_walk_cleanup - Release resources related to graph walking * @graph: Media graph structure that was used to walk the graph */ void media_graph_walk_cleanup(struct media_graph *graph) { media_entity_enum_cleanup(&graph->ent_enum); } EXPORT_SYMBOL_GPL(media_graph_walk_cleanup); void media_graph_walk_start(struct media_graph *graph, struct media_entity *entity) { media_entity_enum_zero(&graph->ent_enum); media_entity_enum_set(&graph->ent_enum, entity); graph->top = 0; graph->stack[graph->top].entity = NULL; stack_push(graph, entity); dev_dbg(entity->graph_obj.mdev->dev, "begin graph walk at '%s'\n", entity->name); } EXPORT_SYMBOL_GPL(media_graph_walk_start); static void media_graph_walk_iter(struct media_graph *graph) { struct media_entity *entity = stack_top(graph); struct media_link *link; struct media_entity *next; link = list_entry(link_top(graph), typeof(*link), list); /* If the link is not a data link, don't follow it */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { link_top(graph) = link_top(graph)->next; return; } /* The link is not enabled so we do not follow. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping disabled link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); return; } /* Get the entity at the other end of the link. */ next = media_entity_other(entity, link); /* Has the entity already been visited? */ if (media_entity_enum_test_and_set(&graph->ent_enum, next)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping entity '%s' (already seen)\n", next->name); return; } /* Push the new entity to stack and start over. */ link_top(graph) = link_top(graph)->next; stack_push(graph, next); dev_dbg(entity->graph_obj.mdev->dev, "walk: pushing '%s' on stack\n", next->name); lockdep_assert_held(&entity->graph_obj.mdev->graph_mutex); } struct media_entity *media_graph_walk_next(struct media_graph *graph) { struct media_entity *entity; if (stack_top(graph) == NULL) return NULL; /* * Depth first search. Push entity to stack and continue from * top of the stack until no more entities on the level can be * found. */ while (link_top(graph) != &stack_top(graph)->links) media_graph_walk_iter(graph); entity = stack_pop(graph); dev_dbg(entity->graph_obj.mdev->dev, "walk: returning entity '%s'\n", entity->name); return entity; } EXPORT_SYMBOL_GPL(media_graph_walk_next); /* ----------------------------------------------------------------------------- * Pipeline management */ /* * The pipeline traversal stack stores pads that are reached during graph * traversal, with a list of links to be visited to continue the traversal. * When a new pad is reached, an entry is pushed on the top of the stack and * points to the incoming pad and the first link of the entity. * * To find further pads in the pipeline, the traversal algorithm follows * internal pad dependencies in the entity, and then links in the graph. It * does so by iterating over all links of the entity, and following enabled * links that originate from a pad that is internally connected to the incoming * pad, as reported by the media_entity_has_pad_interdep() function. */ /** * struct media_pipeline_walk_entry - Entry in the pipeline traversal stack * * @pad: The media pad being visited * @links: Links left to be visited */ struct media_pipeline_walk_entry { struct media_pad *pad; struct list_head *links; }; /** * struct media_pipeline_walk - State used by the media pipeline traversal * algorithm * * @mdev: The media device * @stack: Depth-first search stack * @stack.size: Number of allocated entries in @stack.entries * @stack.top: Index of the top stack entry (-1 if the stack is empty) * @stack.entries: Stack entries */ struct media_pipeline_walk { struct media_device *mdev; struct { unsigned int size; int top; struct media_pipeline_walk_entry *entries; } stack; }; #define MEDIA_PIPELINE_STACK_GROW_STEP 16 static struct media_pipeline_walk_entry * media_pipeline_walk_top(struct media_pipeline_walk *walk) { return &walk->stack.entries[walk->stack.top]; } static bool media_pipeline_walk_empty(struct media_pipeline_walk *walk) { return walk->stack.top == -1; } /* Increase the stack size by MEDIA_PIPELINE_STACK_GROW_STEP elements. */ static int media_pipeline_walk_resize(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entries; unsigned int new_size; /* Safety check, to avoid stack overflows in case of bugs. */ if (walk->stack.size >= 256) return -E2BIG; new_size = walk->stack.size + MEDIA_PIPELINE_STACK_GROW_STEP; entries = krealloc(walk->stack.entries, new_size * sizeof(*walk->stack.entries), GFP_KERNEL); if (!entries) return -ENOMEM; walk->stack.entries = entries; walk->stack.size = new_size; return 0; } /* Push a new entry on the stack. */ static int media_pipeline_walk_push(struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_walk_entry *entry; int ret; if (walk->stack.top + 1 >= walk->stack.size) { ret = media_pipeline_walk_resize(walk); if (ret) return ret; } walk->stack.top++; entry = media_pipeline_walk_top(walk); entry->pad = pad; entry->links = pad->entity->links.next; dev_dbg(walk->mdev->dev, "media pipeline: pushed entry %u: '%s':%u\n", walk->stack.top, pad->entity->name, pad->index); return 0; } /* * Move the top entry link cursor to the next link. If all links of the entry * have been visited, pop the entry itself. Return true if the entry has been * popped. */ static bool media_pipeline_walk_pop(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry; if (WARN_ON(walk->stack.top < 0)) return false; entry = media_pipeline_walk_top(walk); if (entry->links->next == &entry->pad->entity->links) { dev_dbg(walk->mdev->dev, "media pipeline: entry %u has no more links, popping\n", walk->stack.top); walk->stack.top--; return true; } entry->links = entry->links->next; dev_dbg(walk->mdev->dev, "media pipeline: moved entry %u to next link\n", walk->stack.top); return false; } /* Free all memory allocated while walking the pipeline. */ static void media_pipeline_walk_destroy(struct media_pipeline_walk *walk) { kfree(walk->stack.entries); } /* Add a pad to the pipeline and push it to the stack. */ static int media_pipeline_add_pad(struct media_pipeline *pipe, struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_pad *ppad; list_for_each_entry(ppad, &pipe->pads, list) { if (ppad->pad == pad) { dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: already contains pad '%s':%u\n", pad->entity->name, pad->index); return 0; } } ppad = kzalloc(sizeof(*ppad), GFP_KERNEL); if (!ppad) return -ENOMEM; ppad->pipe = pipe; ppad->pad = pad; list_add_tail(&ppad->list, &pipe->pads); dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: added pad '%s':%u\n", pad->entity->name, pad->index); return media_pipeline_walk_push(walk, pad); } /* Explore the next link of the entity at the top of the stack. */ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); struct media_pad *origin; struct media_link *link; struct media_pad *local; struct media_pad *remote; bool last_link; int ret; origin = entry->pad; link = list_entry(entry->links, typeof(*link), list); last_link = media_pipeline_walk_pop(walk); if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (not data-link)\n"); return 0; } dev_dbg(walk->mdev->dev, "media pipeline: exploring link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); /* Get the local pad and remote pad. */ if (link->source->entity == origin->entity) { local = link->source; remote = link->sink; } else { local = link->sink; remote = link->source; } /* * Skip links that originate from a different pad than the incoming pad * that is not connected internally in the entity to the incoming pad. */ if (origin != local && !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (no route)\n"); goto done; } /* * Add the local pad of the link to the pipeline and push it to the * stack, if not already present. */ ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; /* Similarly, add the remote pad, but only if the link is enabled. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (disabled)\n"); goto done; } ret = media_pipeline_add_pad(pipe, walk, remote); if (ret) return ret; done: /* * If we're done iterating over links, iterate over pads of the entity. * This is necessary to discover pads that are not connected with any * link. Those are dead ends from a pipeline exploration point of view, * but are still part of the pipeline and need to be added to enable * proper validation. */ if (!last_link) return 0; dev_dbg(walk->mdev->dev, "media pipeline: adding unconnected pads of '%s'\n", local->entity->name); media_entity_for_each_pad(origin->entity, local) { /* * Skip the origin pad (already handled), pad that have links * (already discovered through iterating over links) and pads * not internally connected. */ if (origin == local || !local->num_links || !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) continue; ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; } return 0; } static void media_pipeline_cleanup(struct media_pipeline *pipe) { while (!list_empty(&pipe->pads)) { struct media_pipeline_pad *ppad; ppad = list_first_entry(&pipe->pads, typeof(*ppad), list); list_del(&ppad->list); kfree(ppad); } } static int media_pipeline_populate(struct media_pipeline *pipe, struct media_pad *pad) { struct media_pipeline_walk walk = { }; struct media_pipeline_pad *ppad; int ret; /* * Populate the media pipeline by walking the media graph, starting * from @pad. */ INIT_LIST_HEAD(&pipe->pads); pipe->mdev = pad->graph_obj.mdev; walk.mdev = pipe->mdev; walk.stack.top = -1; ret = media_pipeline_add_pad(pipe, &walk, pad); if (ret) goto done; /* * Use a depth-first search algorithm: as long as the stack is not * empty, explore the next link of the top entry. The * media_pipeline_explore_next_link() function will either move to the * next link, pop the entry if fully visited, or add new entries on * top. */ while (!media_pipeline_walk_empty(&walk)) { ret = media_pipeline_explore_next_link(pipe, &walk); if (ret) goto done; } dev_dbg(pad->graph_obj.mdev->dev, "media pipeline populated, found pads:\n"); list_for_each_entry(ppad, &pipe->pads, list) dev_dbg(pad->graph_obj.mdev->dev, "- '%s':%u\n", ppad->pad->entity->name, ppad->pad->index); WARN_ON(walk.stack.top != -1); ret = 0; done: media_pipeline_walk_destroy(&walk); if (ret) media_pipeline_cleanup(pipe); return ret; } __must_check int __media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; struct media_pipeline_pad *err_ppad; struct media_pipeline_pad *ppad; int ret; lockdep_assert_held(&mdev->graph_mutex); /* * If the pad is already part of a pipeline, that pipeline must be the * same as the pipe given to media_pipeline_start(). */ if (WARN_ON(origin->pipe && origin->pipe != pipe)) return -EINVAL; /* * If the pipeline has already been started, it is guaranteed to be * valid, so just increase the start count. */ if (pipe->start_count) { pipe->start_count++; return 0; } /* * Populate the pipeline. This populates the media_pipeline pads list * with media_pipeline_pad instances for each pad found during graph * walk. */ ret = media_pipeline_populate(pipe, origin); if (ret) return ret; /* * Now that all the pads in the pipeline have been gathered, perform * the validation steps. */ list_for_each_entry(ppad, &pipe->pads, list) { struct media_pad *pad = ppad->pad; struct media_entity *entity = pad->entity; bool has_enabled_link = false; struct media_link *link; dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, pad->index); /* * 1. Ensure that the pad doesn't already belong to a different * pipeline. */ if (pad->pipe) { dev_dbg(mdev->dev, "Failed to start pipeline: pad '%s':%u busy\n", pad->entity->name, pad->index); ret = -EBUSY; goto error; } /* * 2. Validate all active links whose sink is the current pad. * Validation of the source pads is performed in the context of * the connected sink pad to avoid duplicating checks. */ for_each_media_entity_data_link(entity, link) { /* Skip links unrelated to the current pad. */ if (link->sink != pad && link->source != pad) continue; /* Record if the pad has links and enabled links. */ if (link->flags & MEDIA_LNK_FL_ENABLED) has_enabled_link = true; /* * Validate the link if it's enabled and has the * current pad as its sink. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink != pad) continue; if (!entity->ops || !entity->ops->link_validate) continue; ret = entity->ops->link_validate(link); if (ret) { dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u failed validation: %d\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index, ret); goto error; } dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u is valid\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); } /* * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, * ensure that it has either no link or an enabled link. */ if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && !has_enabled_link) { dev_dbg(mdev->dev, "Pad '%s':%u must be connected by an enabled link\n", pad->entity->name, pad->index); ret = -ENOLINK; goto error; } /* Validation passed, store the pipe pointer in the pad. */ pad->pipe = pipe; } pipe->start_count++; return 0; error: /* * Link validation on graph failed. We revert what we did and * return the error. */ list_for_each_entry(err_ppad, &pipe->pads, list) { if (err_ppad == ppad) break; err_ppad->pad->pipe = NULL; } media_pipeline_cleanup(pipe); return ret; } EXPORT_SYMBOL_GPL(__media_pipeline_start); __must_check int media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; int ret; mutex_lock(&mdev->graph_mutex); ret = __media_pipeline_start(origin, pipe); mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_start); void __media_pipeline_stop(struct media_pad *pad) { struct media_pipeline *pipe = pad->pipe; struct media_pipeline_pad *ppad; /* * If the following check fails, the driver has performed an * unbalanced call to media_pipeline_stop() */ if (WARN_ON(!pipe)) return; if (--pipe->start_count) return; list_for_each_entry(ppad, &pipe->pads, list) ppad->pad->pipe = NULL; media_pipeline_cleanup(pipe); if (pipe->allocated) kfree(pipe); } EXPORT_SYMBOL_GPL(__media_pipeline_stop); void media_pipeline_stop(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; mutex_lock(&mdev->graph_mutex); __media_pipeline_stop(pad); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_pipeline_stop); __must_check int media_pipeline_alloc_start(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; struct media_pipeline *new_pipe = NULL; struct media_pipeline *pipe; int ret; mutex_lock(&mdev->graph_mutex); /* * Is the pad already part of a pipeline? If not, we need to allocate * a pipe. */ pipe = media_pad_pipeline(pad); if (!pipe) { new_pipe = kzalloc(sizeof(*new_pipe), GFP_KERNEL); if (!new_pipe) { ret = -ENOMEM; goto out; } pipe = new_pipe; pipe->allocated = true; } ret = __media_pipeline_start(pad, pipe); if (ret) kfree(new_pipe); out: mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_alloc_start); struct media_pad * __media_pipeline_pad_iter_next(struct media_pipeline *pipe, struct media_pipeline_pad_iter *iter, struct media_pad *pad) { if (!pad) iter->cursor = pipe->pads.next; if (iter->cursor == &pipe->pads) return NULL; pad = list_entry(iter->cursor, struct media_pipeline_pad, list)->pad; iter->cursor = iter->cursor->next; return pad; } EXPORT_SYMBOL_GPL(__media_pipeline_pad_iter_next); int media_pipeline_entity_iter_init(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter) { return media_entity_enum_init(&iter->ent_enum, pipe->mdev); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_init); void media_pipeline_entity_iter_cleanup(struct media_pipeline_entity_iter *iter) { media_entity_enum_cleanup(&iter->ent_enum); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_cleanup); struct media_entity * __media_pipeline_entity_iter_next(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter, struct media_entity *entity) { if (!entity) iter->cursor = pipe->pads.next; while (iter->cursor != &pipe->pads) { struct media_pipeline_pad *ppad; struct media_entity *entity; ppad = list_entry(iter->cursor, struct media_pipeline_pad, list); entity = ppad->pad->entity; iter->cursor = iter->cursor->next; if (!media_entity_enum_test_and_set(&iter->ent_enum, entity)) return entity; } return NULL; } EXPORT_SYMBOL_GPL(__media_pipeline_entity_iter_next); /* ----------------------------------------------------------------------------- * Links management */ static struct media_link *media_add_link(struct list_head *head) { struct media_link *link; link = kzalloc(sizeof(*link), GFP_KERNEL); if (link == NULL) return NULL; list_add_tail(&link->list, head); return link; } static void __media_entity_remove_link(struct media_entity *entity, struct media_link *link) { struct media_link *rlink, *tmp; struct media_entity *remote; /* Remove the reverse links for a data link. */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { link->source->num_links--; link->sink->num_links--; if (link->source->entity == entity) remote = link->sink->entity; else remote = link->source->entity; list_for_each_entry_safe(rlink, tmp, &remote->links, list) { if (rlink != link->reverse) continue; if (link->source->entity == entity) remote->num_backlinks--; /* Remove the remote link */ list_del(&rlink->list); media_gobj_destroy(&rlink->graph_obj); kfree(rlink); if (--remote->num_links == 0) break; } } list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } int media_get_pad_index(struct media_entity *entity, u32 pad_type, enum media_pad_signal_type sig_type) { unsigned int i; if (!entity) return -EINVAL; for (i = 0; i < entity->num_pads; i++) { if ((entity->pads[i].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != pad_type) continue; if (entity->pads[i].sig_type == sig_type) return i; } return -EINVAL; } EXPORT_SYMBOL_GPL(media_get_pad_index); int media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_entity *sink, u16 sink_pad, u32 flags) { struct media_link *link; struct media_link *backlink; if (flags & MEDIA_LNK_FL_LINK_TYPE) return -EINVAL; flags |= MEDIA_LNK_FL_DATA_LINK; if (WARN_ON(!source || !sink) || WARN_ON(source_pad >= source->num_pads) || WARN_ON(sink_pad >= sink->num_pads)) return -EINVAL; if (WARN_ON(!(source->pads[source_pad].flags & MEDIA_PAD_FL_SOURCE))) return -EINVAL; if (WARN_ON(!(sink->pads[sink_pad].flags & MEDIA_PAD_FL_SINK))) return -EINVAL; link = media_add_link(&source->links); if (link == NULL) return -ENOMEM; link->source = &source->pads[source_pad]; link->sink = &sink->pads[sink_pad]; link->flags = flags; /* Initialize graph object embedded at the new link */ media_gobj_create(source->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); /* Create the backlink. Backlinks are used to help graph traversal and * are not reported to userspace. */ backlink = media_add_link(&sink->links); if (backlink == NULL) { __media_entity_remove_link(source, link); return -ENOMEM; } backlink->source = &source->pads[source_pad]; backlink->sink = &sink->pads[sink_pad]; backlink->flags = flags; backlink->is_backlink = true; /* Initialize graph object embedded at the new link */ media_gobj_create(sink->graph_obj.mdev, MEDIA_GRAPH_LINK, &backlink->graph_obj); link->reverse = backlink; backlink->reverse = link; sink->num_backlinks++; sink->num_links++; source->num_links++; link->source->num_links++; link->sink->num_links++; return 0; } EXPORT_SYMBOL_GPL(media_create_pad_link); int media_create_pad_links(const struct media_device *mdev, const u32 source_function, struct media_entity *source, const u16 source_pad, const u32 sink_function, struct media_entity *sink, const u16 sink_pad, u32 flags, const bool allow_both_undefined) { struct media_entity *entity; unsigned function; int ret; /* Trivial case: 1:1 relation */ if (source && sink) return media_create_pad_link(source, source_pad, sink, sink_pad, flags); /* Worse case scenario: n:n relation */ if (!source && !sink) { if (!allow_both_undefined) return 0; media_device_for_each_entity(source, mdev) { if (source->function != source_function) continue; media_device_for_each_entity(sink, mdev) { if (sink->function != sink_function) continue; ret = media_create_pad_link(source, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } } return 0; } /* Handle 1:n and n:1 cases */ if (source) function = sink_function; else function = source_function; media_device_for_each_entity(entity, mdev) { if (entity->function != function) continue; if (source) ret = media_create_pad_link(source, source_pad, entity, sink_pad, flags); else ret = media_create_pad_link(entity, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } return 0; } EXPORT_SYMBOL_GPL(media_create_pad_links); void __media_entity_remove_links(struct media_entity *entity) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &entity->links, list) __media_entity_remove_link(entity, link); entity->num_links = 0; entity->num_backlinks = 0; } EXPORT_SYMBOL_GPL(__media_entity_remove_links); void media_entity_remove_links(struct media_entity *entity) { struct media_device *mdev = entity->graph_obj.mdev; /* Do nothing if the entity is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_entity_remove_links(entity); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_entity_remove_links); static int __media_entity_setup_link_notify(struct media_link *link, u32 flags) { int ret; /* Notify both entities. */ ret = media_entity_call(link->source->entity, link_setup, link->source, link->sink, flags); if (ret < 0 && ret != -ENOIOCTLCMD) return ret; ret = media_entity_call(link->sink->entity, link_setup, link->sink, link->source, flags); if (ret < 0 && ret != -ENOIOCTLCMD) { media_entity_call(link->source->entity, link_setup, link->source, link->sink, link->flags); return ret; } link->flags = flags; link->reverse->flags = link->flags; return 0; } int __media_entity_setup_link(struct media_link *link, u32 flags) { const u32 mask = MEDIA_LNK_FL_ENABLED; struct media_device *mdev; struct media_pad *source, *sink; int ret = -EBUSY; if (link == NULL) return -EINVAL; /* The non-modifiable link flags must not be modified. */ if ((link->flags & ~mask) != (flags & ~mask)) return -EINVAL; if (link->flags & MEDIA_LNK_FL_IMMUTABLE) return link->flags == flags ? 0 : -EINVAL; if (link->flags == flags) return 0; source = link->source; sink = link->sink; if (!(link->flags & MEDIA_LNK_FL_DYNAMIC) && (media_pad_is_streaming(source) || media_pad_is_streaming(sink))) return -EBUSY; mdev = source->graph_obj.mdev; if (mdev->ops && mdev->ops->link_notify) { ret = mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_PRE_LINK_CH); if (ret < 0) return ret; } ret = __media_entity_setup_link_notify(link, flags); if (mdev->ops && mdev->ops->link_notify) mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_POST_LINK_CH); return ret; } EXPORT_SYMBOL_GPL(__media_entity_setup_link); int media_entity_setup_link(struct media_link *link, u32 flags) { int ret; mutex_lock(&link->graph_obj.mdev->graph_mutex); ret = __media_entity_setup_link(link, flags); mutex_unlock(&link->graph_obj.mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_setup_link); struct media_link * media_entity_find_link(struct media_pad *source, struct media_pad *sink) { struct media_link *link; for_each_media_entity_data_link(source->entity, link) { if (link->source->entity == source->entity && link->source->index == source->index && link->sink->entity == sink->entity && link->sink->index == sink->index) return link; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_find_link); struct media_pad *media_pad_remote_pad_first(const struct media_pad *pad) { struct media_link *link; for_each_media_entity_data_link(pad->entity, link) { if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->source == pad) return link->sink; if (link->sink == pad) return link->source; } return NULL; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_first); struct media_pad * media_entity_remote_pad_unique(const struct media_entity *entity, unsigned int type) { struct media_pad *pad = NULL; struct media_link *link; list_for_each_entry(link, &entity->links, list) { struct media_pad *local_pad; struct media_pad *remote_pad; if (((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) || !(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (type == MEDIA_PAD_FL_SOURCE) { local_pad = link->sink; remote_pad = link->source; } else { local_pad = link->source; remote_pad = link->sink; } if (local_pad->entity == entity) { if (pad) return ERR_PTR(-ENOTUNIQ); pad = remote_pad; } } if (!pad) return ERR_PTR(-ENOLINK); return pad; } EXPORT_SYMBOL_GPL(media_entity_remote_pad_unique); struct media_pad *media_pad_remote_pad_unique(const struct media_pad *pad) { struct media_pad *found_pad = NULL; struct media_link *link; list_for_each_entry(link, &pad->entity->links, list) { struct media_pad *remote_pad; if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink == pad) remote_pad = link->source; else if (link->source == pad) remote_pad = link->sink; else continue; if (found_pad) return ERR_PTR(-ENOTUNIQ); found_pad = remote_pad; } if (!found_pad) return ERR_PTR(-ENOLINK); return found_pad; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_unique); int media_entity_get_fwnode_pad(struct media_entity *entity, const struct fwnode_handle *fwnode, unsigned long direction_flags) { struct fwnode_endpoint endpoint; unsigned int i; int ret; if (!entity->ops || !entity->ops->get_fwnode_pad) { for (i = 0; i < entity->num_pads; i++) { if (entity->pads[i].flags & direction_flags) return i; } return -ENXIO; } ret = fwnode_graph_parse_endpoint(fwnode, &endpoint); if (ret) return ret; ret = entity->ops->get_fwnode_pad(entity, &endpoint); if (ret < 0) return ret; if (ret >= entity->num_pads) return -ENXIO; if (!(entity->pads[ret].flags & direction_flags)) return -ENXIO; return ret; } EXPORT_SYMBOL_GPL(media_entity_get_fwnode_pad); struct media_pipeline *media_entity_pipeline(struct media_entity *entity) { struct media_pad *pad; media_entity_for_each_pad(entity, pad) { if (pad->pipe) return pad->pipe; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_pipeline); struct media_pipeline *media_pad_pipeline(struct media_pad *pad) { return pad->pipe; } EXPORT_SYMBOL_GPL(media_pad_pipeline); static void media_interface_init(struct media_device *mdev, struct media_interface *intf, u32 gobj_type, u32 intf_type, u32 flags) { intf->type = intf_type; intf->flags = flags; INIT_LIST_HEAD(&intf->links); media_gobj_create(mdev, gobj_type, &intf->graph_obj); } /* Functions related to the media interface via device nodes */ struct media_intf_devnode *media_devnode_create(struct media_device *mdev, u32 type, u32 flags, u32 major, u32 minor) { struct media_intf_devnode *devnode; devnode = kzalloc(sizeof(*devnode), GFP_KERNEL); if (!devnode) return NULL; devnode->major = major; devnode->minor = minor; media_interface_init(mdev, &devnode->intf, MEDIA_GRAPH_INTF_DEVNODE, type, flags); return devnode; } EXPORT_SYMBOL_GPL(media_devnode_create); void media_devnode_remove(struct media_intf_devnode *devnode) { media_remove_intf_links(&devnode->intf); media_gobj_destroy(&devnode->intf.graph_obj); kfree(devnode); } EXPORT_SYMBOL_GPL(media_devnode_remove); struct media_link *media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags) { struct media_link *link; link = media_add_link(&intf->links); if (link == NULL) return NULL; link->intf = intf; link->entity = entity; link->flags = flags | MEDIA_LNK_FL_INTERFACE_LINK; /* Initialize graph object embedded at the new link */ media_gobj_create(intf->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_intf_link); void __media_remove_intf_link(struct media_link *link) { list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_link); void media_remove_intf_link(struct media_link *link) { struct media_device *mdev = link->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_link(link); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_link); void __media_remove_intf_links(struct media_interface *intf) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &intf->links, list) __media_remove_intf_link(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_links); void media_remove_intf_links(struct media_interface *intf) { struct media_device *mdev = intf->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_links(intf); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_links); struct media_link *media_create_ancillary_link(struct media_entity *primary, struct media_entity *ancillary) { struct media_link *link; link = media_add_link(&primary->links); if (!link) return ERR_PTR(-ENOMEM); link->gobj0 = &primary->graph_obj; link->gobj1 = &ancillary->graph_obj; link->flags = MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_ANCILLARY_LINK; /* Initialize graph object embedded in the new link */ media_gobj_create(primary->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_ancillary_link); struct media_link *__media_entity_next_link(struct media_entity *entity, struct media_link *link, unsigned long link_type) { link = link ? list_next_entry(link, list) : list_first_entry(&entity->links, typeof(*link), list); list_for_each_entry_from(link, &entity->links, list) if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == link_type) return link; return NULL; } EXPORT_SYMBOL_GPL(__media_entity_next_link); |
| 3 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebt_redirect * * Authors: * Bart De Schuymer <bdschuym@pandora.be> * * April, 2002 * */ #include <linux/module.h> #include <net/sock.h> #include "../br_private.h" #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_redirect.h> static unsigned int ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; if (skb_ensure_writable(skb, 0)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) /* rcu_read_lock()ed by nf_hook_thresh */ ether_addr_copy(eth_hdr(skb)->h_dest, br_port_get_rcu(xt_in(par))->br->dev->dev_addr); else ether_addr_copy(eth_hdr(skb)->h_dest, xt_in(par)->dev_addr); skb->pkt_type = PACKET_HOST; return info->target; } static int ebt_redirect_tg_check(const struct xt_tgchk_param *par) { const struct ebt_redirect_info *info = par->targinfo; unsigned int hook_mask; if (BASE_CHAIN && info->target == EBT_RETURN) return -EINVAL; hook_mask = par->hook_mask & ~(1 << NF_BR_NUMHOOKS); if ((strcmp(par->table, "nat") != 0 || hook_mask & ~(1 << NF_BR_PRE_ROUTING)) && (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) return -EINVAL; if (ebt_invalid_target(info->target)) return -EINVAL; return 0; } static struct xt_target ebt_redirect_tg_reg __read_mostly = { .name = "redirect", .revision = 0, .family = NFPROTO_BRIDGE, .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_BROUTING), .target = ebt_redirect_tg, .checkentry = ebt_redirect_tg_check, .targetsize = sizeof(struct ebt_redirect_info), .me = THIS_MODULE, }; static int __init ebt_redirect_init(void) { return xt_register_target(&ebt_redirect_tg_reg); } static void __exit ebt_redirect_fini(void) { xt_unregister_target(&ebt_redirect_tg_reg); } module_init(ebt_redirect_init); module_exit(ebt_redirect_fini); MODULE_DESCRIPTION("Ebtables: Packet redirection to localhost"); MODULE_LICENSE("GPL"); |
| 4 3 2 3 4 1 3 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hpfs/map.c * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * mapping structures to memory with some minimal checks */ #include "hpfs_fn.h" __le32 *hpfs_map_dnode_bitmap(struct super_block *s, struct quad_buffer_head *qbh) { return hpfs_map_4sectors(s, hpfs_sb(s)->sb_dmap, qbh, 0); } __le32 *hpfs_map_bitmap(struct super_block *s, unsigned bmp_block, struct quad_buffer_head *qbh, char *id) { secno sec; __le32 *ret; unsigned n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14; if (hpfs_sb(s)->sb_chk) if (bmp_block >= n_bands) { hpfs_error(s, "hpfs_map_bitmap called with bad parameter: %08x at %s", bmp_block, id); return NULL; } sec = le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[bmp_block]); if (!sec || sec > hpfs_sb(s)->sb_fs_size-4) { hpfs_error(s, "invalid bitmap block pointer %08x -> %08x at %s", bmp_block, sec, id); return NULL; } ret = hpfs_map_4sectors(s, sec, qbh, 4); if (ret) hpfs_prefetch_bitmap(s, bmp_block + 1); return ret; } void hpfs_prefetch_bitmap(struct super_block *s, unsigned bmp_block) { unsigned to_prefetch, next_prefetch; unsigned n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14; if (unlikely(bmp_block >= n_bands)) return; to_prefetch = le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[bmp_block]); if (unlikely(bmp_block + 1 >= n_bands)) next_prefetch = 0; else next_prefetch = le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[bmp_block + 1]); hpfs_prefetch_sectors(s, to_prefetch, 4 + 4 * (to_prefetch + 4 == next_prefetch)); } /* * Load first code page into kernel memory, return pointer to 256-byte array, * first 128 bytes are uppercasing table for chars 128-255, next 128 bytes are * lowercasing table */ unsigned char *hpfs_load_code_page(struct super_block *s, secno cps) { struct buffer_head *bh; secno cpds; unsigned cpi; unsigned char *ptr; unsigned char *cp_table; int i; struct code_page_data *cpd; struct code_page_directory *cp = hpfs_map_sector(s, cps, &bh, 0); if (!cp) return NULL; if (le32_to_cpu(cp->magic) != CP_DIR_MAGIC) { pr_err("Code page directory magic doesn't match (magic = %08x)\n", le32_to_cpu(cp->magic)); brelse(bh); return NULL; } if (!le32_to_cpu(cp->n_code_pages)) { pr_err("n_code_pages == 0\n"); brelse(bh); return NULL; } cpds = le32_to_cpu(cp->array[0].code_page_data); cpi = le16_to_cpu(cp->array[0].index); brelse(bh); if (cpi >= 3) { pr_err("Code page index out of array\n"); return NULL; } if (!(cpd = hpfs_map_sector(s, cpds, &bh, 0))) return NULL; if (le16_to_cpu(cpd->offs[cpi]) > 0x178) { pr_err("Code page index out of sector\n"); brelse(bh); return NULL; } ptr = (unsigned char *)cpd + le16_to_cpu(cpd->offs[cpi]) + 6; if (!(cp_table = kmalloc(256, GFP_KERNEL))) { pr_err("out of memory for code page table\n"); brelse(bh); return NULL; } memcpy(cp_table, ptr, 128); brelse(bh); /* Try to build lowercasing table from uppercasing one */ for (i=128; i<256; i++) cp_table[i]=i; for (i=128; i<256; i++) if (cp_table[i-128]!=i && cp_table[i-128]>=128) cp_table[cp_table[i-128]] = i; return cp_table; } __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) { struct buffer_head *bh; int n = (hpfs_sb(s)->sb_fs_size + 0x200000 - 1) >> 21; int i; __le32 *b; if (!(b = kmalloc_array(n, 512, GFP_KERNEL))) { pr_err("can't allocate memory for bitmap directory\n"); return NULL; } for (i=0;i<n;i++) { __le32 *d = hpfs_map_sector(s, bmp+i, &bh, n - i - 1); if (!d) { kfree(b); return NULL; } memcpy((char *)b + 512 * i, d, 512); brelse(bh); } return b; } void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock) { struct quad_buffer_head qbh; __le32 *directory; u32 n_hotfixes, n_used_hotfixes; unsigned i; n_hotfixes = le32_to_cpu(spareblock->n_spares); n_used_hotfixes = le32_to_cpu(spareblock->n_spares_used); if (n_hotfixes > 256 || n_used_hotfixes > n_hotfixes) { hpfs_error(s, "invalid number of hotfixes: %u, used: %u", n_hotfixes, n_used_hotfixes); return; } if (!(directory = hpfs_map_4sectors(s, le32_to_cpu(spareblock->hotfix_map), &qbh, 0))) { hpfs_error(s, "can't load hotfix map"); return; } for (i = 0; i < n_used_hotfixes; i++) { hpfs_sb(s)->hotfix_from[i] = le32_to_cpu(directory[i]); hpfs_sb(s)->hotfix_to[i] = le32_to_cpu(directory[n_hotfixes + i]); } hpfs_sb(s)->n_hotfixes = n_used_hotfixes; hpfs_brelse4(&qbh); } /* * Load fnode to memory */ struct fnode *hpfs_map_fnode(struct super_block *s, ino_t ino, struct buffer_head **bhp) { struct fnode *fnode; if (hpfs_sb(s)->sb_chk) if (hpfs_chk_sectors(s, ino, 1, "fnode")) { return NULL; } if ((fnode = hpfs_map_sector(s, ino, bhp, FNODE_RD_AHEAD))) { if (hpfs_sb(s)->sb_chk) { struct extended_attribute *ea; struct extended_attribute *ea_end; if (le32_to_cpu(fnode->magic) != FNODE_MAGIC) { hpfs_error(s, "bad magic on fnode %08lx", (unsigned long)ino); goto bail; } if (!fnode_is_dir(fnode)) { if ((unsigned)fnode->btree.n_used_nodes + (unsigned)fnode->btree.n_free_nodes != (bp_internal(&fnode->btree) ? 12 : 8)) { hpfs_error(s, "bad number of nodes in fnode %08lx", (unsigned long)ino); goto bail; } if (le16_to_cpu(fnode->btree.first_free) != 8 + fnode->btree.n_used_nodes * (bp_internal(&fnode->btree) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in fnode %08lx", (unsigned long)ino); goto bail; } } if (le16_to_cpu(fnode->ea_size_s) && (le16_to_cpu(fnode->ea_offs) < 0xc4 || le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s) + le16_to_cpu(fnode->ea_size_s) > 0x200)) { hpfs_error(s, "bad EA info in fnode %08lx: ea_offs == %04x ea_size_s == %04x", (unsigned long)ino, le16_to_cpu(fnode->ea_offs), le16_to_cpu(fnode->ea_size_s)); goto bail; } ea = fnode_ea(fnode); ea_end = fnode_end_ea(fnode); while (ea != ea_end) { if (ea > ea_end) { hpfs_error(s, "bad EA in fnode %08lx", (unsigned long)ino); goto bail; } ea = next_ea(ea); } } } return fnode; bail: brelse(*bhp); return NULL; } struct anode *hpfs_map_anode(struct super_block *s, anode_secno ano, struct buffer_head **bhp) { struct anode *anode; if (hpfs_sb(s)->sb_chk) if (hpfs_chk_sectors(s, ano, 1, "anode")) return NULL; if ((anode = hpfs_map_sector(s, ano, bhp, ANODE_RD_AHEAD))) if (hpfs_sb(s)->sb_chk) { if (le32_to_cpu(anode->magic) != ANODE_MAGIC) { hpfs_error(s, "bad magic on anode %08x", ano); goto bail; } if (le32_to_cpu(anode->self) != ano) { hpfs_error(s, "self pointer invalid on anode %08x", ano); goto bail; } if ((unsigned)anode->btree.n_used_nodes + (unsigned)anode->btree.n_free_nodes != (bp_internal(&anode->btree) ? 60 : 40)) { hpfs_error(s, "bad number of nodes in anode %08x", ano); goto bail; } if (le16_to_cpu(anode->btree.first_free) != 8 + anode->btree.n_used_nodes * (bp_internal(&anode->btree) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in anode %08x", ano); goto bail; } } return anode; bail: brelse(*bhp); return NULL; } /* * Load dnode to memory and do some checks */ struct dnode *hpfs_map_dnode(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh) { struct dnode *dnode; if (hpfs_sb(s)->sb_chk) { if (hpfs_chk_sectors(s, secno, 4, "dnode")) return NULL; if (secno & 3) { hpfs_error(s, "dnode %08x not byte-aligned", secno); return NULL; } } if ((dnode = hpfs_map_4sectors(s, secno, qbh, DNODE_RD_AHEAD))) if (hpfs_sb(s)->sb_chk) { unsigned p, pp = 0; unsigned char *d = (unsigned char *)dnode; int b = 0; if (le32_to_cpu(dnode->magic) != DNODE_MAGIC) { hpfs_error(s, "bad magic on dnode %08x", secno); goto bail; } if (le32_to_cpu(dnode->self) != secno) hpfs_error(s, "bad self pointer on dnode %08x self = %08x", secno, le32_to_cpu(dnode->self)); /* Check dirents - bad dirents would cause infinite loops or shooting to memory */ if (le32_to_cpu(dnode->first_free) > 2048) { hpfs_error(s, "dnode %08x has first_free == %08x", secno, le32_to_cpu(dnode->first_free)); goto bail; } for (p = 20; p < le32_to_cpu(dnode->first_free); p += d[p] + (d[p+1] << 8)) { struct hpfs_dirent *de = (struct hpfs_dirent *)((char *)dnode + p); if (le16_to_cpu(de->length) > 292 || (le16_to_cpu(de->length) < 32) || (le16_to_cpu(de->length) & 3) || p + le16_to_cpu(de->length) > 2048) { hpfs_error(s, "bad dirent size in dnode %08x, dirent %03x, last %03x", secno, p, pp); goto bail; } if (((31 + de->namelen + de->down*4 + 3) & ~3) != le16_to_cpu(de->length)) { if (((31 + de->namelen + de->down*4 + 3) & ~3) < le16_to_cpu(de->length) && s->s_flags & SB_RDONLY) goto ok; hpfs_error(s, "namelen does not match dirent size in dnode %08x, dirent %03x, last %03x", secno, p, pp); goto bail; } ok: if (hpfs_sb(s)->sb_chk >= 2) b |= 1 << de->down; if (de->down) if (de_down_pointer(de) < 0x10) { hpfs_error(s, "bad down pointer in dnode %08x, dirent %03x, last %03x", secno, p, pp); goto bail; } pp = p; } if (p != le32_to_cpu(dnode->first_free)) { hpfs_error(s, "size on last dirent does not match first_free; dnode %08x", secno); goto bail; } if (d[pp + 30] != 1 || d[pp + 31] != 255) { hpfs_error(s, "dnode %08x does not end with \\377 entry", secno); goto bail; } if (b == 3) pr_err("unbalanced dnode tree, dnode %08x; see hpfs.txt 4 more info\n", secno); } return dnode; bail: hpfs_brelse4(qbh); return NULL; } dnode_secno hpfs_fnode_dno(struct super_block *s, ino_t ino) { struct buffer_head *bh; struct fnode *fnode; dnode_secno dno; fnode = hpfs_map_fnode(s, ino, &bh); if (!fnode) return 0; dno = le32_to_cpu(fnode->u.external[0].disk_secno); brelse(bh); return dno; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2018 Intel Corporation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ib_mad #if !defined(_TRACE_IB_MAD_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IB_MAD_H #include <linux/tracepoint.h> #include <rdma/ib_mad.h> #ifdef CONFIG_TRACEPOINTS struct trace_event_raw_ib_mad_send_template; static void create_mad_addr_info(struct ib_mad_send_wr_private *mad_send_wr, struct ib_mad_qp_info *qp_info, struct trace_event_raw_ib_mad_send_template *entry); #endif DECLARE_EVENT_CLASS(ib_mad_send_template, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info), TP_STRUCT__entry( __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u8, port_num) __field(u32, qp_num) __field(u8, method) __field(u8, sl) __field(u16, attr_id) __field(u32, attr_mod) __field(u64, wrtid) __field(u64, tid) __field(u16, status) __field(u16, class_specific) __field(u32, length) __field(u32, dlid) __field(u32, rqpn) __field(u32, rqkey) __field(u32, dev_index) __field(void *, agent_priv) __field(unsigned long, timeout) __field(int, retries_left) __field(int, max_retries) __field(int, retry) ), TP_fast_assign( __entry->dev_index = wr->mad_agent_priv->agent.device->index; __entry->port_num = wr->mad_agent_priv->agent.port_num; __entry->qp_num = wr->mad_agent_priv->qp_info->qp->qp_num; __entry->agent_priv = wr->mad_agent_priv; __entry->wrtid = wr->tid; __entry->max_retries = wr->max_retries; __entry->retries_left = wr->retries_left; __entry->retry = wr->retry; __entry->timeout = wr->timeout; __entry->length = wr->send_buf.hdr_len + wr->send_buf.data_len; __entry->base_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->base_version; __entry->mgmt_class = ((struct ib_mad_hdr *)wr->send_buf.mad)->mgmt_class; __entry->class_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_version; __entry->method = ((struct ib_mad_hdr *)wr->send_buf.mad)->method; __entry->status = ((struct ib_mad_hdr *)wr->send_buf.mad)->status; __entry->class_specific = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_specific; __entry->tid = ((struct ib_mad_hdr *)wr->send_buf.mad)->tid; __entry->attr_id = ((struct ib_mad_hdr *)wr->send_buf.mad)->attr_id; __entry->attr_mod = ((struct ib_mad_hdr *)wr->send_buf.mad)->attr_mod; create_mad_addr_info(wr, qp_info, __entry); ), TP_printk("%d:%d QP%d agent %p: " \ "wrtid 0x%llx; %d/%d retries(%d); timeout %lu length %d : " \ "hdr : base_ver 0x%x class 0x%x class_ver 0x%x " \ "method 0x%x status 0x%x class_specific 0x%x tid 0x%llx " \ "attr_id 0x%x attr_mod 0x%x => dlid 0x%08x sl %d "\ "rpqn 0x%x rqpkey 0x%x", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->agent_priv, be64_to_cpu(__entry->wrtid), __entry->retries_left, __entry->max_retries, __entry->retry, __entry->timeout, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status), be16_to_cpu(__entry->class_specific), be64_to_cpu(__entry->tid), be16_to_cpu(__entry->attr_id), be32_to_cpu(__entry->attr_mod), be32_to_cpu(__entry->dlid), __entry->sl, __entry->rqpn, __entry->rqkey ) ); DEFINE_EVENT(ib_mad_send_template, ib_mad_error_handler, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); DEFINE_EVENT(ib_mad_send_template, ib_mad_ib_send_mad, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); DEFINE_EVENT(ib_mad_send_template, ib_mad_send_done_resend, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); TRACE_EVENT(ib_mad_send_done_handler, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_wc *wc), TP_ARGS(wr, wc), TP_STRUCT__entry( __field(u8, port_num) __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u32, qp_num) __field(u64, wrtid) __field(u16, status) __field(u16, wc_status) __field(u32, length) __field(void *, agent_priv) __field(unsigned long, timeout) __field(u32, dev_index) __field(int, retries_left) __field(int, max_retries) __field(int, retry) __field(u8, method) ), TP_fast_assign( __entry->dev_index = wr->mad_agent_priv->agent.device->index; __entry->port_num = wr->mad_agent_priv->agent.port_num; __entry->qp_num = wr->mad_agent_priv->qp_info->qp->qp_num; __entry->agent_priv = wr->mad_agent_priv; __entry->wrtid = wr->tid; __entry->max_retries = wr->max_retries; __entry->retries_left = wr->retries_left; __entry->retry = wr->retry; __entry->timeout = wr->timeout; __entry->base_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->base_version; __entry->mgmt_class = ((struct ib_mad_hdr *)wr->send_buf.mad)->mgmt_class; __entry->class_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_version; __entry->method = ((struct ib_mad_hdr *)wr->send_buf.mad)->method; __entry->status = ((struct ib_mad_hdr *)wr->send_buf.mad)->status; __entry->wc_status = wc->status; __entry->length = wc->byte_len; ), TP_printk("%d:%d QP%d : SEND WC Status %d : agent %p: " \ "wrtid 0x%llx %d/%d retries(%d) timeout %lu length %d: " \ "hdr : base_ver 0x%x class 0x%x class_ver 0x%x " \ "method 0x%x status 0x%x", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->wc_status, __entry->agent_priv, be64_to_cpu(__entry->wrtid), __entry->retries_left, __entry->max_retries, __entry->retry, __entry->timeout, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status) ) ); TRACE_EVENT(ib_mad_recv_done_handler, TP_PROTO(struct ib_mad_qp_info *qp_info, struct ib_wc *wc, struct ib_mad_hdr *mad_hdr), TP_ARGS(qp_info, wc, mad_hdr), TP_STRUCT__entry( __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u8, port_num) __field(u32, qp_num) __field(u16, status) __field(u16, class_specific) __field(u32, length) __field(u64, tid) __field(u8, method) __field(u8, sl) __field(u16, attr_id) __field(u32, attr_mod) __field(u16, src_qp) __field(u16, wc_status) __field(u32, slid) __field(u32, dev_index) ), TP_fast_assign( __entry->dev_index = qp_info->port_priv->device->index; __entry->port_num = qp_info->port_priv->port_num; __entry->qp_num = qp_info->qp->qp_num; __entry->length = wc->byte_len; __entry->base_version = mad_hdr->base_version; __entry->mgmt_class = mad_hdr->mgmt_class; __entry->class_version = mad_hdr->class_version; __entry->method = mad_hdr->method; __entry->status = mad_hdr->status; __entry->class_specific = mad_hdr->class_specific; __entry->tid = mad_hdr->tid; __entry->attr_id = mad_hdr->attr_id; __entry->attr_mod = mad_hdr->attr_mod; __entry->slid = wc->slid; __entry->src_qp = wc->src_qp; __entry->sl = wc->sl; __entry->wc_status = wc->status; ), TP_printk("%d:%d QP%d : RECV WC Status %d : length %d : hdr : " \ "base_ver 0x%02x class 0x%02x class_ver 0x%02x " \ "method 0x%02x status 0x%04x class_specific 0x%04x " \ "tid 0x%016llx attr_id 0x%04x attr_mod 0x%08x " \ "slid 0x%08x src QP%d, sl %d", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->wc_status, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status), be16_to_cpu(__entry->class_specific), be64_to_cpu(__entry->tid), be16_to_cpu(__entry->attr_id), be32_to_cpu(__entry->attr_mod), __entry->slid, __entry->src_qp, __entry->sl ) ); DECLARE_EVENT_CLASS(ib_mad_agent_template, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent), TP_STRUCT__entry( __field(u32, dev_index) __field(u32, hi_tid) __field(u8, port_num) __field(u8, mgmt_class) __field(u8, mgmt_class_version) ), TP_fast_assign( __entry->dev_index = agent->agent.device->index; __entry->port_num = agent->agent.port_num; __entry->hi_tid = agent->agent.hi_tid; if (agent->reg_req) { __entry->mgmt_class = agent->reg_req->mgmt_class; __entry->mgmt_class_version = agent->reg_req->mgmt_class_version; } else { __entry->mgmt_class = 0; __entry->mgmt_class_version = 0; } ), TP_printk("%d:%d mad agent : hi_tid 0x%08x class 0x%02x class_ver 0x%02x", __entry->dev_index, __entry->port_num, __entry->hi_tid, __entry->mgmt_class, __entry->mgmt_class_version ) ); DEFINE_EVENT(ib_mad_agent_template, ib_mad_recv_done_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_send_done_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_create_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_unregister_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DECLARE_EVENT_CLASS(ib_mad_opa_smi_template, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp), TP_STRUCT__entry( __field(u64, mkey) __field(u32, dr_slid) __field(u32, dr_dlid) __field(u8, hop_ptr) __field(u8, hop_cnt) __array(u8, initial_path, OPA_SMP_MAX_PATH_HOPS) __array(u8, return_path, OPA_SMP_MAX_PATH_HOPS) ), TP_fast_assign( __entry->hop_ptr = smp->hop_ptr; __entry->hop_cnt = smp->hop_cnt; __entry->mkey = smp->mkey; __entry->dr_slid = smp->route.dr.dr_slid; __entry->dr_dlid = smp->route.dr.dr_dlid; memcpy(__entry->initial_path, smp->route.dr.initial_path, OPA_SMP_MAX_PATH_HOPS); memcpy(__entry->return_path, smp->route.dr.return_path, OPA_SMP_MAX_PATH_HOPS); ), TP_printk("OPA SMP: hop_ptr %d hop_cnt %d " \ "mkey 0x%016llx dr_slid 0x%08x dr_dlid 0x%08x " \ "initial_path %*ph return_path %*ph ", __entry->hop_ptr, __entry->hop_cnt, be64_to_cpu(__entry->mkey), be32_to_cpu(__entry->dr_slid), be32_to_cpu(__entry->dr_dlid), OPA_SMP_MAX_PATH_HOPS, __entry->initial_path, OPA_SMP_MAX_PATH_HOPS, __entry->return_path ) ); DEFINE_EVENT(ib_mad_opa_smi_template, ib_mad_handle_opa_smi, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp)); DEFINE_EVENT(ib_mad_opa_smi_template, ib_mad_handle_out_opa_smi, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp)); DECLARE_EVENT_CLASS(ib_mad_opa_ib_template, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp), TP_STRUCT__entry( __field(u64, mkey) __field(u32, dr_slid) __field(u32, dr_dlid) __field(u8, hop_ptr) __field(u8, hop_cnt) __array(u8, initial_path, IB_SMP_MAX_PATH_HOPS) __array(u8, return_path, IB_SMP_MAX_PATH_HOPS) ), TP_fast_assign( __entry->hop_ptr = smp->hop_ptr; __entry->hop_cnt = smp->hop_cnt; __entry->mkey = smp->mkey; __entry->dr_slid = smp->dr_slid; __entry->dr_dlid = smp->dr_dlid; memcpy(__entry->initial_path, smp->initial_path, IB_SMP_MAX_PATH_HOPS); memcpy(__entry->return_path, smp->return_path, IB_SMP_MAX_PATH_HOPS); ), TP_printk("OPA SMP: hop_ptr %d hop_cnt %d " \ "mkey 0x%016llx dr_slid 0x%04x dr_dlid 0x%04x " \ "initial_path %*ph return_path %*ph ", __entry->hop_ptr, __entry->hop_cnt, be64_to_cpu(__entry->mkey), be16_to_cpu(__entry->dr_slid), be16_to_cpu(__entry->dr_dlid), IB_SMP_MAX_PATH_HOPS, __entry->initial_path, IB_SMP_MAX_PATH_HOPS, __entry->return_path ) ); DEFINE_EVENT(ib_mad_opa_ib_template, ib_mad_handle_ib_smi, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp)); DEFINE_EVENT(ib_mad_opa_ib_template, ib_mad_handle_out_ib_smi, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp)); #endif /* _TRACE_IB_MAD_H */ #include <trace/define_trace.h> |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Infinity Unlimited USB Phoenix driver * * Copyright (C) 2010 James Courtier-Dutton (James@superbug.co.uk) * Copyright (C) 2007 Alain Degreffe (eczema@ecze.com) * * Original code taken from iuutool (Copyright (C) 2006 Juan Carlos Borrás) * * And tested with help of WB Electronics */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include "iuu_phoenix.h" #include <linux/random.h> #define DRIVER_DESC "Infinity USB Unlimited Phoenix driver" static const struct usb_device_id id_table[] = { {USB_DEVICE(IUU_USB_VENDOR_ID, IUU_USB_PRODUCT_ID)}, {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); /* turbo parameter */ static int boost = 100; static int clockmode = 1; static int cdmode = 1; static int iuu_cardin; static int iuu_cardout; static bool xmas; static int vcc_default = 5; static int iuu_create_sysfs_attrs(struct usb_serial_port *port); static int iuu_remove_sysfs_attrs(struct usb_serial_port *port); static void read_rxcmd_callback(struct urb *urb); struct iuu_private { spinlock_t lock; /* store irq state */ u8 line_status; int tiostatus; /* store IUART SIGNAL for tiocmget call */ u8 reset; /* if 1 reset is needed */ int poll; /* number of poll */ u8 *writebuf; /* buffer for writing to device */ int writelen; /* num of byte to write to device */ u8 *buf; /* used for initialize speed */ u8 len; int vcc; /* vcc (either 3 or 5 V) */ u32 boost; u32 clk; }; static int iuu_port_probe(struct usb_serial_port *port) { struct iuu_private *priv; int ret; priv = kzalloc(sizeof(struct iuu_private), GFP_KERNEL); if (!priv) return -ENOMEM; priv->buf = kzalloc(256, GFP_KERNEL); if (!priv->buf) { kfree(priv); return -ENOMEM; } priv->writebuf = kzalloc(256, GFP_KERNEL); if (!priv->writebuf) { kfree(priv->buf); kfree(priv); return -ENOMEM; } priv->vcc = vcc_default; spin_lock_init(&priv->lock); usb_set_serial_port_data(port, priv); ret = iuu_create_sysfs_attrs(port); if (ret) { kfree(priv->writebuf); kfree(priv->buf); kfree(priv); return ret; } return 0; } static void iuu_port_remove(struct usb_serial_port *port) { struct iuu_private *priv = usb_get_serial_port_data(port); iuu_remove_sysfs_attrs(port); kfree(priv->writebuf); kfree(priv->buf); kfree(priv); } static int iuu_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct usb_serial_port *port = tty->driver_data; struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; /* FIXME: locking on tiomstatus */ dev_dbg(&port->dev, "%s msg : SET = 0x%04x, CLEAR = 0x%04x\n", __func__, set, clear); spin_lock_irqsave(&priv->lock, flags); if ((set & TIOCM_RTS) && !(priv->tiostatus == TIOCM_RTS)) { dev_dbg(&port->dev, "%s TIOCMSET RESET called !!!\n", __func__); priv->reset = 1; } if (set & TIOCM_RTS) priv->tiostatus = TIOCM_RTS; spin_unlock_irqrestore(&priv->lock, flags); return 0; } /* This is used to provide a carrier detect mechanism * When a card is present, the response is 0x00 * When no card , the reader respond with TIOCM_CD * This is known as CD autodetect mechanism */ static int iuu_tiocmget(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; int rc; spin_lock_irqsave(&priv->lock, flags); rc = priv->tiostatus; spin_unlock_irqrestore(&priv->lock, flags); return rc; } static void iuu_rxcmd(struct urb *urb) { struct usb_serial_port *port = urb->context; int status = urb->status; if (status) { dev_dbg(&port->dev, "%s - status = %d\n", __func__, status); /* error stop all */ return; } memset(port->write_urb->transfer_buffer, IUU_UART_RX, 1); usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 1, read_rxcmd_callback, port); usb_submit_urb(port->write_urb, GFP_ATOMIC); } static int iuu_reset(struct usb_serial_port *port, u8 wt) { struct iuu_private *priv = usb_get_serial_port_data(port); int result; char *buf_ptr = port->write_urb->transfer_buffer; /* Prepare the reset sequence */ *buf_ptr++ = IUU_RST_SET; *buf_ptr++ = IUU_DELAY_MS; *buf_ptr++ = wt; *buf_ptr = IUU_RST_CLEAR; /* send the sequence */ usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 4, iuu_rxcmd, port); result = usb_submit_urb(port->write_urb, GFP_ATOMIC); priv->reset = 0; return result; } /* Status Function * Return value is * 0x00 = no card * 0x01 = smartcard * 0x02 = sim card */ static void iuu_update_status_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct iuu_private *priv = usb_get_serial_port_data(port); u8 *st; int status = urb->status; if (status) { dev_dbg(&port->dev, "%s - status = %d\n", __func__, status); /* error stop all */ return; } st = urb->transfer_buffer; dev_dbg(&port->dev, "%s - enter\n", __func__); if (urb->actual_length == 1) { switch (st[0]) { case 0x1: priv->tiostatus = iuu_cardout; break; case 0x0: priv->tiostatus = iuu_cardin; break; default: priv->tiostatus = iuu_cardin; } } iuu_rxcmd(urb); } static void iuu_status_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; int status = urb->status; dev_dbg(&port->dev, "%s - status = %d\n", __func__, status); usb_fill_bulk_urb(port->read_urb, port->serial->dev, usb_rcvbulkpipe(port->serial->dev, port->bulk_in_endpointAddress), port->read_urb->transfer_buffer, 256, iuu_update_status_callback, port); usb_submit_urb(port->read_urb, GFP_ATOMIC); } static int iuu_status(struct usb_serial_port *port) { int result; memset(port->write_urb->transfer_buffer, IUU_GET_STATE_REGISTER, 1); usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 1, iuu_status_callback, port); result = usb_submit_urb(port->write_urb, GFP_ATOMIC); return result; } static int bulk_immediate(struct usb_serial_port *port, u8 *buf, u8 count) { int status; struct usb_serial *serial = port->serial; int actual = 0; /* send the data out the bulk port */ status = usb_bulk_msg(serial->dev, usb_sndbulkpipe(serial->dev, port->bulk_out_endpointAddress), buf, count, &actual, 1000); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - error = %2x\n", __func__, status); else dev_dbg(&port->dev, "%s - write OK !\n", __func__); return status; } static int read_immediate(struct usb_serial_port *port, u8 *buf, u8 count) { int status; struct usb_serial *serial = port->serial; int actual = 0; /* send the data out the bulk port */ status = usb_bulk_msg(serial->dev, usb_rcvbulkpipe(serial->dev, port->bulk_in_endpointAddress), buf, count, &actual, 1000); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - error = %2x\n", __func__, status); else dev_dbg(&port->dev, "%s - read OK !\n", __func__); return status; } static int iuu_led(struct usb_serial_port *port, unsigned int R, unsigned int G, unsigned int B, u8 f) { int status; u8 *buf; buf = kmalloc(8, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = IUU_SET_LED; buf[1] = R & 0xFF; buf[2] = (R >> 8) & 0xFF; buf[3] = G & 0xFF; buf[4] = (G >> 8) & 0xFF; buf[5] = B & 0xFF; buf[6] = (B >> 8) & 0xFF; buf[7] = f; status = bulk_immediate(port, buf, 8); kfree(buf); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - led error status = %2x\n", __func__, status); else dev_dbg(&port->dev, "%s - led OK !\n", __func__); return IUU_OPERATION_OK; } static void iuu_rgbf_fill_buffer(u8 *buf, u8 r1, u8 r2, u8 g1, u8 g2, u8 b1, u8 b2, u8 freq) { *buf++ = IUU_SET_LED; *buf++ = r1; *buf++ = r2; *buf++ = g1; *buf++ = g2; *buf++ = b1; *buf++ = b2; *buf = freq; } static void iuu_led_activity_on(struct urb *urb) { struct usb_serial_port *port = urb->context; char *buf_ptr = port->write_urb->transfer_buffer; if (xmas) { buf_ptr[0] = IUU_SET_LED; get_random_bytes(buf_ptr + 1, 6); buf_ptr[7] = 1; } else { iuu_rgbf_fill_buffer(buf_ptr, 255, 255, 0, 0, 0, 0, 255); } usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 8 , iuu_rxcmd, port); usb_submit_urb(port->write_urb, GFP_ATOMIC); } static void iuu_led_activity_off(struct urb *urb) { struct usb_serial_port *port = urb->context; char *buf_ptr = port->write_urb->transfer_buffer; if (xmas) { iuu_rxcmd(urb); return; } iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255); usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 8 , iuu_rxcmd, port); usb_submit_urb(port->write_urb, GFP_ATOMIC); } static int iuu_clk(struct usb_serial_port *port, int dwFrq) { int status; struct iuu_private *priv = usb_get_serial_port_data(port); int Count = 0; u8 FrqGenAdr = 0x69; u8 DIV = 0; /* 8bit */ u8 XDRV = 0; /* 8bit */ u8 PUMP = 0; /* 3bit */ u8 PBmsb = 0; /* 2bit */ u8 PBlsb = 0; /* 8bit */ u8 PO = 0; /* 1bit */ u8 Q = 0; /* 7bit */ /* 24bit = 3bytes */ unsigned int P = 0; unsigned int P2 = 0; int frq = (int)dwFrq; if (frq == 0) { priv->buf[Count++] = IUU_UART_WRITE_I2C; priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x09; priv->buf[Count++] = 0x00; status = bulk_immediate(port, (u8 *) priv->buf, Count); if (status != 0) { dev_dbg(&port->dev, "%s - write error\n", __func__); return status; } } else if (frq == 3579000) { DIV = 100; P = 1193; Q = 40; XDRV = 0; } else if (frq == 3680000) { DIV = 105; P = 161; Q = 5; XDRV = 0; } else if (frq == 6000000) { DIV = 66; P = 66; Q = 2; XDRV = 0x28; } else { unsigned int result = 0; unsigned int tmp = 0; unsigned int check; unsigned int check2; char found = 0x00; unsigned int lQ = 2; unsigned int lP = 2055; unsigned int lDiv = 4; for (lQ = 2; lQ <= 47 && !found; lQ++) for (lP = 2055; lP >= 8 && !found; lP--) for (lDiv = 4; lDiv <= 127 && !found; lDiv++) { tmp = (12000000 / lDiv) * (lP / lQ); if (abs((int)(tmp - frq)) < abs((int)(frq - result))) { check2 = (12000000 / lQ); if (check2 < 250000) continue; check = (12000000 / lQ) * lP; if (check > 400000000) continue; if (check < 100000000) continue; if (lDiv < 4 || lDiv > 127) continue; result = tmp; P = lP; DIV = lDiv; Q = lQ; if (result == frq) found = 0x01; } } } P2 = ((P - PO) / 2) - 4; PUMP = 0x04; PBmsb = (P2 >> 8 & 0x03); PBlsb = P2 & 0xFF; PO = (P >> 10) & 0x01; Q = Q - 2; priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x09; priv->buf[Count++] = 0x20; /* Adr = 0x09 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x0C; priv->buf[Count++] = DIV; /* Adr = 0x0C */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x12; priv->buf[Count++] = XDRV; /* Adr = 0x12 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x13; priv->buf[Count++] = 0x6B; /* Adr = 0x13 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x40; priv->buf[Count++] = (0xC0 | ((PUMP & 0x07) << 2)) | (PBmsb & 0x03); /* Adr = 0x40 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x41; priv->buf[Count++] = PBlsb; /* Adr = 0x41 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x42; priv->buf[Count++] = Q | (((PO & 0x01) << 7)); /* Adr = 0x42 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x44; priv->buf[Count++] = (char)0xFF; /* Adr = 0x44 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x45; priv->buf[Count++] = (char)0xFE; /* Adr = 0x45 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x46; priv->buf[Count++] = 0x7F; /* Adr = 0x46 */ priv->buf[Count++] = IUU_UART_WRITE_I2C; /* 0x4C */ priv->buf[Count++] = FrqGenAdr << 1; priv->buf[Count++] = 0x47; priv->buf[Count++] = (char)0x84; /* Adr = 0x47 */ status = bulk_immediate(port, (u8 *) priv->buf, Count); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - write error\n", __func__); return status; } static int iuu_uart_flush(struct usb_serial_port *port) { struct device *dev = &port->dev; int i; int status; u8 *rxcmd; struct iuu_private *priv = usb_get_serial_port_data(port); if (iuu_led(port, 0xF000, 0, 0, 0xFF) < 0) return -EIO; rxcmd = kmalloc(1, GFP_KERNEL); if (!rxcmd) return -ENOMEM; rxcmd[0] = IUU_UART_RX; for (i = 0; i < 2; i++) { status = bulk_immediate(port, rxcmd, 1); if (status != IUU_OPERATION_OK) { dev_dbg(dev, "%s - uart_flush_write error\n", __func__); goto out_free; } status = read_immediate(port, &priv->len, 1); if (status != IUU_OPERATION_OK) { dev_dbg(dev, "%s - uart_flush_read error\n", __func__); goto out_free; } if (priv->len > 0) { dev_dbg(dev, "%s - uart_flush datalen is : %i\n", __func__, priv->len); status = read_immediate(port, priv->buf, priv->len); if (status != IUU_OPERATION_OK) { dev_dbg(dev, "%s - uart_flush_read error\n", __func__); goto out_free; } } } dev_dbg(dev, "%s - uart_flush_read OK!\n", __func__); iuu_led(port, 0, 0xF000, 0, 0xFF); out_free: kfree(rxcmd); return status; } static void read_buf_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; unsigned char *data = urb->transfer_buffer; int status = urb->status; if (status) { if (status == -EPROTO) { /* reschedule needed */ } return; } dev_dbg(&port->dev, "%s - %i chars to write\n", __func__, urb->actual_length); if (urb->actual_length) { tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); } iuu_led_activity_on(urb); } static int iuu_bulk_write(struct usb_serial_port *port) { struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; int result; int buf_len; char *buf_ptr = port->write_urb->transfer_buffer; spin_lock_irqsave(&priv->lock, flags); *buf_ptr++ = IUU_UART_ESC; *buf_ptr++ = IUU_UART_TX; *buf_ptr++ = priv->writelen; memcpy(buf_ptr, priv->writebuf, priv->writelen); buf_len = priv->writelen; priv->writelen = 0; spin_unlock_irqrestore(&priv->lock, flags); dev_dbg(&port->dev, "%s - writing %i chars : %*ph\n", __func__, buf_len, buf_len, buf_ptr); usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, buf_len + 3, iuu_rxcmd, port); result = usb_submit_urb(port->write_urb, GFP_ATOMIC); usb_serial_port_softint(port); return result; } static int iuu_read_buf(struct usb_serial_port *port, int len) { int result; usb_fill_bulk_urb(port->read_urb, port->serial->dev, usb_rcvbulkpipe(port->serial->dev, port->bulk_in_endpointAddress), port->read_urb->transfer_buffer, len, read_buf_callback, port); result = usb_submit_urb(port->read_urb, GFP_ATOMIC); return result; } static void iuu_uart_read_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; int status = urb->status; int len = 0; unsigned char *data = urb->transfer_buffer; priv->poll++; if (status) { dev_dbg(&port->dev, "%s - status = %d\n", __func__, status); /* error stop all */ return; } if (urb->actual_length == 1) len = (int) data[0]; if (urb->actual_length > 1) { dev_dbg(&port->dev, "%s - urb->actual_length = %i\n", __func__, urb->actual_length); return; } /* if len > 0 call readbuf */ if (len > 0) { dev_dbg(&port->dev, "%s - call read buf - len to read is %i\n", __func__, len); status = iuu_read_buf(port, len); return; } /* need to update status ? */ if (priv->poll > 99) { status = iuu_status(port); priv->poll = 0; return; } /* reset waiting ? */ if (priv->reset == 1) { status = iuu_reset(port, 0xC); return; } /* Writebuf is waiting */ spin_lock_irqsave(&priv->lock, flags); if (priv->writelen > 0) { spin_unlock_irqrestore(&priv->lock, flags); status = iuu_bulk_write(port); return; } spin_unlock_irqrestore(&priv->lock, flags); /* if nothing to write call again rxcmd */ dev_dbg(&port->dev, "%s - rxcmd recall\n", __func__); iuu_led_activity_off(urb); } static int iuu_uart_write(struct tty_struct *tty, struct usb_serial_port *port, const u8 *buf, int count) { struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; spin_lock_irqsave(&priv->lock, flags); count = min(count, 256 - priv->writelen); if (count == 0) goto out; /* fill the buffer */ memcpy(priv->writebuf + priv->writelen, buf, count); priv->writelen += count; out: spin_unlock_irqrestore(&priv->lock, flags); return count; } static void read_rxcmd_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; int result; int status = urb->status; if (status) { /* error stop all */ return; } usb_fill_bulk_urb(port->read_urb, port->serial->dev, usb_rcvbulkpipe(port->serial->dev, port->bulk_in_endpointAddress), port->read_urb->transfer_buffer, 256, iuu_uart_read_callback, port); result = usb_submit_urb(port->read_urb, GFP_ATOMIC); dev_dbg(&port->dev, "%s - submit result = %d\n", __func__, result); } static int iuu_uart_on(struct usb_serial_port *port) { int status; u8 *buf; buf = kmalloc(4, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = IUU_UART_ENABLE; buf[1] = (u8) ((IUU_BAUD_9600 >> 8) & 0x00FF); buf[2] = (u8) (0x00FF & IUU_BAUD_9600); buf[3] = (u8) (0x0F0 & IUU_ONE_STOP_BIT) | (0x07 & IUU_PARITY_EVEN); status = bulk_immediate(port, buf, 4); if (status != IUU_OPERATION_OK) { dev_dbg(&port->dev, "%s - uart_on error\n", __func__); goto uart_enable_failed; } /* iuu_reset() the card after iuu_uart_on() */ status = iuu_uart_flush(port); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - uart_flush error\n", __func__); uart_enable_failed: kfree(buf); return status; } /* Disables the IUU UART (a.k.a. the Phoenix voiderface) */ static int iuu_uart_off(struct usb_serial_port *port) { int status; u8 *buf; buf = kmalloc(1, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = IUU_UART_DISABLE; status = bulk_immediate(port, buf, 1); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - uart_off error\n", __func__); kfree(buf); return status; } static int iuu_uart_baud(struct usb_serial_port *port, u32 baud_base, u32 *actual, u8 parity) { int status; u32 baud; u8 *dataout; u8 DataCount = 0; u8 T1Frekvens = 0; u8 T1reload = 0; unsigned int T1FrekvensHZ = 0; dev_dbg(&port->dev, "%s - enter baud_base=%d\n", __func__, baud_base); dataout = kmalloc(5, GFP_KERNEL); if (!dataout) return -ENOMEM; /*baud = (((priv->clk / 35) * baud_base) / 100000); */ baud = baud_base; if (baud < 1200 || baud > 230400) { kfree(dataout); return IUU_INVALID_PARAMETER; } if (baud > 977) { T1Frekvens = 3; T1FrekvensHZ = 500000; } if (baud > 3906) { T1Frekvens = 2; T1FrekvensHZ = 2000000; } if (baud > 11718) { T1Frekvens = 1; T1FrekvensHZ = 6000000; } if (baud > 46875) { T1Frekvens = 0; T1FrekvensHZ = 24000000; } T1reload = 256 - (u8) (T1FrekvensHZ / (baud * 2)); /* magic number here: ENTER_FIRMWARE_UPDATE; */ dataout[DataCount++] = IUU_UART_ESC; /* magic number here: CHANGE_BAUD; */ dataout[DataCount++] = IUU_UART_CHANGE; dataout[DataCount++] = T1Frekvens; dataout[DataCount++] = T1reload; *actual = (T1FrekvensHZ / (256 - T1reload)) / 2; switch (parity & 0x0F) { case IUU_PARITY_NONE: dataout[DataCount++] = 0x00; break; case IUU_PARITY_EVEN: dataout[DataCount++] = 0x01; break; case IUU_PARITY_ODD: dataout[DataCount++] = 0x02; break; case IUU_PARITY_MARK: dataout[DataCount++] = 0x03; break; case IUU_PARITY_SPACE: dataout[DataCount++] = 0x04; break; default: kfree(dataout); return IUU_INVALID_PARAMETER; } switch (parity & 0xF0) { case IUU_ONE_STOP_BIT: dataout[DataCount - 1] |= IUU_ONE_STOP_BIT; break; case IUU_TWO_STOP_BITS: dataout[DataCount - 1] |= IUU_TWO_STOP_BITS; break; default: kfree(dataout); return IUU_INVALID_PARAMETER; } status = bulk_immediate(port, dataout, DataCount); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - uart_off error\n", __func__); kfree(dataout); return status; } static void iuu_set_termios(struct tty_struct *tty, struct usb_serial_port *port, const struct ktermios *old_termios) { const u32 supported_mask = CMSPAR|PARENB|PARODD; struct iuu_private *priv = usb_get_serial_port_data(port); unsigned int cflag = tty->termios.c_cflag; int status; u32 actual; u32 parity; int csize = CS7; int baud; u32 newval = cflag & supported_mask; /* Just use the ospeed. ispeed should be the same. */ baud = tty->termios.c_ospeed; dev_dbg(&port->dev, "%s - enter c_ospeed or baud=%d\n", __func__, baud); /* compute the parity parameter */ parity = 0; if (cflag & CMSPAR) { /* Using mark space */ if (cflag & PARODD) parity |= IUU_PARITY_SPACE; else parity |= IUU_PARITY_MARK; } else if (!(cflag & PARENB)) { parity |= IUU_PARITY_NONE; csize = CS8; } else if (cflag & PARODD) parity |= IUU_PARITY_ODD; else parity |= IUU_PARITY_EVEN; parity |= (cflag & CSTOPB ? IUU_TWO_STOP_BITS : IUU_ONE_STOP_BIT); /* set it */ status = iuu_uart_baud(port, baud * priv->boost / 100, &actual, parity); /* set the termios value to the real one, so the user now what has * changed. We support few fields so its easies to copy the old hw * settings back over and then adjust them */ if (old_termios) tty_termios_copy_hw(&tty->termios, old_termios); if (status != 0) /* Set failed - return old bits */ return; /* Re-encode speed, parity and csize */ tty_encode_baud_rate(tty, baud, baud); tty->termios.c_cflag &= ~(supported_mask|CSIZE); tty->termios.c_cflag |= newval | csize; } static void iuu_close(struct usb_serial_port *port) { /* iuu_led (port,255,0,0,0); */ iuu_uart_off(port); usb_kill_urb(port->write_urb); usb_kill_urb(port->read_urb); iuu_led(port, 0, 0, 0xF000, 0xFF); } static void iuu_init_termios(struct tty_struct *tty) { tty->termios.c_cflag = B9600 | CS8 | CSTOPB | CREAD | PARENB | CLOCAL; tty->termios.c_ispeed = 9600; tty->termios.c_ospeed = 9600; tty->termios.c_lflag = 0; tty->termios.c_oflag = 0; tty->termios.c_iflag = 0; } static int iuu_open(struct tty_struct *tty, struct usb_serial_port *port) { struct usb_serial *serial = port->serial; struct device *dev = &port->dev; int result; int baud; u32 actual; struct iuu_private *priv = usb_get_serial_port_data(port); baud = tty->termios.c_ospeed; dev_dbg(dev, "%s - baud %d\n", __func__, baud); usb_clear_halt(serial->dev, port->write_urb->pipe); usb_clear_halt(serial->dev, port->read_urb->pipe); priv->poll = 0; #define SOUP(a, b, c, d) do { \ result = usb_control_msg(port->serial->dev, \ usb_sndctrlpipe(port->serial->dev, 0), \ b, a, c, d, NULL, 0, 1000); \ dev_dbg(dev, "0x%x:0x%x:0x%x:0x%x %d\n", a, b, c, d, result); } while (0) /* This is not UART related but IUU USB driver related or something */ /* like that. Basically no IUU will accept any commands from the USB */ /* host unless it has received the following message */ /* sprintf(buf ,"%c%c%c%c",0x03,0x02,0x02,0x0); */ SOUP(0x03, 0x02, 0x02, 0x0); iuu_led(port, 0xF000, 0xF000, 0, 0xFF); iuu_uart_on(port); if (boost < 100) boost = 100; priv->boost = boost; switch (clockmode) { case 2: /* 3.680 Mhz */ priv->clk = IUU_CLK_3680000; iuu_clk(port, IUU_CLK_3680000 * boost / 100); result = iuu_uart_baud(port, baud * boost / 100, &actual, IUU_PARITY_EVEN); break; case 3: /* 6.00 Mhz */ iuu_clk(port, IUU_CLK_6000000 * boost / 100); priv->clk = IUU_CLK_6000000; /* Ratio of 6000000 to 3500000 for baud 9600 */ result = iuu_uart_baud(port, 16457 * boost / 100, &actual, IUU_PARITY_EVEN); break; default: /* 3.579 Mhz */ iuu_clk(port, IUU_CLK_3579000 * boost / 100); priv->clk = IUU_CLK_3579000; result = iuu_uart_baud(port, baud * boost / 100, &actual, IUU_PARITY_EVEN); } /* set the cardin cardout signals */ switch (cdmode) { case 0: iuu_cardin = 0; iuu_cardout = 0; break; case 1: iuu_cardin = TIOCM_CD; iuu_cardout = 0; break; case 2: iuu_cardin = 0; iuu_cardout = TIOCM_CD; break; case 3: iuu_cardin = TIOCM_DSR; iuu_cardout = 0; break; case 4: iuu_cardin = 0; iuu_cardout = TIOCM_DSR; break; case 5: iuu_cardin = TIOCM_CTS; iuu_cardout = 0; break; case 6: iuu_cardin = 0; iuu_cardout = TIOCM_CTS; break; case 7: iuu_cardin = TIOCM_RNG; iuu_cardout = 0; break; case 8: iuu_cardin = 0; iuu_cardout = TIOCM_RNG; } iuu_uart_flush(port); dev_dbg(dev, "%s - initialization done\n", __func__); memset(port->write_urb->transfer_buffer, IUU_UART_RX, 1); usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), port->write_urb->transfer_buffer, 1, read_rxcmd_callback, port); result = usb_submit_urb(port->write_urb, GFP_KERNEL); if (result) { dev_err(dev, "%s - failed submitting read urb, error %d\n", __func__, result); iuu_close(port); } else { dev_dbg(dev, "%s - rxcmd OK\n", __func__); } return result; } /* how to change VCC */ static int iuu_vcc_set(struct usb_serial_port *port, unsigned int vcc) { int status; u8 *buf; buf = kmalloc(5, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = IUU_SET_VCC; buf[1] = vcc & 0xFF; buf[2] = (vcc >> 8) & 0xFF; buf[3] = (vcc >> 16) & 0xFF; buf[4] = (vcc >> 24) & 0xFF; status = bulk_immediate(port, buf, 5); kfree(buf); if (status != IUU_OPERATION_OK) dev_dbg(&port->dev, "%s - vcc error status = %2x\n", __func__, status); else dev_dbg(&port->dev, "%s - vcc OK !\n", __func__); return status; } /* * Sysfs Attributes */ static ssize_t vcc_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_serial_port *port = to_usb_serial_port(dev); struct iuu_private *priv = usb_get_serial_port_data(port); return sprintf(buf, "%d\n", priv->vcc); } static ssize_t vcc_mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct usb_serial_port *port = to_usb_serial_port(dev); struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long v; if (kstrtoul(buf, 10, &v)) { dev_err(dev, "%s - vcc_mode: %s is not a unsigned long\n", __func__, buf); goto fail_store_vcc_mode; } dev_dbg(dev, "%s: setting vcc_mode = %ld\n", __func__, v); if ((v != 3) && (v != 5)) { dev_err(dev, "%s - vcc_mode %ld is invalid\n", __func__, v); } else { iuu_vcc_set(port, v); priv->vcc = v; } fail_store_vcc_mode: return count; } static DEVICE_ATTR_RW(vcc_mode); static int iuu_create_sysfs_attrs(struct usb_serial_port *port) { return device_create_file(&port->dev, &dev_attr_vcc_mode); } static int iuu_remove_sysfs_attrs(struct usb_serial_port *port) { device_remove_file(&port->dev, &dev_attr_vcc_mode); return 0; } /* * End Sysfs Attributes */ static struct usb_serial_driver iuu_device = { .driver = { .name = "iuu_phoenix", }, .id_table = id_table, .num_ports = 1, .num_bulk_in = 1, .num_bulk_out = 1, .bulk_in_size = 512, .bulk_out_size = 512, .open = iuu_open, .close = iuu_close, .write = iuu_uart_write, .read_bulk_callback = iuu_uart_read_callback, .tiocmget = iuu_tiocmget, .tiocmset = iuu_tiocmset, .set_termios = iuu_set_termios, .init_termios = iuu_init_termios, .port_probe = iuu_port_probe, .port_remove = iuu_port_remove, }; static struct usb_serial_driver * const serial_drivers[] = { &iuu_device, NULL }; module_usb_serial_driver(serial_drivers, id_table); MODULE_AUTHOR("Alain Degreffe eczema@ecze.com"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); module_param(xmas, bool, 0644); MODULE_PARM_DESC(xmas, "Xmas colors enabled or not"); module_param(boost, int, 0644); MODULE_PARM_DESC(boost, "Card overclock boost (in percent 100-500)"); module_param(clockmode, int, 0644); MODULE_PARM_DESC(clockmode, "Card clock mode (1=3.579 MHz, 2=3.680 MHz, " "3=6 Mhz)"); module_param(cdmode, int, 0644); MODULE_PARM_DESC(cdmode, "Card detect mode (0=none, 1=CD, 2=!CD, 3=DSR, " "4=!DSR, 5=CTS, 6=!CTS, 7=RING, 8=!RING)"); module_param(vcc_default, int, 0644); MODULE_PARM_DESC(vcc_default, "Set default VCC (either 3 for 3.3V or 5 " "for 5V). Default to 5."); |
| 9 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Force feedback support for memoryless devices * * Copyright (c) 2006 Anssi Hannula <anssi.hannula@gmail.com> * Copyright (c) 2006 Dmitry Torokhov <dtor@mail.ru> */ /* #define DEBUG */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/input.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/jiffies.h> #include <linux/fixp-arith.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Anssi Hannula <anssi.hannula@gmail.com>"); MODULE_DESCRIPTION("Force feedback support for memoryless devices"); /* Number of effects handled with memoryless devices */ #define FF_MEMLESS_EFFECTS 16 /* Envelope update interval in ms */ #define FF_ENVELOPE_INTERVAL 50 #define FF_EFFECT_STARTED 0 #define FF_EFFECT_PLAYING 1 #define FF_EFFECT_ABORTING 2 struct ml_effect_state { struct ff_effect *effect; unsigned long flags; /* effect state (STARTED, PLAYING, etc) */ int count; /* loop count of the effect */ unsigned long play_at; /* start time */ unsigned long stop_at; /* stop time */ unsigned long adj_at; /* last time the effect was sent */ }; struct ml_device { void *private; struct ml_effect_state states[FF_MEMLESS_EFFECTS]; int gain; struct timer_list timer; struct input_dev *dev; int (*play_effect)(struct input_dev *dev, void *data, struct ff_effect *effect); }; static const struct ff_envelope *get_envelope(const struct ff_effect *effect) { static const struct ff_envelope empty_envelope; switch (effect->type) { case FF_PERIODIC: return &effect->u.periodic.envelope; case FF_CONSTANT: return &effect->u.constant.envelope; default: return &empty_envelope; } } /* * Check for the next time envelope requires an update on memoryless devices */ static unsigned long calculate_next_time(struct ml_effect_state *state) { const struct ff_envelope *envelope = get_envelope(state->effect); unsigned long attack_stop, fade_start, next_fade; if (envelope->attack_length) { attack_stop = state->play_at + msecs_to_jiffies(envelope->attack_length); if (time_before(state->adj_at, attack_stop)) return state->adj_at + msecs_to_jiffies(FF_ENVELOPE_INTERVAL); } if (state->effect->replay.length) { if (envelope->fade_length) { /* check when fading should start */ fade_start = state->stop_at - msecs_to_jiffies(envelope->fade_length); if (time_before(state->adj_at, fade_start)) return fade_start; /* already fading, advance to next checkpoint */ next_fade = state->adj_at + msecs_to_jiffies(FF_ENVELOPE_INTERVAL); if (time_before(next_fade, state->stop_at)) return next_fade; } return state->stop_at; } return state->play_at; } static void ml_schedule_timer(struct ml_device *ml) { struct ml_effect_state *state; unsigned long now = jiffies; unsigned long earliest = 0; unsigned long next_at; int events = 0; int i; pr_debug("calculating next timer\n"); for (i = 0; i < FF_MEMLESS_EFFECTS; i++) { state = &ml->states[i]; if (!test_bit(FF_EFFECT_STARTED, &state->flags)) continue; if (test_bit(FF_EFFECT_PLAYING, &state->flags)) next_at = calculate_next_time(state); else next_at = state->play_at; if (time_before_eq(now, next_at) && (++events == 1 || time_before(next_at, earliest))) earliest = next_at; } if (!events) { pr_debug("no actions\n"); del_timer(&ml->timer); } else { pr_debug("timer set\n"); mod_timer(&ml->timer, earliest); } } /* * Apply an envelope to a value */ static int apply_envelope(struct ml_effect_state *state, int value, struct ff_envelope *envelope) { struct ff_effect *effect = state->effect; unsigned long now = jiffies; int time_from_level; int time_of_envelope; int envelope_level; int difference; if (envelope->attack_length && time_before(now, state->play_at + msecs_to_jiffies(envelope->attack_length))) { pr_debug("value = 0x%x, attack_level = 0x%x\n", value, envelope->attack_level); time_from_level = jiffies_to_msecs(now - state->play_at); time_of_envelope = envelope->attack_length; envelope_level = min_t(u16, envelope->attack_level, 0x7fff); } else if (envelope->fade_length && effect->replay.length && time_after(now, state->stop_at - msecs_to_jiffies(envelope->fade_length)) && time_before(now, state->stop_at)) { time_from_level = jiffies_to_msecs(state->stop_at - now); time_of_envelope = envelope->fade_length; envelope_level = min_t(u16, envelope->fade_level, 0x7fff); } else return value; difference = abs(value) - envelope_level; pr_debug("difference = %d\n", difference); pr_debug("time_from_level = 0x%x\n", time_from_level); pr_debug("time_of_envelope = 0x%x\n", time_of_envelope); difference = difference * time_from_level / time_of_envelope; pr_debug("difference = %d\n", difference); return value < 0 ? -(difference + envelope_level) : (difference + envelope_level); } /* * Return the type the effect has to be converted into (memless devices) */ static int get_compatible_type(struct ff_device *ff, int effect_type) { if (test_bit(effect_type, ff->ffbit)) return effect_type; if (effect_type == FF_PERIODIC && test_bit(FF_RUMBLE, ff->ffbit)) return FF_RUMBLE; pr_err("invalid type in get_compatible_type()\n"); return 0; } /* * Only left/right direction should be used (under/over 0x8000) for * forward/reverse motor direction (to keep calculation fast & simple). */ static u16 ml_calculate_direction(u16 direction, u16 force, u16 new_direction, u16 new_force) { if (!force) return new_direction; if (!new_force) return direction; return (((u32)(direction >> 1) * force + (new_direction >> 1) * new_force) / (force + new_force)) << 1; } #define FRAC_N 8 static inline s16 fixp_new16(s16 a) { return ((s32)a) >> (16 - FRAC_N); } static inline s16 fixp_mult(s16 a, s16 b) { a = ((s32)a * 0x100) / 0x7fff; return ((s32)(a * b)) >> FRAC_N; } /* * Combine two effects and apply gain. */ static void ml_combine_effects(struct ff_effect *effect, struct ml_effect_state *state, int gain) { struct ff_effect *new = state->effect; unsigned int strong, weak, i; int x, y; s16 level; switch (new->type) { case FF_CONSTANT: i = new->direction * 360 / 0xffff; level = fixp_new16(apply_envelope(state, new->u.constant.level, &new->u.constant.envelope)); x = fixp_mult(fixp_sin16(i), level) * gain / 0xffff; y = fixp_mult(-fixp_cos16(i), level) * gain / 0xffff; /* * here we abuse ff_ramp to hold x and y of constant force * If in future any driver wants something else than x and y * in s8, this should be changed to something more generic */ effect->u.ramp.start_level = clamp_val(effect->u.ramp.start_level + x, -0x80, 0x7f); effect->u.ramp.end_level = clamp_val(effect->u.ramp.end_level + y, -0x80, 0x7f); break; case FF_RUMBLE: strong = (u32)new->u.rumble.strong_magnitude * gain / 0xffff; weak = (u32)new->u.rumble.weak_magnitude * gain / 0xffff; if (effect->u.rumble.strong_magnitude + strong) effect->direction = ml_calculate_direction( effect->direction, effect->u.rumble.strong_magnitude, new->direction, strong); else if (effect->u.rumble.weak_magnitude + weak) effect->direction = ml_calculate_direction( effect->direction, effect->u.rumble.weak_magnitude, new->direction, weak); else effect->direction = 0; effect->u.rumble.strong_magnitude = min(strong + effect->u.rumble.strong_magnitude, 0xffffU); effect->u.rumble.weak_magnitude = min(weak + effect->u.rumble.weak_magnitude, 0xffffU); break; case FF_PERIODIC: i = apply_envelope(state, abs(new->u.periodic.magnitude), &new->u.periodic.envelope); /* here we also scale it 0x7fff => 0xffff */ i = i * gain / 0x7fff; if (effect->u.rumble.strong_magnitude + i) effect->direction = ml_calculate_direction( effect->direction, effect->u.rumble.strong_magnitude, new->direction, i); else effect->direction = 0; effect->u.rumble.strong_magnitude = min(i + effect->u.rumble.strong_magnitude, 0xffffU); effect->u.rumble.weak_magnitude = min(i + effect->u.rumble.weak_magnitude, 0xffffU); break; default: pr_err("invalid type in ml_combine_effects()\n"); break; } } /* * Because memoryless devices have only one effect per effect type active * at one time we have to combine multiple effects into one */ static int ml_get_combo_effect(struct ml_device *ml, unsigned long *effect_handled, struct ff_effect *combo_effect) { struct ff_effect *effect; struct ml_effect_state *state; int effect_type; int i; memset(combo_effect, 0, sizeof(struct ff_effect)); for (i = 0; i < FF_MEMLESS_EFFECTS; i++) { if (__test_and_set_bit(i, effect_handled)) continue; state = &ml->states[i]; effect = state->effect; if (!test_bit(FF_EFFECT_STARTED, &state->flags)) continue; if (time_before(jiffies, state->play_at)) continue; /* * here we have started effects that are either * currently playing (and may need be aborted) * or need to start playing. */ effect_type = get_compatible_type(ml->dev->ff, effect->type); if (combo_effect->type != effect_type) { if (combo_effect->type != 0) { __clear_bit(i, effect_handled); continue; } combo_effect->type = effect_type; } if (__test_and_clear_bit(FF_EFFECT_ABORTING, &state->flags)) { __clear_bit(FF_EFFECT_PLAYING, &state->flags); __clear_bit(FF_EFFECT_STARTED, &state->flags); } else if (effect->replay.length && time_after_eq(jiffies, state->stop_at)) { __clear_bit(FF_EFFECT_PLAYING, &state->flags); if (--state->count <= 0) { __clear_bit(FF_EFFECT_STARTED, &state->flags); } else { state->play_at = jiffies + msecs_to_jiffies(effect->replay.delay); state->stop_at = state->play_at + msecs_to_jiffies(effect->replay.length); } } else { __set_bit(FF_EFFECT_PLAYING, &state->flags); state->adj_at = jiffies; ml_combine_effects(combo_effect, state, ml->gain); } } return combo_effect->type != 0; } static void ml_play_effects(struct ml_device *ml) { struct ff_effect effect; DECLARE_BITMAP(handled_bm, FF_MEMLESS_EFFECTS); memset(handled_bm, 0, sizeof(handled_bm)); while (ml_get_combo_effect(ml, handled_bm, &effect)) ml->play_effect(ml->dev, ml->private, &effect); ml_schedule_timer(ml); } static void ml_effect_timer(struct timer_list *t) { struct ml_device *ml = from_timer(ml, t, timer); struct input_dev *dev = ml->dev; pr_debug("timer: updating effects\n"); guard(spinlock_irqsave)(&dev->event_lock); ml_play_effects(ml); } /* * Sets requested gain for FF effects. Called with dev->event_lock held. */ static void ml_ff_set_gain(struct input_dev *dev, u16 gain) { struct ml_device *ml = dev->ff->private; int i; ml->gain = gain; for (i = 0; i < FF_MEMLESS_EFFECTS; i++) __clear_bit(FF_EFFECT_PLAYING, &ml->states[i].flags); ml_play_effects(ml); } /* * Start/stop specified FF effect. Called with dev->event_lock held. */ static int ml_ff_playback(struct input_dev *dev, int effect_id, int value) { struct ml_device *ml = dev->ff->private; struct ml_effect_state *state = &ml->states[effect_id]; if (value > 0) { pr_debug("initiated play\n"); __set_bit(FF_EFFECT_STARTED, &state->flags); state->count = value; state->play_at = jiffies + msecs_to_jiffies(state->effect->replay.delay); state->stop_at = state->play_at + msecs_to_jiffies(state->effect->replay.length); state->adj_at = state->play_at; } else { pr_debug("initiated stop\n"); if (test_bit(FF_EFFECT_PLAYING, &state->flags)) __set_bit(FF_EFFECT_ABORTING, &state->flags); else __clear_bit(FF_EFFECT_STARTED, &state->flags); } ml_play_effects(ml); return 0; } static int ml_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct ff_effect *old) { struct ml_device *ml = dev->ff->private; struct ml_effect_state *state = &ml->states[effect->id]; guard(spinlock_irq)(&dev->event_lock); if (test_bit(FF_EFFECT_STARTED, &state->flags)) { __clear_bit(FF_EFFECT_PLAYING, &state->flags); state->play_at = jiffies + msecs_to_jiffies(state->effect->replay.delay); state->stop_at = state->play_at + msecs_to_jiffies(state->effect->replay.length); state->adj_at = state->play_at; ml_schedule_timer(ml); } return 0; } static void ml_ff_destroy(struct ff_device *ff) { struct ml_device *ml = ff->private; /* * Even though we stop all playing effects when tearing down * an input device (via input_device_flush() that calls into * input_ff_flush() that stops and erases all effects), we * do not actually stop the timer, and therefore we should * do it here. */ del_timer_sync(&ml->timer); kfree(ml->private); } /** * input_ff_create_memless() - create memoryless force-feedback device * @dev: input device supporting force-feedback * @data: driver-specific data to be passed into @play_effect * @play_effect: driver-specific method for playing FF effect */ int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)) { struct ff_device *ff; int error; int i; struct ml_device *ml __free(kfree) = kzalloc(sizeof(*ml), GFP_KERNEL); if (!ml) return -ENOMEM; ml->dev = dev; ml->private = data; ml->play_effect = play_effect; ml->gain = 0xffff; timer_setup(&ml->timer, ml_effect_timer, 0); set_bit(FF_GAIN, dev->ffbit); error = input_ff_create(dev, FF_MEMLESS_EFFECTS); if (error) return error; ff = dev->ff; ff->upload = ml_ff_upload; ff->playback = ml_ff_playback; ff->set_gain = ml_ff_set_gain; ff->destroy = ml_ff_destroy; /* we can emulate periodic effects with RUMBLE */ if (test_bit(FF_RUMBLE, ff->ffbit)) { set_bit(FF_PERIODIC, dev->ffbit); set_bit(FF_SINE, dev->ffbit); set_bit(FF_TRIANGLE, dev->ffbit); set_bit(FF_SQUARE, dev->ffbit); } for (i = 0; i < FF_MEMLESS_EFFECTS; i++) ml->states[i].effect = &ff->effects[i]; ff->private = no_free_ptr(ml); return 0; } EXPORT_SYMBOL_GPL(input_ff_create_memless); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* cx231xx.h - driver for Conexant Cx23100/101/102 USB video capture devices Copyright (C) 2008 <srinivasa.deevi at conexant dot com> Based on em28xx driver */ #ifndef _CX231XX_H #define _CX231XX_H #include <linux/videodev2.h> #include <linux/types.h> #include <linux/ioctl.h> #include <linux/i2c.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/usb.h> #include <media/drv-intf/cx2341x.h> #include <media/videobuf2-vmalloc.h> #include <media/v4l2-device.