| 4 4 4 2 4 4 3 1 2 1 2 10 2 4 6 4 2 2 2 2 4 4 2 4 2 6 2 4 2 4 2 4 4 2 5 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 | // SPDX-License-Identifier: GPL-2.0-or-later /* * USB Synaptics device driver * * Copyright (c) 2002 Rob Miller (rob@inpharmatica . co . uk) * Copyright (c) 2003 Ron Lee (ron@debian.org) * cPad driver for kernel 2.4 * * Copyright (c) 2004 Jan Steinhoff (cpad@jan-steinhoff . de) * Copyright (c) 2004 Ron Lee (ron@debian.org) * rewritten for kernel 2.6 * * cPad display character device part is not included. It can be found at * http://jan-steinhoff.de/linux/synaptics-usb.html * * Bases on: usb_skeleton.c v2.2 by Greg Kroah-Hartman * drivers/hid/usbhid/usbmouse.c by Vojtech Pavlik * drivers/input/mouse/synaptics.c by Peter Osterlund * * Trademarks are the property of their respective owners. */ /* * There are three different types of Synaptics USB devices: Touchpads, * touchsticks (or trackpoints), and touchscreens. Touchpads are well supported * by this driver, touchstick support has not been tested much yet, and * touchscreens have not been tested at all. * * Up to three alternate settings are possible: * setting 0: one int endpoint for relative movement (used by usbhid.ko) * setting 1: one int endpoint for absolute finger position * setting 2 (cPad only): one int endpoint for absolute finger position and * two bulk endpoints for the display (in/out) * This driver uses setting 1. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/usb.h> #include <linux/input.h> #include <linux/usb/input.h> #define USB_VENDOR_ID_SYNAPTICS 0x06cb #define USB_DEVICE_ID_SYNAPTICS_TP 0x0001 /* Synaptics USB TouchPad */ #define USB_DEVICE_ID_SYNAPTICS_INT_TP 0x0002 /* Integrated USB TouchPad */ #define USB_DEVICE_ID_SYNAPTICS_CPAD 0x0003 /* Synaptics cPad */ #define USB_DEVICE_ID_SYNAPTICS_TS 0x0006 /* Synaptics TouchScreen */ #define USB_DEVICE_ID_SYNAPTICS_STICK 0x0007 /* Synaptics USB Styk */ #define USB_DEVICE_ID_SYNAPTICS_WP 0x0008 /* Synaptics USB WheelPad */ #define USB_DEVICE_ID_SYNAPTICS_COMP_TP 0x0009 /* Composite USB TouchPad */ #define USB_DEVICE_ID_SYNAPTICS_WTP 0x0010 /* Wireless TouchPad */ #define USB_DEVICE_ID_SYNAPTICS_DPAD 0x0013 /* DisplayPad */ #define SYNUSB_TOUCHPAD (1 << 0) #define SYNUSB_STICK (1 << 1) #define SYNUSB_TOUCHSCREEN (1 << 2) #define SYNUSB_AUXDISPLAY (1 << 3) /* For cPad */ #define SYNUSB_COMBO (1 << 4) /* Composite device (TP + stick) */ #define SYNUSB_IO_ALWAYS (1 << 5) #define USB_DEVICE_SYNAPTICS(prod, kind) \ USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, \ USB_DEVICE_ID_SYNAPTICS_##prod), \ .driver_info = (kind), #define SYNUSB_RECV_SIZE 8 #define XMIN_NOMINAL 1472 #define XMAX_NOMINAL 5472 #define YMIN_NOMINAL 1408 #define YMAX_NOMINAL 4448 struct synusb { struct usb_device *udev; struct usb_interface *intf; struct urb *urb; unsigned char *data; /* serialize access to open/suspend */ struct mutex pm_mutex; bool is_open; /* input device related data structures */ struct input_dev *input; char name[128]; char phys[64]; /* characteristics of the device */ unsigned long flags; }; static void synusb_report_buttons(struct synusb *synusb) { struct input_dev *input_dev = synusb->input; input_report_key(input_dev, BTN_LEFT, synusb->data[1] & 0x04); input_report_key(input_dev, BTN_RIGHT, synusb->data[1] & 0x01); input_report_key(input_dev, BTN_MIDDLE, synusb->data[1] & 0x02); } static void synusb_report_stick(struct synusb *synusb) { struct input_dev *input_dev = synusb->input; int x, y; unsigned int pressure; pressure = synusb->data[6]; x = (s16)(be16_to_cpup((__be16 *)&synusb->data[2]) << 3) >> 7; y = (s16)(be16_to_cpup((__be16 *)&synusb->data[4]) << 3) >> 7; if (pressure > 0) { input_report_rel(input_dev, REL_X, x); input_report_rel(input_dev, REL_Y, -y); } input_report_abs(input_dev, ABS_PRESSURE, pressure); synusb_report_buttons(synusb); input_sync(input_dev); } static void synusb_report_touchpad(struct synusb *synusb) { struct input_dev *input_dev = synusb->input; unsigned int num_fingers, tool_width; unsigned int x, y; unsigned int pressure, w; pressure = synusb->data[6]; x = be16_to_cpup((__be16 *)&synusb->data[2]); y = be16_to_cpup((__be16 *)&synusb->data[4]); w = synusb->data[0] & 0x0f; if (pressure > 0) { num_fingers = 1; tool_width = 5; switch (w) { case 0 ... 1: num_fingers = 2 + w; break; case 2: /* pen, pretend its a finger */ break; case 4 ... 15: tool_width = w; break; } } else { num_fingers = 0; tool_width = 0; } /* * Post events * BTN_TOUCH has to be first as mousedev relies on it when doing * absolute -> relative conversion */ if (pressure > 30) input_report_key(input_dev, BTN_TOUCH, 1); if (pressure < 25) input_report_key(input_dev, BTN_TOUCH, 0); if (num_fingers > 0) { input_report_abs(input_dev, ABS_X, x); input_report_abs(input_dev, ABS_Y, YMAX_NOMINAL + YMIN_NOMINAL - y); } input_report_abs(input_dev, ABS_PRESSURE, pressure); input_report_abs(input_dev, ABS_TOOL_WIDTH, tool_width); input_report_key(input_dev, BTN_TOOL_FINGER, num_fingers == 1); input_report_key(input_dev, BTN_TOOL_DOUBLETAP, num_fingers == 2); input_report_key(input_dev, BTN_TOOL_TRIPLETAP, num_fingers == 3); synusb_report_buttons(synusb); if (synusb->flags & SYNUSB_AUXDISPLAY) input_report_key(input_dev, BTN_MIDDLE, synusb->data[1] & 0x08); input_sync(input_dev); } static void synusb_irq(struct urb *urb) { struct synusb *synusb = urb->context; int error; /* Check our status in case we need to bail out early. */ switch (urb->status) { case 0: usb_mark_last_busy(synusb->udev); break; /* Device went away so don't keep trying to read from it. */ case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: return; default: goto resubmit; break; } if (synusb->flags & SYNUSB_STICK) synusb_report_stick(synusb); else synusb_report_touchpad(synusb); resubmit: error = usb_submit_urb(urb, GFP_ATOMIC); if (error && error != -EPERM) dev_err(&synusb->intf->dev, "%s - usb_submit_urb failed with result: %d", __func__, error); } static struct usb_endpoint_descriptor * synusb_get_in_endpoint(struct usb_host_interface *iface) { struct usb_endpoint_descriptor *endpoint; int i; for (i = 0; i < iface->desc.bNumEndpoints; ++i) { endpoint = &iface->endpoint[i].desc; if (usb_endpoint_is_int_in(endpoint)) { /* we found our interrupt in endpoint */ return endpoint; } } return NULL; } static int synusb_open(struct input_dev *dev) { struct synusb *synusb = input_get_drvdata(dev); int retval; retval = usb_autopm_get_interface(synusb->intf); if (retval) { dev_err(&synusb->intf->dev, "%s - usb_autopm_get_interface failed, error: %d\n", __func__, retval); return retval; } mutex_lock(&synusb->pm_mutex); retval = usb_submit_urb(synusb->urb, GFP_KERNEL); if (retval) { dev_err(&synusb->intf->dev, "%s - usb_submit_urb failed, error: %d\n", __func__, retval); retval = -EIO; goto out; } synusb->intf->needs_remote_wakeup = 1; synusb->is_open = true; out: mutex_unlock(&synusb->pm_mutex); usb_autopm_put_interface(synusb->intf); return retval; } static void synusb_close(struct input_dev *dev) { struct synusb *synusb = input_get_drvdata(dev); int autopm_error; autopm_error = usb_autopm_get_interface(synusb->intf); mutex_lock(&synusb->pm_mutex); usb_kill_urb(synusb->urb); synusb->intf->needs_remote_wakeup = 0; synusb->is_open = false; mutex_unlock(&synusb->pm_mutex); if (!autopm_error) usb_autopm_put_interface(synusb->intf); } static int synusb_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); struct usb_endpoint_descriptor *ep; struct synusb *synusb; struct input_dev *input_dev; unsigned int intf_num = intf->cur_altsetting->desc.bInterfaceNumber; unsigned int altsetting = min(intf->num_altsetting, 1U); int error; error = usb_set_interface(udev, intf_num, altsetting); if (error) { dev_err(&udev->dev, "Can not set alternate setting to %i, error: %i", altsetting, error); return error; } ep = synusb_get_in_endpoint(intf->cur_altsetting); if (!ep) return -ENODEV; synusb = kzalloc(sizeof(*synusb), GFP_KERNEL); input_dev = input_allocate_device(); if (!synusb || !input_dev) { error = -ENOMEM; goto err_free_mem; } synusb->udev = udev; synusb->intf = intf; synusb->input = input_dev; mutex_init(&synusb->pm_mutex); synusb->flags = id->driver_info; if (synusb->flags & SYNUSB_COMBO) { /* * This is a combo device, we need to set proper * capability, depending on the interface. */ synusb->flags |= intf_num == 1 ? SYNUSB_STICK : SYNUSB_TOUCHPAD; } synusb->urb = usb_alloc_urb(0, GFP_KERNEL); if (!synusb->urb) { error = -ENOMEM; goto err_free_mem; } synusb->data = usb_alloc_coherent(udev, SYNUSB_RECV_SIZE, GFP_KERNEL, &synusb->urb->transfer_dma); if (!synusb->data) { error = -ENOMEM; goto err_free_urb; } usb_fill_int_urb(synusb->urb, udev, usb_rcvintpipe(udev, ep->bEndpointAddress), synusb->data, SYNUSB_RECV_SIZE, synusb_irq, synusb, ep->bInterval); synusb->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; if (udev->manufacturer) strscpy(synusb->name, udev->manufacturer, sizeof(synusb->name)); if (udev->product) { if (udev->manufacturer) strlcat(synusb->name, " ", sizeof(synusb->name)); strlcat(synusb->name, udev->product, sizeof(synusb->name)); } if (!strlen(synusb->name)) snprintf(synusb->name, sizeof(synusb->name), "USB Synaptics Device %04x:%04x", le16_to_cpu(udev->descriptor.idVendor), le16_to_cpu(udev->descriptor.idProduct)); if (synusb->flags & SYNUSB_STICK) strlcat(synusb->name, " (Stick)", sizeof(synusb->name)); usb_make_path(udev, synusb->phys, sizeof(synusb->phys)); strlcat(synusb->phys, "/input0", sizeof(synusb->phys)); input_dev->name = synusb->name; input_dev->phys = synusb->phys; usb_to_input_id(udev, &input_dev->id); input_dev->dev.parent = &synusb->intf->dev; if (!(synusb->flags & SYNUSB_IO_ALWAYS)) { input_dev->open = synusb_open; input_dev->close = synusb_close; } input_set_drvdata(input_dev, synusb); __set_bit(EV_ABS, input_dev->evbit); __set_bit(EV_KEY, input_dev->evbit); if (synusb->flags & SYNUSB_STICK) { __set_bit(EV_REL, input_dev->evbit); __set_bit(REL_X, input_dev->relbit); __set_bit(REL_Y, input_dev->relbit); __set_bit(INPUT_PROP_POINTING_STICK, input_dev->propbit); input_set_abs_params(input_dev, ABS_PRESSURE, 0, 127, 0, 0); } else { input_set_abs_params(input_dev, ABS_X, XMIN_NOMINAL, XMAX_NOMINAL, 0, 0); input_set_abs_params(input_dev, ABS_Y, YMIN_NOMINAL, YMAX_NOMINAL, 0, 0); input_set_abs_params(input_dev, ABS_PRESSURE, 0, 255, 0, 0); input_set_abs_params(input_dev, ABS_TOOL_WIDTH, 0, 15, 0, 0); __set_bit(BTN_TOUCH, input_dev->keybit); __set_bit(BTN_TOOL_FINGER, input_dev->keybit); __set_bit(BTN_TOOL_DOUBLETAP, input_dev->keybit); __set_bit(BTN_TOOL_TRIPLETAP, input_dev->keybit); } if (synusb->flags & SYNUSB_TOUCHSCREEN) __set_bit(INPUT_PROP_DIRECT, input_dev->propbit); else __set_bit(INPUT_PROP_POINTER, input_dev->propbit); __set_bit(BTN_LEFT, input_dev->keybit); __set_bit(BTN_RIGHT, input_dev->keybit); __set_bit(BTN_MIDDLE, input_dev->keybit); usb_set_intfdata(intf, synusb); if (synusb->flags & SYNUSB_IO_ALWAYS) { error = synusb_open(input_dev); if (error) goto err_free_dma; } error = input_register_device(input_dev); if (error) { dev_err(&udev->dev, "Failed to register input device, error %d\n", error); goto err_stop_io; } return 0; err_stop_io: if (synusb->flags & SYNUSB_IO_ALWAYS) synusb_close(synusb->input); err_free_dma: usb_free_coherent(udev, SYNUSB_RECV_SIZE, synusb->data, synusb->urb->transfer_dma); err_free_urb: usb_free_urb(synusb->urb); err_free_mem: input_free_device(input_dev); kfree(synusb); usb_set_intfdata(intf, NULL); return error; } static void synusb_disconnect(struct usb_interface *intf) { struct synusb *synusb = usb_get_intfdata(intf); struct usb_device *udev = interface_to_usbdev(intf); if (synusb->flags & SYNUSB_IO_ALWAYS) synusb_close(synusb->input); input_unregister_device(synusb->input); usb_free_coherent(udev, SYNUSB_RECV_SIZE, synusb->data, synusb->urb->transfer_dma); usb_free_urb(synusb->urb); kfree(synusb); usb_set_intfdata(intf, NULL); } static int synusb_suspend(struct usb_interface *intf, pm_message_t message) { struct synusb *synusb = usb_get_intfdata(intf); mutex_lock(&synusb->pm_mutex); usb_kill_urb(synusb->urb); mutex_unlock(&synusb->pm_mutex); return 0; } static int synusb_resume(struct usb_interface *intf) { struct synusb *synusb = usb_get_intfdata(intf); int retval = 0; mutex_lock(&synusb->pm_mutex); if ((synusb->is_open || (synusb->flags & SYNUSB_IO_ALWAYS)) && usb_submit_urb(synusb->urb, GFP_NOIO) < 0) { retval = -EIO; } mutex_unlock(&synusb->pm_mutex); return retval; } static int synusb_pre_reset(struct usb_interface *intf) { struct synusb *synusb = usb_get_intfdata(intf); mutex_lock(&synusb->pm_mutex); usb_kill_urb(synusb->urb); return 0; } static int synusb_post_reset(struct usb_interface *intf) { struct synusb *synusb = usb_get_intfdata(intf); int retval = 0; if ((synusb->is_open || (synusb->flags & SYNUSB_IO_ALWAYS)) && usb_submit_urb(synusb->urb, GFP_NOIO) < 0) { retval = -EIO; } mutex_unlock(&synusb->pm_mutex); return retval; } static int synusb_reset_resume(struct usb_interface *intf) { return synusb_resume(intf); } static const struct usb_device_id synusb_idtable[] = { { USB_DEVICE_SYNAPTICS(TP, SYNUSB_TOUCHPAD) }, { USB_DEVICE_SYNAPTICS(INT_TP, SYNUSB_TOUCHPAD) }, { USB_DEVICE_SYNAPTICS(CPAD, SYNUSB_TOUCHPAD | SYNUSB_AUXDISPLAY | SYNUSB_IO_ALWAYS) }, { USB_DEVICE_SYNAPTICS(TS, SYNUSB_TOUCHSCREEN) }, { USB_DEVICE_SYNAPTICS(STICK, SYNUSB_STICK) }, { USB_DEVICE_SYNAPTICS(WP, SYNUSB_TOUCHPAD) }, { USB_DEVICE_SYNAPTICS(COMP_TP, SYNUSB_COMBO) }, { USB_DEVICE_SYNAPTICS(WTP, SYNUSB_TOUCHPAD) }, { USB_DEVICE_SYNAPTICS(DPAD, SYNUSB_TOUCHPAD) }, { } }; MODULE_DEVICE_TABLE(usb, synusb_idtable); static struct usb_driver synusb_driver = { .name = "synaptics_usb", .probe = synusb_probe, .disconnect = synusb_disconnect, .id_table = synusb_idtable, .suspend = synusb_suspend, .resume = synusb_resume, .pre_reset = synusb_pre_reset, .post_reset = synusb_post_reset, .reset_resume = synusb_reset_resume, .supports_autosuspend = 1, }; module_usb_driver(synusb_driver); MODULE_AUTHOR("Rob Miller <rob@inpharmatica.co.uk>, " "Ron Lee <ron@debian.org>, " "Jan Steinhoff <cpad@jan-steinhoff.de>"); MODULE_DESCRIPTION("Synaptics USB device driver"); MODULE_LICENSE("GPL"); |
| 1171 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * cls_cgroup.h Control Group Classifier * * Authors: Thomas Graf <tgraf@suug.ch> */ #ifndef _NET_CLS_CGROUP_H #define _NET_CLS_CGROUP_H #include <linux/cgroup.h> #include <linux/hardirq.h> #include <linux/rcupdate.h> #include <net/sock.h> #include <net/inet_sock.h> #ifdef CONFIG_CGROUP_NET_CLASSID struct cgroup_cls_state { struct cgroup_subsys_state css; u32 classid; }; struct cgroup_cls_state *task_cls_state(struct task_struct *p); static inline u32 task_cls_classid(struct task_struct *p) { u32 classid; if (in_interrupt()) return 0; rcu_read_lock(); classid = container_of(task_css(p, net_cls_cgrp_id), struct cgroup_cls_state, css)->classid; rcu_read_unlock(); return classid; } static inline void sock_update_classid(struct sock_cgroup_data *skcd) { u32 classid; classid = task_cls_classid(current); sock_cgroup_set_classid(skcd, classid); } static inline u32 __task_get_classid(struct task_struct *task) { return task_cls_state(task)->classid; } static inline u32 task_get_classid(const struct sk_buff *skb) { u32 classid = __task_get_classid(current); /* Due to the nature of the classifier it is required to ignore all * packets originating from softirq context as accessing `current' * would lead to false results. * * This test assumes that all callers of dev_queue_xmit() explicitly * disable bh. Knowing this, it is possible to detect softirq based * calls by looking at the number of nested bh disable calls because * softirqs always disables bh. */ if (softirq_count()) { struct sock *sk = skb_to_full_sk(skb); /* If there is an sock_cgroup_classid we'll use that. */ if (!sk || !sk_fullsock(sk)) return 0; classid = sock_cgroup_classid(&sk->sk_cgrp_data); } return classid; } #else /* !CONFIG_CGROUP_NET_CLASSID */ static inline void sock_update_classid(struct sock_cgroup_data *skcd) { } static inline u32 task_get_classid(const struct sk_buff *skb) { return 0; } #endif /* CONFIG_CGROUP_NET_CLASSID */ #endif /* _NET_CLS_CGROUP_H */ |