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-fh.h> #include <media/rc-core.h> #include <media/i2c/ir-kbd-i2c.h> #include "cx231xx-reg.h" #include "cx231xx-pcb-cfg.h" #include "cx231xx-conf-reg.h" #define DRIVER_NAME "cx231xx" #define PWR_SLEEP_INTERVAL 10 /* I2C addresses for control block in Cx231xx */ #define AFE_DEVICE_ADDRESS 0x60 #define I2S_BLK_DEVICE_ADDRESS 0x98 #define VID_BLK_I2C_ADDRESS 0x88 #define VERVE_I2C_ADDRESS 0x40 #define DIF_USE_BASEBAND 0xFFFFFFFF /* Boards supported by driver */ #define CX231XX_BOARD_UNKNOWN 0 #define CX231XX_BOARD_CNXT_CARRAERA 1 #define CX231XX_BOARD_CNXT_SHELBY 2 #define CX231XX_BOARD_CNXT_RDE_253S 3 #define CX231XX_BOARD_CNXT_RDU_253S 4 #define CX231XX_BOARD_CNXT_VIDEO_GRABBER 5 #define CX231XX_BOARD_CNXT_RDE_250 6 #define CX231XX_BOARD_CNXT_RDU_250 7 #define CX231XX_BOARD_HAUPPAUGE_EXETER 8 #define CX231XX_BOARD_HAUPPAUGE_USBLIVE2 9 #define CX231XX_BOARD_PV_PLAYTV_USB_HYBRID 10 #define CX231XX_BOARD_PV_XCAPTURE_USB 11 #define CX231XX_BOARD_KWORLD_UB430_USB_HYBRID 12 #define CX231XX_BOARD_ICONBIT_U100 13 #define CX231XX_BOARD_HAUPPAUGE_USB2_FM_PAL 14 #define CX231XX_BOARD_HAUPPAUGE_USB2_FM_NTSC 15 #define CX231XX_BOARD_ELGATO_VIDEO_CAPTURE_V2 16 #define CX231XX_BOARD_OTG102 17 #define CX231XX_BOARD_KWORLD_UB445_USB_HYBRID 18 #define CX231XX_BOARD_HAUPPAUGE_930C_HD_1113xx 19 #define CX231XX_BOARD_HAUPPAUGE_930C_HD_1114xx 20 #define CX231XX_BOARD_HAUPPAUGE_955Q 21 #define CX231XX_BOARD_TERRATEC_GRABBY 22 #define CX231XX_BOARD_EVROMEDIA_FULL_HYBRID_FULLHD 23 #define CX231XX_BOARD_ASTROMETA_T2HYBRID 24 #define CX231XX_BOARD_THE_IMAGING_SOURCE_DFG_USB2_PRO 25 #define CX231XX_BOARD_HAUPPAUGE_935C 26 #define CX231XX_BOARD_HAUPPAUGE_975 27 /* Limits minimum and default number of buffers */ #define CX231XX_MIN_BUF 4 #define CX231XX_DEF_BUF 12 #define CX231XX_DEF_VBI_BUF 6 #define VBI_LINE_COUNT 17 #define VBI_LINE_LENGTH 1440 /*Limits the max URB message size */ #define URB_MAX_CTRL_SIZE 80 /* Params for validated field */ #define CX231XX_BOARD_NOT_VALIDATED 1 #define CX231XX_BOARD_VALIDATED 0 /* maximum number of cx231xx boards */ #define CX231XX_MAXBOARDS 8 /* maximum number of frames that can be queued */ #define CX231XX_NUM_FRAMES 5 /* number of buffers for isoc transfers */ #define CX231XX_NUM_BUFS 8 /* number of packets for each buffer windows requests only 40 packets .. so we better do the same this is what I found out for all alternate numbers there! */ #define CX231XX_NUM_PACKETS 40 /* default alternate; 0 means choose the best */ #define CX231XX_PINOUT 0 #define CX231XX_INTERLACED_DEFAULT 1 /* time to wait when stopping the isoc transfer */ #define CX231XX_URB_TIMEOUT \ msecs_to_jiffies(CX231XX_NUM_BUFS * CX231XX_NUM_PACKETS) #define CX231xx_NORMS (\ V4L2_STD_NTSC_M | V4L2_STD_NTSC_M_JP | V4L2_STD_NTSC_443 | \ V4L2_STD_PAL_BG | V4L2_STD_PAL_DK | V4L2_STD_PAL_I | \ V4L2_STD_PAL_M | V4L2_STD_PAL_N | V4L2_STD_PAL_Nc | \ V4L2_STD_PAL_60 | V4L2_STD_SECAM_L | V4L2_STD_SECAM_DK) #define SLEEP_S5H1432 30 #define CX23417_OSC_EN 8 #define CX23417_RESET 9 #define EP5_BUF_SIZE 4096 #define EP5_TIMEOUT_MS 2000 struct cx23417_fmt { u32 fourcc; /* v4l2 format id */ int depth; int flags; u32 cxformat; }; enum cx231xx_mode { CX231XX_SUSPEND, CX231XX_ANALOG_MODE, CX231XX_DIGITAL_MODE, }; enum cx231xx_std_mode { CX231XX_TV_AIR = 0, CX231XX_TV_CABLE }; enum cx231xx_stream_state { STREAM_OFF, STREAM_INTERRUPT, STREAM_ON, }; struct cx231xx; struct cx231xx_isoc_ctl { /* max packet size of isoc transaction */ int max_pkt_size; /* number of allocated urbs */ int num_bufs; /* urb for isoc transfers */ struct urb **urb; /* transfer buffers for isoc transfer */ char **transfer_buffer; /* Last buffer command and region */ u8 cmd; int pos, size, pktsize; /* Last field: ODD or EVEN? */ int field; /* Stores incomplete commands */ u32 tmp_buf; int tmp_buf_len; /* Stores already requested buffers */ struct cx231xx_buffer *buf; /* Stores the number of received fields */ int nfields; /* isoc urb callback */ int (*isoc_copy) (struct cx231xx *dev, struct urb *urb); }; struct cx231xx_bulk_ctl { /* max packet size of bulk transaction */ int max_pkt_size; /* number of allocated urbs */ int num_bufs; /* urb for bulk transfers */ struct urb **urb; /* transfer buffers for bulk transfer */ char **transfer_buffer; /* Last buffer command and region */ u8 cmd; int pos, size, pktsize; /* Last field: ODD or EVEN? */ int field; /* Stores incomplete commands */ u32 tmp_buf; int tmp_buf_len; /* Stores already requested buffers */ struct cx231xx_buffer *buf; /* Stores the number of received fields */ int nfields; /* bulk urb callback */ int (*bulk_copy) (struct cx231xx *dev, struct urb *urb); }; struct cx231xx_fmt { char *name; u32 fourcc; /* v4l2 format id */ int depth; int reg; }; /* buffer for one video frame */ struct cx231xx_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; struct list_head frame; int top_field; int receiving; }; enum ps_package_head { CX231XX_NEED_ADD_PS_PACKAGE_HEAD = 0, CX231XX_NONEED_PS_PACKAGE_HEAD }; struct cx231xx_dmaqueue { struct list_head active; wait_queue_head_t wq; /* Counters to control buffer fill */ int pos; u8 is_partial_line; u8 partial_buf[8]; u8 last_sav; int current_field; u32 bytes_left_in_line; u32 lines_completed; u8 field1_done; u32 lines_per_field; u32 sequence; /*Mpeg2 control buffer*/ u8 *p_left_data; u32 left_data_count; u8 mpeg_buffer_done; u32 mpeg_buffer_completed; enum ps_package_head add_ps_package_head; char ps_head[10]; }; /* inputs */ #define MAX_CX231XX_INPUT 4 enum cx231xx_itype { CX231XX_VMUX_COMPOSITE1 = 1, CX231XX_VMUX_SVIDEO, CX231XX_VMUX_TELEVISION, CX231XX_VMUX_CABLE, CX231XX_RADIO, CX231XX_VMUX_DVB, }; enum cx231xx_v_input { CX231XX_VIN_1_1 = 0x1, CX231XX_VIN_2_1, CX231XX_VIN_3_1, CX231XX_VIN_4_1, CX231XX_VIN_1_2 = 0x01, CX231XX_VIN_2_2, CX231XX_VIN_3_2, CX231XX_VIN_1_3 = 0x1, CX231XX_VIN_2_3, CX231XX_VIN_3_3, }; /* cx231xx has two audio inputs: tuner and line in */ enum cx231xx_amux { /* This is the only entry for cx231xx tuner input */ CX231XX_AMUX_VIDEO, /* cx231xx tuner */ CX231XX_AMUX_LINE_IN, /* Line In */ }; struct cx231xx_reg_seq { unsigned char bit; unsigned char val; int sleep; }; struct cx231xx_input { enum cx231xx_itype type; unsigned int vmux; enum cx231xx_amux amux; struct cx231xx_reg_seq *gpio; }; #define INPUT(nr) (&cx231xx_boards[dev->model].input[nr]) enum cx231xx_decoder { CX231XX_NODECODER, CX231XX_AVDECODER }; enum CX231XX_I2C_MASTER_PORT { I2C_0 = 0, /* master 0 - internal connection */ I2C_1 = 1, /* master 1 - used with mux */ I2C_2 = 2, /* master 2 */ I2C_1_MUX_1 = 3, /* master 1 - port 1 (I2C_DEMOD_EN = 0) */ I2C_1_MUX_3 = 4 /* master 1 - port 3 (I2C_DEMOD_EN = 1) */ }; struct cx231xx_board { char *name; int vchannels; int tuner_type; int tuner_addr; v4l2_std_id norm; /* tv norm */ /* demod related */ int demod_addr; int demod_addr2; u8 demod_xfer_mode; /* 0 - Serial; 1 - parallel */ /* GPIO Pins */ struct cx231xx_reg_seq *dvb_gpio; struct cx231xx_reg_seq *suspend_gpio; struct cx231xx_reg_seq *tuner_gpio; /* Negative means don't use it */ s8 tuner_sif_gpio; s8 tuner_scl_gpio; s8 tuner_sda_gpio; /* PIN ctrl */ u32 ctl_pin_status_mask; u8 agc_analog_digital_select_gpio; u32 gpio_pin_status_mask; /* i2c masters */ u8 tuner_i2c_master; u8 demod_i2c_master; u8 ir_i2c_master; /* for devices with I2C chips for IR */ char *rc_map_name; unsigned int max_range_640_480:1; unsigned int has_dvb:1; unsigned int has_417:1; unsigned int valid:1; unsigned int no_alt_vanc:1; unsigned int external_av:1; unsigned char xclk, i2c_speed; enum cx231xx_decoder decoder; int output_mode; struct cx231xx_input input[MAX_CX231XX_INPUT]; struct cx231xx_input radio; struct rc_map *ir_codes; }; /* device states */ enum cx231xx_dev_state { DEV_INITIALIZED = 0x01, DEV_DISCONNECTED = 0x02, }; enum AFE_MODE { AFE_MODE_LOW_IF, AFE_MODE_BASEBAND, AFE_MODE_EU_HI_IF, AFE_MODE_US_HI_IF, AFE_MODE_JAPAN_HI_IF }; enum AUDIO_INPUT { AUDIO_INPUT_MUTE, AUDIO_INPUT_LINE, AUDIO_INPUT_TUNER_TV, AUDIO_INPUT_SPDIF, AUDIO_INPUT_TUNER_FM }; #define CX231XX_AUDIO_BUFS 5 #define CX231XX_NUM_AUDIO_PACKETS 16 #define CX231XX_ISO_NUM_AUDIO_PACKETS 64 /* cx231xx extensions */ #define CX231XX_AUDIO 0x10 #define CX231XX_DVB 0x20 struct cx231xx_audio { char name[50]; char *transfer_buffer[CX231XX_AUDIO_BUFS]; struct urb *urb[CX231XX_AUDIO_BUFS]; struct usb_device *udev; unsigned int capture_transfer_done; struct snd_pcm_substream *capture_pcm_substream; unsigned int hwptr_done_capture; struct snd_card *sndcard; int users, shutdown; /* locks */ spinlock_t slock; int alt; /* alternate */ int max_pkt_size; /* max packet size of isoc transaction */ int num_alt; /* Number of alternative settings */ unsigned int *alt_max_pkt_size; /* array of wMaxPacketSize */ u16 end_point_addr; }; /*****************************************************************/ /* set/get i2c */ /* 00--1Mb/s, 01-400kb/s, 10--100kb/s, 11--5Mb/s */ #define I2C_SPEED_1M 0x0 #define I2C_SPEED_400K 0x1 #define I2C_SPEED_100K 0x2 #define I2C_SPEED_5M 0x3 /* 0-- STOP transaction */ #define I2C_STOP 0x0 /* 1-- do not transmit STOP at end of transaction */ #define I2C_NOSTOP 0x1 /* 1--allow slave to insert clock wait states */ #define I2C_SYNC 0x1 struct cx231xx_i2c { struct cx231xx *dev; int nr; /* i2c i/o */ struct i2c_adapter i2c_adap; int i2c_rc; /* different settings for each bus */ u8 i2c_period; u8 i2c_nostop; u8 i2c_reserve; }; struct cx231xx_i2c_xfer_data { u8 dev_addr; u8 direction; /* 1 - IN, 0 - OUT */ u8 saddr_len; /* sub address len */ u16 saddr_dat; /* sub addr data */ u8 buf_size; /* buffer size */ u8 *p_buffer; /* pointer to the buffer */ }; struct VENDOR_REQUEST_IN { u8 bRequest; u16 wValue; u16 wIndex; u16 wLength; u8 direction; u8 bData; u8 *pBuff; }; struct cx231xx_tvnorm { char *name; v4l2_std_id id; u32 cxiformat; u32 cxoformat; }; enum TRANSFER_TYPE { Raw_Video = 0, Audio, Vbi, /* VANC */ Sliced_cc, /* HANC */ TS1_serial_mode, TS2, TS1_parallel_mode } ; struct cx231xx_video_mode { /* Isoc control struct */ struct cx231xx_dmaqueue vidq; struct cx231xx_isoc_ctl isoc_ctl; struct cx231xx_bulk_ctl bulk_ctl; /* locks */ spinlock_t slock; /* usb transfer */ int alt; /* alternate */ int max_pkt_size; /* max packet size of isoc transaction */ int num_alt; /* Number of alternative settings */ unsigned int *alt_max_pkt_size; /* array of wMaxPacketSize */ u16 end_point_addr; }; struct cx231xx_tsport { struct cx231xx *dev; int nr; int sram_chno; /* dma queues */ u32 ts_packet_size; u32 ts_packet_count; int width; int height; /* locks */ spinlock_t slock; /* registers */ u32 reg_gpcnt; u32 reg_gpcnt_ctl; u32 reg_dma_ctl; u32 reg_lngth; u32 reg_hw_sop_ctrl; u32 reg_gen_ctrl; u32 reg_bd_pkt_status; u32 reg_sop_status; u32 reg_fifo_ovfl_stat; u32 reg_vld_misc; u32 reg_ts_clk_en; u32 reg_ts_int_msk; u32 reg_ts_int_stat; u32 reg_src_sel; /* Default register vals */ int pci_irqmask; u32 dma_ctl_val; u32 ts_int_msk_val; u32 gen_ctrl_val; u32 ts_clk_en_val; u32 src_sel_val; u32 vld_misc_val; u32 hw_sop_ctrl_val; /* Allow a single tsport to have multiple frontends */ u32 num_frontends; void *port_priv; }; /* main device struct */ struct cx231xx { /* generic device properties */ char name[30]; /* name (including minor) of the device */ int model; /* index in the device_data struct */ int devno; /* marks the number of this device */ struct device *dev; /* pointer to USB interface's dev */ struct cx231xx_board board; /* For I2C IR support */ struct IR_i2c_init_data init_data; struct i2c_client *ir_i2c_client; unsigned int stream_on:1; /* Locks streams */ unsigned int vbi_stream_on:1; /* Locks streams for VBI */ unsigned int has_audio_class:1; unsigned int has_alsa_audio:1; unsigned int i2c_scan_running:1; /* true only during i2c_scan */ struct cx231xx_fmt *format; struct v4l2_device v4l2_dev; struct v4l2_subdev *sd_cx25840; struct v4l2_subdev *sd_tuner; struct v4l2_ctrl_handler ctrl_handler; struct v4l2_ctrl_handler radio_ctrl_handler; struct cx2341x_handler mpeg_ctrl_handler; struct work_struct wq_trigger; /* Trigger to start/stop audio for alsa module */ atomic_t stream_started; /* stream should be running if true */ struct list_head devlist; int tuner_type; /* type of the tuner */ int tuner_addr; /* tuner address */ /* I2C adapters: Master 1 & 2 (External) & Master 3 (Internal only) */ struct cx231xx_i2c i2c_bus[3]; struct i2c_mux_core *muxc; struct i2c_adapter *i2c_mux_adap[2]; unsigned int xc_fw_load_done:1; unsigned int port_3_switch_enabled:1; /* locks */ struct mutex gpio_i2c_lock; struct mutex i2c_lock; /* video for linux */ int users; /* user count for exclusive use */ struct video_device vdev; /* video for linux device struct */ v4l2_std_id norm; /* selected tv norm */ int ctl_freq; /* selected frequency */ unsigned int ctl_ainput; /* selected audio input */ /* frame properties */ int width; /* current frame width */ int height; /* current frame height */ int interlaced; /* 1=interlace fields, 0=just top fields */ unsigned int size; struct cx231xx_audio adev; /* states */ enum cx231xx_dev_state state; struct work_struct request_module_wk; /* locks */ struct mutex lock; struct mutex ctrl_urb_lock; /* protects urb_buf */ struct list_head inqueue, outqueue; wait_queue_head_t open, wait_frame, wait_stream; struct video_device vbi_dev; struct video_device radio_dev; #if defined(CONFIG_MEDIA_CONTROLLER) struct media_device *media_dev; struct media_pad video_pad, vbi_pad; struct media_entity input_ent[MAX_CX231XX_INPUT]; struct media_pad input_pad[MAX_CX231XX_INPUT]; #endif struct vb2_queue vidq; struct vb2_queue vbiq; unsigned char eedata[256]; struct cx231xx_video_mode video_mode; struct cx231xx_video_mode vbi_mode; struct cx231xx_video_mode sliced_cc_mode; struct cx231xx_video_mode ts1_mode; atomic_t devlist_count; struct usb_device *udev; /* the usb device */ char urb_buf[URB_MAX_CTRL_SIZE]; /* urb control msg buffer */ /* helper funcs that call usb_control_msg */ int (*cx231xx_read_ctrl_reg) (struct cx231xx *dev, u8 req, u16 reg, char *buf, int len); int (*cx231xx_write_ctrl_reg) (struct cx231xx *dev, u8 req, u16 reg, char *buf, int len); int (*cx231xx_send_usb_command) (struct cx231xx_i2c *i2c_bus, struct cx231xx_i2c_xfer_data *req_data); int (*cx231xx_gpio_i2c_read) (struct cx231xx *dev, u8 dev_addr, u8 *buf, u8 len); int (*cx231xx_gpio_i2c_write) (struct cx231xx *dev, u8 dev_addr, u8 *buf, u8 len); int (*cx231xx_set_analog_freq) (struct cx231xx *dev, u32 freq); int (*cx231xx_reset_analog_tuner) (struct cx231xx *dev); enum cx231xx_mode mode; struct cx231xx_dvb *dvb; /* Cx231xx supported PCB config's */ struct pcb_config current_pcb_config; u8 current_scenario_idx; u8 interface_count; u8 max_iad_interface_count; /* GPIO related register direction and values */ u32 gpio_dir; u32 gpio_val; /* Power Modes */ int power_mode; /* afe parameters */ enum AFE_MODE afe_mode; u32 afe_ref_count; /* video related parameters */ u32 video_input; u32 active_mode; u8 vbi_or_sliced_cc_mode; /* 0 - vbi ; 1 - sliced cc mode */ enum cx231xx_std_mode std_mode; /* 0 - Air; 1 - cable */ /*mode: digital=1 or analog=0*/ u8 mode_tv; u8 USE_ISO; struct cx231xx_tvnorm encodernorm; struct cx231xx_tsport ts1, ts2; struct vb2_queue mpegq; struct video_device v4l_device; atomic_t v4l_reader_count; u32 freq; unsigned int input; u32 cx23417_mailbox; u32 __iomem *lmmio; u8 __iomem *bmmio; }; extern struct list_head cx231xx_devlist; #define cx25840_call(cx231xx, o, f, args...) \ v4l2_subdev_call(cx231xx->sd_cx25840, o, f, ##args) #define tuner_call(cx231xx, o, f, args...) \ v4l2_subdev_call(cx231xx->sd_tuner, o, f, ##args) #define call_all(dev, o, f, args...) \ v4l2_device_call_until_err(&dev->v4l2_dev, 0, o, f, ##args) struct cx231xx_ops { struct list_head next; char *name; int id; int (*init) (struct cx231xx *); int (*fini) (struct cx231xx *); }; /* call back functions in dvb module */ int cx231xx_set_analog_freq(struct cx231xx *dev, u32 freq); int cx231xx_reset_analog_tuner(struct cx231xx *dev); /* Provided by cx231xx-i2c.c */ void cx231xx_do_i2c_scan(struct cx231xx *dev, int i2c_port); int cx231xx_i2c_register(struct cx231xx_i2c *bus); void cx231xx_i2c_unregister(struct cx231xx_i2c *bus); int cx231xx_i2c_mux_create(struct cx231xx *dev); int cx231xx_i2c_mux_register(struct cx231xx *dev, int mux_no); void cx231xx_i2c_mux_unregister(struct cx231xx *dev); struct i2c_adapter *cx231xx_get_i2c_adap(struct cx231xx *dev, int i2c_port); /* Internal block control functions */ int cx231xx_read_i2c_master(struct cx231xx *dev, u8 dev_addr, u16 saddr, u8 saddr_len, u32 *data, u8 data_len, int master); int cx231xx_write_i2c_master(struct cx231xx *dev, u8 dev_addr, u16 saddr, u8 saddr_len, u32 data, u8 data_len, int master); int cx231xx_read_i2c_data(struct cx231xx *dev, u8 dev_addr, u16 saddr, u8 saddr_len, u32 *data, u8 data_len); int cx231xx_write_i2c_data(struct cx231xx *dev, u8 dev_addr, u16 saddr, u8 saddr_len, u32 data, u8 data_len); int cx231xx_reg_mask_write(struct cx231xx *dev, u8 dev_addr, u8 size, u16 register_address, u8 bit_start, u8 bit_end, u32 value); int cx231xx_read_modify_write_i2c_dword(struct cx231xx *dev, u8 dev_addr, u16 saddr, u32 mask, u32 value); u32 cx231xx_set_field(u32 field_mask, u32 data); /*verve r/w*/ void initGPIO(struct cx231xx *dev); void uninitGPIO(struct cx231xx *dev); /* afe related functions */ int cx231xx_afe_init_super_block(struct cx231xx *dev, u32 ref_count); int cx231xx_afe_init_channels(struct cx231xx *dev); int cx231xx_afe_setup_AFE_for_baseband(struct cx231xx *dev); int cx231xx_afe_set_input_mux(struct cx231xx *dev, u32 input_mux); int cx231xx_afe_set_mode(struct cx231xx *dev, enum AFE_MODE mode); int cx231xx_afe_update_power_control(struct cx231xx *dev, enum AV_MODE avmode); int cx231xx_afe_adjust_ref_count(struct cx231xx *dev, u32 video_input); /* i2s block related functions */ int cx231xx_i2s_blk_initialize(struct cx231xx *dev); int cx231xx_i2s_blk_update_power_control(struct cx231xx *dev, enum AV_MODE avmode); int cx231xx_i2s_blk_set_audio_input(struct cx231xx *dev, u8 audio_input); /* DIF related functions */ int cx231xx_dif_configure_C2HH_for_low_IF(struct cx231xx *dev, u32 mode, u32 function_mode, u32 standard); void cx231xx_set_Colibri_For_LowIF(struct cx231xx *dev, u32 if_freq, u8 spectral_invert, u32 mode); u32 cx231xx_Get_Colibri_CarrierOffset(u32 mode, u32 standerd); void cx231xx_set_DIF_bandpass(struct cx231xx *dev, u32 if_freq, u8 spectral_invert, u32 mode); void cx231xx_Setup_AFE_for_LowIF(struct cx231xx *dev); void reset_s5h1432_demod(struct cx231xx *dev); void update_HH_register_after_set_DIF(struct cx231xx *dev); int cx231xx_dif_set_standard(struct cx231xx *dev, u32 standard); int cx231xx_tuner_pre_channel_change(struct cx231xx *dev); int cx231xx_tuner_post_channel_change(struct cx231xx *dev); /* video parser functions */ u8 cx231xx_find_next_SAV_EAV(u8 *p_buffer, u32 buffer_size, u32 *p_bytes_used); u8 cx231xx_find_boundary_SAV_EAV(u8 *p_buffer, u8 *partial_buf, u32 *p_bytes_used); int cx231xx_do_copy(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q, u8 *p_buffer, u32 bytes_to_copy); void cx231xx_reset_video_buffer(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q); u8 cx231xx_is_buffer_done(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q); u32 cx231xx_copy_video_line(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q, u8 *p_line, u32 length, int field_number); u32 cx231xx_get_video_line(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q, u8 sav_eav, u8 *p_buffer, u32 buffer_size); void cx231xx_swab(u16 *from, u16 *to, u16 len); /* Provided by cx231xx-core.c */ u32 cx231xx_request_buffers(struct cx231xx *dev, u32 count); void cx231xx_queue_unusedframes(struct cx231xx *dev); void cx231xx_release_buffers(struct cx231xx *dev); /* read from control pipe */ int cx231xx_read_ctrl_reg(struct cx231xx *dev, u8 req, u16 reg, char *buf, int len); /* write to control pipe */ int cx231xx_write_ctrl_reg(struct cx231xx *dev, u8 req, u16 reg, char *buf, int len); int cx231xx_mode_register(struct cx231xx *dev, u16 address, u32 mode); int cx231xx_send_vendor_cmd(struct cx231xx *dev, struct VENDOR_REQUEST_IN *ven_req); int cx231xx_send_usb_command(struct cx231xx_i2c *i2c_bus, struct cx231xx_i2c_xfer_data *req_data); /* Gpio related functions */ int cx231xx_send_gpio_cmd(struct cx231xx *dev, u32 gpio_bit, u8 *gpio_val, u8 len, u8 request, u8 direction); int cx231xx_set_gpio_value(struct cx231xx *dev, int pin_number, int pin_value); int cx231xx_set_gpio_direction(struct cx231xx *dev, int pin_number, int pin_value); int cx231xx_gpio_i2c_start(struct cx231xx *dev); int cx231xx_gpio_i2c_end(struct cx231xx *dev); int cx231xx_gpio_i2c_write_byte(struct cx231xx *dev, u8 data); int cx231xx_gpio_i2c_read_byte(struct cx231xx *dev, u8 *buf); int cx231xx_gpio_i2c_read_ack(struct cx231xx *dev); int cx231xx_gpio_i2c_write_ack(struct cx231xx *dev); int cx231xx_gpio_i2c_write_nak(struct cx231xx *dev); int cx231xx_gpio_i2c_read(struct cx231xx *dev, u8 dev_addr, u8 *buf, u8 len); int cx231xx_gpio_i2c_write(struct cx231xx *dev, u8 dev_addr, u8 *buf, u8 len); /* audio related functions */ int cx231xx_set_audio_decoder_input(struct cx231xx *dev, enum AUDIO_INPUT audio_input); int cx231xx_capture_start(struct cx231xx *dev, int start, u8 media_type); int cx231xx_set_video_alternate(struct cx231xx *dev); int cx231xx_set_alt_setting(struct cx231xx *dev, u8 index, u8 alt); int is_fw_load(struct cx231xx *dev); int cx231xx_check_fw(struct cx231xx *dev); int cx231xx_init_isoc(struct cx231xx *dev, int max_packets, int num_bufs, int max_pkt_size, int (*isoc_copy) (struct cx231xx *dev, struct urb *urb)); int cx231xx_init_bulk(struct cx231xx *dev, int max_packets, int num_bufs, int max_pkt_size, int (*bulk_copy) (struct cx231xx *dev, struct urb *urb)); void cx231xx_stop_TS1(struct cx231xx *dev); void cx231xx_start_TS1(struct cx231xx *dev); void cx231xx_uninit_isoc(struct cx231xx *dev); void cx231xx_uninit_bulk(struct cx231xx *dev); int cx231xx_set_mode(struct cx231xx *dev, enum cx231xx_mode set_mode); int cx231xx_unmute_audio(struct cx231xx *dev); int cx231xx_ep5_bulkout(struct cx231xx *dev, u8 *firmware, u16 size); void cx231xx_disable656(struct cx231xx *dev); void cx231xx_enable656(struct cx231xx *dev); int cx231xx_demod_reset(struct cx231xx *dev); int cx231xx_gpio_set(struct cx231xx *dev, struct cx231xx_reg_seq *gpio); /* Device list functions */ void cx231xx_release_resources(struct cx231xx *dev); void cx231xx_release_analog_resources(struct cx231xx *dev); int cx231xx_register_analog_devices(struct cx231xx *dev); void cx231xx_remove_from_devlist(struct cx231xx *dev); void cx231xx_add_into_devlist(struct cx231xx *dev); void cx231xx_init_extension(struct cx231xx *dev); void cx231xx_close_extension(struct cx231xx *dev); /* hardware init functions */ int cx231xx_dev_init(struct cx231xx *dev); void cx231xx_dev_uninit(struct cx231xx *dev); void cx231xx_config_i2c(struct cx231xx *dev); int cx231xx_config(struct cx231xx *dev); /* Stream control functions */ int cx231xx_start_stream(struct cx231xx *dev, u32 ep_mask); int cx231xx_stop_stream(struct cx231xx *dev, u32 ep_mask); int cx231xx_initialize_stream_xfer(struct cx231xx *dev, u32 media_type); /* Power control functions */ int cx231xx_set_power_mode(struct cx231xx *dev, enum AV_MODE mode); /* chip specific control functions */ int cx231xx_init_ctrl_pin_status(struct cx231xx *dev); int cx231xx_set_agc_analog_digital_mux_select(struct cx231xx *dev, u8 analog_or_digital); int cx231xx_enable_i2c_port_3(struct cx231xx *dev, bool is_port_3); /* video audio decoder related functions */ void video_mux(struct cx231xx *dev, int index); int cx231xx_set_video_input_mux(struct cx231xx *dev, u8 input); int cx231xx_set_decoder_video_input(struct cx231xx *dev, u8 pin_type, u32 input); int cx231xx_do_mode_ctrl_overrides(struct cx231xx *dev); int cx231xx_set_audio_input(struct cx231xx *dev, u8 input); /* Provided by cx231xx-video.c */ int cx231xx_register_extension(struct cx231xx_ops *dev); void cx231xx_unregister_extension(struct cx231xx_ops *dev); void cx231xx_init_extension(struct cx231xx *dev); void cx231xx_close_extension(struct cx231xx *dev); void cx231xx_v4l2_create_entities(struct cx231xx *dev); int cx231xx_querycap(struct file *file, void *priv, struct v4l2_capability *cap); int cx231xx_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t); int cx231xx_s_tuner(struct file *file, void *priv, const struct v4l2_tuner *t); int cx231xx_g_frequency(struct file *file, void *priv, struct v4l2_frequency *f); int cx231xx_s_frequency(struct file *file, void *priv, const struct v4l2_frequency *f); int cx231xx_enum_input(struct file *file, void *priv, struct v4l2_input *i); int cx231xx_g_input(struct file *file, void *priv, unsigned int *i); int cx231xx_s_input(struct file *file, void *priv, unsigned int i); int cx231xx_g_chip_info(struct file *file, void *fh, struct v4l2_dbg_chip_info *chip); int cx231xx_g_register(struct file *file, void *priv, struct v4l2_dbg_register *reg); int cx231xx_s_register(struct file *file, void *priv, const struct v4l2_dbg_register *reg); /* Provided by cx231xx-cards.c */ extern void cx231xx_pre_card_setup(struct cx231xx *dev); extern void cx231xx_card_setup(struct cx231xx *dev); extern struct cx231xx_board cx231xx_boards[]; extern struct usb_device_id cx231xx_id_table[]; int cx231xx_tuner_callback(void *ptr, int component, int command, int arg); /* cx23885-417.c */ extern int cx231xx_417_register(struct cx231xx *dev); extern void cx231xx_417_unregister(struct cx231xx *dev); /* cx23885-input.c */ #if defined(CONFIG_VIDEO_CX231XX_RC) int cx231xx_ir_init(struct cx231xx *dev); void cx231xx_ir_exit(struct cx231xx *dev); #else static inline int cx231xx_ir_init(struct cx231xx *dev) { return 0; } static inline void cx231xx_ir_exit(struct cx231xx *dev) {} #endif static inline unsigned int norm_maxw(struct cx231xx *dev) { if (dev->board.max_range_640_480) return 640; else return 720; } static inline unsigned int norm_maxh(struct cx231xx *dev) { if (dev->board.max_range_640_480) return 480; else return (dev->norm & V4L2_STD_625_50) ? 576 : 480; } #endif |
| 203 4 307 41 30 3 5 3 3 214 214 2 3 10 2 1 51 52 51 8 308 22 305 14 307 244 9 9 8 2 7 3 3 15 15 15 9 9 214 213 5 29 203 3 3 4 38 117 1 10 10 27 112 101 213 105 167 94 94 94 45 9 50 186 50 17 50 50 14 45 1 14 50 50 50 23 27 49 187 7 185 182 1 186 1 93 185 1 1 186 8 183 2 185 188 14 123 157 157 4 1 152 5 1 11 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * TODO: try to use extents tree (instead of array) */ #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/log2.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* runs_tree is a continues memory. Try to avoid big size. */ #define NTFS3_RUN_MAX_BYTES 0x10000 struct ntfs_run { CLST vcn; /* Virtual cluster number. */ CLST len; /* Length in clusters. */ CLST lcn; /* Logical cluster number. */ }; /* * run_lookup - Lookup the index of a MCB entry that is first <= vcn. * * Case of success it will return non-zero value and set * @index parameter to index of entry been found. * Case of entry missing from list 'index' will be set to * point to insertion position for the entry question. */ static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) { size_t min_idx, max_idx, mid_idx; struct ntfs_run *r; if (!run->count) { *index = 0; return false; } min_idx = 0; max_idx = run->count - 1; /* Check boundary cases specially, 'cause they cover the often requests. */ r = run->runs; if (vcn < r->vcn) { *index = 0; return false; } if (vcn < r->vcn + r->len) { *index = 0; return true; } r += max_idx; if (vcn >= r->vcn + r->len) { *index = run->count; return false; } if (vcn >= r->vcn) { *index = max_idx; return true; } do { mid_idx = min_idx + ((max_idx - min_idx) >> 1); r = run->runs + mid_idx; if (vcn < r->vcn) { max_idx = mid_idx - 1; if (!mid_idx) break; } else if (vcn >= r->vcn + r->len) { min_idx = mid_idx + 1; } else { *index = mid_idx; return true; } } while (min_idx <= max_idx); *index = max_idx + 1; return false; } /* * run_consolidate - Consolidate runs starting from a given one. */ static void run_consolidate(struct runs_tree *run, size_t index) { size_t i; struct ntfs_run *r = run->runs + index; while (index + 1 < run->count) { /* * I should merge current run with next * if start of the next run lies inside one being tested. */ struct ntfs_run *n = r + 1; CLST end = r->vcn + r->len; CLST dl; /* Stop if runs are not aligned one to another. */ if (n->vcn > end) break; dl = end - n->vcn; /* * If range at index overlaps with next one * then I will either adjust it's start position * or (if completely matches) dust remove one from the list. */ if (dl > 0) { if (n->len <= dl) goto remove_next_range; n->len -= dl; n->vcn += dl; if (n->lcn != SPARSE_LCN) n->lcn += dl; dl = 0; } /* * Stop if sparse mode does not match * both current and next runs. */ if ((n->lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) { index += 1; r = n; continue; } /* * Check if volume block * of a next run lcn does not match * last volume block of the current run. */ if (n->lcn != SPARSE_LCN && n->lcn != r->lcn + r->len) break; /* * Next and current are siblings. * Eat/join. */ r->len += n->len - dl; remove_next_range: i = run->count - (index + 1); if (i > 1) memmove(n, n + 1, sizeof(*n) * (i - 1)); run->count -= 1; } } /* * run_is_mapped_full * * Return: True if range [svcn - evcn] is mapped. */ bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn) { size_t i; const struct ntfs_run *r, *end; CLST next_vcn; if (!run_lookup(run, svcn, &i)) return false; end = run->runs + run->count; r = run->runs + i; for (;;) { next_vcn = r->vcn + r->len; if (next_vcn > evcn) return true; if (++r >= end) return false; if (r->vcn != next_vcn) return false; } } bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, CLST *len, size_t *index) { size_t idx; CLST gap; struct ntfs_run *r; /* Fail immediately if nrun was not touched yet. */ if (!run->runs) return false; if (!run_lookup(run, vcn, &idx)) return false; r = run->runs + idx; if (vcn >= r->vcn + r->len) return false; gap = vcn - r->vcn; if (r->len <= gap) return false; *lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + gap); if (len) *len = r->len - gap; if (index) *index = idx; return true; } /* * run_truncate_head - Decommit the range before vcn. */ void run_truncate_head(struct runs_tree *run, CLST vcn) { size_t index; struct ntfs_run *r; if (run_lookup(run, vcn, &index)) { r = run->runs + index; if (vcn > r->vcn) { CLST dlen = vcn - r->vcn; r->vcn = vcn; r->len -= dlen; if (r->lcn != SPARSE_LCN) r->lcn += dlen; } if (!index) return; } r = run->runs; memmove(r, r + index, sizeof(*r) * (run->count - index)); run->count -= index; if (!run->count) { kvfree(run->runs); run->runs = NULL; run->allocated = 0; } } /* * run_truncate - Decommit the range after vcn. */ void run_truncate(struct runs_tree *run, CLST vcn) { size_t index; /* * If I hit the range then * I have to truncate one. * If range to be truncated is becoming empty * then it will entirely be removed. */ if (run_lookup(run, vcn, &index)) { struct ntfs_run *r = run->runs + index; r->len = vcn - r->vcn; if (r->len > 0) index += 1; } /* * At this point 'index' is set to position that * should be thrown away (including index itself) * Simple one - just set the limit. */ run->count = index; /* Do not reallocate array 'runs'. Only free if possible. */ if (!index) { kvfree(run->runs); run->runs = NULL; run->allocated = 0; } } /* * run_truncate_around - Trim head and tail if necessary. */ void run_truncate_around(struct runs_tree *run, CLST vcn) { run_truncate_head(run, vcn); if (run->count >= NTFS3_RUN_MAX_BYTES / sizeof(struct ntfs_run) / 2) run_truncate(run, (run->runs + (run->count >> 1))->vcn); } /* * run_add_entry * * Sets location to known state. * Run to be added may overlap with existing location. * * Return: false if of memory. */ bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, bool is_mft) { size_t used, index; struct ntfs_run *r; bool inrange; CLST tail_vcn = 0, tail_len = 0, tail_lcn = 0; bool should_add_tail = false; /* * Lookup the insertion point. * * Execute bsearch for the entry containing * start position question. */ inrange = run_lookup(run, vcn, &index); /* * Shortcut here would be case of * range not been found but one been added * continues previous run. * This case I can directly make use of * existing range as my start point. */ if (!inrange && index > 0) { struct ntfs_run *t = run->runs + index - 1; if (t->vcn + t->len == vcn && (t->lcn == SPARSE_LCN) == (lcn == SPARSE_LCN) && (lcn == SPARSE_LCN || lcn == t->lcn + t->len)) { inrange = true; index -= 1; } } /* * At this point 'index' either points to the range * containing start position or to the insertion position * for a new range. * So first let's check if range I'm probing is here already. */ if (!inrange) { requires_new_range: /* * Range was not found. * Insert at position 'index' */ used = run->count * sizeof(struct ntfs_run); /* * Check allocated space. * If one is not enough to get one more entry * then it will be reallocated. */ if (run->allocated < used + sizeof(struct ntfs_run)) { size_t bytes; struct ntfs_run *new_ptr; /* Use power of 2 for 'bytes'. */ if (!used) { bytes = 64; } else if (used <= 16 * PAGE_SIZE) { if (is_power_of_2(run->allocated)) bytes = run->allocated << 1; else bytes = (size_t)1 << (2 + blksize_bits(used)); } else { bytes = run->allocated + (16 * PAGE_SIZE); } WARN_ON(!is_mft && bytes > NTFS3_RUN_MAX_BYTES); new_ptr = kvmalloc(bytes, GFP_KERNEL); if (!new_ptr) return false; r = new_ptr + index; memcpy(new_ptr, run->runs, index * sizeof(struct ntfs_run)); memcpy(r + 1, run->runs + index, sizeof(struct ntfs_run) * (run->count - index)); kvfree(run->runs); run->runs = new_ptr; run->allocated = bytes; } else { size_t i = run->count - index; r = run->runs + index; /* memmove appears to be a bottle neck here... */ if (i > 0) memmove(r + 1, r, sizeof(struct ntfs_run) * i); } r->vcn = vcn; r->lcn = lcn; r->len = len; run->count += 1; } else { r = run->runs + index; /* * If one of ranges was not allocated then we * have to split location we just matched and * insert current one. * A common case this requires tail to be reinserted * a recursive call. */ if (((lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) || (lcn != SPARSE_LCN && lcn != r->lcn + (vcn - r->vcn))) { CLST to_eat = vcn - r->vcn; CLST Tovcn = to_eat + len; should_add_tail = Tovcn < r->len; if (should_add_tail) { tail_lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + Tovcn); tail_vcn = r->vcn + Tovcn; tail_len = r->len - Tovcn; } if (to_eat > 0) { r->len = to_eat; inrange = false; index += 1; goto requires_new_range; } /* lcn should match one were going to add. */ r->lcn = lcn; } /* * If existing range fits then were done. * Otherwise extend found one and fall back to range jocode. */ if (r->vcn + r->len < vcn + len) r->len += len - ((r->vcn + r->len) - vcn); } /* * And normalize it starting from insertion point. * It's possible that no insertion needed case if * start point lies within the range of an entry * that 'index' points to. */ if (inrange && index > 0) index -= 1; run_consolidate(run, index); run_consolidate(run, index + 1); /* * A special case. * We have to add extra range a tail. */ if (should_add_tail && !run_add_entry(run, tail_vcn, tail_lcn, tail_len, is_mft)) return false; return true; } /* run_collapse_range * * Helper for attr_collapse_range(), * which is helper for fallocate(collapse_range). */ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len) { size_t index, eat; struct ntfs_run *r, *e, *eat_start, *eat_end; CLST end; if (WARN_ON(!run_lookup(run, vcn, &index))) return true; /* Should never be here. */ e = run->runs + run->count; r = run->runs + index; end = vcn + len; if (vcn > r->vcn) { if (r->vcn + r->len <= end) { /* Collapse tail of run .*/ r->len = vcn - r->vcn; } else if (r->lcn == SPARSE_LCN) { /* Collapse a middle part of sparsed run. */ r->len -= len; } else { /* Collapse a middle part of normal run, split. */ if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) return false; return run_collapse_range(run, vcn, len); } r += 1; } eat_start = r; eat_end = r; for (; r < e; r++) { CLST d; if (r->vcn >= end) { r->vcn -= len; continue; } if (r->vcn + r->len <= end) { /* Eat this run. */ eat_end = r + 1; continue; } d = end - r->vcn; if (r->lcn != SPARSE_LCN) r->lcn += d; r->len -= d; r->vcn -= len - d; } eat = eat_end - eat_start; memmove(eat_start, eat_end, (e - eat_end) * sizeof(*r)); run->count -= eat; return true; } /* run_insert_range * * Helper for attr_insert_range(), * which is helper for fallocate(insert_range). */ bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len) { size_t index; struct ntfs_run *r, *e; if (WARN_ON(!run_lookup(run, vcn, &index))) return false; /* Should never be here. */ e = run->runs + run->count; r = run->runs + index; if (vcn > r->vcn) r += 1; for (; r < e; r++) r->vcn += len; r = run->runs + index; if (vcn > r->vcn) { /* split fragment. */ CLST len1 = vcn - r->vcn; CLST len2 = r->len - len1; CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1); r->len = len1; if (!run_add_entry(run, vcn + len, lcn2, len2, false)) return false; } if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) return false; return true; } /* * run_get_entry - Return index-th mapped region. */ bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, CLST *lcn, CLST *len) { const struct ntfs_run *r; if (index >= run->count) return false; r = run->runs + index; if (!r->len) return false; if (vcn) *vcn = r->vcn; if (lcn) *lcn = r->lcn; if (len) *len = r->len; return true; } /* * run_packed_size - Calculate the size of packed int64. */ #ifdef __BIG_ENDIAN static inline int run_packed_size(const s64 n) { const u8 *p = (const u8 *)&n + sizeof(n) - 1; if (n >= 0) { if (p[-7] || p[-6] || p[-5] || p[-4]) p -= 4; if (p[-3] || p[-2]) p -= 2; if (p[-1]) p -= 1; if (p[0] & 0x80) p -= 1; } else { if (p[-7] != 0xff || p[-6] != 0xff || p[-5] != 0xff || p[-4] != 0xff) p -= 4; if (p[-3] != 0xff || p[-2] != 0xff) p -= 2; if (p[-1] != 0xff) p -= 1; if (!(p[0] & 0x80)) p -= 1; } return (const u8 *)&n + sizeof(n) - p; } /* Full trusted function. It does not check 'size' for errors. */ static inline void run_pack_s64(u8 *run_buf, u8 size, s64 v) { const u8 *p = (u8 *)&v; switch (size) { case 8: run_buf[7] = p[0]; fallthrough; case 7: run_buf[6] = p[1]; fallthrough; case 6: run_buf[5] = p[2]; fallthrough; case 5: run_buf[4] = p[3]; fallthrough; case 4: run_buf[3] = p[4]; fallthrough; case 3: run_buf[2] = p[5]; fallthrough; case 2: run_buf[1] = p[6]; fallthrough; case 1: run_buf[0] = p[7]; } } /* Full trusted function. It does not check 'size' for errors. */ static inline s64 run_unpack_s64(const u8 *run_buf, u8 size, s64 v) { u8 *p = (u8 *)&v; switch (size) { case 8: p[0] = run_buf[7]; fallthrough; case 7: p[1] = run_buf[6]; fallthrough; case 6: p[2] = run_buf[5]; fallthrough; case 5: p[3] = run_buf[4]; fallthrough; case 4: p[4] = run_buf[3]; fallthrough; case 3: p[5] = run_buf[2]; fallthrough; case 2: p[6] = run_buf[1]; fallthrough; case 1: p[7] = run_buf[0]; } return v; } #else static inline int run_packed_size(const s64 n) { const u8 *p = (const u8 *)&n; if (n >= 0) { if (p[7] || p[6] || p[5] || p[4]) p += 4; if (p[3] || p[2]) p += 2; if (p[1]) p += 1; if (p[0] & 0x80) p += 1; } else { if (p[7] != 0xff || p[6] != 0xff || p[5] != 0xff || p[4] != 0xff) p += 4; if (p[3] != 0xff || p[2] != 0xff) p += 2; if (p[1] != 0xff) p += 1; if (!(p[0] & 0x80)) p += 1; } return 1 + p - (const u8 *)&n; } /* Full trusted function. It does not check 'size' for errors. */ static inline void run_pack_s64(u8 *run_buf, u8 size, s64 v) { const u8 *p = (u8 *)&v; /* memcpy( run_buf, &v, size); Is it faster? */ switch (size) { case 8: run_buf[7] = p[7]; fallthrough; case 7: run_buf[6] = p[6]; fallthrough; case 6: run_buf[5] = p[5]; fallthrough; case 5: run_buf[4] = p[4]; fallthrough; case 4: run_buf[3] = p[3]; fallthrough; case 3: run_buf[2] = p[2]; fallthrough; case 2: run_buf[1] = p[1]; fallthrough; case 1: run_buf[0] = p[0]; } } /* full trusted function. It does not check 'size' for errors */ static inline s64 run_unpack_s64(const u8 *run_buf, u8 size, s64 v) { u8 *p = (u8 *)&v; /* memcpy( &v, run_buf, size); Is it faster? */ switch (size) { case 8: p[7] = run_buf[7]; fallthrough; case 7: p[6] = run_buf[6]; fallthrough; case 6: p[5] = run_buf[5]; fallthrough; case 5: p[4] = run_buf[4]; fallthrough; case 4: p[3] = run_buf[3]; fallthrough; case 3: p[2] = run_buf[2]; fallthrough; case 2: p[1] = run_buf[1]; fallthrough; case 1: p[0] = run_buf[0]; } return v; } #endif /* * run_pack - Pack runs into buffer. * * packed_vcns - How much runs we have packed. * packed_size - How much bytes we have used run_buf. */ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, u32 run_buf_size, CLST *packed_vcns) { CLST next_vcn, vcn, lcn; CLST prev_lcn = 0; CLST evcn1 = svcn + len; const struct ntfs_run *r, *r_end; int packed_size = 0; size_t i; s64 dlcn; int offset_size, size_size, tmp; *packed_vcns = 0; if (!len) goto out; /* Check all required entries [svcn, encv1) available. */ if (!run_lookup(run, svcn, &i)) return -ENOENT; r_end = run->runs + run->count; r = run->runs + i; for (next_vcn = r->vcn + r->len; next_vcn < evcn1; next_vcn = r->vcn + r->len) { if (++r >= r_end || r->vcn != next_vcn) return -ENOENT; } /* Repeat cycle above and pack runs. Assume no errors. */ r = run->runs + i; len = svcn - r->vcn; vcn = svcn; lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len); len = r->len - len; for (;;) { next_vcn = vcn + len; if (next_vcn > evcn1) len = evcn1 - vcn; /* How much bytes required to pack len. */ size_size = run_packed_size(len); /* offset_size - How much bytes is packed dlcn. */ if (lcn == SPARSE_LCN) { offset_size = 0; dlcn = 0; } else { /* NOTE: lcn can be less than prev_lcn! */ dlcn = (s64)lcn - prev_lcn; offset_size = run_packed_size(dlcn); prev_lcn = lcn; } tmp = run_buf_size - packed_size - 2 - offset_size; if (tmp <= 0) goto out; /* Can we store this entire run. */ if (tmp < size_size) goto out; if (run_buf) { /* Pack run header. */ run_buf[0] = ((u8)(size_size | (offset_size << 4))); run_buf += 1; /* Pack the length of run. */ run_pack_s64(run_buf, size_size, len); run_buf += size_size; /* Pack the offset from previous LCN. */ run_pack_s64(run_buf, offset_size, dlcn); run_buf += offset_size; } packed_size += 1 + offset_size + size_size; *packed_vcns += len; if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1) goto out; r += 1; vcn = r->vcn; lcn = r->lcn; len = r->len; } out: /* Store last zero. */ if (run_buf) run_buf[0] = 0; return packed_size + 1; } /* * run_unpack - Unpack packed runs from @run_buf. * * Return: Error if negative, or real used bytes. */ int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size) { u64 prev_lcn, vcn64, lcn, next_vcn; const u8 *run_last, *run_0; bool is_mft = ino == MFT_REC_MFT; if (run_buf_size < 0) return -EINVAL; /* Check for empty. */ if (evcn + 1 == svcn) return 0; if (evcn < svcn) return -EINVAL; run_0 = run_buf; run_last = run_buf + run_buf_size; prev_lcn = 0; vcn64 = svcn; /* Read all runs the chain. */ /* size_size - How much bytes is packed len. */ while (run_buf < run_last) { /* size_size - How much bytes is packed len. */ u8 size_size = *run_buf & 0xF; /* offset_size - How much bytes is packed dlcn. */ u8 offset_size = *run_buf++ >> 4; u64 len; if (!size_size) break; /* * Unpack runs. * NOTE: Runs are stored little endian order * "len" is unsigned value, "dlcn" is signed. * Large positive number requires to store 5 bytes * e.g.: 05 FF 7E FF FF 00 00 00 */ if (size_size > sizeof(len)) return -EINVAL; len = run_unpack_s64(run_buf, size_size, 0); /* Skip size_size. */ run_buf += size_size; if (!len) return -EINVAL; if (!offset_size) lcn = SPARSE_LCN64; else if (offset_size <= sizeof(s64)) { s64 dlcn; /* Initial value of dlcn is -1 or 0. */ dlcn = (run_buf[offset_size - 1] & 0x80) ? (s64)-1 : 0; dlcn = run_unpack_s64(run_buf, offset_size, dlcn); /* Skip offset_size. */ run_buf += offset_size; if (!dlcn) return -EINVAL; lcn = prev_lcn + dlcn; prev_lcn = lcn; } else { /* The size of 'dlcn' can't be > 8. */ return -EINVAL; } next_vcn = vcn64 + len; /* Check boundary. */ if (next_vcn > evcn + 1) return -EINVAL; #ifndef CONFIG_NTFS3_64BIT_CLUSTER if (next_vcn > 0x100000000ull || (lcn + len) > 0x100000000ull) { ntfs_err( sbi->sb, "This driver is compiled without CONFIG_NTFS3_64BIT_CLUSTER (like windows driver).\n" "Volume contains 64 bits run: vcn %llx, lcn %llx, len %llx.\n" "Activate CONFIG_NTFS3_64BIT_CLUSTER to process this case", vcn64, lcn, len); return -EOPNOTSUPP; } #endif if (lcn != SPARSE_LCN64 && lcn + len > sbi->used.bitmap.nbits) { /* LCN range is out of volume. */ return -EINVAL; } if (!run) ; /* Called from check_attr(fslog.c) to check run. */ else if (run == RUN_DEALLOCATE) { /* * Called from ni_delete_all to free clusters * without storing in run. */ if (lcn != SPARSE_LCN64) mark_as_free_ex(sbi, lcn, len, true); } else if (vcn64 >= vcn) { if (!run_add_entry(run, vcn64, lcn, len, is_mft)) return -ENOMEM; } else if (next_vcn > vcn) { u64 dlen = vcn - vcn64; if (!run_add_entry(run, vcn, lcn + dlen, len - dlen, is_mft)) return -ENOMEM; } vcn64 = next_vcn; } if (vcn64 != evcn + 1) { /* Not expected length of unpacked runs. */ return -EINVAL; } return run_buf - run_0; } #ifdef NTFS3_CHECK_FREE_CLST /* * run_unpack_ex - Unpack packed runs from "run_buf". * * Checks unpacked runs to be used in bitmap. * * Return: Error if negative, or real used bytes. */ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size) { int ret, err; CLST next_vcn, lcn, len; size_t index, done; bool ok, zone; struct wnd_bitmap *wnd; ret = run_unpack(run, sbi, ino, svcn, evcn, vcn, run_buf, run_buf_size); if (ret <= 0) return ret; if (!sbi->used.bitmap.sb || !run || run == RUN_DEALLOCATE) return ret; if (ino == MFT_REC_BADCLUST) return ret; next_vcn = vcn = svcn; wnd = &sbi->used.bitmap; for (ok = run_lookup_entry(run, vcn, &lcn, &len, &index); next_vcn <= evcn; ok = run_get_entry(run, ++index, &vcn, &lcn, &len)) { if (!ok || next_vcn != vcn) return -EINVAL; next_vcn = vcn + len; if (lcn == SPARSE_LCN) continue; if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) continue; down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); zone = max(wnd->zone_bit, lcn) < min(wnd->zone_end, lcn + len); /* Check for free blocks. */ ok = !zone && wnd_is_used(wnd, lcn, len); up_read(&wnd->rw_lock); if (ok) continue; /* Looks like volume is corrupted. */ ntfs_set_state(sbi, NTFS_DIRTY_ERROR); if (!down_write_trylock(&wnd->rw_lock)) continue; if (zone) { /* * Range [lcn, lcn + len) intersects with zone. * To avoid complex with zone just turn it off. */ wnd_zone_set(wnd, 0, 0); } /* Mark all zero bits as used in range [lcn, lcn+len). */ err = wnd_set_used_safe(wnd, lcn, len, &done); if (zone) { /* Restore zone. Lock mft run. */ struct rw_semaphore *lock = is_mounted(sbi) ? &sbi->mft.ni->file.run_lock : NULL; if (lock) down_read(lock); ntfs_refresh_zone(sbi); if (lock) up_read(lock); } up_write(&wnd->rw_lock); if (err) return err; } return ret; } #endif /* * run_get_highest_vcn * * Return the highest vcn from a mapping pairs array * it used while replaying log file. */ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn) { u64 vcn64 = vcn; u8 size_size; while ((size_size = *run_buf & 0xF)) { u8 offset_size = *run_buf++ >> 4; u64 len; if (size_size > 8 || offset_size > 8) return -EINVAL; len = run_unpack_s64(run_buf, size_size, 0); if (!len) return -EINVAL; run_buf += size_size + offset_size; vcn64 += len; #ifndef CONFIG_NTFS3_64BIT_CLUSTER if (vcn64 > 0x100000000ull) return -EINVAL; #endif } *highest_vcn = vcn64 - 1; return 0; } /* * run_clone * * Make a copy of run */ int run_clone(const struct runs_tree *run, struct runs_tree *new_run) { size_t bytes = run->count * sizeof(struct ntfs_run); if (bytes > new_run->allocated) { struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL); if (!new_ptr) return -ENOMEM; kvfree(new_run->runs); new_run->runs = new_ptr; new_run->allocated = bytes; } memcpy(new_run->runs, run->runs, bytes); new_run->count = run->count; return 0; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007,2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/mm.h> #include <linux/error-injection.h> #include "messages.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "print-tree.h" #include "locking.h" #include "volumes.h" #include "qgroup.h" #include "tree-mod-log.h" #include "tree-checker.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "relocation.h" #include "file-item.h" static struct kmem_cache *btrfs_path_cachep; static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level); static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, int extend); static int push_node_left(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src, int empty); static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); /* * The leaf data grows from end-to-front in the node. this returns the address * of the start of the last item, which is the stop of the leaf data stack. */ static unsigned int leaf_data_end(const struct extent_buffer *leaf) { u32 nr = btrfs_header_nritems(leaf); if (nr == 0) return BTRFS_LEAF_DATA_SIZE(leaf->fs_info); return btrfs_item_offset(leaf, nr - 1); } /* * Move data in a @leaf (using memmove, safe for overlapping ranges). * * @leaf: leaf that we're doing a memmove on * @dst_offset: item data offset we're moving to * @src_offset: item data offset were' moving from * @len: length of the data we're moving * * Wrapper around memmove_extent_buffer() that takes into account the header on * the leaf. The btrfs_item offset's start directly after the header, so we * have to adjust any offsets to account for the header in the leaf. This * handles that math to simplify the callers. */ static inline void memmove_leaf_data(const struct extent_buffer *leaf, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { memmove_extent_buffer(leaf, btrfs_item_nr_offset(leaf, 0) + dst_offset, btrfs_item_nr_offset(leaf, 0) + src_offset, len); } /* * Copy item data from @src into @dst at the given @offset. * * @dst: destination leaf that we're copying into * @src: source leaf that we're copying from * @dst_offset: item data offset we're copying to * @src_offset: item data offset were' copying from * @len: length of the data we're copying * * Wrapper around copy_extent_buffer() that takes into account the header on * the leaf. The btrfs_item offset's start directly after the header, so we * have to adjust any offsets to account for the header in the leaf. This * handles that math to simplify the callers. */ static inline void copy_leaf_data(const struct extent_buffer *dst, const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { copy_extent_buffer(dst, src, btrfs_item_nr_offset(dst, 0) + dst_offset, btrfs_item_nr_offset(src, 0) + src_offset, len); } /* * Move items in a @leaf (using memmove). * * @dst: destination leaf for the items * @dst_item: the item nr we're copying into * @src_item: the item nr we're copying from * @nr_items: the number of items to copy * * Wrapper around memmove_extent_buffer() that does the math to get the * appropriate offsets into the leaf from the item numbers. */ static inline void memmove_leaf_items(const struct extent_buffer *leaf, int dst_item, int src_item, int nr_items) { memmove_extent_buffer(leaf, btrfs_item_nr_offset(leaf, dst_item), btrfs_item_nr_offset(leaf, src_item), nr_items * sizeof(struct btrfs_item)); } /* * Copy items from @src into @dst at the given @offset. * * @dst: destination leaf for the items * @src: source leaf for the items * @dst_item: the item nr we're copying into * @src_item: the item nr we're copying from * @nr_items: the number of items to copy * * Wrapper around copy_extent_buffer() that does the math to get the * appropriate offsets into the leaf from the item numbers. */ static inline void copy_leaf_items(const struct extent_buffer *dst, const struct extent_buffer *src, int dst_item, int src_item, int nr_items) { copy_extent_buffer(dst, src, btrfs_item_nr_offset(dst, dst_item), btrfs_item_nr_offset(src, src_item), nr_items * sizeof(struct btrfs_item)); } struct btrfs_path *btrfs_alloc_path(void) { might_sleep(); return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS); } /* this also releases the path */ void btrfs_free_path(struct btrfs_path *p) { if (!p) return; btrfs_release_path(p); kmem_cache_free(btrfs_path_cachep, p); } /* * path release drops references on the extent buffers in the path * and it drops any locks held by this path * * It is safe to call this on paths that no locks or extent buffers held. */ noinline void btrfs_release_path(struct btrfs_path *p) { int i; for (i = 0; i < BTRFS_MAX_LEVEL; i++) { p->slots[i] = 0; if (!p->nodes[i]) continue; if (p->locks[i]) { btrfs_tree_unlock_rw(p->nodes[i], p->locks[i]); p->locks[i] = 0; } free_extent_buffer(p->nodes[i]); p->nodes[i] = NULL; } } /* * safely gets a reference on the root node of a tree. A lock * is not taken, so a concurrent writer may put a different node * at the root of the tree. See btrfs_lock_root_node for the * looping required. * * The extent buffer returned by this has a reference taken, so * it won't disappear. It may stop being the root of the tree * at any time because there are no locks held. */ struct extent_buffer *btrfs_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { rcu_read_lock(); eb = rcu_dereference(root->node); /* * RCU really hurts here, we could free up the root node because * it was COWed but we may not get the new root node yet so do * the inc_not_zero dance and if it doesn't work then * synchronize_rcu and try again. */ if (atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); break; } rcu_read_unlock(); synchronize_rcu(); } return eb; } /* * Cowonly root (not-shareable trees, everything not subvolume or reloc roots), * just get put onto a simple dirty list. Transaction walks this list to make * sure they get properly updated on disk. */ static void add_root_to_dirty_list(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; if (test_bit(BTRFS_ROOT_DIRTY, &root->state) || !test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state)) return; spin_lock(&fs_info->trans_lock); if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) { /* Want the extent tree to be the last on the list */ if (btrfs_root_id(root) == BTRFS_EXTENT_TREE_OBJECTID) list_move_tail(&root->dirty_list, &fs_info->dirty_cowonly_roots); else list_move(&root->dirty_list, &fs_info->dirty_cowonly_roots); } spin_unlock(&fs_info->trans_lock); } /* * used by snapshot creation to make a copy of a root for a tree with * a given objectid. The buffer with the new root node is returned in * cow_ret, and this func returns zero on success or a negative error code. */ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *cow; int ret = 0; int level; struct btrfs_disk_key disk_key; u64 reloc_src_root = 0; WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != fs_info->running_transaction->transid); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != btrfs_get_root_last_trans(root)); level = btrfs_header_level(buf); if (level == 0) btrfs_item_key(buf, &disk_key, 0); else btrfs_node_key(buf, &disk_key, 0); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) reloc_src_root = btrfs_header_owner(buf); cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid, &disk_key, level, buf->start, 0, reloc_src_root, BTRFS_NESTING_NEW_ROOT); if (IS_ERR(cow)) return PTR_ERR(cow); copy_extent_buffer_full(cow, buf); btrfs_set_header_bytenr(cow, cow->start); btrfs_set_header_generation(cow, trans->transid); btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV); btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN | BTRFS_HEADER_FLAG_RELOC); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC); else btrfs_set_header_owner(cow, new_root_objectid); write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid); WARN_ON(btrfs_header_generation(buf) > trans->transid); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) { btrfs_tree_unlock(cow); free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; } /* * check if the tree block can be shared by multiple trees */ bool btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf) { const u64 buf_gen = btrfs_header_generation(buf); /* * Tree blocks not in shareable trees and tree roots are never shared. * If a block was allocated after the last snapshot and the block was * not allocated by tree relocation, we know the block is not shared. */ if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return false; if (buf == root->node) return false; if (buf_gen > btrfs_root_last_snapshot(&root->root_item) && !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) return false; if (buf != root->commit_root) return true; /* * An extent buffer that used to be the commit root may still be shared * because the tree height may have increased and it became a child of a * higher level root. This can happen when snapshotting a subvolume * created in the current transaction. */ if (buf_gen == trans->transid) return true; return false; } static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *cow, int *last_ref) { struct btrfs_fs_info *fs_info = root->fs_info; u64 refs; u64 owner; u64 flags; int ret; /* * Backrefs update rules: * * Always use full backrefs for extent pointers in tree block * allocated by tree relocation. * * If a shared tree block is no longer referenced by its owner * tree (btrfs_header_owner(buf) == root->root_key.objectid), * use full backrefs for extent pointers in tree block. * * If a tree block is been relocating * (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID), * use full backrefs for extent pointers in tree block. * The reason for this is some operations (such as drop tree) * are only allowed for blocks use full backrefs. */ if (btrfs_block_can_be_shared(trans, root, buf)) { ret = btrfs_lookup_extent_info(trans, fs_info, buf->start, btrfs_header_level(buf), 1, &refs, &flags, NULL); if (ret) return ret; if (unlikely(refs == 0)) { btrfs_crit(fs_info, "found 0 references for tree block at bytenr %llu level %d root %llu", buf->start, btrfs_header_level(buf), btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } } else { refs = 1; if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID || btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) flags = BTRFS_BLOCK_FLAG_FULL_BACKREF; else flags = 0; } owner = btrfs_header_owner(buf); if (unlikely(owner == BTRFS_TREE_RELOC_OBJECTID && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))) { btrfs_crit(fs_info, "found tree block at bytenr %llu level %d root %llu refs %llu flags %llx without full backref flag set", buf->start, btrfs_header_level(buf), btrfs_root_id(root), refs, flags); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } if (refs > 1) { if ((owner == btrfs_root_id(root) || btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { ret = btrfs_inc_ref(trans, root, buf, 1); if (ret) return ret; if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { ret = btrfs_dec_ref(trans, root, buf, 0); if (ret) return ret; ret = btrfs_inc_ref(trans, root, cow, 1); if (ret) return ret; } ret = btrfs_set_disk_extent_flags(trans, buf, BTRFS_BLOCK_FLAG_FULL_BACKREF); if (ret) return ret; } else { if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) return ret; } } else { if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) { if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) return ret; ret = btrfs_dec_ref(trans, root, buf, 1); if (ret) return ret; } btrfs_clear_buffer_dirty(trans, buf); *last_ref = 1; } return 0; } /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked * dirty and returned locked. If you modify the block it needs to be marked * dirty again. * * search_start -- an allocation hint for the new block * * empty_size -- a hint that you plan on doing more cow. This is the size in * bytes the allocator should try to find free next to the block it returns. * This is just a hint and may be ignored by the allocator. */ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, u64 search_start, u64 empty_size, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *cow; int level, ret; int last_ref = 0; int unlock_orig = 0; u64 parent_start = 0; u64 reloc_src_root = 0; if (*cow_ret == buf) unlock_orig = 1; btrfs_assert_tree_write_locked(buf); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != fs_info->running_transaction->transid); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != btrfs_get_root_last_trans(root)); level = btrfs_header_level(buf); if (level == 0) btrfs_item_key(buf, &disk_key, 0); else btrfs_node_key(buf, &disk_key, 0); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { if (parent) parent_start = parent->start; reloc_src_root = btrfs_header_owner(buf); } cow = btrfs_alloc_tree_block(trans, root, parent_start, btrfs_root_id(root), &disk_key, level, search_start, empty_size, reloc_src_root, nest); if (IS_ERR(cow)) return PTR_ERR(cow); /* cow is set to blocking by btrfs_init_new_buffer */ copy_extent_buffer_full(cow, buf); btrfs_set_header_bytenr(cow, cow->start); btrfs_set_header_generation(cow, trans->transid); btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV); btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN | BTRFS_HEADER_FLAG_RELOC); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC); else btrfs_set_header_owner(cow, btrfs_root_id(root)); write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid); ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); if (ret) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (ret) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } if (buf == root->node) { WARN_ON(parent && parent != buf); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID || btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) parent_start = buf->start; ret = btrfs_tree_mod_log_insert_root(root->node, cow, true); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } atomic_inc(&cow->refs); rcu_assign_pointer(root->node, cow); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf, parent_start, last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } else { WARN_ON(trans->transid != btrfs_header_generation(parent)); ret = btrfs_tree_mod_log_insert_key(parent, parent_slot, BTRFS_MOD_LOG_KEY_REPLACE); if (ret) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } btrfs_set_node_blockptr(parent, parent_slot, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); btrfs_mark_buffer_dirty(trans, parent); if (last_ref) { ret = btrfs_tree_mod_log_free_eb(buf); if (ret) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf, parent_start, last_ref); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; error_unlock_cow: btrfs_tree_unlock(cow); free_extent_buffer(cow); return ret; } static inline int should_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf) { if (btrfs_is_testing(root->fs_info)) return 0; /* Ensure we can see the FORCE_COW bit */ smp_mb__before_atomic(); /* * We do not need to cow a block if * 1) this block is not created or changed in this transaction; * 2) this block does not belong to TREE_RELOC tree; * 3) the root is not forced COW. * * What is forced COW: * when we create snapshot during committing the transaction, * after we've finished copying src root, we must COW the shared * block to ensure the metadata consistency. */ if (btrfs_header_generation(buf) == trans->transid && !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) && !(btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) && !test_bit(BTRFS_ROOT_FORCE_COW, &root->state)) return 0; return 1; } /* * COWs a single block, see btrfs_force_cow_block() for the real work. * This version of it has extra checks so that a block isn't COWed more than * once per transaction, as long as it hasn't been written yet */ int btrfs_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); btrfs_crit(fs_info, "attempt to COW block %llu on root %llu that is being deleted", buf->start, btrfs_root_id(root)); return -EUCLEAN; } /* * COWing must happen through a running transaction, which always * matches the current fs generation (it's a transaction with a state * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs * into error state to prevent the commit of any transaction. */ if (unlikely(trans->transaction != fs_info->running_transaction || trans->transid != fs_info->generation)) { btrfs_abort_transaction(trans, -EUCLEAN); btrfs_crit(fs_info, "unexpected transaction when attempting to COW block %llu on root %llu, transaction %llu running transaction %llu fs generation %llu", buf->start, btrfs_root_id(root), trans->transid, fs_info->running_transaction->transid, fs_info->generation); return -EUCLEAN; } if (!should_cow_block(trans, root, buf)) { *cow_ret = buf; return 0; } search_start = round_down(buf->start, SZ_1G); /* * Before CoWing this block for later modification, check if it's * the subtree root and do the delayed subtree trace if needed. * * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); /* * same as comp_keys only with two btrfs_key's */ int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) { if (k1->objectid > k2->objectid) return 1; if (k1->objectid < k2->objectid) return -1; if (k1->type > k2->type) return 1; if (k1->type < k2->type) return -1; if (k1->offset > k2->offset) return 1; if (k1->offset < k2->offset) return -1; return 0; } /* * Search for a key in the given extent_buffer. * * The lower boundary for the search is specified by the slot number @first_slot. * Use a value of 0 to search over the whole extent buffer. Works for both * leaves and nodes. * * The slot in the extent buffer is returned via @slot. If the key exists in the * extent buffer, then @slot will point to the slot where the key is, otherwise * it points to the slot where you would insert the key. * * Slot may point to the total number of items (i.e. one position beyond the last * key) if the key is bigger than the last key in the extent buffer. */ int btrfs_bin_search(struct extent_buffer *eb, int first_slot, const struct btrfs_key *key, int *slot) { unsigned long p; int item_size; /* * Use unsigned types for the low and high slots, so that we get a more * efficient division in the search loop below. */ u32 low = first_slot; u32 high = btrfs_header_nritems(eb); int ret; const int key_size = sizeof(struct btrfs_disk_key); if (unlikely(low > high)) { btrfs_err(eb->fs_info, "%s: low (%u) > high (%u) eb %llu owner %llu level %d", __func__, low, high, eb->start, btrfs_header_owner(eb), btrfs_header_level(eb)); return -EINVAL; } if (btrfs_header_level(eb) == 0) { p = offsetof(struct btrfs_leaf, items); item_size = sizeof(struct btrfs_item); } else { p = offsetof(struct btrfs_node, ptrs); item_size = sizeof(struct btrfs_key_ptr); } while (low < high) { const int unit_size = eb->folio_size; unsigned long oil; unsigned long offset; struct btrfs_disk_key *tmp; struct btrfs_disk_key unaligned; int mid; mid = (low + high) / 2; offset = p + mid * item_size; oil = get_eb_offset_in_folio(eb, offset); if (oil + key_size <= unit_size) { const unsigned long idx = get_eb_folio_index(eb, offset); char *kaddr = folio_address(eb->folios[idx]); oil = get_eb_offset_in_folio(eb, offset); tmp = (struct btrfs_disk_key *)(kaddr + oil); } else { read_extent_buffer(eb, &unaligned, offset, key_size); tmp = &unaligned; } ret = btrfs_comp_keys(tmp, key); if (ret < 0) low = mid + 1; else if (ret > 0) high = mid; else { *slot = mid; return 0; } } *slot = low; return 1; } static void root_add_used_bytes(struct btrfs_root *root) { spin_lock(&root->accounting_lock); btrfs_set_root_used(&root->root_item, btrfs_root_used(&root->root_item) + root->fs_info->nodesize); spin_unlock(&root->accounting_lock); } static void root_sub_used_bytes(struct btrfs_root *root) { spin_lock(&root->accounting_lock); btrfs_set_root_used(&root->root_item, btrfs_root_used(&root->root_item) - root->fs_info->nodesize); spin_unlock(&root->accounting_lock); } /* given a node and slot number, this reads the blocks it points to. The * extent buffer is returned with a reference taken (but unlocked). */ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent, int slot) { int level = btrfs_header_level(parent); struct btrfs_tree_parent_check check = { 0 }; struct extent_buffer *eb; if (slot < 0 || slot >= btrfs_header_nritems(parent)) return ERR_PTR(-ENOENT); ASSERT(level); check.level = level - 1; check.transid = btrfs_node_ptr_generation(parent, slot); check.owner_root = btrfs_header_owner(parent); check.has_first_key = true; btrfs_node_key_to_cpu(parent, &check.first_key, slot); eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot), &check); if (IS_ERR(eb)) return eb; if (!extent_buffer_uptodate(eb)) { free_extent_buffer(eb); return ERR_PTR(-EIO); } return eb; } /* * node level balancing, used to make sure nodes are in proper order for * item deletion. We balance from the top down, so we have to make sure * that a deletion won't leave an node completely empty later on. */ static noinline int balance_level(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *right = NULL; struct extent_buffer *mid; struct extent_buffer *left = NULL; struct extent_buffer *parent = NULL; int ret = 0; int wret; int pslot; int orig_slot = path->slots[level]; u64 orig_ptr; ASSERT(level > 0); mid = path->nodes[level]; WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK); WARN_ON(btrfs_header_generation(mid) != trans->transid); orig_ptr = btrfs_node_blockptr(mid, orig_slot); if (level < BTRFS_MAX_LEVEL - 1) { parent = path->nodes[level + 1]; pslot = path->slots[level + 1]; } /* * deal with the case where there is only one pointer in the root * by promoting the node below to a root */ if (!parent) { struct extent_buffer *child; if (btrfs_header_nritems(mid) != 1) return 0; /* promote the child to a root */ child = btrfs_read_node_slot(mid, 0); if (IS_ERR(child)) { ret = PTR_ERR(child); goto out; } btrfs_tree_lock(child); ret = btrfs_cow_block(trans, root, child, mid, 0, &child, BTRFS_NESTING_COW); if (ret) { btrfs_tree_unlock(child); free_extent_buffer(child); goto out; } ret = btrfs_tree_mod_log_insert_root(root->node, child, true); if (ret < 0) { btrfs_tree_unlock(child); free_extent_buffer(child); btrfs_abort_transaction(trans, ret); goto out; } rcu_assign_pointer(root->node, child); add_root_to_dirty_list(root); btrfs_tree_unlock(child); path->locks[level] = 0; path->nodes[level] = NULL; btrfs_clear_buffer_dirty(trans, mid); btrfs_tree_unlock(mid); /* once for the path */ free_extent_buffer(mid); root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } return 0; } if (btrfs_header_nritems(mid) > BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 4) return 0; if (pslot) { left = btrfs_read_node_slot(parent, pslot - 1); if (IS_ERR(left)) { ret = PTR_ERR(left); left = NULL; goto out; } btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); wret = btrfs_cow_block(trans, root, left, parent, pslot - 1, &left, BTRFS_NESTING_LEFT_COW); if (wret) { ret = wret; goto out; } } if (pslot + 1 < btrfs_header_nritems(parent)) { right = btrfs_read_node_slot(parent, pslot + 1); if (IS_ERR(right)) { ret = PTR_ERR(right); right = NULL; goto out; } btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); wret = btrfs_cow_block(trans, root, right, parent, pslot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (wret) { ret = wret; goto out; } } /* first, try to make some room in the middle buffer */ if (left) { orig_slot += btrfs_header_nritems(left); wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } /* * then try to empty the right most buffer into the middle */ if (right) { wret = push_node_left(trans, mid, right, 1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (btrfs_header_nritems(right) == 0) { btrfs_clear_buffer_dirty(trans, right); btrfs_tree_unlock(right); ret = btrfs_del_ptr(trans, root, path, level + 1, pslot + 1); if (ret < 0) { free_extent_buffer_stale(right); right = NULL; goto out; } root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), right, 0, 1); free_extent_buffer_stale(right); right = NULL; if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } } else { struct btrfs_disk_key right_key; btrfs_node_key(right, &right_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_set_node_key(parent, &right_key, pslot + 1); btrfs_mark_buffer_dirty(trans, parent); } } if (btrfs_header_nritems(mid) == 1) { /* * we're not allowed to leave a node with one item in the * tree during a delete. A deletion from lower in the tree * could try to delete the only pointer in this node. * So, pull some keys from the left. * There has to be a left pointer at this point because * otherwise we would have pulled some pointers from the * right */ if (unlikely(!left)) { btrfs_crit(fs_info, "missing left child when middle child only has 1 item, parent bytenr %llu level %d mid bytenr %llu root %llu", parent->start, btrfs_header_level(parent), mid->start, btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); goto out; } wret = balance_node_right(trans, mid, left); if (wret < 0) { ret = wret; goto out; } if (wret == 1) { wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } BUG_ON(wret == 1); } if (btrfs_header_nritems(mid) == 0) { btrfs_clear_buffer_dirty(trans, mid); btrfs_tree_unlock(mid); ret = btrfs_del_ptr(trans, root, path, level + 1, pslot); if (ret < 0) { free_extent_buffer_stale(mid); mid = NULL; goto out; } root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } } else { /* update the parent key to reflect our changes */ struct btrfs_disk_key mid_key; btrfs_node_key(mid, &mid_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_set_node_key(parent, &mid_key, pslot); btrfs_mark_buffer_dirty(trans, parent); } /* update the path */ if (left) { if (btrfs_header_nritems(left) > orig_slot) { atomic_inc(&left->refs); /* left was locked after cow */ path->nodes[level] = left; path->slots[level + 1] -= 1; path->slots[level] = orig_slot; if (mid) { btrfs_tree_unlock(mid); free_extent_buffer(mid); } } else { orig_slot -= btrfs_header_nritems(left); path->slots[level] = orig_slot; } } /* double check we haven't messed things up */ if (orig_ptr != btrfs_node_blockptr(path->nodes[level], path->slots[level])) BUG(); out: if (right) { btrfs_tree_unlock(right); free_extent_buffer(right); } if (left) { if (path->nodes[level] != left) btrfs_tree_unlock(left); free_extent_buffer(left); } return ret; } /* Node balancing for insertion. Here we only split or push nodes around * when they are completely full. This is also done top down, so we * have to be pessimistic. */ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *right = NULL; struct extent_buffer *mid; struct extent_buffer *left = NULL; struct extent_buffer *parent = NULL; int ret = 0; int wret; int pslot; int orig_slot = path->slots[level]; if (level == 0) return 1; mid = path->nodes[level]; WARN_ON(btrfs_header_generation(mid) != trans->transid); if (level < BTRFS_MAX_LEVEL - 1) { parent = path->nodes[level + 1]; pslot = path->slots[level + 1]; } if (!parent) return 1; /* first, try to make some room in the middle buffer */ if (pslot) { u32 left_nr; left = btrfs_read_node_slot(parent, pslot - 1); if (IS_ERR(left)) return PTR_ERR(left); btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); left_nr = btrfs_header_nritems(left); if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { wret = 1; } else { ret = btrfs_cow_block(trans, root, left, parent, pslot - 1, &left, BTRFS_NESTING_LEFT_COW); if (ret) wret = 1; else { wret = push_node_left(trans, left, mid, 0); } } if (wret < 0) ret = wret; if (wret == 0) { struct btrfs_disk_key disk_key; orig_slot += left_nr; btrfs_node_key(mid, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); if (ret < 0) { btrfs_tree_unlock(left); free_extent_buffer(left); btrfs_abort_transaction(trans, ret); return ret; } btrfs_set_node_key(parent, &disk_key, pslot); btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(left) > orig_slot) { path->nodes[level] = left; path->slots[level + 1] -= 1; path->slots[level] = orig_slot; btrfs_tree_unlock(mid); free_extent_buffer(mid); } else { orig_slot -= btrfs_header_nritems(left); path->slots[level] = orig_slot; btrfs_tree_unlock(left); free_extent_buffer(left); } return 0; } btrfs_tree_unlock(left); free_extent_buffer(left); } /* * then try to empty the right most buffer into the middle */ if (pslot + 1 < btrfs_header_nritems(parent)) { u32 right_nr; right = btrfs_read_node_slot(parent, pslot + 1); if (IS_ERR(right)) return PTR_ERR(right); btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); right_nr = btrfs_header_nritems(right); if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { wret = 1; } else { ret = btrfs_cow_block(trans, root, right, parent, pslot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (ret) wret = 1; else { wret = balance_node_right(trans, right, mid); } } if (wret < 0) ret = wret; if (wret == 0) { struct btrfs_disk_key disk_key; btrfs_node_key(right, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); btrfs_abort_transaction(trans, ret); return ret; } btrfs_set_node_key(parent, &disk_key, pslot + 1); btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(mid) <= orig_slot) { path->nodes[level] = right; path->slots[level + 1] += 1; path->slots[level] = orig_slot - btrfs_header_nritems(mid); btrfs_tree_unlock(mid); free_extent_buffer(mid); } else { btrfs_tree_unlock(right); free_extent_buffer(right); } return 0; } btrfs_tree_unlock(right); free_extent_buffer(right); } return 1; } /* * readahead one full node of leaves, finding things that are close * to the block in 'slot', and triggering ra on them. */ static void reada_for_search(struct btrfs_fs_info *fs_info, struct btrfs_path *path, int level, int slot, u64 objectid) { struct extent_buffer *node; struct btrfs_disk_key disk_key; u32 nritems; u64 search; u64 target; u64 nread = 0; u64 nread_max; u32 nr; u32 blocksize; u32 nscan = 0; if (level != 1 && path->reada != READA_FORWARD_ALWAYS) return; if (!path->nodes[level]) return; node = path->nodes[level]; /* * Since the time between visiting leaves is much shorter than the time * between visiting nodes, limit read ahead of nodes to 1, to avoid too * much IO at once (possibly random). */ if (path->reada == READA_FORWARD_ALWAYS) { if (level > 1) nread_max = node->fs_info->nodesize; else nread_max = SZ_128K; } else { nread_max = SZ_64K; } search = btrfs_node_blockptr(node, slot); blocksize = fs_info->nodesize; if (path->reada != READA_FORWARD_ALWAYS) { struct extent_buffer *eb; eb = find_extent_buffer(fs_info, search); if (eb) { free_extent_buffer(eb); return; } } target = search; nritems = btrfs_header_nritems(node); nr = slot; while (1) { if (path->reada == READA_BACK) { if (nr == 0) break; nr--; } else if (path->reada == READA_FORWARD || path->reada == READA_FORWARD_ALWAYS) { nr++; if (nr >= nritems) break; } if (path->reada == READA_BACK && objectid) { btrfs_node_key(node, &disk_key, nr); if (btrfs_disk_key_objectid(&disk_key) != objectid) break; } search = btrfs_node_blockptr(node, nr); if (path->reada == READA_FORWARD_ALWAYS || (search <= target && target - search <= 65536) || (search > target && search - target <= 65536)) { btrfs_readahead_node_child(node, nr); nread += blocksize; } nscan++; if (nread > nread_max || nscan > 32) break; } } static noinline void reada_for_balance(struct btrfs_path *path, int level) { struct extent_buffer *parent; int slot; int nritems; parent = path->nodes[level + 1]; if (!parent) return; nritems = btrfs_header_nritems(parent); slot = path->slots[level + 1]; if (slot > 0) btrfs_readahead_node_child(parent, slot - 1); if (slot + 1 < nritems) btrfs_readahead_node_child(parent, slot + 1); } /* * when we walk down the tree, it is usually safe to unlock the higher layers * in the tree. The exceptions are when our path goes through slot 0, because * operations on the tree might require changing key pointers higher up in the * tree. * * callers might also have set path->keep_locks, which tells this code to keep * the lock if the path points to the last slot in the block. This is part of * walking through the tree, and selecting the next slot in the higher block. * * lowest_unlock sets the lowest level in the tree we're allowed to unlock. so * if lowest_unlock is 1, level 0 won't be unlocked */ static noinline void unlock_up(struct btrfs_path *path, int level, int lowest_unlock, int min_write_lock_level, int *write_lock_level) { int i; int skip_level = level; bool check_skip = true; for (i = level; i < BTRFS_MAX_LEVEL; i++) { if (!path->nodes[i]) break; if (!path->locks[i]) break; if (check_skip) { if (path->slots[i] == 0) { skip_level = i + 1; continue; } if (path->keep_locks) { u32 nritems; nritems = btrfs_header_nritems(path->nodes[i]); if (nritems < 1 || path->slots[i] >= nritems - 1) { skip_level = i + 1; continue; } } } if (i >= lowest_unlock && i > skip_level) { check_skip = false; btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]); path->locks[i] = 0; if (write_lock_level && i > min_write_lock_level && i <= *write_lock_level) { *write_lock_level = i - 1; } } } } /* * Helper function for btrfs_search_slot() and other functions that do a search * on a btree. The goal is to find a tree block in the cache (the radix tree at * fs_info->buffer_radix), but if we can't find it, or it's not up to date, read * its pages from disk. * * Returns -EAGAIN, with the path unlocked, if the caller needs to repeat the * whole btree search, starting again from the current root node. */ static int read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, struct extent_buffer **eb_ret, int slot, const struct btrfs_key *key) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_tree_parent_check check = { 0 }; u64 blocknr; struct extent_buffer *tmp = NULL; int ret = 0; int parent_level; int err; bool read_tmp = false; bool tmp_locked = false; bool path_released = false; blocknr = btrfs_node_blockptr(*eb_ret, slot); parent_level = btrfs_header_level(*eb_ret); btrfs_node_key_to_cpu(*eb_ret, &check.first_key, slot); check.has_first_key = true; check.level = parent_level - 1; check.transid = btrfs_node_ptr_generation(*eb_ret, slot); check.owner_root = btrfs_root_id(root); /* * If we need to read an extent buffer from disk and we are holding locks * on upper level nodes, we unlock all the upper nodes before reading the * extent buffer, and then return -EAGAIN to the caller as it needs to * restart the search. We don't release the lock on the current level * because we need to walk this node to figure out which blocks to read. */ tmp = find_extent_buffer(fs_info, blocknr); if (tmp) { if (p->reada == READA_FORWARD_ALWAYS) reada_for_search(fs_info, p, parent_level, slot, key->objectid); /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, check.transid, 1) > 0) { /* * Do extra check for first_key, eb can be stale due to * being cached, read from scrub, or have multiple * parents (shared tree blocks). */ if (btrfs_verify_level_key(tmp, &check)) { ret = -EUCLEAN; goto out; } *eb_ret = tmp; tmp = NULL; ret = 0; goto out; } if (p->nowait) { ret = -EAGAIN; goto out; } if (!p->skip_locking) { btrfs_unlock_up_safe(p, parent_level + 1); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); ret = -EAGAIN; path_released = true; } /* Now we're allowed to do a blocking uptodate check. */ err = btrfs_read_extent_buffer(tmp, &check); if (err) { ret = err; goto out; } if (ret == 0) { ASSERT(!tmp_locked); *eb_ret = tmp; tmp = NULL; } goto out; } else if (p->nowait) { ret = -EAGAIN; goto out; } if (!p->skip_locking) { btrfs_unlock_up_safe(p, parent_level + 1); ret = -EAGAIN; } if (p->reada != READA_NONE) reada_for_search(fs_info, p, parent_level, slot, key->objectid); tmp = btrfs_find_create_tree_block(fs_info, blocknr, check.owner_root, check.level); if (IS_ERR(tmp)) { ret = PTR_ERR(tmp); tmp = NULL; goto out; } read_tmp = true; if (!p->skip_locking) { ASSERT(ret == -EAGAIN); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); path_released = true; } /* Now we're allowed to do a blocking uptodate check. */ err = btrfs_read_extent_buffer(tmp, &check); if (err) { ret = err; goto out; } /* * If the read above didn't mark this buffer up to date, * it will never end up being up to date. Set ret to EIO now * and give up so that our caller doesn't loop forever * on our EAGAINs. */ if (!extent_buffer_uptodate(tmp)) { ret = -EIO; goto out; } if (ret == 0) { ASSERT(!tmp_locked); *eb_ret = tmp; tmp = NULL; } out: if (tmp) { if (tmp_locked) btrfs_tree_read_unlock(tmp); if (read_tmp && ret && ret != -EAGAIN) free_extent_buffer_stale(tmp); else free_extent_buffer(tmp); } if (ret && !path_released) btrfs_release_path(p); return ret; } /* * helper function for btrfs_search_slot. This does all of the checks * for node-level blocks and does any balancing required based on * the ins_len. * * If no extra work was required, zero is returned. If we had to * drop the path, -EAGAIN is returned and btrfs_search_slot must * start over */ static int setup_nodes_for_search(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *p, struct extent_buffer *b, int level, int ins_len, int *write_lock_level) { struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) { if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); return -EAGAIN; } reada_for_balance(p, level); ret = split_node(trans, root, p, level); b = p->nodes[level]; } else if (ins_len < 0 && btrfs_header_nritems(b) < BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 2) { if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); return -EAGAIN; } reada_for_balance(p, level); ret = balance_level(trans, root, p, level); if (ret) return ret; b = p->nodes[level]; if (!b) { btrfs_release_path(p); return -EAGAIN; } BUG_ON(btrfs_header_nritems(b) == 1); } return ret; } int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 iobjectid, u64 ioff, u8 key_type, struct btrfs_key *found_key) { int ret; struct btrfs_key key; struct extent_buffer *eb; ASSERT(path); ASSERT(found_key); key.type = key_type; key.objectid = iobjectid; key.offset = ioff; ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); if (ret < 0) return ret; eb = path->nodes[0]; if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { ret = btrfs_next_leaf(fs_root, path); if (ret) return ret; eb = path->nodes[0]; } btrfs_item_key_to_cpu(eb, found_key, path->slots[0]); if (found_key->type != key.type || found_key->objectid != key.objectid) return 1; return 0; } static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root, struct btrfs_path *p, int write_lock_level) { struct extent_buffer *b; int root_lock = 0; int level = 0; if (p->search_commit_root) { b = root->commit_root; atomic_inc(&b->refs); level = btrfs_header_level(b); /* * Ensure that all callers have set skip_locking when * p->search_commit_root = 1. */ ASSERT(p->skip_locking == 1); goto out; } if (p->skip_locking) { b = btrfs_root_node(root); level = btrfs_header_level(b); goto out; } /* We try very hard to do read locks on the root */ root_lock = BTRFS_READ_LOCK; /* * If the level is set to maximum, we can skip trying to get the read * lock. */ if (write_lock_level < BTRFS_MAX_LEVEL) { /* * We don't know the level of the root node until we actually * have it read locked */ if (p->nowait) { b = btrfs_try_read_lock_root_node(root); if (IS_ERR(b)) return b; } else { b = btrfs_read_lock_root_node(root); } level = btrfs_header_level(b); if (level > write_lock_level) goto out; /* Whoops, must trade for write lock */ btrfs_tree_read_unlock(b); free_extent_buffer(b); } b = btrfs_lock_root_node(root); root_lock = BTRFS_WRITE_LOCK; /* The level might have changed, check again */ level = btrfs_header_level(b); out: /* * The root may have failed to write out at some point, and thus is no * longer valid, return an error in this case. */ if (!extent_buffer_uptodate(b)) { if (root_lock) btrfs_tree_unlock_rw(b, root_lock); free_extent_buffer(b); return ERR_PTR(-EIO); } p->nodes[level] = b; if (!p->skip_locking) p->locks[level] = root_lock; /* * Callers are responsible for dropping b's references. */ return b; } /* * Replace the extent buffer at the lowest level of the path with a cloned * version. The purpose is to be able to use it safely, after releasing the * commit root semaphore, even if relocation is happening in parallel, the * transaction used for relocation is committed and the extent buffer is * reallocated in the next transaction. * * This is used in a context where the caller does not prevent transaction * commits from happening, either by holding a transaction handle or holding * some lock, while it's doing searches through a commit root. * At the moment it's only used for send operations. */ static int finish_need_commit_sem_search(struct btrfs_path *path) { const int i = path->lowest_level; const int slot = path->slots[i]; struct extent_buffer *lowest = path->nodes[i]; struct extent_buffer *clone; ASSERT(path->need_commit_sem); if (!lowest) return 0; lockdep_assert_held_read(&lowest->fs_info->commit_root_sem); clone = btrfs_clone_extent_buffer(lowest); if (!clone) return -ENOMEM; btrfs_release_path(path); path->nodes[i] = clone; path->slots[i] = slot; return 0; } static inline int search_for_key_slot(struct extent_buffer *eb, int search_low_slot, const struct btrfs_key *key, int prev_cmp, int *slot) { /* * If a previous call to btrfs_bin_search() on a parent node returned an * exact match (prev_cmp == 0), we can safely assume the target key will * always be at slot 0 on lower levels, since each key pointer * (struct btrfs_key_ptr) refers to the lowest key accessible from the * subtree it points to. Thus we can skip searching lower levels. */ if (prev_cmp == 0) { *slot = 0; return 0; } return btrfs_bin_search(eb, search_low_slot, key, slot); } static int search_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *path, int ins_len, int prev_cmp) { struct extent_buffer *leaf = path->nodes[0]; int leaf_free_space = -1; int search_low_slot = 0; int ret; bool do_bin_search = true; /* * If we are doing an insertion, the leaf has enough free space and the * destination slot for the key is not slot 0, then we can unlock our * write lock on the parent, and any other upper nodes, before doing the * binary search on the leaf (with search_for_key_slot()), allowing other * tasks to lock the parent and any other upper nodes. */ if (ins_len > 0) { /* * Cache the leaf free space, since we will need it later and it * will not change until then. */ leaf_free_space = btrfs_leaf_free_space(leaf); /* * !path->locks[1] means we have a single node tree, the leaf is * the root of the tree. */ if (path->locks[1] && leaf_free_space >= ins_len) { struct btrfs_disk_key first_key; ASSERT(btrfs_header_nritems(leaf) > 0); btrfs_item_key(leaf, &first_key, 0); /* * Doing the extra comparison with the first key is cheap, * taking into account that the first key is very likely * already in a cache line because it immediately follows * the extent buffer's header and we have recently accessed * the header's level field. */ ret = btrfs_comp_keys(&first_key, key); if (ret < 0) { /* * The first key is smaller than the key we want * to insert, so we are safe to unlock all upper * nodes and we have to do the binary search. * * We do use btrfs_unlock_up_safe() and not * unlock_up() because the later does not unlock * nodes with a slot of 0 - we can safely unlock * any node even if its slot is 0 since in this * case the key does not end up at slot 0 of the * leaf and there's no need to split the leaf. */ btrfs_unlock_up_safe(path, 1); search_low_slot = 1; } else { /* * The first key is >= then the key we want to * insert, so we can skip the binary search as * the target key will be at slot 0. * * We can not unlock upper nodes when the key is * less than the first key, because we will need * to update the key at slot 0 of the parent node * and possibly of other upper nodes too. * If the key matches the first key, then we can * unlock all the upper nodes, using * btrfs_unlock_up_safe() instead of unlock_up() * as stated above. */ if (ret == 0) btrfs_unlock_up_safe(path, 1); /* * ret is already 0 or 1, matching the result of * a btrfs_bin_search() call, so there is no need * to adjust it. */ do_bin_search = false; path->slots[0] = 0; } } } if (do_bin_search) { ret = search_for_key_slot(leaf, search_low_slot, key, prev_cmp, &path->slots[0]); if (ret < 0) return ret; } if (ins_len > 0) { /* * Item key already exists. In this case, if we are allowed to * insert the item (for example, in dir_item case, item key * collision is allowed), it will be merged with the original * item. Only the item size grows, no new btrfs item will be * added. If search_for_extension is not set, ins_len already * accounts the size btrfs_item, deduct it here so leaf space * check will be correct. */ if (ret == 0 && !path->search_for_extension) { ASSERT(ins_len >= sizeof(struct btrfs_item)); ins_len -= sizeof(struct btrfs_item); } ASSERT(leaf_free_space >= 0); if (leaf_free_space < ins_len) { int err; err = split_leaf(trans, root, key, path, ins_len, (ret == 0)); ASSERT(err <= 0); if (WARN_ON(err > 0)) err = -EUCLEAN; if (err) ret = err; } } return ret; } /* * Look for a key in a tree and perform necessary modifications to preserve * tree invariants. * * @trans: Handle of transaction, used when modifying the tree * @p: Holds all btree nodes along the search path * @root: The root node of the tree * @key: The key we are looking for * @ins_len: Indicates purpose of search: * >0 for inserts it's size of item inserted (*) * <0 for deletions * 0 for plain searches, not modifying the tree * * (*) If size of item inserted doesn't include * sizeof(struct btrfs_item), then p->search_for_extension must * be set. * @cow: boolean should CoW operations be performed. Must always be 1 * when modifying the tree. * * If @ins_len > 0, nodes and leaves will be split as we walk down the tree. * If @ins_len < 0, nodes will be merged as we walk down the tree (if possible) * * If @key is found, 0 is returned and you can find the item in the leaf level * of the path (level 0) * * If @key isn't found, 1 is returned and the leaf level of the path (level 0) * points to the slot where it should be inserted * * If an error is encountered while searching the tree a negative error number * is returned */ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { struct btrfs_fs_info *fs_info; struct extent_buffer *b; int slot; int ret; int err; int level; int lowest_unlock = 1; /* everything at write_lock_level or lower must be write locked */ int write_lock_level = 0; u8 lowest_level = 0; int min_write_lock_level; int prev_cmp; if (!root) return -EINVAL; fs_info = root->fs_info; might_sleep(); lowest_level = p->lowest_level; WARN_ON(lowest_level && ins_len > 0); WARN_ON(p->nodes[0] != NULL); BUG_ON(!cow && ins_len); /* * For now only allow nowait for read only operations. There's no * strict reason why we can't, we just only need it for reads so it's * only implemented for reads. */ ASSERT(!p->nowait || !cow); if (ins_len < 0) { lowest_unlock = 2; /* when we are removing items, we might have to go up to level * two as we update tree pointers Make sure we keep write * for those levels as well */ write_lock_level = 2; } else if (ins_len > 0) { /* * for inserting items, make sure we have a write lock on * level 1 so we can update keys */ write_lock_level = 1; } if (!cow) write_lock_level = -1; if (cow && (p->keep_locks || p->lowest_level)) write_lock_level = BTRFS_MAX_LEVEL; min_write_lock_level = write_lock_level; if (p->need_commit_sem) { ASSERT(p->search_commit_root); if (p->nowait) { if (!down_read_trylock(&fs_info->commit_root_sem)) return -EAGAIN; } else { down_read(&fs_info->commit_root_sem); } } again: prev_cmp = -1; b = btrfs_search_slot_get_root(root, p, write_lock_level); if (IS_ERR(b)) { ret = PTR_ERR(b); goto done; } while (b) { int dec = 0; level = btrfs_header_level(b); if (cow) { bool last_level = (level == (BTRFS_MAX_LEVEL - 1)); /* * if we don't really need to cow this block * then we don't want to set the path blocking, * so we test it here */ if (!should_cow_block(trans, root, b)) goto cow_done; /* * must have write locks on this node and the * parent */ if (level > write_lock_level || (level + 1 > write_lock_level && level + 1 < BTRFS_MAX_LEVEL && p->nodes[level + 1])) { write_lock_level = level + 1; btrfs_release_path(p); goto again; } if (last_level) err = btrfs_cow_block(trans, root, b, NULL, 0, &b, BTRFS_NESTING_COW); else err = btrfs_cow_block(trans, root, b, p->nodes[level + 1], p->slots[level + 1], &b, BTRFS_NESTING_COW); if (err) { ret = err; goto done; } } cow_done: p->nodes[level] = b; /* * we have a lock on b and as long as we aren't changing * the tree, there is no way to for the items in b to change. * It is safe to drop the lock on our parent before we * go through the expensive btree search on b. * * If we're inserting or deleting (ins_len != 0), then we might * be changing slot zero, which may require changing the parent. * So, we can't drop the lock until after we know which slot * we're operating on. */ if (!ins_len && !p->keep_locks) { int u = level + 1; if (u < BTRFS_MAX_LEVEL && p->locks[u]) { btrfs_tree_unlock_rw(p->nodes[u], p->locks[u]); p->locks[u] = 0; } } if (level == 0) { if (ins_len > 0) ASSERT(write_lock_level >= 1); ret = search_leaf(trans, root, key, p, ins_len, prev_cmp); if (!p->search_for_split) unlock_up(p, level, lowest_unlock, min_write_lock_level, NULL); goto done; } ret = search_for_key_slot(b, 0, key, prev_cmp, &slot); if (ret < 0) goto done; prev_cmp = ret; if (ret && slot > 0) { dec = 1; slot--; } p->slots[level] = slot; err = setup_nodes_for_search(trans, root, p, b, level, ins_len, &write_lock_level); if (err == -EAGAIN) goto again; if (err) { ret = err; goto done; } b = p->nodes[level]; slot = p->slots[level]; /* * Slot 0 is special, if we change the key we have to update * the parent pointer which means we must have a write lock on * the parent */ if (slot == 0 && ins_len && write_lock_level < level + 1) { write_lock_level = level + 1; btrfs_release_path(p); goto again; } unlock_up(p, level, lowest_unlock, min_write_lock_level, &write_lock_level); if (level == lowest_level) { if (dec) p->slots[level]++; goto done; } err = read_block_for_search(root, p, &b, slot, key); if (err == -EAGAIN && !p->nowait) goto again; if (err) { ret = err; goto done; } if (!p->skip_locking) { level = btrfs_header_level(b); btrfs_maybe_reset_lockdep_class(root, b); if (level <= write_lock_level) { btrfs_tree_lock(b); p->locks[level] = BTRFS_WRITE_LOCK; } else { if (p->nowait) { if (!btrfs_try_tree_read_lock(b)) { free_extent_buffer(b); ret = -EAGAIN; goto done; } } else { btrfs_tree_read_lock(b); } p->locks[level] = BTRFS_READ_LOCK; } p->nodes[level] = b; } } ret = 1; done: if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); if (p->need_commit_sem) { int ret2; ret2 = finish_need_commit_sem_search(p); up_read(&fs_info->commit_root_sem); if (ret2) ret = ret2; } return ret; } ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO); /* * Like btrfs_search_slot, this looks for a key in the given tree. It uses the * current state of the tree together with the operations recorded in the tree * modification log to search for the key in a previous version of this tree, as * denoted by the time_seq parameter. * * Naturally, there is no support for insert, delete or cow operations. * * The resulting path and return value will be set up as if we called * btrfs_search_slot at that point in time with ins_len and cow both set to 0. */ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, u64 time_seq) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *b; int slot; int ret; int err; int level; int lowest_unlock = 1; u8 lowest_level = 0; lowest_level = p->lowest_level; WARN_ON(p->nodes[0] != NULL); ASSERT(!p->nowait); if (p->search_commit_root) { BUG_ON(time_seq); return btrfs_search_slot(NULL, root, key, p, 0, 0); } again: b = btrfs_get_old_root(root, time_seq); if (!b) { ret = -EIO; goto done; } level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; while (b) { int dec = 0; level = btrfs_header_level(b); p->nodes[level] = b; /* * we have a lock on b and as long as we aren't changing * the tree, there is no way to for the items in b to change. * It is safe to drop the lock on our parent before we * go through the expensive btree search on b. */ btrfs_unlock_up_safe(p, level + 1); ret = btrfs_bin_search(b, 0, key, &slot); if (ret < 0) goto done; if (level == 0) { p->slots[level] = slot; unlock_up(p, level, lowest_unlock, 0, NULL); goto done; } if (ret && slot > 0) { dec = 1; slot--; } p->slots[level] = slot; unlock_up(p, level, lowest_unlock, 0, NULL); if (level == lowest_level) { if (dec) p->slots[level]++; goto done; } err = read_block_for_search(root, p, &b, slot, key); if (err == -EAGAIN && !p->nowait) goto again; if (err) { ret = err; goto done; } level = btrfs_header_level(b); btrfs_tree_read_lock(b); b = btrfs_tree_mod_log_rewind(fs_info, b, time_seq); if (!b) { ret = -ENOMEM; goto done; } p->locks[level] = BTRFS_READ_LOCK; p->nodes[level] = b; } ret = 1; done: if (ret < 0) btrfs_release_path(p); return ret; } /* * Search the tree again to find a leaf with smaller keys. * Returns 0 if it found something. * Returns 1 if there are no smaller keys. * Returns < 0 on error. * * This may release the path, and so you may lose any locks held at the * time you call it. */ static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); orig_key = key; if (key.offset > 0) { key.offset--; } else if (key.type > 0) { key.type--; key.offset = (u64)-1; } else if (key.objectid > 0) { key.objectid--; key.type = (u8)-1; key.offset = (u64)-1; } else { return 1; } btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret <= 0) return ret; /* * Previous key not found. Even if we were at slot 0 of the leaf we had * before releasing the path and calling btrfs_search_slot(), we now may * be in a slot pointing to the same original key - this can happen if * after we released the path, one of more items were moved from a * sibling leaf into the front of the leaf we had due to an insertion * (see push_leaf_right()). * If we hit this case and our slot is > 0 and just decrement the slot * so that the caller does not process the same key again, which may or * may not break the caller, depending on its logic. */ if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); ret = btrfs_comp_keys(&found_key, &orig_key); if (ret == 0) { if (path->slots[0] > 0) { path->slots[0]--; return 0; } /* * At slot 0, same key as before, it means orig_key is * the lowest, leftmost, key in the tree. We're done. */ return 1; } } btrfs_item_key(path->nodes[0], &found_key, 0); ret = btrfs_comp_keys(&found_key, &key); /* * We might have had an item with the previous key in the tree right * before we released our path. And after we released our path, that * item might have been pushed to the first slot (0) of the leaf we * were holding due to a tree balance. Alternatively, an item with the * previous key can exist as the only element of a leaf (big fat item). * Therefore account for these 2 cases, so that our callers (like * btrfs_previous_item) don't miss an existing item with a key matching * the previous key we computed above. */ if (ret <= 0) return 0; return 1; } /* * helper to use instead of search slot if no exact match is needed but * instead the next or previous item should be returned. * When find_higher is true, the next higher item is returned, the next lower * otherwise. * When return_any and find_higher are both true, and no higher item is found, * return the next lower instead. * When return_any is true and find_higher is false, and no lower item is found, * return the next higher instead. * It returns 0 if any item is found, 1 if none is found (tree empty), and * < 0 on error */ int btrfs_search_slot_for_read(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int find_higher, int return_any) { int ret; struct extent_buffer *leaf; again: ret = btrfs_search_slot(NULL, root, key, p, 0, 0); if (ret <= 0) return ret; /* * a return value of 1 means the path is at the position where the * item should be inserted. Normally this is the next bigger item, * but in case the previous item is the last in a leaf, path points * to the first free slot in the previous leaf, i.e. at an invalid * item. */ leaf = p->nodes[0]; if (find_higher) { if (p->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, p); if (ret <= 0) return ret; if (!return_any) return 1; /* * no higher item found, return the next * lower instead */ return_any = 0; find_higher = 0; btrfs_release_path(p); goto again; } } else { if (p->slots[0] == 0) { ret = btrfs_prev_leaf(root, p); if (ret < 0) return ret; if (!ret) { leaf = p->nodes[0]; if (p->slots[0] == btrfs_header_nritems(leaf)) p->slots[0]--; return 0; } if (!return_any) return 1; /* * no lower item found, return the next * higher instead */ return_any = 0; find_higher = 1; btrfs_release_path(p); goto again; } else { --p->slots[0]; } } return 0; } /* * Execute search and call btrfs_previous_item to traverse backwards if the item * was not found. * * Return 0 if found, 1 if not found and < 0 if error. */ int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path) { int ret; ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret > 0) ret = btrfs_previous_item(root, path, key->objectid, key->type); if (ret == 0) btrfs_item_key_to_cpu(path->nodes[0], key, path->slots[0]); return ret; } /* * Search for a valid slot for the given path. * * @root: The root node of the tree. * @key: Will contain a valid item if found. * @path: The starting point to validate the slot. * * Return: 0 if the item is valid * 1 if not found * <0 if error. */ int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path) { if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { int ret; ret = btrfs_next_leaf(root, path); if (ret) return ret; } btrfs_item_key_to_cpu(path->nodes[0], key, path->slots[0]); return 0; } /* * adjust the pointers going up the tree, starting at level * making sure the right key of each node is points to 'key'. * This is used after shifting pointers to the left, so it stops * fixing up pointers when a given leaf/node is not in slot 0 of the * higher levels * */ static void fixup_low_keys(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_disk_key *key, int level) { int i; struct extent_buffer *t; int ret; for (i = level; i < BTRFS_MAX_LEVEL; i++) { int tslot = path->slots[i]; if (!path->nodes[i]) break; t = path->nodes[i]; ret = btrfs_tree_mod_log_insert_key(t, tslot, BTRFS_MOD_LOG_KEY_REPLACE); BUG_ON(ret < 0); btrfs_set_node_key(t, key, tslot); btrfs_mark_buffer_dirty(trans, path->nodes[i]); if (tslot != 0) break; } } /* * update item key. * * This function isn't completely safe. It's the caller's responsibility * that the new key won't break the order */ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_key *new_key) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *eb; int slot; eb = path->nodes[0]; slot = path->slots[0]; if (slot > 0) { btrfs_item_key(eb, &disk_key, slot - 1); if (unlikely(btrfs_comp_keys(&disk_key, new_key) >= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); BUG(); } } if (slot < btrfs_header_nritems(eb) - 1) { btrfs_item_key(eb, &disk_key, slot + 1); if (unlikely(btrfs_comp_keys(&disk_key, new_key) <= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); BUG(); } } btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(eb, &disk_key, slot); btrfs_mark_buffer_dirty(trans, eb); if (slot == 0) fixup_low_keys(trans, path, &disk_key, 1); } /* * Check key order of two sibling extent buffers. * * Return true if something is wrong. * Return false if everything is fine. * * Tree-checker only works inside one tree block, thus the following * corruption can not be detected by tree-checker: * * Leaf @left | Leaf @right * -------------------------------------------------------------- * | 1 | 2 | 3 | 4 | 5 | f6 | | 7 | 8 | * * Key f6 in leaf @left itself is valid, but not valid when the next * key in leaf @right is 7. * This can only be checked at tree block merge time. * And since tree checker has ensured all key order in each tree block * is correct, we only need to bother the last key of @left and the first * key of @right. */ static bool check_sibling_keys(const struct extent_buffer *left, const struct extent_buffer *right) { struct btrfs_key left_last; struct btrfs_key right_first; int level = btrfs_header_level(left); int nr_left = btrfs_header_nritems(left); int nr_right = btrfs_header_nritems(right); /* No key to check in one of the tree blocks */ if (!nr_left || !nr_right) return false; if (level) { btrfs_node_key_to_cpu(left, &left_last, nr_left - 1); btrfs_node_key_to_cpu(right, &right_first, 0); } else { btrfs_item_key_to_cpu(left, &left_last, nr_left - 1); btrfs_item_key_to_cpu(right, &right_first, 0); } if (unlikely(btrfs_comp_cpu_keys(&left_last, &right_first) >= 0)) { btrfs_crit(left->fs_info, "left extent buffer:"); btrfs_print_tree(left, false); btrfs_crit(left->fs_info, "right extent buffer:"); btrfs_print_tree(right, false); btrfs_crit(left->fs_info, "bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)", left_last.objectid, left_last.type, left_last.offset, right_first.objectid, right_first.type, right_first.offset); return true; } return false; } /* * try to push data from one node into the next node left in the * tree. * * returns 0 if some ptrs were pushed left, < 0 if there was some horrible * error, and > 0 if there was no room in the left hand block. */ static int push_node_left(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src, int empty) { struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int src_nritems; int dst_nritems; int ret = 0; src_nritems = btrfs_header_nritems(src); dst_nritems = btrfs_header_nritems(dst); push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems; WARN_ON(btrfs_header_generation(src) != trans->transid); WARN_ON(btrfs_header_generation(dst) != trans->transid); if (!empty && src_nritems <= 8) return 1; if (push_items <= 0) return 1; if (empty) { push_items = min(src_nritems, push_items); if (push_items < src_nritems) { /* leave at least 8 pointers in the node if * we aren't going to empty it */ if (src_nritems - push_items < 8) { if (push_items <= 8) return 1; push_items -= 8; } } } else push_items = min(src_nritems - 8, push_items); /* dst is the left eb, src is the middle eb */ if (check_sibling_keys(dst, src)) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items); if (ret) { btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst, dst_nritems), btrfs_node_key_ptr_offset(src, 0), push_items * sizeof(struct btrfs_key_ptr)); if (push_items < src_nritems) { /* * btrfs_tree_mod_log_eb_copy handles logging the move, so we * don't need to do an explicit tree mod log operation for it. */ memmove_extent_buffer(src, btrfs_node_key_ptr_offset(src, 0), btrfs_node_key_ptr_offset(src, push_items), (src_nritems - push_items) * sizeof(struct btrfs_key_ptr)); } btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); btrfs_mark_buffer_dirty(trans, src); btrfs_mark_buffer_dirty(trans, dst); return ret; } /* * try to push data from one node into the next node right in the * tree. * * returns 0 if some ptrs were pushed, < 0 if there was some horrible * error, and > 0 if there was no room in the right hand block. * * this will only push up to 1/2 the contents of the left node over */ static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src) { struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int max_push; int src_nritems; int dst_nritems; int ret = 0; WARN_ON(btrfs_header_generation(src) != trans->transid); WARN_ON(btrfs_header_generation(dst) != trans->transid); src_nritems = btrfs_header_nritems(src); dst_nritems = btrfs_header_nritems(dst); push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems; if (push_items <= 0) return 1; if (src_nritems < 4) return 1; max_push = src_nritems / 2 + 1; /* don't try to empty the node */ if (max_push >= src_nritems) return 1; if (max_push < push_items) push_items = max_push; /* dst is the right eb, src is the middle eb */ if (check_sibling_keys(src, dst)) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } /* * btrfs_tree_mod_log_eb_copy handles logging the move, so we don't * need to do an explicit tree mod log operation for it. */ memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(dst, push_items), btrfs_node_key_ptr_offset(dst, 0), (dst_nritems) * sizeof(struct btrfs_key_ptr)); ret = btrfs_tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items, push_items); if (ret) { btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst, 0), btrfs_node_key_ptr_offset(src, src_nritems - push_items), push_items * sizeof(struct btrfs_key_ptr)); btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); btrfs_mark_buffer_dirty(trans, src); btrfs_mark_buffer_dirty(trans, dst); return ret; } /* * helper function to insert a new root level in the tree. * A new node is allocated, and a single item is inserted to * point to the existing root * * returns zero on success or < 0 on failure. */ static noinline int insert_new_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { u64 lower_gen; struct extent_buffer *lower; struct extent_buffer *c; struct extent_buffer *old; struct btrfs_disk_key lower_key; int ret; BUG_ON(path->nodes[level]); BUG_ON(path->nodes[level-1] != root->node); lower = path->nodes[level-1]; if (level == 1) btrfs_item_key(lower, &lower_key, 0); else btrfs_node_key(lower, &lower_key, 0); c = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &lower_key, level, root->node->start, 0, 0, BTRFS_NESTING_NEW_ROOT); if (IS_ERR(c)) return PTR_ERR(c); root_add_used_bytes(root); btrfs_set_header_nritems(c, 1); btrfs_set_node_key(c, &lower_key, 0); btrfs_set_node_blockptr(c, 0, lower->start); lower_gen = btrfs_header_generation(lower); WARN_ON(lower_gen != trans->transid); btrfs_set_node_ptr_generation(c, 0, lower_gen); btrfs_mark_buffer_dirty(trans, c); old = root->node; ret = btrfs_tree_mod_log_insert_root(root->node, c, false); if (ret < 0) { int ret2; ret2 = btrfs_free_tree_block(trans, btrfs_root_id(root), c, 0, 1); if (ret2 < 0) btrfs_abort_transaction(trans, ret2); btrfs_tree_unlock(c); free_extent_buffer(c); return ret; } rcu_assign_pointer(root->node, c); /* the super has an extra ref to root->node */ free_extent_buffer(old); add_root_to_dirty_list(root); atomic_inc(&c->refs); path->nodes[level] = c; path->locks[level] = BTRFS_WRITE_LOCK; path->slots[level] = 0; return 0; } /* * worker function to insert a single pointer in a node. * the node should have enough room for the pointer already * * slot and level indicate where you want the key to go, and * blocknr is the block the key points to. */ static int insert_ptr(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_disk_key *key, u64 bytenr, int slot, int level) { struct extent_buffer *lower; int nritems; int ret; BUG_ON(!path->nodes[level]); btrfs_assert_tree_write_locked(path->nodes[level]); lower = path->nodes[level]; nritems = btrfs_header_nritems(lower); BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(trans->fs_info)); if (slot != nritems) { if (level) { ret = btrfs_tree_mod_log_insert_move(lower, slot + 1, slot, nritems - slot); if (ret < 0) { btrfs_abort_transaction(trans, ret); return ret; } } memmove_extent_buffer(lower, btrfs_node_key_ptr_offset(lower, slot + 1), btrfs_node_key_ptr_offset(lower, slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } if (level) { ret = btrfs_tree_mod_log_insert_key(lower, slot, BTRFS_MOD_LOG_KEY_ADD); if (ret < 0) { btrfs_abort_transaction(trans, ret); return ret; } } btrfs_set_node_key(lower, key, slot); btrfs_set_node_blockptr(lower, slot, bytenr); WARN_ON(trans->transid == 0); btrfs_set_node_ptr_generation(lower, slot, trans->transid); btrfs_set_header_nritems(lower, nritems + 1); btrfs_mark_buffer_dirty(trans, lower); return 0; } /* * split the node at the specified level in path in two. * The path is corrected to point to the appropriate node after the split * * Before splitting this tries to make some room in the node by pushing * left and right, if either one works, it returns right away. * * returns 0 on success and < 0 on failure */ static noinline int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *c; struct extent_buffer *split; struct btrfs_disk_key disk_key; int mid; int ret; u32 c_nritems; c = path->nodes[level]; WARN_ON(btrfs_header_generation(c) != trans->transid); if (c == root->node) { /* * trying to split the root, lets make a new one * * tree mod log: We don't log_removal old root in * insert_new_root, because that root buffer will be kept as a * normal node. We are going to log removal of half of the * elements below with btrfs_tree_mod_log_eb_copy(). We're * holding a tree lock on the buffer, which is why we cannot * race with other tree_mod_log users. */ ret = insert_new_root(trans, root, path, level + 1); if (ret) return ret; } else { ret = push_nodes_for_insert(trans, root, path, level); c = path->nodes[level]; if (!ret && btrfs_header_nritems(c) < BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) return 0; if (ret < 0) return ret; } c_nritems = btrfs_header_nritems(c); mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); split = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &disk_key, level, c->start, 0, 0, BTRFS_NESTING_SPLIT); if (IS_ERR(split)) return PTR_ERR(split); root_add_used_bytes(root); ASSERT(btrfs_header_level(c) == level); ret = btrfs_tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid); if (ret) { btrfs_tree_unlock(split); free_extent_buffer(split); btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(split, c, btrfs_node_key_ptr_offset(split, 0), btrfs_node_key_ptr_offset(c, mid), (c_nritems - mid) * sizeof(struct btrfs_key_ptr)); btrfs_set_header_nritems(split, c_nritems - mid); btrfs_set_header_nritems(c, mid); btrfs_mark_buffer_dirty(trans, c); btrfs_mark_buffer_dirty(trans, split); ret = insert_ptr(trans, path, &disk_key, split->start, path->slots[level + 1] + 1, level + 1); if (ret < 0) { btrfs_tree_unlock(split); free_extent_buffer(split); return ret; } if (path->slots[level] >= mid) { path->slots[level] -= mid; btrfs_tree_unlock(c); free_extent_buffer(c); path->nodes[level] = split; path->slots[level + 1] += 1; } else { btrfs_tree_unlock(split); free_extent_buffer(split); } return 0; } /* * how many bytes are required to store the items in a leaf. start * and nr indicate which items in the leaf to check. This totals up the * space used both by the item structs and the item data */ static int leaf_space_used(const struct extent_buffer *l, int start, int nr) { int data_len; int nritems = btrfs_header_nritems(l); int end = min(nritems, start + nr) - 1; if (!nr) return 0; data_len = btrfs_item_offset(l, start) + btrfs_item_size(l, start); data_len = data_len - btrfs_item_offset(l, end); data_len += sizeof(struct btrfs_item) * nr; WARN_ON(data_len < 0); return data_len; } /* * The space between the end of the leaf items and * the start of the leaf data. IOW, how much room * the leaf has left for both items and data */ int btrfs_leaf_free_space(const struct extent_buffer *leaf) { struct btrfs_fs_info *fs_info = leaf->fs_info; int nritems = btrfs_header_nritems(leaf); int ret; ret = BTRFS_LEAF_DATA_SIZE(fs_info) - leaf_space_used(leaf, 0, nritems); if (ret < 0) { btrfs_crit(fs_info, "leaf free space ret %d, leaf data size %lu, used %d nritems %d", ret, (unsigned long) BTRFS_LEAF_DATA_SIZE(fs_info), leaf_space_used(leaf, 0, nritems), nritems); } return ret; } /* * min slot controls the lowest index we're willing to push to the * right. We'll push up to and including min_slot, but no lower */ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *right, int free_space, u32 left_nritems, u32 min_slot) { struct btrfs_fs_info *fs_info = right->fs_info; struct extent_buffer *left = path->nodes[0]; struct extent_buffer *upper = path->nodes[1]; struct btrfs_map_token token; struct btrfs_disk_key disk_key; int slot; u32 i; int push_space = 0; int push_items = 0; u32 nr; u32 right_nritems; u32 data_end; u32 this_item_size; if (empty) nr = 0; else nr = max_t(u32, 1, min_slot); if (path->slots[0] >= left_nritems) push_space += data_size; slot = path->slots[1]; i = left_nritems - 1; while (i >= nr) { if (!empty && push_items > 0) { if (path->slots[0] > i) break; if (path->slots[0] == i) { int space = btrfs_leaf_free_space(left); if (space + push_space * 2 > free_space) break; } } if (path->slots[0] == i) push_space += data_size; this_item_size = btrfs_item_size(left, i); if (this_item_size + sizeof(struct btrfs_item) + push_space > free_space) break; push_items++; push_space += this_item_size + sizeof(struct btrfs_item); if (i == 0) break; i--; } if (push_items == 0) goto out_unlock; WARN_ON(!empty && push_items == left_nritems); /* push left to right */ right_nritems = btrfs_header_nritems(right); push_space = btrfs_item_data_end(left, left_nritems - push_items); push_space -= leaf_data_end(left); /* make room in the right data area */ data_end = leaf_data_end(right); memmove_leaf_data(right, data_end - push_space, data_end, BTRFS_LEAF_DATA_SIZE(fs_info) - data_end); /* copy from the left data area */ copy_leaf_data(right, left, BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, leaf_data_end(left), push_space); memmove_leaf_items(right, push_items, 0, right_nritems); /* copy the items from left to right */ copy_leaf_items(right, left, 0, left_nritems - push_items, push_items); /* update the item pointers */ btrfs_init_map_token(&token, right); right_nritems += push_items; btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(fs_info); for (i = 0; i < right_nritems; i++) { push_space -= btrfs_token_item_size(&token, i); btrfs_set_token_item_offset(&token, i, push_space); } left_nritems -= push_items; btrfs_set_header_nritems(left, left_nritems); if (left_nritems) btrfs_mark_buffer_dirty(trans, left); else btrfs_clear_buffer_dirty(trans, left); btrfs_mark_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); btrfs_set_node_key(upper, &disk_key, slot + 1); btrfs_mark_buffer_dirty(trans, upper); /* then fixup the leaf pointer in the path */ if (path->slots[0] >= left_nritems) { path->slots[0] -= left_nritems; if (btrfs_header_nritems(path->nodes[0]) == 0) btrfs_clear_buffer_dirty(trans, path->nodes[0]); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[1] += 1; } else { btrfs_tree_unlock(right); free_extent_buffer(right); } return 0; out_unlock: btrfs_tree_unlock(right); free_extent_buffer(right); return 1; } /* * push some data in the path leaf to the right, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * returns 1 if the push failed because the other node didn't have enough * room, 0 if everything worked out and < 0 if there were major errors. * * this will push starting from min_slot to the end of the leaf. It won't * push any slot lower than min_slot */ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int min_data_size, int data_size, int empty, u32 min_slot) { struct extent_buffer *left = path->nodes[0]; struct extent_buffer *right; struct extent_buffer *upper; int slot; int free_space; u32 left_nritems; int ret; if (!path->nodes[1]) return 1; slot = path->slots[1]; upper = path->nodes[1]; if (slot >= btrfs_header_nritems(upper) - 1) return 1; btrfs_assert_tree_write_locked(path->nodes[1]); right = btrfs_read_node_slot(upper, slot + 1); if (IS_ERR(right)) return PTR_ERR(right); btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); free_space = btrfs_leaf_free_space(right); if (free_space < data_size) goto out_unlock; ret = btrfs_cow_block(trans, root, right, upper, slot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (ret) goto out_unlock; left_nritems = btrfs_header_nritems(left); if (left_nritems == 0) goto out_unlock; if (check_sibling_keys(left, right)) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } if (path->slots[0] == left_nritems && !empty) { /* Key greater than all keys in the leaf, right neighbor has * enough room for it and we're not emptying our leaf to delete * it, therefore use right neighbor to insert the new item and * no need to touch/dirty our left leaf. */ btrfs_tree_unlock(left); free_extent_buffer(left); path->nodes[0] = right; path->slots[0] = 0; path->slots[1]++; return 0; } return __push_leaf_right(trans, path, min_data_size, empty, right, free_space, left_nritems, min_slot); out_unlock: btrfs_tree_unlock(right); free_extent_buffer(right); return 1; } /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * max_slot can put a limit on how far into the leaf we'll push items. The * item at 'max_slot' won't be touched. Use (u32)-1 to make us do all the * items */ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *left, int free_space, u32 right_nritems, u32 max_slot) { struct btrfs_fs_info *fs_info = left->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *right = path->nodes[0]; int i; int push_space = 0; int push_items = 0; u32 old_left_nritems; u32 nr; int ret = 0; u32 this_item_size; u32 old_left_item_size; struct btrfs_map_token token; if (empty) nr = min(right_nritems, max_slot); else nr = min(right_nritems - 1, max_slot); for (i = 0; i < nr; i++) { if (!empty && push_items > 0) { if (path->slots[0] < i) break; if (path->slots[0] == i) { int space = btrfs_leaf_free_space(right); if (space + push_space * 2 > free_space) break; } } if (path->slots[0] == i) push_space += data_size; this_item_size = btrfs_item_size(right, i); if (this_item_size + sizeof(struct btrfs_item) + push_space > free_space) break; push_items++; push_space += this_item_size + sizeof(struct btrfs_item); } if (push_items == 0) { ret = 1; goto out; } WARN_ON(!empty && push_items == btrfs_header_nritems(right)); /* push data from right to left */ copy_leaf_items(left, right, btrfs_header_nritems(left), 0, push_items); push_space = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_offset(right, push_items - 1); copy_leaf_data(left, right, leaf_data_end(left) - push_space, btrfs_item_offset(right, push_items - 1), push_space); old_left_nritems = btrfs_header_nritems(left); BUG_ON(old_left_nritems <= 0); btrfs_init_map_token(&token, left); old_left_item_size = btrfs_item_offset(left, old_left_nritems - 1); for (i = old_left_nritems; i < old_left_nritems + push_items; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff - (BTRFS_LEAF_DATA_SIZE(fs_info) - old_left_item_size)); } btrfs_set_header_nritems(left, old_left_nritems + push_items); /* fixup right node */ if (push_items > right_nritems) WARN(1, KERN_CRIT "push items %d nr %u\n", push_items, right_nritems); if (push_items < right_nritems) { push_space = btrfs_item_offset(right, push_items - 1) - leaf_data_end(right); memmove_leaf_data(right, BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, leaf_data_end(right), push_space); memmove_leaf_items(right, 0, push_items, btrfs_header_nritems(right) - push_items); } btrfs_init_map_token(&token, right); right_nritems -= push_items; btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(fs_info); for (i = 0; i < right_nritems; i++) { push_space = push_space - btrfs_token_item_size(&token, i); btrfs_set_token_item_offset(&token, i, push_space); } btrfs_mark_buffer_dirty(trans, left); if (right_nritems) btrfs_mark_buffer_dirty(trans, right); else btrfs_clear_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, 1); /* then fixup the leaf pointer in the path */ if (path->slots[0] < push_items) { path->slots[0] += old_left_nritems; btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = left; path->slots[1] -= 1; } else { btrfs_tree_unlock(left); free_extent_buffer(left); path->slots[0] -= push_items; } BUG_ON(path->slots[0] < 0); return ret; out: btrfs_tree_unlock(left); free_extent_buffer(left); return ret; } /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * max_slot can put a limit on how far into the leaf we'll push items. The * item at 'max_slot' won't be touched. Use (u32)-1 to make us push all the * items */ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int min_data_size, int data_size, int empty, u32 max_slot) { struct extent_buffer *right = path->nodes[0]; struct extent_buffer *left; int slot; int free_space; u32 right_nritems; int ret = 0; slot = path->slots[1]; if (slot == 0) return 1; if (!path->nodes[1]) return 1; right_nritems = btrfs_header_nritems(right); if (right_nritems == 0) return 1; btrfs_assert_tree_write_locked(path->nodes[1]); left = btrfs_read_node_slot(path->nodes[1], slot - 1); if (IS_ERR(left)) return PTR_ERR(left); btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); free_space = btrfs_leaf_free_space(left); if (free_space < data_size) { ret = 1; goto out; } ret = btrfs_cow_block(trans, root, left, path->nodes[1], slot - 1, &left, BTRFS_NESTING_LEFT_COW); if (ret) { /* we hit -ENOSPC, but it isn't fatal here */ if (ret == -ENOSPC) ret = 1; goto out; } if (check_sibling_keys(left, right)) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); goto out; } return __push_leaf_left(trans, path, min_data_size, empty, left, free_space, right_nritems, max_slot); out: btrfs_tree_unlock(left); free_extent_buffer(left); return ret; } /* * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. */ static noinline int copy_for_split(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct extent_buffer *l, struct extent_buffer *right, int slot, int mid, int nritems) { struct btrfs_fs_info *fs_info = trans->fs_info; int data_copy_size; int rt_data_off; int i; int ret; struct btrfs_disk_key disk_key; struct btrfs_map_token token; nritems = nritems - mid; btrfs_set_header_nritems(right, nritems); data_copy_size = btrfs_item_data_end(l, mid) - leaf_data_end(l); copy_leaf_items(right, l, 0, mid, nritems); copy_leaf_data(right, l, BTRFS_LEAF_DATA_SIZE(fs_info) - data_copy_size, leaf_data_end(l), data_copy_size); rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_data_end(l, mid); btrfs_init_map_token(&token, right); for (i = 0; i < nritems; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff + rt_data_off); } btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); if (ret < 0) return ret; btrfs_mark_buffer_dirty(trans, right); btrfs_mark_buffer_dirty(trans, l); BUG_ON(path->slots[0] != slot); if (mid <= slot) { btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] -= mid; path->slots[1] += 1; } else { btrfs_tree_unlock(right); free_extent_buffer(right); } BUG_ON(path->slots[0] < 0); return 0; } /* * double splits happen when we need to insert a big item in the middle * of a leaf. A double split can leave us with 3 mostly empty leaves: * leaf: [ slots 0 - N] [ our target ] [ N + 1 - total in leaf ] * A B C * * We avoid this by trying to push the items on either side of our target * into the adjacent leaves. If all goes well we can avoid the double split * completely. */ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int data_size) { int ret; int progress = 0; int slot; u32 nritems; int space_needed = data_size; slot = path->slots[0]; if (slot < btrfs_header_nritems(path->nodes[0])) space_needed -= btrfs_leaf_free_space(path->nodes[0]); /* * try to push all the items after our slot into the * right leaf */ ret = push_leaf_right(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; if (ret == 0) progress++; nritems = btrfs_header_nritems(path->nodes[0]); /* * our goal is to get our slot at the start or end of a leaf. If * we've done so we're done */ if (path->slots[0] == 0 || path->slots[0] == nritems) return 0; if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; /* try to push all the items before our slot into the next leaf */ slot = path->slots[0]; space_needed = data_size; if (slot > 0) space_needed -= btrfs_leaf_free_space(path->nodes[0]); ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; if (ret == 0) progress++; if (progress) return 0; return 1; } /* * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. * * returns 0 if all went well and < 0 on failure. */ static noinline int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, int extend) { struct btrfs_disk_key disk_key; struct extent_buffer *l; u32 nritems; int mid; int slot; struct extent_buffer *right; struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; int wret; int split; int num_doubles = 0; int tried_avoid_double = 0; l = path->nodes[0]; slot = path->slots[0]; if (extend && data_size + btrfs_item_size(l, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(fs_info)) return -EOVERFLOW; /* first try to make some room by pushing left and right */ if (data_size && path->nodes[1]) { int space_needed = data_size; if (slot < btrfs_header_nritems(l)) space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_right(trans, root, path, space_needed, space_needed, 0, 0); if (wret < 0) return wret; if (wret) { space_needed = data_size; if (slot > 0) space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_left(trans, root, path, space_needed, space_needed, 0, (u32)-1); if (wret < 0) return wret; } l = path->nodes[0]; /* did the pushes work? */ if (btrfs_leaf_free_space(l) >= data_size) return 0; } if (!path->nodes[1]) { ret = insert_new_root(trans, root, path, 1); if (ret) return ret; } again: split = 1; l = path->nodes[0]; slot = path->slots[0]; nritems = btrfs_header_nritems(l); mid = (nritems + 1) / 2; if (mid <= slot) { if (nritems == 1 || leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (slot >= nritems) { split = 0; } else { mid = slot; if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (data_size && !tried_avoid_double) goto push_for_double; split = 2; } } } } else { if (leaf_space_used(l, 0, mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (!extend && data_size && slot == 0) { split = 0; } else if ((extend || !data_size) && slot == 0) { mid = 1; } else { mid = slot; if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (data_size && !tried_avoid_double) goto push_for_double; split = 2; } } } } if (split == 0) btrfs_cpu_key_to_disk(&disk_key, ins_key); else btrfs_item_key(l, &disk_key, mid); /* * We have to about BTRFS_NESTING_NEW_ROOT here if we've done a double * split, because we're only allowed to have MAX_LOCKDEP_SUBCLASSES * subclasses, which is 8 at the time of this patch, and we've maxed it * out. In the future we could add a * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just * use BTRFS_NESTING_NEW_ROOT. */ right = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &disk_key, 0, l->start, 0, 0, num_doubles ? BTRFS_NESTING_NEW_ROOT : BTRFS_NESTING_SPLIT); if (IS_ERR(right)) return PTR_ERR(right); root_add_used_bytes(root); if (split == 0) { if (mid <= slot) { btrfs_set_header_nritems(right, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] = 0; path->slots[1] += 1; } else { btrfs_set_header_nritems(right, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1], 1); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] = 0; if (path->slots[1] == 0) fixup_low_keys(trans, path, &disk_key, 1); } /* * We create a new leaf 'right' for the required ins_len and * we'll do btrfs_mark_buffer_dirty() on this leaf after copying * the content of ins_len to 'right'. */ return ret; } ret = copy_for_split(trans, path, l, right, slot, mid, nritems); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } if (split == 2) { BUG_ON(num_doubles != 0); num_doubles++; goto again; } return 0; push_for_double: push_for_double_split(trans, root, path, data_size); tried_avoid_double = 1; if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; goto again; } static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int ins_len) { struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; u64 extent_len = 0; u32 item_size; int ret; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY && key.type != BTRFS_RAID_STRIPE_KEY && key.type != BTRFS_EXTENT_CSUM_KEY); if (btrfs_leaf_free_space(leaf) >= ins_len) return 0; item_size = btrfs_item_size(leaf, path->slots[0]); if (key.type == BTRFS_EXTENT_DATA_KEY) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); extent_len = btrfs_file_extent_num_bytes(leaf, fi); } btrfs_release_path(path); path->keep_locks = 1; path->search_for_split = 1; ret = btrfs_search_slot(trans, root, &key, path, 0, 1); path->search_for_split = 0; if (ret > 0) ret = -EAGAIN; if (ret < 0) goto err; ret = -EAGAIN; leaf = path->nodes[0]; /* if our item isn't there, return now */ if (item_size != btrfs_item_size(leaf, path->slots[0])) goto err; /* the leaf has changed, it now has room. return now */ if (btrfs_leaf_free_space(path->nodes[0]) >= ins_len) goto err; if (key.type == BTRFS_EXTENT_DATA_KEY) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); if (extent_len != btrfs_file_extent_num_bytes(leaf, fi)) goto err; } ret = split_leaf(trans, root, &key, path, ins_len, 1); if (ret) goto err; path->keep_locks = 0; btrfs_unlock_up_safe(path, 1); return 0; err: path->keep_locks = 0; return ret; } static noinline int split_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { struct extent_buffer *leaf; int orig_slot, slot; char *buf; u32 nritems; u32 item_size; u32 orig_offset; struct btrfs_disk_key disk_key; leaf = path->nodes[0]; /* * Shouldn't happen because the caller must have previously called * setup_leaf_for_split() to make room for the new item in the leaf. */ if (WARN_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item))) return -ENOSPC; orig_slot = path->slots[0]; orig_offset = btrfs_item_offset(leaf, path->slots[0]); item_size = btrfs_item_size(leaf, path->slots[0]); buf = kmalloc(item_size, GFP_NOFS); if (!buf) return -ENOMEM; read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, path->slots[0]), item_size); slot = path->slots[0] + 1; nritems = btrfs_header_nritems(leaf); if (slot != nritems) { /* shift the items */ memmove_leaf_items(leaf, slot + 1, slot, nritems - slot); } btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(leaf, &disk_key, slot); btrfs_set_item_offset(leaf, slot, orig_offset); btrfs_set_item_size(leaf, slot, item_size - split_offset); btrfs_set_item_offset(leaf, orig_slot, orig_offset + item_size - split_offset); btrfs_set_item_size(leaf, orig_slot, split_offset); btrfs_set_header_nritems(leaf, nritems + 1); /* write the data for the start of the original item */ write_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, path->slots[0]), split_offset); /* write the data for the new item */ write_extent_buffer(leaf, buf + split_offset, btrfs_item_ptr_offset(leaf, slot), item_size - split_offset); btrfs_mark_buffer_dirty(trans, leaf); BUG_ON(btrfs_leaf_free_space(leaf) < 0); kfree(buf); return 0; } /* * This function splits a single item into two items, * giving 'new_key' to the new item and splitting the * old one at split_offset (from the start of the item). * * The path may be released by this operation. After * the split, the path is pointing to the old item. The * new item is going to be in the same node as the old one. * * Note, the item being split must be smaller enough to live alone on * a tree block with room for one extra struct btrfs_item * * This allows us to split the item in place, keeping a lock on the * leaf the entire time. */ int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { int ret; ret = setup_leaf_for_split(trans, root, path, sizeof(struct btrfs_item)); if (ret) return ret; ret = split_item(trans, path, new_key, split_offset); return ret; } /* * make the item pointed to by the path smaller. new_size indicates * how small to make it, and from_end tells us if we just chop bytes * off the end of the item or if we shift the item to chop bytes off * the front. */ void btrfs_truncate_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 new_size, int from_end) { int slot; struct extent_buffer *leaf; u32 nritems; unsigned int data_end; unsigned int old_data_start; unsigned int old_size; unsigned int size_diff; int i; struct btrfs_map_token token; leaf = path->nodes[0]; slot = path->slots[0]; old_size = btrfs_item_size(leaf, slot); if (old_size == new_size) return; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); old_data_start = btrfs_item_offset(leaf, slot); size_diff = old_size - new_size; BUG_ON(slot < 0); BUG_ON(slot >= nritems); /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ btrfs_init_map_token(&token, leaf); for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff + size_diff); } /* shift the data */ if (from_end) { memmove_leaf_data(leaf, data_end + size_diff, data_end, old_data_start + new_size - data_end); } else { struct btrfs_disk_key disk_key; u64 offset; btrfs_item_key(leaf, &disk_key, slot); if (btrfs_disk_key_type(&disk_key) == BTRFS_EXTENT_DATA_KEY) { unsigned long ptr; struct btrfs_file_extent_item *fi; fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); fi = (struct btrfs_file_extent_item *)( (unsigned long)fi - size_diff); if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { ptr = btrfs_item_ptr_offset(leaf, slot); memmove_extent_buffer(leaf, ptr, (unsigned long)fi, BTRFS_FILE_EXTENT_INLINE_DATA_START); } } memmove_leaf_data(leaf, data_end + size_diff, data_end, old_data_start - data_end); offset = btrfs_disk_key_offset(&disk_key); btrfs_set_disk_key_offset(&disk_key, offset + size_diff); btrfs_set_item_key(leaf, &disk_key, slot); if (slot == 0) fixup_low_keys(trans, path, &disk_key, 1); } btrfs_set_item_size(leaf, slot, new_size); btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } } /* * make the item pointed to by the path bigger, data_size is the added size. */ void btrfs_extend_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 data_size) { int slot; struct extent_buffer *leaf; u32 nritems; unsigned int data_end; unsigned int old_data; unsigned int old_size; int i; struct btrfs_map_token token; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); if (btrfs_leaf_free_space(leaf) < data_size) { btrfs_print_leaf(leaf); BUG(); } slot = path->slots[0]; old_data = btrfs_item_data_end(leaf, slot); BUG_ON(slot < 0); if (slot >= nritems) { btrfs_print_leaf(leaf); btrfs_crit(leaf->fs_info, "slot %d too large, nritems %d", slot, nritems); BUG(); } /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ btrfs_init_map_token(&token, leaf); for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff - data_size); } /* shift the data */ memmove_leaf_data(leaf, data_end - data_size, data_end, old_data - data_end); data_end = old_data; old_size = btrfs_item_size(leaf, slot); btrfs_set_item_size(leaf, slot, old_size + data_size); btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } } /* * Make space in the node before inserting one or more items. * * @trans: transaction handle * @root: root we are inserting items to * @path: points to the leaf/slot where we are going to insert new items * @batch: information about the batch of items to insert * * Main purpose is to save stack depth by doing the bulk of the work in a * function that doesn't call btrfs_search_slot */ static void setup_items_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch) { struct btrfs_fs_info *fs_info = root->fs_info; int i; u32 nritems; unsigned int data_end; struct btrfs_disk_key disk_key; struct extent_buffer *leaf; int slot; struct btrfs_map_token token; u32 total_size; /* * Before anything else, update keys in the parent and other ancestors * if needed, then release the write locks on them, so that other tasks * can use them while we modify the leaf. */ if (path->slots[0] == 0) { btrfs_cpu_key_to_disk(&disk_key, &batch->keys[0]); fixup_low_keys(trans, path, &disk_key, 1); } btrfs_unlock_up_safe(path, 1); leaf = path->nodes[0]; slot = path->slots[0]; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); total_size = batch->total_data_size + (batch->nr * sizeof(struct btrfs_item)); if (btrfs_leaf_free_space(leaf) < total_size) { btrfs_print_leaf(leaf); btrfs_crit(fs_info, "not enough freespace need %u have %d", total_size, btrfs_leaf_free_space(leaf)); BUG(); } btrfs_init_map_token(&token, leaf); if (slot != nritems) { unsigned int old_data = btrfs_item_data_end(leaf, slot); if (old_data < data_end) { btrfs_print_leaf(leaf); btrfs_crit(fs_info, "item at slot %d with data offset %u beyond data end of leaf %u", slot, old_data, data_end); BUG(); } /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff - batch->total_data_size); } /* shift the items */ memmove_leaf_items(leaf, slot + batch->nr, slot, nritems - slot); /* shift the data */ memmove_leaf_data(leaf, data_end - batch->total_data_size, data_end, old_data - data_end); data_end = old_data; } /* setup the item for the new data */ for (i = 0; i < batch->nr; i++) { btrfs_cpu_key_to_disk(&disk_key, &batch->keys[i]); btrfs_set_item_key(leaf, &disk_key, slot + i); data_end -= batch->data_sizes[i]; btrfs_set_token_item_offset(&token, slot + i, data_end); btrfs_set_token_item_size(&token, slot + i, batch->data_sizes[i]); } btrfs_set_header_nritems(leaf, nritems + batch->nr); btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); BUG(); } } /* * Insert a new item into a leaf. * * @trans: Transaction handle. * @root: The root of the btree. * @path: A path pointing to the target leaf and slot. * @key: The key of the new item. * @data_size: The size of the data associated with the new key. */ void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size) { struct btrfs_item_batch batch; batch.keys = key; batch.data_sizes = &data_size; batch.total_data_size = data_size; batch.nr = 1; setup_items_for_insert(trans, root, path, &batch); } /* * Given a key and some data, insert items into the tree. * This does all the path init required, making room in the tree if needed. * * Returns: 0 on success * -EEXIST if the first key already exists * < 0 on other errors */ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch) { int ret = 0; int slot; u32 total_size; total_size = batch->total_data_size + (batch->nr * sizeof(struct btrfs_item)); ret = btrfs_search_slot(trans, root, &batch->keys[0], path, total_size, 1); if (ret == 0) return -EEXIST; if (ret < 0) return ret; slot = path->slots[0]; BUG_ON(slot < 0); setup_items_for_insert(trans, root, path, batch); return 0; } /* * Given a key and some data, insert an item into the tree. * This does all the path init required, making room in the tree if needed. */ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *cpu_key, void *data, u32 data_size) { int ret = 0; struct btrfs_path *path; struct extent_buffer *leaf; unsigned long ptr; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_insert_empty_item(trans, root, path, cpu_key, data_size); if (!ret) { leaf = path->nodes[0]; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, data, ptr, data_size); btrfs_mark_buffer_dirty(trans, leaf); } btrfs_free_path(path); return ret; } /* * This function duplicates an item, giving 'new_key' to the new item. * It guarantees both items live in the same tree leaf and the new item is * contiguous with the original item. * * This allows us to split a file extent in place, keeping a lock on the leaf * the entire time. */ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key) { struct extent_buffer *leaf; int ret; u32 item_size; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); ret = setup_leaf_for_split(trans, root, path, item_size + sizeof(struct btrfs_item)); if (ret) return ret; path->slots[0]++; btrfs_setup_item_for_insert(trans, root, path, new_key, item_size); leaf = path->nodes[0]; memcpy_extent_buffer(leaf, btrfs_item_ptr_offset(leaf, path->slots[0]), btrfs_item_ptr_offset(leaf, path->slots[0] - 1), item_size); return 0; } /* * delete the pointer from a given node. * * the tree should have been previously balanced so the deletion does not * empty a node. * * This is exported for use inside btrfs-progs, don't un-export it. */ int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot) { struct extent_buffer *parent = path->nodes[level]; u32 nritems; int ret; nritems = btrfs_header_nritems(parent); if (slot != nritems - 1) { if (level) { ret = btrfs_tree_mod_log_insert_move(parent, slot, slot + 1, nritems - slot - 1); if (ret < 0) { btrfs_abort_transaction(trans, ret); return ret; } } memmove_extent_buffer(parent, btrfs_node_key_ptr_offset(parent, slot), btrfs_node_key_ptr_offset(parent, slot + 1), sizeof(struct btrfs_key_ptr) * (nritems - slot - 1)); } else if (level) { ret = btrfs_tree_mod_log_insert_key(parent, slot, BTRFS_MOD_LOG_KEY_REMOVE); if (ret < 0) { btrfs_abort_transaction(trans, ret); return ret; } } nritems--; btrfs_set_header_nritems(parent, nritems); if (nritems == 0 && parent == root->node) { BUG_ON(btrfs_header_level(root->node) != 1); /* just turn the root into a leaf and break */ btrfs_set_header_level(root->node, 0); } else if (slot == 0) { struct btrfs_disk_key disk_key; btrfs_node_key(parent, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, level + 1); } btrfs_mark_buffer_dirty(trans, parent); return 0; } /* * a helper function to delete the leaf pointed to by path->slots[1] and * path->nodes[1]. * * This deletes the pointer in path->nodes[1] and frees the leaf * block extent. zero is returned if it all worked out, < 0 otherwise. * * The path must have already been setup for deleting the leaf, including * all the proper balancing. path->nodes[1] must be locked. */ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *leaf) { int ret; WARN_ON(btrfs_header_generation(leaf) != trans->transid); ret = btrfs_del_ptr(trans, root, path, 1, path->slots[1]); if (ret < 0) return ret; /* * btrfs_free_extent is expensive, we want to make sure we * aren't holding any locks when we call it */ btrfs_unlock_up_safe(path, 0); root_sub_used_bytes(root); atomic_inc(&leaf->refs); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); if (ret < 0) btrfs_abort_transaction(trans, ret); return ret; } /* * delete the item at the leaf level in path. If that empties * the leaf, remove it from the tree */ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int slot, int nr) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; int ret = 0; int wret; u32 nritems; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (slot + nr != nritems) { const u32 last_off = btrfs_item_offset(leaf, slot + nr - 1); const int data_end = leaf_data_end(leaf); struct btrfs_map_token token; u32 dsize = 0; int i; for (i = 0; i < nr; i++) dsize += btrfs_item_size(leaf, slot + i); memmove_leaf_data(leaf, data_end + dsize, data_end, last_off - data_end); btrfs_init_map_token(&token, leaf); for (i = slot + nr; i < nritems; i++) { u32 ioff; ioff = btrfs_token_item_offset(&token, i); btrfs_set_token_item_offset(&token, i, ioff + dsize); } memmove_leaf_items(leaf, slot, slot + nr, nritems - slot - nr); } btrfs_set_header_nritems(leaf, nritems - nr); nritems -= nr; /* delete the leaf if we've emptied it */ if (nritems == 0) { if (leaf == root->node) { btrfs_set_header_level(leaf, 0); } else { btrfs_clear_buffer_dirty(trans, leaf); ret = btrfs_del_leaf(trans, root, path, leaf); if (ret < 0) return ret; } } else { int used = leaf_space_used(leaf, 0, nritems); if (slot == 0) { struct btrfs_disk_key disk_key; btrfs_item_key(leaf, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, 1); } /* * Try to delete the leaf if it is mostly empty. We do this by * trying to move all its items into its left and right neighbours. * If we can't move all the items, then we don't delete it - it's * not ideal, but future insertions might fill the leaf with more * items, or items from other leaves might be moved later into our * leaf due to deletions on those leaves. */ if (used < BTRFS_LEAF_DATA_SIZE(fs_info) / 3) { u32 min_push_space; /* push_leaf_left fixes the path. * make sure the path still points to our leaf * for possible call to btrfs_del_ptr below */ slot = path->slots[1]; atomic_inc(&leaf->refs); /* * We want to be able to at least push one item to the * left neighbour leaf, and that's the first item. */ min_push_space = sizeof(struct btrfs_item) + btrfs_item_size(leaf, 0); wret = push_leaf_left(trans, root, path, 0, min_push_space, 1, (u32)-1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (path->nodes[0] == leaf && btrfs_header_nritems(leaf)) { /* * If we were not able to push all items from our * leaf to its left neighbour, then attempt to * either push all the remaining items to the * right neighbour or none. There's no advantage * in pushing only some items, instead of all, as * it's pointless to end up with a leaf having * too few items while the neighbours can be full * or nearly full. */ nritems = btrfs_header_nritems(leaf); min_push_space = leaf_space_used(leaf, 0, nritems); wret = push_leaf_right(trans, root, path, 0, min_push_space, 1, 0); if (wret < 0 && wret != -ENOSPC) ret = wret; } if (btrfs_header_nritems(leaf) == 0) { path->slots[1] = slot; ret = btrfs_del_leaf(trans, root, path, leaf); if (ret < 0) return ret; free_extent_buffer(leaf); ret = 0; } else { /* if we're still in the path, make sure * we're dirty. Otherwise, one of the * push_leaf functions must have already * dirtied this buffer */ if (path->nodes[0] == leaf) btrfs_mark_buffer_dirty(trans, leaf); free_extent_buffer(leaf); } } else { btrfs_mark_buffer_dirty(trans, leaf); } } return ret; } /* * A helper function to walk down the tree starting at min_key, and looking * for nodes or leaves that are have a minimum transaction id. * This is used by the btree defrag code, and tree logging * * This does not cow, but it does stuff the starting key it finds back * into min_key, so you can call btrfs_search_slot with cow=1 on the * key and get a writable path. * * This honors path->lowest_level to prevent descent past a given level * of the tree. * * min_trans indicates the oldest transaction that you are interested * in walking through. Any nodes or leaves older than min_trans are * skipped over (without reading them). * * returns zero if something useful was found, < 0 on error and 1 if there * was nothing in the tree that matched the search criteria. */ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key, struct btrfs_path *path, u64 min_trans) { struct extent_buffer *cur; struct btrfs_key found_key; int slot; int sret; u32 nritems; int level; int ret = 1; int keep_locks = path->keep_locks; ASSERT(!path->nowait); path->keep_locks = 1; again: cur = btrfs_read_lock_root_node(root); level = btrfs_header_level(cur); WARN_ON(path->nodes[level]); path->nodes[level] = cur; path->locks[level] = BTRFS_READ_LOCK; if (btrfs_header_generation(cur) < min_trans) { ret = 1; goto out; } while (1) { nritems = btrfs_header_nritems(cur); level = btrfs_header_level(cur); sret = btrfs_bin_search(cur, 0, min_key, &slot); if (sret < 0) { ret = sret; goto out; } /* at the lowest level, we're done, setup the path and exit */ if (level == path->lowest_level) { if (slot >= nritems) goto find_next_key; ret = 0; path->slots[level] = slot; btrfs_item_key_to_cpu(cur, &found_key, slot); goto out; } if (sret && slot > 0) slot--; /* * check this node pointer against the min_trans parameters. * If it is too old, skip to the next one. */ while (slot < nritems) { u64 gen; gen = btrfs_node_ptr_generation(cur, slot); if (gen < min_trans) { slot++; continue; } break; } find_next_key: /* * we didn't find a candidate key in this node, walk forward * and find another one */ if (slot >= nritems) { path->slots[level] = slot; sret = btrfs_find_next_key(root, path, min_key, level, min_trans); if (sret == 0) { btrfs_release_path(path); goto again; } else { goto out; } } /* save our key for returning back */ btrfs_node_key_to_cpu(cur, &found_key, slot); path->slots[level] = slot; if (level == path->lowest_level) { ret = 0; goto out; } cur = btrfs_read_node_slot(cur, slot); if (IS_ERR(cur)) { ret = PTR_ERR(cur); goto out; } btrfs_tree_read_lock(cur); path->locks[level - 1] = BTRFS_READ_LOCK; path->nodes[level - 1] = cur; unlock_up(path, level, 1, 0, NULL); } out: path->keep_locks = keep_locks; if (ret == 0) { btrfs_unlock_up_safe(path, path->lowest_level + 1); memcpy(min_key, &found_key, sizeof(found_key)); } return ret; } /* * this is similar to btrfs_next_leaf, but does not try to preserve * and fixup the path. It looks for and returns the next key in the * tree based on the current path and the min_trans parameters. * * 0 is returned if another key is found, < 0 if there are any errors * and 1 is returned if there are no higher keys in the tree * * path->keep_locks should be set to 1 on the search made before * calling this function. */ int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *key, int level, u64 min_trans) { int slot; struct extent_buffer *c; WARN_ON(!path->keep_locks && !path->skip_locking); while (level < BTRFS_MAX_LEVEL) { if (!path->nodes[level]) return 1; slot = path->slots[level] + 1; c = path->nodes[level]; next: if (slot >= btrfs_header_nritems(c)) { int ret; int orig_lowest; struct btrfs_key cur_key; if (level + 1 >= BTRFS_MAX_LEVEL || !path->nodes[level + 1]) return 1; if (path->locks[level + 1] || path->skip_locking) { level++; continue; } slot = btrfs_header_nritems(c) - 1; if (level == 0) btrfs_item_key_to_cpu(c, &cur_key, slot); else btrfs_node_key_to_cpu(c, &cur_key, slot); orig_lowest = path->lowest_level; btrfs_release_path(path); path->lowest_level = level; ret = btrfs_search_slot(NULL, root, &cur_key, path, 0, 0); path->lowest_level = orig_lowest; if (ret < 0) return ret; c = path->nodes[level]; slot = path->slots[level]; if (ret == 0) slot++; goto next; } if (level == 0) btrfs_item_key_to_cpu(c, key, slot); else { u64 gen = btrfs_node_ptr_generation(c, slot); if (gen < min_trans) { slot++; goto next; } btrfs_node_key_to_cpu(c, key, slot); } return 0; } return 1; } int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq) { int slot; int level; struct extent_buffer *c; struct extent_buffer *next; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; bool need_commit_sem = false; u32 nritems; int ret; int i; /* * The nowait semantics are used only for write paths, where we don't * use the tree mod log and sequence numbers. */ if (time_seq) ASSERT(!path->nowait); nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) return 1; btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1); again: level = 1; next = NULL; btrfs_release_path(path); path->keep_locks = 1; if (time_seq) { ret = btrfs_search_old_slot(root, &key, path, time_seq); } else { if (path->need_commit_sem) { path->need_commit_sem = 0; need_commit_sem = true; if (path->nowait) { if (!down_read_trylock(&fs_info->commit_root_sem)) { ret = -EAGAIN; goto done; } } else { down_read(&fs_info->commit_root_sem); } } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); } path->keep_locks = 0; if (ret < 0) goto done; nritems = btrfs_header_nritems(path->nodes[0]); /* * by releasing the path above we dropped all our locks. A balance * could have added more items next to the key that used to be * at the very end of the block. So, check again here and * advance the path if there are now more items available. */ if (nritems > 0 && path->slots[0] < nritems - 1) { if (ret == 0) path->slots[0]++; ret = 0; goto done; } /* * So the above check misses one case: * - after releasing the path above, someone has removed the item that * used to be at the very end of the block, and balance between leafs * gets another one with bigger key.offset to replace it. * * This one should be returned as well, or we can get leaf corruption * later(esp. in __btrfs_drop_extents()). * * And a bit more explanation about this check, * with ret > 0, the key isn't found, the path points to the slot * where it should be inserted, so the path->slots[0] item must be the * bigger one. */ if (nritems > 0 && ret > 0 && path->slots[0] == nritems - 1) { ret = 0; goto done; } while (level < BTRFS_MAX_LEVEL) { if (!path->nodes[level]) { ret = 1; goto done; } slot = path->slots[level] + 1; c = path->nodes[level]; if (slot >= btrfs_header_nritems(c)) { level++; if (level == BTRFS_MAX_LEVEL) { ret = 1; goto done; } continue; } /* * Our current level is where we're going to start from, and to * make sure lockdep doesn't complain we need to drop our locks * and nodes from 0 to our current level. */ for (i = 0; i < level; i++) { if (path->locks[level]) { btrfs_tree_read_unlock(path->nodes[i]); path->locks[i] = 0; } free_extent_buffer(path->nodes[i]); path->nodes[i] = NULL; } next = c; ret = read_block_for_search(root, path, &next, slot, &key); if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { btrfs_release_path(path); goto done; } if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); if (!ret && path->nowait) { ret = -EAGAIN; goto done; } if (!ret && time_seq) { /* * If we don't get the lock, we may be racing * with push_leaf_left, holding that lock while * itself waiting for the leaf we've currently * locked. To solve this situation, we give up * on our lock and cycle. */ free_extent_buffer(next); btrfs_release_path(path); cond_resched(); goto again; } if (!ret) btrfs_tree_read_lock(next); } break; } path->slots[level] = slot; while (1) { level--; path->nodes[level] = next; path->slots[level] = 0; if (!path->skip_locking) path->locks[level] = BTRFS_READ_LOCK; if (!level) break; ret = read_block_for_search(root, path, &next, 0, &key); if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { btrfs_release_path(path); goto done; } if (!path->skip_locking) { if (path->nowait) { if (!btrfs_try_tree_read_lock(next)) { ret = -EAGAIN; goto done; } } else { btrfs_tree_read_lock(next); } } } ret = 0; done: unlock_up(path, 0, 1, 0, NULL); if (need_commit_sem) { int ret2; path->need_commit_sem = 1; ret2 = finish_need_commit_sem_search(path); up_read(&fs_info->commit_root_sem); if (ret2) ret = ret2; } return ret; } int btrfs_next_old_item(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq) { path->slots[0]++; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) return btrfs_next_old_leaf(root, path, time_seq); return 0; } /* * this uses btrfs_prev_leaf to walk backwards in the tree, and keeps * searching until it gets past min_objectid or finds an item of 'type' * * returns 0 if something is found, 1 if nothing was found and < 0 on error */ int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, int type) { struct btrfs_key found_key; struct extent_buffer *leaf; u32 nritems; int ret; while (1) { if (path->slots[0] == 0) { ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; } else { path->slots[0]--; } leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (nritems == 0) return 1; if (path->slots[0] == nritems) path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid < min_objectid) break; if (found_key.type == type) return 0; if (found_key.objectid == min_objectid && found_key.type < type) break; } return 1; } /* * search in extent tree to find a previous Metadata/Data extent item with * min objecitd. * * returns 0 if something is found, 1 if nothing was found and < 0 on error */ int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid) { struct btrfs_key found_key; struct extent_buffer *leaf; u32 nritems; int ret; while (1) { if (path->slots[0] == 0) { ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; } else { path->slots[0]--; } leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (nritems == 0) return 1; if (path->slots[0] == nritems) path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid < min_objectid) break; if (found_key.type == BTRFS_EXTENT_ITEM_KEY || found_key.type == BTRFS_METADATA_ITEM_KEY) return 0; if (found_key.objectid == min_objectid && found_key.type < BTRFS_EXTENT_ITEM_KEY) break; } return 1; } int __init btrfs_ctree_init(void) { btrfs_path_cachep = KMEM_CACHE(btrfs_path, 0); if (!btrfs_path_cachep) return -ENOMEM; return 0; } void __cold btrfs_ctree_exit(void) { kmem_cache_destroy(btrfs_path_cachep); } |
| 736 530 672 39 673 611 609 368 612 611 383 665 235 235 542 2 541 445 442 1 184 377 1 346 380 404 402 372 523 27 573 405 257 578 382 252 915 560 385 621 385 236 493 324 170 366 255 111 201 110 93 291 169 120 217 134 83 67 41 27 51 24 27 339 146 339 340 339 339 236 104 339 337 338 235 104 196 25 181 181 235 60 211 2 43 178 12 1 12 12 37 78 41 39 1 38 538 7 539 82 1 82 35 3 35 46 3 43 34 9 34 9 38 37 5 112 10 4 105 105 1 10 20 15 5 22 310 311 11 69 77 77 11 7 13 9 9 9 2 7 2 7 9 9 9 9 9 9 660 660 409 166 98 238 410 375 377 244 171 17 375 374 4 376 26 23 1 2 27 478 472 465 468 43 1 1 1 42 25 24 1 2 454 440 450 451 24 9 10 19 29 19 26 1 2 103 12 426 74 13 3 12 1 1 48 26 21 1 28 1 17 13 22 32 27 26 23 1 3 1 24 25 5 3 2 34 23 9 3 1 267 32 265 186 414 178 211 47 17 31 47 202 59 1 431 16 378 64 67 66 52 12 367 60 4 3 422 1 422 52 372 25 400 409 1 33 4 424 1 1 20 417 20 449 449 1 448 1 2 444 423 1 390 46 46 45 1 445 436 434 436 435 435 432 434 434 436 435 434 435 435 9 13 2 14 1 14 14 15 15 15 15 15 14 12 14 15 15 2 12 3 14 1 15 15 14 1 11 4 12 2 15 3 5 15 15 11 3 15 1 14 15 15 15 15 331 27 47 2 9 246 247 258 256 2 257 286 45 102 102 102 118 16 102 102 102 102 267 48 145 75 329 1 355 217 141 356 368 368 368 365 2 360 7 1 364 361 3 359 6 2 360 356 3 357 3 3 357 318 36 137 218 356 322 249 60 60 356 338 18 336 329 407 2 86 3 1 358 2 5 34 40 7 38 237 9 5 6 238 252 324 6 69 252 252 108 238 252 109 237 240 32 32 32 32 32 32 32 32 32 271 271 272 272 271 248 3 18 320 165 155 326 193 378 39 332 86 333 86 368 51 404 15 324 42 51 354 65 86 332 73 346 418 380 1 109 1 269 1 4 23 348 356 354 356 21 1 1 1 117 265 9 3 7 5 400 2 1 418 2 419 2 417 4 130 284 400 382 14 5 384 15 1 379 21 6 380 13 5 1 388 386 1 1 383 373 1 373 1 369 371 369 370 368 2 366 245 123 368 365 368 368 15 15 13 402 51 1 1 12 37 49 352 426 2 1 1 292 130 1 129 2 382 1 204 35 63 11 67 385 385 122 264 1 1 1 381 308 22 400 426 426 2 421 419 418 414 11 403 2 16 3 1 7 6 12 312 44 229 4 122 271 4 285 15 63 1 1 2 2 2 329 28 101 199 329 243 87 271 8 2 293 27 56 255 8 10 300 1 310 193 118 1 234 75 300 300 133 166 30 30 122 121 300 426 423 2 426 299 300 126 424 27 8 19 2 4 6 1 7 12 3 2 6 6 7 6 470 470 47 431 471 470 470 279 154 296 338 144 312 469 470 471 468 470 465 2 62 5 57 11 22 11 22 41 29 32 4 4 4 4 42 4 1 41 40 2 41 1 42 1 41 10 2 1 15 15 1 14 15 14 2 6 6 34 1 14 23 25 3 4 5 30 3 20 15 33 25 8 10 10 10 46 4 42 10 33 28 1 28 29 29 29 3 29 95 95 3 95 155 155 8 112 50 96 95 1 3 3 4 1 1 2 3 18 95 4 91 111 106 100 95 80 22 26 8 19 22 8 1 1 195 1 192 4 42 185 135 5 22 132 129 48 3 3 3 1 1 135 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/super.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> #include <linux/part_stat.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fsnotify.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "mballoc.h" #include "fsmap.h" #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> static struct ext4_lazy_init *ext4_li_info; static DEFINE_MUTEX(ext4_li_mtx); static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static void ext4_update_super(struct super_block *sb); static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); static int ext4_validate_options(struct fs_context *fc); static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb); static void ext4_apply_options(struct fs_context *fc, struct super_block *sb); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param); static int ext4_get_tree(struct fs_context *fc); static int ext4_reconfigure(struct fs_context *fc); static void ext4_fc_free(struct fs_context *fc); static int ext4_init_fs_context(struct fs_context *fc); static void ext4_kill_sb(struct super_block *sb); static const struct fs_parameter_spec ext4_param_specs[]; /* * Lock ordering * * page fault path: * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start * -> page lock -> i_data_sem (rw) * * buffered write path: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> page lock -> * i_data_sem (rw) * * truncate: * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) -> * page lock * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start -> * i_data_sem (rw) * * direct IO: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw) * * writepages: * transaction start -> page lock(s) -> i_data_sem (rw) */ static const struct fs_context_operations ext4_context_ops = { .parse_param = ext4_parse_param, .get_tree = ext4_get_tree, .reconfigure = ext4_reconfigure, .free = ext4_fc_free, }; #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); #define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type) #else #define IS_EXT2_SB(sb) (0) #endif static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type) static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { if (simu_fail) { clear_buffer_uptodate(bh); unlock_buffer(bh); return; } /* * buffer's verified bit is no longer valid after reading from * disk again due to write out error, clear it to make sure we * recheck the buffer contents. */ clear_buffer_verified(bh); bh->b_end_io = end_io ? end_io : end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); } int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { lock_buffer(bh); if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL, false); return 0; } return ext4_read_bh(bh, op_flags, NULL, false); } /* * This works like __bread_gfp() except it uses ERR_PTR for error * returns. Currently with sb_bread it's impossible to distinguish * between ENOMEM and EIO situations (since both result in a NULL * return. */ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, sector_t block, blk_opf_t op_flags, gfp_t gfp) { struct buffer_head *bh; int ret; bh = sb_getblk_gfp(sb, block, gfp); if (bh == NULL) return ERR_PTR(-ENOMEM); if (ext4_buffer_uptodate(bh)) return bh; ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true); if (ret) { put_bh(bh); return ERR_PTR(ret); } return bh; } struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE; return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS); return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); if (likely(bh)) { if (trylock_buffer(bh)) ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false); brelse(bh); } } static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct ext4_super_block, s_checksum); __u32 csum; csum = ext4_chksum(sbi, ~0, (char *)es, offset); return cpu_to_le32(csum); } static int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16); } void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count)); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16)); } void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16); } void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_itable_unused_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now) { now = clamp_val(now, 0, (1ull << 40) - 1); *lo = cpu_to_le32(lower_32_bits(now)); *hi = upper_32_bits(now); } static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) { return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo); } #define ext4_update_tstamp(es, tstamp) \ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \ ktime_get_real_seconds()) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) #define EXT4_SB_REFRESH_INTERVAL_SEC (3600) /* seconds (1 hour) */ #define EXT4_SB_REFRESH_INTERVAL_KB (16384) /* kilobytes (16MB) */ /* * The ext4_maybe_update_superblock() function checks and updates the * superblock if needed. * * This function is designed to update the on-disk superblock only under * certain conditions to prevent excessive disk writes and unnecessary * waking of the disk from sleep. The superblock will be updated if: * 1. More than an hour has passed since the last superblock update, and * 2. More than 16MB have been written since the last superblock update. * * @sb: The superblock */ static void ext4_maybe_update_superblock(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; journal_t *journal = sbi->s_journal; time64_t now; __u64 last_update; __u64 lifetime_write_kbytes; __u64 diff_size; if (sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) || !journal || (journal->j_flags & JBD2_UNMOUNT)) return; now = ktime_get_real_seconds(); last_update = ext4_get_tstamp(es, s_wtime); if (likely(now - last_update < EXT4_SB_REFRESH_INTERVAL_SEC)) return; lifetime_write_kbytes = sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); /* Get the number of kilobytes not written to disk to account * for statistics and compare with a multiple of 16 MB. This * is used to determine when the next superblock commit should * occur (i.e. not more often than once per 16MB if there was * less written in an hour). */ diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); if (diff_size > EXT4_SB_REFRESH_INTERVAL_KB) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int error = is_journal_aborted(journal); struct ext4_journal_cb_entry *jce; BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); ext4_maybe_update_superblock(sb); spin_lock(&sbi->s_md_lock); while (!list_empty(&txn->t_private_list)) { jce = list_entry(txn->t_private_list.next, struct ext4_journal_cb_entry, jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); jce->jce_func(sb, jce, error); spin_lock(&sbi->s_md_lock); } spin_unlock(&sbi->s_md_lock); } /* * This writepage callback for write_cache_pages() * takes care of a few cases after page cleaning. * * write_cache_pages() already checks for dirty pages * and calls clear_page_dirty_for_io(), which we want, * to write protect the pages. * * However, we may have to redirty a page (see below.) */ static int ext4_journalled_writepage_callback(struct folio *folio, struct writeback_control *wbc, void *data) { transaction_t *transaction = (transaction_t *) data; struct buffer_head *bh, *head; struct journal_head *jh; bh = head = folio_buffers(folio); do { /* * We have to redirty a page in these cases: * 1) If buffer is dirty, it means the page was dirty because it * contains a buffer that needs checkpointing. So the dirty bit * needs to be preserved so that checkpointing writes the buffer * properly. * 2) If buffer is not part of the committing transaction * (we may have just accidentally come across this buffer because * inode range tracking is not exact) or if the currently running * transaction already contains this buffer as well, dirty bit * needs to be preserved so that the buffer gets writeprotected * properly on running transaction's commit. */ jh = bh2jh(bh); if (buffer_dirty(bh) || (jh && (jh->b_transaction != transaction || jh->b_next_transaction))) { folio_redirty_for_writepage(wbc, folio); goto out; } } while ((bh = bh->b_this_page) != head); out: return AOP_WRITEPAGE_ACTIVATE; } static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct address_space *mapping = jinode->i_vfs_inode->i_mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; return write_cache_pages(mapping, &wbc, ext4_journalled_writepage_callback, jinode->i_transaction); } static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { int ret; if (ext4_should_journal_data(jinode->i_vfs_inode)) ret = ext4_journalled_submit_inode_data_buffers(jinode); else ret = ext4_normal_submit_inode_data_buffers(jinode); return ret; } static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode) { int ret = 0; if (!ext4_should_journal_data(jinode->i_vfs_inode)) ret = jbd2_journal_finish_inode_data_buffers(jinode); return ret; } static bool system_going_down(void) { return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART; } struct ext4_err_translation { int code; int errno; }; #define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } static struct ext4_err_translation err_translation[] = { EXT4_ERR_TRANSLATE(EIO), EXT4_ERR_TRANSLATE(ENOMEM), EXT4_ERR_TRANSLATE(EFSBADCRC), EXT4_ERR_TRANSLATE(EFSCORRUPTED), EXT4_ERR_TRANSLATE(ENOSPC), EXT4_ERR_TRANSLATE(ENOKEY), EXT4_ERR_TRANSLATE(EROFS), EXT4_ERR_TRANSLATE(EFBIG), EXT4_ERR_TRANSLATE(EEXIST), EXT4_ERR_TRANSLATE(ERANGE), EXT4_ERR_TRANSLATE(EOVERFLOW), EXT4_ERR_TRANSLATE(EBUSY), EXT4_ERR_TRANSLATE(ENOTDIR), EXT4_ERR_TRANSLATE(ENOTEMPTY), EXT4_ERR_TRANSLATE(ESHUTDOWN), EXT4_ERR_TRANSLATE(EFAULT), }; static int ext4_errno_to_code(int errno) { int i; for (i = 0; i < ARRAY_SIZE(err_translation); i++) if (err_translation[i].errno == errno) return err_translation[i].code; return EXT4_ERR_UNKNOWN; } static void save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; spin_lock(&sbi->s_error_lock); sbi->s_add_error_count++; sbi->s_last_error_code = error; sbi->s_last_error_line = line; sbi->s_last_error_ino = ino; sbi->s_last_error_block = block; sbi->s_last_error_func = func; sbi->s_last_error_time = ktime_get_real_seconds(); if (!sbi->s_first_error_time) { sbi->s_first_error_code = error; sbi->s_first_error_line = line; sbi->s_first_error_ino = ino; sbi->s_first_error_block = block; sbi->s_first_error_func = func; sbi->s_first_error_time = sbi->s_last_error_time; } spin_unlock(&sbi->s_error_lock); } /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * * On ext2, we can store the error state of the filesystem in the * superblock. That is not possible on ext4, because we may have other * write ordering constraints on the superblock which prevent us from * writing it out straight away; and given that the journal is about to * be aborted, we can't rely on the current, or future, transactions to * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. * * If force_ro is set, we unconditionally force the filesystem into an * ABORT|READONLY state, unless the error response on the fs has been set to * panic in which case we take the easy way out and panic immediately. This is * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); if (!continue_fs && !sb_rdonly(sb)) { set_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); if (journal) jbd2_journal_abort(journal, -EIO); } if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, error, ino, block, func, line); /* * In case the fs should keep running, we need to writeout * superblock through the journal. Due to lock ordering * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. */ if (continue_fs && journal) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } if (sb_rdonly(sb) || continue_fs) return; ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * EXT4_FLAGS_SHUTDOWN was set which stops all filesystem * modifications. We don't set SB_RDONLY because that requires * sb->s_umount semaphore and setting it without proper remount * procedure is confusing code such as freeze_super() leading to * deadlocks and other problems. */ } static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; /* * If the journal is still running, we have to write out superblock * through the journal to avoid collisions of other journalled sb * updates. * * We use directly jbd2 functions here to avoid recursing back into * ext4 error handling code during handling of previous errors. */ if (!sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; bool call_notify_err = false; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } if (sbi->s_add_error_count > 0) call_notify_err = true; ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } jbd2_journal_stop(handle); if (call_notify_err) ext4_notify_error_sysfs(sbi); return; } write_directly: /* * Write through journal failed. Write sb directly to get error info * out and hope for the best. */ ext4_commit_super(sbi->s_sb); ext4_notify_error_sysfs(sbi); } #define ext4_error_ratelimit(sb) \ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \ "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; va_list args; if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); } fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED); ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, unsigned int line, ext4_fsblk_t block, int error, const char *fmt, ...) { va_list args; struct va_format vaf; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: block %llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } void __ext4_error_file(struct file *file, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct inode *inode = file_inode(file); char pathname[80], *path; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "block %llu: comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, path, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, path, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; switch (errno) { case -EFSCORRUPTED: errstr = "Corrupt filesystem"; break; case -EFSBADCRC: errstr = "Filesystem failed CRC"; break; case -EIO: errstr = "IO failure"; break; case -ENOMEM: errstr = "Out of memory"; break; case -EROFS: if (!sb || (EXT4_SB(sb)->s_journal && EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; break; default: /* If the caller passed in an extra buffer for unknown * errors, textualise them now. Else we just return * NULL. */ if (nbuf) { /* Check for truncated error codes... */ if (snprintf(nbuf, 16, "error %d", -errno) >= 0) errstr = nbuf; } break; } return errstr; } /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ void __ext4_std_error(struct super_block *sb, const char *function, unsigned int line, int errno) { char nbuf[16]; const char *errstr; if (unlikely(ext4_forced_shutdown(sb))) return; /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb)) return; if (ext4_error_ratelimit(sb)) { errstr = ext4_decode_error(sb, errno, nbuf); printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; if (sb) { atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sb) printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); else printk("%sEXT4-fs: %pV\n", prefix, &vaf); va_end(args); } static int ext4_warning_ratelimit(struct super_block *sb) { atomic_inc(&EXT4_SB(sb)->s_warning_count); return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), "EXT4-fs warning"); } void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n", sb->s_id, function, line, &vaf); va_end(args); } void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(inode->i_sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } void __ext4_grp_locked_error(const char *function, unsigned int line, struct super_block *sb, ext4_group_t grp, unsigned long ino, ext4_fsblk_t block, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { struct va_format vaf; va_list args; if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %lu: ", ino); if (block) printk(KERN_CONT "block %llu:", (unsigned long long) block); printk(KERN_CONT "%pV\n", &vaf); va_end(args); } if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } ext4_unlock_group(sb, grp); ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the * filesystem will have already been marked read/only and the * journal has been aborted. We return 1 as a hint to callers * who might what to use the return value from * ext4_grp_locked_error() to distinguish between the * ERRORS_CONT and ERRORS_RO case, and perhaps return more * aggressively from the ext4 function in question, with a * more appropriate error code. */ ext4_lock_group(sb, grp); return; } void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t group, unsigned int flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; if (!grp || !gdp) return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); } if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret && gdp) { int count; count = ext4_free_inodes_count(sb, gdp); percpu_counter_sub(&sbi->s_freeinodes_counter, count); } } } void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; ext4_warning(sb, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); /* leave es->s_feature_*compat flags alone */ /* es->s_uuid will be set by e2fsck if empty */ /* * The rest of the superblock fields should be zero, and if not it * means they are likely already in use, so leave them alone. We * can leave it up to e2fsck to clean up any inconsistencies there. */ } static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; } static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; ext4_msg(sb, KERN_ERR, "sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } #ifdef CONFIG_QUOTA static int ext4_quota_off(struct super_block *sb, int type); static inline void ext4_quotas_off(struct super_block *sb, int type) { BUG_ON(type > EXT4_MAXQUOTAS); /* Use our quota_off function to clear inode flags etc. */ for (type--; type >= 0; type--) ext4_quota_off(sb, type); } /* * This is a helper function which is used in the mount/remount * codepaths (which holds s_umount) to fetch the quota file name. */ static inline char *get_qf_name(struct super_block *sb, struct ext4_sb_info *sbi, int type) { return rcu_dereference_protected(sbi->s_qf_names[type], lockdep_is_held(&sb->s_umount)); } #else static inline void ext4_quotas_off(struct super_block *sb, int type) { } #endif static int ext4_percpu_param_init(struct ext4_sb_info *sbi) { ext4_fsblk_t block; int err; block = ext4_count_free_clusters(sbi->s_sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sbi->s_sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } if (!err) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sbi->s_sb), GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, GFP_KERNEL); if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory"); return err; } static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); } static void ext4_group_desc_free(struct ext4_sb_info *sbi) { struct buffer_head **group_desc; int i; rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); rcu_read_unlock(); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) { struct flex_groups **flex_groups; int i; rcu_read_lock(); flex_groups = rcu_dereference(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } rcu_read_unlock(); } static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int aborted = 0; int err; /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) ext4_msg(sb, KERN_INFO, "unmounting filesystem %pU.", &sb->s_uuid); ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); flush_work(&sbi->s_sb_upd_work); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } } ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); if (!sb_rdonly(sb) && !aborted) { ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!sb_rdonly(sb)) ext4_commit_super(sb); ext4_group_desc_free(sbi); ext4_flex_groups_free(sbi); WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) && percpu_counter_sum(&sbi->s_dirtyclusters_counter)); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA for (int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list * isn't empty. The on-disk one can be non-empty if we've * detected an error and taken the fs readonly, but the * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); ASSERT(list_empty(&sbi->s_orphan)); sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev_file) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(file_bdev(sbi->s_journal_bdev_file)); invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; ext4_stop_mmpd(sbi); brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); } static struct kmem_cache *ext4_inode_cachep; /* * Called inside transaction, so use GFP_NOFS */ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); rwlock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_list); ei->i_es_all_nr = 0; ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_reserved_data_blocks = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); ext4_fc_init_inode(&ei->vfs_inode); mutex_init(&ei->i_fc_lock); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); if (!drop) drop = fscrypt_drop_inode(inode); trace_ext4_drop_inode(inode, drop); return drop; } static void ext4_free_in_core_inode(struct inode *inode) { fscrypt_free_inode(inode); if (!list_empty(&(EXT4_I(inode)->i_fc_list))) { pr_warn("%s: inode %ld still in fc list", __func__, inode->i_ino); } kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); dump_stack(); } if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) && WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks)) ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", inode->i_ino, EXT4_I(inode), EXT4_I(inode)->i_reserved_data_blocks); } static void ext4_shutdown(struct super_block *sb) { ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); } static void init_once(void *foo) { struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); ext4_fc_init_inode(&ei->vfs_inode); } static int __init init_inodecache(void) { ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, offsetof(struct ext4_inode_info, i_data), sizeof_field(struct ext4_inode_info, i_data), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } void ext4_clear_inode(struct inode *inode) { ext4_fc_del(inode); invalidate_inode_buffers(inode); clear_inode(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } fscrypt_put_encryption_info(inode); fsverity_cleanup_inode(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct inode *inode; /* * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static int ext4_nfs_commit_metadata(struct inode *inode) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL }; trace_ext4_nfs_commit_metadata(inode); return ext4_write_inode(inode, &wbc); } #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, .write_dquot = ext4_write_dquot, .acquire_dquot = ext4_acquire_dquot, .release_dquot = ext4_release_dquot, .mark_dirty = ext4_mark_dquot_dirty, .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = ext4_get_projid, .get_inode_usage = ext4_get_inode_usage, .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, .get_nextdqblk = dquot_get_next_dqblk, }; #endif static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, .free_inode = ext4_free_in_core_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, .get_dquots = ext4_get_dquots, #endif }; static const struct export_operations ext4_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, .commit_metadata = ext4_nfs_commit_metadata, }; enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_acl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif }; static const struct constant_table ext4_param_errors[] = { {"continue", EXT4_MOUNT_ERRORS_CONT}, {"panic", EXT4_MOUNT_ERRORS_PANIC}, {"remount-ro", EXT4_MOUNT_ERRORS_RO}, {} }; static const struct constant_table ext4_param_data[] = { {"journal", EXT4_MOUNT_JOURNAL_DATA}, {"ordered", EXT4_MOUNT_ORDERED_DATA}, {"writeback", EXT4_MOUNT_WRITEBACK_DATA}, {} }; static const struct constant_table ext4_param_data_err[] = { {"abort", Opt_data_err_abort}, {"ignore", Opt_data_err_ignore}, {} }; static const struct constant_table ext4_param_jqfmt[] = { {"vfsold", QFMT_VFS_OLD}, {"vfsv0", QFMT_VFS_V0}, {"vfsv1", QFMT_VFS_V1}, {} }; static const struct constant_table ext4_param_dax[] = { {"always", Opt_dax_always}, {"inode", Opt_dax_inode}, {"never", Opt_dax_never}, {} }; /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the * options and the way we show them in _ext4_show_options(). To * keep the changes to a minimum, let's keep the negative options * separate for now. */ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_flag ("bsddf", Opt_bsd_df), fsparam_flag ("minixdf", Opt_minix_df), fsparam_flag ("grpid", Opt_grpid), fsparam_flag ("bsdgroups", Opt_grpid), fsparam_flag ("nogrpid", Opt_nogrpid), fsparam_flag ("sysvgroups", Opt_nogrpid), fsparam_gid ("resgid", Opt_resgid), fsparam_uid ("resuid", Opt_resuid), fsparam_u32 ("sb", Opt_sb), fsparam_enum ("errors", Opt_errors, ext4_param_errors), fsparam_flag ("nouid32", Opt_nouid32), fsparam_flag ("debug", Opt_debug), fsparam_flag ("oldalloc", Opt_removed), fsparam_flag ("orlov", Opt_removed), fsparam_flag ("user_xattr", Opt_user_xattr), fsparam_flag ("acl", Opt_acl), fsparam_flag ("norecovery", Opt_noload), fsparam_flag ("noload", Opt_noload), fsparam_flag ("bh", Opt_removed), fsparam_flag ("nobh", Opt_removed), fsparam_u32 ("commit", Opt_commit), fsparam_u32 ("min_batch_time", Opt_min_batch_time), fsparam_u32 ("max_batch_time", Opt_max_batch_time), fsparam_u32 ("journal_dev", Opt_journal_dev), fsparam_bdev ("journal_path", Opt_journal_path), fsparam_flag ("journal_checksum", Opt_journal_checksum), fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum), fsparam_flag ("journal_async_commit",Opt_journal_async_commit), fsparam_flag ("abort", Opt_abort), fsparam_enum ("data", Opt_data, ext4_param_data), fsparam_enum ("data_err", Opt_data_err, ext4_param_data_err), fsparam_string_empty ("usrjquota", Opt_usrjquota), fsparam_string_empty ("grpjquota", Opt_grpjquota), fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt), fsparam_flag ("grpquota", Opt_grpquota), fsparam_flag ("quota", Opt_quota), fsparam_flag ("noquota", Opt_noquota), fsparam_flag ("usrquota", Opt_usrquota), fsparam_flag ("prjquota", Opt_prjquota), fsparam_flag ("barrier", Opt_barrier), fsparam_u32 ("barrier", Opt_barrier), fsparam_flag ("nobarrier", Opt_nobarrier), fsparam_flag ("i_version", Opt_removed), fsparam_flag ("dax", Opt_dax), fsparam_enum ("dax", Opt_dax_type, ext4_param_dax), fsparam_u32 ("stripe", Opt_stripe), fsparam_flag ("delalloc", Opt_delalloc), fsparam_flag ("nodelalloc", Opt_nodelalloc), fsparam_flag ("warn_on_error", Opt_warn_on_error), fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), fsparam_u32 ("debug_want_extra_isize", Opt_debug_want_extra_isize), fsparam_flag ("mblk_io_submit", Opt_removed), fsparam_flag ("nomblk_io_submit", Opt_removed), fsparam_flag ("block_validity", Opt_block_validity), fsparam_flag ("noblock_validity", Opt_noblock_validity), fsparam_u32 ("inode_readahead_blks", Opt_inode_readahead_blks), fsparam_u32 ("journal_ioprio", Opt_journal_ioprio), fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc), fsparam_flag ("dioread_nolock", Opt_dioread_nolock), fsparam_flag ("nodioread_nolock", Opt_dioread_lock), fsparam_flag ("dioread_lock", Opt_dioread_lock), fsparam_flag ("discard", Opt_discard), fsparam_flag ("nodiscard", Opt_nodiscard), fsparam_u32 ("init_itable", Opt_init_itable), fsparam_flag ("init_itable", Opt_init_itable), fsparam_flag ("noinit_itable", Opt_noinit_itable), #ifdef CONFIG_EXT4_DEBUG fsparam_flag ("fc_debug_force", Opt_fc_debug_force), fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay), #endif fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag ("inlinecrypt", Opt_inlinecrypt), fsparam_flag ("nombcache", Opt_nombcache), fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */ fsparam_flag ("prefetch_block_bitmaps", Opt_removed), fsparam_flag ("no_prefetch_block_bitmaps", Opt_no_prefetch_block_bitmaps), fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */ fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */ {} }; #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 #ifdef CONFIG_QUOTA #define MOPT_Q 0 #define MOPT_QFMT 0x0010 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif #define MOPT_NO_EXT2 0x0020 #define MOPT_NO_EXT3 0x0040 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) #define MOPT_SKIP 0x0080 #define MOPT_2 0x0100 static const struct mount_opts { int token; int mount_opt; int flags; } ext4_mount_opts[] = { {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET}, {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR}, {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET}, {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR}, {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET}, {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR}, {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET}, {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR}, {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_data_err, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, {Opt_dax_type, 0, MOPT_EXT4_ONLY}, {Opt_journal_dev, 0, MOPT_NO_EXT2}, {Opt_journal_path, 0, MOPT_NO_EXT2}, {Opt_journal_ioprio, 0, MOPT_NO_EXT2}, {Opt_data, 0, MOPT_NO_EXT2}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA, MOPT_SET | MOPT_Q}, {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA, MOPT_SET | MOPT_Q}, {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; #if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; unsigned int version; } ext4_sb_encoding_map[] = { {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct ext4_sb_encodings * ext4_sb_read_encoding(const struct ext4_super_block *es) { __u16 magic = le16_to_cpu(es->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) if (magic == ext4_sb_encoding_map[i].magic) return &ext4_sb_encoding_map[i]; return NULL; } #endif #define EXT4_SPEC_JQUOTA (1 << 0) #define EXT4_SPEC_JQFMT (1 << 1) #define EXT4_SPEC_DATAJ (1 << 2) #define EXT4_SPEC_SB_BLOCK (1 << 3) #define EXT4_SPEC_JOURNAL_DEV (1 << 4) #define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5) #define EXT4_SPEC_s_want_extra_isize (1 << 7) #define EXT4_SPEC_s_max_batch_time (1 << 8) #define EXT4_SPEC_s_min_batch_time (1 << 9) #define EXT4_SPEC_s_inode_readahead_blks (1 << 10) #define EXT4_SPEC_s_li_wait_mult (1 << 11) #define EXT4_SPEC_s_max_dir_size_kb (1 << 12) #define EXT4_SPEC_s_stripe (1 << 13) #define EXT4_SPEC_s_resuid (1 << 14) #define EXT4_SPEC_s_resgid (1 << 15) #define EXT4_SPEC_s_commit_interval (1 << 16) #define EXT4_SPEC_s_fc_debug_max_replay (1 << 17) #define EXT4_SPEC_s_sb_block (1 << 18) #define EXT4_SPEC_mb_optimize_scan (1 << 19) struct ext4_fs_context { char *s_qf_names[EXT4_MAXQUOTAS]; struct fscrypt_dummy_policy dummy_enc_policy; int s_jquota_fmt; /* Format of quota to use */ #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif unsigned short qname_spec; unsigned long vals_s_flags; /* Bits to set in s_flags */ unsigned long mask_s_flags; /* Bits changed in s_flags */ unsigned long journal_devnum; unsigned long s_commit_interval; unsigned long s_stripe; unsigned int s_inode_readahead_blks; unsigned int s_want_extra_isize; unsigned int s_li_wait_mult; unsigned int s_max_dir_size_kb; unsigned int journal_ioprio; unsigned int vals_s_mount_opt; unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; u32 s_min_batch_time; kuid_t s_resuid; kgid_t s_resgid; ext4_fsblk_t s_sb_block; }; static void ext4_fc_free(struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; int i; if (!ctx) return; for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(ctx->s_qf_names[i]); fscrypt_free_dummy_policy(&ctx->dummy_enc_policy); kfree(ctx); } int ext4_init_fs_context(struct fs_context *fc) { struct ext4_fs_context *ctx; ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &ext4_context_ops; return 0; } #ifdef CONFIG_QUOTA /* * Note the name of the specified quota file. */ static int note_qf_name(struct fs_context *fc, int qtype, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; char *qname; if (param->size < 1) { ext4_msg(NULL, KERN_ERR, "Missing quota name"); return -EINVAL; } if (strchr(param->string, '/')) { ext4_msg(NULL, KERN_ERR, "quotafile must be on filesystem root"); return -EINVAL; } if (ctx->s_qf_names[qtype]) { if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) { ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(qtype)); return -EINVAL; } return 0; } qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); if (!qname) { ext4_msg(NULL, KERN_ERR, "Not enough memory for storing quotafile name"); return -ENOMEM; } ctx->s_qf_names[qtype] = qname; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } /* * Clear the name of the specified quota file. */ static int unnote_qf_name(struct fs_context *fc, int qtype) { struct ext4_fs_context *ctx = fc->fs_private; kfree(ctx->s_qf_names[qtype]); ctx->s_qf_names[qtype] = NULL; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } #endif static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, struct ext4_fs_context *ctx) { int err; if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption option not supported"); return -EINVAL; } err = fscrypt_parse_test_dummy_encryption(param, &ctx->dummy_enc_policy); if (err == -EINVAL) { ext4_msg(NULL, KERN_WARNING, "Value of option \"%s\" is unrecognized", param->key); } else if (err == -EEXIST) { ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return err; } #define EXT4_SET_CTX(name) \ static inline __maybe_unused \ void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name |= flag; \ } #define EXT4_CLEAR_CTX(name) \ static inline __maybe_unused \ void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name &= ~flag; \ } #define EXT4_TEST_CTX(name) \ static inline unsigned long \ ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ return (ctx->vals_s_##name & flag); \ } EXT4_SET_CTX(flags); /* set only */ EXT4_SET_CTX(mount_opt); EXT4_CLEAR_CTX(mount_opt); EXT4_TEST_CTX(mount_opt); EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; struct fs_parse_result result; const struct mount_opts *m; int is_remount; int token; token = fs_parse(fc, ext4_param_specs, param, &result); if (token < 0) return token; is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; ctx->opt_flags |= m->flags; if (m->flags & MOPT_EXPLICIT) { if (m->mount_opt & EXT4_MOUNT_DELALLOC) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC); } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM); } else return -EINVAL; } if (m->flags & MOPT_NOSUPPORT) { ext4_msg(NULL, KERN_ERR, "%s option not supported", param->key); return 0; } switch (token) { #ifdef CONFIG_QUOTA case Opt_usrjquota: if (!