| 2 5 120 121 121 78 55 78 56 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Synchronous Compression operations * * Copyright 2015 LG Electronics Inc. * Copyright (c) 2016, Intel Corporation * Author: Giovanni Cabiddu <giovanni.cabiddu@intel.com> */ #include <crypto/internal/scompress.h> #include <crypto/scatterwalk.h> #include <linux/cpumask.h> #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/overflow.h> #include <linux/scatterlist.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/workqueue.h> #include <net/netlink.h> #include "compress.h" struct scomp_scratch { spinlock_t lock; union { void *src; unsigned long saddr; }; }; static DEFINE_PER_CPU(struct scomp_scratch, scomp_scratch) = { .lock = __SPIN_LOCK_UNLOCKED(scomp_scratch.lock), }; static const struct crypto_type crypto_scomp_type; static int scomp_scratch_users; static DEFINE_MUTEX(scomp_lock); static cpumask_t scomp_scratch_want; static void scomp_scratch_workfn(struct work_struct *work); static DECLARE_WORK(scomp_scratch_work, scomp_scratch_workfn); static int __maybe_unused crypto_scomp_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_comp rscomp; memset(&rscomp, 0, sizeof(rscomp)); strscpy(rscomp.type, "scomp", sizeof(rscomp.type)); return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(rscomp), &rscomp); } static void crypto_scomp_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_scomp_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : scomp\n"); } static void crypto_scomp_free_scratches(void) { struct scomp_scratch *scratch; int i; for_each_possible_cpu(i) { scratch = per_cpu_ptr(&scomp_scratch, i); free_page(scratch->saddr); scratch->src = NULL; } } static int scomp_alloc_scratch(struct scomp_scratch *scratch, int cpu) { int node = cpu_to_node(cpu); struct page *page; page = alloc_pages_node(node, GFP_KERNEL, 0); if (!page) return -ENOMEM; spin_lock_bh(&scratch->lock); scratch->src = page_address(page); spin_unlock_bh(&scratch->lock); return 0; } static void scomp_scratch_workfn(struct work_struct *work) { int cpu; for_each_cpu(cpu, &scomp_scratch_want) { struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, cpu); if (scratch->src) continue; if (scomp_alloc_scratch(scratch, cpu)) break; cpumask_clear_cpu(cpu, &scomp_scratch_want); } } static int crypto_scomp_alloc_scratches(void) { unsigned int i = cpumask_first(cpu_possible_mask); struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, i); return scomp_alloc_scratch(scratch, i); } static int crypto_scomp_init_tfm(struct crypto_tfm *tfm) { struct scomp_alg *alg = crypto_scomp_alg(__crypto_scomp_tfm(tfm)); int ret = 0; mutex_lock(&scomp_lock); ret = crypto_acomp_alloc_streams(&alg->streams); if (ret) goto unlock; if (!scomp_scratch_users++) { ret = crypto_scomp_alloc_scratches(); if (ret) scomp_scratch_users--; } unlock: mutex_unlock(&scomp_lock); return ret; } static struct scomp_scratch *scomp_lock_scratch(void) __acquires(scratch) { int cpu = raw_smp_processor_id(); struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, cpu); spin_lock(&scratch->lock); if (likely(scratch->src)) return scratch; spin_unlock(&scratch->lock); cpumask_set_cpu(cpu, &scomp_scratch_want); schedule_work(&scomp_scratch_work); scratch = per_cpu_ptr(&scomp_scratch, cpumask_first(cpu_possible_mask)); spin_lock(&scratch->lock); return scratch; } static inline void scomp_unlock_scratch(struct scomp_scratch *scratch) __releases(scratch) { spin_unlock(&scratch->lock); } static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); struct crypto_scomp **tfm_ctx = acomp_tfm_ctx(tfm); bool src_isvirt = acomp_request_src_isvirt(req); bool dst_isvirt = acomp_request_dst_isvirt(req); struct crypto_scomp *scomp = *tfm_ctx; struct crypto_acomp_stream *stream; struct scomp_scratch *scratch; unsigned int slen = req->slen; unsigned int dlen = req->dlen; struct page *spage, *dpage; unsigned int n; const u8 *src; size_t soff; size_t doff; u8 *dst; int ret; if (!req->src || !slen) return -EINVAL; if (!req->dst || !dlen) return -EINVAL; if (dst_isvirt) dst = req->dvirt; else { if (dlen <= req->dst->length) { dpage = sg_page(req->dst); doff = req->dst->offset; } else return -ENOSYS; dpage += doff / PAGE_SIZE; doff = offset_in_page(doff); n = (dlen - 1) / PAGE_SIZE; n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE; if (PageHighMem(dpage + n) && size_add(doff, dlen) > PAGE_SIZE) return -ENOSYS; dst = kmap_local_page(dpage) + doff; } if (src_isvirt) src = req->svirt; else { src = NULL; do { if (slen <= req->src->length) { spage = sg_page(req->src); soff = req->src->offset; } else break; spage = spage + soff / PAGE_SIZE; soff = offset_in_page(soff); n = (slen - 1) / PAGE_SIZE; n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE; if (PageHighMem(spage + n) && size_add(soff, slen) > PAGE_SIZE) break; src = kmap_local_page(spage) + soff; } while (0); } stream = crypto_acomp_lock_stream_bh(&crypto_scomp_alg(scomp)->streams); if (!src_isvirt && !src) { const u8 *src; scratch = scomp_lock_scratch(); src = scratch->src; memcpy_from_sglist(scratch->src, req->src, 0, slen); if (dir) ret = crypto_scomp_compress(scomp, src, slen, dst, &dlen, stream->ctx); else ret = crypto_scomp_decompress(scomp, src, slen, dst, &dlen, stream->ctx); scomp_unlock_scratch(scratch); } else if (dir) ret = crypto_scomp_compress(scomp, src, slen, dst, &dlen, stream->ctx); else ret = crypto_scomp_decompress(scomp, src, slen, dst, &dlen, stream->ctx); crypto_acomp_unlock_stream_bh(stream); req->dlen = dlen; if (!src_isvirt && src) kunmap_local(src); if (!dst_isvirt) { kunmap_local(dst); dlen += doff; for (;;) { flush_dcache_page(dpage); if (dlen <= PAGE_SIZE) break; dlen -= PAGE_SIZE; dpage++; } } return ret; } static int scomp_acomp_compress(struct acomp_req *req) { return scomp_acomp_comp_decomp(req, 1); } static int scomp_acomp_decompress(struct acomp_req *req) { return scomp_acomp_comp_decomp(req, 0); } static void crypto_exit_scomp_ops_async(struct crypto_tfm *tfm) { struct crypto_scomp **ctx = crypto_tfm_ctx(tfm); crypto_free_scomp(*ctx); flush_work(&scomp_scratch_work); mutex_lock(&scomp_lock); if (!--scomp_scratch_users) crypto_scomp_free_scratches(); mutex_unlock(&scomp_lock); } int crypto_init_scomp_ops_async(struct crypto_tfm *tfm) { struct crypto_alg *calg = tfm->__crt_alg; struct crypto_acomp *crt = __crypto_acomp_tfm(tfm); struct crypto_scomp **ctx = crypto_tfm_ctx(tfm); struct crypto_scomp *scomp; if (!crypto_mod_get(calg)) return -EAGAIN; scomp = crypto_create_tfm(calg, &crypto_scomp_type); if (IS_ERR(scomp)) { crypto_mod_put(calg); return PTR_ERR(scomp); } *ctx = scomp; tfm->exit = crypto_exit_scomp_ops_async; crt->compress = scomp_acomp_compress; crt->decompress = scomp_acomp_decompress; return 0; } static void crypto_scomp_destroy(struct crypto_alg *alg) { struct scomp_alg *scomp = __crypto_scomp_alg(alg); crypto_acomp_free_streams(&scomp->streams); } static const struct crypto_type crypto_scomp_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_scomp_init_tfm, .destroy = crypto_scomp_destroy, #ifdef CONFIG_PROC_FS .show = crypto_scomp_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_scomp_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SCOMPRESS, .tfmsize = offsetof(struct crypto_scomp, base), .algsize = offsetof(struct scomp_alg, base), }; static void scomp_prepare_alg(struct scomp_alg *alg) { struct crypto_alg *base = &alg->calg.base; comp_prepare_alg(&alg->calg); base->cra_flags |= CRYPTO_ALG_REQ_VIRT; } int crypto_register_scomp(struct scomp_alg *alg) { struct crypto_alg *base = &alg->calg.base; scomp_prepare_alg(alg); base->cra_type = &crypto_scomp_type; base->cra_flags |= CRYPTO_ALG_TYPE_SCOMPRESS; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_scomp); void crypto_unregister_scomp(struct scomp_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_scomp); int crypto_register_scomps(struct scomp_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_scomp(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_scomp(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_scomps); void crypto_unregister_scomps(struct scomp_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_scomp(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_scomps); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Synchronous compression type"); |