*param->string) return unnote_qf_name(fc, USRQUOTA); else return note_qf_name(fc, USRQUOTA, param); case Opt_grpjquota: if (!*param->string) return unnote_qf_name(fc, GRPQUOTA); else return note_qf_name(fc, GRPQUOTA, param); #endif case Opt_sb: if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { ext4_msg(NULL, KERN_WARNING, "Ignoring %s option on remount", param->key); } else { ctx->s_sb_block = result.uint_32; ctx->spec |= EXT4_SPEC_s_sb_block; } return 0; case Opt_removed: ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); #else ext4_msg(NULL, KERN_ERR, "inline encryption not supported"); #endif return 0; case Opt_errors: ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK); ctx_set_mount_opt(ctx, result.uint_32); return 0; #ifdef CONFIG_QUOTA case Opt_jqfmt: ctx->s_jquota_fmt = result.uint_32; ctx->spec |= EXT4_SPEC_JQFMT; return 0; #endif case Opt_data: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); ctx_set_mount_opt(ctx, result.uint_32); ctx->spec |= EXT4_SPEC_DATAJ; return 0; case Opt_commit: if (result.uint_32 == 0) result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE; else if (result.uint_32 > INT_MAX / HZ) { ext4_msg(NULL, KERN_ERR, "Invalid commit interval %d, " "must be smaller than %d", result.uint_32, INT_MAX / HZ); return -EINVAL; } ctx->s_commit_interval = HZ * result.uint_32; ctx->spec |= EXT4_SPEC_s_commit_interval; return 0; case Opt_debug_want_extra_isize: if ((result.uint_32 & 1) || (result.uint_32 < 4)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", result.uint_32); return -EINVAL; } ctx->s_want_extra_isize = result.uint_32; ctx->spec |= EXT4_SPEC_s_want_extra_isize; return 0; case Opt_max_batch_time: ctx->s_max_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_batch_time; return 0; case Opt_min_batch_time: ctx->s_min_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_min_batch_time; return 0; case Opt_inode_readahead_blks: if (result.uint_32 && (result.uint_32 > (1 << 30) || !is_power_of_2(result.uint_32))) { ext4_msg(NULL, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); return -EINVAL; } ctx->s_inode_readahead_blks = result.uint_32; ctx->spec |= EXT4_SPEC_s_inode_readahead_blks; return 0; case Opt_init_itable: ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE); ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; if (param->type == fs_value_is_string) ctx->s_li_wait_mult = result.uint_32; ctx->spec |= EXT4_SPEC_s_li_wait_mult; return 0; case Opt_max_dir_size_kb: ctx->s_max_dir_size_kb = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_dir_size_kb; return 0; #ifdef CONFIG_EXT4_DEBUG case Opt_fc_debug_max_replay: ctx->s_fc_debug_max_replay = result.uint_32; ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay; return 0; #endif case Opt_stripe: ctx->s_stripe = result.uint_32; ctx->spec |= EXT4_SPEC_s_stripe; return 0; case Opt_resuid: ctx->s_resuid = result.uid; ctx->spec |= EXT4_SPEC_s_resuid; return 0; case Opt_resgid: ctx->s_resgid = result.gid; ctx->spec |= EXT4_SPEC_s_resgid; return 0; case Opt_journal_dev: if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } ctx->journal_devnum = result.uint_32; ctx->spec |= EXT4_SPEC_JOURNAL_DEV; return 0; case Opt_journal_path: { struct inode *journal_inode; struct path path; int error; if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } error = fs_lookup_param(fc, param, 1, LOOKUP_FOLLOW, &path); if (error) { ext4_msg(NULL, KERN_ERR, "error: could not find " "journal device path"); return -EINVAL; } journal_inode = d_inode(path.dentry); ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev); ctx->spec |= EXT4_SPEC_JOURNAL_DEV; path_put(&path); return 0; } case Opt_journal_ioprio: if (result.uint_32 > 7) { ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); return -EINVAL; } ctx->journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32); ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO; return 0; case Opt_test_dummy_encryption: return ext4_parse_test_dummy_encryption(param, ctx); case Opt_dax: case Opt_dax_type: #ifdef CONFIG_FS_DAX { int type = (token == Opt_dax) ? Opt_dax : result.uint_32; switch (type) { case Opt_dax: case Opt_dax_always: ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); break; case Opt_dax_never: ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); break; case Opt_dax_inode: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); /* Strictly for printing options */ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE); break; } return 0; } #else ext4_msg(NULL, KERN_INFO, "dax option not supported"); return -EINVAL; #endif case Opt_data_err: if (result.uint_32 == Opt_data_err_abort) ctx_set_mount_opt(ctx, m->mount_opt); else if (result.uint_32 == Opt_data_err_ignore) ctx_clear_mount_opt(ctx, m->mount_opt); return 0; case Opt_mb_optimize_scan: if (result.int_32 == 1) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else if (result.int_32 == 0) { ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else { ext4_msg(NULL, KERN_WARNING, "mb_optimize_scan should be set to 0 or 1."); return -EINVAL; } return 0; } /* * At this point we should only be getting options requiring MOPT_SET, * or MOPT_CLEAR. Anything else is a bug */ if (m->token == Opt_err) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } else { unsigned int set = 0; if ((param->type == fs_value_is_flag) || result.uint_32 > 0) set = 1; if (m->flags & MOPT_CLEAR) set = !set; else if (unlikely(!(m->flags & MOPT_SET))) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } if (m->flags & MOPT_2) { if (set != 0) ctx_set_mount_opt2(ctx, m->mount_opt); else ctx_clear_mount_opt2(ctx, m->mount_opt); } else { if (set != 0) ctx_set_mount_opt(ctx, m->mount_opt); else ctx_clear_mount_opt(ctx, m->mount_opt); } } return 0; } static int parse_options(struct fs_context *fc, char *options) { struct fs_parameter param; int ret; char *key; if (!options) return 0; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); param.type = fs_value_is_flag; param.string = NULL; if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); param.string = kmemdup_nul(value, v_len, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } param.key = key; param.size = v_len; ret = ext4_parse_param(fc, ¶m); kfree(param.string); if (ret < 0) return ret; } } ret = ext4_validate_options(fc); if (ret < 0) return ret; return 0; } static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); char *s_mount_opts = NULL; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; if (!sbi->s_es->s_mount_opts[0]) return 0; s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, sizeof(sbi->s_es->s_mount_opts), GFP_KERNEL); if (!s_mount_opts) return ret; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); if (!fc) goto out_free; s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!s_ctx) goto out_free; fc->fs_private = s_ctx; fc->s_fs_info = sbi; ret = parse_options(fc, s_mount_opts); if (ret < 0) goto parse_failed; ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) { parse_failed: ext4_msg(sb, KERN_WARNING, "failed to parse options in superblock: %s", s_mount_opts); ret = 0; goto out_free; } if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV) m_ctx->journal_devnum = s_ctx->journal_devnum; if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO) m_ctx->journal_ioprio = s_ctx->journal_ioprio; ext4_apply_options(fc, sb); ret = 0; out_free: if (fc) { ext4_fc_free(fc); kfree(fc); } kfree(s_mount_opts); return ret; } static void ext4_apply_quota_options(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA bool quota_feature = ext4_has_feature_quota(sb); struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); char *qname; int i; if (quota_feature) return; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; qname = ctx->s_qf_names[i]; /* May be NULL */ if (qname) set_opt(sb, QUOTA); ctx->s_qf_names[i] = NULL; qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) kfree_rcu_mightsleep(qname); } } if (ctx->spec & EXT4_SPEC_JQFMT) sbi->s_jquota_fmt = ctx->s_jquota_fmt; #endif } /* * Check quota settings consistency. */ static int ext4_check_quota_consistency(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); bool quota_feature = ext4_has_feature_quota(sb); bool quota_loaded = sb_any_quota_loaded(sb); bool usr_qf_name, grp_qf_name, usrquota, grpquota; int quota_flags, i; /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ if (ctx_test_mount_opt(ctx, EXT4_MOUNT_PRJQUOTA) && !ext4_has_feature_project(sb)) { ext4_msg(NULL, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); return -EINVAL; } quota_flags = EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA; if (quota_loaded && ctx->mask_s_mount_opt & quota_flags && !ctx_test_mount_opt(ctx, quota_flags)) goto err_quota_change; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; if (quota_loaded && !!sbi->s_qf_names[i] != !!ctx->s_qf_names[i]) goto err_jquota_change; if (sbi->s_qf_names[i] && ctx->s_qf_names[i] && strcmp(get_qf_name(sb, sbi, i), ctx->s_qf_names[i]) != 0) goto err_jquota_specified; } if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Journaled quota options ignored when " "QUOTA feature is enabled"); return 0; } } if (ctx->spec & EXT4_SPEC_JQFMT) { if (sbi->s_jquota_fmt != ctx->s_jquota_fmt && quota_loaded) goto err_jquota_change; if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Quota format mount options " "ignored when QUOTA feature is enabled"); return 0; } } /* Make sure we don't mix old and new quota format */ usr_qf_name = (get_qf_name(sb, sbi, USRQUOTA) || ctx->s_qf_names[USRQUOTA]); grp_qf_name = (get_qf_name(sb, sbi, GRPQUOTA) || ctx->s_qf_names[GRPQUOTA]); usrquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || test_opt(sb, USRQUOTA)); grpquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) || test_opt(sb, GRPQUOTA)); if (usr_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); usrquota = false; } if (grp_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); grpquota = false; } if (usr_qf_name || grp_qf_name) { if (usrquota || grpquota) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } if (!(ctx->spec & EXT4_SPEC_JQFMT || sbi->s_jquota_fmt)) { ext4_msg(NULL, KERN_ERR, "journaled quota format " "not specified"); return -EINVAL; } } return 0; err_quota_change: ext4_msg(NULL, KERN_ERR, "Cannot change quota options when quota turned on"); return -EINVAL; err_jquota_change: ext4_msg(NULL, KERN_ERR, "Cannot change journaled quota " "options when quota turned on"); return -EINVAL; err_jquota_specified: ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(i)); return -EINVAL; #else return 0; #endif } static int ext4_check_test_dummy_encryption(const struct fs_context *fc, struct super_block *sb) { const struct ext4_fs_context *ctx = fc->fs_private; const struct ext4_sb_info *sbi = EXT4_SB(sb); if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) return 0; if (!ext4_has_feature_encrypt(sb)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption requires encrypt feature"); return -EINVAL; } /* * This mount option is just for testing, and it's not worthwhile to * implement the extra complexity (e.g. RCU protection) that would be * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Can't set or change test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure s_mount_opts didn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&sbi->s_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return 0; } static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, struct super_block *sb) { if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy) || /* if already set, it was already verified to be the same */ fscrypt_is_dummy_policy_set(&EXT4_SB(sb)->s_dummy_enc_policy)) return; EXT4_SB(sb)->s_dummy_enc_policy = ctx->dummy_enc_policy; memset(&ctx->dummy_enc_policy, 0, sizeof(ctx->dummy_enc_policy)); ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); } static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; int err; if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext2"); return -EINVAL; } if ((ctx->opt_flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext3"); return -EINVAL; } if (ctx->s_want_extra_isize > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", ctx->s_want_extra_isize); return -EINVAL; } err = ext4_check_test_dummy_encryption(fc, sb); if (err) return err; if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { if (!sbi->s_journal) { ext4_msg(NULL, KERN_WARNING, "Remounting file system with no journal " "so ignoring journalled data option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); } else if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS) != test_opt(sb, DATA_FLAGS)) { ext4_msg(NULL, KERN_ERR, "Cannot change data mode " "on remount"); return -EINVAL; } } if (is_remount) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { fail_dax_change_remount: ext4_msg(NULL, KERN_ERR, "can't change " "dax mount option while remounting"); return -EINVAL; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER) && (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) { goto fail_dax_change_remount; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE) && ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { goto fail_dax_change_remount; } } return ext4_check_quota_consistency(fc, sb); } static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; sbi->s_mount_opt &= ~ctx->mask_s_mount_opt; sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; }) APPLY(s_commit_interval); APPLY(s_stripe); APPLY(s_max_batch_time); APPLY(s_min_batch_time); APPLY(s_want_extra_isize); APPLY(s_inode_readahead_blks); APPLY(s_max_dir_size_kb); APPLY(s_li_wait_mult); APPLY(s_resgid); APPLY(s_resuid); #ifdef CONFIG_EXT4_DEBUG APPLY(s_fc_debug_max_replay); #endif ext4_apply_quota_options(fc, sb); ext4_apply_test_dummy_encryption(ctx, sb); } static int ext4_validate_options(struct fs_context *fc) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; char *usr_qf_name, *grp_qf_name; usr_qf_name = ctx->s_qf_names[USRQUOTA]; grp_qf_name = ctx->s_qf_names[GRPQUOTA]; if (usr_qf_name || grp_qf_name) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) && usr_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) && grp_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA)) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } } #endif return 1; } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; switch (sbi->s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } rcu_read_lock(); usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); if (usr_qf_name) seq_show_option(seq, "usrjquota", usr_qf_name); if (grp_qf_name) seq_show_option(seq, "grpjquota", grp_qf_name); rcu_read_unlock(); #endif } static const char *token2str(int token) { const struct fs_parameter_spec *spec; for (spec = ext4_param_specs; spec->name != NULL; spec++) if (spec->opt == token && !spec->type) break; return spec->name; } /* * Show an option if * - it's set to a non-default value OR * - if the per-sb default is different from the global default */ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, int nodefs) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; #define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep) #define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg) if (sbi->s_sb_block != 1) SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block); for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; int opt_2 = m->flags & MOPT_2; unsigned int mount_opt, def_mount_opt; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || m->flags & MOPT_SKIP) continue; if (opt_2) { mount_opt = sbi->s_mount_opt2; def_mount_opt = sbi->s_def_mount_opt2; } else { mount_opt = sbi->s_mount_opt; def_mount_opt = sbi->s_def_mount_opt; } /* skip if same as the default */ if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) continue; /* select Opt_noFoo vs Opt_Foo */ if ((want_set && (mount_opt & m->mount_opt) != m->mount_opt) || (!want_set && (mount_opt & m->mount_opt))) continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) SEQ_OPTS_PRINT("resuid=%u", from_kuid_munged(&init_user_ns, sbi->s_resuid)); if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) SEQ_OPTS_PRINT("resgid=%u", from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) SEQ_OPTS_PUTS("errors=continue"); if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) SEQ_OPTS_PUTS("errors=panic"); if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ); if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) SEQ_OPTS_PUTS("data=ordered"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) SEQ_OPTS_PUTS("data=writeback"); } if (nodefs || sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) SEQ_OPTS_PRINT("inode_readahead_blks=%u", sbi->s_inode_readahead_blks); if (test_opt(sb, INIT_INODE_TABLE) && (nodefs || (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); if (nodefs || sbi->s_max_dir_size_kb) SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); fscrypt_show_test_dummy_encryption(seq, sep, sb); if (sb->s_flags & SB_INLINECRYPT) SEQ_OPTS_PUTS("inlinecrypt"); if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); else SEQ_OPTS_PUTS("dax=always"); } else if (test_opt2(sb, DAX_NEVER)) { SEQ_OPTS_PUTS("dax=never"); } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && !test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=0"); } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=1"); } if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) SEQ_OPTS_PUTS("prefetch_block_bitmaps"); ext4_show_quota_options(seq, sb); return 0; } static int ext4_show_options(struct seq_file *seq, struct dentry *root) { return _ext4_show_options(seq, root->d_sb, 0); } int ext4_seq_options_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_putc(seq, '\n'); return rc; } static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; goto done; } if (read_only) goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); else if (sbi->s_mount_state & EXT4_ERROR_FS) ext4_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) ext4_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (ext4_get_tstamp(es, s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds())) ext4_msg(sb, KERN_WARNING, "warning: checktime reached, " "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); ext4_update_tstamp(es, s_mtime); if (sbi->s_journal) { ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); return err; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; size = ext4_flex_group(sbi, ngroup - 1) + 1; if (size <= sbi->s_flex_groups_allocated) return 0; new_groups = kvzalloc(roundup_pow_of_two(size * sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { ext4_msg(sb, KERN_ERR, "not enough memory for %d flex group pointers", size); return -ENOMEM; } for (i = sbi->s_flex_groups_allocated; i < size; i++) { new_groups[i] = kvzalloc(roundup_pow_of_two( sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { for (j = sbi->s_flex_groups_allocated; j < i; j++) kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); return -ENOMEM; } } rcu_read_lock(); old_groups = rcu_dereference(sbi->s_flex_groups); if (old_groups) memcpy(new_groups, old_groups, (sbi->s_flex_groups_allocated * sizeof(struct flex_groups *))); rcu_read_unlock(); rcu_assign_pointer(sbi->s_flex_groups, new_groups); sbi->s_flex_groups_allocated = size; if (old_groups) ext4_kvfree_array_rcu(old_groups); return 0; } static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct flex_groups *fg; ext4_group_t flex_group; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) goto failed; for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), &fg->free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; failed: return 0; } static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { int offset = offsetof(struct ext4_group_desc, bg_checksum); __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __u32 csum32; __u16 dummy_csum = 0; csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset); csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); if (offset < sbi->s_desc_size) csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset, sbi->s_desc_size - offset); crc = csum32 & 0xFFFF; goto out; } /* old crc16 code */ if (!ext4_has_feature_gdt_csum(sb)) return 0; crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, sbi->s_desc_size - offset); out: return cpu_to_le16(crc); } int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp))) return 0; return 1; } void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (!ext4_has_group_desc_csum(sb)) return; gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp); } /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; if (ext4_has_feature_flex_bg(sb)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); if ((grp == sbi->s_groups_count) && !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap >= sb_block + 1 && block_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap >= sb_block + 1 && inode_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_table >= sb_block + 1 && inode_table <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!sb_rdonly(sb)) { ext4_unlock_group(sb, i); return 0; } } ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } if (NULL != first_not_zeroed) *first_not_zeroed = grp; return 1; } /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk * extent format containers, within a sector_t, and within i_blocks * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * * However there is other limiting factor. We do store extents in the form * of starting block and length, hence the resulting length of the extent * covering maximum file size must fit into on-disk format containers as * well. Given that length is always by 1 unit bigger than max unit (because * we count 0 as well) we have to lower the s_maxbytes by one fs block. * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) { loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (blkbits - 9); upper_limit <<= blkbits; } /* * 32-bit extent-start container, ee_block. We lower the maxbytes * by one fs block, so ee_len can cover the extent of maximum file * size */ res = (1LL << 32) - 1; res <<= blkbits; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) res = upper_limit; return res; } /* * Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks. * We need to be 1 filesystem block less than the 2^48 sector limit. */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { loff_t upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; unsigned int ppb = 1 << (bits - 2); /* * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field * represents total file blocks in 2^32 512-byte sectors == * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (bits - 9); } else { /* * We use 48 bit ext4_inode i_blocks * With EXT4_HUGE_FILE_FL set the i_blocks * represent total number of blocks in * file system block size */ upper_limit = (1LL << 48) - 1; } /* Compute how many blocks we can address by block tree */ res += ppb; res += ppb * ppb; res += ((loff_t)ppb) * ppb * ppb; /* Compute how many metadata blocks are needed */ meta_blocks = 1; meta_blocks += 1 + ppb; meta_blocks += 1 + ppb + ppb * ppb; /* Does block tree limit file size? */ if (res + meta_blocks <= upper_limit) goto check_lfs; res = upper_limit; /* How many metadata blocks are needed for addressing upper_limit? */ upper_limit -= EXT4_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; upper_limit -= ppb; /* double indirect blocks */ if (upper_limit < ppb * ppb) { meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb); res -= meta_blocks; goto check_lfs; } meta_blocks += 1 + ppb; upper_limit -= ppb * ppb; /* tripple indirect blocks for the rest */ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) + DIV_ROUND_UP_ULL(upper_limit, ppb*ppb); res -= meta_blocks; check_lfs: res <<= bits; if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; return res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; int has_super = 0; first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg) return logical_sb_block + nr + 1; bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; /* * If we have a meta_bg fs with 1k blocks, group 0's GDT is at * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled * on modern mke2fs or blksize > 1k on older mke2fs) then we must * compensate. */ if (sb->s_blocksize == 1024 && nr == 0 && le32_to_cpu(sbi->s_es->s_first_data_block) == 0) has_super++; return (has_super + ext4_group_first_block_no(sb, bg)); } /** * ext4_get_stripe_size: Get the stripe size. * @sbi: In memory super block info * * If we have specified it via mount option, then * use the mount option value. If the value specified at mount time is * greater than the blocks per group use the super block value. * If the super block value is greater than blocks per group return 0. * Allocator needs it be less than blocks per group. * */ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) { unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); unsigned long stripe_width = le32_to_cpu(sbi->s_es->s_raid_stripe_width); int ret; if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) ret = sbi->s_stripe; else if (stripe_width && stripe_width <= sbi->s_blocks_per_group) ret = stripe_width; else if (stride && stride <= sbi->s_blocks_per_group) ret = stride; else ret = 0; /* * If the stripe width is 1, this makes no sense and * we set it to 0 to turn off stripe handling code. */ if (ret <= 1) ret = 0; return ret; } /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. * Returns 1 if this filesystem can be mounted as requested, * 0 if it cannot be. */ int ext4_feature_set_ok(struct super_block *sb, int readonly) { if (ext4_has_unknown_ext4_incompat_features(sb)) { ext4_msg(sb, KERN_ERR, "Couldn't mount because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & ~EXT4_FEATURE_INCOMPAT_SUPP)); return 0; } if (!IS_ENABLED(CONFIG_UNICODE) && ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " "mounted without CONFIG_UNICODE"); return 0; } if (readonly) return 1; if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); sb->s_flags |= SB_RDONLY; return 1; } /* Check that feature set is OK for a read-write mount */ if (ext4_has_unknown_ext4_ro_compat_features(sb)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " "extents feature\n"); return 0; } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ return 1; } /* * This function is called once a day if we have errors logged * on the file system */ static void print_daily_error_info(struct timer_list *t) { struct ext4_sb_info *sbi = from_timer(sbi, t, s_err_report); struct super_block *sb = sbi->s_sb; struct ext4_super_block *es = sbi->s_es; if (es->s_error_count) /* fsck newer than v1.41.13 is needed to clean this condition. */ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, le32_to_cpu(es->s_first_error_line)); if (es->s_first_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_first_error_ino)); if (es->s_first_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_first_error_block)); printk(KERN_CONT "\n"); } if (es->s_last_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, le32_to_cpu(es->s_last_error_line)); if (es->s_last_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_last_error_ino)); if (es->s_last_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_last_error_block)); printk(KERN_CONT "\n"); } mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } /* Find next suitable group and run ext4_init_inode_table */ static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; struct super_block *sb = elr->lr_super; ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; ext4_group_t group = elr->lr_next_group; unsigned int prefetch_ios = 0; int ret = 0; int nr = EXT4_SB(sb)->s_mb_prefetch; u64 start_time; if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { elr->lr_next_group = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); ext4_mb_prefetch_fini(sb, elr->lr_next_group, nr); trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, nr); if (group >= elr->lr_next_group) { ret = 1; if (elr->lr_first_not_zeroed != ngroups && !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { elr->lr_next_group = elr->lr_first_not_zeroed; elr->lr_mode = EXT4_LI_MODE_ITABLE; ret = 0; } } return ret; } for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; break; } if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } if (group >= ngroups) ret = 1; if (!ret) { start_time = ktime_get_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) * EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } return ret; } /* * Remove lr_request from the list_request and free the * request structure. Should be called with li_list_mtx held */ static void ext4_remove_li_request(struct ext4_li_request *elr) { if (!elr) return; list_del(&elr->lr_request); EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } static void ext4_unregister_li_request(struct super_block *sb) { mutex_lock(&ext4_li_mtx); if (!ext4_li_info) { mutex_unlock(&ext4_li_mtx); return; } mutex_lock(&ext4_li_info->li_list_mtx); ext4_remove_li_request(EXT4_SB(sb)->s_li_request); mutex_unlock(&ext4_li_info->li_list_mtx); mutex_unlock(&ext4_li_mtx); } static struct task_struct *ext4_lazyinit_task; /* * This is the function where ext4lazyinit thread lives. It walks * through the request list searching for next scheduled filesystem. * When such a fs is found, run the lazy initialization request * (ext4_rn_li_request) and keep track of the time spend in this * function. Based on that time we compute next schedule time of * the request. When walking through the list is complete, compute * next waking time and put itself into sleep. */ static int ext4_lazyinit_thread(void *arg) { struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; BUG_ON(NULL == eli); set_freezable(); cont_thread: while (true) { bool next_wakeup_initialized = false; next_wakeup = 0; mutex_lock(&eli->li_list_mtx); if (list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); goto exit_thread; } list_for_each_safe(pos, n, &eli->li_request_list) { int err = 0; int progress = 0; elr = list_entry(pos, struct ext4_li_request, lr_request); if (time_before(jiffies, elr->lr_next_sched)) { if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } continue; } if (down_read_trylock(&elr->lr_super->s_umount)) { if (sb_start_write_trylock(elr->lr_super)) { progress = 1; /* * We hold sb->s_umount, sb can not * be removed from the list, it is * now safe to drop li_list_mtx */ mutex_unlock(&eli->li_list_mtx); err = ext4_run_li_request(elr); sb_end_write(elr->lr_super); mutex_lock(&eli->li_list_mtx); n = pos->next; } up_read((&elr->lr_super->s_umount)); } /* error, remove the lazy_init job */ if (err) { ext4_remove_li_request(elr); continue; } if (!progress) { elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } } mutex_unlock(&eli->li_list_mtx); try_to_freeze(); cur = jiffies; if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) { cond_resched(); continue; } schedule_timeout_interruptible(next_wakeup - cur); if (kthread_should_stop()) { ext4_clear_request_list(); goto exit_thread; } } exit_thread: /* * It looks like the request list is empty, but we need * to check it under the li_list_mtx lock, to prevent any * additions into it, and of course we should lock ext4_li_mtx * to atomically free the list and ext4_li_info, because at * this point another ext4 filesystem could be registering * new one. */ mutex_lock(&ext4_li_mtx); mutex_lock(&eli->li_list_mtx); if (!list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); mutex_unlock(&ext4_li_mtx); goto cont_thread; } mutex_unlock(&eli->li_list_mtx); kfree(ext4_li_info); ext4_li_info = NULL; mutex_unlock(&ext4_li_mtx); return 0; } static void ext4_clear_request_list(void) { struct list_head *pos, *n; struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); ext4_remove_li_request(elr); } mutex_unlock(&ext4_li_info->li_list_mtx); } static int ext4_run_lazyinit_thread(void) { ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); if (IS_ERR(ext4_lazyinit_task)) { int err = PTR_ERR(ext4_lazyinit_task); ext4_clear_request_list(); kfree(ext4_li_info); ext4_li_info = NULL; printk(KERN_CRIT "EXT4-fs: error %d creating inode table " "initialization thread\n", err); return err; } ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; return 0; } /* * Check whether it make sense to run itable init. thread or not. * If there is at least one uninitialized inode table, return * corresponding group number, else the loop goes through all * groups and return total number of groups. */ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) { ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; struct ext4_group_desc *gdp = NULL; if (!ext4_has_group_desc_csum(sb)) return ngroups; for (group = 0; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) continue; if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } return group; } static int ext4_li_info_new(void) { struct ext4_lazy_init *eli = NULL; eli = kzalloc(sizeof(*eli), GFP_KERNEL); if (!eli) return -ENOMEM; INIT_LIST_HEAD(&eli->li_request_list); mutex_init(&eli->li_list_mtx); eli->li_state |= EXT4_LAZYINIT_QUIT; ext4_li_info = eli; return 0; } static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); if (!elr) return NULL; elr->lr_super = sb; elr->lr_first_not_zeroed = start; if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) { elr->lr_mode = EXT4_LI_MODE_ITABLE; elr->lr_next_group = start; } else { elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; } /* * Randomize first schedule time of the request to * spread the inode table initialization requests * better. */ elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr = NULL; ext4_group_t ngroups = sbi->s_groups_count; int ret = 0; mutex_lock(&ext4_li_mtx); if (sbi->s_li_request != NULL) { /* * Reset timeout so it can be computed again, because * s_li_wait_mult might have changed. */ sbi->s_li_request->lr_timeout = 0; goto out; } if (sb_rdonly(sb) || (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); if (!elr) { ret = -ENOMEM; goto out; } if (NULL == ext4_li_info) { ret = ext4_li_info_new(); if (ret) goto out; } mutex_lock(&ext4_li_info->li_list_mtx); list_add(&elr->lr_request, &ext4_li_info->li_request_list); mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; /* * set elr to NULL here since it has been inserted to * the request_list and the removal and free of it is * handled by ext4_clear_request_list from now on. */ elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); if (ret) goto out; } out: mutex_unlock(&ext4_li_mtx); if (ret) kfree(elr); return ret; } /* * We do not need to lock anything since this is called on * module unload. */ static void ext4_destroy_lazyinit_thread(void) { /* * If thread exited earlier * there's nothing to be done. */ if (!ext4_li_info || !ext4_lazyinit_task) return; kthread_stop(ext4_lazyinit_task); } static int set_journal_csum_feature_set(struct super_block *sb) { int ret = 1; int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; incompat = 0; } jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | incompat); } else if (test_opt(sb, JOURNAL_CHECKSUM)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, incompat); jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } else { jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } return ret; } /* * Note: calculating the overhead so we can be compatible with * historical BSD practice is quite difficult in the face of * clusters/bigalloc. This is because multiple metadata blocks from * different block group can end up in the same allocation cluster. * Calculating the exact overhead in the face of clustered allocation * requires either O(all block bitmaps) in memory or O(number of block * groups**2) in time. We will still calculate the superblock for * older file systems --- and if we come across with a bigalloc file * system with zero in s_overhead_clusters the estimate will be close to * correct especially for very large cluster sizes --- but for newer * file systems, it's better to calculate this figure once at mkfs * time, and store it in the superblock. If the superblock value is * present (even for non-bigalloc file systems), we will use it. */ static int count_overhead(struct super_block *sb, ext4_group_t grp, char *buf) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp; ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) return (has_super + ext4_bg_num_gdb(sb, grp) + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); b = ext4_block_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_table(sb, gdp); if (b >= first_block && b + sbi->s_itb_per_group <= last_block) for (j = 0; j < sbi->s_itb_per_group; j++, b++) { int c = EXT4_B2C(sbi, b - first_block); ext4_set_bit(c, buf); count++; } if (i != grp) continue; s = 0; if (ext4_bg_has_super(sb, grp)) { ext4_set_bit(s++, buf); count++; } j = ext4_bg_num_gdb(sb, grp); if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) { ext4_error(sb, "Invalid number of block group " "descriptor blocks: %d", j); j = EXT4_BLOCKS_PER_GROUP(sb) - s; } count += j; for (; j > 0; j--) ext4_set_bit(EXT4_B2C(sbi, s++), buf); } if (!count) return 0; return EXT4_CLUSTERS_PER_GROUP(sb) - ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); } /* * Compute the overhead and stash it in sbi->s_overhead */ int ext4_calculate_overhead(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct inode *j_inode; unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum); ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; char *buf = (char *) get_zeroed_page(GFP_NOFS); if (!buf) return -ENOMEM; /* * Compute the overhead (FS structures). This is constant * for a given filesystem unless the number of block groups * changes so we cache the previous value until it does. */ /* * All of the blocks before first_data_block are overhead */ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); /* * Add the overhead found in each block group */ for (i = 0; i < ngroups; i++) { int blks; blks = count_overhead(sb, i, buf); overhead += blks; if (blks) memset(buf, 0, PAGE_SIZE); cond_resched(); } /* * Add the internal journal blocks whether the journal has been * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev_file) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); } else { ext4_msg(sb, KERN_ERR, "can't get journal size"); } } sbi->s_overhead = overhead; smp_wmb(); free_page((unsigned long) buf); return 0; } static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * There's no need to reserve anything when we aren't using extents. * The space estimates are exact, there are no unwritten extents, * hole punching doesn't need new metadata... This is needed especially * to keep ext2/3 backward compatibility. */ if (!ext4_has_feature_extents(sb)) return; /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting * unwritten extents in delalloc path. In most cases such * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ resv_clusters = (ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits); do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); atomic64_set(&sbi->s_resv_clusters, resv_clusters); } static const char *ext4_quota_mode(struct super_block *sb) { #ifdef CONFIG_QUOTA if (!ext4_quota_capable(sb)) return "none"; if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb)) return "journalled"; else return "writeback"; #else return "disabled"; #endif } static void ext4_setup_csum_trigger(struct super_block *sb, enum ext4_journal_trigger_type type, void (*trigger)( struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size)) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_journal_triggers[type].sb = sb; sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger; } static void ext4_free_sbi(struct ext4_sb_info *sbi) { if (!sbi) return; kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) { struct ext4_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return NULL; sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, NULL, NULL); sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) goto err_out; sb->s_fs_info = sbi; sbi->s_sb = sb; return sbi; err_out: fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } static void ext4_set_def_opts(struct super_block *sb, struct ext4_super_block *es) { unsigned long def_mount_opts; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); set_opt(sb, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sb, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) set_opt(sb, GRPID); if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif if (ext4_has_feature_fast_commit(sb)) set_opt2(sb, JOURNAL_FAST_COMMIT); /* don't forget to enable journal_csum when metadata_csum is enabled. */ if (ext4_has_metadata_csum(sb)) set_opt(sb, JOURNAL_CHECKSUM); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) set_opt(sb, ORDERED_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) set_opt(sb, WRITEBACK_DATA); if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sb, ERRORS_PANIC); else if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_CONTINUE) set_opt(sb, ERRORS_CONT); else set_opt(sb, ERRORS_RO); /* block_validity enabled by default; disable with noblock_validity */ set_opt(sb, BLOCK_VALIDITY); if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0) set_opt(sb, BARRIER); /* * enable delayed allocation by default * Use -o nodelalloc to turn it off */ if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); if (sb->s_blocksize <= PAGE_SIZE) set_opt(sb, DIOREAD_NOLOCK); } static int ext4_handle_clustersize(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int clustersize; /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); if (ext4_has_feature_bigalloc(sb)) { if (clustersize < sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "cluster size (%d) smaller than " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); } else { if (clustersize != sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "fragment/cluster size (%d) != " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#blocks per group too big: %lu", sbi->s_blocks_per_group); return -EINVAL; } sbi->s_cluster_bits = 0; } sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group); if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu", sbi->s_clusters_per_group); return -EINVAL; } if (sbi->s_blocks_per_group != (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and clusters per group (%lu) inconsistent", sbi->s_blocks_per_group, sbi->s_clusters_per_group); return -EINVAL; } sbi->s_cluster_ratio = clustersize / sb->s_blocksize; /* Do we have standard group size of clustersize * 8 blocks ? */ if (sbi->s_blocks_per_group == clustersize << 3) set_opt2(sb, STD_GROUP_SIZE); return 0; } /* * ext4_atomic_write_init: Initializes filesystem min & max atomic write units. * @sb: super block * TODO: Later add support for bigalloc */ static void ext4_atomic_write_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct block_device *bdev = sb->s_bdev; if (!bdev_can_atomic_write(bdev)) return; if (!ext4_has_feature_extents(sb)) return; sbi->s_awu_min = max(sb->s_blocksize, bdev_atomic_write_unit_min_bytes(bdev)); sbi->s_awu_max = min(sb->s_blocksize, bdev_atomic_write_unit_max_bytes(bdev)); if (sbi->s_awu_min && sbi->s_awu_max && sbi->s_awu_min <= sbi->s_awu_max) { ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u", sbi->s_awu_min, sbi->s_awu_max); } else { sbi->s_awu_min = 0; sbi->s_awu_max = 0; } } static void ext4_fast_commit_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Initialize fast commit stuff */ atomic_set(&sbi->s_fc_subtid, 0); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); sbi->s_fc_ineligible_tid = 0; spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; sbi->s_fc_replay_state.fc_regions_size = 0; sbi->s_fc_replay_state.fc_regions_used = 0; sbi->s_fc_replay_state.fc_regions_valid = 0; sbi->s_fc_replay_state.fc_modified_inodes = NULL; sbi->s_fc_replay_state.fc_modified_inodes_size = 0; sbi->s_fc_replay_state.fc_modified_inodes_used = 0; } static int ext4_inode_info_init(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; } else { sbi->s_inode_size = le16_to_cpu(es->s_inode_size); sbi->s_first_ino = le32_to_cpu(es->s_first_ino); if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { ext4_msg(sb, KERN_ERR, "invalid first ino: %u", sbi->s_first_ino); return -EINVAL; } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > sb->s_blocksize)) { ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); ext4_msg(sb, KERN_ERR, "blocksize: %lu", sb->s_blocksize); return -EINVAL; } /* * i_atime_extra is the last extra field available for * [acm]times in struct ext4_inode. Checking for that * field should suffice to ensure we have extra space * for all three. */ if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { sb->s_time_gran = 1; sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; } else { sb->s_time_gran = NSEC_PER_SEC; sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; } sb->s_time_min = EXT4_TIMESTAMP_MIN; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; if (ext4_has_feature_extra_isize(sb)) { unsigned v, max = (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE); v = le16_to_cpu(es->s_want_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_want_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; v = le16_to_cpu(es->s_min_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_min_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; } } return 0; } #if IS_ENABLED(CONFIG_UNICODE) static int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags); if (!ext4_has_feature_casefold(sb) || sb->s_encoding) return 0; encoding_info = ext4_sb_read_encoding(es); if (!encoding_info) { ext4_msg(sb, KERN_ERR, "Encoding requested by superblock is unknown"); return -EINVAL; } encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { ext4_msg(sb, KERN_ERR, "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); return -EINVAL; } ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); sb->s_encoding = encoding; sb->s_encoding_flags = encoding_flags; return 0; } #else static inline int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { return 0; } #endif static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Warn if metadata_csum and gdt_csum are both set. */ if (ext4_has_feature_metadata_csum(sb) && ext4_has_feature_gdt_csum(sb)) ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); /* Check for a known checksum algorithm */ if (!ext4_verify_csum_type(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "unknown checksum algorithm."); return -EINVAL; } ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "invalid superblock checksum. Run e2fsck?"); return -EFSBADCRC; } /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); return 0; } static int ext4_check_feature_compatibility(struct super_block *sb, struct ext4_super_block *es, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || ext4_has_ro_compat_features(sb) || ext4_has_incompat_features(sb))) ext4_msg(sb, KERN_WARNING, "feature flags set on rev 0 fs, " "running e2fsck is recommended"); if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) { set_opt2(sb, HURD_COMPAT); if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); return -EINVAL; } /* * ea_inode feature uses l_i_version field which is not * available in HURD_COMPAT mode. */ if (ext4_has_feature_ea_inode(sb)) { ext4_msg(sb, KERN_ERR, "ea_inode feature is not supported for Hurd"); return -EINVAL; } } if (IS_EXT2_SB(sb)) { if (ext2_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext2 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext[34] filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due " "to feature incompatibilities"); return -EINVAL; } } if (IS_EXT3_SB(sb)) { if (ext3_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext3 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext4 filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due " "to feature incompatibilities"); return -EINVAL; } } /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) return -EINVAL; if (sbi->s_daxdev) { if (sb->s_blocksize == PAGE_SIZE) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); else ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem" " that may contain inline data"); return -EINVAL; } if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "DAX unsupported by block device."); return -EINVAL; } } if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) { ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", es->s_encryption_level); return -EINVAL; } return 0; } static int ext4_check_geometry(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u64 blocks_count; int err; if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); return -EINVAL; } /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); return err; } /* check blocks count against device size */ blocks_count = sb_bdev_nr_blocks(sb); if (blocks_count && ext4_blocks_count(es) > blocks_count) { ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); return -EINVAL; } /* * It makes no sense for the first data block to be beyond the end * of the filesystem. */ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block %u is beyond end of filesystem (%llu)", le32_to_cpu(es->s_first_data_block), ext4_blocks_count(es)); return -EINVAL; } if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && (sbi->s_cluster_ratio == 1)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block is 0 with a 1k block and cluster size"); return -EINVAL; } blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); return -EINVAL; } sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != le32_to_cpu(es->s_inodes_count)) { ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", le32_to_cpu(es->s_inodes_count), ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); return -EINVAL; } return 0; } static int ext4_group_desc_init(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t logical_sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int db_count; ext4_fsblk_t block; int i; db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { if (le32_to_cpu(es->s_first_meta_bg) > db_count) { ext4_msg(sb, KERN_WARNING, "first meta block group too large: %u " "(group descriptor block count %u)", le32_to_cpu(es->s_first_meta_bg), db_count); return -EINVAL; } } rcu_assign_pointer(sbi->s_group_desc, kvmalloc_array(db_count, sizeof(struct buffer_head *), GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); return -ENOMEM; } bgl_lock_init(sbi->s_blockgroup_lock); /* Pre-read the descriptors into the buffer cache */ for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); ext4_sb_breadahead_unmovable(sb, block); } for (i = 0; i < db_count; i++) { struct buffer_head *bh; block = descriptor_loc(sb, logical_sb_block, i); bh = ext4_sb_bread_unmovable(sb, block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); sbi->s_gdb_count = i; return PTR_ERR(bh); } rcu_read_lock(); rcu_dereference(sbi->s_group_desc)[i] = bh; rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); return -EFSCORRUPTED; } return 0; } static int ext4_load_and_init_journal(struct super_block *sb, struct ext4_super_block *es, struct ext4_fs_context *ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err; err = ext4_load_journal(sb, es, ctx->journal_devnum); if (err) return err; if (ext4_has_feature_64bit(sb) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto out; } if (!set_journal_csum_feature_set(sb)) { ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " "feature set"); goto out; } if (test_opt2(sb, JOURNAL_FAST_COMMIT) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { ext4_msg(sb, KERN_ERR, "Failed to set fast commit journal feature"); goto out; } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { case 0: /* No mode set, assume a default based on the journal * capabilities: ORDERED_DATA if the journal can * cope, else JOURNAL_DATA */ if (jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { set_opt(sb, ORDERED_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; } else { set_opt(sb, JOURNAL_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; } break; case EXT4_MOUNT_ORDERED_DATA: case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { ext4_msg(sb, KERN_ERR, "Journal does not support " "requested data journaling mode"); goto out; } break; default: break; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); goto out; } set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; sbi->s_journal->j_finish_inode_data_buffers = ext4_journal_finish_inode_data_buffers; return 0; out: /* flush s_sb_upd_work before destroying the journal. */ flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; return -EINVAL; } static int ext4_check_journal_data_mode(struct super_block *sb) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with " "data=journal disables delayed allocation, " "dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); return -EINVAL; } if (test_opt(sb, DAX_ALWAYS)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ext4_has_feature_encrypt(sb)) { ext4_msg(sb, KERN_WARNING, "encrypted files will use data=ordered " "instead of data journaling mode"); } if (test_opt(sb, DELALLOC)) clear_opt(sb, DELALLOC); } else { sb->s_iflags |= SB_I_CGROUPWB; } return 0; } static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es; ext4_fsblk_t logical_sb_block; unsigned long offset = 0; struct buffer_head *bh; int ret = -EINVAL; int blocksize; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { ext4_msg(sb, KERN_ERR, "unable to set blocksize"); return -EINVAL; } /* * The ext4 superblock will not be buffer aligned for other than 1kB * block sizes. We need to calculate the offset from buffer start. */ if (blocksize != EXT4_MIN_BLOCK_SIZE) { logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); } else { logical_sb_block = sbi->s_sb_block; } bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "unable to read superblock"); return PTR_ERR(bh); } /* * Note: s_es must be initialized as soon as possible because * some ext4 macro-instructions depend on its value */ es = (struct ext4_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT4_SUPER_MAGIC) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto out; } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log block size: %u", le32_to_cpu(es->s_log_block_size)); goto out; } if (le32_to_cpu(es->s_log_cluster_size) > (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log cluster size: %u", le32_to_cpu(es->s_log_cluster_size)); goto out; } blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); /* * If the default block size is not the same as the real block size, * we need to reload it. */ if (sb->s_blocksize == blocksize) { *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; } /* * bh must be released before kill_bdev(), otherwise * it won't be freed and its page also. kill_bdev() * is called by sb_set_blocksize(). */ brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); bh = NULL; goto out; } logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "Can't read superblock on 2nd try"); ret = PTR_ERR(bh); bh = NULL; goto out; } es = (struct ext4_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); goto out; } *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; out: brelse(bh); return ret; } static int ext4_hash_info_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; unsigned int i; sbi->s_def_hash_version = es->s_def_hash_version; if (sbi->s_def_hash_version > DX_HASH_LAST) { ext4_msg(sb, KERN_ERR, "Invalid default hash set in the superblock"); return -EINVAL; } else if (sbi->s_def_hash_version == DX_HASH_SIPHASH) { ext4_msg(sb, KERN_ERR, "SIPHASH is not a valid default hash value"); return -EINVAL; } for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) sbi->s_hash_unsigned = 3; else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); sbi->s_hash_unsigned = 3; #else if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif } } return 0; } static int ext4_block_group_meta_init(struct super_block *sb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int has_huge_files; has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { ext4_msg(sb, KERN_ERR, "unsupported descriptor size %lu", sbi->s_desc_size); return -EINVAL; } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); return -EINVAL; } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", sbi->s_inodes_per_group); return -EINVAL; } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb); sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); return 0; } /* * It's hard to get stripe aligned blocks if stripe is not aligned with * cluster, just disable stripe and alert user to simplify code and avoid * stripe aligned allocation which will rarely succeed. */ static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe) { struct ext4_sb_info *sbi = EXT4_SB(sb); return (stripe > 0 && sbi->s_cluster_ratio > 1 && stripe % sbi->s_cluster_ratio != 0); } static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) { struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t logical_sb_block; struct inode *root; int needs_recovery; int err; ext4_group_t first_not_zeroed; struct ext4_fs_context *ctx = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; /* Set defaults for the variables that will be set during parsing */ if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); err = ext4_load_super(sb, &logical_sb_block, silent); if (err) goto out_fail; es = sbi->s_es; sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); err = ext4_init_metadata_csum(sb, es); if (err) goto failed_mount; ext4_set_def_opts(sb, es); sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; /* * set default s_li_wait_mult for lazyinit, for the case there is * no mount option specified. */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; err = ext4_inode_info_init(sb, es); if (err) goto failed_mount; err = parse_apply_sb_mount_options(sb, ctx); if (err < 0) goto failed_mount; sbi->s_def_mount_opt = sbi->s_mount_opt; sbi->s_def_mount_opt2 = sbi->s_mount_opt2; err = ext4_check_opt_consistency(fc, sb); if (err < 0) goto failed_mount; ext4_apply_options(fc, sb); err = ext4_encoding_init(sb, es); if (err) goto failed_mount; err = ext4_check_journal_data_mode(sb); if (err) goto failed_mount; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; /* HSM events are allowed by default. */ sb->s_iflags |= SB_I_ALLOW_HSM; err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; err = ext4_block_group_meta_init(sb, silent); if (err) goto failed_mount; err = ext4_hash_info_init(sb); if (err) goto failed_mount; err = ext4_handle_clustersize(sb); if (err) goto failed_mount; err = ext4_check_geometry(sb, es); if (err) goto failed_mount; timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) goto failed_mount3; err = ext4_es_register_shrinker(sbi); if (err) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", sbi->s_stripe, sbi->s_cluster_ratio); sbi->s_stripe = 0; } sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode */ sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif #ifdef CONFIG_FS_VERITY sb->s_vop = &ext4_verityops; #endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid)); super_set_sysfs_name_bdev(sb); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); spin_lock_init(&sbi->s_bdev_wb_lock); ext4_atomic_write_init(sb); ext4_fast_commit_init(sb); sb->s_root = NULL; needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_orphan_present(sb) || ext4_has_feature_journal_needs_recovery(sb)); if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto failed_mount3a; } err = -EINVAL; /* * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); goto failed_mount3a; } if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_checksum, fs mounted w/o journal"); goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); clear_opt2(sb, JOURNAL_FAST_COMMIT); sbi->s_journal = NULL; needs_recovery = 0; } if (!test_opt(sb, NO_MBCACHE)) { sbi->s_ea_block_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_block_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); err = -EINVAL; goto failed_mount_wq; } if (ext4_has_feature_ea_inode(sb)) { sbi->s_ea_inode_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_inode_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_inode_cache"); err = -EINVAL; goto failed_mount_wq; } } } /* * Get the # of file system overhead blocks from the * superblock if present. */ sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); /* ignore the precalculated value if it is ridiculous */ if (sbi->s_overhead > ext4_blocks_count(es)) sbi->s_overhead = 0; /* * If the bigalloc feature is not enabled recalculating the * overhead doesn't take long, so we might as well just redo * it to make sure we are using the correct value. */ if (!ext4_has_feature_bigalloc(sb)) sbi->s_overhead = 0; if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; } /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ EXT4_SB(sb)->rsv_conversion_wq = alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->rsv_conversion_wq) { printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); err = -ENOMEM; goto failed_mount4; } /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. */ root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); err = PTR_ERR(root); root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); iput(root); err = -EFSCORRUPTED; goto failed_mount4; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); err = -ENOMEM; goto failed_mount4; } err = ext4_setup_super(sb, es, sb_rdonly(sb)); if (err == -EROFS) { sb->s_flags |= SB_RDONLY; } else if (err) goto failed_mount4a; ext4_set_resv_clusters(sb); if (test_opt(sb, BLOCK_VALIDITY)) { err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); goto failed_mount4a; } } ext4_fc_replay_cleanup(sb); ext4_ext_init(sb); /* * Enable optimize_scan if number of groups is > threshold. This can be * turned off by passing "mb_optimize_scan=0". This can also be * turned on forcefully by passing "mb_optimize_scan=1". */ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) { if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) set_opt2(sb, MB_OPTIMIZE_SCAN); else clear_opt2(sb, MB_OPTIMIZE_SCAN); } err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", err); goto failed_mount5; } /* * We can only set up the journal commit callback once * mballoc is initialized */ if (sbi->s_journal) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; err = ext4_percpu_param_init(sbi); if (err) goto failed_mount6; if (ext4_has_feature_flex_bg(sb)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); err = -ENOMEM; goto failed_mount6; } err = ext4_register_li_request(sb, first_not_zeroed); if (err) goto failed_mount6; err = ext4_init_orphan_info(sb); if (err) goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; } #endif /* CONFIG_QUOTA */ /* * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; /* * Update the checksum after updating free space/inode counters and * ext4_orphan_cleanup. Otherwise the superblock can have an incorrect * checksum in the buffer cache until it is written out and * e2fsprogs programs trying to open a file system immediately * after it is mounted can fail. */ ext4_superblock_csum_set(sb); if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) goto failed_mount9; } if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) ext4_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); /* Register sysfs after all initializations are complete. */ err = ext4_register_sysfs(sb); if (err) goto failed_mount9; return 0; failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); failed_mount8: __maybe_unused ext4_release_orphan_info(sb); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); ext4_flex_groups_free(sbi); ext4_percpu_param_destroy(sbi); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { /* flush s_sb_upd_work before journal destroy. */ flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: /* flush s_sb_upd_work before sbi destroy */ flush_work(&sbi->s_sb_upd_work); ext4_stop_mmpd(sbi); del_timer_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif #ifdef CONFIG_QUOTA for (unsigned int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; return err; } static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi; const char *descr; int ret; sbi = ext4_alloc_sbi(sb); if (!sbi) return -ENOMEM; fc->s_fs_info = sbi; /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); sbi->s_sb_block = 1; /* Default super block location */ if (ctx->spec & EXT4_SPEC_s_sb_block) sbi->s_sb_block = ctx->s_sb_block; ret = __ext4_fill_super(fc, sb); if (ret < 0) goto free_sbi; if (sbi->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) descr = " journalled data mode"; else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) descr = " ordered data mode"; else descr = " writeback data mode"; } else descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " "Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ ext4_update_overhead(sb, false); return 0; free_sbi: ext4_free_sbi(sbi); fc->s_fs_info = NULL; return ret; } static int ext4_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, ext4_fill_super); } /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've * done any recovery; and again on any subsequent remount. */ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) { struct ext4_sb_info *sbi = EXT4_SB(sb); journal->j_commit_interval = sbi->s_commit_interval; journal->j_min_batch_time = sbi->s_min_batch_time; journal->j_max_batch_time = sbi->s_max_batch_time; ext4_fc_init(sb, journal); write_lock(&journal->j_state_lock); if (test_opt(sb, BARRIER)) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; if (test_opt(sb, DATA_ERR_ABORT)) journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR; else journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR; /* * Always enable journal cycle record option, letting the journal * records log transactions continuously between each mount. */ journal->j_flags |= JBD2_CYCLE_RECORD; write_unlock(&journal->j_state_lock); } static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; /* * Test for the existence of a valid inode on disk. Bad things * happen if we iget() an unused inode, as the subsequent iput() * will try to delete it. */ journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return ERR_PTR(-EFSCORRUPTED); } if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return ERR_PTR(-EFSCORRUPTED); } ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); return journal_inode; } static int ext4_journal_bmap(journal_t *journal, sector_t *block) { struct ext4_map_blocks map; int ret; if (journal->j_inode == NULL) return 0; map.m_lblk = *block; map.m_len = 1; ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); if (ret <= 0) { ext4_msg(journal->j_inode->i_sb, KERN_CRIT, "journal bmap failed: block %llu ret %d\n", *block, ret); jbd2_journal_abort(journal, ret ? ret : -EIO); return ret; } *block = map.m_pblk; return 0; } static journal_t *ext4_open_inode_journal(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (IS_ERR(journal_inode)) return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } static struct file *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; struct file *bdev_file; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; int errno; bdev_file = bdev_file_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file)); return bdev_file; } bdev = file_bdev(bdev_file); blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev_file, blocksize); bh = __bread(bdev, sb_block, blocksize); if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); errno = -EINVAL; goto out_bdev; } es = (struct ext4_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); errno = -EFSCORRUPTED; goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); errno = -EFSCORRUPTED; goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); errno = -EFSCORRUPTED; goto out_bh; } *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); return bdev_file; out_bh: brelse(bh); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static journal_t *ext4_open_dev_journal(struct super_block *sb, dev_t j_dev) { journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; struct file *bdev_file; int errno = 0; bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); if (IS_ERR(bdev_file)) return ERR_CAST(bdev_file); journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); errno = PTR_ERR(journal); goto out_bdev; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); errno = -EINVAL; goto out_journal; } journal->j_private = sb; EXT4_SB(sb)->s_journal_bdev_file = bdev_file; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, struct ext4_super_block *es, unsigned long journal_devnum) { journal_t *journal; unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); dev_t journal_dev; int err = 0; int really_read_only; int journal_dev_ro; if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { ext4_msg(sb, KERN_INFO, "external journal device major/minor " "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); if (journal_inum && journal_dev) { ext4_msg(sb, KERN_ERR, "filesystem has both journal inode and journal device!"); return -EINVAL; } if (journal_inum) { journal = ext4_open_inode_journal(sb, journal_inum); if (IS_ERR(journal)) return PTR_ERR(journal); } else { journal = ext4_open_dev_journal(sb, journal_dev); if (IS_ERR(journal)) return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; if (journal_dev_ro && !sb_rdonly(sb)) { ext4_msg(sb, KERN_ERR, "journal device read-only, try mounting with '-o ro'"); err = -EROFS; goto err_out; } /* * Are we loading a blank journal or performing recovery after a * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ if (ext4_has_feature_journal_needs_recovery(sb)) { if (sb_rdonly(sb)) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); if (really_read_only) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); err = -EROFS; goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!ext4_has_feature_journal_needs_recovery(sb)) err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); __le16 orig_state; bool changed = false; if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); err = jbd2_journal_load(journal); if (save && memcmp(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN)) { memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); changed = true; } kfree(save); orig_state = es->s_state; es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS); if (orig_state != es->s_state) changed = true; /* Write out restored error information to the superblock */ if (changed && !really_read_only) { int err2; err2 = ext4_commit_super(sb); err = err ? : err2; } } if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); goto err_out; } EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { EXT4_SB(sb)->s_journal = NULL; jbd2_journal_destroy(journal); return err; } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); ext4_commit_super(sb); } if (!really_read_only && journal_inum && journal_inum != le32_to_cpu(es->s_journal_inum)) { es->s_journal_inum = cpu_to_le32(journal_inum); ext4_commit_super(sb); } return 0; err_out: jbd2_journal_destroy(journal); return err; } /* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *sbh = sbi->s_sbh; lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system * read/only but we need to replay the journal; at that point, * for people who are east of GMT and who make their clock * tick in localtime for Windows bug-for-bug compatibility, * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(sbi, percpu_counter_sum_positive( &sbi->s_freeclusters_counter))); if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { es->s_state |= cpu_to_le16(EXT4_ERROR_FS); if (!es->s_first_error_time && !es->s_first_error_time_hi) { __ext4_update_tstamp(&es->s_first_error_time, &es->s_first_error_time_hi, sbi->s_first_error_time); strtomem_pad(es->s_first_error_func, sbi->s_first_error_func, 0); es->s_first_error_line = cpu_to_le32(sbi->s_first_error_line); es->s_first_error_ino = cpu_to_le32(sbi->s_first_error_ino); es->s_first_error_block = cpu_to_le64(sbi->s_first_error_block); es->s_first_error_errcode = ext4_errno_to_code(sbi->s_first_error_code); } __ext4_update_tstamp(&es->s_last_error_time, &es->s_last_error_time_hi, sbi->s_last_error_time); strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0); es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); es->s_last_error_errcode = ext4_errno_to_code(sbi->s_last_error_code); /* * Start the daily error reporting function if it hasn't been * started already */ if (!es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); le32_add_cpu(&es->s_error_count, sbi->s_add_error_count); sbi->s_add_error_count = 0; } spin_unlock(&sbi->s_error_lock); ext4_superblock_csum_set(sb); unlock_buffer(sbh); } static int ext4_commit_super(struct super_block *sb) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; if (!sbh) return -EINVAL; ext4_update_super(sb); lock_buffer(sbh); /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(sbh)) { unlock_buffer(sbh); return -EIO; } if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ ext4_msg(sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } get_bh(sbh); /* Clear potential dirty bit if it was journalled update */ clear_buffer_dirty(sbh); sbh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh); wait_on_buffer(sbh); if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); return -EIO; } return 0; } /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es) { int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { if (journal != NULL) { ext4_error(sb, "Journal got removed while the fs was " "mounted!"); return -EFSCORRUPTED; } return 0; } jbd2_journal_lock_updates(journal); err = jbd2_journal_flush(journal, 0); if (err < 0) goto out; if (sb_rdonly(sb) && (ext4_has_feature_journal_needs_recovery(sb) || ext4_has_feature_orphan_present(sb))) { if (!ext4_orphan_file_empty(sb)) { ext4_error(sb, "Orphan file not empty on read-only fs."); err = -EFSCORRUPTED; goto out; } ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); return err; } /* * If we are mounting (or read-write remounting) a filesystem whose journal * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; if (!ext4_has_feature_journal(sb)) { ext4_error(sb, "Journal got removed while the fs was mounted!"); return -EFSCORRUPTED; } journal = EXT4_SB(sb)->s_journal; /* * Now check for any error status which may have been recorded in the * journal by a prior ext4_error() or ext4_abort() */ j_errno = jbd2_journal_errno(journal); if (j_errno) { char nbuf[16]; errstr = ext4_decode_error(sb, j_errno, nbuf); ext4_warning(sb, "Filesystem error recorded " "from previous mount: %s", errstr); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); j_errno = ext4_commit_super(sb); if (j_errno) return j_errno; ext4_warning(sb, "Marked fs in need of filesystem check."); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } return 0; } /* * Force the running and committing transactions to commit, * and wait on the commit. */ int ext4_force_commit(struct super_block *sb) { return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); if (unlikely(ext4_forced_shutdown(sb))) return -EIO; trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots */ dquot_writeback_dquots(sb, -1); /* * Data writeback is possible w/o journal transaction, so barrier must * being sent at the end of the function. But we can skip it if * transaction_commit will do it for us. */ if (sbi->s_journal) { target = jbd2_get_latest_transaction(sbi->s_journal); if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) needs_barrier = true; if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) ret = jbd2_log_wait_commit(sbi->s_journal, target); } } else if (wait && test_opt(sb, BARRIER)) needs_barrier = true; if (needs_barrier) { int err; err = blkdev_issue_flush(sb->s_bdev); if (!ret) ret = err; } return ret; } /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean * state independently. It relies on upper layer to stop all data & metadata * modifications. */ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ jbd2_journal_lock_updates(journal); /* * Don't clear the needs_recovery flag if we failed to * flush the journal. */ error = jbd2_journal_flush(journal, 0); if (error < 0) goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ ext4_clear_feature_journal_needs_recovery(sb); if (ext4_orphan_file_empty(sb)) ext4_clear_feature_orphan_present(sb); } error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(journal); return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ static int ext4_unfreeze(struct super_block *sb) { if (ext4_forced_shutdown(sb)) return 0; if (EXT4_SB(sb)->s_journal) { /* Reset the needs_recovery flag before the fs is unlocked. */ ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } ext4_commit_super(sb); return 0; } /* * Structure to save mount options for ext4_remount's benefit */ struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; kuid_t s_resuid; kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA int s_jquota_fmt; char *s_qf_names[EXT4_MAXQUOTAS]; #endif }; static int __ext4_remount(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; old_opts.s_resuid = sbi->s_resuid; old_opts.s_resgid = sbi->s_resgid; old_opts.s_commit_interval = sbi->s_commit_interval; old_opts.s_min_batch_time = sbi->s_min_batch_time; old_opts.s_max_batch_time = sbi->s_max_batch_time; #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { char *qf_name = get_qf_name(sb, sbi, i); old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); return -ENOMEM; } } else old_opts.s_qf_names[i] = NULL; #endif if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { if (sbi->s_journal && sbi->s_journal->j_task->io_context) ctx->journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; } if ((ctx->spec & EXT4_SPEC_s_stripe) && ext4_is_stripe_incompatible(sb, ctx->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", ctx->s_stripe, sbi->s_cluster_ratio); ctx->s_stripe = 0; } /* * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause * two calls to ext4_should_dioread_nolock() to return inconsistent * values, triggering WARN_ON in ext4_add_complete_io(). we grab * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " "during remount not supported; ignoring"); sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); err = -EINVAL; goto restore_opts; } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dioread_nolock"); err = -EINVAL; goto restore_opts; } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); err = -EINVAL; goto restore_opts; } } if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); err = -EINVAL; goto restore_opts; } if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) && !test_opt(sb, DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount"); err = -EINVAL; goto restore_opts; } sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); es = sbi->s_es; if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); } /* Flush outstanding errors before changing fs state */ flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_forced_shutdown(sb)) { err = -EROFS; goto restore_opts; } if (fc->sb_flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; /* * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount */ sb->s_flags |= SB_RDONLY; /* * OK, test if we are remounting a valid rw partition * readonly, and if so set the rdonly flag and then * mark the partition as valid again. */ if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) && (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); if (sbi->s_journal) { /* * We let remount-ro finish even if marking fs * as clean failed... */ ext4_mark_recovery_complete(sb, es); } } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EFSBADCRC; goto restore_opts; } } /* * If we have an unprocessed orphan list hanging * around from a previously readonly bdev mount, * require a full umount/remount for now. */ if (es->s_last_orphan || !ext4_orphan_file_empty(sb)) { ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " "umount/remount instead"); err = -EINVAL; goto restore_opts; } /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ if (sbi->s_journal) { err = ext4_clear_journal_err(sb, es); if (err) goto restore_opts; } sbi->s_mount_state = (le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) goto restore_opts; sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA enable_quota = 1; #endif } } /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. */ if (test_opt(sb, BLOCK_VALIDITY) && !sbi->s_system_blks) { err = ext4_setup_system_zone(sb); if (err) goto restore_opts; } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); else if (ext4_has_feature_quota(sb)) { err = ext4_enable_quotas(sb); if (err) goto restore_opts; } } /* Release old quota file names */ for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); /* * Reinitialize lazy itable initialization thread based on * current settings */ if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) ext4_unregister_li_request(sb); else { ext4_group_t first_not_zeroed; first_not_zeroed = ext4_has_uninit_itable(sb); ext4_register_li_request(sb, first_not_zeroed); } if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); /* * Handle aborting the filesystem as the last thing during remount to * avoid obsure errors during remount when some option changes fail to * apply due to shutdown filesystem. */ if (test_opt2(sb, ABORT)) ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); return 0; restore_opts: /* * If there was a failing r/w to ro transition, we may need to * re-enable quota */ if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; sbi->s_resuid = old_opts.s_resuid; sbi->s_resgid = old_opts.s_resgid; sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { to_free[i] = get_qf_name(sb, sbi, i); rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } synchronize_rcu(); for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(to_free[i]); #endif if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return err; } static int ext4_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int ret; fc->s_fs_info = EXT4_SB(sb); ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) return ret; ret = __ext4_remount(fc, sb); if (ret < 0) return ret; ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", ext4_quota_mode(sb)); return 0; } #ifdef CONFIG_QUOTA static int ext4_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) { struct kqid qid; struct dquot *dquot; u64 limit; u64 curblock; qid = make_kqid_projid(projid); dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; buf->f_blocks = limit; buf->f_bfree = buf->f_bavail = (buf->f_blocks > curblock) ? (buf->f_blocks - curblock) : 0; } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); if (limit && buf->f_files > limit) { buf->f_files = limit; buf->f_ffree = (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; } spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } #endif static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_fsblk_t overhead = 0, resv_blocks; s64 bfree; resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - (ext4_r_blocks_count(es) + resv_blocks); if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); buf->f_namelen = EXT4_NAME_LEN; buf->f_fsid = uuid_to_fsid(es->s_uuid); #ifdef CONFIG_QUOTA if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf); #endif return 0; } #ifdef CONFIG_QUOTA /* * Helper functions so that transaction is started before we acquire dqio_sem * to keep correct lock ordering of transaction > dqio_sem */ static inline struct inode *dquot_to_inode(struct dquot *dquot) { return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext4_write_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; struct inode *inode; inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to commit dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_acquire_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to acquire dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); return PTR_ERR(handle); } ret = dquot_release(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to release dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; if (ext4_is_quota_journalled(sb)) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); } else { return dquot_mark_dquot_dirty(dquot); } } static int ext4_write_info(struct super_block *sb, int type) { int ret, err; handle_t *handle; /* Data block + inode block */ handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static void lockdep_set_quota_inode(struct inode *inode, int subclass) { struct ext4_inode_info *ei = EXT4_I(inode); /* The first argument of lockdep_set_subclass has to be * *exactly* the same as the argument to init_rwsem() --- in * this case, in init_once() --- or lockdep gets unhappy * because the name of the lock is set using the * stringification of the argument to init_rwsem(). */ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, subclass); } /* * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int err; if (!test_opt(sb, QUOTA)) return -EINVAL; /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; /* Quota already enabled for this file? */ if (IS_NOQUOTA(d_inode(path->dentry))) return -EBUSY; /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path->dentry->d_parent != sb->s_root) ext4_msg(sb, KERN_WARNING, "Quota file not on filesystem root. " "Journaled quota will not work"); sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY; } else { /* * Clear the flag just in case mount options changed since * last time. */ sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY; } lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; /* * Set inode flags to prevent userspace from messing with quota * files. If this fails, we return success anyway since quotas * are already enabled and this is not a hard failure. */ inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) goto unlock_inode; EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); if (err) dquot_quota_off(sb, type); } if (err) lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_NORMAL); return err; } static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) { switch (type) { case USRQUOTA: return qf_inum == EXT4_USR_QUOTA_INO; case GRPQUOTA: return qf_inum == EXT4_GRP_QUOTA_INO; case PRJQUOTA: return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; default: BUG(); } } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { int err; struct inode *qf_inode; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; BUG_ON(!ext4_has_feature_quota(sb)); if (!qf_inums[type]) return -EPERM; if (!ext4_check_quota_inum(type, qf_inums[type])) { ext4_error(sb, "Bad quota inum: %lu, type: %d", qf_inums[type], type); return -EUCLEAN; } qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { ext4_error(sb, "Bad quota inode: %lu, type: %d", qf_inums[type], type); return PTR_ERR(qf_inode); } /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_load_quota_inode(qf_inode, type, format_id, flags); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); iput(qf_inode); return err; } /* Enable usage tracking for all quota types. */ int ext4_enable_quotas(struct super_block *sb) { int type, err = 0; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; bool quota_mopt[EXT4_MAXQUOTAS] = { test_opt(sb, USRQUOTA), test_opt(sb, GRPQUOTA), test_opt(sb, PRJQUOTA), }; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < EXT4_MAXQUOTAS; type++) { if (qf_inums[type]) { err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d, ino=%lu). " "Please run e2fsck to fix.", type, err, qf_inums[type]); ext4_quotas_off(sb, type); return err; } } } return 0; } static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; handle_t *handle; int err; /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); if (!inode || !igrab(inode)) goto out; err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; /* * When the filesystem was remounted read-only first, we cannot cleanup * inode flags here. Bad luck but people should be using QUOTA feature * these days anyway. */ if (sb_rdonly(sb)) goto out_put; inode_lock(inode); /* * Update modification times of quota files when userspace can * start looking at them. If we fail, we return success anyway since * this is not a hard failure and quotas are already disabled. */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out_unlock; } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: inode_unlock(inode); out_put: lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL); iput(inode); return err; out: return dquot_quota_off(sb, type); } /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) * we don't have to be afraid of races */ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int offset = off & (sb->s_blocksize - 1); int tocopy; size_t toread; struct buffer_head *bh; loff_t i_size = i_size_read(inode); if (off > i_size) return 0; if (off+len > i_size) len = i_size-off; toread = len; while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); bh = ext4_bread(NULL, inode, blk, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) /* A hole? */ memset(data, 0, tocopy); else memcpy(data, bh->b_data+offset, tocopy); brelse(bh); offset = 0; toread -= tocopy; data += tocopy; blk++; } return len; } /* Write to quotafile (we know the transaction is already started and has * enough credits) */ static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1); int retries = 0; struct buffer_head *bh; handle_t *handle = journal_current_handle(); if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } /* * Since we account only one data block in transaction credits, * then it is impossible to cross a block boundary. */ if (sb->s_blocksize - offset < len) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because not block aligned", (unsigned long long)off, (unsigned long long)len); return -EIO; } do { bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) goto out; BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) { brelse(bh); return err; } lock_buffer(bh); memcpy(bh->b_data+offset, data, len); flush_dcache_page(bh->b_page); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; } return err ? err : len; } #endif #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static inline void register_as_ext2(void) { int err = register_filesystem(&ext2_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext2 (%d)\n", err); } static inline void unregister_as_ext2(void) { unregister_filesystem(&ext2_fs_type); } static inline int ext2_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; return 1; } #else static inline void register_as_ext2(void) { } static inline void unregister_as_ext2(void) { } static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; } #endif static inline void register_as_ext3(void) { int err = register_filesystem(&ext3_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext3 (%d)\n", err); } static inline void unregister_as_ext3(void) { unregister_filesystem(&ext3_fs_type); } static inline int ext3_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext3_incompat_features(sb)) return 0; if (!ext4_has_feature_journal(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; return 1; } static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL; kill_block_super(sb); if (bdev_file) bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { .owner = THIS_MODULE, .name = "ext4", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("ext4"); /* Shared across all ext4 file systems */ wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; static int __init ext4_init_fs(void) { int i, err; ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; /* Build-time check for flags consistency */ ext4_check_flag_values(); for (i = 0; i < EXT4_WQ_HASH_SZ; i++) init_waitqueue_head(&ext4__ioend_wq[i]); err = ext4_init_es(); if (err) return err; err = ext4_init_pending(); if (err) goto out7; err = ext4_init_post_read_processing(); if (err) goto out6; err = ext4_init_pageio(); if (err) goto out5; err = ext4_init_system_zone(); if (err) goto out4; err = ext4_init_sysfs(); if (err) goto out3; err = ext4_init_mballoc(); if (err) goto out2; err = init_inodecache(); if (err) goto out1; err = ext4_fc_init_dentry_cache(); if (err) goto out05; register_as_ext3(); register_as_ext2(); err = register_filesystem(&ext4_fs_type); if (err) goto out; return 0; out: unregister_as_ext2(); unregister_as_ext3(); ext4_fc_destroy_dentry_cache(); out05: destroy_inodecache(); out1: ext4_exit_mballoc(); out2: ext4_exit_sysfs(); out3: ext4_exit_system_zone(); out4: ext4_exit_pageio(); out5: ext4_exit_post_read_processing(); out6: ext4_exit_pending(); out7: ext4_exit_es(); return err; } static void __exit ext4_exit_fs(void) { ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); ext4_fc_destroy_dentry_cache(); destroy_inodecache(); ext4_exit_mballoc(); ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) |