| 9 9 4 9 9 5 9 9 2 7 12 1 6 5 1 1 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0-or-later /* General persistent per-UID keyrings register * * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/user_namespace.h> #include <linux/cred.h> #include "internal.h" unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */ /* * Create the persistent keyring register for the current user namespace. * * Called with the namespace's sem locked for writing. */ static int key_create_persistent_register(struct user_namespace *ns) { struct key *reg = keyring_alloc(".persistent_register", KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ), KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(reg)) return PTR_ERR(reg); ns->persistent_keyring_register = reg; return 0; } /* * Create the persistent keyring for the specified user. * * Called with the namespace's sem locked for writing. */ static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid, struct keyring_index_key *index_key) { struct key *persistent; key_ref_t reg_ref, persistent_ref; if (!ns->persistent_keyring_register) { long err = key_create_persistent_register(ns); if (err < 0) return ERR_PTR(err); } else { reg_ref = make_key_ref(ns->persistent_keyring_register, true); persistent_ref = find_key_to_update(reg_ref, index_key); if (persistent_ref) return persistent_ref; } persistent = keyring_alloc(index_key->description, uid, INVALID_GID, current_cred(), ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ), KEY_ALLOC_NOT_IN_QUOTA, NULL, ns->persistent_keyring_register); if (IS_ERR(persistent)) return ERR_CAST(persistent); return make_key_ref(persistent, true); } /* * Get the persistent keyring for a specific UID and link it to the nominated * keyring. */ static long key_get_persistent(struct user_namespace *ns, kuid_t uid, key_ref_t dest_ref) { struct keyring_index_key index_key; struct key *persistent; key_ref_t reg_ref, persistent_ref; char buf[32]; long ret; /* Look in the register if it exists */ memset(&index_key, 0, sizeof(index_key)); index_key.type = &key_type_keyring; index_key.description = buf; index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid)); key_set_index_key(&index_key); if (ns->persistent_keyring_register) { reg_ref = make_key_ref(ns->persistent_keyring_register, true); down_read(&ns->keyring_sem); persistent_ref = find_key_to_update(reg_ref, &index_key); up_read(&ns->keyring_sem); if (persistent_ref) goto found; } /* It wasn't in the register, so we'll need to create it. We might * also need to create the register. */ down_write(&ns->keyring_sem); persistent_ref = key_create_persistent(ns, uid, &index_key); up_write(&ns->keyring_sem); if (!IS_ERR(persistent_ref)) goto found; return PTR_ERR(persistent_ref); found: ret = key_task_permission(persistent_ref, current_cred(), KEY_NEED_LINK); if (ret == 0) { persistent = key_ref_to_ptr(persistent_ref); ret = key_link(key_ref_to_ptr(dest_ref), persistent); if (ret == 0) { key_set_timeout(persistent, persistent_keyring_expiry); ret = persistent->serial; } } key_ref_put(persistent_ref); return ret; } /* * Get the persistent keyring for a specific UID and link it to the nominated * keyring. */ long keyctl_get_persistent(uid_t _uid, key_serial_t destid) { struct user_namespace *ns = current_user_ns(); key_ref_t dest_ref; kuid_t uid; long ret; /* -1 indicates the current user */ if (_uid == (uid_t)-1) { uid = current_uid(); } else { uid = make_kuid(ns, _uid); if (!uid_valid(uid)) return -EINVAL; /* You can only see your own persistent cache if you're not * sufficiently privileged. */ if (!uid_eq(uid, current_uid()) && !uid_eq(uid, current_euid()) && !ns_capable(ns, CAP_SETUID)) return -EPERM; } /* There must be a destination keyring */ dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(dest_ref)) return PTR_ERR(dest_ref); if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) { ret = -ENOTDIR; goto out_put_dest; } ret = key_get_persistent(ns, uid, dest_ref); out_put_dest: key_ref_put(dest_ref); return ret; } |
| 44 35 43 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 | /* * linux/fs/nls/nls_koi8-u.c * * Charset koi8-u translation tables. * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590, /* 0x90*/ 0x2591, 0x2592, 0x2593, 0x2320, 0x25a0, 0x2219, 0x221a, 0x2248, 0x2264, 0x2265, 0x00a0, 0x2321, 0x00b0, 0x00b2, 0x00b7, 0x00f7, /* 0xa0*/ 0x2550, 0x2551, 0x2552, 0x0451, 0x0454, 0x2554, 0x0456, 0x0457, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x0491, 0x255d, 0x255e, /* 0xb0*/ 0x255f, 0x2560, 0x2561, 0x0401, 0x0404, 0x2563, 0x0406, 0x0407, 0x2566, 0x2567, 0x2568, 0x2569, 0x256a, 0x0490, 0x256c, 0x00a9, /* 0xc0*/ 0x044e, 0x0430, 0x0431, 0x0446, 0x0434, 0x0435, 0x0444, 0x0433, 0x0445, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, /* 0xd0*/ 0x043f, 0x044f, 0x0440, 0x0441, 0x0442, 0x0443, 0x0436, 0x0432, 0x044c, 0x044b, 0x0437, 0x0448, 0x044d, 0x0449, 0x0447, 0x044a, /* 0xe0*/ 0x042e, 0x0410, 0x0411, 0x0426, 0x0414, 0x0415, 0x0424, 0x0413, 0x0425, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, /* 0xf0*/ 0x041f, 0x042f, 0x0420, 0x0421, 0x0422, 0x0423, 0x0416, 0x0412, 0x042c, 0x042b, 0x0417, 0x0428, 0x042d, 0x0429, 0x0427, 0x042a, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x9a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0xbf, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x9c, 0x00, 0x9d, 0x00, 0x00, 0x00, 0x00, 0x9e, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9f, /* 0xf0-0xf7 */ }; static const unsigned char page04[256] = { 0x00, 0xb3, 0x00, 0x00, 0xb4, 0x00, 0xb6, 0xb7, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa, /* 0x10-0x17 */ 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, /* 0x18-0x1f */ 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe, /* 0x20-0x27 */ 0xfb, 0xfd, 0xff, 0xf9, 0xf8, 0xfc, 0xe0, 0xf1, /* 0x28-0x2f */ 0xc1, 0xc2, 0xd7, 0xc7, 0xc4, 0xc5, 0xd6, 0xda, /* 0x30-0x37 */ 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, /* 0x38-0x3f */ 0xd2, 0xd3, 0xd4, 0xd5, 0xc6, 0xc8, 0xc3, 0xde, /* 0x40-0x47 */ 0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1, /* 0x48-0x4f */ 0x00, 0xa3, 0x00, 0x00, 0xa4, 0x00, 0xa6, 0xa7, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xbd, 0xad, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x95, 0x96, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x97, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x98, 0x99, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x93, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0x80, 0x00, 0x81, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x82, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x83, 0x00, 0x00, 0x00, 0x84, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x85, 0x00, 0x00, 0x00, 0x86, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x87, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x88, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x89, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x8a, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xa0, 0xa1, 0xa2, 0x00, 0xa5, 0x00, 0x00, 0xa8, /* 0x50-0x57 */ 0xa9, 0xaa, 0xab, 0xac, 0x00, 0xae, 0xaf, 0xb0, /* 0x58-0x5f */ 0xb1, 0xb2, 0x00, 0xb5, 0x00, 0x00, 0xb8, 0xb9, /* 0x60-0x67 */ 0xba, 0xbb, 0xbc, 0x00, 0xbe, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x8b, 0x00, 0x00, 0x00, 0x8c, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x8d, 0x00, 0x00, 0x00, 0x8e, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x8f, 0x90, 0x91, 0x92, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x94, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xa3, 0xa4, 0xb5, 0xa6, 0xa7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xad, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xb3, 0xb4, 0xa5, 0xb6, 0xb7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xbd, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "koi8-u", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_koi8_u(void) { return register_nls(&table); } static void __exit exit_nls_koi8_u(void) { unregister_nls(&table); } module_init(init_nls_koi8_u) module_exit(exit_nls_koi8_u) MODULE_DESCRIPTION("NLS KOI8-U (Ukrainian)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 389 285 121 123 184 185 100 100 162 162 174 175 110 111 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/random.h> #include <linux/hrtimer.h> #include <linux/ktime.h> #include <linux/string.h> #include <linux/net.h> #include <linux/siphash.h> #include <net/secure_seq.h> #if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) #include <linux/in6.h> #include <net/tcp.h> static siphash_aligned_key_t net_secret; static siphash_aligned_key_t ts_secret; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } static __always_inline void ts_secret_init(void) { net_get_random_once(&ts_secret, sizeof(ts_secret)); } #endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) { /* * As close as possible to RFC 793, which * suggests using a 250 kHz clock. * Further reading shows this assumes 2 Mb/s networks. * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but * we also need to limit the resolution so that the u32 seq * overlaps less than one time per MSL (2 minutes). * Choosing a clock of 64 ns period is OK. (period of 274 s) */ return seq + (ktime_get_real_ns() >> 6); } #endif #if IS_ENABLED(CONFIG_IPV6) u32 secure_tcpv6_ts_off(const struct net *net, const __be32 *saddr, const __be32 *daddr) { const struct { struct in6_addr saddr; struct in6_addr daddr; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, }; if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); return siphash(&combined, offsetofend(typeof(combined), daddr), &ts_secret); } EXPORT_IPV6_MOD(secure_tcpv6_ts_off); u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; __be16 sport; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, .sport = sport, .dport = dport }; u32 hash; net_secret_init(); hash = siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); return seq_scale(hash); } EXPORT_SYMBOL(secure_tcpv6_seq); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); } EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); return siphash_2u32((__force u32)saddr, (__force u32)daddr, &ts_secret); } /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) { u32 hash; net_secret_init(); hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, &net_secret); return seq_scale(hash); } EXPORT_SYMBOL_GPL(secure_tcp_seq); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); return siphash_4u32((__force u32)saddr, (__force u32)daddr, (__force u16)dport, jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif |
| 16 12 113 17 17 17 48 1123 1120 1121 1226 112 1123 631 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl_sz("net", empty, 0); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } /* Verify that sysctls for non-init netns are safe by either: * 1) being read-only, or * 2) having a data pointer which points outside of the global kernel/module * data segment, and rather into the heap where a per-net object was * allocated. */ static void ensure_safe_net_sysctl(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { struct ctl_table *ent; pr_debug("Registering net sysctl (net %p): %s\n", net, path); ent = table; for (size_t i = 0; i < table_size; ent++, i++) { unsigned long addr; const char *where; pr_debug(" procname=%s mode=%o proc_handler=%ps data=%p\n", ent->procname, ent->mode, ent->proc_handler, ent->data); /* If it's not writable inside the netns, then it can't hurt. */ if ((ent->mode & 0222) == 0) { pr_debug(" Not writable by anyone\n"); continue; } /* Where does data point? */ addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; else if (is_kernel_core_data(addr)) where = "kernel"; else continue; /* If it is writable and points to kernel/module global * data, then it's probably a netns leak. */ WARN(1, "sysctl %s/%s: data points to %s global data: %ps\n", path, ent->procname, where, ent->data); /* Make it "safe" by dropping writable perms */ ent->mode &= ~0222; } } struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table, table_size); return __register_sysctl_table(&net->sysctls, path, table, table_size); } EXPORT_SYMBOL_GPL(register_net_sysctl_sz); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table); |
| 6 3 3 7 6 2 5 3 6 2 5 3 5 3 5 3 7 10 10 193 13 16 15 167 166 167 19 95 2 19 25 8 89 88 24 24 19 20 36 36 130 15 4 13 16 15 32 17 15 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include <net/genetlink.h> #include <net/sock.h> #include "devl_internal.h" #define DEVLINK_NL_FLAG_NEED_PORT BIT(0) #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_DEV_LOCK BIT(2) static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; struct devlink_nl_sock_priv { struct devlink_obj_desc __rcu *flt; spinlock_t flt_lock; /* Protects flt. */ }; static void devlink_nl_sock_priv_init(void *priv) { struct devlink_nl_sock_priv *sk_priv = priv; spin_lock_init(&sk_priv->flt_lock); } static void devlink_nl_sock_priv_destroy(void *priv) { struct devlink_nl_sock_priv *sk_priv = priv; struct devlink_obj_desc *flt; flt = rcu_dereference_protected(sk_priv->flt, true); kfree_rcu(flt, rcu); } int devlink_nl_notify_filter_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_nl_sock_priv *sk_priv; struct nlattr **attrs = info->attrs; struct devlink_obj_desc *flt; size_t data_offset = 0; size_t data_size = 0; char *pos; if (attrs[DEVLINK_ATTR_BUS_NAME]) data_size = size_add(data_size, nla_len(attrs[DEVLINK_ATTR_BUS_NAME]) + 1); if (attrs[DEVLINK_ATTR_DEV_NAME]) data_size = size_add(data_size, nla_len(attrs[DEVLINK_ATTR_DEV_NAME]) + 1); flt = kzalloc(size_add(sizeof(*flt), data_size), GFP_KERNEL); if (!flt) return -ENOMEM; pos = (char *) flt->data; if (attrs[DEVLINK_ATTR_BUS_NAME]) { data_offset += nla_strscpy(pos, attrs[DEVLINK_ATTR_BUS_NAME], data_size) + 1; flt->bus_name = pos; pos += data_offset; } if (attrs[DEVLINK_ATTR_DEV_NAME]) { nla_strscpy(pos, attrs[DEVLINK_ATTR_DEV_NAME], data_size - data_offset); flt->dev_name = pos; } if (attrs[DEVLINK_ATTR_PORT_INDEX]) { flt->port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); flt->port_index_valid = true; } /* Don't attach empty filter. */ if (!flt->bus_name && !flt->dev_name && !flt->port_index_valid) { kfree(flt); flt = NULL; } sk_priv = genl_sk_priv_get(&devlink_nl_family, NETLINK_CB(skb).sk); if (IS_ERR(sk_priv)) { kfree(flt); return PTR_ERR(sk_priv); } spin_lock(&sk_priv->flt_lock); flt = rcu_replace_pointer(sk_priv->flt, flt, lockdep_is_held(&sk_priv->flt_lock)); spin_unlock(&sk_priv->flt_lock); kfree_rcu(flt, rcu); return 0; } static bool devlink_obj_desc_match(const struct devlink_obj_desc *desc, const struct devlink_obj_desc *flt) { if (desc->bus_name && flt->bus_name && strcmp(desc->bus_name, flt->bus_name)) return false; if (desc->dev_name && flt->dev_name && strcmp(desc->dev_name, flt->dev_name)) return false; if (desc->port_index_valid && flt->port_index_valid && desc->port_index != flt->port_index) return