| 50 50 103 132 132 52 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * zpool memory storage api * * Copyright (C) 2014 Dan Streetman * * This is a common frontend for memory storage pool implementations. * Typically, this is used to store compressed memory. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/list.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/module.h> #include <linux/zpool.h> struct zpool { struct zpool_driver *driver; void *pool; }; static LIST_HEAD(drivers_head); static DEFINE_SPINLOCK(drivers_lock); /** * zpool_register_driver() - register a zpool implementation. * @driver: driver to register */ void zpool_register_driver(struct zpool_driver *driver) { spin_lock(&drivers_lock); atomic_set(&driver->refcount, 0); list_add(&driver->list, &drivers_head); spin_unlock(&drivers_lock); } EXPORT_SYMBOL(zpool_register_driver); /** * zpool_unregister_driver() - unregister a zpool implementation. * @driver: driver to unregister. * * Module usage counting is used to prevent using a driver * while/after unloading, so if this is called from module * exit function, this should never fail; if called from * other than the module exit function, and this returns * failure, the driver is in use and must remain available. */ int zpool_unregister_driver(struct zpool_driver *driver) { int ret = 0, refcount; spin_lock(&drivers_lock); refcount = atomic_read(&driver->refcount); WARN_ON(refcount < 0); if (refcount > 0) ret = -EBUSY; else list_del(&driver->list); spin_unlock(&drivers_lock); return ret; } EXPORT_SYMBOL(zpool_unregister_driver); /* this assumes @type is null-terminated. */ static struct zpool_driver *zpool_get_driver(const char *type) { struct zpool_driver *driver; spin_lock(&drivers_lock); list_for_each_entry(driver, &drivers_head, list) { if (!strcmp(driver->type, type)) { bool got = try_module_get(driver->owner); if (got) atomic_inc(&driver->refcount); spin_unlock(&drivers_lock); return got ? driver : NULL; } } spin_unlock(&drivers_lock); return NULL; } static void zpool_put_driver(struct zpool_driver *driver) { atomic_dec(&driver->refcount); module_put(driver->owner); } /** * zpool_has_pool() - Check if the pool driver is available * @type: The type of the zpool to check (e.g. zbud, zsmalloc) * * This checks if the @type pool driver is available. This will try to load * the requested module, if needed, but there is no guarantee the module will * still be loaded and available immediately after calling. If this returns * true, the caller should assume the pool is available, but must be prepared * to handle the @zpool_create_pool() returning failure. However if this * returns false, the caller should assume the requested pool type is not * available; either the requested pool type module does not exist, or could * not be loaded, and calling @zpool_create_pool() with the pool type will * fail. * * The @type string must be null-terminated. * * Returns: true if @type pool is available, false if not */ bool zpool_has_pool(char *type) { struct zpool_driver *driver = zpool_get_driver(type); if (!driver) { request_module("zpool-%s", type); driver = zpool_get_driver(type); } if (!driver) return false; zpool_put_driver(driver); return true; } EXPORT_SYMBOL(zpool_has_pool); /** * zpool_create_pool() - Create a new zpool * @type: The type of the zpool to create (e.g. zbud, zsmalloc) * @name: The name of the zpool (e.g. zram0, zswap) * @gfp: The GFP flags to use when allocating the pool. * * This creates a new zpool of the specified type. The gfp flags will be * used when allocating memory, if the implementation supports it. If the * ops param is NULL, then the created zpool will not be evictable. * * Implementations must guarantee this to be thread-safe. * * The @type and @name strings must be null-terminated. * * Returns: New zpool on success, NULL on failure. */ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp) { struct zpool_driver *driver; struct zpool *zpool; pr_debug("creating pool type %s\n", type); driver = zpool_get_driver(type); if (!driver) { request_module("zpool-%s", type); driver = zpool_get_driver(type); } if (!driver) { pr_err("no driver for type %s\n", type); return NULL; } zpool = kmalloc(sizeof(*zpool), gfp); if (!zpool) { pr_err("couldn't create zpool - out of memory\n"); zpool_put_driver(driver); return NULL; } zpool->driver = driver; zpool->pool = driver->create(name, gfp); if (!zpool->pool) { pr_err("couldn't create %s pool\n", type); zpool_put_driver(driver); kfree(zpool); return NULL; } pr_debug("created pool type %s\n", type); return zpool; } /** * zpool_destroy_pool() - Destroy a zpool * @zpool: The zpool to destroy. * * Implementations must guarantee this to be thread-safe, * however only when destroying different pools. The same * pool should only be destroyed once, and should not be used * after it is destroyed. * * This destroys an existing zpool. The zpool should not be in use. */ void zpool_destroy_pool(struct zpool *zpool) { pr_debug("destroying pool type %s\n", zpool->driver->type); zpool->driver->destroy(zpool->pool); zpool_put_driver(zpool->driver); kfree(zpool); } /** * zpool_get_type() - Get the type of the zpool * @zpool: The zpool to check * * This returns the type of the pool. * * Implementations must guarantee this to be thread-safe. * * Returns: The type of zpool. */ const char *zpool_get_type(struct zpool *zpool) { return zpool->driver->type; } /** * zpool_malloc_support_movable() - Check if the zpool supports * allocating movable memory * @zpool: The zpool to check * * This returns if the zpool supports allocating movable memory. * * Implementations must guarantee this to be thread-safe. * * Returns: true if the zpool supports allocating movable memory, false if not */ bool zpool_malloc_support_movable(struct zpool *zpool) { return zpool->driver->malloc_support_movable; } /** * zpool_malloc() - Allocate memory * @zpool: The zpool to allocate from. * @size: The amount of memory to allocate. * @gfp: The GFP flags to use when allocating memory. * @handle: Pointer to the handle to set * * This allocates the requested amount of memory from the pool. * The gfp flags will be used when allocating memory, if the * implementation supports it. The provided @handle will be * set to the allocated object handle. * * Implementations must guarantee this to be thread-safe. * * Returns: 0 on success, negative value on error. */ int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp, unsigned long *handle) { return zpool->driver->malloc(zpool->pool, size, gfp, handle); } /** * zpool_free() - Free previously allocated memory * @zpool: The zpool that allocated the memory. * @handle: The handle to the memory to free. * * This frees previously allocated memory. This does not guarantee * that the pool will actually free memory, only that the memory * in the pool will become available for use by the pool. * * Implementations must guarantee this to be thread-safe, * however only when freeing different handles. The same * handle should only be freed once, and should not be used * after freeing. */ void zpool_free(struct zpool *zpool, unsigned long handle) { zpool->driver->free(zpool->pool, handle); } /** * zpool_map_handle() - Map a previously allocated handle into memory * @zpool: The zpool that the handle was allocated from * @handle: The handle to map * @mapmode: How the memory should be mapped * * This maps a previously allocated handle into memory. The @mapmode * param indicates to the implementation how the memory will be * used, i.e. read-only, write-only, read-write. If the * implementation does not support it, the memory will be treated * as read-write. * * This may hold locks, disable interrupts, and/or preemption, * and the zpool_unmap_handle() must be called to undo those * actions. The code that uses the mapped handle should complete * its operations on the mapped handle memory quickly and unmap * as soon as possible. As the implementation may use per-cpu * data, multiple handles should not be mapped concurrently on * any cpu. * * Returns: A pointer to the handle's mapped memory area. */ void *zpool_map_handle(struct zpool *zpool, unsigned long handle, enum zpool_mapmode mapmode) { return zpool->driver->map(zpool->pool, handle, mapmode); } /** * zpool_unmap_handle() - Unmap a previously mapped handle * @zpool: The zpool that the handle was allocated from * @handle: The handle to unmap * * This unmaps a previously mapped handle. Any locks or other * actions that the implementation took in zpool_map_handle() * will be undone here. The memory area returned from * zpool_map_handle() should no longer be used after this. */ void zpool_unmap_handle(struct zpool *zpool, unsigned long handle) { zpool->driver->unmap(zpool->pool, handle); } /** * zpool_get_total_pages() - The total size of the pool * @zpool: The zpool to check * * This returns the total size in pages of the pool. * * Returns: Total size of the zpool in pages. */ u64 zpool_get_total_pages(struct zpool *zpool) { return zpool->driver->total_pages(zpool->pool); } /** * zpool_can_sleep_mapped - Test if zpool can sleep when do mapped. * @zpool: The zpool to test * * Some allocators enter non-preemptible context in ->map() callback (e.g. * disable pagefaults) and exit that context in ->unmap(), which limits what * we can do with the mapped object. For instance, we cannot wait for * asynchronous crypto API to decompress such an object or take mutexes * since those will call into the scheduler. This function tells us whether * we use such an allocator. * * Returns: true if zpool can sleep; false otherwise. */ bool zpool_can_sleep_mapped(struct zpool *zpool) { return zpool->driver->sleep_mapped; } MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>"); MODULE_DESCRIPTION("Common API for compressed memory storage"); |
| 24 24 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cred.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/quotaops.h> #include <linux/sched.h> #include <linux/slab.h> #include <net/netlink.h> #include <net/genetlink.h> static const struct genl_multicast_group quota_mcgrps[] = { { .name = "events", }, }; /* Netlink family structure for quota */ static struct genl_family quota_genl_family __ro_after_init = { .module = THIS_MODULE, .hdrsize = 0, .name = "VFS_DQUOT", .version = 1, .maxattr = QUOTA_NL_A_MAX, .mcgrps = quota_mcgrps, .n_mcgrps = ARRAY_SIZE(quota_mcgrps), }; /** * quota_send_warning - Send warning to userspace about exceeded quota * @qid: The kernel internal quota identifier. * @dev: The device on which the fs is mounted (sb->s_dev) * @warntype: The type of the warning: QUOTA_NL_... * * This can be used by filesystems (including those which don't use * dquot) to send a message to userspace relating to quota limits. * */ void quota_send_warning(struct kqid qid, dev_t dev, const char warntype) { static atomic_t seq; struct sk_buff *skb; void *msg_head; int ret; int msg_size = 4 * nla_total_size(sizeof(u32)) + 2 * nla_total_size_64bit(sizeof(u64)); /* We have to allocate using GFP_NOFS as we are called from a * filesystem performing write and thus further recursion into * the fs to free some data could cause deadlocks. */ skb = genlmsg_new(msg_size, GFP_NOFS); if (!skb) { printk(KERN_ERR "VFS: Not enough memory to send quota warning.\n"); return; } msg_head = genlmsg_put(skb, 0, atomic_add_return(1, &seq), "a_genl_family, 0, QUOTA_NL_C_WARNING); if (!msg_head) { printk(KERN_ERR "VFS: Cannot store netlink header in quota warning.\n"); goto err_out; } ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, qid.type); if (ret) goto attr_err_out; ret = nla_put_u64_64bit(skb, QUOTA_NL_A_EXCESS_ID, from_kqid_munged(&init_user_ns, qid), QUOTA_NL_A_PAD); if (ret) goto attr_err_out; ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype); if (ret) goto attr_err_out; ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MAJOR, MAJOR(dev)); if (ret) goto attr_err_out; ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, MINOR(dev)); if (ret) goto attr_err_out; ret = nla_put_u64_64bit(skb, QUOTA_NL_A_CAUSED_ID, from_kuid_munged(&init_user_ns, current_uid()), QUOTA_NL_A_PAD); if (ret) goto attr_err_out; genlmsg_end(skb, msg_head); genlmsg_multicast("a_genl_family, skb, 0, 0, GFP_NOFS); return; attr_err_out: printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); err_out: kfree_skb(skb); } EXPORT_SYMBOL(quota_send_warning); static int __init quota_init(void) { if (genl_register_family("a_genl_family) != 0) printk(KERN_ERR "VFS: Failed to create quota netlink interface.\n"); return 0; }; fs_initcall(quota_init); |
| 1 17 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM nfs #if !defined(_TRACE_NFS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NFS_H #include <linux/tracepoint.h> #include <linux/iversion.h> #include <trace/misc/fs.h> #include <trace/misc/nfs.h> #include <trace/misc/sunrpc.h> #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ { NFS_INO_INVALID_DATA, "INVALID_DATA" }, \ { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }, \ { NFS_INO_INVALID_CHANGE, "INVALID_CHANGE" }, \ { NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \ { NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \ { NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \ { NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \ { NFS_INO_DATA_INVAL_DEFER, "DATA_INVAL_DEFER" }, \ { NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \ { NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \ { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \ { NFS_INO_INVALID_MODE, "INVALID_MODE" }) #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ { BIT(NFS_INO_STALE), "STALE" }, \ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ { BIT(NFS_INO_ODIRECT), "ODIRECT" }) DECLARE_EVENT_CLASS(nfs_inode_event, TP_PROTO( const struct inode *inode ), TP_ARGS(inode), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (unsigned long long)__entry->version ) ); DECLARE_EVENT_CLASS(nfs_inode_event_done, TP_PROTO( const struct inode *inode, int error ), TP_ARGS(inode, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u32, fhandle) __field(unsigned char, type) __field(u64, fileid) __field(u64, version) __field(loff_t, size) __field(unsigned long, nfsi_flags) __field(unsigned long, cache_validity) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->error = error < 0 ? -error : 0; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->type = nfs_umode_to_dtype(inode->i_mode); __entry->version = inode_peek_iversion_raw(inode); __entry->size = i_size_read(inode); __entry->nfsi_flags = nfsi->flags; __entry->cache_validity = nfsi->cache_validity; ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, nfs_show_cache_validity(__entry->cache_validity), __entry->nfsi_flags, nfs_show_nfsi_flags(__entry->nfsi_flags) ) ); #define DEFINE_NFS_INODE_EVENT(name) \ DEFINE_EVENT(nfs_inode_event, name, \ TP_PROTO( \ const struct inode *inode \ ), \ TP_ARGS(inode)) #define DEFINE_NFS_INODE_EVENT_DONE(name) \ DEFINE_EVENT(nfs_inode_event_done, name, \ TP_PROTO( \ const struct inode *inode, \ int error \ ), \ TP_ARGS(inode, error)) DEFINE_NFS_INODE_EVENT(nfs_set_inode_stale); DEFINE_NFS_INODE_EVENT(nfs_refresh_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_refresh_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_revalidate_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_revalidate_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_invalidate_mapping_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_invalidate_mapping_exit); DEFINE_NFS_INODE_EVENT(nfs_getattr_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_getattr_exit); DEFINE_NFS_INODE_EVENT(nfs_setattr_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_setattr_exit); DEFINE_NFS_INODE_EVENT(nfs_writeback_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus); DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done); DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done); TRACE_EVENT(nfs_access_exit, TP_PROTO( const struct inode *inode, unsigned int mask, unsigned int permitted, int error ), TP_ARGS(inode, mask, permitted, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u32, fhandle) __field(unsigned char, type) __field(u64, fileid) __field(u64, version) __field(loff_t, size) __field(unsigned long, nfsi_flags) __field(unsigned long, cache_validity) __field(unsigned int, mask) __field(unsigned int, permitted) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->error = error < 0 ? -error : 0; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->type = nfs_umode_to_dtype(inode->i_mode); __entry->version = inode_peek_iversion_raw(inode); __entry->size = i_size_read(inode); __entry->nfsi_flags = nfsi->flags; __entry->cache_validity = nfsi->cache_validity; __entry->mask = mask; __entry->permitted = permitted; ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " "mask=0x%x permitted=0x%x", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, nfs_show_cache_validity(__entry->cache_validity), __entry->nfsi_flags, nfs_show_nfsi_flags(__entry->nfsi_flags), __entry->mask, __entry->permitted ) ); DECLARE_EVENT_CLASS(nfs_update_size_class, TP_PROTO( const struct inode *inode, loff_t new_size ), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, cur_size) __field(loff_t, new_size) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->fileid = nfsi->fileid; __entry->version = inode_peek_iversion_raw(inode); __entry->cur_size = i_size_read(inode); __entry->new_size = new_size; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cursize=%lld newsize=%lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->cur_size, __entry->new_size ) ); #define DEFINE_NFS_UPDATE_SIZE_EVENT(name) \ DEFINE_EVENT(nfs_update_size_class, nfs_size_##name, \ TP_PROTO( \ const struct inode *inode, \ loff_t new_size \ ), \ TP_ARGS(inode, new_size)) DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); DECLARE_EVENT_CLASS(nfs_inode_range_event, TP_PROTO( const struct inode *inode, loff_t range_start, loff_t range_end ), TP_ARGS(inode, range_start, range_end), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, range_start) __field(loff_t, range_end) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->fileid = nfsi->fileid; __entry->version = inode_peek_iversion_raw(inode); __entry->range_start = range_start; __entry->range_end = range_end; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "range=[%lld, %lld]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->range_start, __entry->range_end ) ); #define DEFINE_NFS_INODE_RANGE_EVENT(name) \ DEFINE_EVENT(nfs_inode_range_event, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t range_start, \ loff_t range_end \ ), \ TP_ARGS(inode, range_start, range_end)) DEFINE_NFS_INODE_RANGE_EVENT(nfs_readdir_invalidate_cache_range); DECLARE_EVENT_CLASS(nfs_readdir_event, TP_PROTO( const struct file *file, const __be32 *verifier, u64 cookie, pgoff_t page_index, unsigned int dtsize ), TP_ARGS(file, verifier, cookie, page_index, dtsize), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __array(char, verifier, NFS4_VERIFIER_SIZE) __field(u64, cookie) __field(pgoff_t, index) __field(unsigned int, dtsize) ), TP_fast_assign( const struct inode *dir = file_inode(file); const struct nfs_inode *nfsi = NFS_I(dir); __entry->dev = dir->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(dir); if (cookie != 0) memcpy(__entry->verifier, verifier, NFS4_VERIFIER_SIZE); else memset(__entry->verifier, 0, NFS4_VERIFIER_SIZE); __entry->cookie = cookie; __entry->index = page_index; __entry->dtsize = dtsize; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "cookie=%s:0x%llx cache_index=%lu dtsize=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, show_nfs4_verifier(__entry->verifier), (unsigned long long)__entry->cookie, __entry->index, __entry->dtsize ) ); #define DEFINE_NFS_READDIR_EVENT(name) \ DEFINE_EVENT(nfs_readdir_event, name, \ TP_PROTO( \ const struct file *file, \ const __be32 *verifier, \ u64 cookie, \ pgoff_t page_index, \ unsigned int dtsize \ ), \ TP_ARGS(file, verifier, cookie, page_index, dtsize)) DEFINE_NFS_READDIR_EVENT(nfs_readdir_cache_fill); DEFINE_NFS_READDIR_EVENT(nfs_readdir_uncached); DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags ), TP_ARGS(dir, dentry, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __field(u64, fileid) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry)); __assign_str(name); ), TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu", __entry->flags, show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name), __entry->fileid ) ); #define DEFINE_NFS_LOOKUP_EVENT(name) \ DEFINE_EVENT(nfs_lookup_event, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ unsigned int flags \ ), \ TP_ARGS(dir, dentry, flags)) DECLARE_EVENT_CLASS(nfs_lookup_event_done, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags, int error ), TP_ARGS(dir, dentry, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __field(u64, fileid) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __entry->flags = flags; __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry)); __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name), __entry->fileid ) ); #define DEFINE_NFS_LOOKUP_EVENT_DONE(name) \ DEFINE_EVENT(nfs_lookup_event_done, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ unsigned int flags, \ int error \ ), \ TP_ARGS(dir, dentry, flags, error)) DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup); DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup_revalidate_failed); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_readdir_lookup_revalidate); TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( const struct inode *dir, const struct nfs_open_context *ctx, unsigned int flags ), TP_ARGS(dir, ctx, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name); ), TP_printk( "flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s", __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_atomic_open_exit, TP_PROTO( const struct inode *dir, const struct nfs_open_context *ctx, unsigned int flags, int error ), TP_ARGS(dir, ctx, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) ), TP_fast_assign( __entry->error = -error; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) fmode=%s " "name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_create_enter, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags ), TP_ARGS(dir, dentry, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __assign_str(name); ), TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_create_exit, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags, int error ), TP_ARGS(dir, dentry, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->error = -error; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_directory_event, TP_PROTO( const struct inode *dir, const struct dentry *dentry ), TP_ARGS(dir, dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __assign_str(name); ), TP_printk( "name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); #define DEFINE_NFS_DIRECTORY_EVENT(name) \ DEFINE_EVENT(nfs_directory_event, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry \ ), \ TP_ARGS(dir, dentry)) DECLARE_EVENT_CLASS(nfs_directory_event_done, TP_PROTO( const struct inode *dir, const struct dentry *dentry, int error ), TP_ARGS(dir, dentry, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __assign_str(name); ), TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); #define DEFINE_NFS_DIRECTORY_EVENT_DONE(name) \ DEFINE_EVENT(nfs_directory_event_done, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ int error \ ), \ TP_ARGS(dir, dentry, error)) DEFINE_NFS_DIRECTORY_EVENT(nfs_mknod_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mknod_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_mkdir_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mkdir_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_rmdir_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_rmdir_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_remove_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_remove_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_unlink_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_unlink_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_symlink_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_symlink_exit); TRACE_EVENT(nfs_link_enter, TP_PROTO( const struct inode *inode, const struct inode *dir, const struct dentry *dentry ), TP_ARGS(inode, dir, dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, fileid) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->dir = NFS_FILEID(dir); __assign_str(name); ), TP_printk( "fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_link_exit, TP_PROTO( const struct inode *inode, const struct inode *dir, const struct dentry *dentry, int error ), TP_ARGS(inode, dir, dentry, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u64, fileid) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __assign_str(name); ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_rename_event, TP_PROTO( const struct inode *old_dir, const struct dentry *old_dentry, const struct inode *new_dir, const struct dentry *new_dentry ), TP_ARGS(old_dir, old_dentry, new_dir, new_dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, old_dir) __field(u64, new_dir) __string(old_name, old_dentry->d_name.name) __string(new_name, new_dentry->d_name.name) ), TP_fast_assign( __entry->dev = old_dir->i_sb->s_dev; __entry->old_dir = NFS_FILEID(old_dir); __entry->new_dir = NFS_FILEID(new_dir); __assign_str(old_name); __assign_str(new_name); ), TP_printk( "old_name=%02x:%02x:%llu/%s new_name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->new_dir, __get_str(new_name) ) ); #define DEFINE_NFS_RENAME_EVENT(name) \ DEFINE_EVENT(nfs_rename_event, name, \ TP_PROTO( \ const struct inode *old_dir, \ const struct dentry *old_dentry, \ const struct inode *new_dir, \ const struct dentry *new_dentry \ ), \ TP_ARGS(old_dir, old_dentry, new_dir, new_dentry)) DECLARE_EVENT_CLASS(nfs_rename_event_done, TP_PROTO( const struct inode *old_dir, const struct dentry *old_dentry, const struct inode *new_dir, const struct dentry *new_dentry, int error ), TP_ARGS(old_dir, old_dentry, new_dir, new_dentry, error), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, error) __field(u64, old_dir) __string(old_name, old_dentry->d_name.name) __field(u64, new_dir) __string(new_name, new_dentry->d_name.name) ), TP_fast_assign( __entry->dev = old_dir->i_sb->s_dev; __entry->error = -error; __entry->old_dir = NFS_FILEID(old_dir); __entry->new_dir = NFS_FILEID(new_dir); __assign_str(old_name); __assign_str(new_name); ), TP_printk( "error=%ld (%s) old_name=%02x:%02x:%llu/%s " "new_name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->new_dir, __get_str(new_name) ) ); #define DEFINE_NFS_RENAME_EVENT_DONE(name) \ DEFINE_EVENT(nfs_rename_event_done, name, \ TP_PROTO( \ const struct inode *old_dir, \ const struct dentry *old_dentry, \ const struct inode *new_dir, \ const struct dentry *new_dentry, \ int error \ ), \ TP_ARGS(old_dir, old_dentry, new_dir, \ new_dentry, error)) DEFINE_NFS_RENAME_EVENT(nfs_rename_enter); DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit); DEFINE_NFS_RENAME_EVENT_DONE(nfs_async_rename_done); TRACE_EVENT(nfs_sillyrename_unlink, TP_PROTO( const struct nfs_unlinkdata *data, int error ), TP_ARGS(data, error), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, error) __field(u64, dir) __dynamic_array(char, name, data->args.name.len + 1) ), TP_fast_assign( struct inode *dir = d_inode(data->dentry->d_parent); size_t len = data->args.name.len; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = -error; memcpy(__get_str(name), data->args.name.name, len); __get_str(name)[len] = 0; ), TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_folio_event, TP_PROTO( const struct inode *inode, loff_t offset, size_t count ), TP_ARGS(inode, offset, count), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = offset, __entry->count = count; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "offset=%lld count=%zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->count ) ); #define DEFINE_NFS_FOLIO_EVENT(name) \ DEFINE_EVENT(nfs_folio_event, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t offset, \ size_t count \ ), \ TP_ARGS(inode, offset, count)) DECLARE_EVENT_CLASS(nfs_folio_event_done, TP_PROTO( const struct inode *inode, loff_t offset, size_t count, int ret ), TP_ARGS(inode, offset, count, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(int, ret) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = offset, __entry->count = count, __entry->ret = ret; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "offset=%lld count=%zu ret=%d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->count, __entry->ret ) ); #define DEFINE_NFS_FOLIO_EVENT_DONE(name) \ DEFINE_EVENT(nfs_folio_event_done, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t offset, \ size_t count, \ int ret \ ), \ TP_ARGS(inode, offset, count, ret)) DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); DEFINE_NFS_FOLIO_EVENT(nfs_invalidate_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_launder_folio_done); TRACE_EVENT(nfs_aop_readahead, TP_PROTO( const struct inode *inode, loff_t pos, unsigned int nr_pages ), TP_ARGS(inode, pos, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(unsigned int, nr_pages) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = pos; __entry->nr_pages = nr_pages; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld nr_pages=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->nr_pages ) ); TRACE_EVENT(nfs_aop_readahead_done, TP_PROTO( const struct inode *inode, unsigned int nr_pages, int ret ), TP_ARGS(inode, nr_pages, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(int, ret) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(unsigned int, nr_pages) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->nr_pages = nr_pages; __entry->ret = ret; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu nr_pages=%u ret=%d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->nr_pages, __entry->ret ) ); TRACE_EVENT(nfs_initiate_read, TP_PROTO( const struct nfs_pgio_header *hdr ), TP_ARGS(hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_readpage_done, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->eof = hdr->res.eof; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->eof ? " eof" : "" ) ); TRACE_EVENT(nfs_readpage_short, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->eof = hdr->res.eof; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->eof ? " eof" : "" ) ); TRACE_EVENT(nfs_pgio_error, TP_PROTO( const struct nfs_pgio_header *hdr, int error, loff_t pos ), TP_ARGS(hdr, error, pos), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(loff_t, pos) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = error; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk("error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u pos=%llu", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->pos ) ); TRACE_EVENT(nfs_initiate_write, TP_PROTO( const struct nfs_pgio_header *hdr ), TP_ARGS(hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) __field(unsigned long, stable) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->stable = hdr->args.stable; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u stable=%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count, show_nfs_stable_how(__entry->stable) ) ); TRACE_EVENT(nfs_writeback_done, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = hdr->res.verf; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->stable = verf->committed; memcpy(__entry->verifier, &verf->verifier, NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u stable=%s " "verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); DECLARE_EVENT_CLASS(nfs_page_error_class, TP_PROTO( const struct inode *inode, const struct nfs_page *req, int error ), TP_ARGS(inode, req, error), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(unsigned int, count) __field(int, error) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->offset = req_offset(req); __entry->count = req->wb_bytes; __entry->error = error; ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->offset, __entry->count ) ); #define DEFINE_NFS_PAGEERR_EVENT(name) \ DEFINE_EVENT(nfs_page_error_class, name, \ TP_PROTO( \ const struct inode *inode, \ const struct nfs_page *req, \ int error \ ), \ TP_ARGS(inode, req, error)) DEFINE_NFS_PAGEERR_EVENT(nfs_write_error); DEFINE_NFS_PAGEERR_EVENT(nfs_comp_error); DEFINE_NFS_PAGEERR_EVENT(nfs_commit_error); TRACE_EVENT(nfs_initiate_commit, TP_PROTO( const struct nfs_commit_data *data ), TP_ARGS(data), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = data->args.fh ? data->args.fh : &nfsi->fh; __entry->offset = data->args.offset; __entry->count = data->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_commit_done, TP_PROTO( const struct rpc_task *task, const struct nfs_commit_data *data ), TP_ARGS(task, data), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = data->args.fh ? data->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = data->res.verf; __entry->error = task->tk_status; __entry->offset = data->args.offset; __entry->stable = verf->committed; memcpy(__entry->verifier, &verf->verifier, NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld stable=%s verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); #define nfs_show_direct_req_flags(v) \ __print_flags(v, "|", \ { NFS_ODIRECT_DO_COMMIT, "DO_COMMIT" }, \ { NFS_ODIRECT_RESCHED_WRITES, "RESCHED_WRITES" }, \ { NFS_ODIRECT_SHOULD_DIRTY, "SHOULD DIRTY" }, \ { NFS_ODIRECT_DONE, "DONE" } ) DECLARE_EVENT_CLASS(nfs_direct_req_class, TP_PROTO( const struct nfs_direct_req *dreq ), TP_ARGS(dreq), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, fileid) __field(u32, fhandle) __field(loff_t, offset) __field(ssize_t, count) __field(ssize_t, error) __field(int, flags) ), TP_fast_assign( const struct inode *inode = dreq->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = &nfsi->fh; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); __entry->offset = dreq->io_start; __entry->count = dreq->count; __entry->error = dreq->error; __entry->flags = dreq->flags; ), TP_printk( "error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%zd flags=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->offset, __entry->count, nfs_show_direct_req_flags(__entry->flags) ) ); #define DEFINE_NFS_DIRECT_REQ_EVENT(name) \ DEFINE_EVENT(nfs_direct_req_class, name, \ TP_PROTO( \ const struct nfs_direct_req *dreq \ ), \ TP_ARGS(dreq)) DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_commit_complete); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_resched_write); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_complete); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_completion); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_schedule_iovec); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_reschedule_io); TRACE_EVENT(nfs_fh_to_dentry, TP_PROTO( const struct super_block *sb, const struct nfs_fh *fh, u64 fileid, int error ), TP_ARGS(sb, fh, fileid, error), TP_STRUCT__entry( __field(int, error) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) ), TP_fast_assign( __entry->error = error; __entry->dev = sb->s_dev; __entry->fileid = fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x ", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle ) ); TRACE_EVENT(nfs_mount_assign, TP_PROTO( const char *option, const char *value ), TP_ARGS(option, value), TP_STRUCT__entry( __string(option, option) __string(value, value) ), TP_fast_assign( __assign_str(option); __assign_str(value); ), TP_printk("option %s=%s", __get_str(option), __get_str(value) ) ); TRACE_EVENT(nfs_mount_option, TP_PROTO( const struct fs_parameter *param ), TP_ARGS(param), TP_STRUCT__entry( __string(option, param->key) ), TP_fast_assign( __assign_str(option); ), TP_printk("option %s", __get_str(option)) ); TRACE_EVENT(nfs_mount_path, TP_PROTO( const char *path ), TP_ARGS(path), TP_STRUCT__entry( __string(path, path) ), TP_fast_assign( __assign_str(path); ), TP_printk("path='%s'", __get_str(path)) ); TRACE_EVENT(nfs_local_open_fh, TP_PROTO( const struct nfs_fh *fh, fmode_t fmode, int error ), TP_ARGS(fh, fmode, error), TP_STRUCT__entry( __field(int, error) __field(u32, fhandle) __field(unsigned int, fmode) ), TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fh); __entry->fmode = (__force unsigned int)fmode; ), TP_printk( "error=%d fhandle=0x%08x mode=%s", __entry->error, __entry->fhandle, show_fs_fmode_flags(__entry->fmode) ) ); DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, int error ), TP_ARGS(xdr, error), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) __field(u32, xid) __field(int, version) __field(unsigned long, error) __string(program, xdr->rqst->rq_task->tk_client->cl_program->name) __string(procedure, xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) ), TP_fast_assign( const struct rpc_rqst *rqstp = xdr->rqst; const struct rpc_task *task = rqstp->rq_task; __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->version = task->tk_client->cl_vers; __entry->error = error; __assign_str(program); __assign_str(procedure); ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, __get_str(program), __entry->version, __get_str(procedure), -__entry->error, show_nfs_status(__entry->error) ) ); #define DEFINE_NFS_XDR_EVENT(name) \ DEFINE_EVENT(nfs_xdr_event, name, \ TP_PROTO( \ const struct xdr_stream *xdr, \ int error \ ), \ TP_ARGS(xdr, error)) DEFINE_NFS_XDR_EVENT(nfs_xdr_status); DEFINE_NFS_XDR_EVENT(nfs_xdr_bad_filehandle); #endif /* _TRACE_NFS_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE nfstrace /* This part must be outside protection */ #include <trace/define_trace.h> |
| 7654 5653 2252 2254 2249 5613 95 5699 34 5692 5697 5695 5696 3075 3073 3087 3054 27 7 37 3089 3072 3082 2871 3099 3085 4 6288 6291 4 4 4 4 2246 66 1410 3102 2824 2113 3319 216 56 179 181 4459 4468 6252 34 3268 3471 6278 3422 72 3368 89 89 89 89 77 3 3 74 77 8 8 8 8 8 8 23 24 24 24 24 24 24 2244 1436 2134 2240 4 2240 89 2239 4 2243 13 2246 183 183 89 13 3 11 10 21 4 21 19 610 2251 530 1 9 535 537 538 535 390 148 3559 3102 3563 3358 32 1 2348 2038 1176 3301 2221 3181 2349 150 76 145 147 148 148 1669 655 1669 937 940 692 939 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool on_lru, bool disable_irq) { unsigned long flags; if (on_lru && !folio_test_clear_lru(folio)) return; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op, on_lru) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ on_lru, \ offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_move_tail, true); } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; do { unsigned long lrusize; /* * Hold lruvec->lru_lock is safe here, since * 1) The pinned lruvec in reclaim, or * 2) From a pre-LRU page during refault (which also holds the * rcu lock, so would be safe even if the page was on the LRU * and could move simultaneously to a new lruvec). */ spin_lock_irq(&lruvec->lru_lock); /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_refault(struct folio *folio) { lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_activate, true); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { struct lru_gen_folio *lrugen; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); if (gen < 0) return true; set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0); lrugen = &folio_lruvec(folio)->lrugen; /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add, false); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file, true); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate, true); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree, true); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (put_devmap_managed_folio_refs(folio, nr_refs)) continue; if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[PAGEVEC_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } |
| 4 7 7 7 7 6 1 2 2 2 1 1 2 2 2 2 9 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Transparent proxy support for Linux/iptables * * Copyright (C) 2007-2008 BalaBit IT Ltd. * Author: Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> #include <net/sock.h> #include <net/inet_sock.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/inet6_hashtables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/netfilter/nf_socket.h> #include <linux/netfilter/xt_socket.h> /* "socket" match based redirection (no specific rule) * =================================================== * * There are connections with dynamic endpoints (e.g. FTP data * connection) that the user is unable to add explicit rules * for. These are taken care of by a generic "socket" rule. It is * assumed that the proxy application is trusted to open such * connections without explicit iptables rule (except of course the * generic 'socket' rule). In this case the following sockets are * matched in preference order: * * - match: if there's a fully established connection matching the * _packet_ tuple * * - match: if there's a non-zero bound listener (possibly with a * non-local address) We don't accept zero-bound listeners, since * then local services could intercept traffic going through the * box. */ static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { static struct xt_socket_mtinfo1 xt_info_v0 = { .flags = 0, }; return socket_match(skb, par, &xt_info_v0); } static bool socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static bool socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } #endif static int socket_mt_enable_defrag(struct net *net, int family) { switch (family) { case NFPROTO_IPV4: return nf_defrag_ipv4_enable(net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: return nf_defrag_ipv6_enable(net); #endif } WARN_ONCE(1, "Unknown family %d\n", family); return 0; } static int socket_mt_v1_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V1) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } return 0; } static int socket_mt_v2_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V2) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } return 0; } static int socket_mt_v3_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo3 *info = (struct xt_socket_mtinfo3 *)par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V3) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V3); return -EINVAL; } return 0; } static void socket_mt_destroy(const struct xt_mtdtor_param *par) { if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) else if (par->family == NFPROTO_IPV6) nf_defrag_ipv6_disable(par->net); #endif } static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", .revision = 0, .family = NFPROTO_IPV4, .match = socket_mt4_v0, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .destroy = socket_mt_destroy, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 1, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .destroy = socket_mt_destroy, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 2, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 2, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 3, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 3, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif }; static int __init socket_mt_init(void) { return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } static void __exit socket_mt_exit(void) { xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } module_init(socket_mt_init); module_exit(socket_mt_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); MODULE_DESCRIPTION("x_tables socket match module"); MODULE_ALIAS("ipt_socket"); MODULE_ALIAS("ip6t_socket"); |
| 13 13 13 13 13 13 5 13 13 12 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/auth.c * * Generic RPC client authentication API. * * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de> */ #include <linux/types.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/hash.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> #include <trace/events/sunrpc.h> #define RPC_CREDCACHE_DEFAULT_HASHBITS (4) struct rpc_cred_cache { struct hlist_head *hashtable; unsigned int hashbits; spinlock_t lock; }; static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS; static const struct rpc_authops __rcu *auth_flavors[RPC_AUTH_MAXFLAVOR] = { [RPC_AUTH_NULL] = (const struct rpc_authops __force __rcu *)&authnull_ops, [RPC_AUTH_UNIX] = (const struct rpc_authops __force __rcu *)&authunix_ops, [RPC_AUTH_TLS] = (const struct rpc_authops __force __rcu *)&authtls_ops, }; static LIST_HEAD(cred_unused); static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), }; /* * Return the machine_cred pointer to be used whenever * the a generic machine credential is needed. */ const struct cred *rpc_machine_cred(void) { return &machine_cred; } EXPORT_SYMBOL_GPL(rpc_machine_cred); #define MAX_HASHTABLE_BITS (14) static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) { unsigned long num; unsigned int nbits; int ret; if (!val) goto out_inval; ret = kstrtoul(val, 0, &num); if (ret) goto out_inval; nbits = fls(num - 1); if (nbits > MAX_HASHTABLE_BITS || nbits < 2) goto out_inval; *(unsigned int *)kp->arg = nbits; return 0; out_inval: return -EINVAL; } static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp) { unsigned int nbits; nbits = *(unsigned int *)kp->arg; return sprintf(buffer, "%u\n", 1U << nbits); } #define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int); static const struct kernel_param_ops param_ops_hashtbl_sz = { .set = param_set_hashtbl_sz, .get = param_get_hashtbl_sz, }; module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644); MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size"); static unsigned long auth_max_cred_cachesize = ULONG_MAX; module_param(auth_max_cred_cachesize, ulong, 0644); MODULE_PARM_DESC(auth_max_cred_cachesize, "RPC credential maximum total cache size"); static u32 pseudoflavor_to_flavor(u32 flavor) { if (flavor > RPC_AUTH_MAXFLAVOR) return RPC_AUTH_GSS; return flavor; } int rpcauth_register(const struct rpc_authops *ops) { const struct rpc_authops *old; rpc_authflavor_t flavor; if ((flavor = ops->au_flavor) >= RPC_AUTH_MAXFLAVOR) return -EINVAL; old = cmpxchg((const struct rpc_authops ** __force)&auth_flavors[flavor], NULL, ops); if (old == NULL || old == ops) return 0; return -EPERM; } EXPORT_SYMBOL_GPL(rpcauth_register); int rpcauth_unregister(const struct rpc_authops *ops) { const struct rpc_authops *old; rpc_authflavor_t flavor; if ((flavor = ops->au_flavor) >= RPC_AUTH_MAXFLAVOR) return -EINVAL; old = cmpxchg((const struct rpc_authops ** __force)&auth_flavors[flavor], ops, NULL); if (old == ops || old == NULL) return 0; return -EPERM; } EXPORT_SYMBOL_GPL(rpcauth_unregister); static const struct rpc_authops * rpcauth_get_authops(rpc_authflavor_t flavor) { const struct rpc_authops *ops; if (flavor >= RPC_AUTH_MAXFLAVOR) return NULL; rcu_read_lock(); ops = rcu_dereference(auth_flavors[flavor]); if (ops == NULL) { rcu_read_unlock(); request_module("rpc-auth-%u", flavor); rcu_read_lock(); ops = rcu_dereference(auth_flavors[flavor]); if (ops == NULL) goto out; } if (!try_module_get(ops->owner)) ops = NULL; out: rcu_read_unlock(); return ops; } static void rpcauth_put_authops(const struct rpc_authops *ops) { module_put(ops->owner); } /** * rpcauth_get_pseudoflavor - check if security flavor is supported * @flavor: a security flavor * @info: a GSS mech OID, quality of protection, and service value * * Verifies that an appropriate kernel module is available or already loaded. * Returns an equivalent pseudoflavor, or RPC_AUTH_MAXFLAVOR if "flavor" is * not supported locally. */ rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t flavor, struct rpcsec_gss_info *info) { const struct rpc_authops *ops = rpcauth_get_authops(flavor); rpc_authflavor_t pseudoflavor; if (!ops) return RPC_AUTH_MAXFLAVOR; pseudoflavor = flavor; if (ops->info2flavor != NULL) pseudoflavor = ops->info2flavor(info); rpcauth_put_authops(ops); return pseudoflavor; } EXPORT_SYMBOL_GPL(rpcauth_get_pseudoflavor); /** * rpcauth_get_gssinfo - find GSS tuple matching a GSS pseudoflavor * @pseudoflavor: GSS pseudoflavor to match * @info: rpcsec_gss_info structure to fill in * * Returns zero and fills in "info" if pseudoflavor matches a * supported mechanism. */ int rpcauth_get_gssinfo(rpc_authflavor_t pseudoflavor, struct rpcsec_gss_info *info) { rpc_authflavor_t flavor = pseudoflavor_to_flavor(pseudoflavor); const struct rpc_authops *ops; int result; ops = rpcauth_get_authops(flavor); if (ops == NULL) return -ENOENT; result = -ENOENT; if (ops->flavor2info != NULL) result = ops->flavor2info(pseudoflavor, info); rpcauth_put_authops(ops); return result; } EXPORT_SYMBOL_GPL(rpcauth_get_gssinfo); struct rpc_auth * rpcauth_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct rpc_auth *auth = ERR_PTR(-EINVAL); const struct rpc_authops *ops; u32 flavor = pseudoflavor_to_flavor(args->pseudoflavor); ops = rpcauth_get_authops(flavor); if (ops == NULL) goto out; auth = ops->create(args, clnt); rpcauth_put_authops(ops); if (IS_ERR(auth)) return auth; if (clnt->cl_auth) rpcauth_release(clnt->cl_auth); clnt->cl_auth = auth; out: return auth; } EXPORT_SYMBOL_GPL(rpcauth_create); void rpcauth_release(struct rpc_auth *auth) { if (!refcount_dec_and_test(&auth->au_count)) return; auth->au_ops->destroy(auth); } static DEFINE_SPINLOCK(rpc_credcache_lock); /* * On success, the caller is responsible for freeing the reference * held by the hashtable */ static bool rpcauth_unhash_cred_locked(struct rpc_cred *cred) { if (!test_and_clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) return false; hlist_del_rcu(&cred->cr_hash); return true; } static bool rpcauth_unhash_cred(struct rpc_cred *cred) { spinlock_t *cache_lock; bool ret; if (!test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) return false; cache_lock = &cred->cr_auth->au_credcache->lock; spin_lock(cache_lock); ret = rpcauth_unhash_cred_locked(cred); spin_unlock(cache_lock); return ret; } /* * Initialize RPC credential cache */ int rpcauth_init_credcache(struct rpc_auth *auth) { struct rpc_cred_cache *new; unsigned int hashsize; new = kmalloc(sizeof(*new), GFP_KERNEL); if (!new) goto out_nocache; new->hashbits = auth_hashbits; hashsize = 1U << new->hashbits; new->hashtable = kcalloc(hashsize, sizeof(new->hashtable[0]), GFP_KERNEL); if (!new->hashtable) goto out_nohashtbl; spin_lock_init(&new->lock); auth->au_credcache = new; return 0; out_nohashtbl: kfree(new); out_nocache: return -ENOMEM; } EXPORT_SYMBOL_GPL(rpcauth_init_credcache); char * rpcauth_stringify_acceptor(struct rpc_cred *cred) { if (!cred->cr_ops->crstringify_acceptor) return NULL; return cred->cr_ops->crstringify_acceptor(cred); } EXPORT_SYMBOL_GPL(rpcauth_stringify_acceptor); /* * Destroy a list of credentials */ static inline void rpcauth_destroy_credlist(struct list_head *head) { struct rpc_cred *cred; while (!list_empty(head)) { cred = list_entry(head->next, struct rpc_cred, cr_lru); list_del_init(&cred->cr_lru); put_rpccred(cred); } } static void rpcauth_lru_add_locked(struct rpc_cred *cred) { if (!list_empty(&cred->cr_lru)) return; number_cred_unused++; list_add_tail(&cred->cr_lru, &cred_unused); } static void rpcauth_lru_add(struct rpc_cred *cred) { if (!list_empty(&cred->cr_lru)) return; spin_lock(&rpc_credcache_lock); rpcauth_lru_add_locked(cred); spin_unlock(&rpc_credcache_lock); } static void rpcauth_lru_remove_locked(struct rpc_cred *cred) { if (list_empty(&cred->cr_lru)) return; number_cred_unused--; list_del_init(&cred->cr_lru); } static void rpcauth_lru_remove(struct rpc_cred *cred) { if (list_empty(&cred->cr_lru)) return; spin_lock(&rpc_credcache_lock); rpcauth_lru_remove_locked(cred); spin_unlock(&rpc_credcache_lock); } /* * Clear the RPC credential cache, and delete those credentials * that are not referenced. */ void rpcauth_clear_credcache(struct rpc_cred_cache *cache) { LIST_HEAD(free); struct hlist_head *head; struct rpc_cred *cred; unsigned int hashsize = 1U << cache->hashbits; int i; spin_lock(&rpc_credcache_lock); spin_lock(&cache->lock); for (i = 0; i < hashsize; i++) { head = &cache->hashtable[i]; while (!hlist_empty(head)) { cred = hlist_entry(head->first, struct rpc_cred, cr_hash); rpcauth_unhash_cred_locked(cred); /* Note: We now hold a reference to cred */ rpcauth_lru_remove_locked(cred); list_add_tail(&cred->cr_lru, &free); } } spin_unlock(&cache->lock); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); } /* * Destroy the RPC credential cache */ void rpcauth_destroy_credcache(struct rpc_auth *auth) { struct rpc_cred_cache *cache = auth->au_credcache; if (cache) { auth->au_credcache = NULL; rpcauth_clear_credcache(cache); kfree(cache->hashtable); kfree(cache); } } EXPORT_SYMBOL_GPL(rpcauth_destroy_credcache); #define RPC_AUTH_EXPIRY_MORATORIUM (60 * HZ) /* * Remove stale credentials. Avoid sleeping inside the loop. */ static long rpcauth_prune_expired(struct list_head *free, int nr_to_scan) { struct rpc_cred *cred, *next; unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM; long freed = 0; list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { if (nr_to_scan-- == 0) break; if (refcount_read(&cred->cr_count) > 1) { rpcauth_lru_remove_locked(cred); continue; } /* * Enforce a 60 second garbage collection moratorium * Note that the cred_unused list must be time-ordered. */ if (time_in_range(cred->cr_expire, expired, jiffies)) continue; if (!rpcauth_unhash_cred(cred)) continue; rpcauth_lru_remove_locked(cred); freed++; list_add_tail(&cred->cr_lru, free); } return freed ? freed : SHRINK_STOP; } static unsigned long rpcauth_cache_do_shrink(int nr_to_scan) { LIST_HEAD(free); unsigned long freed; spin_lock(&rpc_credcache_lock); freed = rpcauth_prune_expired(&free, nr_to_scan); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); return freed; } /* * Run memory cache shrinker. */ static unsigned long rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL) return SHRINK_STOP; /* nothing left, don't come back */ if (list_empty(&cred_unused)) return SHRINK_STOP; return rpcauth_cache_do_shrink(sc->nr_to_scan); } static unsigned long rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return number_cred_unused * sysctl_vfs_cache_pressure / 100; } static void rpcauth_cache_enforce_limit(void) { unsigned long diff; unsigned int nr_to_scan; if (number_cred_unused <= auth_max_cred_cachesize) return; diff = number_cred_unused - auth_max_cred_cachesize; nr_to_scan = 100; if (diff < nr_to_scan) nr_to_scan = diff; rpcauth_cache_do_shrink(nr_to_scan); } /* * Look up a process' credentials in the authentication cache */ struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, int flags, gfp_t gfp) { LIST_HEAD(free); struct rpc_cred_cache *cache = auth->au_credcache; struct rpc_cred *cred = NULL, *entry, *new; unsigned int nr; nr = auth->au_ops->hash_cred(acred, cache->hashbits); rcu_read_lock(); hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); if (cred) break; } rcu_read_unlock(); if (cred != NULL) goto found; new = auth->au_ops->crcreate(auth, acred, flags, gfp); if (IS_ERR(new)) { cred = new; goto out; } spin_lock(&cache->lock); hlist_for_each_entry(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); if (cred) break; } if (cred == NULL) { cred = new; set_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags); refcount_inc(&cred->cr_count); hlist_add_head_rcu(&cred->cr_hash, &cache->hashtable[nr]); } else list_add_tail(&new->cr_lru, &free); spin_unlock(&cache->lock); rpcauth_cache_enforce_limit(); found: if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags) && cred->cr_ops->cr_init != NULL && !(flags & RPCAUTH_LOOKUP_NEW)) { int res = cred->cr_ops->cr_init(auth, cred); if (res < 0) { put_rpccred(cred); cred = ERR_PTR(res); } } rpcauth_destroy_credlist(&free); out: return cred; } EXPORT_SYMBOL_GPL(rpcauth_lookup_credcache); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *auth, int flags) { struct auth_cred acred; struct rpc_cred *ret; const struct cred *cred = current_cred(); memset(&acred, 0, sizeof(acred)); acred.cred = cred; ret = auth->au_ops->lookup_cred(auth, &acred, flags); return ret; } EXPORT_SYMBOL_GPL(rpcauth_lookupcred); void rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, struct rpc_auth *auth, const struct rpc_credops *ops) { INIT_HLIST_NODE(&cred->cr_hash); INIT_LIST_HEAD(&cred->cr_lru); refcount_set(&cred->cr_count, 1); cred->cr_auth = auth; cred->cr_flags = 0; cred->cr_ops = ops; cred->cr_expire = jiffies; cred->cr_cred = get_cred(acred->cred); } EXPORT_SYMBOL_GPL(rpcauth_init_cred); static struct rpc_cred * rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .cred = get_task_cred(&init_task), }; struct rpc_cred *ret; if (RPC_IS_ASYNC(task)) lookupflags |= RPCAUTH_LOOKUP_ASYNC; ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags); put_cred(acred.cred); return ret; } static struct rpc_cred * rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .principal = task->tk_client->cl_principal, .cred = init_task.cred, }; if (!acred.principal) return NULL; if (RPC_IS_ASYNC(task)) lookupflags |= RPCAUTH_LOOKUP_ASYNC; return auth->au_ops->lookup_cred(auth, &acred, lookupflags); } static struct rpc_cred * rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; return rpcauth_lookupcred(auth, lookupflags); } static int rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_cred *new = NULL; int lookupflags = 0; struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .cred = cred, }; if (flags & RPC_TASK_ASYNC) lookupflags |= RPCAUTH_LOOKUP_NEW | RPCAUTH_LOOKUP_ASYNC; if (task->tk_op_cred) /* Task must use exactly this rpc_cred */ new = get_rpccred(task->tk_op_cred); else if (cred != NULL && cred != &machine_cred) new = auth->au_ops->lookup_cred(auth, &acred, lookupflags); else if (cred == &machine_cred) new = rpcauth_bind_machine_cred(task, lookupflags); /* If machine cred couldn't be bound, try a root cred */ if (new) ; else if (cred == &machine_cred) new = rpcauth_bind_root_cred(task, lookupflags); else if (flags & RPC_TASK_NULLCREDS) new = authnull_ops.lookup_cred(NULL, NULL, 0); else new = rpcauth_bind_new_cred(task, lookupflags); if (IS_ERR(new)) return PTR_ERR(new); put_rpccred(req->rq_cred); req->rq_cred = new; return 0; } void put_rpccred(struct rpc_cred *cred) { if (cred == NULL) return; rcu_read_lock(); if (refcount_dec_and_test(&cred->cr_count)) goto destroy; if (refcount_read(&cred->cr_count) != 1 || !test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) goto out; if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) { cred->cr_expire = jiffies; rpcauth_lru_add(cred); /* Race breaker */ if (unlikely(!test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags))) rpcauth_lru_remove(cred); } else if (rpcauth_unhash_cred(cred)) { rpcauth_lru_remove(cred); if (refcount_dec_and_test(&cred->cr_count)) goto destroy; } out: rcu_read_unlock(); return; destroy: rcu_read_unlock(); cred->cr_ops->crdestroy(cred); } EXPORT_SYMBOL_GPL(put_rpccred); /** * rpcauth_marshcred - Append RPC credential to end of @xdr * @task: controlling RPC task * @xdr: xdr_stream containing initial portion of RPC Call header * * On success, an appropriate verifier is added to @xdr, @xdr is * updated to point past the verifier, and zero is returned. * Otherwise, @xdr is in an undefined state and a negative errno * is returned. */ int rpcauth_marshcred(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crmarshal(task, xdr); } /** * rpcauth_wrap_req_encode - XDR encode the RPC procedure * @task: controlling RPC task * @xdr: stream where on-the-wire bytes are to be marshalled * * On success, @xdr contains the encoded and wrapped message. * Otherwise, @xdr is in an undefined state. */ int rpcauth_wrap_req_encode(struct rpc_task *task, struct xdr_stream *xdr) { kxdreproc_t encode = task->tk_msg.rpc_proc->p_encode; encode(task->tk_rqstp, xdr, task->tk_msg.rpc_argp); return 0; } EXPORT_SYMBOL_GPL(rpcauth_wrap_req_encode); /** * rpcauth_wrap_req - XDR encode and wrap the RPC procedure * @task: controlling RPC task * @xdr: stream where on-the-wire bytes are to be marshalled * * On success, @xdr contains the encoded and wrapped message, * and zero is returned. Otherwise, @xdr is in an undefined * state and a negative errno is returned. */ int rpcauth_wrap_req(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crwrap_req(task, xdr); } /** * rpcauth_checkverf - Validate verifier in RPC Reply header * @task: controlling RPC task * @xdr: xdr_stream containing RPC Reply header * * Return values: * %0: Verifier is valid. @xdr now points past the verifier. * %-EIO: Verifier is corrupted or message ended early. * %-EACCES: Verifier is intact but not valid. * %-EPROTONOSUPPORT: Server does not support the requested auth type. * * When a negative errno is returned, @xdr is left in an undefined * state. */ int rpcauth_checkverf(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crvalidate(task, xdr); } /** * rpcauth_unwrap_resp_decode - Invoke XDR decode function * @task: controlling RPC task * @xdr: stream where the Reply message resides * * Returns zero on success; otherwise a negative errno is returned. */ int rpcauth_unwrap_resp_decode(struct rpc_task *task, struct xdr_stream *xdr) { kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; return decode(task->tk_rqstp, xdr, task->tk_msg.rpc_resp); } EXPORT_SYMBOL_GPL(rpcauth_unwrap_resp_decode); /** * rpcauth_unwrap_resp - Invoke unwrap and decode function for the cred * @task: controlling RPC task * @xdr: stream where the Reply message resides * * Returns zero on success; otherwise a negative errno is returned. */ int rpcauth_unwrap_resp(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crunwrap_resp(task, xdr); } bool rpcauth_xmit_need_reencode(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; if (!cred || !cred->cr_ops->crneed_reencode) return false; return cred->cr_ops->crneed_reencode(task); } int rpcauth_refreshcred(struct rpc_task *task) { struct rpc_cred *cred; int err; cred = task->tk_rqstp->rq_cred; if (cred == NULL) { err = rpcauth_bindcred(task, task->tk_msg.rpc_cred, task->tk_flags); if (err < 0) goto out; cred = task->tk_rqstp->rq_cred; } err = cred->cr_ops->crrefresh(task); out: if (err < 0) task->tk_status = err; return err; } void rpcauth_invalcred(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; if (cred) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); } int rpcauth_uptodatecred(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; return cred == NULL || test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0; } static struct shrinker *rpc_cred_shrinker; int __init rpcauth_init_module(void) { int err; err = rpc_init_authunix(); if (err < 0) goto out1; rpc_cred_shrinker = shrinker_alloc(0, "sunrpc_cred"); if (!rpc_cred_shrinker) { err = -ENOMEM; goto out2; } rpc_cred_shrinker->count_objects = rpcauth_cache_shrink_count; rpc_cred_shrinker->scan_objects = rpcauth_cache_shrink_scan; shrinker_register(rpc_cred_shrinker); return 0; out2: rpc_destroy_authunix(); out1: return err; } void rpcauth_remove_module(void) { rpc_destroy_authunix(); shrinker_free(rpc_cred_shrinker); } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | // SPDX-License-Identifier: GPL-2.0-only /* * drivers/mfd/mfd-core.c * * core MFD support * Copyright (c) 2006 Ian Molton * Copyright (c) 2007,2008 Dmitry Baryshkov */ #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/acpi.h> #include <linux/list.h> #include <linux/property.h> #include <linux/mfd/core.h> #include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/irqdomain.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/regulator/consumer.h> static LIST_HEAD(mfd_of_node_list); struct mfd_of_node_entry { struct list_head list; struct device *dev; struct device_node *np; }; static const struct device_type mfd_dev_type = { .name = "mfd_device", }; #if IS_ENABLED(CONFIG_ACPI) struct match_ids_walk_data { struct acpi_device_id *ids; struct acpi_device *adev; }; static int match_device_ids(struct acpi_device *adev, void *data) { struct match_ids_walk_data *wd = data; if (!acpi_match_device_ids(adev, wd->ids)) { wd->adev = adev; return 1; } return 0; } static void mfd_acpi_add_device(const struct mfd_cell *cell, struct platform_device *pdev) { const struct mfd_cell_acpi_match *match = cell->acpi_match; struct acpi_device *adev = NULL; struct acpi_device *parent; parent = ACPI_COMPANION(pdev->dev.parent); if (!parent) return; /* * MFD child device gets its ACPI handle either from the ACPI device * directly under the parent that matches the either _HID or _CID, or * _ADR or it will use the parent handle if is no ID is given. * * Note that use of _ADR is a grey area in the ACPI specification, * though at least Intel Galileo Gen 2 is using it to distinguish * the children devices. */ if (match) { if (match->pnpid) { struct acpi_device_id ids[2] = {}; struct match_ids_walk_data wd = { .adev = NULL, .ids = ids, }; strscpy(ids[0].id, match->pnpid, sizeof(ids[0].id)); acpi_dev_for_each_child(parent, match_device_ids, &wd); adev = wd.adev; } else { adev = acpi_find_child_device(parent, match->adr, false); } } device_set_node(&pdev->dev, acpi_fwnode_handle(adev ?: parent)); } #else static inline void mfd_acpi_add_device(const struct mfd_cell *cell, struct platform_device *pdev) { } #endif static int mfd_match_of_node_to_dev(struct platform_device *pdev, struct device_node *np, const struct mfd_cell *cell) { #if IS_ENABLED(CONFIG_OF) struct mfd_of_node_entry *of_entry; u64 of_node_addr; /* Skip if OF node has previously been allocated to a device */ list_for_each_entry(of_entry, &mfd_of_node_list, list) if (of_entry->np == np) return -EAGAIN; if (!cell->use_of_reg) /* No of_reg defined - allocate first free compatible match */ goto allocate_of_node; /* We only care about each node's first defined address */ if (of_property_read_reg(np, 0, &of_node_addr, NULL)) /* OF node does not contatin a 'reg' property to match to */ return -EAGAIN; if (cell->of_reg != of_node_addr) /* No match */ return -EAGAIN; allocate_of_node: of_entry = kzalloc(sizeof(*of_entry), GFP_KERNEL); if (!of_entry) return -ENOMEM; of_entry->dev = &pdev->dev; of_entry->np = np; list_add_tail(&of_entry->list, &mfd_of_node_list); device_set_node(&pdev->dev, of_fwnode_handle(np)); #endif return 0; } static int mfd_add_device(struct device *parent, int id, const struct mfd_cell *cell, struct resource *mem_base, int irq_base, struct irq_domain *domain) { struct resource *res; struct platform_device *pdev; struct device_node *np = NULL; struct mfd_of_node_entry *of_entry, *tmp; bool disabled = false; int ret = -ENOMEM; int platform_id; int r; if (id == PLATFORM_DEVID_AUTO) platform_id = id; else platform_id = id + cell->id; pdev = platform_device_alloc(cell->name, platform_id); if (!pdev) goto fail_alloc; pdev->mfd_cell = kmemdup(cell, sizeof(*cell), GFP_KERNEL); if (!pdev->mfd_cell) goto fail_device; res = kcalloc(cell->num_resources, sizeof(*res), GFP_KERNEL); if (!res) goto fail_device; pdev->dev.parent = parent; pdev->dev.type = &mfd_dev_type; pdev->dev.dma_mask = parent->dma_mask; pdev->dev.dma_parms = parent->dma_parms; pdev->dev.coherent_dma_mask = parent->coherent_dma_mask; ret = regulator_bulk_register_supply_alias( &pdev->dev, cell->parent_supplies, parent, cell->parent_supplies, cell->num_parent_supplies); if (ret < 0) goto fail_res; if (IS_ENABLED(CONFIG_OF) && parent->of_node && cell->of_compatible) { for_each_child_of_node(parent->of_node, np) { if (of_device_is_compatible(np, cell->of_compatible)) { /* Skip 'disabled' devices */ if (!of_device_is_available(np)) { disabled = true; continue; } ret = mfd_match_of_node_to_dev(pdev, np, cell); if (ret == -EAGAIN) continue; of_node_put(np); if (ret) goto fail_alias; goto match; } } if (disabled) { /* Ignore 'disabled' devices error free */ ret = 0; goto fail_alias; } match: if (!pdev->dev.of_node) pr_warn("%s: Failed to locate of_node [id: %d]\n", cell->name, platform_id); } mfd_acpi_add_device(cell, pdev); if (cell->pdata_size) { ret = platform_device_add_data(pdev, cell->platform_data, cell->pdata_size); if (ret) goto fail_of_entry; } if (cell->swnode) { ret = device_add_software_node(&pdev->dev, cell->swnode); if (ret) goto fail_of_entry; } for (r = 0; r < cell->num_resources; r++) { res[r].name = cell->resources[r].name; res[r].flags = cell->resources[r].flags; /* Find out base to use */ if ((cell->resources[r].flags & IORESOURCE_MEM) && mem_base) { res[r].parent = mem_base; res[r].start = mem_base->start + cell->resources[r].start; res[r].end = mem_base->start + cell->resources[r].end; } else if (cell->resources[r].flags & IORESOURCE_IRQ) { if (domain) { /* Unable to create mappings for IRQ ranges. */ WARN_ON(cell->resources[r].start != cell->resources[r].end); res[r].start = res[r].end = irq_create_mapping( domain, cell->resources[r].start); } else { res[r].start = irq_base + cell->resources[r].start; res[r].end = irq_base + cell->resources[r].end; } } else { res[r].parent = cell->resources[r].parent; res[r].start = cell->resources[r].start; res[r].end = cell->resources[r].end; } if (!cell->ignore_resource_conflicts) { if (has_acpi_companion(&pdev->dev)) { ret = acpi_check_resource_conflict(&res[r]); if (ret) goto fail_res_conflict; } } } ret = platform_device_add_resources(pdev, res, cell->num_resources); if (ret) goto fail_res_conflict; ret = platform_device_add(pdev); if (ret) goto fail_res_conflict; if (cell->pm_runtime_no_callbacks) pm_runtime_no_callbacks(&pdev->dev); kfree(res); return 0; fail_res_conflict: if (cell->swnode) device_remove_software_node(&pdev->dev); fail_of_entry: list_for_each_entry_safe(of_entry, tmp, &mfd_of_node_list, list) if (of_entry->dev == &pdev->dev) { list_del(&of_entry->list); kfree(of_entry); } fail_alias: regulator_bulk_unregister_supply_alias(&pdev->dev, cell->parent_supplies, cell->num_parent_supplies); fail_res: kfree(res); fail_device: platform_device_put(pdev); fail_alloc: return ret; } /** * mfd_add_devices - register child devices * * @parent: Pointer to parent device. * @id: Can be PLATFORM_DEVID_AUTO to let the Platform API take care * of device numbering, or will be added to a device's cell_id. * @cells: Array of (struct mfd_cell)s describing child devices. * @n_devs: Number of child devices to register. * @mem_base: Parent register range resource for child devices. * @irq_base: Base of the range of virtual interrupt numbers allocated for * this MFD device. Unused if @domain is specified. * @domain: Interrupt domain to create mappings for hardware interrupts. */ int mfd_add_devices(struct device *parent, int id, const struct mfd_cell *cells, int n_devs, struct resource *mem_base, int irq_base, struct irq_domain *domain) { int i; int ret; for (i = 0; i < n_devs; i++) { ret = mfd_add_device(parent, id, cells + i, mem_base, irq_base, domain); if (ret) goto fail; } return 0; fail: if (i) mfd_remove_devices(parent); return ret; } EXPORT_SYMBOL(mfd_add_devices); static int mfd_remove_devices_fn(struct device *dev, void *data) { struct platform_device *pdev; const struct mfd_cell *cell; struct mfd_of_node_entry *of_entry, *tmp; int *level = data; if (dev->type != &mfd_dev_type) return 0; pdev = to_platform_device(dev); cell = mfd_get_cell(pdev); if (level && cell->level > *level) return 0; if (cell->swnode) device_remove_software_node(&pdev->dev); list_for_each_entry_safe(of_entry, tmp, &mfd_of_node_list, list) if (of_entry->dev == &pdev->dev) { list_del(&of_entry->list); kfree(of_entry); } regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies, cell->num_parent_supplies); platform_device_unregister(pdev); return 0; } void mfd_remove_devices_late(struct device *parent) { int level = MFD_DEP_LEVEL_HIGH; device_for_each_child_reverse(parent, &level, mfd_remove_devices_fn); } EXPORT_SYMBOL(mfd_remove_devices_late); void mfd_remove_devices(struct device *parent) { int level = MFD_DEP_LEVEL_NORMAL; device_for_each_child_reverse(parent, &level, mfd_remove_devices_fn); } EXPORT_SYMBOL(mfd_remove_devices); static void devm_mfd_dev_release(struct device *dev, void *res) { mfd_remove_devices(dev); } /** * devm_mfd_add_devices - Resource managed version of mfd_add_devices() * * Returns 0 on success or an appropriate negative error number on failure. * All child-devices of the MFD will automatically be removed when it gets * unbinded. * * @dev: Pointer to parent device. * @id: Can be PLATFORM_DEVID_AUTO to let the Platform API take care * of device numbering, or will be added to a device's cell_id. * @cells: Array of (struct mfd_cell)s describing child devices. * @n_devs: Number of child devices to register. * @mem_base: Parent register range resource for child devices. * @irq_base: Base of the range of virtual interrupt numbers allocated for * this MFD device. Unused if @domain is specified. * @domain: Interrupt domain to create mappings for hardware interrupts. */ int devm_mfd_add_devices(struct device *dev, int id, const struct mfd_cell *cells, int n_devs, struct resource *mem_base, int irq_base, struct irq_domain *domain) { struct device **ptr; int ret; ptr = devres_alloc(devm_mfd_dev_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return -ENOMEM; ret = mfd_add_devices(dev, id, cells, n_devs, mem_base, irq_base, domain); if (ret < 0) { devres_free(ptr); return ret; } *ptr = dev; devres_add(dev, ptr); return ret; } EXPORT_SYMBOL(devm_mfd_add_devices); MODULE_DESCRIPTION("Core MFD support"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Ian Molton, Dmitry Baryshkov"); |
| 1 1 1 29 28 1 27 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Host Side support for RNDIS Networking Links * Copyright (C) 2005 by David Brownell */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/mii.h> #include <linux/usb.h> #include <linux/usb/cdc.h> #include <linux/usb/usbnet.h> #include <linux/usb/rndis_host.h> /* * RNDIS is NDIS remoted over USB. It's a MSFT variant of CDC ACM ... of * course ACM was intended for modems, not Ethernet links! USB's standard * for Ethernet links is "CDC Ethernet", which is significantly simpler. * * NOTE that Microsoft's "RNDIS 1.0" specification is incomplete. Issues * include: * - Power management in particular relies on information that's scattered * through other documentation, and which is incomplete or incorrect even * there. * - There are various undocumented protocol requirements, such as the * need to send unused garbage in control-OUT messages. * - In some cases, MS-Windows will emit undocumented requests; this * matters more to peripheral implementations than host ones. * * Moreover there's a no-open-specs variant of RNDIS called "ActiveSync". * * For these reasons and others, ** USE OF RNDIS IS STRONGLY DISCOURAGED ** in * favor of such non-proprietary alternatives as CDC Ethernet or the newer (and * currently rare) "Ethernet Emulation Model" (EEM). */ /* * RNDIS notifications from device: command completion; "reverse" * keepalives; etc */ void rndis_status(struct usbnet *dev, struct urb *urb) { netdev_dbg(dev->net, "rndis status urb, len %d stat %d\n", urb->actual_length, urb->status); // FIXME for keepalives, respond immediately (asynchronously) // if not an RNDIS status, do like cdc_status(dev,urb) does } EXPORT_SYMBOL_GPL(rndis_status); /* * RNDIS indicate messages. */ static void rndis_msg_indicate(struct usbnet *dev, struct rndis_indicate *msg, int buflen) { struct cdc_state *info = (void *)&dev->data; struct device *udev = &info->control->dev; if (dev->driver_info->indication) { dev->driver_info->indication(dev, msg, buflen); } else { u32 status = le32_to_cpu(msg->status); switch (status) { case RNDIS_STATUS_MEDIA_CONNECT: dev_info(udev, "rndis media connect\n"); break; case RNDIS_STATUS_MEDIA_DISCONNECT: dev_info(udev, "rndis media disconnect\n"); break; default: dev_info(udev, "rndis indication: 0x%08x\n", status); } } } /* * RPC done RNDIS-style. Caller guarantees: * - message is properly byteswapped * - there's no other request pending * - buf can hold up to 1KB response (required by RNDIS spec) * On return, the first few entries are already byteswapped. * * Call context is likely probe(), before interface name is known, * which is why we won't try to use it in the diagnostics. */ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) { struct cdc_state *info = (void *) &dev->data; struct usb_cdc_notification notification; int master_ifnum; int retval; int partial; unsigned count; u32 xid = 0, msg_len, request_id, msg_type, rsp, status; /* REVISIT when this gets called from contexts other than probe() or * disconnect(): either serialize, or dispatch responses on xid */ msg_type = le32_to_cpu(buf->msg_type); /* Issue the request; xid is unique, don't bother byteswapping it */ if (likely(msg_type != RNDIS_MSG_HALT && msg_type != RNDIS_MSG_RESET)) { xid = dev->xid++; if (!xid) xid = dev->xid++; buf->request_id = (__force __le32) xid; } master_ifnum = info->control->cur_altsetting->desc.bInterfaceNumber; retval = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), USB_CDC_SEND_ENCAPSULATED_COMMAND, USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, master_ifnum, buf, le32_to_cpu(buf->msg_len), RNDIS_CONTROL_TIMEOUT_MS); if (unlikely(retval < 0 || xid == 0)) return retval; /* Some devices don't respond on the control channel until * polled on the status channel, so do that first. */ if (dev->driver_info->data & RNDIS_DRIVER_DATA_POLL_STATUS) { retval = usb_interrupt_msg( dev->udev, usb_rcvintpipe(dev->udev, dev->status->desc.bEndpointAddress), ¬ification, sizeof(notification), &partial, RNDIS_CONTROL_TIMEOUT_MS); if (unlikely(retval < 0)) return retval; } /* Poll the control channel; the request probably completed immediately */ rsp = le32_to_cpu(buf->msg_type) | RNDIS_MSG_COMPLETION; for (count = 0; count < 10; count++) { memset(buf, 0, CONTROL_BUFFER_SIZE); retval = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), USB_CDC_GET_ENCAPSULATED_RESPONSE, USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, master_ifnum, buf, buflen, RNDIS_CONTROL_TIMEOUT_MS); if (likely(retval >= 8)) { msg_type = le32_to_cpu(buf->msg_type); msg_len = le32_to_cpu(buf->msg_len); status = le32_to_cpu(buf->status); request_id = (__force u32) buf->request_id; if (likely(msg_type == rsp)) { if (likely(request_id == xid)) { if (unlikely(rsp == RNDIS_MSG_RESET_C)) return 0; if (likely(RNDIS_STATUS_SUCCESS == status)) return 0; dev_dbg(&info->control->dev, "rndis reply status %08x\n", status); return -EL3RST; } dev_dbg(&info->control->dev, "rndis reply id %d expected %d\n", request_id, xid); /* then likely retry */ } else switch (msg_type) { case RNDIS_MSG_INDICATE: /* fault/event */ rndis_msg_indicate(dev, (void *)buf, buflen); break; case RNDIS_MSG_KEEPALIVE: { /* ping */ struct rndis_keepalive_c *msg = (void *)buf; msg->msg_type = cpu_to_le32(RNDIS_MSG_KEEPALIVE_C); msg->msg_len = cpu_to_le32(sizeof *msg); msg->status = cpu_to_le32(RNDIS_STATUS_SUCCESS); retval = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), USB_CDC_SEND_ENCAPSULATED_COMMAND, USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, master_ifnum, msg, sizeof *msg, RNDIS_CONTROL_TIMEOUT_MS); if (unlikely(retval < 0)) dev_dbg(&info->control->dev, "rndis keepalive err %d\n", retval); } break; default: dev_dbg(&info->control->dev, "unexpected rndis msg %08x len %d\n", le32_to_cpu(buf->msg_type), msg_len); } } else { /* device probably issued a protocol stall; ignore */ dev_dbg(&info->control->dev, "rndis response error, code %d\n", retval); } msleep(40); } dev_dbg(&info->control->dev, "rndis response timeout\n"); return -ETIMEDOUT; } EXPORT_SYMBOL_GPL(rndis_command); /* * rndis_query: * * Performs a query for @oid along with 0 or more bytes of payload as * specified by @in_len. If @reply_len is not set to -1 then the reply * length is checked against this value, resulting in an error if it * doesn't match. * * NOTE: Adding a payload exactly or greater than the size of the expected * response payload is an evident requirement MSFT added for ActiveSync. * * The only exception is for OIDs that return a variably sized response, * in which case no payload should be added. This undocumented (and * nonsensical!) issue was found by sniffing protocol requests from the * ActiveSync 4.1 Windows driver. */ static int rndis_query(struct usbnet *dev, struct usb_interface *intf, void *buf, u32 oid, u32 in_len, void **reply, int *reply_len) { int retval; union { void *buf; struct rndis_msg_hdr *header; struct rndis_query *get; struct rndis_query_c *get_c; } u; u32 off, len; u.buf = buf; memset(u.get, 0, sizeof *u.get + in_len); u.get->msg_type = cpu_to_le32(RNDIS_MSG_QUERY); u.get->msg_len = cpu_to_le32(sizeof *u.get + in_len); u.get->oid = cpu_to_le32(oid); u.get->len = cpu_to_le32(in_len); u.get->offset = cpu_to_le32(20); retval = rndis_command(dev, u.header, CONTROL_BUFFER_SIZE); if (unlikely(retval < 0)) { dev_err(&intf->dev, "RNDIS_MSG_QUERY(0x%08x) failed, %d\n", oid, retval); return retval; } off = le32_to_cpu(u.get_c->offset); len = le32_to_cpu(u.get_c->len); if (unlikely((off > CONTROL_BUFFER_SIZE - 8) || (len > CONTROL_BUFFER_SIZE - 8 - off))) goto response_error; if (*reply_len != -1 && len != *reply_len) goto response_error; *reply = (unsigned char *) &u.get_c->request_id + off; *reply_len = len; return retval; response_error: dev_err(&intf->dev, "RNDIS_MSG_QUERY(0x%08x) " "invalid response - off %d len %d\n", oid, off, len); return -EDOM; } /* same as usbnet_netdev_ops but MTU change not allowed */ static const struct net_device_ops rndis_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; int generic_rndis_bind(struct usbnet *dev, struct usb_interface *intf, int flags) { int retval; struct net_device *net = dev->net; struct cdc_state *info = (void *) &dev->data; union { void *buf; struct rndis_msg_hdr *header; struct rndis_init *init; struct rndis_init_c *init_c; struct rndis_query *get; struct rndis_query_c *get_c; struct rndis_set *set; struct rndis_set_c *set_c; struct rndis_halt *halt; } u; u32 tmp; __le32 phym_unspec, *phym; int reply_len; unsigned char *bp; /* we can't rely on i/o from stack working, or stack allocation */ u.buf = kmalloc(CONTROL_BUFFER_SIZE, GFP_KERNEL); if (!u.buf) return -ENOMEM; retval = usbnet_generic_cdc_bind(dev, intf); if (retval < 0) goto fail; u.init->msg_type = cpu_to_le32(RNDIS_MSG_INIT); u.init->msg_len = cpu_to_le32(sizeof *u.init); u.init->major_version = cpu_to_le32(1); u.init->minor_version = cpu_to_le32(0); /* max transfer (in spec) is 0x4000 at full speed, but for * TX we'll stick to one Ethernet packet plus RNDIS framing. * For RX we handle drivers that zero-pad to end-of-packet. * Don't let userspace change these settings. * * NOTE: there still seems to be weirdness here, as if we need * to do some more things to make sure WinCE targets accept this. * They default to jumbograms of 8KB or 16KB, which is absurd * for such low data rates and which is also more than Linux * can usually expect to allocate for SKB data... */ net->hard_header_len += sizeof (struct rndis_data_hdr); dev->hard_mtu = net->mtu + net->hard_header_len; dev->maxpacket = usb_maxpacket(dev->udev, dev->out); if (dev->maxpacket == 0) { netif_dbg(dev, probe, dev->net, "dev->maxpacket can't be 0\n"); retval = -EINVAL; goto fail_and_release; } dev->rx_urb_size = dev->hard_mtu + (dev->maxpacket + 1); dev->rx_urb_size &= ~(dev->maxpacket - 1); u.init->max_transfer_size = cpu_to_le32(dev->rx_urb_size); net->netdev_ops = &rndis_netdev_ops; retval = rndis_command(dev, u.header, CONTROL_BUFFER_SIZE); if (unlikely(retval < 0)) { /* it might not even be an RNDIS device!! */ dev_err(&intf->dev, "RNDIS init failed, %d\n", retval); goto fail_and_release; } tmp = le32_to_cpu(u.init_c->max_transfer_size); if (tmp < dev->hard_mtu) { if (tmp <= net->hard_header_len) { dev_err(&intf->dev, "dev can't take %u byte packets (max %u)\n", dev->hard_mtu, tmp); retval = -EINVAL; goto halt_fail_and_release; } dev_warn(&intf->dev, "dev can't take %u byte packets (max %u), " "adjusting MTU to %u\n", dev->hard_mtu, tmp, tmp - net->hard_header_len); dev->hard_mtu = tmp; net->mtu = dev->hard_mtu - net->hard_header_len; } /* REVISIT: peripheral "alignment" request is ignored ... */ dev_dbg(&intf->dev, "hard mtu %u (%u from dev), rx buflen %zu, align %d\n", dev->hard_mtu, tmp, dev->rx_urb_size, 1 << le32_to_cpu(u.init_c->packet_alignment)); /* module has some device initialization code needs to be done right * after RNDIS_INIT */ if (dev->driver_info->early_init && dev->driver_info->early_init(dev) != 0) goto halt_fail_and_release; /* Check physical medium */ phym = NULL; reply_len = sizeof *phym; retval = rndis_query(dev, intf, u.buf, RNDIS_OID_GEN_PHYSICAL_MEDIUM, reply_len, (void **)&phym, &reply_len); if (retval != 0 || !phym) { /* OID is optional so don't fail here. */ phym_unspec = cpu_to_le32(RNDIS_PHYSICAL_MEDIUM_UNSPECIFIED); phym = &phym_unspec; } if ((flags & FLAG_RNDIS_PHYM_WIRELESS) && le32_to_cpup(phym) != RNDIS_PHYSICAL_MEDIUM_WIRELESS_LAN) { netif_dbg(dev, probe, dev->net, "driver requires wireless physical medium, but device is not\n"); retval = -ENODEV; goto halt_fail_and_release; } if ((flags & FLAG_RNDIS_PHYM_NOT_WIRELESS) && le32_to_cpup(phym) == RNDIS_PHYSICAL_MEDIUM_WIRELESS_LAN) { netif_dbg(dev, probe, dev->net, "driver requires non-wireless physical medium, but device is wireless.\n"); retval = -ENODEV; goto halt_fail_and_release; } /* Get designated host ethernet address */ reply_len = ETH_ALEN; retval = rndis_query(dev, intf, u.buf, RNDIS_OID_802_3_PERMANENT_ADDRESS, 48, (void **) &bp, &reply_len); if (unlikely(retval< 0)) { dev_err(&intf->dev, "rndis get ethaddr, %d\n", retval); goto halt_fail_and_release; } eth_hw_addr_set(net, bp); /* set a nonzero filter to enable data transfers */ memset(u.set, 0, sizeof *u.set); u.set->msg_type = cpu_to_le32(RNDIS_MSG_SET); u.set->msg_len = cpu_to_le32(4 + sizeof *u.set); u.set->oid = cpu_to_le32(RNDIS_OID_GEN_CURRENT_PACKET_FILTER); u.set->len = cpu_to_le32(4); u.set->offset = cpu_to_le32((sizeof *u.set) - 8); *(__le32 *)(u.buf + sizeof *u.set) = cpu_to_le32(RNDIS_DEFAULT_FILTER); retval = rndis_command(dev, u.header, CONTROL_BUFFER_SIZE); if (unlikely(retval < 0)) { dev_err(&intf->dev, "rndis set packet filter, %d\n", retval); goto halt_fail_and_release; } retval = 0; kfree(u.buf); return retval; halt_fail_and_release: memset(u.halt, 0, sizeof *u.halt); u.halt->msg_type = cpu_to_le32(RNDIS_MSG_HALT); u.halt->msg_len = cpu_to_le32(sizeof *u.halt); (void) rndis_command(dev, (void *)u.halt, CONTROL_BUFFER_SIZE); fail_and_release: usb_set_intfdata(info->data, NULL); usb_driver_release_interface(driver_of(intf), info->data); info->data = NULL; fail: kfree(u.buf); return retval; } EXPORT_SYMBOL_GPL(generic_rndis_bind); static int rndis_bind(struct usbnet *dev, struct usb_interface *intf) { return generic_rndis_bind(dev, intf, FLAG_RNDIS_PHYM_NOT_WIRELESS); } static int zte_rndis_bind(struct usbnet *dev, struct usb_interface *intf) { int status = rndis_bind(dev, intf); if (!status && (dev->net->dev_addr[0] & 0x02)) eth_hw_addr_random(dev->net); return status; } void rndis_unbind(struct usbnet *dev, struct usb_interface *intf) { struct rndis_halt *halt; /* try to clear any rndis state/activity (no i/o from stack!) */ halt = kzalloc(CONTROL_BUFFER_SIZE, GFP_KERNEL); if (halt) { halt->msg_type = cpu_to_le32(RNDIS_MSG_HALT); halt->msg_len = cpu_to_le32(sizeof *halt); (void) rndis_command(dev, (void *)halt, CONTROL_BUFFER_SIZE); kfree(halt); } usbnet_cdc_unbind(dev, intf); } EXPORT_SYMBOL_GPL(rndis_unbind); /* * DATA -- host must not write zlps */ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { bool dst_mac_fixup; /* This check is no longer done by usbnet */ if (skb->len < dev->net->hard_header_len) return 0; dst_mac_fixup = !!(dev->driver_info->data & RNDIS_DRIVER_DATA_DST_MAC_FIXUP); /* peripheral may have batched packets to us... */ while (likely(skb->len)) { struct rndis_data_hdr *hdr = (void *)skb->data; struct sk_buff *skb2; u32 msg_type, msg_len, data_offset, data_len; msg_type = le32_to_cpu(hdr->msg_type); msg_len = le32_to_cpu(hdr->msg_len); data_offset = le32_to_cpu(hdr->data_offset); data_len = le32_to_cpu(hdr->data_len); /* don't choke if we see oob, per-packet data, etc */ if (unlikely(msg_type != RNDIS_MSG_PACKET || skb->len < msg_len || (data_offset + data_len + 8) > msg_len)) { dev->net->stats.rx_frame_errors++; netdev_dbg(dev->net, "bad rndis message %d/%d/%d/%d, len %d\n", le32_to_cpu(hdr->msg_type), msg_len, data_offset, data_len, skb->len); return 0; } skb_pull(skb, 8 + data_offset); /* at most one packet left? */ if (likely((data_len - skb->len) <= sizeof *hdr)) { skb_trim(skb, data_len); break; } /* try to return all the packets in the batch */ skb2 = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb2)) break; skb_pull(skb, msg_len - sizeof *hdr); skb_trim(skb2, data_len); if (unlikely(dst_mac_fixup)) usbnet_cdc_zte_rx_fixup(dev, skb2); usbnet_skb_return(dev, skb2); } /* caller will usbnet_skb_return the remaining packet */ if (unlikely(dst_mac_fixup)) usbnet_cdc_zte_rx_fixup(dev, skb); return 1; } EXPORT_SYMBOL_GPL(rndis_rx_fixup); struct sk_buff * rndis_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { struct rndis_data_hdr *hdr; struct sk_buff *skb2; unsigned len = skb->len; if (likely(!skb_cloned(skb))) { int room = skb_headroom(skb); /* enough head room as-is? */ if (unlikely((sizeof *hdr) <= room)) goto fill; /* enough room, but needs to be readjusted? */ room += skb_tailroom(skb); if (likely((sizeof *hdr) <= room)) { skb->data = memmove(skb->head + sizeof *hdr, skb->data, len); skb_set_tail_pointer(skb, len); goto fill; } } /* create a new skb, with the correct size (and tailpad) */ skb2 = skb_copy_expand(skb, sizeof *hdr, 1, flags); dev_kfree_skb_any(skb); if (unlikely(!skb2)) return skb2; skb = skb2; /* fill out the RNDIS header. we won't bother trying to batch * packets; Linux minimizes wasted bandwidth through tx queues. */ fill: hdr = __skb_push(skb, sizeof *hdr); memset(hdr, 0, sizeof *hdr); hdr->msg_type = cpu_to_le32(RNDIS_MSG_PACKET); hdr->msg_len = cpu_to_le32(skb->len); hdr->data_offset = cpu_to_le32(sizeof(*hdr) - 8); hdr->data_len = cpu_to_le32(len); /* FIXME make the last packet always be short ... */ return skb; } EXPORT_SYMBOL_GPL(rndis_tx_fixup); static const struct driver_info rndis_info = { .description = "RNDIS device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT, .bind = rndis_bind, .unbind = rndis_unbind, .status = rndis_status, .rx_fixup = rndis_rx_fixup, .tx_fixup = rndis_tx_fixup, }; static const struct driver_info rndis_poll_status_info = { .description = "RNDIS device (poll status before control)", .flags = FLAG_ETHER | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT, .data = RNDIS_DRIVER_DATA_POLL_STATUS, .bind = rndis_bind, .unbind = rndis_unbind, .status = rndis_status, .rx_fixup = rndis_rx_fixup, .tx_fixup = rndis_tx_fixup, }; static const struct driver_info zte_rndis_info = { .description = "ZTE RNDIS device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT, .data = RNDIS_DRIVER_DATA_DST_MAC_FIXUP, .bind = zte_rndis_bind, .unbind = rndis_unbind, .status = rndis_status, .rx_fixup = rndis_rx_fixup, .tx_fixup = rndis_tx_fixup, }; /*-------------------------------------------------------------------------*/ static const struct usb_device_id products [] = { { /* 2Wire HomePortal 1000SW */ USB_DEVICE_AND_INTERFACE_INFO(0x1630, 0x0042, USB_CLASS_COMM, 2 /* ACM */, 0x0ff), .driver_info = (unsigned long) &rndis_poll_status_info, }, { /* Hytera Communications DMR radios' "Radio to PC Network" */ USB_VENDOR_AND_INTERFACE_INFO(0x238b, USB_CLASS_COMM, 2 /* ACM */, 0x0ff), .driver_info = (unsigned long)&rndis_info, }, { /* ZTE WWAN modules */ USB_VENDOR_AND_INTERFACE_INFO(0x19d2, USB_CLASS_WIRELESS_CONTROLLER, 1, 3), .driver_info = (unsigned long)&zte_rndis_info, }, { /* ZTE WWAN modules, ACM flavour */ USB_VENDOR_AND_INTERFACE_INFO(0x19d2, USB_CLASS_COMM, 2 /* ACM */, 0x0ff), .driver_info = (unsigned long)&zte_rndis_info, }, { /* RNDIS is MSFT's un-official variant of CDC ACM */ USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff), .driver_info = (unsigned long) &rndis_info, }, { /* "ActiveSync" is an undocumented variant of RNDIS, used in WM5 */ USB_INTERFACE_INFO(USB_CLASS_MISC, 1, 1), .driver_info = (unsigned long) &rndis_poll_status_info, }, { /* RNDIS for tethering */ USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3), .driver_info = (unsigned long) &rndis_info, }, { /* Novatel Verizon USB730L */ USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1), .driver_info = (unsigned long) &rndis_info, }, { }, // END }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver rndis_driver = { .name = "rndis_host", .id_table = products, .probe = usbnet_probe, .disconnect = usbnet_disconnect, .suspend = usbnet_suspend, .resume = usbnet_resume, .disable_hub_initiated_lpm = 1, }; module_usb_driver(rndis_driver); MODULE_AUTHOR("David Brownell"); MODULE_DESCRIPTION("USB Host side RNDIS driver"); MODULE_LICENSE("GPL"); |
| 29 10 8048 4 8048 5631 7415 7823 4200 463 457 462 446 7803 6118 7821 200 2026 6016 6130 7840 6126 9 9 50 35 45 4 8033 8022 47 4 4 7815 11 8 761 7515 7512 674 7386 5042 3099 5108 5488 3968 4 1353 384 3635 5199 4220 3835 5206 458 428 123 463 7463 5896 6264 7480 7816 7397 7802 6299 4826 7165 828 6658 76 7818 12 96 125 138 80 202 7532 750 7746 737 7821 172 1147 787 660 1404 1439 44 1157 332 357 1154 7817 13 7820 7470 739 7823 5219 4699 7822 7813 7841 7739 5206 7108 5832 7850 1441 1443 1448 1448 9 9 9 8 9 9 9 9 22 1439 1443 5006 69 3921 7827 5019 3926 3923 1 1408 245 245 7819 7807 7821 7824 741 7468 7847 7813 14 4 7815 5 9 7819 25 22 22 7481 7848 7819 5 5 5 5 2212 1105 1448 1441 4 1445 4 1439 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->private = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->private; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { if (move_front) list_move(&chunk->list, &pcpu_chunk_lists[slot]); else list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); /* leave isolated chunks in-place */ if (chunk->isolated) return; if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, start, end); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } /* * If the allocation is not atomic, some blocks may not be * populated with pages, while we account it here. The number * of pages will be added back with pcpu_chunk_populated() * when populating pages. */ if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int start, end; start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); start = find_next_zero_bit(chunk->populated, end, start); if (start >= end) return true; end = find_next_bit(chunk->populated, end, start + 1); *next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * This is an optimization to prevent scanning by assuming if the * allocation cannot fit in the global hint, there is memory pressure * and creating a new chunk would happen soon. */ if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; region_size = ALIGN(start_offset + map_size, PAGE_SIZE); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); #ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ chunk->obj_exts = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef NEED_PCPUOBJ_EXT if (need_pcpuobj_ext()) { chunk->obj_exts = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct pcpuobj_ext), gfp); if (!chunk->obj_exts) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef NEED_PCPUOBJ_EXT objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef NEED_PCPUOBJ_EXT pcpu_mem_free(chunk->obj_exts); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = current_obj_cgroup(); if (!objcg) return true; if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; *objcgp = objcg; return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg); chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, pcpu_obj_full_size(size)); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (unlikely(!chunk->obj_exts)) return; objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup; if (!objcg) return; chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -pcpu_obj_full_size(size)); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MEM_ALLOC_PROFILING static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, current->alloc_tag, size); } } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); } #else static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) { pcpu_reintegrate_chunk(chunk); goto area_found; } } } spin_unlock_irqrestore(&pcpu_lock, flags); if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_end, rs, re; rs = PFN_DOWN(off); page_end = PFN_UP(off + size); for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, chunk->base_addr, off, ptr, pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); pcpu_alloc_tag_alloc_hook(chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); if (!is_atomic) dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } EXPORT_SYMBOL_GPL(pcpu_alloc_noprof); /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; if (!empty_only || chunk->nr_empty_pop_pages == 0) list_move(&chunk->list, &to_free); } if (list_empty(&to_free)) return; spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } spin_lock_irq(&pcpu_lock); } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; pcpu_chunk_populated(chunk, rs, rs + nr); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ spin_unlock_irq(&pcpu_lock); chunk = pcpu_create_chunk(gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (chunk) { pcpu_chunk_relocate(chunk, -1); goto retry_pop; } } } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { struct pcpu_chunk *chunk; struct pcpu_block_md *block; int freed_page_start, freed_page_end; int i, end; bool reintegrate; lockdep_assert_held(&pcpu_lock); /* * Once a chunk is isolated to the to_depopulate list, the chunk is no * longer discoverable to allocations whom may populate pages. The only * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ while ((chunk = list_first_entry_or_null( &pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list))) { WARN_ON(chunk->immutable); /* * Scan chunk's pages in the reverse order to keep populated * pages close to the beginning of the chunk. */ freed_page_start = chunk->nr_pages; freed_page_end = 0; reintegrate = false; for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { /* no more work to do */ if (chunk->nr_empty_pop_pages == 0) break; /* reintegrate chunk to prevent atomic alloc failures */ if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; } /* * If the page is empty and populated, start or * extend the (i, end) range. If i == 0, decrease * i and perform the depopulation to cover the last * (first) page in the chunk. */ block = chunk->md_blocks + i; if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && test_bit(i, chunk->populated)) { if (end == -1) end = i; if (i > 0) continue; i--; } /* depopulate if there is an active range */ if (end == -1) continue; spin_unlock_irq(&pcpu_lock); pcpu_depopulate_chunk(chunk, i + 1, end + 1); cond_resched(); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, i + 1, end + 1); freed_page_start = min(freed_page_start, i + 1); freed_page_end = max(freed_page_end, end + 1); /* reset the range and continue */ end = -1; } /* batch tlb flush per chunk to amortize cost */ if (freed_page_start < freed_page_end) { spin_unlock_irq(&pcpu_lock); pcpu_post_unmap_tlb_flush(chunk, freed_page_start, freed_page_end); cond_resched(); spin_lock_irq(&pcpu_lock); } if (reintegrate || chunk->free_bytes == pcpu_unit_size) pcpu_reintegrate_chunk(chunk); else list_move_tail(&chunk->list, &pcpu_chunk_lists[pcpu_sidelined_slot]); } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us * to grow other chunks. This then gives pcpu_reclaim_populated() time * to move fully free chunks to the active list to be freed if * appropriate. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); pcpu_balance_free(false); pcpu_reclaim_populated(); pcpu_balance_populated(); pcpu_balance_free(true); spin_unlock_irq(&pcpu_lock); mutex_unlock(&pcpu_alloc_mutex); } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_alloc_tag_free_hook(chunk, off, size); pcpu_memcg_free_hook(chunk, off, size); /* * If there are more than one fully free chunks, wake up grim reaper. * If the chunk is isolated, it may be in the process of being * reclaimed. Let reclaim manage cleaning up of that chunk. */ if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free(ai, ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; unsigned long tmp_addr; size_t alloc_size; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The slots after the active slots are: * sidelined_slot - isolated, depopulated chunks * free_slot - fully free chunks * to_depopulate_slot - isolated, chunks to depopulate */ pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc_or_panic(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk: * This chunk is broken up into 3 parts: * < static | [reserved] | dynamic > * - static - there is no backing chunk because these allocations can * never be freed. * - reserved (pcpu_reserved_chunk) - exists primarily to serve * allocations from module load. * - dynamic (pcpu_first_chunk) - serves the dynamic part of the first * chunk. */ tmp_addr = (unsigned long)base_addr + static_size; if (ai->reserved_size) pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, ai->reserved_size); tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size); pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; static struct cpumask mask __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); cpumask_clear(&mask); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; cpumask_copy(&mask, cpu_possible_mask); /* group cpus according to their proximity */ for (group = 0; !cpumask_empty(&mask); group++) { /* pop the group's first cpu */ cpu = cpumask_first(&mask); group_map[cpu] = group; group_cnt[group]++; cpumask_clear_cpu(cpu, &mask); for_each_cpu(tcpu, &mask) { if (!cpu_distance_fn || (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE && cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) { group_map[tcpu] = group; group_cnt[group]++; cpumask_clear_cpu(tcpu, &mask); } } } nr_groups = group; /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA int node = NUMA_NO_NODE; void *ptr; if (cpu_to_nd_fn) node = cpu_to_nd_fn(cpu); if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", cpu, size, (u64)__pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", cpu, size, node, (u64)__pa(ptr)); } return ptr; #else return memblock_alloc_from(size, align, goal); #endif } static void __init pcpu_fc_free(void *ptr, size_t size) { memblock_free(ptr, size); } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <asm/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE PAGE_SIZE #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE PAGE_SIZE #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE PAGE_SIZE #endif void __init __weak pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); pgd_populate(&init_mm, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); p4d_populate(&init_mm, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE); pud_populate(&init_mm, pud, pmd); } pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) { pte_t *new; new = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE); pmd_populate_kernel(&init_mm, pmd, new); } return; } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc_or_panic(pages_size, SMP_CACHE_BYTES); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 7 7 7 7 7 4 3 4 4 4 4 4 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 | /* * llc_s_ev.c - Defines SAP component events * * The followed event functions are SAP component events which are described * in 802.2 LLC protocol standard document. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/socket.h> #include <net/sock.h> #include <net/llc_if.h> #include <net/llc_s_ev.h> #include <net/llc_pdu.h> int llc_sap_ev_activation_req(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); return ev->type == LLC_SAP_EV_TYPE_SIMPLE && ev->prim_type == LLC_SAP_EV_ACTIVATION_REQ ? 0 : 1; } int llc_sap_ev_rx_ui(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return ev->type == LLC_SAP_EV_TYPE_PDU && LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_UI ? 0 : 1; } int llc_sap_ev_unitdata_req(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); return ev->type == LLC_SAP_EV_TYPE_PRIM && ev->prim == LLC_DATAUNIT_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_sap_ev_xid_req(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); return ev->type == LLC_SAP_EV_TYPE_PRIM && ev->prim == LLC_XID_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_sap_ev_rx_xid_c(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return ev->type == LLC_SAP_EV_TYPE_PDU && LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID ? 0 : 1; } int llc_sap_ev_rx_xid_r(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return ev->type == LLC_SAP_EV_TYPE_PDU && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_1_PDU_CMD_XID ? 0 : 1; } int llc_sap_ev_test_req(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); return ev->type == LLC_SAP_EV_TYPE_PRIM && ev->prim == LLC_TEST_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_sap_ev_rx_test_c(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return ev->type == LLC_SAP_EV_TYPE_PDU && LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST ? 0 : 1; } int llc_sap_ev_rx_test_r(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return ev->type == LLC_SAP_EV_TYPE_PDU && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_1_PDU_CMD_TEST ? 0 : 1; } int llc_sap_ev_deactivation_req(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); return ev->type == LLC_SAP_EV_TYPE_SIMPLE && ev->prim_type == LLC_SAP_EV_DEACTIVATION_REQ ? 0 : 1; } |
| 34 31 164 175 2 7 4 2 2 5 8 1 3 1 7 32 4 11 2 14 9 1 4 4 4 6 10 15 5 4 9 21 7 6 13 36 36 10 11 21 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _INET_ECN_H_ #define _INET_ECN_H_ #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #include <net/inet_sock.h> #include <net/dsfield.h> #include <net/checksum.h> enum { INET_ECN_NOT_ECT = 0, INET_ECN_ECT_1 = 1, INET_ECN_ECT_0 = 2, INET_ECN_CE = 3, INET_ECN_MASK = 3, }; extern int sysctl_tunnel_ecn_log; static inline int INET_ECN_is_ce(__u8 dsfield) { return (dsfield & INET_ECN_MASK) == INET_ECN_CE; } static inline int INET_ECN_is_not_ect(__u8 dsfield) { return (dsfield & INET_ECN_MASK) == INET_ECN_NOT_ECT; } static inline int INET_ECN_is_capable(__u8 dsfield) { return dsfield & INET_ECN_ECT_0; } /* * RFC 3168 9.1.1 * The full-functionality option for ECN encapsulation is to copy the * ECN codepoint of the inside header to the outside header on * encapsulation if the inside header is not-ECT or ECT, and to set the * ECN codepoint of the outside header to ECT(0) if the ECN codepoint of * the inside header is CE. */ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) { outer &= ~INET_ECN_MASK; outer |= !INET_ECN_is_ce(inner) ? (inner & INET_ECN_MASK) : INET_ECN_ECT_0; return outer; } static inline void INET_ECN_xmit(struct sock *sk) { inet_sk(sk)->tos |= INET_ECN_ECT_0; if (inet6_sk(sk) != NULL) inet6_sk(sk)->tclass |= INET_ECN_ECT_0; } static inline void INET_ECN_dontxmit(struct sock *sk) { inet_sk(sk)->tos &= ~INET_ECN_MASK; if (inet6_sk(sk) != NULL) inet6_sk(sk)->tclass &= ~INET_ECN_MASK; } #define IP6_ECN_flow_init(label) do { \ (label) &= ~htonl(INET_ECN_MASK << 20); \ } while (0) #define IP6_ECN_flow_xmit(sk, label) do { \ if (INET_ECN_is_capable(inet6_sk(sk)->tclass)) \ (label) |= htonl(INET_ECN_ECT_0 << 20); \ } while (0) static inline int IP_ECN_set_ce(struct iphdr *iph) { u32 ecn = (iph->tos + 1) & INET_ECN_MASK; __be16 check_add; /* * After the last operation we have (in binary): * INET_ECN_NOT_ECT => 01 * INET_ECN_ECT_1 => 10 * INET_ECN_ECT_0 => 11 * INET_ECN_CE => 00 */ if (!(ecn & 2)) return !ecn; /* * The following gives us: * INET_ECN_ECT_1 => check += htons(0xFFFD) * INET_ECN_ECT_0 => check += htons(0xFFFE) */ check_add = (__force __be16)((__force u16)htons(0xFFFB) + (__force u16)htons(ecn)); iph->check = csum16_add(iph->check, check_add); iph->tos |= INET_ECN_CE; return 1; } static inline int IP_ECN_set_ect1(struct iphdr *iph) { if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; iph->check = csum16_add(iph->check, htons(0x1)); iph->tos ^= INET_ECN_MASK; return 1; } static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; } static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner) { dscp &= ~INET_ECN_MASK; ipv4_change_dsfield(inner, INET_ECN_MASK, dscp); } struct ipv6hdr; /* Note: * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE, * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE * In IPv6 case, no checksum compensates the change in IPv6 header, * so we have to update skb->csum. */ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) { __be32 from, to; if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph))) return 0; from = *(__be32 *)iph; to = from | htonl(INET_ECN_CE << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), (__force __wsum)to); return 1; } static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) { __be32 from, to; if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; from = *(__be32 *)iph; to = from ^ htonl(INET_ECN_MASK << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), (__force __wsum)to); return 1; } static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; ipv6_change_dsfield(inner, INET_ECN_MASK, dscp); } static inline int INET_ECN_set_ce(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) return IP_ECN_set_ce(ip_hdr(skb)); break; case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) return IP6_ECN_set_ce(skb, ipv6_hdr(skb)); break; } return 0; } static inline int skb_get_dsfield(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) break; return ipv4_get_dsfield(ip_hdr(skb)); case cpu_to_be16(ETH_P_IPV6): if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) break; return ipv6_get_dsfield(ipv6_hdr(skb)); } return -1; } static inline int INET_ECN_set_ect1(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) return IP_ECN_set_ect1(ip_hdr(skb)); break; case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); break; } return 0; } /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant * tunnel egress MUST set the outgoing ECN field to the codepoint at the * intersection of the appropriate arriving inner header (row) and outer * header (column) in Figure 4 * * +---------+------------------------------------------------+ * |Arriving | Arriving Outer Header | * | Inner +---------+------------+------------+------------+ * | Header | Not-ECT | ECT(0) | ECT(1) | CE | * +---------+---------+------------+------------+------------+ * | Not-ECT | Not-ECT |Not-ECT(!!!)|Not-ECT(!!!)| <drop>(!!!)| * | ECT(0) | ECT(0) | ECT(0) | ECT(1) | CE | * | ECT(1) | ECT(1) | ECT(1) (!) | ECT(1) | CE | * | CE | CE | CE | CE(!!!)| CE | * +---------+---------+------------+------------+------------+ * * Figure 4: New IP in IP Decapsulation Behaviour * * returns 0 on success * 1 if something is broken and should be logged (!!! above) * 2 if packet should be dropped */ static inline int __INET_ECN_decapsulate(__u8 outer, __u8 inner, bool *set_ce) { if (INET_ECN_is_not_ect(inner)) { switch (outer & INET_ECN_MASK) { case INET_ECN_NOT_ECT: return 0; case INET_ECN_ECT_0: case INET_ECN_ECT_1: return 1; case INET_ECN_CE: return 2; } } *set_ce = INET_ECN_is_ce(outer); return 0; } static inline int INET_ECN_decapsulate(struct sk_buff *skb, __u8 outer, __u8 inner) { bool set_ce = false; int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); if (!rc) { if (set_ce) INET_ECN_set_ce(skb); else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) INET_ECN_set_ect1(skb); } return rc; } static inline int IP_ECN_decapsulate(const struct iphdr *oiph, struct sk_buff *skb) { __u8 inner; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; break; case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); break; default: return 0; } return INET_ECN_decapsulate(skb, oiph->tos, inner); } static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, struct sk_buff *skb) { __u8 inner; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; break; case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); break; default: return 0; } return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); } #endif |
| 5 5 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ChaCha and XChaCha stream ciphers, including ChaCha20 (RFC7539) * * Copyright (C) 2015 Martin Willi * Copyright (C) 2018 Google LLC */ #include <linux/unaligned.h> #include <crypto/algapi.h> #include <crypto/internal/chacha.h> #include <crypto/internal/skcipher.h> #include <linux/module.h> static int chacha_stream_xor(struct skcipher_request *req, const struct chacha_ctx *ctx, const u8 *iv) { struct skcipher_walk walk; u32 state[16]; int err; err = skcipher_walk_virt(&walk, req, false); chacha_init_generic(state, ctx->key, iv); while (walk.nbytes > 0) { unsigned int nbytes = walk.nbytes; if (nbytes < walk.total) nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE); chacha_crypt_generic(state, walk.dst.virt.addr, walk.src.virt.addr, nbytes, ctx->nrounds); err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; } static int crypto_chacha_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); return chacha_stream_xor(req, ctx, req->iv); } static int crypto_xchacha_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); struct chacha_ctx subctx; u32 state[16]; u8 real_iv[16]; /* Compute the subkey given the original key and first 128 nonce bits */ chacha_init_generic(state, ctx->key, req->iv); hchacha_block_generic(state, subctx.key, ctx->nrounds); subctx.nrounds = ctx->nrounds; /* Build the real IV */ memcpy(&real_iv[0], req->iv + 24, 8); /* stream position */ memcpy(&real_iv[8], req->iv + 16, 8); /* remaining 64 nonce bits */ /* Generate the stream and XOR it with the data */ return chacha_stream_xor(req, &subctx, real_iv); } static struct skcipher_alg algs[] = { { .base.cra_name = "chacha20", .base.cra_driver_name = "chacha20-generic", .base.cra_priority = 100, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CHACHA_KEY_SIZE, .max_keysize = CHACHA_KEY_SIZE, .ivsize = CHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .setkey = chacha20_setkey, .encrypt = crypto_chacha_crypt, .decrypt = crypto_chacha_crypt, }, { .base.cra_name = "xchacha20", .base.cra_driver_name = "xchacha20-generic", .base.cra_priority = 100, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CHACHA_KEY_SIZE, .max_keysize = CHACHA_KEY_SIZE, .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .setkey = chacha20_setkey, .encrypt = crypto_xchacha_crypt, .decrypt = crypto_xchacha_crypt, }, { .base.cra_name = "xchacha12", .base.cra_driver_name = "xchacha12-generic", .base.cra_priority = 100, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CHACHA_KEY_SIZE, .max_keysize = CHACHA_KEY_SIZE, .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .setkey = chacha12_setkey, .encrypt = crypto_xchacha_crypt, .decrypt = crypto_xchacha_crypt, } }; static int __init chacha_generic_mod_init(void) { return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); } static void __exit chacha_generic_mod_fini(void) { crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } subsys_initcall(chacha_generic_mod_init); module_exit(chacha_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (generic)"); MODULE_ALIAS_CRYPTO("chacha20"); MODULE_ALIAS_CRYPTO("chacha20-generic"); MODULE_ALIAS_CRYPTO("xchacha20"); MODULE_ALIAS_CRYPTO("xchacha20-generic"); MODULE_ALIAS_CRYPTO("xchacha12"); MODULE_ALIAS_CRYPTO("xchacha12-generic"); |
| 26 25 1 1 26 26 26 | 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 | /* * Copyright (c) 2004-2011 Atheros Communications Inc. * Copyright (c) 2011-2012 Qualcomm Atheros, Inc. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above * copyright notice and this permission notice appear in all copies. * * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ #include "core.h" #include "hif-ops.h" #include "target.h" #include "debug.h" int ath6kl_bmi_done(struct ath6kl *ar) { int ret; u32 cid = BMI_DONE; if (ar->bmi.done_sent) { ath6kl_dbg(ATH6KL_DBG_BMI, "bmi done skipped\n"); return 0; } ar->bmi.done_sent = true; ret = ath6kl_hif_bmi_write(ar, (u8 *)&cid, sizeof(cid)); if (ret) { ath6kl_err("Unable to send bmi done: %d\n", ret); return ret; } return 0; } int ath6kl_bmi_get_target_info(struct ath6kl *ar, struct ath6kl_bmi_target_info *targ_info) { int ret; u32 cid = BMI_GET_TARGET_INFO; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } ret = ath6kl_hif_bmi_write(ar, (u8 *)&cid, sizeof(cid)); if (ret) { ath6kl_err("Unable to send get target info: %d\n", ret); return ret; } if (ar->hif_type == ATH6KL_HIF_TYPE_USB) { ret = ath6kl_hif_bmi_read(ar, (u8 *)targ_info, sizeof(*targ_info)); } else { ret = ath6kl_hif_bmi_read(ar, (u8 *)&targ_info->version, sizeof(targ_info->version)); } if (ret) { ath6kl_err("Unable to recv target info: %d\n", ret); return ret; } if (le32_to_cpu(targ_info->version) == TARGET_VERSION_SENTINAL) { /* Determine how many bytes are in the Target's targ_info */ ret = ath6kl_hif_bmi_read(ar, (u8 *)&targ_info->byte_count, sizeof(targ_info->byte_count)); if (ret) { ath6kl_err("unable to read target info byte count: %d\n", ret); return ret; } /* * The target's targ_info doesn't match the host's targ_info. * We need to do some backwards compatibility to make this work. */ if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) { WARN_ON(1); return -EINVAL; } /* Read the remainder of the targ_info */ ret = ath6kl_hif_bmi_read(ar, ((u8 *)targ_info) + sizeof(targ_info->byte_count), sizeof(*targ_info) - sizeof(targ_info->byte_count)); if (ret) { ath6kl_err("Unable to read target info (%d bytes): %d\n", targ_info->byte_count, ret); return ret; } } ath6kl_dbg(ATH6KL_DBG_BMI, "target info (ver: 0x%x type: 0x%x)\n", targ_info->version, targ_info->type); return 0; } int ath6kl_bmi_read(struct ath6kl *ar, u32 addr, u8 *buf, u32 len) { u32 cid = BMI_READ_MEMORY; int ret; u32 offset; u32 len_remain, rx_len; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = ar->bmi.max_data_size + sizeof(cid) + sizeof(addr) + sizeof(len); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi read memory: device: addr: 0x%x, len: %d\n", addr, len); len_remain = len; while (len_remain) { rx_len = (len_remain < ar->bmi.max_data_size) ? len_remain : ar->bmi.max_data_size; offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); memcpy(&(ar->bmi.cmd_buf[offset]), &rx_len, sizeof(rx_len)); offset += sizeof(len); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, rx_len); if (ret) { ath6kl_err("Unable to read from the device: %d\n", ret); return ret; } memcpy(&buf[len - len_remain], ar->bmi.cmd_buf, rx_len); len_remain -= rx_len; addr += rx_len; } return 0; } int ath6kl_bmi_write(struct ath6kl *ar, u32 addr, u8 *buf, u32 len) { u32 cid = BMI_WRITE_MEMORY; int ret; u32 offset; u32 len_remain, tx_len; const u32 header = sizeof(cid) + sizeof(addr) + sizeof(len); u8 aligned_buf[400]; u8 *src; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } if ((ar->bmi.max_data_size + header) > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } if (WARN_ON(ar->bmi.max_data_size > sizeof(aligned_buf))) return -E2BIG; memset(ar->bmi.cmd_buf, 0, ar->bmi.max_data_size + header); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi write memory: addr: 0x%x, len: %d\n", addr, len); len_remain = len; while (len_remain) { src = &buf[len - len_remain]; if (len_remain < (ar->bmi.max_data_size - header)) { if (len_remain & 3) { /* align it with 4 bytes */ len_remain = len_remain + (4 - (len_remain & 3)); memcpy(aligned_buf, src, len_remain); src = aligned_buf; } tx_len = len_remain; } else { tx_len = (ar->bmi.max_data_size - header); } offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); memcpy(&(ar->bmi.cmd_buf[offset]), &tx_len, sizeof(tx_len)); offset += sizeof(tx_len); memcpy(&(ar->bmi.cmd_buf[offset]), src, tx_len); offset += tx_len; ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } len_remain -= tx_len; addr += tx_len; } return 0; } int ath6kl_bmi_execute(struct ath6kl *ar, u32 addr, u32 *param) { u32 cid = BMI_EXECUTE; int ret; u32 offset; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = sizeof(cid) + sizeof(addr) + sizeof(*param); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi execute: addr: 0x%x, param: %d)\n", addr, *param); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); memcpy(&(ar->bmi.cmd_buf[offset]), param, sizeof(*param)); offset += sizeof(*param); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, sizeof(*param)); if (ret) { ath6kl_err("Unable to read from the device: %d\n", ret); return ret; } memcpy(param, ar->bmi.cmd_buf, sizeof(*param)); return 0; } int ath6kl_bmi_set_app_start(struct ath6kl *ar, u32 addr) { u32 cid = BMI_SET_APP_START; int ret; u32 offset; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = sizeof(cid) + sizeof(addr); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi set app start: addr: 0x%x\n", addr); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } return 0; } int ath6kl_bmi_reg_read(struct ath6kl *ar, u32 addr, u32 *param) { u32 cid = BMI_READ_SOC_REGISTER; int ret; u32 offset; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = sizeof(cid) + sizeof(addr); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi read SOC reg: addr: 0x%x\n", addr); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, sizeof(*param)); if (ret) { ath6kl_err("Unable to read from the device: %d\n", ret); return ret; } memcpy(param, ar->bmi.cmd_buf, sizeof(*param)); return 0; } int ath6kl_bmi_reg_write(struct ath6kl *ar, u32 addr, u32 param) { u32 cid = BMI_WRITE_SOC_REGISTER; int ret; u32 offset; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = sizeof(cid) + sizeof(addr) + sizeof(param); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi write SOC reg: addr: 0x%x, param: %d\n", addr, param); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); memcpy(&(ar->bmi.cmd_buf[offset]), ¶m, sizeof(param)); offset += sizeof(param); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } return 0; } int ath6kl_bmi_lz_data(struct ath6kl *ar, u8 *buf, u32 len) { u32 cid = BMI_LZ_DATA; int ret; u32 offset; u32 len_remain, tx_len; const u32 header = sizeof(cid) + sizeof(len); u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = ar->bmi.max_data_size + header; if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi send LZ data: len: %d)\n", len); len_remain = len; while (len_remain) { tx_len = (len_remain < (ar->bmi.max_data_size - header)) ? len_remain : (ar->bmi.max_data_size - header); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &tx_len, sizeof(tx_len)); offset += sizeof(tx_len); memcpy(&(ar->bmi.cmd_buf[offset]), &buf[len - len_remain], tx_len); offset += tx_len; ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to write to the device: %d\n", ret); return ret; } len_remain -= tx_len; } return 0; } int ath6kl_bmi_lz_stream_start(struct ath6kl *ar, u32 addr) { u32 cid = BMI_LZ_STREAM_START; int ret; u32 offset; u16 size; if (ar->bmi.done_sent) { ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid); return -EACCES; } size = sizeof(cid) + sizeof(addr); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; } memset(ar->bmi.cmd_buf, 0, size); ath6kl_dbg(ATH6KL_DBG_BMI, "bmi LZ stream start: addr: 0x%x)\n", addr); offset = 0; memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid)); offset += sizeof(cid); memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr)); offset += sizeof(addr); ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset); if (ret) { ath6kl_err("Unable to start LZ stream to the device: %d\n", ret); return ret; } return 0; } int ath6kl_bmi_fast_download(struct ath6kl *ar, u32 addr, u8 *buf, u32 len) { int ret; u32 last_word = 0; u32 last_word_offset = len & ~0x3; u32 unaligned_bytes = len & 0x3; ret = ath6kl_bmi_lz_stream_start(ar, addr); if (ret) return ret; if (unaligned_bytes) { /* copy the last word into a zero padded buffer */ memcpy(&last_word, &buf[last_word_offset], unaligned_bytes); } ret = ath6kl_bmi_lz_data(ar, buf, last_word_offset); if (ret) return ret; if (unaligned_bytes) ret = ath6kl_bmi_lz_data(ar, (u8 *)&last_word, 4); if (!ret) { /* Close compressed stream and open a new (fake) one. * This serves mainly to flush Target caches. */ ret = ath6kl_bmi_lz_stream_start(ar, 0x00); } return ret; } void ath6kl_bmi_reset(struct ath6kl *ar) { ar->bmi.done_sent = false; } int ath6kl_bmi_init(struct ath6kl *ar) { if (WARN_ON(ar->bmi.max_data_size == 0)) return -EINVAL; /* cmd + addr + len + data_size */ ar->bmi.max_cmd_size = ar->bmi.max_data_size + (sizeof(u32) * 3); ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_KERNEL); if (!ar->bmi.cmd_buf) return -ENOMEM; return 0; } void ath6kl_bmi_cleanup(struct ath6kl *ar) { kfree(ar->bmi.cmd_buf); ar->bmi.cmd_buf = NULL; } |
| 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * phonet.c -- USB CDC Phonet host driver * * Copyright (C) 2008-2009 Nokia Corporation. All rights reserved. * * Author: Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/usb.h> #include <linux/usb/cdc.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/if_phonet.h> #include <linux/phonet.h> #define PN_MEDIA_USB 0x1B static const unsigned rxq_size = 17; struct usbpn_dev { struct net_device *dev; struct usb_interface *intf, *data_intf; struct usb_device *usb; unsigned int tx_pipe, rx_pipe; u8 active_setting; u8 disconnected; unsigned tx_queue; spinlock_t tx_lock; spinlock_t rx_lock; struct sk_buff *rx_skb; struct urb *urbs[]; }; static void tx_complete(struct urb *req); static void rx_complete(struct urb *req); /* * Network device callbacks */ static netdev_tx_t usbpn_xmit(struct sk_buff *skb, struct net_device *dev) { struct usbpn_dev *pnd = netdev_priv(dev); struct urb *req = NULL; unsigned long flags; int err; if (skb->protocol != htons(ETH_P_PHONET)) goto drop; req = usb_alloc_urb(0, GFP_ATOMIC); if (!req) goto drop; usb_fill_bulk_urb(req, pnd->usb, pnd->tx_pipe, skb->data, skb->len, tx_complete, skb); req->transfer_flags = URB_ZERO_PACKET; err = usb_submit_urb(req, GFP_ATOMIC); if (err) { usb_free_urb(req); goto drop; } spin_lock_irqsave(&pnd->tx_lock, flags); pnd->tx_queue++; if (pnd->tx_queue >= dev->tx_queue_len) netif_stop_queue(dev); spin_unlock_irqrestore(&pnd->tx_lock, flags); return NETDEV_TX_OK; drop: dev_kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static void tx_complete(struct urb *req) { struct sk_buff *skb = req->context; struct net_device *dev = skb->dev; struct usbpn_dev *pnd = netdev_priv(dev); int status = req->status; unsigned long flags; switch (status) { case 0: dev->stats.tx_bytes += skb->len; break; case -ENOENT: case -ECONNRESET: case -ESHUTDOWN: dev->stats.tx_aborted_errors++; fallthrough; default: dev->stats.tx_errors++; dev_dbg(&dev->dev, "TX error (%d)\n", status); } dev->stats.tx_packets++; spin_lock_irqsave(&pnd->tx_lock, flags); pnd->tx_queue--; netif_wake_queue(dev); spin_unlock_irqrestore(&pnd->tx_lock, flags); dev_kfree_skb_any(skb); usb_free_urb(req); } static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags) { struct net_device *dev = pnd->dev; struct page *page; int err; page = __dev_alloc_page(gfp_flags | __GFP_NOMEMALLOC); if (!page) return -ENOMEM; usb_fill_bulk_urb(req, pnd->usb, pnd->rx_pipe, page_address(page), PAGE_SIZE, rx_complete, dev); req->transfer_flags = 0; err = usb_submit_urb(req, gfp_flags); if (unlikely(err)) { dev_dbg(&dev->dev, "RX submit error (%d)\n", err); put_page(page); } return err; } static void rx_complete(struct urb *req) { struct net_device *dev = req->context; struct usbpn_dev *pnd = netdev_priv(dev); struct page *page = virt_to_page(req->transfer_buffer); struct sk_buff *skb; unsigned long flags; int status = req->status; switch (status) { case 0: spin_lock_irqsave(&pnd->rx_lock, flags); skb = pnd->rx_skb; if (!skb) { skb = pnd->rx_skb = netdev_alloc_skb(dev, 12); if (likely(skb)) { /* Can't use pskb_pull() on page in IRQ */ skb_put_data(skb, page_address(page), 1); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, 1, req->actual_length, PAGE_SIZE); page = NULL; } } else { skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, 0, req->actual_length, PAGE_SIZE); page = NULL; } if (req->actual_length < PAGE_SIZE) pnd->rx_skb = NULL; /* Last fragment */ else skb = NULL; spin_unlock_irqrestore(&pnd->rx_lock, flags); if (skb) { skb->protocol = htons(ETH_P_PHONET); skb_reset_mac_header(skb); __skb_pull(skb, 1); skb->dev = dev; dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; netif_rx(skb); } goto resubmit; case -ENOENT: case -ECONNRESET: case -ESHUTDOWN: req = NULL; break; case -EOVERFLOW: dev->stats.rx_over_errors++; dev_dbg(&dev->dev, "RX overflow\n"); break; case -EILSEQ: dev->stats.rx_crc_errors++; break; } dev->stats.rx_errors++; resubmit: if (page) put_page(page); if (req) rx_submit(pnd, req, GFP_ATOMIC); } static int usbpn_close(struct net_device *dev); static int usbpn_open(struct net_device *dev) { struct usbpn_dev *pnd = netdev_priv(dev); int err; unsigned i; unsigned num = pnd->data_intf->cur_altsetting->desc.bInterfaceNumber; err = usb_set_interface(pnd->usb, num, pnd->active_setting); if (err) return err; for (i = 0; i < rxq_size; i++) { struct urb *req = usb_alloc_urb(0, GFP_KERNEL); if (!req || rx_submit(pnd, req, GFP_KERNEL)) { usb_free_urb(req); usbpn_close(dev); return -ENOMEM; } pnd->urbs[i] = req; } netif_wake_queue(dev); return 0; } static int usbpn_close(struct net_device *dev) { struct usbpn_dev *pnd = netdev_priv(dev); unsigned i; unsigned num = pnd->data_intf->cur_altsetting->desc.bInterfaceNumber; netif_stop_queue(dev); for (i = 0; i < rxq_size; i++) { struct urb *req = pnd->urbs[i]; if (!req) continue; usb_kill_urb(req); usb_free_urb(req); pnd->urbs[i] = NULL; } return usb_set_interface(pnd->usb, num, !pnd->active_setting); } static int usbpn_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct if_phonet_req *req = (struct if_phonet_req *)ifr; switch (cmd) { case SIOCPNGAUTOCONF: req->ifr_phonet_autoconf.device = PN_DEV_PC; return 0; } return -ENOIOCTLCMD; } static const struct net_device_ops usbpn_ops = { .ndo_open = usbpn_open, .ndo_stop = usbpn_close, .ndo_start_xmit = usbpn_xmit, .ndo_siocdevprivate = usbpn_siocdevprivate, }; static void usbpn_setup(struct net_device *dev) { const u8 addr = PN_MEDIA_USB; dev->features = 0; dev->netdev_ops = &usbpn_ops; dev->header_ops = &phonet_header_ops; dev->type = ARPHRD_PHONET; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = PHONET_MAX_MTU; dev->min_mtu = PHONET_MIN_MTU; dev->max_mtu = PHONET_MAX_MTU; dev->hard_header_len = 1; dev->addr_len = 1; dev_addr_set(dev, &addr); dev->tx_queue_len = 3; dev->needs_free_netdev = true; } /* * USB driver callbacks */ static const struct usb_device_id usbpn_ids[] = { { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS | USB_DEVICE_ID_MATCH_INT_SUBCLASS, .idVendor = 0x0421, /* Nokia */ .bInterfaceClass = USB_CLASS_COMM, .bInterfaceSubClass = 0xFE, }, { }, }; MODULE_DEVICE_TABLE(usb, usbpn_ids); static struct usb_driver usbpn_driver; static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) { static const char ifname[] = "usbpn%d"; const struct usb_cdc_union_desc *union_header = NULL; const struct usb_host_interface *data_desc; struct usb_interface *data_intf; struct usb_device *usbdev = interface_to_usbdev(intf); struct net_device *dev; struct usbpn_dev *pnd; u8 *data; int phonet = 0; int len, err; struct usb_cdc_parsed_header hdr; data = intf->altsetting->extra; len = intf->altsetting->extralen; cdc_parse_cdc_header(&hdr, intf, data, len); union_header = hdr.usb_cdc_union_desc; phonet = hdr.phonet_magic_present; if (!union_header || !phonet) return -EINVAL; data_intf = usb_ifnum_to_if(usbdev, union_header->bSlaveInterface0); if (data_intf == NULL) return -ENODEV; /* Data interface has one inactive and one active setting */ if (data_intf->num_altsetting != 2) return -EINVAL; if (data_intf->altsetting[0].desc.bNumEndpoints == 0 && data_intf->altsetting[1].desc.bNumEndpoints == 2) data_desc = data_intf->altsetting + 1; else if (data_intf->altsetting[0].desc.bNumEndpoints == 2 && data_intf->altsetting[1].desc.bNumEndpoints == 0) data_desc = data_intf->altsetting; else return -EINVAL; dev = alloc_netdev(struct_size(pnd, urbs, rxq_size), ifname, NET_NAME_UNKNOWN, usbpn_setup); if (!dev) return -ENOMEM; pnd = netdev_priv(dev); SET_NETDEV_DEV(dev, &intf->dev); pnd->dev = dev; pnd->usb = usbdev; pnd->intf = intf; pnd->data_intf = data_intf; spin_lock_init(&pnd->tx_lock); spin_lock_init(&pnd->rx_lock); /* Endpoints */ if (usb_pipein(data_desc->endpoint[0].desc.bEndpointAddress)) { pnd->rx_pipe = usb_rcvbulkpipe(usbdev, data_desc->endpoint[0].desc.bEndpointAddress); pnd->tx_pipe = usb_sndbulkpipe(usbdev, data_desc->endpoint[1].desc.bEndpointAddress); } else { pnd->rx_pipe = usb_rcvbulkpipe(usbdev, data_desc->endpoint[1].desc.bEndpointAddress); pnd->tx_pipe = usb_sndbulkpipe(usbdev, data_desc->endpoint[0].desc.bEndpointAddress); } pnd->active_setting = data_desc - data_intf->altsetting; err = usb_driver_claim_interface(&usbpn_driver, data_intf, pnd); if (err) goto out; /* Force inactive mode until the network device is brought UP */ usb_set_interface(usbdev, union_header->bSlaveInterface0, !pnd->active_setting); usb_set_intfdata(intf, pnd); err = register_netdev(dev); if (err) { /* Set disconnected flag so that disconnect() returns early. */ pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, data_intf); goto out; } dev_dbg(&dev->dev, "USB CDC Phonet device found\n"); return 0; out: usb_set_intfdata(intf, NULL); free_netdev(dev); return err; } static void usbpn_disconnect(struct usb_interface *intf) { struct usbpn_dev *pnd = usb_get_intfdata(intf); if (pnd->disconnected) return; pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, (pnd->intf == intf) ? pnd->data_intf : pnd->intf); unregister_netdev(pnd->dev); } static struct usb_driver usbpn_driver = { .name = "cdc_phonet", .probe = usbpn_probe, .disconnect = usbpn_disconnect, .id_table = usbpn_ids, .disable_hub_initiated_lpm = 1, }; module_usb_driver(usbpn_driver); MODULE_AUTHOR("Remi Denis-Courmont"); MODULE_DESCRIPTION("USB CDC Phonet host interface"); MODULE_LICENSE("GPL"); |
| 2 2 2 2 2 2 1009 1010 549 460 463 462 462 32 463 | 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 #include <linux/compat.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/smp.h> #include <linux/sem.h> #include <linux/msg.h> #include <linux/shm.h> #include <linux/stat.h> #include <linux/mman.h> #include <linux/file.h> #include <linux/utsname.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/uaccess.h> #include <linux/elf.h> #include <linux/hugetlb.h> #include <asm/elf.h> #include <asm/ia32.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. */ static unsigned long get_align_mask(struct file *filp) { if (filp && is_file_hugepages(filp)) return huge_page_mask_align(filp); /* handle 32- and 64-bit case with a single conditional */ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) return 0; if (!(current->flags & PF_RANDOMIZE)) return 0; return va_align.mask; } /* * To avoid aliasing in the I$ on AMD F15h, the bits defined by the * va_align.bits, [12:upper_bit), are set to a random value instead of * zeroing them. This random value is computed once per boot. This form * of ASLR is known as "per-boot ASLR". * * To achieve this, the random value is added to the info.align_offset * value before calling vm_unmapped_area() or ORed directly to the * address. */ static unsigned long get_align_bits(void) { return va_align.bits & get_align_mask(NULL); } static int __init control_va_addr_alignment(char *str) { /* guard against enabling this on other CPU families */ if (va_align.flags < 0) return 1; if (*str == 0) return 1; if (!strcmp(str, "32")) va_align.flags = ALIGN_VA_32; else if (!strcmp(str, "64")) va_align.flags = ALIGN_VA_64; else if (!strcmp(str, "off")) va_align.flags = 0; else if (!strcmp(str, "on")) va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; else pr_warn("invalid option value: 'align_va_addr=%s'\n", str); return 1; } __setup("align_va_addr=", control_va_addr_alignment); SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, off) { if (off & ~PAGE_MASK) return -EINVAL; return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } static void find_start_end(unsigned long addr, unsigned long flags, unsigned long *begin, unsigned long *end) { if (!in_32bit_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit it to that. This means we need to move the unmapped base down for this case. This can give conflicts with the heap, but we assume that glibc malloc knows how to fall back to mmap. Give it 1GB of playground for now. -AK */ *begin = 0x40000000; *end = 0x80000000; if (current->flags & PF_RANDOMIZE) { *begin = randomize_page(*begin, 0x02000000); } return; } *begin = get_mmap_base(1); if (in_32bit_syscall()) *end = task_size_32bit(); else *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) { if (vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct vm_unmapped_area_info info = {}; unsigned long begin, end; if (flags & MAP_FIXED) return addr; find_start_end(addr, flags, &begin, &end); if (len > end) return -ENOMEM; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } info.length = len; info.low_limit = begin; info.high_limit = end; if (!(filp && is_file_hugepages(filp))) { info.align_offset = pgoff << PAGE_SHIFT; info.start_gap = stack_guard_placement(vm_flags); } if (filp) { info.align_mask = get_align_mask(filp); info.align_offset += get_align_bits(); } return vm_unmapped_area(&info); } unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; /* No address checking. See comment at mmap_address_hint_valid() */ if (flags & MAP_FIXED) return addr; /* for MAP_32BIT mappings we force the legacy mmap base */ if (!in_32bit_syscall() && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ if (addr) { addr &= PAGE_MASK; if (!mmap_address_hint_valid(addr, len)) goto get_unmapped_area; vma = find_vma(mm, addr); if (!vma || addr + len <= vm_start_gap(vma)) return addr; } get_unmapped_area: info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; if (!in_32bit_syscall() && (flags & MAP_ABOVE4G)) info.low_limit = SZ_4G; else info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); if (!(filp && is_file_hugepages(filp))) { info.start_gap = stack_guard_placement(vm_flags); info.align_offset = pgoff << PAGE_SHIFT; } /* * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area * in the full address space. * * !in_32bit_syscall() check to avoid high addresses for x32 * (and make it no op on native i386). */ if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; if (filp) { info.align_mask = get_align_mask(filp); info.align_offset += get_align_bits(); } addr = vm_unmapped_area(&info); if (!(addr & ~PAGE_MASK)) return addr; VM_BUG_ON(addr != -ENOMEM); bottomup: /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags, 0); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match AH parameters. */ /* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/types.h> #include <net/checksum.h> #include <net/ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_ah.h> MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: IPv6 IPsec-AH match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); /* 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_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct ip_auth_hdr _ah; const struct ip_auth_hdr *ah; const struct ip6t_ah *ahinfo = par->matchinfo; unsigned int ptr = 0; unsigned int hdrlen = 0; int err; err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL); if (err < 0) { if (err != -ENOENT) par->hotdrop = true; return false; } ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); if (ah == NULL) { par->hotdrop = true; return false; } hdrlen = ipv6_authlen(ah); pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); pr_debug("RES %04X ", ah->reserved); pr_debug("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi)); pr_debug("IPv6 AH spi %02X ", spi_match(ahinfo->spis[0], ahinfo->spis[1], ntohl(ah->spi), !!(ahinfo->invflags & IP6T_AH_INV_SPI))); pr_debug("len %02X %04X %02X ", ahinfo->hdrlen, hdrlen, (!ahinfo->hdrlen || (ahinfo->hdrlen == hdrlen) ^ !!(ahinfo->invflags & IP6T_AH_INV_LEN))); pr_debug("res %02X %04X %02X\n", ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); return spi_match(ahinfo->spis[0], ahinfo->spis[1], ntohl(ah->spi), !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && (!ahinfo->hdrlen || (ahinfo->hdrlen == hdrlen) ^ !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && !(ahinfo->hdrres && ah->reserved); } static int ah_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_ah *ahinfo = par->matchinfo; if (ahinfo->invflags & ~IP6T_AH_INV_MASK) { pr_debug("unknown flags %X\n", ahinfo->invflags); return -EINVAL; } return 0; } static struct xt_match ah_mt6_reg __read_mostly = { .name = "ah", .family = NFPROTO_IPV6, .match = ah_mt6, .matchsize = sizeof(struct ip6t_ah), .checkentry = ah_mt6_check, .me = THIS_MODULE, }; static int __init ah_mt6_init(void) { return xt_register_match(&ah_mt6_reg); } static void __exit ah_mt6_exit(void) { xt_unregister_match(&ah_mt6_reg); } module_init(ah_mt6_init); module_exit(ah_mt6_exit); |
| 1382 230 21 3983 12 868 61 70 1555 81 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 10 10 10 10 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2005 PathScale, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * 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 AUTHORS OR COPYRIGHT HOLDERS * 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. */ #include <linux/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/file.h> #include <linux/cdev.h> #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <rdma/ib.h> #include <rdma/uverbs_std_types.h> #include <rdma/rdma_netlink.h> #include "uverbs.h" #include "core_priv.h" #include "rdma_core.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace verbs access"); MODULE_LICENSE("Dual BSD/GPL"); enum { IB_UVERBS_MAJOR = 231, IB_UVERBS_BASE_MINOR = 192, IB_UVERBS_MAX_DEVICES = RDMA_MAX_PORTS, IB_UVERBS_NUM_FIXED_MINOR = 32, IB_UVERBS_NUM_DYNAMIC_MINOR = IB_UVERBS_MAX_DEVICES - IB_UVERBS_NUM_FIXED_MINOR, }; #define IB_UVERBS_BASE_DEV MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR) static dev_t dynamic_uverbs_dev; static DEFINE_IDA(uverbs_ida); static int ib_uverbs_add_one(struct ib_device *device); static void ib_uverbs_remove_one(struct ib_device *device, void *client_data); static struct ib_client uverbs_client; static char *uverbs_devnode(const struct device *dev, umode_t *mode) { if (mode) *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } static const struct class uverbs_class = { .name = "infiniband_verbs", .devnode = uverbs_devnode, }; /* * Must be called with the ufile->device->disassociate_srcu held, and the lock * must be held until use of the ucontext is finished. */ struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile) { /* * We do not hold the hw_destroy_rwsem lock for this flow, instead * srcu is used. It does not matter if someone races this with * get_context, we get NULL or valid ucontext. */ struct ib_ucontext *ucontext = smp_load_acquire(&ufile->ucontext); if (!srcu_dereference(ufile->device->ib_dev, &ufile->device->disassociate_srcu)) return ERR_PTR(-EIO); if (!ucontext) return ERR_PTR(-EINVAL); return ucontext; } EXPORT_SYMBOL(ib_uverbs_get_ucontext_file); int uverbs_dealloc_mw(struct ib_mw *mw) { struct ib_pd *pd = mw->pd; int ret; ret = mw->device->ops.dealloc_mw(mw); if (ret) return ret; atomic_dec(&pd->usecnt); kfree(mw); return ret; } static void ib_uverbs_release_dev(struct device *device) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); uverbs_destroy_api(dev->uapi); cleanup_srcu_struct(&dev->disassociate_srcu); mutex_destroy(&dev->lists_mutex); mutex_destroy(&dev->xrcd_tree_mutex); kfree(dev); } void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj) { struct ib_uverbs_event *evt, *tmp; if (ev_file) { spin_lock_irq(&ev_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->comp_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&ev_file->ev_queue.lock); uverbs_uobject_put(&ev_file->uobj); } ib_uverbs_release_uevent(&uobj->uevent); } void ib_uverbs_release_uevent(struct ib_uevent_object *uobj) { struct ib_uverbs_async_event_file *async_file = uobj->event_file; struct ib_uverbs_event *evt, *tmp; if (!async_file) return; spin_lock_irq(&async_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&async_file->ev_queue.lock); uverbs_uobject_put(&async_file->uobj); } void ib_uverbs_detach_umcast(struct ib_qp *qp, struct ib_uqp_object *uobj) { struct ib_uverbs_mcast_entry *mcast, *tmp; list_for_each_entry_safe(mcast, tmp, &uobj->mcast_list, list) { ib_detach_mcast(qp, &mcast->gid, mcast->lid); list_del(&mcast->list); kfree(mcast); } } static void ib_uverbs_comp_dev(struct ib_uverbs_device *dev) { complete(&dev->comp); } void ib_uverbs_release_file(struct kref *ref) { struct ib_uverbs_file *file = container_of(ref, struct ib_uverbs_file, ref); struct ib_device *ib_dev; int srcu_key; release_ufile_idr_uobject(file); srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ib_dev = srcu_dereference(file->device->ib_dev, &file->device->disassociate_srcu); if (ib_dev && !ib_dev->ops.disassociate_ucontext) module_put(ib_dev->ops.owner); srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); if (file->default_async_file) uverbs_uobject_put(&file->default_async_file->uobj); put_device(&file->device->dev); if (file->disassociate_page) __free_pages(file->disassociate_page, 0); mutex_destroy(&file->disassociation_lock); mutex_destroy(&file->umap_lock); mutex_destroy(&file->ucontext_lock); kfree(file); } static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, struct file *filp, char __user *buf, size_t count, loff_t *pos, size_t eventsz) { struct ib_uverbs_event *event; int ret = 0; spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { if (ev_queue->is_closed) { spin_unlock_irq(&ev_queue->lock); return -EIO; } spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(ev_queue->poll_wait, (!list_empty(&ev_queue->event_list) || ev_queue->is_closed))) return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); if (eventsz > count) { ret = -EINVAL; event = NULL; } else { list_del(ev_queue->event_list.next); if (event->counter) { ++(*event->counter); list_del(&event->obj_list); } } spin_unlock_irq(&ev_queue->lock); if (event) { if (copy_to_user(buf, event, eventsz)) ret = -EFAULT; else ret = eventsz; } kfree(event); return ret; } static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_async_event_desc)); } static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_comp_event_desc)); } static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue, struct file *filp, struct poll_table_struct *wait) { __poll_t pollflags = 0; poll_wait(filp, &ev_queue->poll_wait, wait); spin_lock_irq(&ev_queue->lock); if (!list_empty(&ev_queue->event_list)) pollflags = EPOLLIN | EPOLLRDNORM; else if (ev_queue->is_closed) pollflags = EPOLLERR; spin_unlock_irq(&ev_queue->lock); return pollflags; } static __poll_t ib_uverbs_async_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_poll(&file->ev_queue, filp, wait); } static __poll_t ib_uverbs_comp_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_poll(&comp_ev_file->ev_queue, filp, wait); } static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_async_event_file *file = filp->private_data; return fasync_helper(fd, filp, on, &file->ev_queue.async_queue); } static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue); } const struct file_operations uverbs_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_comp_event_read, .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, }; const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) { struct ib_uverbs_event_queue *ev_queue = cq_context; struct ib_ucq_object *uobj; struct ib_uverbs_event *entry; unsigned long flags; if (!ev_queue) return; spin_lock_irqsave(&ev_queue->lock, flags); if (ev_queue->is_closed) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } uobj = cq->uobject; entry->desc.comp.cq_handle = cq->uobject->uevent.uobject.user_handle; entry->counter = &uobj->comp_events_reported; list_add_tail(&entry->list, &ev_queue->event_list); list_add_tail(&entry->obj_list, &uobj->comp_list); spin_unlock_irqrestore(&ev_queue->lock, flags); wake_up_interruptible(&ev_queue->poll_wait); kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, __u64 element, __u64 event, struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; if (!async_file) return; spin_lock_irqsave(&async_file->ev_queue.lock, flags); if (async_file->ev_queue.is_closed) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry->desc.async.element = element; entry->desc.async.event_type = event; entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &async_file->ev_queue.event_list); if (obj_list) list_add_tail(&entry->obj_list, obj_list); spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); wake_up_interruptible(&async_file->ev_queue.poll_wait); kill_fasync(&async_file->ev_queue.async_queue, SIGIO, POLL_IN); } static void uverbs_uobj_event(struct ib_uevent_object *eobj, struct ib_event *event) { ib_uverbs_async_handler(eobj->event_file, eobj->uobject.user_handle, event->event, &eobj->event_list, &eobj->events_reported); } void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.cq->uobject->uevent, event); } void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr) { /* for XRC target qp's, check that qp is live */ if (!event->element.qp->uobject) return; uverbs_uobj_event(&event->element.qp->uobject->uevent, event); } void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.wq->uobject->uevent, event); } void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.srq->uobject->uevent, event); } static void ib_uverbs_event_handler(struct ib_event_handler *handler, struct ib_event *event) { ib_uverbs_async_handler( container_of(handler, struct ib_uverbs_async_event_file, event_handler), event->element.port_num, event->event, NULL, NULL); } void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue) { spin_lock_init(&ev_queue->lock); INIT_LIST_HEAD(&ev_queue->event_list); init_waitqueue_head(&ev_queue->poll_wait); ev_queue->is_closed = 0; ev_queue->async_queue = NULL; } void ib_uverbs_init_async_event_file( struct ib_uverbs_async_event_file *async_file) { struct ib_uverbs_file *uverbs_file = async_file->uobj.ufile; struct ib_device *ib_dev = async_file->uobj.context->device; ib_uverbs_init_event_queue(&async_file->ev_queue); /* The first async_event_file becomes the default one for the file. */ mutex_lock(&uverbs_file->ucontext_lock); if (!uverbs_file->default_async_file) { /* Pairs with the put in ib_uverbs_release_file */ uverbs_uobject_get(&async_file->uobj); smp_store_release(&uverbs_file->default_async_file, async_file); } mutex_unlock(&uverbs_file->ucontext_lock); INIT_IB_EVENT_HANDLER(&async_file->event_handler, ib_dev, ib_uverbs_event_handler); ib_register_event_handler(&async_file->event_handler); } static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, struct ib_uverbs_ex_cmd_hdr *ex_hdr, size_t count, const struct uverbs_api_write_method *method_elm) { if (method_elm->is_ex) { count -= sizeof(*hdr) + sizeof(*ex_hdr); if ((hdr->in_words + ex_hdr->provider_in_words) * 8 != count) return -EINVAL; if (hdr->in_words * 8 < method_elm->req_size) return -ENOSPC; if (ex_hdr->cmd_hdr_reserved) return -EINVAL; if (ex_hdr->response) { if (!hdr->out_words && !ex_hdr->provider_out_words) return -EINVAL; if (hdr->out_words * 8 < method_elm->resp_size) return -ENOSPC; if (!access_ok(u64_to_user_ptr(ex_hdr->response), (hdr->out_words + ex_hdr->provider_out_words) * 8)) return -EFAULT; } else { if (hdr->out_words || ex_hdr->provider_out_words) return -EINVAL; } return 0; } /* not extended command */ if (hdr->in_words * 4 != count) return -EINVAL; if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't * check the size so they allowed this. Now that the size is * checked provide a compatibility work around to not break * those userspaces. */ if (hdr->command == IB_USER_VERBS_CMD_DESTROY_CQ && count == 16) { hdr->in_words = 6; return 0; } return -ENOSPC; } if (hdr->out_words * 4 < method_elm->resp_size) return -ENOSPC; return 0; } static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; const struct uverbs_api_write_method *method_elm; struct uverbs_api *uapi = file->device->uapi; struct ib_uverbs_ex_cmd_hdr ex_hdr; struct ib_uverbs_cmd_hdr hdr; struct uverbs_attr_bundle bundle; int srcu_key; ssize_t ret; if (!ib_safe_file_access(filp)) { pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", task_tgid_vnr(current), current->comm); return -EACCES; } if (count < sizeof(hdr)) return -EINVAL; if (copy_from_user(&hdr, buf, sizeof(hdr))) return -EFAULT; method_elm = uapi_get_method(uapi, hdr.command); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (method_elm->is_ex) { if (count < (sizeof(hdr) + sizeof(ex_hdr))) return -EINVAL; if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr))) return -EFAULT; } ret = verify_hdr(&hdr, &ex_hdr, count, method_elm); if (ret) return ret; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); buf += sizeof(hdr); memset(bundle.attr_present, 0, sizeof(bundle.attr_present)); bundle.ufile = file; bundle.context = NULL; /* only valid if bundle has uobject */ bundle.uobject = NULL; if (!method_elm->is_ex) { size_t in_len = hdr.in_words * 4 - sizeof(hdr); size_t out_len = hdr.out_words * 4; u64 response = 0; if (method_elm->has_udata) { bundle.driver_udata.inlen = in_len - method_elm->req_size; in_len = method_elm->req_size; if (bundle.driver_udata.inlen) bundle.driver_udata.inbuf = buf + in_len; else bundle.driver_udata.inbuf = NULL; } else { memset(&bundle.driver_udata, 0, sizeof(bundle.driver_udata)); } if (method_elm->has_resp) { /* * The macros check that if has_resp is set * then the command request structure starts * with a '__aligned u64 response' member. */ ret = get_user(response, (const u64 __user *)buf); if (ret) goto out_unlock; if (method_elm->has_udata) { bundle.driver_udata.outlen = out_len - method_elm->resp_size; out_len = method_elm->resp_size; if (bundle.driver_udata.outlen) bundle.driver_udata.outbuf = u64_to_user_ptr(response + out_len); else bundle.driver_udata.outbuf = NULL; } } else { bundle.driver_udata.outlen = 0; bundle.driver_udata.outbuf = NULL; } ib_uverbs_init_udata_buf_or_null( &bundle.ucore, buf, u64_to_user_ptr(response), in_len, out_len); } else { buf += sizeof(ex_hdr); ib_uverbs_init_udata_buf_or_null(&bundle.ucore, buf, u64_to_user_ptr(ex_hdr.response), hdr.in_words * 8, hdr.out_words * 8); ib_uverbs_init_udata_buf_or_null( &bundle.driver_udata, buf + bundle.ucore.inlen, u64_to_user_ptr(ex_hdr.response) + bundle.ucore.outlen, ex_hdr.provider_in_words * 8, ex_hdr.provider_out_words * 8); } ret = method_elm->handler(&bundle); if (bundle.uobject) uverbs_finalize_object(bundle.uobject, UVERBS_ACCESS_NEW, true, !ret, &bundle); out_unlock: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return (ret) ? : count; } static const struct vm_operations_struct rdma_umap_ops; static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma) { struct ib_uverbs_file *file = filp->private_data; struct ib_ucontext *ucontext; int ret = 0; int srcu_key; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ucontext = ib_uverbs_get_ucontext_file(file); if (IS_ERR(ucontext)) { ret = PTR_ERR(ucontext); goto out; } mutex_lock(&file->disassociation_lock); vma->vm_ops = &rdma_umap_ops; ret = ucontext->device->ops.mmap(ucontext, vma); mutex_unlock(&file->disassociation_lock); out: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return ret; } /* * The VMA has been dup'd, initialize the vm_private_data with a new tracking * struct */ static void rdma_umap_open(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *opriv = vma->vm_private_data; struct rdma_umap_priv *priv; if (!opriv) return; /* We are racing with disassociation */ if (!down_read_trylock(&ufile->hw_destroy_rwsem)) goto out_zap; mutex_lock(&ufile->disassociation_lock); /* * Disassociation already completed, the VMA should already be zapped. */ if (!ufile->ucontext) goto out_unlock; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) goto out_unlock; rdma_umap_priv_init(priv, vma, opriv->entry); mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); return; out_unlock: mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); out_zap: /* * We can't allow the VMA to be created with the actual IO pages, that * would break our API contract, and it can't be stopped at this * point, so zap it. */ vma->vm_private_data = NULL; zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); } static void rdma_umap_close(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *priv = vma->vm_private_data; if (!priv) return; /* * The vma holds a reference on the struct file that created it, which * in turn means that the ib_uverbs_file is guaranteed to exist at * this point. */ mutex_lock(&ufile->umap_lock); if (priv->entry) rdma_user_mmap_entry_put(priv->entry); list_del(&priv->list); mutex_unlock(&ufile->umap_lock); kfree(priv); } /* * Once the zap_vma_ptes has been called touches to the VMA will come here and * we return a dummy writable zero page for all the pfns. */ static vm_fault_t rdma_umap_fault(struct vm_fault *vmf) { struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data; struct rdma_umap_priv *priv = vmf->vma->vm_private_data; vm_fault_t ret = 0; if (!priv) return VM_FAULT_SIGBUS; /* Read only pages can just use the system zero page. */ if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) { vmf->page = ZERO_PAGE(vmf->address); get_page(vmf->page); return 0; } mutex_lock(&ufile->umap_lock); if (!ufile->disassociate_page) ufile->disassociate_page = alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0); if (ufile->disassociate_page) { /* * This VMA is forced to always be shared so this doesn't have * to worry about COW. */ vmf->page = ufile->disassociate_page; get_page(vmf->page); } else { ret = VM_FAULT_SIGBUS; } mutex_unlock(&ufile->umap_lock); return ret; } static const struct vm_operations_struct rdma_umap_ops = { .open = rdma_umap_open, .close = rdma_umap_close, .fault = rdma_umap_fault, }; void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) { struct rdma_umap_priv *priv, *next_priv; mutex_lock(&ufile->disassociation_lock); while (1) { struct mm_struct *mm = NULL; /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); while (!list_empty(&ufile->umaps)) { int ret; priv = list_first_entry(&ufile->umaps, struct rdma_umap_priv, list); mm = priv->vma->vm_mm; ret = mmget_not_zero(mm); if (!ret) { list_del_init(&priv->list); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } mm = NULL; continue; } break; } mutex_unlock(&ufile->umap_lock); if (!mm) { mutex_unlock(&ufile->disassociation_lock); return; } /* * The umap_lock is nested under mmap_lock since it used within * the vma_ops callbacks, so we have to clean the list one mm * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ mmap_read_lock(mm); mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { struct vm_area_struct *vma = priv->vma; if (vma->vm_mm != mm) continue; list_del_init(&priv->list); zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } } mutex_unlock(&ufile->umap_lock); mmap_read_unlock(mm); mmput(mm); } mutex_unlock(&ufile->disassociation_lock); } /** * rdma_user_mmap_disassociate() - Revoke mmaps for a device * @device: device to revoke * * This function should be called by drivers that need to disable mmaps for the * device, for instance because it is going to be reset. */ void rdma_user_mmap_disassociate(struct ib_device *device) { struct ib_uverbs_device *uverbs_dev = ib_get_client_data(device, &uverbs_client); struct ib_uverbs_file *ufile; mutex_lock(&uverbs_dev->lists_mutex); list_for_each_entry(ufile, &uverbs_dev->uverbs_file_list, list) { if (ufile->ucontext) uverbs_user_mmap_disassociate(ufile); } mutex_unlock(&uverbs_dev->lists_mutex); } EXPORT_SYMBOL(rdma_user_mmap_disassociate); /* * ib_uverbs_open() does not need the BKL: * * - the ib_uverbs_device structures are properly reference counted and * everything else is purely local to the file being created, so * races against other open calls are not a problem; * - there is no ioctl method to race against; * - the open method will either immediately run -ENXIO, or all * required initialization will be done. */ static int ib_uverbs_open(struct inode *inode, struct file *filp) { struct ib_uverbs_device *dev; struct ib_uverbs_file *file; struct ib_device *ib_dev; int ret; int module_dependent; int srcu_key; dev = container_of(inode->i_cdev, struct ib_uverbs_device, cdev); if (!refcount_inc_not_zero(&dev->refcount)) return -ENXIO; get_device(&dev->dev); srcu_key = srcu_read_lock(&dev->disassociate_srcu); mutex_lock(&dev->lists_mutex); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (!ib_dev) { ret = -EIO; goto err; } if (!rdma_dev_access_netns(ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto err; } /* In case IB device supports disassociate ucontext, there is no hard * dependency between uverbs device and its low level device. */ module_dependent = !(ib_dev->ops.disassociate_ucontext); if (module_dependent) { if (!try_module_get(ib_dev->ops.owner)) { ret = -ENODEV; goto err; } } file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) { ret = -ENOMEM; if (module_dependent) goto err_module; goto err; } file->device = dev; kref_init(&file->ref); mutex_init(&file->ucontext_lock); spin_lock_init(&file->uobjects_lock); INIT_LIST_HEAD(&file->uobjects); init_rwsem(&file->hw_destroy_rwsem); mutex_init(&file->umap_lock); INIT_LIST_HEAD(&file->umaps); mutex_init(&file->disassociation_lock); filp->private_data = file; list_add_tail(&file->list, &dev->uverbs_file_list); mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); setup_ufile_idr_uobject(file); return stream_open(inode, filp); err_module: module_put(ib_dev->ops.owner); err: mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&dev->refcount)) ib_uverbs_comp_dev(dev); put_device(&dev->dev); return ret; } static int ib_uverbs_close(struct inode *inode, struct file *filp) { struct ib_uverbs_file *file = filp->private_data; uverbs_destroy_ufile_hw(file, RDMA_REMOVE_CLOSE); mutex_lock(&file->device->lists_mutex); list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); kref_put(&file->ref, ib_uverbs_release_file); return 0; } static const struct file_operations uverbs_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static const struct file_operations uverbs_mmap_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static int ib_uverbs_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_uverbs_device *uverbs_dev = client_data; int ret; if (res->port != -1) return -EINVAL; res->abi = ibdev->ops.uverbs_abi_ver; res->cdev = &uverbs_dev->dev; /* * To support DRIVER_ID binding in userspace some of the driver need * upgrading to expose their PCI dependent revision information * through get_context instead of relying on modalias matching. When * the drivers are fixed they can drop this flag. */ if (!ibdev->ops.uverbs_no_driver_id_binding) { ret = nla_put_u32(res->nl_msg, RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID, ibdev->ops.driver_id); if (ret) return ret; } return 0; } static struct ib_client uverbs_client = { .name = "uverbs", .no_kverbs_req = true, .add = ib_uverbs_add_one, .remove = ib_uverbs_remove_one, .get_nl_info = ib_uverbs_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("uverbs"); static ssize_t ibdev_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%s\n", dev_name(&ib_dev->dev)); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(ibdev); static ssize_t abi_version_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%u\n", ib_dev->ops.uverbs_abi_ver); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(abi_version); static struct attribute *ib_dev_attrs[] = { &dev_attr_abi_version.attr, &dev_attr_ibdev.attr, NULL, }; static const struct attribute_group dev_attr_group = { .attrs = ib_dev_attrs, }; static CLASS_ATTR_STRING(abi_version, S_IRUGO, __stringify(IB_USER_VERBS_ABI_VERSION)); static int ib_uverbs_create_uapi(struct ib_device *device, struct ib_uverbs_device *uverbs_dev) { struct uverbs_api *uapi; uapi = uverbs_alloc_api(device); if (IS_ERR(uapi)) return PTR_ERR(uapi); uverbs_dev->uapi = uapi; return 0; } static int ib_uverbs_add_one(struct ib_device *device) { int devnum; dev_t base; struct ib_uverbs_device *uverbs_dev; int ret; if (!device->ops.alloc_ucontext || device->type == RDMA_DEVICE_TYPE_SMI) return -EOPNOTSUPP; uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL); if (!uverbs_dev) return -ENOMEM; ret = init_srcu_struct(&uverbs_dev->disassociate_srcu); if (ret) { kfree(uverbs_dev); return -ENOMEM; } device_initialize(&uverbs_dev->dev); uverbs_dev->dev.class = &uverbs_class; uverbs_dev->dev.parent = device->dev.parent; uverbs_dev->dev.release = ib_uverbs_release_dev; uverbs_dev->groups[0] = &dev_attr_group; uverbs_dev->dev.groups = uverbs_dev->groups; refcount_set(&uverbs_dev->refcount, 1); init_completion(&uverbs_dev->comp); uverbs_dev->xrcd_tree = RB_ROOT; mutex_init(&uverbs_dev->xrcd_tree_mutex); mutex_init(&uverbs_dev->lists_mutex); INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list); rcu_assign_pointer(uverbs_dev->ib_dev, device); uverbs_dev->num_comp_vectors = device->num_comp_vectors; devnum = ida_alloc_max(&uverbs_ida, IB_UVERBS_MAX_DEVICES - 1, GFP_KERNEL); if (devnum < 0) { ret = -ENOMEM; goto err; } uverbs_dev->devnum = devnum; if (devnum >= IB_UVERBS_NUM_FIXED_MINOR) base = dynamic_uverbs_dev + devnum - IB_UVERBS_NUM_FIXED_MINOR; else base = IB_UVERBS_BASE_DEV + devnum; ret = ib_uverbs_create_uapi(device, uverbs_dev); if (ret) goto err_uapi; uverbs_dev->dev.devt = base; dev_set_name(&uverbs_dev->dev, "uverbs%d", uverbs_dev->devnum); cdev_init(&uverbs_dev->cdev, device->ops.mmap ? &uverbs_mmap_fops : &uverbs_fops); uverbs_dev->cdev.owner = THIS_MODULE; ret = cdev_device_add(&uverbs_dev->cdev, &uverbs_dev->dev); if (ret) goto err_uapi; ib_set_client_data(device, &uverbs_client, uverbs_dev); return 0; err_uapi: ida_free(&uverbs_ida, devnum); err: if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); return ret; } static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, struct ib_device *ib_dev) { struct ib_uverbs_file *file; /* Pending running commands to terminate */ uverbs_disassociate_api_pre(uverbs_dev); mutex_lock(&uverbs_dev->lists_mutex); while (!list_empty(&uverbs_dev->uverbs_file_list)) { file = list_first_entry(&uverbs_dev->uverbs_file_list, struct ib_uverbs_file, list); list_del_init(&file->list); kref_get(&file->ref); /* We must release the mutex before going ahead and calling * uverbs_cleanup_ufile, as it might end up indirectly calling * uverbs_close, for example due to freeing the resources (e.g * mmput). */ mutex_unlock(&uverbs_dev->lists_mutex); uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); mutex_lock(&uverbs_dev->lists_mutex); } mutex_unlock(&uverbs_dev->lists_mutex); uverbs_disassociate_api(uverbs_dev->uapi); } static void ib_uverbs_remove_one(struct ib_device *device, void *client_data) { struct ib_uverbs_device *uverbs_dev = client_data; int wait_clients = 1; cdev_device_del(&uverbs_dev->cdev, &uverbs_dev->dev); ida_free(&uverbs_ida, uverbs_dev->devnum); if (device->ops.disassociate_ucontext) { /* We disassociate HW resources and immediately return. * Userspace will see a EIO errno for all future access. * Upon returning, ib_device may be freed internally and is not * valid any more. * uverbs_device is still available until all clients close * their files, then the uverbs device ref count will be zero * and its resources will be freed. * Note: At this point no more files can be opened since the * cdev was deleted, however active clients can still issue * commands and close their open files. */ ib_uverbs_free_hw_resources(uverbs_dev, device); wait_clients = 0; } if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); if (wait_clients) wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); } static int __init ib_uverbs_init(void) { int ret; ret = register_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR, "infiniband_verbs"); if (ret) { pr_err("user_verbs: couldn't register device number\n"); goto out; } ret = alloc_chrdev_region(&dynamic_uverbs_dev, 0, IB_UVERBS_NUM_DYNAMIC_MINOR, "infiniband_verbs"); if (ret) { pr_err("couldn't register dynamic device number\n"); goto out_alloc; } ret = class_register(&uverbs_class); if (ret) { pr_err("user_verbs: couldn't create class infiniband_verbs\n"); goto out_chrdev; } ret = class_create_file(&uverbs_class, &class_attr_abi_version.attr); if (ret) { pr_err("user_verbs: couldn't create abi_version attribute\n"); goto out_class; } ret = ib_register_client(&uverbs_client); if (ret) { pr_err("user_verbs: couldn't register client\n"); goto out_class; } return 0; out_class: class_unregister(&uverbs_class); out_chrdev: unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); out_alloc: unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); out: return ret; } static void __exit ib_uverbs_cleanup(void) { ib_unregister_client(&uverbs_client); class_unregister(&uverbs_class); unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); mmu_notifier_synchronize(); } module_init(ib_uverbs_init); module_exit(ib_uverbs_cleanup); |
| 14 8 8 14 14 5 5 12 8 4 4 2 2 4 2 2 4 2 2 2 8 2 6 6 6 12 7 5 4 2 5 2 3 3 1 1 3 3 3 9 5 5 7 5 4 7 7 7 5 1 4 4 8 6 8 2 4 2 1 4 4 7 6 2 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * RTC subsystem, interface functions * * Copyright (C) 2005 Tower Technologies * Author: Alessandro Zummo <a.zummo@towertech.it> * * based on arch/arm/common/rtctime.c */ #include <linux/rtc.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/log2.h> #include <linux/workqueue.h> #define CREATE_TRACE_POINTS #include <trace/events/rtc.h> static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer); static void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer); static void rtc_add_offset(struct rtc_device *rtc, struct rtc_time *tm) { time64_t secs; if (!rtc->offset_secs) return; secs = rtc_tm_to_time64(tm); /* * Since the reading time values from RTC device are always in the RTC * original valid range, but we need to skip the overlapped region * between expanded range and original range, which is no need to add * the offset. */ if ((rtc->start_secs > rtc->range_min && secs >= rtc->start_secs) || (rtc->start_secs < rtc->range_min && secs <= (rtc->start_secs + rtc->range_max - rtc->range_min))) return; rtc_time64_to_tm(secs + rtc->offset_secs, tm); } static void rtc_subtract_offset(struct rtc_device *rtc, struct rtc_time *tm) { time64_t secs; if (!rtc->offset_secs) return; secs = rtc_tm_to_time64(tm); /* * If the setting time values are in the valid range of RTC hardware * device, then no need to subtract the offset when setting time to RTC * device. Otherwise we need to subtract the offset to make the time * values are valid for RTC hardware device. */ if (secs >= rtc->range_min && secs <= rtc->range_max) return; rtc_time64_to_tm(secs - rtc->offset_secs, tm); } static int rtc_valid_range(struct rtc_device *rtc, struct rtc_time *tm) { if (rtc->range_min != rtc->range_max) { time64_t time = rtc_tm_to_time64(tm); time64_t range_min = rtc->set_start_time ? rtc->start_secs : rtc->range_min; timeu64_t range_max = rtc->set_start_time ? (rtc->start_secs + rtc->range_max - rtc->range_min) : rtc->range_max; if (time < range_min || time > range_max) return -ERANGE; } return 0; } static int __rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm) { int err; if (!rtc->ops) { err = -ENODEV; } else if (!rtc->ops->read_time) { err = -EINVAL; } else { memset(tm, 0, sizeof(struct rtc_time)); err = rtc->ops->read_time(rtc->dev.parent, tm); if (err < 0) { dev_dbg(&rtc->dev, "read_time: fail to read: %d\n", err); return err; } rtc_add_offset(rtc, tm); err = rtc_valid_tm(tm); if (err < 0) dev_dbg(&rtc->dev, "read_time: rtc_time isn't valid\n"); } return err; } int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm) { int err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; err = __rtc_read_time(rtc, tm); mutex_unlock(&rtc->ops_lock); trace_rtc_read_time(rtc_tm_to_time64(tm), err); return err; } EXPORT_SYMBOL_GPL(rtc_read_time); int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) { int err, uie; err = rtc_valid_tm(tm); if (err != 0) return err; err = rtc_valid_range(rtc, tm); if (err) return err; rtc_subtract_offset(rtc, tm); #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL uie = rtc->uie_rtctimer.enabled || rtc->uie_irq_active; #else uie = rtc->uie_rtctimer.enabled; #endif if (uie) { err = rtc_update_irq_enable(rtc, 0); if (err) return err; } err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; if (!rtc->ops) err = -ENODEV; else if (rtc->ops->set_time) err = rtc->ops->set_time(rtc->dev.parent, tm); else err = -EINVAL; pm_stay_awake(rtc->dev.parent); mutex_unlock(&rtc->ops_lock); /* A timer might have just expired */ schedule_work(&rtc->irqwork); if (uie) { err = rtc_update_irq_enable(rtc, 1); if (err) return err; } trace_rtc_set_time(rtc_tm_to_time64(tm), err); return err; } EXPORT_SYMBOL_GPL(rtc_set_time); static int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; if (!rtc->ops) { err = -ENODEV; } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->read_alarm) { err = -EINVAL; } else { alarm->enabled = 0; alarm->pending = 0; alarm->time.tm_sec = -1; alarm->time.tm_min = -1; alarm->time.tm_hour = -1; alarm->time.tm_mday = -1; alarm->time.tm_mon = -1; alarm->time.tm_year = -1; alarm->time.tm_wday = -1; alarm->time.tm_yday = -1; alarm->time.tm_isdst = -1; err = rtc->ops->read_alarm(rtc->dev.parent, alarm); } mutex_unlock(&rtc->ops_lock); trace_rtc_read_alarm(rtc_tm_to_time64(&alarm->time), err); return err; } int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; struct rtc_time before, now; int first_time = 1; time64_t t_now, t_alm; enum { none, day, month, year } missing = none; unsigned int days; /* The lower level RTC driver may return -1 in some fields, * creating invalid alarm->time values, for reasons like: * * - The hardware may not be capable of filling them in; * many alarms match only on time-of-day fields, not * day/month/year calendar data. * * - Some hardware uses illegal values as "wildcard" match * values, which non-Linux firmware (like a BIOS) may try * to set up as e.g. "alarm 15 minutes after each hour". * Linux uses only oneshot alarms. * * When we see that here, we deal with it by using values from * a current RTC timestamp for any missing (-1) values. The * RTC driver prevents "periodic alarm" modes. * * But this can be racey, because some fields of the RTC timestamp * may have wrapped in the interval since we read the RTC alarm, * which would lead to us inserting inconsistent values in place * of the -1 fields. * * Reading the alarm and timestamp in the reverse sequence * would have the same race condition, and not solve the issue. * * So, we must first read the RTC timestamp, * then read the RTC alarm value, * and then read a second RTC timestamp. * * If any fields of the second timestamp have changed * when compared with the first timestamp, then we know * our timestamp may be inconsistent with that used by * the low-level rtc_read_alarm_internal() function. * * So, when the two timestamps disagree, we just loop and do * the process again to get a fully consistent set of values. * * This could all instead be done in the lower level driver, * but since more than one lower level RTC implementation needs it, * then it's probably best to do it here instead of there.. */ /* Get the "before" timestamp */ err = rtc_read_time(rtc, &before); if (err < 0) return err; do { if (!first_time) memcpy(&before, &now, sizeof(struct rtc_time)); first_time = 0; /* get the RTC alarm values, which may be incomplete */ err = rtc_read_alarm_internal(rtc, alarm); if (err) return err; /* full-function RTCs won't have such missing fields */ err = rtc_valid_tm(&alarm->time); if (!err) goto done; /* get the "after" timestamp, to detect wrapped fields */ err = rtc_read_time(rtc, &now); if (err < 0) return err; /* note that tm_sec is a "don't care" value here: */ } while (before.tm_min != now.tm_min || before.tm_hour != now.tm_hour || before.tm_mon != now.tm_mon || before.tm_year != now.tm_year); /* Fill in the missing alarm fields using the timestamp; we * know there's at least one since alarm->time is invalid. */ if (alarm->time.tm_sec == -1) alarm->time.tm_sec = now.tm_sec; if (alarm->time.tm_min == -1) alarm->time.tm_min = now.tm_min; if (alarm->time.tm_hour == -1) alarm->time.tm_hour = now.tm_hour; /* For simplicity, only support date rollover for now */ if (alarm->time.tm_mday < 1 || alarm->time.tm_mday > 31) { alarm->time.tm_mday = now.tm_mday; missing = day; } if ((unsigned int)alarm->time.tm_mon >= 12) { alarm->time.tm_mon = now.tm_mon; if (missing == none) missing = month; } if (alarm->time.tm_year == -1) { alarm->time.tm_year = now.tm_year; if (missing == none) missing = year; } /* Can't proceed if alarm is still invalid after replacing * missing fields. */ err = rtc_valid_tm(&alarm->time); if (err) goto done; /* with luck, no rollover is needed */ t_now = rtc_tm_to_time64(&now); t_alm = rtc_tm_to_time64(&alarm->time); if (t_now < t_alm) goto done; switch (missing) { /* 24 hour rollover ... if it's now 10am Monday, an alarm that * that will trigger at 5am will do so at 5am Tuesday, which * could also be in the next month or year. This is a common * case, especially for PCs. */ case day: dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day"); t_alm += 24 * 60 * 60; rtc_time64_to_tm(t_alm, &alarm->time); break; /* Month rollover ... if it's the 31th, an alarm on the 3rd will * be next month. An alarm matching on the 30th, 29th, or 28th * may end up in the month after that! Many newer PCs support * this type of alarm. */ case month: dev_dbg(&rtc->dev, "alarm rollover: %s\n", "month"); do { if (alarm->time.tm_mon < 11) { alarm->time.tm_mon++; } else { alarm->time.tm_mon = 0; alarm->time.tm_year++; } days = rtc_month_days(alarm->time.tm_mon, alarm->time.tm_year); } while (days < alarm->time.tm_mday); break; /* Year rollover ... easy except for leap years! */ case year: dev_dbg(&rtc->dev, "alarm rollover: %s\n", "year"); do { alarm->time.tm_year++; } while (!is_leap_year(alarm->time.tm_year + 1900) && rtc_valid_tm(&alarm->time) != 0); break; default: dev_warn(&rtc->dev, "alarm rollover not handled\n"); } err = rtc_valid_tm(&alarm->time); done: if (err && alarm->enabled) dev_warn(&rtc->dev, "invalid alarm value: %ptR\n", &alarm->time); else rtc_add_offset(rtc, &alarm->time); return err; } int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; if (!rtc->ops) { err = -ENODEV; } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) { err = -EINVAL; } else { memset(alarm, 0, sizeof(struct rtc_wkalrm)); alarm->enabled = rtc->aie_timer.enabled; alarm->time = rtc_ktime_to_tm(rtc->aie_timer.node.expires); } mutex_unlock(&rtc->ops_lock); trace_rtc_read_alarm(rtc_tm_to_time64(&alarm->time), err); return err; } EXPORT_SYMBOL_GPL(rtc_read_alarm); static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { struct rtc_time tm; time64_t now, scheduled; int err; err = rtc_valid_tm(&alarm->time); if (err) return err; scheduled = rtc_tm_to_time64(&alarm->time); /* Make sure we're not setting alarms in the past */ err = __rtc_read_time(rtc, &tm); if (err) return err; now = rtc_tm_to_time64(&tm); if (scheduled <= now) return -ETIME; /* * XXX - We just checked to make sure the alarm time is not * in the past, but there is still a race window where if * the is alarm set for the next second and the second ticks * over right here, before we set the alarm. */ rtc_subtract_offset(rtc, &alarm->time); if (!rtc->ops) err = -ENODEV; else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) err = -EINVAL; else err = rtc->ops->set_alarm(rtc->dev.parent, alarm); trace_rtc_set_alarm(rtc_tm_to_time64(&alarm->time), err); return err; } int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { ktime_t alarm_time; int err; if (!rtc->ops) return -ENODEV; else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -EINVAL; err = rtc_valid_tm(&alarm->time); if (err != 0) return err; err = rtc_valid_range(rtc, &alarm->time); if (err) return err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; if (rtc->aie_timer.enabled) rtc_timer_remove(rtc, &rtc->aie_timer); alarm_time = rtc_tm_to_ktime(alarm->time); /* * Round down so we never miss a deadline, checking for past deadline is * done in __rtc_set_alarm */ if (test_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features)) alarm_time = ktime_sub_ns(alarm_time, (u64)alarm->time.tm_sec * NSEC_PER_SEC); rtc->aie_timer.node.expires = alarm_time; rtc->aie_timer.period = 0; if (alarm->enabled) err = rtc_timer_enqueue(rtc, &rtc->aie_timer); mutex_unlock(&rtc->ops_lock); return err; } EXPORT_SYMBOL_GPL(rtc_set_alarm); /* Called once per device from rtc_device_register */ int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; struct rtc_time now; err = rtc_valid_tm(&alarm->time); if (err != 0) return err; err = rtc_read_time(rtc, &now); if (err) return err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time); rtc->aie_timer.period = 0; /* Alarm has to be enabled & in the future for us to enqueue it */ if (alarm->enabled && (rtc_tm_to_ktime(now) < rtc->aie_timer.node.expires)) { rtc->aie_timer.enabled = 1; timerqueue_add(&rtc->timerqueue, &rtc->aie_timer.node); trace_rtc_timer_enqueue(&rtc->aie_timer); } mutex_unlock(&rtc->ops_lock); return err; } EXPORT_SYMBOL_GPL(rtc_initialize_alarm); int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) { int err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; if (rtc->aie_timer.enabled != enabled) { if (enabled) err = rtc_timer_enqueue(rtc, &rtc->aie_timer); else rtc_timer_remove(rtc, &rtc->aie_timer); } if (err) /* nothing */; else if (!rtc->ops) err = -ENODEV; else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) err = -EINVAL; else err = rtc->ops->alarm_irq_enable(rtc->dev.parent, enabled); mutex_unlock(&rtc->ops_lock); trace_rtc_alarm_irq_enable(enabled, err); return err; } EXPORT_SYMBOL_GPL(rtc_alarm_irq_enable); int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled) { int err; err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL if (enabled == 0 && rtc->uie_irq_active) { mutex_unlock(&rtc->ops_lock); return rtc_dev_update_irq_enable_emul(rtc, 0); } #endif /* make sure we're changing state */ if (rtc->uie_rtctimer.enabled == enabled) goto out; if (!test_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features) || !test_bit(RTC_FEATURE_ALARM, rtc->features)) { mutex_unlock(&rtc->ops_lock); #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL return rtc_dev_update_irq_enable_emul(rtc, enabled); #else return -EINVAL; #endif } if (enabled) { struct rtc_time tm; ktime_t now, onesec; err = __rtc_read_time(rtc, &tm); if (err) goto out; onesec = ktime_set(1, 0); now = rtc_tm_to_ktime(tm); rtc->uie_rtctimer.node.expires = ktime_add(now, onesec); rtc->uie_rtctimer.period = ktime_set(1, 0); err = rtc_timer_enqueue(rtc, &rtc->uie_rtctimer); } else { rtc_timer_remove(rtc, &rtc->uie_rtctimer); } out: mutex_unlock(&rtc->ops_lock); return err; } EXPORT_SYMBOL_GPL(rtc_update_irq_enable); /** * rtc_handle_legacy_irq - AIE, UIE and PIE event hook * @rtc: pointer to the rtc device * @num: number of occurence of the event * @mode: type of the event, RTC_AF, RTC_UF of RTC_PF * * This function is called when an AIE, UIE or PIE mode interrupt * has occurred (or been emulated). * */ void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode) { unsigned long flags; /* mark one irq of the appropriate mode */ spin_lock_irqsave(&rtc->irq_lock, flags); rtc->irq_data = (rtc->irq_data + (num << 8)) | (RTC_IRQF | mode); spin_unlock_irqrestore(&rtc->irq_lock, flags); wake_up_interruptible(&rtc->irq_queue); kill_fasync(&rtc->async_queue, SIGIO, POLL_IN); } /** * rtc_aie_update_irq - AIE mode rtctimer hook * @rtc: pointer to the rtc_device * * This functions is called when the aie_timer expires. */ void rtc_aie_update_irq(struct rtc_device *rtc) { rtc_handle_legacy_irq(rtc, 1, RTC_AF); } /** * rtc_uie_update_irq - UIE mode rtctimer hook * @rtc: pointer to the rtc_device * * This functions is called when the uie_timer expires. */ void rtc_uie_update_irq(struct rtc_device *rtc) { rtc_handle_legacy_irq(rtc, 1, RTC_UF); } /** * rtc_pie_update_irq - PIE mode hrtimer hook * @timer: pointer to the pie mode hrtimer * * This function is used to emulate PIE mode interrupts * using an hrtimer. This function is called when the periodic * hrtimer expires. */ enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer) { struct rtc_device *rtc; ktime_t period; u64 count; rtc = container_of(timer, struct rtc_device, pie_timer); period = NSEC_PER_SEC / rtc->irq_freq; count = hrtimer_forward_now(timer, period); rtc_handle_legacy_irq(rtc, count, RTC_PF); return HRTIMER_RESTART; } /** * rtc_update_irq - Triggered when a RTC interrupt occurs. * @rtc: the rtc device * @num: how many irqs are being reported (usually one) * @events: mask of RTC_IRQF with one or more of RTC_PF, RTC_AF, RTC_UF * Context: any */ void rtc_update_irq(struct rtc_device *rtc, unsigned long num, unsigned long events) { if (IS_ERR_OR_NULL(rtc)) return; pm_stay_awake(rtc->dev.parent); schedule_work(&rtc->irqwork); } EXPORT_SYMBOL_GPL(rtc_update_irq); struct rtc_device *rtc_class_open(const char *name) { struct device *dev; struct rtc_device *rtc = NULL; dev = class_find_device_by_name(&rtc_class, name); if (dev) rtc = to_rtc_device(dev); if (rtc) { if (!try_module_get(rtc->owner)) { put_device(dev); rtc = NULL; } } return rtc; } EXPORT_SYMBOL_GPL(rtc_class_open); void rtc_class_close(struct rtc_device *rtc) { module_put(rtc->owner); put_device(&rtc->dev); } EXPORT_SYMBOL_GPL(rtc_class_close); static int rtc_update_hrtimer(struct rtc_device *rtc, int enabled) { /* * We always cancel the timer here first, because otherwise * we could run into BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); * when we manage to start the timer before the callback * returns HRTIMER_RESTART. * * We cannot use hrtimer_cancel() here as a running callback * could be blocked on rtc->irq_task_lock and hrtimer_cancel() * would spin forever. */ if (hrtimer_try_to_cancel(&rtc->pie_timer) < 0) return -1; if (enabled) { ktime_t period = NSEC_PER_SEC / rtc->irq_freq; hrtimer_start(&rtc->pie_timer, period, HRTIMER_MODE_REL); } return 0; } /** * rtc_irq_set_state - enable/disable 2^N Hz periodic IRQs * @rtc: the rtc device * @enabled: true to enable periodic IRQs * Context: any * * Note that rtc_irq_set_freq() should previously have been used to * specify the desired frequency of periodic IRQ. */ int rtc_irq_set_state(struct rtc_device *rtc, int enabled) { int err = 0; while (rtc_update_hrtimer(rtc, enabled) < 0) cpu_relax(); rtc->pie_enabled = enabled; trace_rtc_irq_set_state(enabled, err); return err; } /** * rtc_irq_set_freq - set 2^N Hz periodic IRQ frequency for IRQ * @rtc: the rtc device * @freq: positive frequency * Context: any * * Note that rtc_irq_set_state() is used to enable or disable the * periodic IRQs. */ int rtc_irq_set_freq(struct rtc_device *rtc, int freq) { int err = 0; if (freq <= 0 || freq > RTC_MAX_FREQ) return -EINVAL; rtc->irq_freq = freq; while (rtc->pie_enabled && rtc_update_hrtimer(rtc, 1) < 0) cpu_relax(); trace_rtc_irq_set_freq(freq, err); return err; } /** * rtc_timer_enqueue - Adds a rtc_timer to the rtc_device timerqueue * @rtc: rtc device * @timer: timer being added. * * Enqueues a timer onto the rtc devices timerqueue and sets * the next alarm event appropriately. * * Sets the enabled bit on the added timer. * * Must hold ops_lock for proper serialization of timerqueue */ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) { struct timerqueue_node *next = timerqueue_getnext(&rtc->timerqueue); struct rtc_time tm; ktime_t now; int err; err = __rtc_read_time(rtc, &tm); if (err) return err; timer->enabled = 1; now = rtc_tm_to_ktime(tm); /* Skip over expired timers */ while (next) { if (next->expires >= now) break; next = timerqueue_iterate_next(next); } timerqueue_add(&rtc->timerqueue, &timer->node); trace_rtc_timer_enqueue(timer); if (!next || ktime_before(timer->node.expires, next->expires)) { struct rtc_wkalrm alarm; alarm.time = rtc_ktime_to_tm(timer->node.expires); alarm.enabled = 1; err = __rtc_set_alarm(rtc, &alarm); if (err == -ETIME) { pm_stay_awake(rtc->dev.parent); schedule_work(&rtc->irqwork); } else if (err) { timerqueue_del(&rtc->timerqueue, &timer->node); trace_rtc_timer_dequeue(timer); timer->enabled = 0; return err; } } return 0; } static void rtc_alarm_disable(struct rtc_device *rtc) { if (!rtc->ops || !test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) return; rtc->ops->alarm_irq_enable(rtc->dev.parent, false); trace_rtc_alarm_irq_enable(0, 0); } /** * rtc_timer_remove - Removes a rtc_timer from the rtc_device timerqueue * @rtc: rtc device * @timer: timer being removed. * * Removes a timer onto the rtc devices timerqueue and sets * the next alarm event appropriately. * * Clears the enabled bit on the removed timer. * * Must hold ops_lock for proper serialization of timerqueue */ static void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer) { struct timerqueue_node *next = timerqueue_getnext(&rtc->timerqueue); timerqueue_del(&rtc->timerqueue, &timer->node); trace_rtc_timer_dequeue(timer); timer->enabled = 0; if (next == &timer->node) { struct rtc_wkalrm alarm; int err; next = timerqueue_getnext(&rtc->timerqueue); if (!next) { rtc_alarm_disable(rtc); return; } alarm.time = rtc_ktime_to_tm(next->expires); alarm.enabled = 1; err = __rtc_set_alarm(rtc, &alarm); if (err == -ETIME) { pm_stay_awake(rtc->dev.parent); schedule_work(&rtc->irqwork); } } } /** * rtc_timer_do_work - Expires rtc timers * @work: work item * * Expires rtc timers. Reprograms next alarm event if needed. * Called via worktask. * * Serializes access to timerqueue via ops_lock mutex */ void rtc_timer_do_work(struct work_struct *work) { struct rtc_timer *timer; struct timerqueue_node *next; ktime_t now; struct rtc_time tm; int err; struct rtc_device *rtc = container_of(work, struct rtc_device, irqwork); mutex_lock(&rtc->ops_lock); again: err = __rtc_read_time(rtc, &tm); if (err) { mutex_unlock(&rtc->ops_lock); return; } now = rtc_tm_to_ktime(tm); while ((next = timerqueue_getnext(&rtc->timerqueue))) { if (next->expires > now) break; /* expire timer */ timer = container_of(next, struct rtc_timer, node); timerqueue_del(&rtc->timerqueue, &timer->node); trace_rtc_timer_dequeue(timer); timer->enabled = 0; if (timer->func) timer->func(timer->rtc); trace_rtc_timer_fired(timer); /* Re-add/fwd periodic timers */ if (ktime_to_ns(timer->period)) { timer->node.expires = ktime_add(timer->node.expires, timer->period); timer->enabled = 1; timerqueue_add(&rtc->timerqueue, &timer->node); trace_rtc_timer_enqueue(timer); } } /* Set next alarm */ if (next) { struct rtc_wkalrm alarm; int err; int retry = 3; alarm.time = rtc_ktime_to_tm(next->expires); alarm.enabled = 1; reprogram: err = __rtc_set_alarm(rtc, &alarm); if (err == -ETIME) { goto again; } else if (err) { if (retry-- > 0) goto reprogram; timer = container_of(next, struct rtc_timer, node); timerqueue_del(&rtc->timerqueue, &timer->node); trace_rtc_timer_dequeue(timer); timer->enabled = 0; dev_err(&rtc->dev, "__rtc_set_alarm: err=%d\n", err); goto again; } } else { rtc_alarm_disable(rtc); } pm_relax(rtc->dev.parent); mutex_unlock(&rtc->ops_lock); } /* rtc_timer_init - Initializes an rtc_timer * @timer: timer to be intiialized * @f: function pointer to be called when timer fires * @rtc: pointer to the rtc_device * * Kernel interface to initializing an rtc_timer. */ void rtc_timer_init(struct rtc_timer *timer, void (*f)(struct rtc_device *r), struct rtc_device *rtc) { timerqueue_init(&timer->node); timer->enabled = 0; timer->func = f; timer->rtc = rtc; } /* rtc_timer_start - Sets an rtc_timer to fire in the future * @ rtc: rtc device to be used * @ timer: timer being set * @ expires: time at which to expire the timer * @ period: period that the timer will recur * * Kernel interface to set an rtc_timer */ int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, ktime_t expires, ktime_t period) { int ret = 0; mutex_lock(&rtc->ops_lock); if (timer->enabled) rtc_timer_remove(rtc, timer); timer->node.expires = expires; timer->period = period; ret = rtc_timer_enqueue(rtc, timer); mutex_unlock(&rtc->ops_lock); return ret; } /* rtc_timer_cancel - Stops an rtc_timer * @ rtc: rtc device to be used * @ timer: timer being set * * Kernel interface to cancel an rtc_timer */ void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer) { mutex_lock(&rtc->ops_lock); if (timer->enabled) rtc_timer_remove(rtc, timer); mutex_unlock(&rtc->ops_lock); } /** * rtc_read_offset - Read the amount of rtc offset in parts per billion * @rtc: rtc device to be used * @offset: the offset in parts per billion * * see below for details. * * Kernel interface to read rtc clock offset * Returns 0 on success, or a negative number on error. * If read_offset() is not implemented for the rtc, return -EINVAL */ int rtc_read_offset(struct rtc_device *rtc, long *offset) { int ret; if (!rtc->ops) return -ENODEV; if (!rtc->ops->read_offset) return -EINVAL; mutex_lock(&rtc->ops_lock); ret = rtc->ops->read_offset(rtc->dev.parent, offset); mutex_unlock(&rtc->ops_lock); trace_rtc_read_offset(*offset, ret); return ret; } /** * rtc_set_offset - Adjusts the duration of the average second * @rtc: rtc device to be used * @offset: the offset in parts per billion * * Some rtc's allow an adjustment to the average duration of a second * to compensate for differences in the actual clock rate due to temperature, * the crystal, capacitor, etc. * * The adjustment applied is as follows: * t = t0 * (1 + offset * 1e-9) * where t0 is the measured length of 1 RTC second with offset = 0 * * Kernel interface to adjust an rtc clock offset. * Return 0 on success, or a negative number on error. * If the rtc offset is not setable (or not implemented), return -EINVAL */ int rtc_set_offset(struct rtc_device *rtc, long offset) { int ret; if (!rtc->ops) return -ENODEV; if (!rtc->ops->set_offset) return -EINVAL; mutex_lock(&rtc->ops_lock); ret = rtc->ops->set_offset(rtc->dev.parent, offset); mutex_unlock(&rtc->ops_lock); trace_rtc_set_offset(offset, ret); return ret; } |