false; return true; } int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data) { struct devlink_obj_desc *desc = data; struct devlink_nl_sock_priv *sk_priv; struct devlink_obj_desc *flt; int ret = 0; rcu_read_lock(); sk_priv = __genl_sk_priv_get(&devlink_nl_family, dsk); if (!IS_ERR_OR_NULL(sk_priv)) { flt = rcu_dereference(sk_priv->flt); if (flt) ret = !devlink_obj_desc_match(desc, flt); } rcu_read_unlock(); return ret; } int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net, struct devlink *devlink, int attrtype) { struct nlattr *nested_attr; struct net *devl_net; nested_attr = nla_nest_start(msg, attrtype); if (!nested_attr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; rcu_read_lock(); devl_net = read_pnet_rcu(&devlink->_net); if (!net_eq(net, devl_net)) { int id = peernet2id_alloc(net, devl_net, GFP_ATOMIC); rcu_read_unlock(); if (nla_put_s32(msg, DEVLINK_ATTR_NETNS_ID, id)) return -EMSGSIZE; } else { rcu_read_unlock(); } nla_nest_end(msg, nested_attr); return 0; nla_put_failure: nla_nest_cancel(msg, nested_attr); return -EMSGSIZE; } int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info) { int err; if (*msg) { err = genlmsg_reply(*msg, info); if (err) return err; } *msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*msg) return -ENOMEM; return 0; } struct devlink * devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, bool dev_lock) { struct devlink *devlink; unsigned long index; char *busname; char *devname; if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) return ERR_PTR(-EINVAL); busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); devlinks_xa_for_each_registered_get(net, index, devlink) { if (strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0) { devl_dev_lock(devlink, dev_lock); if (devl_is_registered(devlink)) return devlink; devl_dev_unlock(devlink, dev_lock); } devlink_put(devlink); } return ERR_PTR(-ENODEV); } static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info, u8 flags) { bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK; struct devlink_port *devlink_port; struct devlink *devlink; int err; devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs, dev_lock); if (IS_ERR(devlink)) return PTR_ERR(devlink); info->user_ptr[0] = devlink; if (flags & DEVLINK_NL_FLAG_NEED_PORT) { devlink_port = devlink_port_get_from_info(devlink, info); if (IS_ERR(devlink_port)) { err = PTR_ERR(devlink_port); goto unlock; } info->user_ptr[1] = devlink_port; } else if (flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { devlink_port = devlink_port_get_from_info(devlink, info); if (!IS_ERR(devlink_port)) info->user_ptr[1] = devlink_port; } return 0; unlock: devl_dev_unlock(devlink, dev_lock); devlink_put(devlink); return err; } int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { return __devlink_nl_pre_doit(skb, info, 0); } int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT); } int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK); } int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT); } static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info, u8 flags) { bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK; struct devlink *devlink; devlink = info->user_ptr[0]; devl_dev_unlock(devlink, dev_lock); devlink_put(devlink); } void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { __devlink_nl_post_doit(skb, info, 0); } void devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { __devlink_nl_post_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK); } static int devlink_nl_inst_single_dumpit(struct sk_buff *msg, struct netlink_callback *cb, int flags, devlink_nl_dump_one_func_t *dump_one, struct nlattr **attrs) { struct devlink *devlink; int err; devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED); devl_unlock(devlink); devlink_put(devlink); if (err != -EMSGSIZE) return err; return msg->len; } static int devlink_nl_inst_iter_dumpit(struct sk_buff *msg, struct netlink_callback *cb, int flags, devlink_nl_dump_one_func_t *dump_one) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink *devlink; int err = 0; while ((devlink = devlinks_xa_find_get(sock_net(msg->sk), &state->instance))) { devl_lock(devlink); if (devl_is_registered(devlink)) err = dump_one(msg, devlink, cb, flags); else err = 0; devl_unlock(devlink); devlink_put(devlink); if (err) break; state->instance++; /* restart sub-object walk for the next instance */ state->idx = 0; } if (err != -EMSGSIZE) return err; return msg->len; } int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, devlink_nl_dump_one_func_t *dump_one) { const struct genl_info *info = genl_info_dump(cb); struct nlattr **attrs = info->attrs; int flags = NLM_F_MULTI; if (attrs && (attrs[DEVLINK_ATTR_BUS_NAME] || attrs[DEVLINK_ATTR_DEV_NAME])) return devlink_nl_inst_single_dumpit(msg, cb, flags, dump_one, attrs); else return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one); } struct genl_family devlink_nl_family __ro_after_init = { .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, .netnsok = true, .parallel_ops = true, .module = THIS_MODULE, .split_ops = devlink_nl_ops, .n_split_ops = ARRAY_SIZE(devlink_nl_ops), .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), .sock_priv_size = sizeof(struct devlink_nl_sock_priv), .sock_priv_init = devlink_nl_sock_priv_init, .sock_priv_destroy = devlink_nl_sock_priv_destroy, }; |
| 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 1 6 6 6 6 6 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_trace.h" #include "xfs_trans_priv.h" #include "xfs_buf_item.h" #include "xfs_log.h" #include "xfs_error.h" #include "xfs_log_priv.h" #include "xfs_log_recover.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" STATIC void xlog_recover_inode_ra_pass2( struct xlog *log, struct xlog_recover_item *item) { if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) { struct xfs_inode_log_format *ilfp = item->ri_buf[0].iov_base; xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len, &xfs_inode_buf_ra_ops); } else { struct xfs_inode_log_format_32 *ilfp = item->ri_buf[0].iov_base; xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len, &xfs_inode_buf_ra_ops); } } /* * Inode fork owner changes * * If we have been told that we have to reparent the inode fork, it's because an * extent swap operation on a CRC enabled filesystem has been done and we are * replaying it. We need to walk the BMBT of the appropriate fork and change the * owners of it. * * The complexity here is that we don't have an inode context to work with, so * after we've replayed the inode we need to instantiate one. This is where the * fun begins. * * We are in the middle of log recovery, so we can't run transactions. That * means we cannot use cache coherent inode instantiation via xfs_iget(), as * that will result in the corresponding iput() running the inode through * xfs_inactive(). If we've just replayed an inode core that changes the link * count to zero (i.e. it's been unlinked), then xfs_inactive() will run * transactions (bad!). * * So, to avoid this, we instantiate an inode directly from the inode core we've * just recovered. We have the buffer still locked, and all we really need to * instantiate is the inode core and the forks being modified. We can do this * manually, then run the inode btree owner change, and then tear down the * xfs_inode without having to run any transactions at all. * * Also, because we don't have a transaction context available here but need to * gather all the buffers we modify for writeback so we pass the buffer_list * instead for the operation to use. */ STATIC int xfs_recover_inode_owner_change( struct xfs_mount *mp, struct xfs_dinode *dip, struct xfs_inode_log_format *in_f, struct list_head *buffer_list) { struct xfs_inode *ip; int error; ASSERT(in_f->ilf_fields & (XFS_ILOG_DOWNER|XFS_ILOG_AOWNER)); ip = xfs_inode_alloc(mp, in_f->ilf_ino); if (!ip) return -ENOMEM; /* instantiate the inode */ ASSERT(dip->di_version >= 3); error = xfs_inode_from_disk(ip, dip); if (error) goto out_free_ip; if (in_f->ilf_fields & XFS_ILOG_DOWNER) { ASSERT(in_f->ilf_fields & XFS_ILOG_DBROOT); error = xfs_bmbt_change_owner(NULL, ip, XFS_DATA_FORK, ip->i_ino, buffer_list); if (error) goto out_free_ip; } if (in_f->ilf_fields & XFS_ILOG_AOWNER) { ASSERT(in_f->ilf_fields & XFS_ILOG_ABROOT); error = xfs_bmbt_change_owner(NULL, ip, XFS_ATTR_FORK, ip->i_ino, buffer_list); if (error) goto out_free_ip; } out_free_ip: xfs_inode_free(ip); return error; } static inline bool xfs_log_dinode_has_bigtime(const struct xfs_log_dinode *ld) { return ld->di_version >= 3 && (ld->di_flags2 & XFS_DIFLAG2_BIGTIME); } /* Convert a log timestamp to an ondisk timestamp. */ static inline xfs_timestamp_t xfs_log_dinode_to_disk_ts( struct xfs_log_dinode *from, const xfs_log_timestamp_t its) { struct xfs_legacy_timestamp *lts; struct xfs_log_legacy_timestamp *lits; xfs_timestamp_t ts; if (xfs_log_dinode_has_bigtime(from)) return cpu_to_be64(its); lts = (struct xfs_legacy_timestamp *)&ts; lits = (struct xfs_log_legacy_timestamp *)&its; lts->t_sec = cpu_to_be32(lits->t_sec); lts->t_nsec = cpu_to_be32(lits->t_nsec); return ts; } static inline bool xfs_log_dinode_has_large_extent_counts( const struct xfs_log_dinode *ld) { return ld->di_version >= 3 && (ld->di_flags2 & XFS_DIFLAG2_NREXT64); } static inline void xfs_log_dinode_to_disk_iext_counters( struct xfs_log_dinode *from, struct xfs_dinode *to) { if (xfs_log_dinode_has_large_extent_counts(from)) { to->di_big_nextents = cpu_to_be64(from->di_big_nextents); to->di_big_anextents = cpu_to_be32(from->di_big_anextents); to->di_nrext64_pad = cpu_to_be16(from->di_nrext64_pad); } else { to->di_nextents = cpu_to_be32(from->di_nextents); to->di_anextents = cpu_to_be16(from->di_anextents); } } STATIC void xfs_log_dinode_to_disk( struct xfs_log_dinode *from, struct xfs_dinode *to, xfs_lsn_t lsn) { to->di_magic = cpu_to_be16(from->di_magic); to->di_mode = cpu_to_be16(from->di_mode); to->di_version = from->di_version; to->di_format = from->di_format; to->di_metatype = cpu_to_be16(from->di_metatype); to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); to->di_nlink = cpu_to_be32(from->di_nlink); to->di_projid_lo = cpu_to_be16(from->di_projid_lo); to->di_projid_hi = cpu_to_be16(from->di_projid_hi); to->di_atime = xfs_log_dinode_to_disk_ts(from, from->di_atime); to->di_mtime = xfs_log_dinode_to_disk_ts(from, from->di_mtime); to->di_ctime = xfs_log_dinode_to_disk_ts(from, from->di_ctime); to->di_size = cpu_to_be64(from->di_size); to->di_nblocks = cpu_to_be64(from->di_nblocks); to->di_extsize = cpu_to_be32(from->di_extsize); to->di_forkoff = from->di_forkoff; to->di_aformat = from->di_aformat; to->di_dmevmask = cpu_to_be32(from->di_dmevmask); to->di_dmstate = cpu_to_be16(from->di_dmstate); to->di_flags = cpu_to_be16(from->di_flags); to->di_gen = cpu_to_be32(from->di_gen); if (from->di_version == 3) { to->di_changecount = cpu_to_be64(from->di_changecount); to->di_crtime = xfs_log_dinode_to_disk_ts(from, from->di_crtime); to->di_flags2 = cpu_to_be64(from->di_flags2); /* also covers the di_used_blocks union arm: */ to->di_cowextsize = cpu_to_be32(from->di_cowextsize); to->di_ino = cpu_to_be64(from->di_ino); to->di_lsn = cpu_to_be64(lsn); memset(to->di_pad2, 0, sizeof(to->di_pad2)); uuid_copy(&to->di_uuid, &from->di_uuid); to->di_v3_pad = 0; } else { to->di_flushiter = cpu_to_be16(from->di_flushiter); memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad)); } xfs_log_dinode_to_disk_iext_counters(from, to); } STATIC int xlog_dinode_verify_extent_counts( struct xfs_mount *mp, struct xfs_log_dinode *ldip) { xfs_extnum_t nextents; xfs_aextnum_t anextents; if (xfs_log_dinode_has_large_extent_counts(ldip)) { if (!xfs_has_large_extent_counts(mp) || (ldip->di_nrext64_pad != 0)) { XFS_CORRUPTION_ERROR( "Bad log dinode large extent count format", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, large extent counts %d, padding 0x%x", ldip->di_ino, xfs_has_large_extent_counts(mp), ldip->di_nrext64_pad); return -EFSCORRUPTED; } nextents = ldip->di_big_nextents; anextents = ldip->di_big_anextents; } else { if (ldip->di_version == 3 && ldip->di_v3_pad != 0) { XFS_CORRUPTION_ERROR( "Bad log dinode di_v3_pad", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, di_v3_pad 0x%llx", ldip->di_ino, ldip->di_v3_pad); return -EFSCORRUPTED; } nextents = ldip->di_nextents; anextents = ldip->di_anextents; } if (unlikely(nextents + anextents > ldip->di_nblocks)) { XFS_CORRUPTION_ERROR("Bad log dinode extent counts", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, large extent counts %d, nextents 0x%llx, anextents 0x%x, nblocks 0x%llx", ldip->di_ino, xfs_has_large_extent_counts(mp), nextents, anextents, ldip->di_nblocks); return -EFSCORRUPTED; } return 0; } static inline int xlog_recover_inode_dbroot( struct xfs_mount *mp, void *src, unsigned int len, struct xfs_dinode *dip) { void *dfork = XFS_DFORK_DPTR(dip); unsigned int dsize = XFS_DFORK_DSIZE(dip, mp); switch (dip->di_format) { case XFS_DINODE_FMT_BTREE: xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize); break; case XFS_DINODE_FMT_META_BTREE: switch (be16_to_cpu(dip->di_metatype)) { case XFS_METAFILE_RTRMAP: xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); return 0; case XFS_METAFILE_RTREFCOUNT: xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize); return 0; default: ASSERT(0); return -EFSCORRUPTED; } break; default: ASSERT(0); return -EFSCORRUPTED; } return 0; } STATIC int xlog_recover_inode_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t current_lsn) { struct xfs_inode_log_format *in_f; struct xfs_mount *mp = log->l_mp; struct xfs_buf *bp; struct xfs_dinode *dip; int len; char *src; char *dest; int error; int attr_index; uint fields; struct xfs_log_dinode *ldip; uint isize; int need_free = 0; xfs_failaddr_t fa; if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) { in_f = item->ri_buf[0].iov_base; } else { in_f = kmalloc(sizeof(struct xfs_inode_log_format), GFP_KERNEL | __GFP_NOFAIL); need_free = 1; error = xfs_inode_item_format_convert(&item->ri_buf[0], in_f); if (error) goto error; } /* * Inode buffers can be freed, look out for it, * and do not replay the inode. */ if (xlog_is_buffer_cancelled(log, in_f->ilf_blkno, in_f->ilf_len)) { error = 0; trace_xfs_log_recover_inode_cancel(log, in_f); goto error; } trace_xfs_log_recover_inode_recover(log, in_f); error = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0, &bp, &xfs_inode_buf_ops); if (error) goto error; ASSERT(in_f->ilf_fields & XFS_ILOG_CORE); dip = xfs_buf_offset(bp, in_f->ilf_boffset); /* * Make sure the place we're flushing out to really looks * like an inode! */ if (XFS_IS_CORRUPT(mp, !xfs_verify_magic16(bp, dip->di_magic))) { xfs_alert(mp, "%s: Bad inode magic number, dip = "PTR_FMT", dino bp = "PTR_FMT", ino = %lld", __func__, dip, bp, in_f->ilf_ino); error = -EFSCORRUPTED; goto out_release; } ldip = item->ri_buf[1].iov_base; if (XFS_IS_CORRUPT(mp, ldip->di_magic != XFS_DINODE_MAGIC)) { xfs_alert(mp, "%s: Bad inode log record, rec ptr "PTR_FMT", ino %lld", __func__, item, in_f->ilf_ino); error = -EFSCORRUPTED; goto out_release; } /* * If the inode has an LSN in it, recover the inode only if the on-disk * inode's LSN is older than the lsn of the transaction we are * replaying. We can have multiple checkpoints with the same start LSN, * so the current LSN being equal to the on-disk LSN doesn't necessarily * mean that the on-disk inode is more recent than the change being * replayed. * * We must check the current_lsn against the on-disk inode * here because the we can't trust the log dinode to contain a valid LSN * (see comment below before replaying the log dinode for details). * * Note: we still need to replay an owner change even though the inode * is more recent than the transaction