| 15 146 19 18 1 2 16 44 2206 56 4 1574 210 260 577 505 56 260 280 80 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ADDRCONF_H #define _ADDRCONF_H #define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ #define TEMP_VALID_LIFETIME (7*86400) /* 1 week */ #define TEMP_PREFERRED_LIFETIME (86400) /* 24 hours */ #define REGEN_MIN_ADVANCE (2) /* 2 seconds */ #define REGEN_MAX_RETRY (3) #define MAX_DESYNC_FACTOR (600) #define ADDR_CHECK_FREQUENCY (120*HZ) #define IPV6_MAX_ADDRESSES 16 #define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ / 50 : 1) #define ADDRCONF_TIMER_FUZZ (HZ / 4) #define ADDRCONF_TIMER_FUZZ_MAX (HZ) #define ADDRCONF_NOTIFY_PRIORITY 0 #include <linux/in.h> #include <linux/in6.h> struct prefix_info { __u8 type; __u8 length; __u8 prefix_len; union __packed { __u8 flags; struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, autoconf : 1, routeraddr : 1, preferpd : 1, reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved : 4, preferpd : 1, routeraddr : 1, autoconf : 1, onlink : 1; #else #error "Please fix <asm/byteorder.h>" #endif }; }; __be32 valid; __be32 prefered; __be32 reserved2; struct in6_addr prefix; }; /* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ static_assert(sizeof(struct prefix_info) == 32); #include <linux/ipv6.h> #include <linux/netdevice.h> #include <net/if_inet6.h> #include <net/ipv6.h> struct in6_validator_info { struct in6_addr i6vi_addr; struct inet6_dev *i6vi_dev; struct netlink_ext_ack *extack; }; struct ifa6_config { const struct in6_addr *pfx; unsigned int plen; u8 ifa_proto; const struct in6_addr *peer_pfx; u32 rt_priority; u32 ifa_flags; u32 preferred_lft; u32 valid_lft; u16 scope; }; enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, }; struct inet6_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; enum addr_type_t type; bool force_rt_scope_universe; }; int addrconf_init(void); void addrconf_cleanup(void); int addrconf_add_ifaddr(struct net *net, void __user *arg); int addrconf_del_ifaddr(struct net *net, void __user *arg); int addrconf_set_dstaddr(struct net *net, void __user *arg); int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr); #endif int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, unsigned char nsegs); bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict); int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); bool inet_rcv_saddr_any(const struct sock *sk); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags); int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, const struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft); static inline void addrconf_addr_eui48_base(u8 *eui, const char *const addr) { memcpy(eui, addr, 3); eui[3] = 0xFF; eui[4] = 0xFE; memcpy(eui + 5, addr + 3, 3); } static inline void addrconf_addr_eui48(u8 *eui, const char *const addr) { addrconf_addr_eui48_base(eui, addr); eui[0] ^= 2; } static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) return -1; /* * The zSeries OSA network cards can be shared among various * OS instances, but the OSA cards have only one MAC address. * This leads to duplicate address conflicts in conjunction * with IPv6 if more than one instance uses the same card. * * The driver for these cards can deliver a unique 16-bit * identifier for each instance sharing the same card. It is * placed instead of 0xFFFE in the interface identifier. The * "u" bit of the interface identifier is not inverted in this * case. Hence the resulting interface identifier has local * scope according to RFC2373. */ addrconf_addr_eui48_base(eui, dev->dev_addr); if (dev->dev_id) { eui[3] = (dev->dev_id >> 8) & 0xFF; eui[4] = dev->dev_id & 0xFF; } else { eui[0] ^= 2; } return 0; } #define INFINITY_LIFE_TIME 0xFFFFFFFF static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* * Avoid arithmetic overflow. * Assuming unit is constant and non-zero, this "if" statement * will go away on 64bit archs. */ if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit) return LONG_MAX / unit; return timeout; } static inline int addrconf_finite_timeout(unsigned long timeout) { return ~timeout; } /* * IPv6 Address Label subsystem (addrlabel.c) */ int ipv6_addr_label_init(void); void ipv6_addr_label_cleanup(void); int ipv6_addr_label_rtnl_register(void); u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex); /* * multicast prototypes (mcast.c) */ static inline bool ipv6_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) return false; return pskb_may_pull(skb, len); } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_mc_close(struct sock *sk); void ipv6_sock_mc_close(struct sock *sk); bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr); int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr); int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr); int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr); void ipv6_mc_up(struct inet6_dev *idev); void ipv6_mc_down(struct inet6_dev *idev); void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr); void ipv6_mc_dad_complete(struct inet6_dev *idev); /* * identify MLD packets for MLD filter exceptions */ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset) { struct icmp6hdr *hdr; if (nexthdr != IPPROTO_ICMPV6 || !pskb_network_may_pull(skb, offset + sizeof(struct icmp6hdr))) return false; hdr = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (hdr->icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: return true; default: break; } return false; } void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao); /* * anycast prototypes (anycast.c) */ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); void ipv6_ac_destroy_dev(struct inet6_dev *idev); bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); int ipv6_anycast_init(void); void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); int unregister_inet6addr_notifier(struct notifier_block *nb); int inet6addr_notifier_call_chain(unsigned long val, void *v); int register_inet6addr_validator_notifier(struct notifier_block *nb); int unregister_inet6addr_validator_notifier(struct notifier_block *nb); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v); void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf); /** * __in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) { return rcu_dereference_rtnl(dev->ip6_ptr); } static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); } /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev, const struct sk_buff *skb) { if (netif_is_l3_master(dev)) dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb)); return __in6_dev_get(dev); } /** * __in6_dev_get_safely - get inet6_dev pointer from netdevice * @dev: network device * * This is a safer version of __in6_dev_get */ static inline struct inet6_dev *__in6_dev_get_safely(const struct net_device *dev) { if (likely(dev)) return rcu_dereference_rtnl(dev->ip6_ptr); else return NULL; } /** * in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * This version can be used in any context, and takes a reference * on the inet6_dev. Callers must use in6_dev_put() later to * release this reference. */ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) { struct inet6_dev *idev; rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); if (idev) refcount_inc(&idev->refcnt); rcu_read_unlock(); return idev; } static inline struct neigh_parms *__in6_dev_nd_parms_get_rcu(const struct net_device *dev) { struct inet6_dev *idev = __in6_dev_get(dev); return idev ? idev->nd_parms : NULL; } void in6_dev_finish_destroy(struct inet6_dev *idev); static inline void in6_dev_put(struct inet6_dev *idev) { if (refcount_dec_and_test(&idev->refcnt)) in6_dev_finish_destroy(idev); } static inline void in6_dev_put_clear(struct inet6_dev **pidev) { struct inet6_dev *idev = *pidev; if (idev) { in6_dev_put(idev); *pidev = NULL; } } static inline void __in6_dev_put(struct inet6_dev *idev) { refcount_dec(&idev->refcnt); } static inline void in6_dev_hold(struct inet6_dev *idev) { refcount_inc(&idev->refcnt); } /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { const struct inet6_dev *idev = __in6_dev_get(dev); if (unlikely(!idev)) return true; return !!READ_ONCE(idev->cnf.ignore_routes_with_linkdown); } void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) { if (refcount_dec_and_test(&ifp->refcnt)) inet6_ifa_finish_destroy(ifp); } static inline void __in6_ifa_put(struct inet6_ifaddr *ifp) { refcount_dec(&ifp->refcnt); } static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) { refcount_inc(&ifp->refcnt); } static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) { return refcount_inc_not_zero(&ifp->refcnt); } /* * compute link-local solicited-node multicast address */ static inline void addrconf_addr_solict_mult(const struct in6_addr *addr, struct in6_addr *solicited) { ipv6_addr_set(solicited, htonl(0xFF020000), 0, htonl(0x1), htonl(0xFF000000) | addr->s6_addr32[3]); } static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000001))) == 0; #endif } static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000002))) == 0; #endif } static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) { return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); } static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | ((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) & cpu_to_be64(0xffffffffff000000UL))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x00000001)) | (addr->s6_addr[12] ^ 0xff)) == 0; #endif } static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(0x6a))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x0000006a))) == 0; #endif } #ifdef CONFIG_PROC_FS int if6_proc_init(void); void if6_proc_exit(void); #endif int inet6_fill_ifmcaddr(struct sk_buff *skb, const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args); int inet6_fill_ifacaddr(struct sk_buff *skb, const struct ifacaddr6 *ifaca, struct inet6_fill_args *args); #endif |
| 20 6 20 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #ifndef __PHY_H #define __PHY_H #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/leds.h> #include <linux/linkmode.h> #include <linux/netlink.h> #include <linux/mdio.h> #include <linux/mii.h> #include <linux/mii_timestamper.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> #include <linux/u64_stats_sync.h> #include <linux/irqreturn.h> #include <linux/iopoll.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <net/eee.h> extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_basic_t1s_p2mp_features_array[2]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 #define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define PHY_POLL_CABLE_TEST 0x00000004 #define PHY_ALWAYS_CALL_SUSPEND 0x00000008 #define MDIO_DEVICE_IS_PHY 0x80000000 /** * enum phy_interface_t - Interface Mode definitions * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined * @PHY_INTERFACE_MODE_MII: Media-independent interface * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_10G_QXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; /* PHY interface mode bitmap handling */ #define DECLARE_PHY_INTERFACE_MASK(name) \ DECLARE_BITMAP(name, PHY_INTERFACE_MODE_MAX) static inline void phy_interface_zero(unsigned long *intf) { bitmap_zero(intf, PHY_INTERFACE_MODE_MAX); } static inline bool phy_interface_empty(const unsigned long *intf) { return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_and(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_or(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_or(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_set_rgmii(unsigned long *intf) { __set_bit(PHY_INTERFACE_MODE_RGMII, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_ID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); } /* * phy_supported_speeds - return all speeds currently supported by a PHY device */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, unsigned int size); /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * * Description: maps enum &phy_interface_t defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get PHY interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; case PHY_INTERFACE_MODE_INTERNAL: return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: return "gmii"; case PHY_INTERFACE_MODE_SGMII: return "sgmii"; case PHY_INTERFACE_MODE_TBI: return "tbi"; case PHY_INTERFACE_MODE_REVMII: return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; case PHY_INTERFACE_MODE_REVRMII: return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: return "rgmii-id"; case PHY_INTERFACE_MODE_RGMII_RXID: return "rgmii-rxid"; case PHY_INTERFACE_MODE_RGMII_TXID: return "rgmii-txid"; case PHY_INTERFACE_MODE_RTBI: return "rtbi"; case PHY_INTERFACE_MODE_SMII: return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; case PHY_INTERFACE_MODE_XLGMII: return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_PSGMII: return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; case PHY_INTERFACE_MODE_1000BASEKX: return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; case PHY_INTERFACE_MODE_25GBASER: return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; case PHY_INTERFACE_MODE_10G_QXGMII: return "10g-qxgmii"; default: return "unknown"; } } /** * rgmii_clock - map link speed to the clock rate * @speed: link speed value * * Description: maps RGMII supported link speeds * into the clock rates. * * Returns: clock rate or negative errno */ static inline long rgmii_clock(int speed) { switch (speed) { case SPEED_10: return 2500000; case SPEED_100: return 25000000; case SPEED_1000: return 125000000; default: return -EINVAL; } } #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" #define MII_BUS_ID_SIZE 61 struct device; struct kernel_hwtstamp_config; struct phylink; struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; /** * struct mdio_bus_stats - Statistics counters for MDIO busses * @transfers: Total number of transfers, i.e. @writes + @reads * @errors: Number of MDIO transfers that returned an error * @writes: Number of write transfers * @reads: Number of read transfers * @syncp: Synchronisation for incrementing statistics */ struct mdio_bus_stats { u64_stats_t transfers; u64_stats_t errors; u64_stats_t writes; u64_stats_t reads; /* Must be last, add new statistics above */ struct u64_stats_sync syncp; }; /** * struct phy_package_shared - Shared information in PHY packages * @base_addr: Base PHY address of PHY package used to combine PHYs * in one package and for offset calculation of phy_package_read/write * @np: Pointer to the Device Node if PHY package defined in DT * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv * @priv: Driver private data shared across a PHY package * * Represents a shared structure between different phydev's in the same * package, for example a quad PHY. See phy_package_join() and * phy_package_leave(). */ struct phy_package_shared { u8 base_addr; /* With PHY package defined in DT this points to the PHY package node */ struct device_node *np; refcount_t refcnt; unsigned long flags; size_t priv_size; /* private data pointer */ /* note that this pointer is shared between different phydevs and * the user has to take care of appropriate locking. It is allocated * and freed automatically by phy_package_join() and * phy_package_leave(). */ void *priv; }; /* used as bit number in atomic bitops */ #define PHY_SHARED_F_INIT_DONE 0 #define PHY_SHARED_F_PROBE_DONE 1 /** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device * @name: User friendly name for this MDIO device, or driver name * @id: Unique identifier for this bus, typical from bus hierarchy * @priv: Driver private data * * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ struct mii_bus { struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; /** @read: Perform a read transfer on the bus */ int (*read)(struct mii_bus *bus, int addr, int regnum); /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); /** @read_c45: Perform a C45 read transfer on the bus */ int (*read_c45)(struct mii_bus *bus, int addr, int devnum, int regnum); /** @write_c45: Perform a C45 write transfer on the bus */ int (*write_c45)(struct mii_bus *bus, int addr, int devnum, int regnum, u16 val); /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); /** @stats: Statistic counters per device on the bus */ struct mdio_bus_stats stats[PHY_MAX_ADDR]; /** * @mdio_lock: A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; /** @parent: Parent device of this bus */ struct device *parent; /** @state: State of bus structure */ enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; /** @dev: Kernel device representation */ struct device dev; /** @mdio_map: list of all MDIO devices on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; /** @phy_mask: PHY addresses to be ignored when probing */ u32 phy_mask; /** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; /** * @irq: An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; /** @reset_delay_us: GPIO reset pulse width in microseconds */ int reset_delay_us; /** @reset_post_delay_us: GPIO reset deassert delay in microseconds */ int reset_post_delay_us; /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) struct mii_bus *mdiobus_alloc_size(size_t size); /** * mdiobus_alloc - Allocate an MDIO bus structure * * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready * for the driver to register the bus. */ static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); } int __mdiobus_register(struct mii_bus *bus, struct module *owner); int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) #define devm_mdiobus_register(dev, bus) \ __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) { return devm_mdiobus_alloc_size(dev, 0); } struct mii_bus *mdio_find_bus(const char *mdio_name); struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true /** * enum phy_state - PHY state machine states: * * @PHY_DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. * - PHY driver probe function will set the state to @PHY_READY * * @PHY_READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * * @PHY_UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to @PHY_NOLINK or @PHY_RUNNING * * @PHY_NOLINK: PHY is up, but not currently plugged in. * - irq or timer will set @PHY_RUNNING if link comes back * - phy_stop moves to @PHY_HALTED * * @PHY_RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set @PHY_NOLINK if link goes down * - phy_stop moves to @PHY_HALTED * * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending * is not expected to work, carrier will be indicated as down. PHY will be * poll once per second, or on interrupt for it current state. * Once complete, move to UP to restart the PHY. * - phy_stop aborts the running test and moves to @PHY_HALTED * * @PHY_HALTED: PHY is up, but no polling or interrupts are done. * - phy_start moves to @PHY_UP * * @PHY_ERROR: PHY is up, but is in an error state. * - phy_stop moves to @PHY_HALTED */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, PHY_ERROR, PHY_UP, PHY_RUNNING, PHY_NOLINK, PHY_CABLETEST, }; #define MDIO_MMD_NUM 32 /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: IEEE 802.3 devices in package register value. * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; struct macsec_ops; /** * struct phy_device - An instance of a PHY * * @mdio: MDIO bus this PHY is on * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. * @phyindex: Unique id across the phy's parent tree of phys to address the PHY * from userspace, similar to ifindex. A zero index means the PHY * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. * @is_internal: Set to true if this PHY is internal to a MAC. * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc. * @is_gigabit_capable: Set to true if PHY supports 1000Mbps * @has_fixups: Set to true if this PHY has fixups/quirks. * @suspended: Set to true if this PHY has been suspended successfully. * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus. * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN * enabled. * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * * - Bits [15:0] are free to use by the PHY driver to communicate * driver specific behavior. * - Bits [23:16] are currently reserved for future use. * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port * @attached_dev: The attached enet driver's device instance ptr * @adjust_link: Callback for the enet controller to respond to changes: in the * link state. * @phy_link_change: Callback for phylink for notification of link change * @macsec_ops: MACsec offloading ops. * * @speed: Current link speed * @duplex: Current duplex * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @supported_eee: supported PHY EEE linkmodes * @advertising_eee: Currently advertised EEE linkmodes * @enable_tx_lpi: When True, MAC should transmit LPI to PHY * @eee_active: phylib private state, indicating that EEE has been negotiated * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @default_timestamp: Flag indicating whether we are using the phy * timestamp as the default one * @interface: enum phy_interface_t value * @possible_interfaces: bitmap if interface modes that the attached PHY * will switch between depending on media speed. * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics * @phy_led_triggers: Array of LED triggers * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed * @leds: list of PHY LED structures * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling * and disabling specific interrupts * * Contains some infrastructure for polling and interrupt * handling, as well as handling shifts in PHY hardware state */ struct phy_device { struct mdio_device mdio; /* Information about the PHY type */ /* And management functions */ const struct phy_driver *drv; struct device_link *devlink; u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; unsigned wol_enabled:1; unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; unsigned irq_suspended:1; unsigned irq_rerun:1; unsigned default_timestamp:1; int rate_matching; enum phy_state state; u32 dev_flags; phy_interface_t interface; DECLARE_PHY_INTERFACE_MASK(possible_interfaces); /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) */ int speed; int duplex; int port; int pause; int asym_pause; u8 master_slave_get; u8 master_slave_set; u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* used for eee validation and configuration*/ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); /* Energy efficient ethernet modes which should be prohibited */ __ETHTOOL_DECLARE_LINK_MODE_MASK(eee_broken_modes); bool enable_tx_lpi; bool eee_active; struct eee_config eee_cfg; /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; struct phy_led_trigger *led_link_trigger; #endif struct list_head leds; /* * Interrupt number for this PHY * -1 means no interrupt */ int irq; /* private data pointer */ /* For use by PHYs to maintain extra state */ void *priv; /* shared data pointer */ /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; /* Reporting cable test results */ struct sk_buff *skb; void *ehdr; struct nlattr *nest; /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; struct mutex lock; /* This may be modified under the rtnl lock */ bool sfp_bus_attached; struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; struct pse_control *psec; u8 mdix; u8 mdix_ctrl; int pma_extable; unsigned int link_down_events; void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif }; /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 #define PHY_F_RXC_ALWAYS_ON 0x40000000 static inline struct phy_device *to_phy_device(const struct device *dev) { return container_of(to_mdio_device(dev), struct phy_device, mdio); } /** * struct phy_tdr_config - Configuration of a TDR raw test * * @first: Distance for first data collection point * @last: Distance for last data collection point * @step: Step between data collection points * @pair: Bitmap of cable pairs to collect data for * * A structure containing possible configuration parameters * for a TDR cable test. The driver does not need to implement * all the parameters, but should report what is actually used. * All distances are in centimeters. */ struct phy_tdr_config { u32 first; u32 last; u32 step; s8 pair; }; #define PHY_PAIR_ALL -1 /** * enum link_inband_signalling - in-band signalling modes that are supported * * @LINK_INBAND_DISABLE: in-band signalling can be disabled * @LINK_INBAND_ENABLE: in-band signalling can be enabled without bypass * @LINK_INBAND_BYPASS: in-band signalling can be enabled with bypass * * The possible and required bits can only be used if the valid bit is set. * If possible is clear, that means inband signalling can not be used. * Required is only valid when possible is set, and means that inband * signalling must be used. */ enum link_inband_signalling { LINK_INBAND_DISABLE = BIT(0), LINK_INBAND_ENABLE = BIT(1), LINK_INBAND_BYPASS = BIT(2), }; /** * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @version: read-only PLCA register map version. -1 = not available. Ignored * when setting the configuration. Format is the same as reported by the PLCA * IDVER register (31.CA00). -1 = not available. * @enabled: PLCA configured mode (enabled/disabled). -1 = not available / don't * set. 0 = disabled, anything else = enabled. * @node_id: the PLCA local node identifier. -1 = not available / don't set. * Allowed values [0 .. 254]. 255 = node disabled. * @node_cnt: the PLCA node count (maximum number of nodes having a TO). Only * meaningful for the coordinator (node_id = 0). -1 = not available / don't * set. Allowed values [1 .. 255]. * @to_tmr: The value of the PLCA to_timer in bit-times, which determines the * PLCA transmit opportunity window opening. See IEEE802.3 Clause 148 for * more details. The to_timer shall be set equal over all nodes. * -1 = not available / don't set. Allowed values [0 .. 255]. * @burst_cnt: controls how many additional frames a node is allowed to send in * single transmit opportunity (TO). The default value of 0 means that the * node is allowed exactly one frame per TO. A value of 1 allows two frames * per TO, and so on. -1 = not available / don't set. * Allowed values [0 .. 255]. * @burst_tmr: controls how many bit times to wait for the MAC to send a new * frame before interrupting the burst. This value should be set to a value * greater than the MAC inter-packet gap (which is typically 96 bits). * -1 = not available / don't set. Allowed values [0 .. 255]. * * A structure containing configuration parameters for setting/getting the PLCA * RS configuration. The driver does not need to implement all the parameters, * but should report what is actually used. */ struct phy_plca_cfg { int version; int enabled; int node_id; int node_cnt; int to_tmr; int burst_cnt; int burst_tmr; }; /** * struct phy_plca_status - Status of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @pst: The PLCA status as reported by the PST bit in the PLCA STATUS * register(31.CA03), indicating BEACON activity. * * A structure containing status information of the PLCA RS configuration. * The driver does not need to implement all the parameters, but should report * what is actually used. */ struct phy_plca_status { bool pst; }; /* Modes for PHY LED configuration */ enum phy_led_modes { PHY_LED_ACTIVE_HIGH = 0, PHY_LED_ACTIVE_LOW = 1, PHY_LED_INACTIVE_HIGH_IMPEDANCE = 2, /* keep it last */ __PHY_LED_MODES_NUM, }; /** * struct phy_led: An LED driven by the PHY * * @list: List of LEDs * @phydev: PHY this LED is attached to * @led_cdev: Standard LED class structure * @index: Number of the LED */ struct phy_led { struct list_head list; struct phy_device *phydev; struct led_classdev led_cdev; u8 index; }; #define to_phy_led(d) container_of(d, struct phy_led, led_cdev) /** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices * @phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field * @name: The friendly name of this PHY type * @phy_id_mask: Defines the important bits of the phy_id * @features: A mandatory list of features (speed, duplex, etc) * supported by this PHY * @flags: A bitfield defining certain other features this PHY * supports (like interrupts) * @driver_data: Static driver data * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. * Note that none of these functions should be called from * interrupt time. The goal is for the bus read/write functions * to be able to block when the bus transaction is happening, * and be freed up by an interrupt (The MPC85xx has this ability, * though it is not currently supported in the driver). */ struct phy_driver { struct mdio_driver_common mdiodrv; u32 phy_id; char *name; u32 phy_id_mask; const unsigned long * const features; u32 flags; const void *driver_data; /** * @soft_reset: Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); /** * @config_init: Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); /** * @probe: Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); /** * @get_features: Probe the hardware to determine what * abilities it has. Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /** * @inband_caps: query whether in-band is supported for the given PHY * interface mode. Returns a bitmask of bits defined by enum * link_inband_signalling. */ unsigned int (*inband_caps)(struct phy_device *phydev, phy_interface_t interface); /** * @config_inband: configure in-band mode for the PHY */ int (*config_inband)(struct phy_device *phydev, unsigned int modes); /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine * whether to advertise lower-speed modes for that interface. It is * assumed that if a rate matching mode is supported on an interface, * then that interface's rate can be adapted to all slower link speeds * supported by the phy. If the interface is not supported, this should * return %RATE_MATCH_NONE. */ int (*get_rate_matching)(struct phy_device *phydev, phy_interface_t iface); /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); /** @resume: Resume the hardware, restoring state if needed */ int (*resume)(struct phy_device *phydev); /** * @config_aneg: Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); /** @aneg_done: Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); /** @read_status: Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); /** * @config_intr: Enables or disables interrupts. * It should also clear any pending interrupts prior to enabling the * IRQs and after disabling them. */ int (*config_intr)(struct phy_device *phydev); /** @handle_interrupt: Override default interrupt handling */ irqreturn_t (*handle_interrupt)(struct phy_device *phydev); /** @remove: Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); /** * @match_phy_device: Returns true if this is a suitable * driver for the given phydev. If NULL, matching is based on * phy_id and phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev); /** * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY * register changes to enable Wake on LAN, so set_wol is * provided to be called in the ethernet driver's set_wol * function. */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @get_wol: See set_wol, but for checking whether Wake on LAN * is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @link_change_notify: Called to inform a PHY device driver * when the core is about to change the link state. This * callback is supposed to be used as fixup hook for drivers * that need to take action when the link state * changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); /** * @read_mmd: PHY specific driver override for reading a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD read function * will be used by phy_read_mmd(), which will use either a * direct read for Clause 45 PHYs or an indirect read for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); /** * @write_mmd: PHY specific driver override for writing a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD write function * will be used by phy_write_mmd(), which will use either a * direct write for Clause 45 PHYs, or an indirect write for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); /** @read_page: Return the current PHY register page number */ int (*read_page)(struct phy_device *dev); /** @write_page: Set the current PHY register page number */ int (*write_page)(struct phy_device *dev, int page); /** * @module_info: Get the size and type of the eeprom contained * within a plug-in module */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); /** * @module_eeprom: Get the eeprom information from the plug-in * module */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); /** @cable_test_start: Start a cable test */ int (*cable_test_start)(struct phy_device *dev); /** @cable_test_tdr_start: Start a raw TDR cable test */ int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config); /** * @cable_test_get_status: Once per second, or on interrupt, * request the status of the test. */ int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ /** * @get_phy_stats: Retrieve PHY statistics. * @dev: The PHY device for which the statistics are retrieved. * @eth_stats: structure where Ethernet PHY stats will be stored. * @stats: structure where additional PHY-specific stats will be stored. * * Retrieves the supported PHY statistics and populates the provided * structures. The input structures are pre-initialized with * `ETHTOOL_STAT_NOT_SET`, and the driver must only modify members * corresponding to supported statistics. Unmodified members will remain * set to `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. */ void (*get_phy_stats)(struct phy_device *dev, struct ethtool_eth_phy_stats *eth_stats, struct ethtool_phy_stats *stats); /** * @get_link_stats: Retrieve link statistics. * @dev: The PHY device for which the statistics are retrieved. * @link_stats: structure where link-specific stats will be stored. * * Retrieves link-related statistics for the given PHY device. The input * structure is pre-initialized with `ETHTOOL_STAT_NOT_SET`, and the * driver must only modify members corresponding to supported * statistics. Unmodified members will remain set to * `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. */ void (*get_link_stats)(struct phy_device *dev, struct ethtool_link_ext_stats *link_stats); /** * @update_stats: Trigger periodic statistics updates. * @dev: The PHY device for which statistics updates are triggered. * * Periodically gathers statistics from the PHY device to update locally * maintained 64-bit counters. This is necessary for PHYs that implement * reduced-width counters (e.g., 16-bit or 32-bit) which can overflow * more frequently compared to 64-bit counters. By invoking this * callback, drivers can fetch the current counter values, handle * overflow detection, and accumulate the results into local 64-bit * counters for accurate reporting through the `get_phy_stats` and * `get_link_stats` interfaces. * * Return: 0 on success or a negative error code on failure. */ int (*update_stats)(struct phy_device *dev); /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ void (*get_strings)(struct phy_device *dev, u8 *data); /** @get_stats: Return the statistic counter values */ void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /* Get and Set PHY tunables */ /** @get_tunable: Return the value of a tunable */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); /** @set_tunable: Set the value of a tunable */ int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); /** @set_loopback: Set the loopback mood of the PHY */ int (*set_loopback)(struct phy_device *dev, bool enable); /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); /* PLCA RS interface */ /** @get_plca_cfg: Return the current PLCA configuration */ int (*get_plca_cfg)(struct phy_device *dev, struct phy_plca_cfg *plca_cfg); /** @set_plca_cfg: Set the PLCA configuration */ int (*set_plca_cfg)(struct phy_device *dev, const struct phy_plca_cfg *plca_cfg); /** @get_plca_status: Return the current PLCA status info */ int (*get_plca_status)(struct phy_device *dev, struct phy_plca_status *plca_st); /** * @led_brightness_set: Set a PHY LED brightness. Index * indicates which of the PHYs led should be set. Value * follows the standard LED class meaning, e.g. LED_OFF, * LED_HALF, LED_FULL. */ int (*led_brightness_set)(struct phy_device *dev, u8 index, enum led_brightness value); /** * @led_blink_set: Set a PHY LED blinking. Index indicates * which of the PHYs led should be configured to blink. Delays * are in milliseconds and if both are zero then a sensible * default should be chosen. The call should adjust the * timings in that case and if it can't match the values * specified exactly. */ int (*led_blink_set)(struct phy_device *dev, u8 index, unsigned long *delay_on, unsigned long *delay_off); /** * @led_hw_is_supported: Can the HW support the given rules. * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The core is interested in these rules * * Return 0 if yes, -EOPNOTSUPP if not, or an error code. */ int (*led_hw_is_supported)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_set: Set the HW to control the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The rules used to control the LED * * Returns 0, or a an error code. */ int (*led_hw_control_set)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_get: Get how the HW is controlling the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules Pointer to the rules used to control the LED * * Set *@rules to how the HW is currently blinking. Returns 0 * on success, or a error code if the current blinking cannot * be represented in rules, or some other error happens. */ int (*led_hw_control_get)(struct phy_device *dev, u8 index, unsigned long *rules); /** * @led_polarity_set: Set the LED polarity modes * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @modes: bitmap of LED polarity modes * * Configure LED with all the required polarity modes in @modes * to make it correctly turn ON or OFF. * * Returns 0, or an error code. */ int (*led_polarity_set)(struct phy_device *dev, int index, unsigned long modes); }; #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) /** * phy_id_compare - compare @id1 with @id2 taking account of @mask * @id1: first PHY ID * @id2: second PHY ID * @mask: the PHY ID mask, set bits are significant in matching * * Return true if the bits from @id1 and @id2 specified by @mask match. * This uses an equivalent test to (@id & @mask) == (@phy_id & @mask). */ static inline bool phy_id_compare(u32 id1, u32 id2, u32 mask) { return !((id1 ^ id2) & mask); } /** * phydev_id_compare - compare @id with the PHY's Clause 22 ID * @phydev: the PHY device * @id: the PHY ID to be matched * * Compare the @phydev clause 22 ID with the provided @id and return true or * false depending whether it matches, using the bound driver mask. The * @phydev must be bound to a driver. */ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) { return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); } /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; char bus_id[MII_BUS_ID_SIZE + 3]; u32 phy_uid; u32 phy_uid_mask; int (*run)(struct phy_device *phydev); }; const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value */ struct phy_setting { u32 speed; u8 duplex; u8 bit; }; const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); void of_set_phy_timing_role(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** * phy_set_eee_broken - Mark an EEE mode as broken so that it isn't advertised. * @phydev: The phy_device struct * @link_mode: The broken EEE mode */ static inline void phy_set_eee_broken(struct phy_device *phydev, u32 link_mode) { linkmode_set_bit(link_mode, phydev->eee_broken_modes); } /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { return phydev->state >= PHY_UP; } void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); void phy_check_downshift(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * The caller must have taken the MDIO bus lock. */ static inline int __phy_read(struct phy_device *phydev, u32 regnum) { return __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * The caller must have taken the MDIO bus lock. */ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set * * Returns negative errno, 0 if there was no change, and 1 in case of change */ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { return __mdiobus_modify_changed(phydev->mdio.bus, phydev->mdio.addr, regnum, mask, set); } /* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a * condition is met or a timeout occurs * * @phydev: The phy_device struct * @devaddr: The MMD to read from * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please * read usleep_range() function description for details and * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read_mmd, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, \ phydev, devaddr, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); /* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, 0, val); } /** * __phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, val, 0); } /** * phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set */ static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, 0, val); } /** * phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear */ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, val, 0); } /** * __phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * __phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set */ static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear */ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** * phy_polling_mode - Convenience function for testing whether polling is * used to detect PHY status changes * @phydev: the phy_device struct */ static inline bool phy_polling_mode(struct phy_device *phydev) { if (phydev->state == PHY_CABLETEST) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; if (phydev->drv->update_stats) return true; return phydev->irq == PHY_POLL; } /** * phy_has_hwtstamp - Tests whether a PHY time stamp configuration. * @phydev: the phy_device struct */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp; } /** * phy_has_rxtstamp - Tests whether a PHY supports receive time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_rxtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->rxtstamp; } /** * phy_has_tsinfo - Tests whether a PHY reports time stamping and/or * PTP hardware clock capabilities. * @phydev: the phy_device struct */ static inline bool phy_has_tsinfo(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->ts_info; } /** * phy_has_txtstamp - Tests whether a PHY supports transmit time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_txtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } static inline int phy_hwtstamp(struct phy_device *phydev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { return phydev->mii_ts->rxtstamp(phydev->mii_ts, skb, type); } static inline int phy_ts_info(struct phy_device *phydev, struct kernel_ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { phydev->mii_ts->txtstamp(phydev->mii_ts, skb, type); } /** * phy_is_default_hwtstamp - Is the PHY hwtstamp the default timestamp * @phydev: Pointer to phy_device * * This is used to get default timestamping device taking into account * the new API choice, which is selecting the timestamping from MAC by * default if the phydev does not have default_timestamp flag enabled. * * Return: True if phy is the default hw timestamp, false otherwise. */ static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) { return phy_has_hwtstamp(phydev) && phydev->default_timestamp; } /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ static inline bool phy_is_internal(struct phy_device *phydev) { return phydev->is_internal; } /** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ static inline bool phy_on_sfp(struct phy_device *phydev) { return phydev->is_on_sfp_module; } /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) * @mode: the &phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { return mode >= PHY_INTERFACE_MODE_RGMII && mode <= PHY_INTERFACE_MODE_RGMII_TXID; }; /** * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * * Returns true if the PHY interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) { return mode == PHY_INTERFACE_MODE_1000BASEX || mode == PHY_INTERFACE_MODE_2500BASEX; } /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phy_interface_mode_is_rgmii(phydev->interface); }; /** * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct */ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) { return phydev->is_pseudo_fixed_link; } int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) { return 0; } static inline struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) { return 0; } static inline struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) { return NULL; } static inline struct phy_device *device_phy_find_device(struct device *dev) { return NULL; } static inline struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) { return NULL; } static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { return NULL; } static inline int phy_device_register(struct phy_device *phy) { return 0; } static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); unsigned int phy_inband_caps(struct phy_device *phydev, phy_interface_t interface); int phy_config_inband(struct phy_device *phydev, unsigned int modes); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); bool phy_check_valid(int speed, int duplex, unsigned long *features); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } #endif static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); } #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_err_probe(_phydev, err, format, args...) \ dev_err_probe(&_phydev->mdio.dev, err, format, ##args) #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { return dev_name(&phydev->mdio.dev); } static inline void phy_lock_mdio_bus(struct phy_device *phydev) { mutex_lock(&phydev->mdio.bus->mdio_lock); } static inline void phy_unlock_mdio_bus(struct phy_device *phydev) { mutex_unlock(&phydev->mdio.bus->mdio_lock); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); char *phy_attached_info_irq(struct phy_device *phydev) __malloc; void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { return __genphy_config_aneg(phydev, false); } static inline int genphy_no_config_intr(struct phy_device *phydev) { return 0; } int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); /* Clause 37 */ int genphy_c37_config_aneg(struct phy_device *phydev); int genphy_c37_read_status(struct phy_device *phydev, bool *changed); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_c45_aneg_done(struct phy_device *phydev); int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); int genphy_c45_plca_get_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) return -EIO; if (phydev->drv->read_status) return phydev->drv->read_status(phydev); else return genphy_read_status(phydev); } void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_get_rate_matching(struct phy_device *phydev, phy_interface_t iface); void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_support_eee(struct phy_device *phydev); void phy_disable_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx); void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); int phy_eee_tx_clock_stop_capable(struct phy_device *phydev); int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); int of_phy_package_join(struct phy_device *phydev, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int base_addr, size_t priv_size); int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); void __phy_ethtool_get_phy_stats(struct phy_device *phydev, struct ethtool_eth_phy_stats *phy_stats, struct ethtool_phy_stats *phydev_stats); void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats); int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg, struct netlink_ext_ack *extack); int phy_ethtool_get_plca_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int __phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config); int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); static inline int phy_package_address(struct phy_device *phydev, unsigned int addr_offset) { struct phy_package_shared *shared = phydev->shared; u8 base_addr = shared->base_addr; if (addr_offset >= PHY_MAX_ADDR - base_addr) return -EIO; /* we know that addr will be in the range 0..31 and thus the * implicit cast to a signed int is not a problem. */ return base_addr + addr_offset; } static inline int phy_package_read(struct phy_device *phydev, unsigned int addr_offset, u32 regnum) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int __phy_package_read(struct phy_device *phydev, unsigned int addr_offset, u32 regnum) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return __mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int phy_package_write(struct phy_device *phydev, unsigned int addr_offset, u32 regnum, u16 val) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return mdiobus_write(phydev->mdio.bus, addr, regnum, val); } static inline int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset, u32 regnum, u16 val) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); } int __phy_package_read_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum); int phy_package_read_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum); int __phy_package_write_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum, u16 val); int phy_package_write_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum, u16 val); static inline bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { struct phy_package_shared *shared = phydev->shared; if (!shared) return false; return !test_and_set_bit(b, &shared->flags); } static inline bool phy_package_init_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); } static inline bool phy_package_probe_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } extern const struct bus_type mdio_bus_type; struct mdio_board_info { const char *bus_id; char modalias[MDIO_NAME_SIZE]; int mdio_addr; const void *platform_data; }; #if IS_ENABLED(CONFIG_MDIO_DEVICE) int mdiobus_register_board_info(const struct mdio_board_info *info, unsigned int n); #else static inline int mdiobus_register_board_info(const struct mdio_board_info *i, unsigned int n) { return 0; } #endif /** * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register * @__count: Numbers of members in array * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ { \ phy_drivers_unregister(__phy_drivers, __count); \ } \ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) bool phy_driver_is_genphy(struct phy_device *phydev); bool phy_driver_is_genphy_10g(struct phy_device *phydev); #endif /* __PHY_H */ |
| 6 6 6 6 6 6 6 5 1 3 1 3 1 4 6 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_route.c ROUTE4 classifier. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/dst.h> #include <net/route.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> /* * 1. For now we assume that route tags < 256. * It allows to use direct table lookups, instead of hash tables. * 2. For now we assume that "from TAG" and "fromdev DEV" statements * are mutually exclusive. * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" */ struct route4_fastmap { struct route4_filter *filter; u32 id; int iif; }; struct route4_head { struct route4_fastmap fastmap[16]; struct route4_bucket __rcu *table[256 + 1]; struct rcu_head rcu; }; struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ struct route4_filter __rcu *ht[16 + 16 + 1]; struct rcu_head rcu; }; struct route4_filter { struct route4_filter __rcu *next; u32 id; int iif; struct tcf_result res; struct tcf_exts exts; u32 handle; struct route4_bucket *bkt; struct tcf_proto *tp; struct rcu_work rwork; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) static inline int route4_fastmap_hash(u32 id, int iif) { return id & 0xF; } static DEFINE_SPINLOCK(fastmap_lock); static void route4_reset_fastmap(struct route4_head *head) { spin_lock_bh(&fastmap_lock); memset(head->fastmap, 0, sizeof(head->fastmap)); spin_unlock_bh(&fastmap_lock); } static void route4_set_fastmap(struct route4_head *head, u32 id, int iif, struct route4_filter *f) { int h = route4_fastmap_hash(id, iif); /* fastmap updates must look atomic to aling id, iff, filter */ spin_lock_bh(&fastmap_lock); head->fastmap[h].id = id; head->fastmap[h].iif = iif; head->fastmap[h].filter = f; spin_unlock_bh(&fastmap_lock); } static inline int route4_hash_to(u32 id) { return id & 0xFF; } static inline int route4_hash_from(u32 id) { return (id >> 16) & 0xF; } static inline int route4_hash_iif(int iif) { return 16 + ((iif >> 16) & 0xF); } static inline int route4_hash_wild(void) { return 32; } #define ROUTE4_APPLY_RESULT() \ { \ *res = f->res; \ if (tcf_exts_has_actions(&f->exts)) { \ int r = tcf_exts_exec(skb, &f->exts, res); \ if (r < 0) { \ dont_cache = 1; \ continue; \ } \ return r; \ } else if (!dont_cache) \ route4_set_fastmap(head, id, iif, f); \ return 0; \ } TC_INDIRECT_SCOPE int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct route4_head *head = rcu_dereference_bh(tp->root); struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; u32 id, h; int iif, dont_cache = 0; dst = skb_dst(skb); if (!dst) goto failure; id = dst->tclassid; iif = inet_iif(skb); h = route4_fastmap_hash(id, iif); spin_lock(&fastmap_lock); if (id == head->fastmap[h].id && iif == head->fastmap[h].iif && (f = head->fastmap[h].filter) != NULL) { if (f == ROUTE4_FAILURE) { spin_unlock(&fastmap_lock); goto failure; } *res = f->res; spin_unlock(&fastmap_lock); return 0; } spin_unlock(&fastmap_lock); h = route4_hash_to(id); restart: b = rcu_dereference_bh(head->table[h]); if (b) { for (f = rcu_dereference_bh(b->ht[route4_hash_from(id)]); f; f = rcu_dereference_bh(f->next)) if (f->id == id) ROUTE4_APPLY_RESULT(); for (f = rcu_dereference_bh(b->ht[route4_hash_iif(iif)]); f; f = rcu_dereference_bh(f->next)) if (f->iif == iif) ROUTE4_APPLY_RESULT(); for (f = rcu_dereference_bh(b->ht[route4_hash_wild()]); f; f = rcu_dereference_bh(f->next)) ROUTE4_APPLY_RESULT(); } if (h < 256) { h = 256; id &= ~0xFFFF; goto restart; } if (!dont_cache) route4_set_fastmap(head, id, iif, ROUTE4_FAILURE); failure: return -1; } static inline u32 to_hash(u32 id) { u32 h = id & 0xFF; if (id & 0x8000) h += 256; return h; } static inline u32 from_hash(u32 id) { id &= 0xFFFF; if (id == 0xFFFF) return 32; if (!(id & 0x8000)) { if (id > 255) return 256; return id & 0xF; } return 16 + (id & 0xF); } static void *route4_get(struct tcf_proto *tp, u32 handle) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_bucket *b; struct route4_filter *f; unsigned int h1, h2; h1 = to_hash(handle); if (h1 > 256) return NULL; h2 = from_hash(handle >> 16); if (h2 > 32) return NULL; b = rtnl_dereference(head->table[h1]); if (b) { for (f = rtnl_dereference(b->ht[h2]); f; f = rtnl_dereference(f->next)) if (f->handle == handle) return f; } return NULL; } static int route4_init(struct tcf_proto *tp) { struct route4_head *head; head = kzalloc(sizeof(struct route4_head), GFP_KERNEL); if (head == NULL) return -ENOBUFS; rcu_assign_pointer(tp->root, head); return 0; } static void __route4_delete_filter(struct route4_filter *f) { tcf_exts_destroy(&f->exts); tcf_exts_put_net(&f->exts); kfree(f); } static void route4_delete_filter_work(struct work_struct *work) { struct route4_filter *f = container_of(to_rcu_work(work), struct route4_filter, rwork); rtnl_lock(); __route4_delete_filter(f); rtnl_unlock(); } static void route4_queue_work(struct route4_filter *f) { tcf_queue_work(&f->rwork, route4_delete_filter_work); } static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; if (head == NULL) return; for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; b = rtnl_dereference(head->table[h1]); if (b) { for (h2 = 0; h2 <= 32; h2++) { struct route4_filter *f; while ((f = rtnl_dereference(b->ht[h2])) != NULL) { struct route4_filter *next; next = rtnl_dereference(f->next); RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); if (tcf_exts_get_net(&f->exts)) route4_queue_work(f); else __route4_delete_filter(f); } } RCU_INIT_POINTER(head->table[h1], NULL); kfree_rcu(b, rcu); } } kfree_rcu(head, rcu); } static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter *f = arg; struct route4_filter __rcu **fp; struct route4_filter *nf; struct route4_bucket *b; unsigned int h = 0; int i, h1; if (!head || !f) return -EINVAL; h = f->handle; b = f->bkt; fp = &b->ht[from_hash(h >> 16)]; for (nf = rtnl_dereference(*fp); nf; fp = &nf->next, nf = rtnl_dereference(*fp)) { if (nf == f) { /* unlink it */ RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); /* Remove any fastmap lookups that might ref filter * notice we unlink'd the filter so we can't get it * back in the fastmap. */ route4_reset_fastmap(head); /* Delete it */ tcf_unbind_filter(tp, &f->res); tcf_exts_get_net(&f->exts); tcf_queue_work(&f->rwork, route4_delete_filter_work); /* Strip RTNL protected tree */ for (i = 0; i <= 32; i++) { struct route4_filter *rt; rt = rtnl_dereference(b->ht[i]); if (rt) goto out; } /* OK, session has no flows */ RCU_INIT_POINTER(head->table[to_hash(h)], NULL); kfree_rcu(b, rcu); break; } } out: *last = true; for (h1 = 0; h1 <= 256; h1++) { if (rcu_access_pointer(head->table[h1])) { *last = false; break; } } return 0; } static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { [TCA_ROUTE4_CLASSID] = { .type = NLA_U32 }, [TCA_ROUTE4_TO] = NLA_POLICY_MAX(NLA_U32, 0xFF), [TCA_ROUTE4_FROM] = NLA_POLICY_MAX(NLA_U32, 0xFF), [TCA_ROUTE4_IIF] = NLA_POLICY_MAX(NLA_U32, 0x7FFF), }; static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, struct nlattr **tb, struct nlattr *est, int new, u32 flags, struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; unsigned int h1; struct route4_bucket *b; int err; err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; if (tb[TCA_ROUTE4_TO]) { if (new && handle & 0x8000) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } to = nla_get_u32(tb[TCA_ROUTE4_TO]); nhandle = to; } if (tb[TCA_ROUTE4_FROM] && tb[TCA_ROUTE4_IIF]) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_ROUTE4_FROM], "'from' and 'fromif' are mutually exclusive"); return -EINVAL; } if (tb[TCA_ROUTE4_FROM]) { id = nla_get_u32(tb[TCA_ROUTE4_FROM]); nhandle |= id << 16; } else if (tb[TCA_ROUTE4_IIF]) { id = nla_get_u32(tb[TCA_ROUTE4_IIF]); nhandle |= (id | 0x8000) << 16; } else nhandle |= 0xFFFF << 16; if (handle && new) { nhandle |= handle & 0x7F00; if (nhandle != handle) { NL_SET_ERR_MSG_FMT(extack, "Handle mismatch constructed: %x (expected: %x)", handle, nhandle); return -EINVAL; } } if (!nhandle) { NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid"); return -EINVAL; } h1 = to_hash(nhandle); b = rtnl_dereference(head->table[h1]); if (!b) { b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) return -ENOBUFS; rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) if (fp->handle == f->handle) return -EEXIST; } if (tb[TCA_ROUTE4_TO]) f->id = to; if (tb[TCA_ROUTE4_FROM]) f->id = to | id<<16; else if (tb[TCA_ROUTE4_IIF]) f->iif = id; f->handle = nhandle; f->bkt = b; f->tp = tp; if (tb[TCA_ROUTE4_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_ROUTE4_CLASSID]); tcf_bind_filter(tp, &f->res, base); } return 0; } static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, u32 flags, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; struct route4_filter *fold, *f1, *pfp, *f = NULL; struct route4_bucket *b; struct nlattr *tb[TCA_ROUTE4_MAX + 1]; unsigned int h, th; int err; bool new = true; if (!handle) { NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); return -EINVAL; } if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) { NL_SET_ERR_MSG_MOD(extack, "Missing options"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, tca[TCA_OPTIONS], route4_policy, NULL); if (err < 0) return err; fold = *arg; if (fold && fold->handle != handle) return -EINVAL; err = -ENOBUFS; f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL); if (!f) goto errout; err = tcf_exts_init(&f->exts, net, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); if (err < 0) goto errout; if (fold) { f->id = fold->id; f->iif = fold->iif; f->handle = fold->handle; f->tp = fold->tp; f->bkt = fold->bkt; new = false; } err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], new, flags, extack); if (err < 0) goto errout; h = from_hash(f->handle >> 16); fp = &f->bkt->ht[h]; for (pfp = rtnl_dereference(*fp); (f1 = rtnl_dereference(*fp)) != NULL; fp = &f1->next) if (f->handle < f1->handle) break; tcf_block_netif_keep_dst(tp->chain->block); rcu_assign_pointer(f->next, f1); rcu_assign_pointer(*fp, f); if (fold) { th = to_hash(fold->handle); h = from_hash(fold->handle >> 16); b = rtnl_dereference(head->table[th]); if (b) { fp = &b->ht[h]; for (pfp = rtnl_dereference(*fp); pfp; fp = &pfp->next, pfp = rtnl_dereference(*fp)) { if (pfp == fold) { rcu_assign_pointer(*fp, fold->next); break; } } } } route4_reset_fastmap(head); *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); tcf_queue_work(&fold->rwork, route4_delete_filter_work); } return 0; errout: if (f) tcf_exts_destroy(&f->exts); kfree(f); return err; } static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct route4_head *head = rtnl_dereference(tp->root); unsigned int h, h1; if (head == NULL || arg->stop) return; for (h = 0; h <= 256; h++) { struct route4_bucket *b = rtnl_dereference(head->table[h]); if (b) { for (h1 = 0; h1 <= 32; h1++) { struct route4_filter *f; for (f = rtnl_dereference(b->ht[h1]); f; f = rtnl_dereference(f->next)) { if (!tc_cls_stats_dump(tp, arg, f)) return; } } } } } static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct route4_filter *f = fh; struct nlattr *nest; u32 id; if (f == NULL) return skb->len; t->tcm_handle = f->handle; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (!(f->handle & 0x8000)) { id = f->id & 0xFF; if (nla_put_u32(skb, TCA_ROUTE4_TO, id)) goto nla_put_failure; } if (f->handle & 0x80000000) { if ((f->handle >> 16) != 0xFFFF && nla_put_u32(skb, TCA_ROUTE4_IIF, f->iif)) goto nla_put_failure; } else { id = f->id >> 16; if (nla_put_u32(skb, TCA_ROUTE4_FROM, id)) goto nla_put_failure; } if (f->res.classid && nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid)) goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q, unsigned long base) { struct route4_filter *f = fh; tc_cls_bind_class(classid, cl, q, &f->res, base); } static struct tcf_proto_ops cls_route4_ops __read_mostly = { .kind = "route", .classify = route4_classify, .init = route4_init, .destroy = route4_destroy, .get = route4_get, .change = route4_change, .delete = route4_delete, .walk = route4_walk, .dump = route4_dump, .bind_class = route4_bind_class, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_CLS("route"); static int __init init_route4(void) { return register_tcf_proto_ops(&cls_route4_ops); } static void __exit exit_route4(void) { unregister_tcf_proto_ops(&cls_route4_ops); } module_init(init_route4) module_exit(exit_route4) MODULE_DESCRIPTION("Routing table realm based TC classifier"); MODULE_LICENSE("GPL"); |
| 1542 1626 1541 1629 1068 2 2 1 11 11 2 116 115 115 115 116 116 6 7 7 7 7 2649 | 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <linux/cc_platform.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, SYNC_STATE_KICKED, SYNC_STATE_SHOULD_DIE, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE, SYNC_STATE_ONLINE, }; #ifdef CONFIG_HOTPLUG_CORE_SYNC /** * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown * @state: The synchronization state to set * * No synchronization point. Just update of the synchronization state, but implies * a full barrier so that the AP changes are visible before the control CPU proceeds. */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); (void)atomic_xchg(st, state); } void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, enum cpuhp_sync_state next_state) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); ktime_t now, end, start = ktime_get(); int sync; end = start + 10ULL * NSEC_PER_SEC; sync = atomic_read(st); while (1) { if (sync == state) { if (!atomic_try_cmpxchg(st, &sync, next_state)) continue; return true; } now = ktime_get(); if (now > end) { /* Timeout. Leave the state unchanged */ return false; } else if (now - start < NSEC_PER_MSEC) { /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); } sync = atomic_read(st); } return true; } #else /* CONFIG_HOTPLUG_CORE_SYNC */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD /** * cpuhp_ap_report_dead - Update synchronization state to DEAD * * No synchronization point. Just update of the synchronization state. */ void cpuhp_ap_report_dead(void) { cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); } void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } /* * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down * because the AP cannot issue complete() at this stage. */ static void cpuhp_bp_sync_dead(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); do { /* CPU can have reported dead already. Don't overwrite that! */ if (sync == SYNC_STATE_DEAD) break; } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { /* CPU reached dead state. Invoke the cleanup function */ arch_cpuhp_cleanup_dead_cpu(cpu); return; } /* No further action possible. Emit message and give up. */ pr_err("CPU%u failed to report dead state\n", cpu); } #else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL /** * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive * * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits * for the BP to release it. */ void cpuhp_ap_sync_alive(void) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); /* Wait for the control CPU to release it. */ while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) cpu_relax(); } static bool cpuhp_can_boot_ap(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); again: switch (sync) { case SYNC_STATE_DEAD: /* CPU is properly dead */ break; case SYNC_STATE_KICKED: /* CPU did not come up in previous attempt */ break; case SYNC_STATE_ALIVE: /* CPU is stuck cpuhp_ap_sync_alive(). */ break; default: /* CPU failed to report online or dead and is in limbo state. */ return false; } /* Prepare for booting */ if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) goto again; return true; } void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } /* * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up * because the AP cannot issue complete() so early in the bringup. */ static int cpuhp_bp_sync_alive(unsigned int cpu) { int ret = 0; if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) return 0; if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { pr_err("CPU%u failed to report alive state\n", cpu); ret = -EIO; } /* Let the architecture cleanup the kick alive mechanics. */ arch_cpuhp_cleanup_kick_cpu(cpu); return ret; } #else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); static bool cpu_hotplug_offline_disabled __ro_after_init; void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* Declare CPU offlining not supported */ void cpu_hotplug_disable_offlining(void) { cpu_maps_update_begin(); cpu_hotplug_offline_disabled = true; cpu_maps_update_done(); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; static unsigned int cpu_smt_max_threads __ro_after_init; unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_set_num_threads(unsigned int num_threads, unsigned int max_threads) { WARN_ON(!num_threads || (num_threads > max_threads)); if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; cpu_smt_max_threads = max_threads; /* * If SMT has been disabled via the kernel command line or SMT is * not supported, set cpu_smt_num_threads to 1 for consistency. * If enabled, take the architecture requested number of threads * to bring up into account. */ if (cpu_smt_control != CPU_SMT_ENABLED) cpu_smt_num_threads = 1; else if (num_threads < cpu_smt_num_threads) cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); /* * For Archicture supporting partial SMT states check if the thread is allowed. * Otherwise this has already been checked through cpu_smt_max_threads when * setting the SMT level. */ static inline bool cpu_smt_thread_allowed(unsigned int cpu) { #ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC return topology_smt_thread_allowed(cpu); #else return true; #endif } static inline bool cpu_bootable(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) return true; /* All CPUs are bootable if controls are not configured */ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) return true; /* All CPUs are bootable if CPU is not SMT capable */ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_bootable() check will now return false if this is not the * primary sibling. */ if (!cpu_bootable(cpu)) return -ECANCELED; return 0; } #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP static int cpuhp_kick_ap_alive(unsigned int cpu) { if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); } static int cpuhp_bringup_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * * Prevent irq alloc/free across the bringup by acquiring the * sparse irq lock. Hold it until the upcoming CPU completes the * startup in cpuhp_online_idle() which allows to avoid * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #endif static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * sched_force_init_mm() ensured the use of &init_mm, * drop that refcount now that the CPU has stopped. */ WARN_ON(mm != &init_mm); idle->active_mm = NULL; mmdrop_lazy_tlb(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; static __init void cpuhp_init_state(void) { struct cpuhp_cpu_state *st; int cpu; for_each_possible_cpu(cpu) { st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } } void __init cpuhp_threads_init(void) { cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); cpuhp_bp_sync_dead(cpu); lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function * waiting for its completion. */ rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); tick_assert_timekeeping_handover(); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); /* * Do post unplug cleanup. This is still protected against * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); arch_smt_update(); return ret; } struct cpu_down_work { unsigned int cpu; enum cpuhp_state target; }; static long __cpu_down_maps_locked(void *arg) { struct cpu_down_work *work = arg; return _cpu_down(work->cpu, 0, work->target); } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { struct cpu_down_work work = { .cpu = cpu, .target = target, }; /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ if (cpu_hotplug_offline_disabled) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; /* * Ensure that the control task does not run on the to be offlined * CPU to prevent a deadlock against cfs_b->period_timer. * Also keep at least one housekeeping cpu onlined to avoid generating * an empty sched_domain span. */ for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) { if (cpu != work.cpu) return work_on_cpu(cpu, __cpu_down_maps_locked, &work); } return -EBUSY; } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); /* * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, enum cpuhp_state target) { unsigned int cpu; for_each_cpu(cpu, mask) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); if (cpu_up(cpu, target) && can_rollback_cpu(st)) { /* * If this failed then cpu_up() might have only * rolled back to CPUHP_BP_KICK_AP for the final * online. Clean it up. NOOP if already rolled back. */ WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); } if (!--ncpus) break; } } #ifdef CONFIG_HOTPLUG_PARALLEL static bool __cpuhp_parallel_bringup __ro_after_init = true; static int __init parallel_bringup_parse_param(char *arg) { return kstrtobool(arg, &__cpuhp_parallel_bringup); } early_param("cpuhp.parallel", parallel_bringup_parse_param); #ifdef CONFIG_HOTPLUG_SMT static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } #else static inline bool cpuhp_smt_aware(void) { return false; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_none_mask; } #endif bool __weak arch_cpuhp_init_parallel_bringup(void) { return true; } /* * On architectures which have enabled parallel bringup this invokes all BP * prepare states for each of the to be onlined APs first. The last state * sends the startup IPI to the APs. The APs proceed through the low level * bringup code in parallel and then wait for the control CPU to release * them one by one for the final onlining procedure. * * This avoids waiting for each AP to respond to the startup IPI in * CPUHP_BRINGUP_CPU. */ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) { const struct cpumask *mask = cpu_present_mask; if (__cpuhp_parallel_bringup) __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); if (!__cpuhp_parallel_bringup) return false; if (cpuhp_smt_aware()) { const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); static struct cpumask tmp_mask __initdata; /* * X86 requires to prevent that SMT siblings stopped while * the primary thread does a microcode update for various * reasons. Bring the primary threads up first. */ cpumask_and(&tmp_mask, mask, pmask); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); /* Account for the online CPUs */ ncpus -= num_online_cpus(); if (!ncpus) return true; /* Create the mask for secondary CPUs */ cpumask_andnot(&tmp_mask, mask, pmask); mask = &tmp_mask; } /* Bring the not-yet started CPUs up */ cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); return true; } #else static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ void __init bringup_nonboot_cpus(unsigned int max_cpus) { if (!max_cpus) return; /* Try parallel bringup optimization if enabled */ if (cpuhp_bringup_cpus_parallel(max_cpus)) return; /* Full per CPU serialized bringup */ cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) { if (!cpu_online(cpu) || cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP /* * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until * the next step will release it. */ [CPUHP_BP_KICK_AP] = { .name = "cpu:kick_ap", .startup.single = cpuhp_kick_ap_alive, }, /* * Waits for the AP to reach cpuhp_ap_sync_alive() and then * releases it for the complete bringup. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = cpuhp_bringup_ap, .teardown.single = finish_cpu, .cant_stop = true, }, #else /* * All-in-one CPU bringup state which includes the kick alive. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, #endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = hrtimers_cpu_starting, .teardown.single = hrtimers_cpu_dying, }, [CPUHP_AP_TICK_DYING] = { .name = "tick:dying", .startup.single = NULL, .teardown.single = tick_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; /* * Disable can be called with CPU_SMT_ENABLED when changing * from a higher to lower number of SMT threads per core. */ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } /* Check if the core a CPU belongs to is online */ #if !defined(topology_is_core_online) static inline bool topology_is_core_online(unsigned int cpu) { return true; } #endif int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", }; #ifdef CONFIG_HOTPLUG_SMT static bool cpu_smt_num_threads_valid(unsigned int threads) { if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) return threads >= 1 && threads <= cpu_smt_max_threads; return threads == 1 || threads == cpu_smt_max_threads; } static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret, num_threads, orig_threads; bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; if (sysfs_streq(buf, "on")) { ctrlval = CPU_SMT_ENABLED; num_threads = cpu_smt_max_threads; } else if (sysfs_streq(buf, "off")) { ctrlval = CPU_SMT_DISABLED; num_threads = 1; } else if (sysfs_streq(buf, "forceoff")) { ctrlval = CPU_SMT_FORCE_DISABLED; num_threads = 1; } else if (kstrtoint(buf, 10, &num_threads) == 0) { if (num_threads == 1) ctrlval = CPU_SMT_DISABLED; else if (cpu_smt_num_threads_valid(num_threads)) ctrlval = CPU_SMT_ENABLED; else return -EINVAL; } else { return -EINVAL; } ret = lock_device_hotplug_sysfs(); if (ret) return ret; orig_threads = cpu_smt_num_threads; cpu_smt_num_threads = num_threads; force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; if (num_threads > orig_threads) ret = cpuhp_smt_enable(); else if (num_threads < orig_threads || force_off) ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; #ifdef CONFIG_HOTPLUG_SMT /* * If SMT is enabled but not all threads are enabled then show the * number of threads. If all threads are enabled show "on". Otherwise * show the state name. */ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_num_threads != cpu_smt_max_threads) return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", }; static int __init cpu_smt_sysfs_init(void) { struct device *dev_root; int ret = -ENODEV; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); put_device(dev_root); } return ret; } static int __init cpuhp_sysfs_init(void) { struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); put_device(dev_root); if (ret) return ret; } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_enabled_mask __read_mostly; EXPORT_SYMBOL(__cpu_enabled_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } #ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); #else static int __init mitigations_parse_cmdline(char *arg) { pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); return 0; } #endif early_param("mitigations", mitigations_parse_cmdline); |
| 2 1 8 8 8 7 2 4 7 6 1 4 1 1 4 1 5 3 5 3 4 5 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:net,port type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ /* 7 skbinfo support added */ #define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,port"); /* Type specific function prefix */ #define HTYPE hash_netport #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS /* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0 * However this way we have to store internally cidr - 1, * dancing back and forth. */ #define IP_SET_HASH_WITH_NETS_PACKED /* IPv4 variant */ /* Member elements */ struct hash_netport4_elem { __be32 ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport4_data_equal(const struct hash_netport4_elem *ip1, const struct hash_netport4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport4_do_data_match(const struct hash_netport4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport4_data_set_flags(struct hash_netport4_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport4_data_reset_flags(struct hash_netport4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr) { elem->ip &= ip_set_netmask(cidr); elem->cidr = cidr - 1; } static bool hash_netport4_data_list(struct sk_buff *skb, const struct hash_netport4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport4_data_next(struct hash_netport4_elem *next, const struct hash_netport4_elem *d) { next->ip = d->ip; next->port = d->port; } #define MTYPE hash_netport4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= ip_set_netmask(e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = port_to = ntohs(e.port); if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port_to < port) swap(port, port_to); } if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip_to < ip) swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } if (retried) { ip = ntohl(h->next.ip); p = ntohs(h->next.port); } else { p = port; } do { e.ip = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; for (; p <= port_to; p++, i++) { e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_netport4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } p = port; } while (ip++ < ip_to); return ret; } /* IPv6 variant */ struct hash_netport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport6_data_equal(const struct hash_netport6_elem *ip1, const struct hash_netport6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport6_do_data_match(const struct hash_netport6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport6_data_set_flags(struct hash_netport6_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport6_data_reset_flags(struct hash_netport6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip, cidr); elem->cidr = cidr - 1; } static bool hash_netport6_data_list(struct sk_buff *skb, const struct hash_netport6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport6_data_next(struct hash_netport6_elem *next, const struct hash_netport6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_netport6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6_netmask(&e.ip, e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } ip6_netmask(&e.ip, e.cidr + 1); e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_netport_type __read_mostly = { .name = "hash:net,port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_netport_init(void) { return ip_set_type_register(&hash_netport_type); } static void __exit hash_netport_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_netport_type); } module_init(hash_netport_init); module_exit(hash_netport_fini); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ELF_H #define _ASM_X86_ELF_H /* * ELF register definitions.. */ #include <linux/thread_info.h> #include <asm/ia32.h> #include <asm/ptrace.h> #include <asm/user.h> #include <asm/auxvec.h> #include <asm/fsgsbase.h> typedef unsigned long elf_greg_t; #define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t)) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef struct user_i387_struct elf_fpregset_t; #ifdef __i386__ #define R_386_NONE 0 #define R_386_32 1 #define R_386_PC32 2 #define R_386_GOT32 3 #define R_386_PLT32 4 #define R_386_COPY 5 #define R_386_GLOB_DAT 6 #define R_386_JMP_SLOT 7 #define R_386_RELATIVE 8 #define R_386_GOTOFF 9 #define R_386_GOTPC 10 #define R_386_NUM 11 /* * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2LSB #define ELF_ARCH EM_386 #else /* x86-64 relocation types */ #define R_X86_64_NONE 0 /* No reloc */ #define R_X86_64_64 1 /* Direct 64 bit */ #define R_X86_64_PC32 2 /* PC relative 32 bit signed */ #define R_X86_64_GOT32 3 /* 32 bit GOT entry */ #define R_X86_64_PLT32 4 /* 32 bit PLT address */ #define R_X86_64_COPY 5 /* Copy symbol at runtime */ #define R_X86_64_GLOB_DAT 6 /* Create GOT entry */ #define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */ #define R_X86_64_RELATIVE 8 /* Adjust by program base */ #define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative offset to GOT */ #define R_X86_64_32 10 /* Direct 32 bit zero extended */ #define R_X86_64_32S 11 /* Direct 32 bit sign extended */ #define R_X86_64_16 12 /* Direct 16 bit zero extended */ #define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */ #define R_X86_64_8 14 /* Direct 8 bit sign extended */ #define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */ #define R_X86_64_PC64 24 /* Place relative 64-bit signed */ /* * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS64 #define ELF_DATA ELFDATA2LSB #define ELF_ARCH EM_X86_64 #endif #include <asm/vdso.h> #ifdef CONFIG_X86_64 extern unsigned int vdso64_enabled; #endif #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) extern unsigned int vdso32_enabled; #endif /* * This is used to ensure we don't load something for the wrong architecture. */ #define elf_check_arch_ia32(x) \ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include <asm/processor.h> #ifdef CONFIG_X86_32 #include <asm/desc.h> #define elf_check_arch(x) elf_check_arch_ia32(x) /* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx contains a pointer to a function which might be registered using `atexit'. This provides a mean for the dynamic linker to call DT_FINI functions for shared libraries that have been loaded before the code runs. A value of 0 tells we have no such handler. We might as well make sure everything else is cleared too (except for %esp), just to make things more deterministic. */ #define ELF_PLAT_INIT(_r, load_addr) \ do { \ _r->bx = 0; _r->cx = 0; _r->dx = 0; \ _r->si = 0; _r->di = 0; _r->bp = 0; \ _r->ax = 0; \ } while (0) /* * regs is struct pt_regs, pr_reg is elf_gregset_t (which is * now struct_user_regs, they are different) */ #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ pr_reg[0] = regs->bx; \ pr_reg[1] = regs->cx; \ pr_reg[2] = regs->dx; \ pr_reg[3] = regs->si; \ pr_reg[4] = regs->di; \ pr_reg[5] = regs->bp; \ pr_reg[6] = regs->ax; \ pr_reg[7] = regs->ds; \ pr_reg[8] = regs->es; \ pr_reg[9] = regs->fs; \ savesegment(gs, pr_reg[10]); \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ pr_reg[13] = regs->cs; \ pr_reg[14] = regs->flags; \ pr_reg[15] = regs->sp; \ pr_reg[16] = regs->ss; \ } while (0); #define ELF_PLATFORM (utsname()->machine) #define set_personality_64bit() do { } while (0) #else /* CONFIG_X86_32 */ /* * This is used to ensure we don't load something for the wrong architecture. */ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) #define compat_elf_check_arch(x) \ ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { /* ax gets execve's return value. */ /*regs->ax = */ regs->bx = regs->cx = regs->dx = 0; regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; t->fsbase = t->gsbase = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; } #define ELF_PLAT_INIT(_r, load_addr) \ elf_common_init(¤t->thread, _r, 0) #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32); #define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ compat_start_thread(regs, new_ip, new_sp, ex->e_machine == EM_X86_64) void set_personality_ia32(bool); #define COMPAT_SET_PERSONALITY(ex) \ set_personality_ia32((ex).e_machine == EM_X86_64) #define COMPAT_ELF_PLATFORM ("i686") /* * regs is struct pt_regs, pr_reg is elf_gregset_t (which is * now struct_user_regs, they are different). Assumes current is the process * getting dumped. */ #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ unsigned v; \ (pr_reg)[0] = (regs)->r15; \ (pr_reg)[1] = (regs)->r14; \ (pr_reg)[2] = (regs)->r13; \ (pr_reg)[3] = (regs)->r12; \ (pr_reg)[4] = (regs)->bp; \ (pr_reg)[5] = (regs)->bx; \ (pr_reg)[6] = (regs)->r11; \ (pr_reg)[7] = (regs)->r10; \ (pr_reg)[8] = (regs)->r9; \ (pr_reg)[9] = (regs)->r8; \ (pr_reg)[10] = (regs)->ax; \ (pr_reg)[11] = (regs)->cx; \ (pr_reg)[12] = (regs)->dx; \ (pr_reg)[13] = (regs)->si; \ (pr_reg)[14] = (regs)->di; \ (pr_reg)[15] = (regs)->orig_ax; \ (pr_reg)[16] = (regs)->ip; \ (pr_reg)[17] = (regs)->cs; \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ (pr_reg)[21] = x86_fsbase_read_cpu(); \ (pr_reg)[22] = x86_gsbase_read_cpu_inactive(); \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ asm("movl %%gs,%0" : "=r" (v)); (pr_reg)[26] = v; \ } while (0); /* I'm not sure if we can use '-' here */ #define ELF_PLATFORM ("x86_64") extern void set_personality_64bit(void); extern int force_personality32; #endif /* !CONFIG_X86_32 */ #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 /* * This is the base location for PIE (ET_DYN with INTERP) loads. On * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ (DEFAULT_MAP_WINDOW / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, but it's not easy, and we've already done it here. */ #define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) extern u32 elf_hwcap2; /* * HWCAP2 supplies mask with kernel enabled CPU features, so that * the application can discover that it can safely use them. * The bits are defined in uapi/asm/hwcap2.h. */ #define ELF_HWCAP2 (elf_hwcap2) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. For the moment, we have only optimizations for the Intel generations, but that could change... */ #define SET_PERSONALITY(ex) set_personality_64bit() /* * An executable for which elf_read_implies_exec() returns TRUE will * have the READ_IMPLIES_EXEC personality flag set automatically. * * The decision process for determining the results are: * * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 | * ELF: | | | | * ---------------------|------------|------------------|----------------| * missing PT_GNU_STACK | exec-all | exec-all | exec-none | * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack | * PT_GNU_STACK == RW | exec-none | exec-none | exec-none | * * exec-all : all PROT_READ user mappings are executable, except when * backed by files on a noexec-filesystem. * exec-none : only PROT_EXEC user mappings are executable. * exec-stack: only the stack and PROT_EXEC user mappings are executable. * * *this column has no architectural effect: NX markings are ignored by * hardware, but may have behavioral effects when "wants X" collides with * "cannot be X" constraints in memory permission flags, as in * https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com * */ #define elf_read_implies_exec(ex, executable_stack) \ (mmap_is_ia32() && executable_stack == EXSTACK_DEFAULT) struct task_struct; #define ARCH_DLINFO_IA32 \ do { \ if (VDSO_CURRENT_BASE) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* * True on X86_32 or when emulating IA32 on X86_64 */ static inline int mmap_is_ia32(void) { return IS_ENABLED(CONFIG_X86_32) || (IS_ENABLED(CONFIG_COMPAT) && test_thread_flag(TIF_ADDR32)); } extern unsigned long task_size_32bit(void); extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); extern unsigned long get_sigframe_size(void); #ifdef CONFIG_X86_32 #define __STACK_RND_MASK(is32bit) (0x7ff) #define STACK_RND_MASK (0x7ff) #define ARCH_DLINFO ARCH_DLINFO_IA32 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #else /* CONFIG_X86_32 */ /* 1GB for 64bit, 8MB for 32bit */ #define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) #define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) #define ARCH_DLINFO \ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ #define ARCH_DLINFO_X32 \ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) #define AT_SYSINFO 32 #define COMPAT_ARCH_DLINFO \ if (exec->e_machine == EM_X86_64) \ ARCH_DLINFO_X32; \ else if (IS_ENABLED(CONFIG_IA32_EMULATION)) \ ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) #endif /* !CONFIG_X86_32 */ #define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) #define VDSO_ENTRY \ ((unsigned long)current->mm->context.vdso + \ vdso_image_32.sym___kernel_vsyscall) struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp, bool x32); #define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ compat_arch_setup_additional_pages(bprm, interpreter, \ (ex->e_machine == EM_X86_64)) extern bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs); /* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), ALIGN_VA_64 = BIT(1), }; struct va_alignment { int flags; unsigned long mask; unsigned long bits; } ____cacheline_aligned; extern struct va_alignment va_align; #endif /* _ASM_X86_ELF_H */ |
| 4 3 8 46 44 2 71 1 1 72 1 1 1 1 72 70 2 8 3 6 1 16 6 1 16 1 1 2 81 82 1 42 40 59 25 25 59 25 45 3 1 1 70 72 24 53 71 72 17 60 72 83 4 1 70 36 65 35 81 4 70 36 65 37 84 84 2 1 1 2 2 2 8 2 1 8 2 8 8 6 64 7 6 2 8 5 8 84 84 44 44 40 41 76 6 84 84 6 78 84 81 1 2 84 84 84 84 6 2 2 79 68 37 84 3 3 84 83 1 78 6 3 3 81 41 72 7 73 66 39 78 8 73 73 72 73 73 73 84 79 72 65 50 43 50 13 7 6 72 69 21 15 3 17 17 21 21 72 46 12 12 12 39 35 6 6 11 72 72 72 71 6 66 68 14 72 35 37 14 2 3 3 2 2 4 4 4 4 34 34 34 44 2 3 2 4 34 45 3 29 13 41 38 2 31 10 29 12 37 2 2 39 2 39 2 38 3 39 2 39 2 39 2 39 2 37 3 1 37 3 1 38 3 38 3 35 2 4 36 5 41 5 5 31 42 1 40 42 42 42 42 42 2 39 42 42 1 41 1 2 1 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 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* COMMON Applications Kept Enhanced (CAKE) discipline * * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com> * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk> * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com> * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de> * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au> * * The CAKE Principles: * (or, how to have your cake and eat it too) * * This is a combination of several shaping, AQM and FQ techniques into one * easy-to-use package: * * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), * eliminating the need for any sort of burst parameter (eg. token bucket * depth). Burst support is limited to that necessary to overcome scheduling * latency. * * - A Diffserv-aware priority queue, giving more priority to certain classes, * up to a specified fraction of bandwidth. Above that bandwidth threshold, * the priority is reduced to avoid starving other tins. * * - Each priority tin has a separate Flow Queue system, to isolate traffic * flows from each other. This prevents a burst on one flow from increasing * the delay to another. Flows are distributed to queues using a * set-associative hash function. * * - Each queue is actively managed by Cobalt, which is a combination of the * Codel and Blue AQM algorithms. This serves flows fairly, and signals * congestion early via ECN (if available) and/or packet drops, to keep * latency low. The codel parameters are auto-tuned based on the bandwidth * setting, as is necessary at low bandwidths. * * The configuration parameters are kept deliberately simple for ease of use. * Everything has sane defaults. Complete generality of configuration is *not* * a goal. * * The priority queue operates according to a weighted DRR scheme, combined with * a bandwidth tracker which reuses the shaper logic to detect which side of the * bandwidth sharing threshold the tin is operating. This determines whether a * priority-based weight (high) or a bandwidth-based weight (low) is used for * that tin in the current pass. * * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly * granted us permission to leverage. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> #include <linux/if_vlan.h> #include <net/gso.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/flow_dissector.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif #define CAKE_SET_WAYS (8) #define CAKE_MAX_TINS (8) #define CAKE_QUEUES (1024) #define CAKE_FLOW_MASK 63 #define CAKE_FLOW_NAT_FLAG 64 /* struct cobalt_params - contains codel and blue parameters * @interval: codel initial drop rate * @target: maximum persistent sojourn time & blue update rate * @mtu_time: serialisation delay of maximum-size packet * @p_inc: increment of blue drop probability (0.32 fxp) * @p_dec: decrement of blue drop probability (0.32 fxp) */ struct cobalt_params { u64 interval; u64 target; u64 mtu_time; u32 p_inc; u32 p_dec; }; /* struct cobalt_vars - contains codel and blue variables * @count: codel dropping frequency * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 * @drop_next: time to drop next packet, or when we dropped last * @blue_timer: Blue time to next drop * @p_drop: BLUE drop probability (0.32 fxp) * @dropping: set if in dropping state * @ecn_marked: set if marked */ struct cobalt_vars { u32 count; u32 rec_inv_sqrt; ktime_t drop_next; ktime_t blue_timer; u32 p_drop; bool dropping; bool ecn_marked; }; enum { CAKE_SET_NONE = 0, CAKE_SET_SPARSE, CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ CAKE_SET_BULK, CAKE_SET_DECAYING }; struct cake_flow { /* this stuff is all needed per-flow at dequeue time */ struct sk_buff *head; struct sk_buff *tail; struct list_head flowchain; s32 deficit; u32 dropped; struct cobalt_vars cvars; u16 srchost; /* index into cake_host table */ u16 dsthost; u8 set; }; /* please try to keep this structure <= 64 bytes */ struct cake_host { u32 srchost_tag; u32 dsthost_tag; u16 srchost_bulk_flow_count; u16 dsthost_bulk_flow_count; }; struct cake_heap_entry { u16 t:3, b:10; }; struct cake_tin_data { struct cake_flow flows[CAKE_QUEUES]; u32 backlogs[CAKE_QUEUES]; u32 tags[CAKE_QUEUES]; /* for set association */ u16 overflow_idx[CAKE_QUEUES]; struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ u16 flow_quantum; struct cobalt_params cparams; u32 drop_overlimit; u16 bulk_flow_count; u16 sparse_flow_count; u16 decaying_flow_count; u16 unresponsive_flow_count; u32 max_skblen; struct list_head new_flows; struct list_head old_flows; struct list_head decaying_flows; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ ktime_t time_next_packet; u64 tin_rate_ns; u64 tin_rate_bps; u16 tin_rate_shft; u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; u32 tin_ecn_mark; u32 packets; u64 bytes; u32 ack_drops; /* moving averages */ u64 avge_delay; u64 peak_delay; u64 base_delay; /* hash function stats */ u32 way_directs; u32 way_hits; u32 way_misses; u32 way_collisions; }; /* number of tins is small, so size of this struct doesn't matter much */ struct cake_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ struct tcf_block *block; struct cake_tin_data *tins; struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; u16 overflow_timeout; u16 tin_cnt; u8 tin_mode; u8 flow_mode; u8 ack_filter; u8 atm_mode; u32 fwmark_mask; u16 fwmark_shft; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ u16 rate_shft; ktime_t time_next_packet; ktime_t failsafe_next_packet; u64 rate_ns; u64 rate_bps; u16 rate_flags; s16 rate_overhead; u16 rate_mpu; u64 interval; u64 target; /* resource tracking */ u32 buffer_used; u32 buffer_max_used; u32 buffer_limit; u32 buffer_config_limit; /* indices for dequeue */ u16 cur_tin; u16 cur_flow; struct qdisc_watchdog watchdog; const u8 *tin_index; const u8 *tin_order; /* bandwidth capacity estimate */ ktime_t last_packet_time; ktime_t avg_window_begin; u64 avg_packet_interval; u64 avg_window_bytes; u64 avg_peak_bandwidth; ktime_t last_reconfig_time; /* packet length stats */ u32 avg_netoff; u16 max_netlen; u16 max_adjlen; u16 min_netlen; u16 min_adjlen; }; enum { CAKE_FLAG_OVERHEAD = BIT(0), CAKE_FLAG_AUTORATE_INGRESS = BIT(1), CAKE_FLAG_INGRESS = BIT(2), CAKE_FLAG_WASH = BIT(3), CAKE_FLAG_SPLIT_GSO = BIT(4) }; /* COBALT operates the Codel and BLUE algorithms in parallel, in order to * obtain the best features of each. Codel is excellent on flows which * respond to congestion signals in a TCP-like way. BLUE is more effective on * unresponsive flows. */ struct cobalt_skb_cb { ktime_t enqueue_time; u32 adjusted_len; }; static u64 us_to_ns(u64 us) { return us * NSEC_PER_USEC; } static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; } static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) { return get_cobalt_cb(skb)->enqueue_time; } static void cobalt_set_enqueue_time(struct sk_buff *skb, ktime_t now) { get_cobalt_cb(skb)->enqueue_time = now; } static u16 quantum_div[CAKE_QUEUES + 1] = {0}; /* Diffserv lookup tables */ static const u8 precedence[] = { 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, }; static const u8 diffserv8[] = { 2, 0, 1, 2, 4, 2, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 5, 2, 4, 2, 4, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 6, 2, 3, 2, 3, 2, 3, 2, 6, 2, 2, 2, 6, 2, 6, 2, 7, 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 2, 2, 2, 2, 2, }; static const u8 diffserv4[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 3, 0, 2, 0, 2, 0, 2, 0, 3, 0, 0, 0, 3, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, }; static const u8 diffserv3[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, }; static const u8 besteffort[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, }; /* tin priority order for stats dumping */ static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7}; static const u8 bulk_order[] = {1, 0, 2, 3}; /* There is a big difference in timing between the accurate values placed in the * cache and the approximations given by a single Newton step for small count * values, particularly when stepping from count 1 to 2 or vice versa. Hence, * these values are calculated using eight Newton steps, using the * implementation below. Above 16, a single Newton step gives sufficient * accuracy in either direction, given the precision stored. * * The magnitude of the error when stepping up to count 2 is such as to give the * value that *should* have been produced at count 4. */ #define REC_INV_SQRT_CACHE (16) static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { ~0, ~0, 3037000500, 2479700525, 2147483647, 1920767767, 1753413056, 1623345051, 1518500250, 1431655765, 1358187914, 1294981364, 1239850263, 1191209601, 1147878294, 1108955788 }; /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ static void cobalt_newton_step(struct cobalt_vars *vars) { u32 invsqrt, invsqrt2; u64 val; invsqrt = vars->rec_inv_sqrt; invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; val = (3LL << 32) - ((u64)vars->count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); vars->rec_inv_sqrt = val; } static void cobalt_invsqrt(struct cobalt_vars *vars) { if (vars->count < REC_INV_SQRT_CACHE) vars->rec_inv_sqrt = inv_sqrt_cache[vars->count]; else cobalt_newton_step(vars); } static void cobalt_vars_init(struct cobalt_vars *vars) { memset(vars, 0, sizeof(*vars)); } /* CoDel control_law is t + interval/sqrt(count) * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid * both sqrt() and divide operation. */ static ktime_t cobalt_control(ktime_t t, u64 interval, u32 rec_inv_sqrt) { return ktime_add_ns(t, reciprocal_scale(interval, rec_inv_sqrt)); } /* Call this when a packet had to be dropped due to queue overflow. Returns * true if the BLUE state was quiescent before but active after this call. */ static bool cobalt_queue_full(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool up = false; if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { up = !vars->p_drop; vars->p_drop += p->p_inc; if (vars->p_drop < p->p_inc) vars->p_drop = ~0; vars->blue_timer = now; } vars->dropping = true; vars->drop_next = now; if (!vars->count) vars->count = 1; return up; } /* Call this when the queue was serviced but turned out to be empty. Returns * true if the BLUE state was active before but quiescent after this call. */ static bool cobalt_queue_empty(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool down = false; if (vars->p_drop && ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { if (vars->p_drop < p->p_dec) vars->p_drop = 0; else vars->p_drop -= p->p_dec; vars->blue_timer = now; down = !vars->p_drop; } vars->dropping = false; if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); } return down; } /* Call this with a freshly dequeued packet for possible congestion marking. * Returns true as an instruction to drop the packet, false for delivery. */ static enum skb_drop_reason cobalt_should_drop(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now, struct sk_buff *skb, u32 bulk_flows) { enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; bool next_due, over_target; ktime_t schedule; u64 sojourn; /* The 'schedule' variable records, in its sign, whether 'now' is before or * after 'drop_next'. This allows 'drop_next' to be updated before the next * scheduling decision is actually branched, without destroying that * information. Similarly, the first 'schedule' value calculated is preserved * in the boolean 'next_due'. * * As for 'drop_next', we take advantage of the fact that 'interval' is both * the delay between first exceeding 'target' and the first signalling event, * *and* the scaling factor for the signalling frequency. It's therefore very * natural to use a single mechanism for both purposes, and eliminates a * significant amount of reference Codel's spaghetti code. To help with this, * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close * as possible to 1.0 in fixed-point. */ sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); schedule = ktime_sub(now, vars->drop_next); over_target = sojourn > p->target && sojourn > p->mtu_time * bulk_flows * 2 && sojourn > p->mtu_time * 4; next_due = vars->count && ktime_to_ns(schedule) >= 0; vars->ecn_marked = false; if (over_target) { if (!vars->dropping) { vars->dropping = true; vars->drop_next = cobalt_control(now, p->interval, vars->rec_inv_sqrt); } if (!vars->count) vars->count = 1; } else if (vars->dropping) { vars->dropping = false; } if (next_due && vars->dropping) { /* Use ECN mark if possible, otherwise drop */ if (!(vars->ecn_marked = INET_ECN_set_ce(skb))) reason = SKB_DROP_REASON_QDISC_CONGESTED; vars->count++; if (!vars->count) vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); } else { while (next_due) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); next_due = vars->count && ktime_to_ns(schedule) >= 0; } } /* Simple BLUE implementation. Lack of ECN is deliberate. */ if (vars->p_drop && reason == SKB_NOT_DROPPED_YET && get_random_u32() < vars->p_drop) reason = SKB_DROP_REASON_CAKE_FLOOD; /* Overload the drop_next field as an activity timeout */ if (!vars->count) vars->drop_next = ktime_add_ns(now, p->interval); else if (ktime_to_ns(schedule) > 0 && reason == SKB_NOT_DROPPED_YET) vars->drop_next = now; return reason; } static bool cake_update_flowkeys(struct flow_keys *keys, const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct, upd = false; __be32 ip; if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) return false; ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip; if (ip != keys->addrs.v4addrs.src) { keys->addrs.v4addrs.src = ip; upd = true; } ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip; if (ip != keys->addrs.v4addrs.dst) { keys->addrs.v4addrs.dst = ip; upd = true; } if (keys->ports.ports) { __be16 port; port = rev ? tuple.dst.u.all : tuple.src.u.all; if (port != keys->ports.src) { keys->ports.src = port; upd = true; } port = rev ? tuple.src.u.all : tuple.dst.u.all; if (port != keys->ports.dst) { port = keys->ports.dst; upd = true; } } return upd; #else return false; #endif } /* Cake has several subtle multiple bit settings. In these cases you * would be matching triple isolate mode as well. */ static bool cake_dsrc(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC; } static bool cake_ddst(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; } static void cake_dec_srchost_bulk_flow_count(struct cake_tin_data *q, struct cake_flow *flow, int flow_mode) { if (likely(cake_dsrc(flow_mode) && q->hosts[flow->srchost].srchost_bulk_flow_count)) q->hosts[flow->srchost].srchost_bulk_flow_count--; } static void cake_inc_srchost_bulk_flow_count(struct cake_tin_data *q, struct cake_flow *flow, int flow_mode) { if (likely(cake_dsrc(flow_mode) && q->hosts[flow->srchost].srchost_bulk_flow_count < CAKE_QUEUES)) q->hosts[flow->srchost].srchost_bulk_flow_count++; } static void cake_dec_dsthost_bulk_flow_count(struct cake_tin_data *q, struct cake_flow *flow, int flow_mode) { if (likely(cake_ddst(flow_mode) && q->hosts[flow->dsthost].dsthost_bulk_flow_count)) q->hosts[flow->dsthost].dsthost_bulk_flow_count--; } static void cake_inc_dsthost_bulk_flow_count(struct cake_tin_data *q, struct cake_flow *flow, int flow_mode) { if (likely(cake_ddst(flow_mode) && q->hosts[flow->dsthost].dsthost_bulk_flow_count < CAKE_QUEUES)) q->hosts[flow->dsthost].dsthost_bulk_flow_count++; } static u16 cake_get_flow_quantum(struct cake_tin_data *q, struct cake_flow *flow, int flow_mode) { u16 host_load = 1; if (cake_dsrc(flow_mode)) host_load = max(host_load, q->hosts[flow->srchost].srchost_bulk_flow_count); if (cake_ddst(flow_mode)) host_load = max(host_load, q->hosts[flow->dsthost].dsthost_bulk_flow_count); /* The get_random_u16() is a way to apply dithering to avoid * accumulating roundoff errors */ return (q->flow_quantum * quantum_div[host_load] + get_random_u16()) >> 16; } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode, u16 flow_override, u16 host_override) { bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS)); bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS)); bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG); u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; bool use_skbhash = skb->l4_hash; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; /* If both overrides are set, or we can use the SKB hash and nat mode is * disabled, we can skip packet dissection entirely. If nat mode is * enabled there's another check below after doing the conntrack lookup. */ if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts) goto skip_hash; skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); /* Don't use the SKB hash if we change the lookup keys from conntrack */ if (nat_enabled && cake_update_flowkeys(&keys, skb)) use_skbhash = false; /* If we can still use the SKB hash and don't need the host hash, we can * skip the rest of the hashing procedure */ if (use_skbhash && !hash_hosts) goto skip_hash; /* flow_hash_from_keys() sorts the addresses by value, so we have * to preserve their order in a separate data structure to treat * src and dst host addresses as independently selectable. */ host_keys = keys; host_keys.ports.ports = 0; host_keys.basic.ip_proto = 0; host_keys.keyid.keyid = 0; host_keys.tags.flow_label = 0; switch (host_keys.control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: host_keys.addrs.v4addrs.src = 0; dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; host_keys.addrs.v4addrs.dst = 0; srchost_hash = flow_hash_from_keys(&host_keys); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: memset(&host_keys.addrs.v6addrs.src, 0, sizeof(host_keys.addrs.v6addrs.src)); dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; memset(&host_keys.addrs.v6addrs.dst, 0, sizeof(host_keys.addrs.v6addrs.dst)); srchost_hash = flow_hash_from_keys(&host_keys); break; default: dsthost_hash = 0; srchost_hash = 0; } /* This *must* be after the above switch, since as a * side-effect it sorts the src and dst addresses. */ if (hash_flows && !use_skbhash) flow_hash = flow_hash_from_keys(&keys); skip_hash: if (flow_override) flow_hash = flow_override - 1; else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; srchost_hash = host_override - 1; } if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; if (flow_mode & CAKE_FLOW_DST_IP) flow_hash ^= dsthost_hash; } reduced_hash = flow_hash % CAKE_QUEUES; /* set-associative hashing */ /* fast path if no hash collision (direct lookup succeeds) */ if (likely(q->tags[reduced_hash] == flow_hash && q->flows[reduced_hash].set)) { q->way_directs++; } else { u32 inner_hash = reduced_hash % CAKE_SET_WAYS; u32 outer_hash = reduced_hash - inner_hash; bool allocate_src = false; bool allocate_dst = false; u32 i, k; /* check if any active queue in the set is reserved for * this flow. */ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->tags[outer_hash + k] == flow_hash) { if (i) q->way_hits++; if (!q->flows[outer_hash + k].set) { /* need to increment host refcnts */ allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); } goto found; } } /* no queue is reserved for this flow, look for an * empty one. */ for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->flows[outer_hash + k].set) { q->way_misses++; allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); goto found; } } /* With no empty queues, default to the original * queue, accept the collision, update the host tags. */ q->way_collisions++; allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { cake_dec_srchost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); cake_dec_dsthost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); } found: /* reserve queue for future packets in same flow */ reduced_hash = outer_hash + k; q->tags[reduced_hash] = flow_hash; if (allocate_src) { srchost_idx = srchost_hash % CAKE_QUEUES; inner_hash = srchost_idx % CAKE_SET_WAYS; outer_hash = srchost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].srchost_tag == srchost_hash) goto found_src; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].srchost_bulk_flow_count) break; } q->hosts[outer_hash + k].srchost_tag = srchost_hash; found_src: srchost_idx = outer_hash + k; q->flows[reduced_hash].srchost = srchost_idx; if (q->flows[reduced_hash].set == CAKE_SET_BULK) cake_inc_srchost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } if (allocate_dst) { dsthost_idx = dsthost_hash % CAKE_QUEUES; inner_hash = dsthost_idx % CAKE_SET_WAYS; outer_hash = dsthost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].dsthost_tag == dsthost_hash) goto found_dst; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count) break; } q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; found_dst: dsthost_idx = outer_hash + k; q->flows[reduced_hash].dsthost = dsthost_idx; if (q->flows[reduced_hash].set == CAKE_SET_BULK) cake_inc_dsthost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } } return reduced_hash; } /* helper functions : might be changed when/if skb use a standard list_head */ /* remove one skb from head of slot queue */ static struct sk_buff *dequeue_head(struct cake_flow *flow) { struct sk_buff *skb = flow->head; if (skb) { flow->head = skb->next; skb_mark_not_on_list(skb); } return skb; } /* add skb to flow queue (tail add) */ static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) { if (!flow->head) flow->head = skb; else flow->tail->next = skb; flow->tail = skb; skb->next = NULL; } static struct iphdr *cake_get_iphdr(const struct sk_buff *skb, struct ipv6hdr *buf) { unsigned int offset = skb_network_offset(skb); struct iphdr *iph; iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf); if (!iph) return NULL; if (iph->version == 4 && iph->protocol == IPPROTO_IPV6) return skb_header_pointer(skb, offset + iph->ihl * 4, sizeof(struct ipv6hdr), buf); else if (iph->version == 4) return iph; else if (iph->version == 6) return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr), buf); return NULL; } static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, void *buf, unsigned int bufsize) { unsigned int offset = skb_network_offset(skb); const struct ipv6hdr *ipv6h; const struct tcphdr *tcph; const struct iphdr *iph; struct ipv6hdr _ipv6h; struct tcphdr _tcph; ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h) return NULL; if (ipv6h->version == 4) { iph = (struct iphdr *)ipv6h; offset += iph->ihl * 4; /* special-case 6in4 tunnelling, as that is a common way to get * v6 connectivity in the home */ if (iph->protocol == IPPROTO_IPV6) { ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else if (iph->protocol != IPPROTO_TCP) { return NULL; } } else if (ipv6h->version == 6) { if (ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else { return NULL; } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, min(__tcp_hdrlen(tcph), bufsize), buf); } static const void *cake_get_tcpopt(const struct tcphdr *tcph, int code, int *oplen) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; if (opcode == code) { *oplen = opsize; return ptr; } ptr += opsize - 2; length -= opsize; } return NULL; } /* Compare two SACK sequences. A sequence is considered greater if it SACKs more * bytes than the other. In the case where both sequences ACKs bytes that the * other doesn't, A is considered greater. DSACKs in A also makes A be * considered greater. * * @return -1, 0 or 1 as normal compare functions */ static int cake_tcph_sack_compare(const struct tcphdr *tcph_a, const struct tcphdr *tcph_b) { const struct tcp_sack_block_wire *sack_a, *sack_b; u32 ack_seq_a = ntohl(tcph_a->ack_seq); u32 bytes_a = 0, bytes_b = 0; int oplen_a, oplen_b; bool first = true; sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a); sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b); /* pointers point to option contents */ oplen_a -= TCPOLEN_SACK_BASE; oplen_b -= TCPOLEN_SACK_BASE; if (sack_a && oplen_a >= sizeof(*sack_a) && (!sack_b || oplen_b < sizeof(*sack_b))) return -1; else if (sack_b && oplen_b >= sizeof(*sack_b) && (!sack_a || oplen_a < sizeof(*sack_a))) return 1; else if ((!sack_a || oplen_a < sizeof(*sack_a)) && (!sack_b || oplen_b < sizeof(*sack_b))) return 0; while (oplen_a >= sizeof(*sack_a)) { const struct tcp_sack_block_wire *sack_tmp = sack_b; u32 start_a = get_unaligned_be32(&sack_a->start_seq); u32 end_a = get_unaligned_be32(&sack_a->end_seq); int oplen_tmp = oplen_b; bool found = false; /* DSACK; always considered greater to prevent dropping */ if (before(start_a, ack_seq_a)) return -1; bytes_a += end_a - start_a; while (oplen_tmp >= sizeof(*sack_tmp)) { u32 start_b = get_unaligned_be32(&sack_tmp->start_seq); u32 end_b = get_unaligned_be32(&sack_tmp->end_seq); /* first time through we count the total size */ if (first) bytes_b += end_b - start_b; if (!after(start_b, start_a) && !before(end_b, end_a)) { found = true; if (!first) break; } oplen_tmp -= sizeof(*sack_tmp); sack_tmp++; } if (!found) return -1; oplen_a -= sizeof(*sack_a); sack_a++; first = false; } /* If we made it this far, all ranges SACKed by A are covered by B, so * either the SACKs are equal, or B SACKs more bytes. */ return bytes_b > bytes_a ? 1 : 0; } static void cake_tcph_get_tstamp(const struct tcphdr *tcph, u32 *tsval, u32 *tsecr) { const u8 *ptr; int opsize; ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize); if (ptr && opsize == TCPOLEN_TIMESTAMP) { *tsval = get_unaligned_be32(ptr); *tsecr = get_unaligned_be32(ptr + 4); } } static bool cake_tcph_may_drop(const struct tcphdr *tcph, u32 tstamp_new, u32 tsecr_new) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); u32 tstamp, tsecr; /* 3 reserved flags must be unset to avoid future breakage * ACK must be set * ECE/CWR are handled separately * All other flags URG/PSH/RST/SYN/FIN must be unset * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero) * 0x00C00000 = CWR/ECE (handled separately) * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000 */ if (((tcp_flag_word(tcph) & cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK)) return false; while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; switch (opcode) { case TCPOPT_MD5SIG: /* doesn't influence state */ break; case TCPOPT_SACK: /* stricter checking performed later */ if (opsize % 8 != 2) return false; break; case TCPOPT_TIMESTAMP: /* only drop timestamps lower than new */ if (opsize != TCPOLEN_TIMESTAMP) return false; tstamp = get_unaligned_be32(ptr); tsecr = get_unaligned_be32(ptr + 4); if (after(tstamp, tstamp_new) || after(tsecr, tsecr_new)) return false; break; case TCPOPT_MSS: /* these should only be set on SYN */ case TCPOPT_WINDOW: case TCPOPT_SACK_PERM: case TCPOPT_FASTOPEN: case TCPOPT_EXP: default: /* don't drop if any unknown options are present */ return false; } ptr += opsize - 2; length -= opsize; } return true; } static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, struct cake_flow *flow) { bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE; struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL; struct sk_buff *skb_check, *skb_prev = NULL; const struct ipv6hdr *ipv6h, *ipv6h_check; unsigned char _tcph[64], _tcph_check[64]; const struct tcphdr *tcph, *tcph_check; const struct iphdr *iph, *iph_check; struct ipv6hdr _iph, _iph_check; const struct sk_buff *skb; int seglen, num_found = 0; u32 tstamp = 0, tsecr = 0; __be32 elig_flags = 0; int sack_comp; /* no other possible ACKs to filter */ if (flow->head == flow->tail) return NULL; skb = flow->tail; tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph)); iph = cake_get_iphdr(skb, &_iph); if (!tcph) return NULL; cake_tcph_get_tstamp(tcph, &tstamp, &tsecr); /* the 'triggering' packet need only have the ACK flag set. * also check that SYN is not set, as there won't be any previous ACKs. */ if ((tcp_flag_word(tcph) & (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK) return NULL; /* the 'triggering' ACK is at the tail of the queue, we have already * returned if it is the only packet in the flow. loop through the rest * of the queue looking for pure ACKs with the same 5-tuple as the * triggering one. */ for (skb_check = flow->head; skb_check && skb_check != skb; skb_prev = skb_check, skb_check = skb_check->next) { iph_check = cake_get_iphdr(skb_check, &_iph_check); tcph_check = cake_get_tcphdr(skb_check, &_tcph_check, sizeof(_tcph_check)); /* only TCP packets with matching 5-tuple are eligible, and only * drop safe headers */ if (!tcph_check || iph->version != iph_check->version || tcph_check->source != tcph->source || tcph_check->dest != tcph->dest) continue; if (iph_check->version == 4) { if (iph_check->saddr != iph->saddr || iph_check->daddr != iph->daddr) continue; seglen = iph_totlen(skb, iph_check) - (4 * iph_check->ihl); } else if (iph_check->version == 6) { ipv6h = (struct ipv6hdr *)iph; ipv6h_check = (struct ipv6hdr *)iph_check; if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) || ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr)) continue; seglen = ntohs(ipv6h_check->payload_len); } else { WARN_ON(1); /* shouldn't happen */ continue; } /* If the ECE/CWR flags changed from the previous eligible * packet in the same flow, we should no longer be dropping that * previous packet as this would lose information. */ if (elig_ack && (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) { elig_ack = NULL; elig_ack_prev = NULL; num_found--; } /* Check TCP options and flags, don't drop ACKs with segment * data, and don't drop ACKs with a higher cumulative ACK * counter than the triggering packet. Check ACK seqno here to * avoid parsing SACK options of packets we are going to exclude * anyway. */ if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) || (seglen - __tcp_hdrlen(tcph_check)) != 0 || after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq))) continue; /* Check SACK options. The triggering packet must SACK more data * than the ACK under consideration, or SACK the same range but * have a larger cumulative ACK counter. The latter is a * pathological case, but is contained in the following check * anyway, just to be safe. */ sack_comp = cake_tcph_sack_compare(tcph_check, tcph); if (sack_comp < 0 || (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) && sack_comp == 0)) continue; /* At this point we have found an eligible pure ACK to drop; if * we are in aggressive mode, we are done. Otherwise, keep * searching unless this is the second eligible ACK we * found. * * Since we want to drop ACK closest to the head of the queue, * save the first eligible ACK we find, even if we need to loop * again. */ if (!elig_ack) { elig_ack = skb_check; elig_ack_prev = skb_prev; elig_flags = (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)); } if (num_found++ > 0) goto found; } /* We made it through the queue without finding two eligible ACKs . If * we found a single eligible ACK we can drop it in aggressive mode if * we can guarantee that this does not interfere with ECN flag * information. We ensure this by dropping it only if the enqueued * packet is consecutive with the eligible ACK, and their flags match. */ if (elig_ack && aggressive && elig_ack->next == skb && (elig_flags == (tcp_flag_word(tcph) & (TCP_FLAG_ECE | TCP_FLAG_CWR)))) goto found; return NULL; found: if (elig_ack_prev) elig_ack_prev->next = elig_ack->next; else flow->head = elig_ack->next; skb_mark_not_on_list(elig_ack); return elig_ack; } static u64 cake_ewma(u64 avg, u64 sample, u32 shift) { avg -= avg >> shift; avg += sample >> shift; return avg; } static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off) { if (q->rate_flags & CAKE_FLAG_OVERHEAD) len -= off; if (q->max_netlen < len) q->max_netlen = len; if (q->min_netlen > len) q->min_netlen = len; len += q->rate_overhead; if (len < q->rate_mpu) len = q->rate_mpu; if (q->atm_mode == CAKE_ATM_ATM) { len += 47; len /= 48; len *= 53; } else if (q->atm_mode == CAKE_ATM_PTM) { /* Add one byte per 64 bytes or part thereof. * This is conservative and easier to calculate than the * precise value. */ len += (len + 63) / 64; } if (q->max_adjlen < len) q->max_adjlen = len; if (q->min_adjlen > len) q->min_adjlen = len; return len; } static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int hdr_len, last_len = 0; u32 off = skb_network_offset(skb); u32 len = qdisc_pkt_len(skb); u16 segs = 1; q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); if (!shinfo->gso_size) return cake_calc_overhead(q, len, off); /* borrowed from qdisc_pkt_len_init() */ hdr_len = skb_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) segs = DIV_ROUND_UP(skb->len - hdr_len, shinfo->gso_size); else segs = shinfo->gso_segs; len = shinfo->gso_size + hdr_len; last_len = skb->len - shinfo->gso_size * (segs - 1); return (cake_calc_overhead(q, len, off) * (segs - 1) + cake_calc_overhead(q, last_len, off)); } static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j) { struct cake_heap_entry ii = q->overflow_heap[i]; struct cake_heap_entry jj = q->overflow_heap[j]; q->overflow_heap[i] = jj; q->overflow_heap[j] = ii; q->tins[ii.t].overflow_idx[ii.b] = j; q->tins[jj.t].overflow_idx[jj.b] = i; } static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i) { struct cake_heap_entry ii = q->overflow_heap[i]; return q->tins[ii.t].backlogs[ii.b]; } static void cake_heapify(struct cake_sched_data *q, u16 i) { static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES; u32 mb = cake_heap_get_backlog(q, i); u32 m = i; while (m < a) { u32 l = m + m + 1; u32 r = l + 1; if (l < a) { u32 lb = cake_heap_get_backlog(q, l); if (lb > mb) { m = l; mb = lb; } } if (r < a) { u32 rb = cake_heap_get_backlog(q, r); if (rb > mb) { m = r; mb = rb; } } if (m != i) { cake_heap_swap(q, i, m); i = m; } else { break; } } } static void cake_heapify_up(struct cake_sched_data *q, u16 i) { while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) { u16 p = (i - 1) >> 1; u32 ib = cake_heap_get_backlog(q, i); u32 pb = cake_heap_get_backlog(q, p); if (ib > pb) { cake_heap_swap(q, i, p); i = p; } else { break; } } } static int cake_advance_shaper(struct cake_sched_data *q, struct cake_tin_data *b, struct sk_buff *skb, ktime_t now, bool drop) { u32 len = get_cobalt_cb(skb)->adjusted_len; /* charge packet bandwidth to this tin * and to the global shaper. */ if (q->rate_ns) { u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft; u64 global_dur = (len * q->rate_ns) >> q->rate_shft; u64 failsafe_dur = global_dur + (global_dur >> 1); if (ktime_before(b->time_next_packet, now)) b->time_next_packet = ktime_add_ns(b->time_next_packet, tin_dur); else if (ktime_before(b->time_next_packet, ktime_add_ns(now, tin_dur))) b->time_next_packet = ktime_add_ns(now, tin_dur); q->time_next_packet = ktime_add_ns(q->time_next_packet, global_dur); if (!drop) q->failsafe_next_packet = \ ktime_add_ns(q->failsafe_next_packet, failsafe_dur); } return len; } static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); ktime_t now = ktime_get(); u32 idx = 0, tin = 0, len; struct cake_heap_entry qq; struct cake_tin_data *b; struct cake_flow *flow; struct sk_buff *skb; if (!q->overflow_timeout) { int i; /* Build fresh max-heap */ for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--) cake_heapify(q, i); } q->overflow_timeout = 65535; /* select longest queue for pruning */ qq = q->overflow_heap[0]; tin = qq.t; idx = qq.b; b = &q->tins[tin]; flow = &b->flows[idx]; skb = dequeue_head(flow); if (unlikely(!skb)) { /* heap has gone wrong, rebuild it next time */ q->overflow_timeout = 0; return idx + (tin << 16); } if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count++; len = qdisc_pkt_len(skb); q->buffer_used -= skb->truesize; b->backlogs[idx] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; flow->dropped++; b->tin_dropped++; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); sch->q.qlen--; qdisc_tree_reduce_backlog(sch, 1, len); cake_heapify(q, 0); return idx + (tin << 16); } static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { const int offset = skb_network_offset(skb); u16 *buf, buf_; u8 dscp; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* ToS is in the second byte of iphdr */ dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_IPV6): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* Traffic class is in the first and second bytes of ipv6hdr */ dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_ARP): return 0x38; /* CS7 - Net Control */ default: /* If there is no Diffserv field, treat as best-effort */ return 0; } } static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding * using firewall marks or skb->priority. Call DSCP parsing early if * wash is enabled, otherwise defer to below to skip unneeded parsing. */ mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; wash = !!(q->rate_flags & CAKE_FLAG_WASH); if (wash) dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; else if (mark && mark <= q->tin_cnt) tin = q->tin_order[mark - 1]; else if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && TC_H_MIN(skb->priority) <= q->tin_cnt) tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { if (!wash) dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) tin = 0; } return &q->tins[tin]; } static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct sk_buff *skb, int flow_mode, int *qerr) { struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); if (!filter) goto hash; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return 0; } #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); int len = qdisc_pkt_len(skb); int ret; struct sk_buff *ack = NULL; ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; u32 idx; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); if (idx == 0) { if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return ret; } idx--; flow = &b->flows[idx]; /* ensure shaper state isn't stale */ if (!b->tin_backlog) { if (ktime_before(b->time_next_packet, now)) b->time_next_packet = now; if (!sch->q.qlen) { if (ktime_before(q->time_next_packet, now)) { q->failsafe_next_packet = now; q->time_next_packet = now; } else if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = \ min(ktime_to_ns(q->time_next_packet), ktime_to_ns( q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); } } } if (unlikely(len > b->max_skblen)) b->max_skblen = len; if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); unsigned int slen = 0, numsegs = 0; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, segs); flow_queue_add(flow, segs); sch->q.qlen++; numsegs++; slen += segs->len; q->buffer_used += segs->truesize; b->packets++; } /* stats */ b->bytes += slen; b->backlogs[idx] += slen; b->tin_backlog += slen; sch->qstats.backlog += slen; q->avg_window_bytes += slen; qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); consume_skb(skb); } else { /* not splitting */ cobalt_set_enqueue_time(skb, now); get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb); flow_queue_add(flow, skb); if (q->ack_filter) ack = cake_ack_filter(q, flow); if (ack) { b->ack_drops++; sch->qstats.drops++; b->bytes += qdisc_pkt_len(ack); len -= qdisc_pkt_len(ack); q->buffer_used += skb->truesize - ack->truesize; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, ack, now, true); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack)); consume_skb(ack); } else { sch->q.qlen++; q->buffer_used += skb->truesize; } /* stats */ b->packets++; b->bytes += len; b->backlogs[idx] += len; b->tin_backlog += len; sch->qstats.backlog += len; q->avg_window_bytes += len; } if (q->overflow_timeout) cake_heapify_up(q, b->overflow_idx[idx]); /* incoming bandwidth capacity estimate */ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) { u64 packet_interval = \ ktime_to_ns(ktime_sub(now, q->last_packet_time)); if (packet_interval > NSEC_PER_SEC) packet_interval = NSEC_PER_SEC; /* filter out short-term bursts, eg. wifi aggregation */ q->avg_packet_interval = \ cake_ewma(q->avg_packet_interval, packet_interval, (packet_interval > q->avg_packet_interval ? 2 : 8)); q->last_packet_time = now; if (packet_interval > q->avg_packet_interval) { u64 window_interval = \ ktime_to_ns(ktime_sub(now, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); q->avg_window_bytes = 0; q->avg_window_begin = now; if (ktime_after(now, ktime_add_ms(q->last_reconfig_time, 250))) { q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4; cake_reconfigure(sch); } } } else { q->avg_window_bytes = 0; q->last_packet_time = now; } /* flowchain */ if (!flow->set || flow->set == CAKE_SET_DECAYING) { if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { b->decaying_flow_count--; list_move_tail(&flow->flowchain, &b->new_flows); } flow->set = CAKE_SET_SPARSE; b->sparse_flow_count++; flow->deficit = cake_get_flow_quantum(b, flow, q->flow_mode); } else if (flow->set == CAKE_SET_SPARSE_WAIT) { /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ flow->set = CAKE_SET_BULK; b->sparse_flow_count--; b->bulk_flow_count++; cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); } if (q->buffer_used > q->buffer_max_used) q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { u32 dropped = 0; while (q->buffer_used > q->buffer_limit) { dropped++; cake_drop(sch, to_free); } b->drop_overlimit += dropped; } return NET_XMIT_SUCCESS; } static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; struct cake_flow *flow = &b->flows[q->cur_flow]; struct sk_buff *skb = NULL; u32 len; if (flow->head) { skb = dequeue_head(flow); len = qdisc_pkt_len(skb); b->backlogs[q->cur_flow] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; q->buffer_used -= skb->truesize; sch->q.qlen--; if (q->overflow_timeout) cake_heapify(q, b->overflow_idx[q->cur_flow]); } return skb; } /* Discard leftover packets from a tin no longer in use. */ static void cake_clear_tin(struct Qdisc *sch, u16 tin) { struct cake_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; q->cur_tin = tin; for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) while (!!(skb = cake_dequeue_one(sch))) kfree_skb_reason(skb, SKB_DROP_REASON_QUEUE_PURGE); } static struct sk_buff *cake_dequeue(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; enum skb_drop_reason reason; ktime_t now = ktime_get(); struct cake_flow *flow; struct list_head *head; bool first_flow = true; struct sk_buff *skb; u64 delay; u32 len; begin: if (!sch->q.qlen) return NULL; /* global hard shaper */ if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); return NULL; } /* Choose a class to work on. */ if (!q->rate_ns) { /* In unlimited mode, can't rely on shaper timings, just balance * with DRR */ bool wrapped = false, empty = true; while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; q->cur_tin++; b++; if (q->cur_tin >= q->tin_cnt) { q->cur_tin = 0; b = q->tins; if (wrapped) { /* It's possible for q->qlen to be * nonzero when we actually have no * packets anywhere. */ if (empty) return NULL; } else { wrapped = true; } } } } else { /* In shaped mode, choose: * - Highest-priority tin with queue and meeting schedule, or * - The earliest-scheduled tin with queue. */ ktime_t best_time = KTIME_MAX; int tin, best_tin = 0; for (tin = 0; tin < q->tin_cnt; tin++) { b = q->tins + tin; if ((b->sparse_flow_count + b->bulk_flow_count) > 0) { ktime_t time_to_pkt = \ ktime_sub(b->time_next_packet, now); if (ktime_to_ns(time_to_pkt) <= 0 || ktime_compare(time_to_pkt, best_time) <= 0) { best_time = time_to_pkt; best_tin = tin; } } } q->cur_tin = best_tin; b = q->tins + best_tin; /* No point in going further if no packets to deliver. */ if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count))) return NULL; } retry: /* service this class */ head = &b->decaying_flows; if (!first_flow || list_empty(head)) { head = &b->new_flows; if (list_empty(head)) { head = &b->old_flows; if (unlikely(list_empty(head))) { head = &b->decaying_flows; if (unlikely(list_empty(head))) goto begin; } } } flow = list_first_entry(head, struct cake_flow, flowchain); q->cur_flow = flow - b->flows; first_flow = false; /* flow isolation (DRR++) */ if (flow->deficit <= 0) { /* Keep all flows with deficits out of the sparse and decaying * rotations. No non-empty flow can go into the decaying * rotation, so they can't get deficits */ if (flow->set == CAKE_SET_SPARSE) { if (flow->head) { b->sparse_flow_count--; b->bulk_flow_count++; cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); flow->set = CAKE_SET_BULK; } else { /* we've moved it to the bulk rotation for * correct deficit accounting but we still want * to count it as a sparse flow, not a bulk one. */ flow->set = CAKE_SET_SPARSE_WAIT; } } flow->deficit += cake_get_flow_quantum(b, flow, q->flow_mode); list_move_tail(&flow->flowchain, &b->old_flows); goto retry; } /* Retrieve a packet via the AQM */ while (1) { skb = cake_dequeue_one(sch); if (!skb) { /* this queue was actually empty */ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count--; if (flow->cvars.p_drop || flow->cvars.count || ktime_before(now, flow->cvars.drop_next)) { /* keep in the flowchain until the state has * decayed to rest */ list_move_tail(&flow->flowchain, &b->decaying_flows); if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); b->decaying_flow_count++; } else if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) { b->sparse_flow_count--; b->decaying_flow_count++; } flow->set = CAKE_SET_DECAYING; } else { /* remove empty queue from the flowchain */ list_del_init(&flow->flowchain); if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) b->sparse_flow_count--; else if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); } else b->decaying_flow_count--; flow->set = CAKE_SET_NONE; } goto begin; } reason = cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, (b->bulk_flow_count * !!(q->rate_flags & CAKE_FLAG_INGRESS))); /* Last packet in queue may be marked, shouldn't be dropped */ if (reason == SKB_NOT_DROPPED_YET || !flow->head) break; /* drop this packet, get another one */ if (q->rate_flags & CAKE_FLAG_INGRESS) { len = cake_advance_shaper(q, b, skb, now, true); flow->deficit -= len; b->tin_deficit -= len; } flow->dropped++; b->tin_dropped++; qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); kfree_skb_reason(skb, reason); if (q->rate_flags & CAKE_FLAG_INGRESS) goto retry; } b->tin_ecn_mark += !!flow->cvars.ecn_marked; qdisc_bstats_update(sch, skb); /* collect delay stats */ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); b->avge_delay = cake_ewma(b->avge_delay, delay, 8); b->peak_delay = cake_ewma(b->peak_delay, delay, delay > b->peak_delay ? 2 : 8); b->base_delay = cake_ewma(b->base_delay, delay, delay < b->base_delay ? 2 : 8); len = cake_advance_shaper(q, b, skb, now, false); flow->deficit -= len; b->tin_deficit -= len; if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); qdisc_watchdog_schedule_ns(&q->watchdog, next); } else if (!sch->q.qlen) { int i; for (i = 0; i < q->tin_cnt; i++) { if (q->tins[i].decaying_flow_count) { ktime_t next = \ ktime_add_ns(now, q->tins[i].cparams.target); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); break; } } } if (q->overflow_timeout) q->overflow_timeout--; return skb; } static void cake_reset(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); u32 c; if (!q->tins) return; for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 }, [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 }, [TCA_CAKE_ATM] = { .type = NLA_U32 }, [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 }, [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 }, [TCA_CAKE_RTT] = { .type = NLA_U32 }, [TCA_CAKE_TARGET] = { .type = NLA_U32 }, [TCA_CAKE_AUTORATE] = { .type = NLA_U32 }, [TCA_CAKE_MEMORY] = { .type = NLA_U32 }, [TCA_CAKE_NAT] = { .type = NLA_U32 }, [TCA_CAKE_RAW] = { .type = NLA_U32 }, [TCA_CAKE_WASH] = { .type = NLA_U32 }, [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, u64 target_ns, u64 rtt_est_ns) { /* convert byte-rate into time-per-byte * so it will always unwedge in reasonable time. */ static const u64 MIN_RATE = 64; u32 byte_target = mtu; u64 byte_target_ns; u8 rate_shft = 0; u64 rate_ns = 0; b->flow_quantum = 1514; if (rate) { b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); rate_shft = 34; rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); while (!!(rate_ns >> 34)) { rate_ns >>= 1; rate_shft--; } } /* else unlimited, ie. zero delay */ b->tin_rate_bps = rate; b->tin_rate_ns = rate_ns; b->tin_rate_shft = rate_shft; byte_target_ns = (byte_target * rate_ns) >> rate_shft; b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); b->cparams.interval = max(rtt_est_ns + b->cparams.target - target_ns, b->cparams.target * 2); b->cparams.mtu_time = byte_target_ns; b->cparams.p_inc = 1 << 24; /* 1/256 */ b->cparams.p_dec = 1 << 20; /* 1/4096 */ } static int cake_config_besteffort(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; q->tin_cnt = 1; q->tin_index = besteffort; q->tin_order = normal_order; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = 65535; return 0; } static int cake_config_precedence(struct Qdisc *sch) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; q->tin_index = precedence; q->tin_order = normal_order; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } /* List of known Diffserv codepoints: * * Default Forwarding (DF/CS0) - Best Effort * Max Throughput (TOS2) * Min Delay (TOS4) * LLT "La" (TOS5) * Assured Forwarding 1 (AF1x) - x3 * Assured Forwarding 2 (AF2x) - x3 * Assured Forwarding 3 (AF3x) - x3 * Assured Forwarding 4 (AF4x) - x3 * Precedence Class 1 (CS1) * Precedence Class 2 (CS2) * Precedence Class 3 (CS3) * Precedence Class 4 (CS4) * Precedence Class 5 (CS5) * Precedence Class 6 (CS6) * Precedence Class 7 (CS7) * Voice Admit (VA) * Expedited Forwarding (EF) * Lower Effort (LE) * * Total 26 codepoints. */ /* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * * Network Control (CS6,CS7) - routing traffic * Telephony (EF,VA) - aka. VoIP streams * Signalling (CS5) - VoIP setup * Multimedia Conferencing (AF4x) - aka. video calls * Realtime Interactive (CS4) - eg. games * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch * Broadcast Video (CS3) * Low-Latency Data (AF2x,TOS4) - eg. database * Ops, Admin, Management (CS2) - eg. ssh * Standard Service (DF & unrecognised codepoints) * High-Throughput Data (AF1x,TOS2) - eg. web traffic * Low-Priority Data (LE,CS1) - eg. BitTorrent * * Total 12 traffic classes. */ static int cake_config_diffserv8(struct Qdisc *sch) { /* Pruned list of traffic classes for typical applications: * * Network Control (CS6, CS7) * Minimum Latency (EF, VA, CS5, CS4) * Interactive Shell (CS2) * Low Latency Transactions (AF2x, TOS4) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (DF etc.) * High Throughput (AF1x, TOS2, CS1) * Background Traffic (LE) * * Total 8 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; /* codepoint to class mapping */ q->tin_index = diffserv8; q->tin_order = normal_order; /* class characteristics */ for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } static int cake_config_diffserv4(struct Qdisc *sch) { /* Further pruned list of traffic classes for four-class system: * * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2) * Best Effort (DF, AF1x, TOS2, and those not specified) * Background Traffic (LE, CS1) * * Total 4 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; /* codepoint to class mapping */ q->tin_index = diffserv4; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 1, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 1; q->tins[3].tin_quantum = quantum >> 2; return 0; } static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) * Best Effort * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; /* codepoint to class mapping */ q->tin_index = diffserv3; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 2; return 0; } static void cake_reconfigure(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: ft = cake_config_besteffort(sch); break; case CAKE_DIFFSERV_PRECEDENCE: ft = cake_config_precedence(sch); break; case CAKE_DIFFSERV_DIFFSERV8: ft = cake_config_diffserv8(sch); break; case CAKE_DIFFSERV_DIFFSERV4: ft = cake_config_diffserv4(sch); break; case CAKE_DIFFSERV_DIFFSERV3: default: ft = cake_config_diffserv3(sch); break; } for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) { cake_clear_tin(sch, c); q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time; } q->rate_ns = q->tins[ft].tin_rate_ns; q->rate_shft = q->tins[ft].tin_rate_shft; if (q->buffer_config_limit) { q->buffer_limit = q->buffer_config_limit; } else if (q->rate_bps) { u64 t = q->rate_bps * q->interval; do_div(t, USEC_PER_SEC / 4); q->buffer_limit = max_t(u32, t, 4U << 20); } else { q->buffer_limit = ~0; } sch->flags &= ~TCQ_F_CAN_BYPASS; q->buffer_limit = min(q->buffer_limit, max(sch->limit * psched_mtu(qdisc_dev(sch)), q->buffer_config_limit)); } static int cake_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CAKE_MAX + 1]; u16 rate_flags; u8 flow_mode; int err; err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy, extack); if (err < 0) return err; flow_mode = q->flow_mode; if (tb[TCA_CAKE_NAT]) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) flow_mode &= ~CAKE_FLOW_NAT_FLAG; flow_mode |= CAKE_FLOW_NAT_FLAG * !!nla_get_u32(tb[TCA_CAKE_NAT]); #else NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT], "No conntrack support in kernel"); return -EOPNOTSUPP; #endif } if (tb[TCA_CAKE_BASE_RATE64]) WRITE_ONCE(q->rate_bps, nla_get_u64(tb[TCA_CAKE_BASE_RATE64])); if (tb[TCA_CAKE_DIFFSERV_MODE]) WRITE_ONCE(q->tin_mode, nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE])); rate_flags = q->rate_flags; if (tb[TCA_CAKE_WASH]) { if (!!nla_get_u32(tb[TCA_CAKE_WASH])) rate_flags |= CAKE_FLAG_WASH; else rate_flags &= ~CAKE_FLAG_WASH; } if (tb[TCA_CAKE_FLOW_MODE]) flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) | (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & CAKE_FLOW_MASK)); if (tb[TCA_CAKE_ATM]) WRITE_ONCE(q->atm_mode, nla_get_u32(tb[TCA_CAKE_ATM])); if (tb[TCA_CAKE_OVERHEAD]) { WRITE_ONCE(q->rate_overhead, nla_get_s32(tb[TCA_CAKE_OVERHEAD])); rate_flags |= CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_RAW]) { rate_flags &= ~CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_MPU]) WRITE_ONCE(q->rate_mpu, nla_get_u32(tb[TCA_CAKE_MPU])); if (tb[TCA_CAKE_RTT]) { u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]); WRITE_ONCE(q->interval, max(interval, 1U)); } if (tb[TCA_CAKE_TARGET]) { u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]); WRITE_ONCE(q->target, max(target, 1U)); } if (tb[TCA_CAKE_AUTORATE]) { if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE])) rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; else rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; } if (tb[TCA_CAKE_INGRESS]) { if (!!nla_get_u32(tb[TCA_CAKE_INGRESS])) rate_flags |= CAKE_FLAG_INGRESS; else rate_flags &= ~CAKE_FLAG_INGRESS; } if (tb[TCA_CAKE_ACK_FILTER]) WRITE_ONCE(q->ack_filter, nla_get_u32(tb[TCA_CAKE_ACK_FILTER])); if (tb[TCA_CAKE_MEMORY]) WRITE_ONCE(q->buffer_config_limit, nla_get_u32(tb[TCA_CAKE_MEMORY])); if (tb[TCA_CAKE_SPLIT_GSO]) { if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) rate_flags |= CAKE_FLAG_SPLIT_GSO; else rate_flags &= ~CAKE_FLAG_SPLIT_GSO; } if (tb[TCA_CAKE_FWMARK]) { WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK])); WRITE_ONCE(q->fwmark_shft, q->fwmark_mask ? __ffs(q->fwmark_mask) : 0); } WRITE_ONCE(q->rate_flags, rate_flags); WRITE_ONCE(q->flow_mode, flow_mode); if (q->tins) { sch_tree_lock(sch); cake_reconfigure(sch); sch_tree_unlock(sch); } return 0; } static void cake_destroy(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); tcf_block_put(q->block); kvfree(q->tins); } static int cake_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); int i, j, err; sch->limit = 10240; q->tin_mode = CAKE_DIFFSERV_DIFFSERV3; q->flow_mode = CAKE_FLOW_TRIPLE; q->rate_bps = 0; /* unlimited by default */ q->interval = 100000; /* 100ms default */ q->target = 5000; /* 5ms: codel RFC argues * for 5 to 10% of interval */ q->rate_flags |= CAKE_FLAG_SPLIT_GSO; q->cur_tin = 0; q->cur_flow = 0; qdisc_watchdog_init(&q->watchdog, sch); if (opt) { err = cake_change(sch, opt, extack); if (err) return err; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; quantum_div[0] = ~0; for (i = 1; i <= CAKE_QUEUES; i++) quantum_div[i] = 65535 / i; q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; INIT_LIST_HEAD(&b->new_flows); INIT_LIST_HEAD(&b->old_flows); INIT_LIST_HEAD(&b->decaying_flows); b->sparse_flow_count = 0; b->bulk_flow_count = 0; b->decaying_flow_count = 0; for (j = 0; j < CAKE_QUEUES; j++) { struct cake_flow *flow = b->flows + j; u32 k = j * CAKE_MAX_TINS + i; INIT_LIST_HEAD(&flow->flowchain); cobalt_vars_init(&flow->cvars); q->overflow_heap[k].t = i; q->overflow_heap[k].b = j; b->overflow_idx[j] = k; } } cake_reconfigure(sch); q->avg_peak_bandwidth = q->rate_bps; q->min_netlen = ~0; q->min_adjlen = ~0; return 0; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *opts; u16 rate_flags; u8 flow_mode; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, READ_ONCE(q->rate_bps), TCA_CAKE_PAD)) goto nla_put_failure; flow_mode = READ_ONCE(q->flow_mode); if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MEMORY, READ_ONCE(q->buffer_config_limit))) goto nla_put_failure; rate_flags = READ_ONCE(q->rate_flags); if (nla_put_u32(skb, TCA_CAKE_AUTORATE, !!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_INGRESS, !!(rate_flags & CAKE_FLAG_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_NAT, !!(flow_mode & CAKE_FLOW_NAT_FLAG))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_WASH, !!(rate_flags & CAKE_FLAG_WASH))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead))) goto nla_put_failure; if (!(rate_flags & CAKE_FLAG_OVERHEAD)) if (nla_put_u32(skb, TCA_CAKE_RAW, 0)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO, !!(rate_flags & CAKE_FLAG_SPLIT_GSO))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: return -1; } static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tstats, *ts; int i; if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \ data, TCA_CAKE_STATS_PAD)) \ goto nla_put_failure; \ } while (0) PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); PUT_STAT_U32(MAX_NETLEN, q->max_netlen); PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); PUT_STAT_U32(MIN_NETLEN, q->min_netlen); PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); #undef PUT_STAT_U32 #undef PUT_STAT_U64 tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS); if (!tstats) goto nla_put_failure; #define PUT_TSTAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_TSTAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \ data, TCA_CAKE_TIN_STATS_PAD)) \ goto nla_put_failure; \ } while (0) for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; ts = nla_nest_start_noflag(d->skb, i + 1); if (!ts) goto nla_put_failure; PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); PUT_TSTAT_U64(SENT_BYTES64, b->bytes); PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); PUT_TSTAT_U32(TARGET_US, ktime_to_us(ns_to_ktime(b->cparams.target))); PUT_TSTAT_U32(INTERVAL_US, ktime_to_us(ns_to_ktime(b->cparams.interval))); PUT_TSTAT_U32(SENT_PACKETS, b->packets); PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); PUT_TSTAT_U32(PEAK_DELAY_US, ktime_to_us(ns_to_ktime(b->peak_delay))); PUT_TSTAT_U32(AVG_DELAY_US, ktime_to_us(ns_to_ktime(b->avge_delay))); PUT_TSTAT_U32(BASE_DELAY_US, ktime_to_us(ns_to_ktime(b->base_delay))); PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); PUT_TSTAT_U32(WAY_MISSES, b->way_misses); PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + b->decaying_flow_count); PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); nla_nest_end(d->skb, ts); } #undef PUT_TSTAT_U32 #undef PUT_TSTAT_U64 nla_nest_end(d->skb, tstats); return nla_nest_end(d->skb, stats); nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; } static unsigned long cake_find(struct Qdisc *sch, u32 classid) { return 0; } static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { return 0; } static void cake_unbind(struct Qdisc *q, unsigned long cl) { } static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static int cake_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { tcm->tcm_handle |= TC_H_MIN(cl); return 0; } static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct cake_sched_data *q = qdisc_priv(sch); const struct cake_flow *flow = NULL; struct gnet_stats_queue qs = { 0 }; struct nlattr *stats; u32 idx = cl - 1; if (idx < CAKE_QUEUES * q->tin_cnt) { const struct cake_tin_data *b = \ &q->tins[q->tin_order[idx / CAKE_QUEUES]]; const struct sk_buff *skb; flow = &b->flows[idx % CAKE_QUEUES]; if (flow->head) { sch_tree_lock(sch); skb = flow->head; while (skb) { qs.qlen++; skb = skb->next; } sch_tree_unlock(sch); } qs.backlog = b->backlogs[idx % CAKE_QUEUES]; qs.drops = flow->dropped; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; if (flow) { ktime_t now = ktime_get(); stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_S32(attr, data) do { \ if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) PUT_STAT_S32(DEFICIT, flow->deficit); PUT_STAT_U32(DROPPING, flow->cvars.dropping); PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); PUT_STAT_U32(P_DROP, flow->cvars.p_drop); if (flow->cvars.p_drop) { PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, ktime_to_us( ktime_sub(now, flow->cvars.drop_next))); } if (nla_nest_end(d->skb, stats) < 0) return -1; } return 0; nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct cake_sched_data *q = qdisc_priv(sch); unsigned int i, j; if (arg->stop) return; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; for (j = 0; j < CAKE_QUEUES; j++) { if (list_empty(&b->flows[j].flowchain)) { arg->count++; continue; } if (!tc_qdisc_stats_dump(sch, i * CAKE_QUEUES + j + 1, arg)) break; } } } static const struct Qdisc_class_ops cake_class_ops = { .leaf = cake_leaf, .find = cake_find, .tcf_block = cake_tcf_block, .bind_tcf = cake_bind, .unbind_tcf = cake_unbind, .dump = cake_dump_class, .dump_stats = cake_dump_class_stats, .walk = cake_walk, }; static struct Qdisc_ops cake_qdisc_ops __read_mostly = { .cl_ops = &cake_class_ops, .id = "cake", .priv_size = sizeof(struct cake_sched_data), .enqueue = cake_enqueue, .dequeue = cake_dequeue, .peek = qdisc_peek_dequeued, .init = cake_init, .reset = cake_reset, .destroy = cake_destroy, .change = cake_change, .dump = cake_dump, .dump_stats = cake_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("cake"); static int __init cake_module_init(void) { return register_qdisc(&cake_qdisc_ops); } static void __exit cake_module_exit(void) { unregister_qdisc(&cake_qdisc_ops); } module_init(cake_module_init) module_exit(cake_module_exit) MODULE_AUTHOR("Jonathan Morton"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("The CAKE shaper."); |
| 508 505 206 501 504 3948 3941 3613 1242 2953 2955 2952 1069 2 2 4572 1064 3552 1156 3613 1071 2298 2300 4623 4433 2830 933 310 1159 4575 4541 4492 633 1160 4539 3655 3717 2298 4476 504 4547 4567 4566 2 5 8 1 7 8 38 2 37 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * kernel userspace event delivery * * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * Copyright (C) 2004 Novell, Inc. All rights reserved. * Copyright (C) 2004 IBM, Inc. All rights reserved. * * Authors: * Robert Love <rml@novell.com> * Kay Sievers <kay.sievers@vrfy.org> * Arjan van de Ven <arjanv@redhat.com> * Greg Kroah-Hartman <greg@kroah.com> */ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/kobject.h> #include <linux/export.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> atomic64_t uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif struct uevent_sock { struct list_head list; struct sock *sk; }; #ifdef CONFIG_NET static LIST_HEAD(uevent_sock_list); /* This lock protects uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); #endif /* the strings here must match the enum in include/linux/kobject.h */ static const char *kobject_actions[] = { [KOBJ_ADD] = "add", [KOBJ_REMOVE] = "remove", [KOBJ_CHANGE] = "change", [KOBJ_MOVE] = "move", [KOBJ_ONLINE] = "online", [KOBJ_OFFLINE] = "offline", [KOBJ_BIND] = "bind", [KOBJ_UNBIND] = "unbind", }; static int kobject_action_type(const char *buf, size_t count, enum kobject_action *type, const char **args) { enum kobject_action action; size_t count_first; const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) count--; if (!count) goto out; args_start = strnchr(buf, count, ' '); if (args_start) { count_first = args_start - buf; args_start = args_start + 1; } else count_first = count; for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; if (kobject_actions[action][count_first] != '\0') continue; if (args) *args = args_start; *type = action; ret = 0; break; } out: return ret; } static const char *action_arg_word_end(const char *buf, const char *buf_end, char delim) { const char *next = buf; while (next <= buf_end && *next != delim) if (!isalnum(*next++)) return NULL; if (next == buf) return NULL; return next; } static int kobject_action_args(const char *buf, size_t count, struct kobj_uevent_env **ret_env) { struct kobj_uevent_env *env = NULL; const char *next, *buf_end, *key; int key_len; int r = -EINVAL; if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) count--; if (!count) return -EINVAL; env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return -ENOMEM; /* first arg is UUID */ if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) goto out; /* * the rest are custom environment variables in KEY=VALUE * format with ' ' delimiter between each KEY=VALUE pair */ next = buf + UUID_STRING_LEN; buf_end = buf + count - 1; while (next <= buf_end) { if (*next != ' ') goto out; /* skip the ' ', key must follow */ key = ++next; if (key > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, '='); if (!next || next > buf_end || *next != '=') goto out; key_len = next - buf; /* skip the '=', value must follow */ if (++next > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, ' '); if (!next) goto out; if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", key_len, key, (int) (next - buf), buf)) goto out; } r = 0; out: if (r) kfree(env); else *ret_env = env; return r; } /** * kobject_synth_uevent - send synthetic uevent with arguments * * @kobj: struct kobject for which synthetic uevent is to be generated * @buf: buffer containing action type and action args, newline is ignored * @count: length of buffer * * Returns 0 if kobject_synthetic_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) { char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; enum kobject_action action; const char *action_args; struct kobj_uevent_env *env; const char *msg = NULL, *devpath; int r; r = kobject_action_type(buf, count, &action, &action_args); if (r) { msg = "unknown uevent action string"; goto out; } if (!action_args) { r = kobject_uevent_env(kobj, action, no_uuid_envp); goto out; } r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { msg = "incorrect uevent action arguments"; goto out; } if (r) goto out; r = kobject_uevent_env(kobj, action, env->envp); kfree(env); out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); } return r; } #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { int buffer_size = sizeof(env->buf) - env->buflen; int len; len = strscpy(&env->buf[env->buflen], subsystem, buffer_size); if (len < 0) { pr_warn("%s: insufficient buffer space (%u left) for %s\n", __func__, buffer_size, subsystem); return -ENOMEM; } env->argv[0] = uevent_helper; env->argv[1] = &env->buf[env->buflen]; env->argv[2] = NULL; env->buflen += len + 1; return 0; } static void cleanup_uevent_env(struct subprocess_info *info) { kfree(info->data); } #endif #ifdef CONFIG_NET static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct netlink_skb_parms *parms; struct sk_buff *skb = NULL; char *scratch; size_t len; /* allocate message with maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (!skb) return NULL; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); skb_put_data(skb, env->buf, env->buflen); parms = &NETLINK_CB(skb); parms->creds.uid = GLOBAL_ROOT_UID; parms->creds.gid = GLOBAL_ROOT_GID; parms->dst_group = 1; parms->portid = 0; return skb; } static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; int retval = 0; /* send netlink message */ mutex_lock(&uevent_sock_mutex); list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; if (!netlink_has_listeners(uevent_sock, 1)) continue; if (!skb) { retval = -ENOMEM; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; } retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } mutex_unlock(&uevent_sock_mutex); consume_skb(skb); return retval; } static int uevent_net_broadcast_tagged(struct sock *usk, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; struct sk_buff *skb = NULL; int ret = 0; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) return -ENOMEM; /* fix credentials */ if (owning_user_ns != &init_user_ns) { struct netlink_skb_parms *parms = &NETLINK_CB(skb); kuid_t root_uid; kgid_t root_gid; /* fix uid */ root_uid = make_kuid(owning_user_ns, 0); if (uid_valid(root_uid)) parms->creds.uid = root_uid; /* fix gid */ root_gid = make_kgid(owning_user_ns, 0); if (gid_valid(root_gid)) parms->creds.gid = root_gid; } ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } #endif static int kobject_uevent_net_broadcast(struct kobject *kobj, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { int ret = 0; #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; const struct net *net = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { struct kobject *ksobj = &kobj->kset->kobj; if (ksobj->parent != NULL) ops = kobj_ns_ops(ksobj->parent); } /* kobjects currently only carry network namespace tags and they * are the only tag relevant here since we want to decide which * network namespaces to broadcast the uevent into. */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) net = kobj->ktype->namespace(kobj); if (!net) ret = uevent_net_broadcast_untagged(env, action_string, devpath); else ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); #endif return ret; } static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; size_t len; int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, sizeof(modalias_prefix) - 1)) { i++; continue; } len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { /* @env->envp[] contains pointers to @env->buf[] * with @env->buflen chars, and we are removing * variable MODALIAS here pointed by @env->envp[i] * with length @len as shown below: * * 0 @env->buf[] @env->buflen * --------------------------------------------- * ^ ^ ^ ^ * | |-> @len <-| target block | * @env->envp[0] @env->envp[i] @env->envp[i + 1] * * so the "target block" indicated above is moved * backward by @len, and its right size is * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). */ memmove(env->envp[i], env->envp[i + 1], env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; } env->envp_idx--; env->buflen -= len; } } /** * kobject_uevent_env - send an uevent with environmental data * * @kobj: struct kobject that the action is happening to * @action: action that is happening * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; /* * Mark "remove" event done regardless of result, for some subsystems * do not want to re-trigger "remove" event via automatic cleanup. */ if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } switch (action) { case KOBJ_ADD: /* * Mark "add" event so we can make sure we deliver "remove" * event to userspace during automatic cleanup. If * the object did send an "add" event, "remove" will * automatically generated by the core, if not already done * by the caller. */ kobj->state_add_uevent_sent = 1; break; case KOBJ_UNBIND: zap_modalias_env(env); break; default: break; } /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (retval) goto exit; retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); #ifdef CONFIG_UEVENT_HELPER /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { struct subprocess_info *info; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = init_uevent_argv(env, subsystem); if (retval) goto exit; retval = -ENOMEM; info = call_usermodehelper_setup(env->argv[0], env->argv, env->envp, GFP_KERNEL, NULL, cleanup_uevent_env, env); if (info) { retval = call_usermodehelper_exec(info, UMH_NO_WAIT); env = NULL; /* freed by cleanup_uevent_env */ } } #endif exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @kobj: struct kobject that the action is happening to * @action: action that is happening * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, struct netlink_ext_ack *extack) { /* u64 to chars: 2^64 - 1 = 21 chars */ char buf[sizeof("SEQNUM=") + 21]; struct sk_buff *skbc; int ret; /* bump and prepare sequence number */ ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; /* verify message does not overflow */ if ((skb->len + ret) > UEVENT_BUFFER_SIZE) { NL_SET_ERR_MSG(extack, "uevent message too big"); return -EINVAL; } /* copy skb and extend to accommodate sequence number */ skbc = skb_copy_expand(skb, 0, ret, GFP_KERNEL); if (!skbc) return -ENOMEM; /* append sequence number */ skb_put_data(skbc, buf, ret); /* remove msg header */ skb_pull(skbc, NLMSG_HDRLEN); /* set portid 0 to inform userspace message comes from kernel */ NETLINK_CB(skbc).portid = 0; NETLINK_CB(skbc).dst_group = 1; ret = netlink_broadcast(usk, skbc, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } static int uevent_net_rcv_skb(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net; int ret; if (!nlmsg_data(nlh)) return -EINVAL; /* * Verify that we are allowed to send messages to the target * network namespace. The caller must have CAP_SYS_ADMIN in the * owning user namespace of the target network namespace. */ net = sock_net(NETLINK_CB(skb).sk); if (!netlink_ns_capable(skb, net->user_ns, CAP_SYS_ADMIN)) { NL_SET_ERR_MSG(extack, "missing CAP_SYS_ADMIN capability"); return -EPERM; } ret = uevent_net_broadcast(net->uevent_sock->sk, skb, extack); return ret; } static void uevent_net_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &uevent_net_rcv_skb); } static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .input = uevent_net_rcv, .flags = NL_CFG_F_NONROOT_RECV }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } net->uevent_sock = ue_sk; /* Restrict uevents to initial user namespace. */ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); } return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif |
| 1193 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_INTERNAL_H #define _LINUX_HIGHMEM_INTERNAL_H /* * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft. */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); static inline void kmap_assert_nomap(void) { DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx); } #else static inline void kmap_local_fork(struct task_struct *tsk) { } static inline void kmap_assert_nomap(void) { } #endif #ifdef CONFIG_HIGHMEM #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); void kunmap_high(struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } static inline void kunmap(struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } static inline struct page *kmap_to_page(void *addr) { return __kmap_to_page(addr); } static inline void kmap_flush_unused(void) { __kmap_flush_unused(); } static inline void *kmap_local_page(struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } static inline void *kmap_local_pfn(unsigned long pfn) { return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_page_prot(page, prot); } static inline void *kmap_atomic(struct page *page) { return kmap_atomic_prot(page, kmap_prot); } static inline void *kmap_atomic_pfn(unsigned long pfn) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } unsigned long __nr_free_highpages(void); unsigned long __totalhigh_pages(void); static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || (addr >= __fix_to_virt(FIX_KMAP_END) && addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(struct page *page) { } static inline void kmap_flush_unused(void) { } static inline void kunmap(struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_local_page(struct page *page) { return page_address(page); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { return page_address(&folio->page) + offset; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); } static inline void *kmap_local_pfn(unsigned long pfn) { return kmap_local_page(pfn_to_page(pfn)); } static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } static inline void *kmap_atomic(struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return page_address(page); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { return kmap_atomic(page); } static inline void *kmap_atomic_pfn(unsigned long pfn) { return kmap_atomic(pfn_to_page(pfn)); } static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } static inline unsigned long nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { return false; } #endif /* CONFIG_HIGHMEM */ /** * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! * @__addr: Virtual address to be unmapped * * Unmaps an address previously mapped by kmap_atomic() and re-enables * pagefaults. Depending on PREEMP_RT configuration, re-enables also * migration and preemption. Users should not count on these side effects. * * Mappings should be unmapped in the reverse order that they were mapped. * See kmap_local_page() for details on nesting. * * @__addr can be any address within the mapped page, so there is no need * to subtract any offset that has been added. In contrast to kunmap(), * this function takes the address returned from kmap_atomic(), not the * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_atomic(__addr); \ } while (0) /** * kunmap_local - Unmap a page mapped via kmap_local_page(). * @__addr: An address within the page mapped * * @__addr can be any address within the mapped page. Commonly it is the * address return from kmap_local_page(), but it can also include offsets. * * Unmapping should be done in the reverse order of the mapping. See * kmap_local_page() for details. */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_local(__addr); \ } while (0) #endif |
| 2 1 1 2 10 2 8 7 5 7 6 6 9 9 1 1 6 1 1 1 9 1 1 2 6 11 11 1 10 4 2 2 6 1 4 1 5 11 14 7 1 6 6 | 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 | /* Block- or MTD-based romfs * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Derived from: ROMFS file system, Linux implementation * * Copyright © 1997-1999 Janos Farkas <chexum@shadow.banki.hu> * * Using parts of the minix filesystem * Copyright © 1991, 1992 Linus Torvalds * * and parts of the affs filesystem additionally * Copyright © 1993 Ray Burr * Copyright © 1996 Hans-Joachim Widmaier * * Changes * Changed for 2.1.19 modules * Jan 1997 Initial release * Jun 1997 2.1.43+ changes * Proper page locking in read_folio * Changed to work with 2.1.45+ fs * Jul 1997 Fixed follow_link * 2.1.47 * lookup shouldn't return -ENOENT * from Horst von Brand: * fail on wrong checksum * double unlock_super was possible * correct namelen for statfs * spotted by Bill Hawes: * readlink shouldn't iput() * Jun 1998 2.1.106 from Avery Pennarun: glibc scandir() * exposed a problem in readdir * 2.1.107 code-freeze spellchecker run * Aug 1998 2.1.118+ VFS changes * Sep 1998 2.1.122 another VFS change (follow_link) * Apr 1999 2.2.7 no more EBADF checking in * lookup/readdir, use ERR_PTR * Jun 1999 2.3.6 d_alloc_root use changed * 2.3.9 clean up usage of ENOENT/negative * dentries in lookup * clean up page flags setting * (error, uptodate, locking) in * in read_folio * use init_special_inode for * fifos/sockets (and streamline) in * read_inode, fix _ops table order * Aug 1999 2.3.16 __initfunc() => __init change * Oct 1999 2.3.24 page->owner hack obsoleted * Nov 1999 2.3.27 2.3.25+ page->offset => index change * * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/statfs.h> #include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/uaccess.h> #include <linux/major.h> #include "internal.h" static struct kmem_cache *romfs_inode_cachep; static const umode_t romfs_modemap[8] = { 0, /* hard link */ S_IFDIR | 0644, /* directory */ S_IFREG | 0644, /* regular file */ S_IFLNK | 0777, /* symlink */ S_IFBLK | 0600, /* blockdev */ S_IFCHR | 0600, /* chardev */ S_IFSOCK | 0644, /* socket */ S_IFIFO | 0644 /* FIFO */ }; static const unsigned char romfs_dtype_table[] = { DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_SOCK, DT_FIFO }; static struct inode *romfs_iget(struct super_block *sb, unsigned long pos); /* * read a page worth of data from the image */ static int romfs_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; loff_t offset, size; unsigned long fillsize, pos; void *buf; int ret; buf = kmap_local_folio(folio, 0); offset = folio_pos(folio); size = i_size_read(inode); fillsize = 0; ret = 0; if (offset < size) { size -= offset; fillsize = size > PAGE_SIZE ? PAGE_SIZE : size; pos = ROMFS_I(inode)->i_dataoffset + offset; ret = romfs_dev_read(inode->i_sb, pos, buf, fillsize); if (ret < 0) { fillsize = 0; ret = -EIO; } } buf = folio_zero_tail(folio, fillsize, buf + fillsize); kunmap_local(buf); folio_end_read(folio, ret == 0); return ret; } static const struct address_space_operations romfs_aops = { .read_folio = romfs_read_folio }; /* * read the entries from a directory */ static int romfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *i = file_inode(file); struct romfs_inode ri; unsigned long offset, maxoff; int j, ino, nextfh; char fsname[ROMFS_MAXFN]; /* XXX dynamic? */ int ret; maxoff = romfs_maxsize(i->i_sb); offset = ctx->pos; if (!offset) { offset = i->i_ino & ROMFH_MASK; ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; offset = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* Not really failsafe, but we are read-only... */ for (;;) { if (!offset || offset >= maxoff) { offset = maxoff; ctx->pos = offset; goto out; } ctx->pos = offset; /* Fetch inode info */ ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; j = romfs_dev_strnlen(i->i_sb, offset + ROMFH_SIZE, sizeof(fsname) - 1); if (j < 0) goto out; ret = romfs_dev_read(i->i_sb, offset + ROMFH_SIZE, fsname, j); if (ret < 0) goto out; fsname[j] = '\0'; ino = offset; nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) == ROMFH_HRD) ino = be32_to_cpu(ri.spec); if (!dir_emit(ctx, fsname, j, ino, romfs_dtype_table[nextfh & ROMFH_TYPE])) goto out; offset = nextfh & ROMFH_MASK; } out: return 0; } /* * look up an entry in a directory */ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long offset, maxoff; struct inode *inode = NULL; struct romfs_inode ri; const char *name; /* got from dentry */ int len, ret; offset = dir->i_ino & ROMFH_MASK; ret = romfs_dev_read(dir->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto error; /* search all the file entries in the list starting from the one * pointed to by the directory's special data */ maxoff = romfs_maxsize(dir->i_sb); offset = be32_to_cpu(ri.spec) & ROMFH_MASK; name = dentry->d_name.name; len = dentry->d_name.len; for (;;) { if (!offset || offset >= maxoff) break; ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri)); if (ret < 0) goto error; /* try to match the first 16 bytes of name */ ret = romfs_dev_strcmp(dir->i_sb, offset + ROMFH_SIZE, name, len); if (ret < 0) goto error; if (ret == 1) { /* Hard link handling */ if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD) offset = be32_to_cpu(ri.spec) & ROMFH_MASK; inode = romfs_iget(dir->i_sb, offset); break; } /* next entry */ offset = be32_to_cpu(ri.next) & ROMFH_MASK; } return d_splice_alias(inode, dentry); error: return ERR_PTR(ret); } static const struct file_operations romfs_dir_operations = { .read = generic_read_dir, .iterate_shared = romfs_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations romfs_dir_inode_operations = { .lookup = romfs_lookup, }; /* * get a romfs inode based on its position in the image (which doubles as the * inode number) */ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) { struct romfs_inode_info *inode; struct romfs_inode ri; struct inode *i; unsigned long nlen; unsigned nextfh; int ret; umode_t mode; /* we might have to traverse a chain of "hard link" file entries to get * to the actual file */ for (;;) { ret = romfs_dev_read(sb, pos, &ri, sizeof(ri)); if (ret < 0) goto error; /* XXX: do romfs_checksum here too (with name) */ nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) != ROMFH_HRD) break; pos = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* determine the length of the filename */ nlen = romfs_dev_strnlen(sb, pos + ROMFH_SIZE, ROMFS_MAXFN); if (IS_ERR_VALUE(nlen)) goto eio; /* get an inode for this image position */ i = iget_locked(sb, pos); if (!i) return ERR_PTR(-ENOMEM); if (!(i->i_state & I_NEW)) return i; /* precalculate the data offset */ inode = ROMFS_I(i); inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK; inode->i_dataoffset = pos + inode->i_metasize; set_nlink(i, 1); /* Hard to decide.. */ i->i_size = be32_to_cpu(ri.size); inode_set_mtime_to_ts(i, inode_set_atime_to_ts(i, inode_set_ctime(i, 0, 0))); /* set up mode and ops */ mode = romfs_modemap[nextfh & ROMFH_TYPE]; switch (nextfh & ROMFH_TYPE) { case ROMFH_DIR: i->i_size = ROMFS_I(i)->i_metasize; i->i_op = &romfs_dir_inode_operations; i->i_fop = &romfs_dir_operations; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_REG: i->i_fop = &romfs_ro_fops; i->i_data.a_ops = &romfs_aops; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; default: /* depending on MBZ for sock/fifos */ nextfh = be32_to_cpu(ri.spec); init_special_inode(i, mode, MKDEV(nextfh >> 16, nextfh & 0xffff)); break; } i->i_mode = mode; i->i_blocks = (i->i_size + 511) >> 9; unlock_new_inode(i); return i; eio: ret = -EIO; error: pr_err("read error for inode 0x%lx\n", pos); return ERR_PTR(ret); } /* * allocate a new inode */ static struct inode *romfs_alloc_inode(struct super_block *sb) { struct romfs_inode_info *inode; inode = alloc_inode_sb(sb, romfs_inode_cachep, GFP_KERNEL); return inode ? &inode->vfs_inode : NULL; } /* * return a spent inode to the slab cache */ static void romfs_free_inode(struct inode *inode) { kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode)); } /* * get filesystem statistics */ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; u64 id = 0; /* When calling huge_encode_dev(), * use sb->s_bdev->bd_dev when, * - CONFIG_ROMFS_ON_BLOCK defined * use sb->s_dev when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD defined * leave id as 0 when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD undefined */ if (sb->s_bdev) id = huge_encode_dev(sb->s_bdev->bd_dev); else if (sb->s_dev) id = huge_encode_dev(sb->s_dev); buf->f_type = ROMFS_MAGIC; buf->f_namelen = ROMFS_MAXFN; buf->f_bsize = ROMBSIZE; buf->f_bfree = buf->f_bavail = buf->f_ffree; buf->f_blocks = (romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS; buf->f_fsid = u64_to_fsid(id); return 0; } /* * remounting must involve read-only */ static int romfs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static const struct super_operations romfs_super_ops = { .alloc_inode = romfs_alloc_inode, .free_inode = romfs_free_inode, .statfs = romfs_statfs, }; /* * checksum check on part of a romfs filesystem */ static __u32 romfs_checksum(const void *data, int size) { const __be32 *ptr = data; __u32 sum; sum = 0; size >>= 2; while (size > 0) { sum += be32_to_cpu(*ptr++); size--; } return sum; } /* * fill in the superblock */ static int romfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct romfs_super_block *rsb; struct inode *root; unsigned long pos, img_size; const char *storage; size_t len; int ret; #ifdef CONFIG_BLOCK if (!sb->s_mtd) { sb_set_blocksize(sb, ROMBSIZE); } else { sb->s_blocksize = ROMBSIZE; sb->s_blocksize_bits = blksize_bits(ROMBSIZE); } #endif sb->s_maxbytes = 0xFFFFFFFF; sb->s_magic = ROMFS_MAGIC; sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_time_min = 0; sb->s_time_max = 0; sb->s_op = &romfs_super_ops; #ifdef CONFIG_ROMFS_ON_MTD /* Use same dev ID from the underlying mtdblock device */ if (sb->s_mtd) sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index); #endif /* read the image superblock and check it */ rsb = kmalloc(512, GFP_KERNEL); if (!rsb) return -ENOMEM; sb->s_fs_info = (void *) 512; ret = romfs_dev_read(sb, 0, rsb, 512); if (ret < 0) goto error_rsb; img_size = be32_to_cpu(rsb->size); if (sb->s_mtd && img_size > sb->s_mtd->size) goto error_rsb_inval; sb->s_fs_info = (void *) img_size; if (rsb->word0 != ROMSB_WORD0 || rsb->word1 != ROMSB_WORD1 || img_size < ROMFH_SIZE) { if (!(fc->sb_flags & SB_SILENT)) errorf(fc, "VFS: Can't find a romfs filesystem on dev %s.\n", sb->s_id); goto error_rsb_inval; } if (romfs_checksum(rsb, min_t(size_t, img_size, 512))) { pr_err("bad initial checksum on dev %s.\n", sb->s_id); goto error_rsb_inval; } storage = sb->s_mtd ? "MTD" : "the block layer"; len = strnlen(rsb->name, ROMFS_MAXFN); if (!(fc->sb_flags & SB_SILENT)) pr_notice("Mounting image '%*.*s' through %s\n", (unsigned) len, (unsigned) len, rsb->name, storage); kfree(rsb); rsb = NULL; /* find the root directory */ pos = (ROMFH_SIZE + len + 1 + ROMFH_PAD) & ROMFH_MASK; root = romfs_iget(sb, pos); if (IS_ERR(root)) return PTR_ERR(root); sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; return 0; error_rsb_inval: ret = -EINVAL; error_rsb: kfree(rsb); return ret; } /* * get a superblock for mounting */ static int romfs_get_tree(struct fs_context *fc) { int ret = -EINVAL; #ifdef CONFIG_ROMFS_ON_MTD ret = get_tree_mtd(fc, romfs_fill_super); #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (ret == -EINVAL) ret = get_tree_bdev(fc, romfs_fill_super); #endif return ret; } static const struct fs_context_operations romfs_context_ops = { .get_tree = romfs_get_tree, .reconfigure = romfs_reconfigure, }; /* * Set up the filesystem mount context. */ static int romfs_init_fs_context(struct fs_context *fc) { fc->ops = &romfs_context_ops; return 0; } /* * destroy a romfs superblock in the appropriate manner */ static void romfs_kill_sb(struct super_block *sb) { generic_shutdown_super(sb); #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) { put_mtd_device(sb->s_mtd); sb->s_mtd = NULL; } #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); bdev_fput(sb->s_bdev_file); } #endif } static struct file_system_type romfs_fs_type = { .owner = THIS_MODULE, .name = "romfs", .init_fs_context = romfs_init_fs_context, .kill_sb = romfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("romfs"); /* * inode storage initialiser */ static void romfs_i_init_once(void *_inode) { struct romfs_inode_info *inode = _inode; inode_init_once(&inode->vfs_inode); } /* * romfs module initialisation */ static int __init init_romfs_fs(void) { int ret; pr_info("ROMFS MTD (C) 2007 Red Hat, Inc.\n"); romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); return -ENOMEM; } ret = register_filesystem(&romfs_fs_type); if (ret) { pr_err("Failed to register filesystem\n"); goto error_register; } return 0; error_register: kmem_cache_destroy(romfs_inode_cachep); return ret; } /* * romfs module removal */ static void __exit exit_romfs_fs(void) { unregister_filesystem(&romfs_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(romfs_inode_cachep); } module_init(init_romfs_fs); module_exit(exit_romfs_fs); MODULE_DESCRIPTION("Direct-MTD Capable RomFS"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); /* Actually dual-licensed, but it doesn't matter for */ |
| 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 | /* SPDX-License-Identifier: MIT */ #ifndef __LINUX_GUD_INTERNAL_H #define __LINUX_GUD_INTERNAL_H #include <linux/list.h> #include <linux/mutex.h> #include <linux/scatterlist.h> #include <linux/usb.h> #include <linux/workqueue.h> #include <uapi/drm/drm_fourcc.h> #include <drm/drm_modes.h> #include <drm/drm_simple_kms_helper.h> struct gud_device { struct drm_device drm; struct drm_simple_display_pipe pipe; struct device *dmadev; struct work_struct work; u32 flags; const struct drm_format_info *xrgb8888_emulation_format; u16 *properties; unsigned int num_properties; unsigned int bulk_pipe; void *bulk_buf; size_t bulk_len; struct sg_table bulk_sgt; u8 compression; void *lz4_comp_mem; void *compress_buf; u64 stats_length; u64 stats_actual_length; unsigned int stats_num_errors; struct mutex ctrl_lock; /* Serialize get/set and status transfers */ struct mutex damage_lock; /* Protects the following members: */ struct drm_framebuffer *fb; struct drm_rect damage; bool prev_flush_failed; void *shadow_buf; }; static inline struct gud_device *to_gud_device(struct drm_device *drm) { return container_of(drm, struct gud_device, drm); } static inline struct usb_device *gud_to_usb_device(struct gud_device *gdrm) { return interface_to_usbdev(to_usb_interface(gdrm->drm.dev)); } int gud_usb_get(struct gud_device *gdrm, u8 request, u16 index, void *buf, size_t len); int gud_usb_set(struct gud_device *gdrm, u8 request, u16 index, void *buf, size_t len); int gud_usb_get_u8(struct gud_device *gdrm, u8 request, u16 index, u8 *val); int gud_usb_set_u8(struct gud_device *gdrm, u8 request, u8 val); void gud_clear_damage(struct gud_device *gdrm); void gud_flush_work(struct work_struct *work); int gud_pipe_check(struct drm_simple_display_pipe *pipe, struct drm_plane_state *new_plane_state, struct drm_crtc_state *new_crtc_state); void gud_pipe_update(struct drm_simple_display_pipe *pipe, struct drm_plane_state *old_state); int gud_connector_fill_properties(struct drm_connector_state *connector_state, struct gud_property_req *properties); int gud_get_connectors(struct gud_device *gdrm); /* Driver internal fourcc transfer formats */ #define GUD_DRM_FORMAT_R1 0x00000122 #define GUD_DRM_FORMAT_XRGB1111 0x03121722 static inline u8 gud_from_fourcc(u32 fourcc) { switch (fourcc) { case GUD_DRM_FORMAT_R1: return GUD_PIXEL_FORMAT_R1; case DRM_FORMAT_R8: return GUD_PIXEL_FORMAT_R8; case GUD_DRM_FORMAT_XRGB1111: return GUD_PIXEL_FORMAT_XRGB1111; case DRM_FORMAT_RGB332: return GUD_PIXEL_FORMAT_RGB332; case DRM_FORMAT_RGB565: return GUD_PIXEL_FORMAT_RGB565; case DRM_FORMAT_RGB888: return GUD_PIXEL_FORMAT_RGB888; case DRM_FORMAT_XRGB8888: return GUD_PIXEL_FORMAT_XRGB8888; case DRM_FORMAT_ARGB8888: return GUD_PIXEL_FORMAT_ARGB8888; } return 0; } static inline u32 gud_to_fourcc(u8 format) { switch (format) { case GUD_PIXEL_FORMAT_R1: return GUD_DRM_FORMAT_R1; case GUD_PIXEL_FORMAT_R8: return DRM_FORMAT_R8; case GUD_PIXEL_FORMAT_XRGB1111: return GUD_DRM_FORMAT_XRGB1111; case GUD_PIXEL_FORMAT_RGB332: return DRM_FORMAT_RGB332; case GUD_PIXEL_FORMAT_RGB565: return DRM_FORMAT_RGB565; case GUD_PIXEL_FORMAT_RGB888: return DRM_FORMAT_RGB888; case GUD_PIXEL_FORMAT_XRGB8888: return DRM_FORMAT_XRGB8888; case GUD_PIXEL_FORMAT_ARGB8888: return DRM_FORMAT_ARGB8888; } return 0; } static inline void gud_from_display_mode(struct gud_display_mode_req *dst, const struct drm_display_mode *src) { u32 flags = src->flags & GUD_DISPLAY_MODE_FLAG_USER_MASK; if (src->type & DRM_MODE_TYPE_PREFERRED) flags |= GUD_DISPLAY_MODE_FLAG_PREFERRED; dst->clock = cpu_to_le32(src->clock); dst->hdisplay = cpu_to_le16(src->hdisplay); dst->hsync_start = cpu_to_le16(src->hsync_start); dst->hsync_end = cpu_to_le16(src->hsync_end); dst->htotal = cpu_to_le16(src->htotal); dst->vdisplay = cpu_to_le16(src->vdisplay); dst->vsync_start = cpu_to_le16(src->vsync_start); dst->vsync_end = cpu_to_le16(src->vsync_end); dst->vtotal = cpu_to_le16(src->vtotal); dst->flags = cpu_to_le32(flags); } static inline void gud_to_display_mode(struct drm_display_mode *dst, const struct gud_display_mode_req *src) { u32 flags = le32_t |