as there is no guarantee that all * the btree blocks are more recent than this transaction, too. */ if (dip->di_version >= 3) { xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn); if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) { trace_xfs_log_recover_inode_skip(log, in_f); error = 0; goto out_owner_change; } } /* * di_flushiter is only valid for v1/2 inodes. All changes for v3 inodes * are transactional and if ordering is necessary we can determine that * more accurately by the LSN field in the V3 inode core. Don't trust * the inode versions we might be changing them here - use the * superblock flag to determine whether we need to look at di_flushiter * to skip replay when the on disk inode is newer than the log one */ if (!xfs_has_v3inodes(mp)) { if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { /* * Deal with the wrap case, DI_MAX_FLUSH is less * than smaller numbers */ if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { /* do nothing */ } else { trace_xfs_log_recover_inode_skip(log, in_f); error = 0; goto out_release; } } /* Take the opportunity to reset the flush iteration count */ ldip->di_flushiter = 0; } if (unlikely(S_ISREG(ldip->di_mode))) { if (ldip->di_format != XFS_DINODE_FMT_EXTENTS && ldip->di_format != XFS_DINODE_FMT_BTREE && ldip->di_format != XFS_DINODE_FMT_META_BTREE) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for regular file", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, data fork format 0x%x", in_f->ilf_ino, ldip->di_format); error = -EFSCORRUPTED; goto out_release; } } else if (unlikely(S_ISDIR(ldip->di_mode))) { if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && (ldip->di_format != XFS_DINODE_FMT_BTREE) && (ldip->di_format != XFS_DINODE_FMT_LOCAL)) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for directory", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, data fork format 0x%x", in_f->ilf_ino, ldip->di_format); error = -EFSCORRUPTED; goto out_release; } } error = xlog_dinode_verify_extent_counts(mp, ldip); if (error) goto out_release; if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) { XFS_CORRUPTION_ERROR("Bad log dinode fork offset", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx, di_forkoff 0x%x", in_f->ilf_ino, ldip->di_forkoff); error = -EFSCORRUPTED; goto out_release; } isize = xfs_log_dinode_size(mp); if (unlikely(item->ri_buf[1].iov_len > isize)) { XFS_CORRUPTION_ERROR("Bad log dinode size", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); xfs_alert(mp, "Bad inode 0x%llx log dinode size 0x%zx", in_f->ilf_ino, item->ri_buf[1].iov_len); error = -EFSCORRUPTED; goto out_release; } /* * Recover the log dinode inode into the on disk inode. * * The LSN in the log dinode is garbage - it can be zero or reflect * stale in-memory runtime state that isn't coherent with the changes * logged in this transaction or the changes written to the on-disk * inode. Hence we write the current lSN into the inode because that * matches what xfs_iflush() would write inode the inode when flushing * the changes in this transaction. */ xfs_log_dinode_to_disk(ldip, dip, current_lsn); fields = in_f->ilf_fields; if (fields & XFS_ILOG_DEV) xfs_dinode_put_rdev(dip, in_f->ilf_u.ilfu_rdev); if (in_f->ilf_size == 2) goto out_owner_change; len = item->ri_buf[2].iov_len; src = item->ri_buf[2].iov_base; ASSERT(in_f->ilf_size <= 4); ASSERT((in_f->ilf_size == 3) || (fields & XFS_ILOG_AFORK)); ASSERT(!(fields & XFS_ILOG_DFORK) || (len == xlog_calc_iovec_len(in_f->ilf_dsize))); switch (fields & XFS_ILOG_DFORK) { case XFS_ILOG_DDATA: case XFS_ILOG_DEXT: memcpy(XFS_DFORK_DPTR(dip), src, len); break; case XFS_ILOG_DBROOT: error = xlog_recover_inode_dbroot(mp, src, len, dip); if (error) goto out_release; break; default: /* * There are no data fork flags set. */ ASSERT((fields & XFS_ILOG_DFORK) == 0); break; } /* * If we logged any attribute data, recover it. There may or * may not have been any other non-core data logged in this * transaction. */ if (in_f->ilf_fields & XFS_ILOG_AFORK) { if (in_f->ilf_fields & XFS_ILOG_DFORK) { attr_index = 3; } else { attr_index = 2; } len = item->ri_buf[attr_index].iov_len; src = item->ri_buf[attr_index].iov_base; ASSERT(len == xlog_calc_iovec_len(in_f->ilf_asize)); switch (in_f->ilf_fields & XFS_ILOG_AFORK) { case XFS_ILOG_ADATA: case XFS_ILOG_AEXT: dest = XFS_DFORK_APTR(dip); ASSERT(len <= XFS_DFORK_ASIZE(dip, mp)); memcpy(dest, src, len); break; case XFS_ILOG_ABROOT: dest = XFS_DFORK_APTR(dip); xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len, (struct xfs_bmdr_block *)dest, XFS_DFORK_ASIZE(dip, mp)); break; default: xfs_warn(log->l_mp, "%s: Invalid flag", __func__); ASSERT(0); error = -EFSCORRUPTED; goto out_release; } } out_owner_change: /* Recover the swapext owner change unless inode has been deleted */ if ((in_f->ilf_fields & (XFS_ILOG_DOWNER|XFS_ILOG_AOWNER)) && (dip->di_mode != 0)) error = xfs_recover_inode_owner_change(mp, dip, in_f, buffer_list); /* re-generate the checksum and validate the recovered inode. */ xfs_dinode_calc_crc(log->l_mp, dip); fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip); if (fa) { XFS_CORRUPTION_ERROR( "Bad dinode after recovery", XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip)); xfs_alert(mp, "Metadata corruption detected at %pS, inode 0x%llx", fa, in_f->ilf_ino); error = -EFSCORRUPTED; goto out_release; } ASSERT(bp->b_mount == mp); bp->b_flags |= _XBF_LOGRECOVERY; xfs_buf_delwri_queue(bp, buffer_list); out_release: xfs_buf_relse(bp); error: if (need_free) kfree(in_f); return error; } const struct xlog_recover_item_ops xlog_inode_item_ops = { .item_type = XFS_LI_INODE, .ra_pass2 = xlog_recover_inode_ra_pass2, .commit_pass2 = xlog_recover_inode_commit_pass2, }; |
| 23 23 23 23 23 23 23 23 23 23 14 14 31 31 31 19 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Domain management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2024-2025 Microsoft Corporation */ #include <kunit/test.h> #include <linux/bitops.h> #include <linux/bits.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/path.h> #include <linux/pid.h> #include <linux/sched.h> #include <linux/signal.h> #include <linux/uidgid.h> #include "access.h" #include "common.h" #include "domain.h" #include "id.h" #ifdef CONFIG_AUDIT /** * get_current_exe - Get the current's executable path, if any * * @exe_str: Returned pointer to a path string with a lifetime tied to the * returned buffer, if any. * @exe_size: Returned size of @exe_str (including the trailing null * character), if any. * * Returns: A pointer to an allocated buffer where @exe_str point to, %NULL if * there is no executable path, or an error otherwise. */ static const void *get_current_exe(const char **const exe_str, size_t *const exe_size) { const size_t buffer_size = LANDLOCK_PATH_MAX_SIZE; struct mm_struct *mm = current->mm; struct file *file __free(fput) = NULL; char *buffer __free(kfree) = NULL; const char *exe; ssize_t size; if (!mm) return NULL; file = get_mm_exe_file(mm); if (!file) return NULL; buffer = kmalloc(buffer_size, GFP_KERNEL); if (!buffer) return ERR_PTR(-ENOMEM); exe = d_path(&file->f_path, buffer, buffer_size); if (WARN_ON_ONCE(IS_ERR(exe))) /* Should never happen according to LANDLOCK_PATH_MAX_SIZE. */ return ERR_CAST(exe); size = buffer + buffer_size - exe; if (WARN_ON_ONCE(size <= 0)) return ERR_PTR(-ENAMETOOLONG); *exe_size = size; *exe_str = exe; return no_free_ptr(buffer); } /* * Returns: A newly allocated object describing a domain, or an error * otherwise. */ static struct landlock_details *get_current_details(void) { /* Cf. audit_log_d_path_exe() */ static const char null_path[] = "(null)"; const char *path_str = null_path; size_t path_size = sizeof(null_path); const void *buffer __free(kfree) = NULL; struct landlock_details *details; buffer = get_current_exe(&path_str, &path_size); if (IS_ERR(buffer)) return ERR_CAST(buffer); /* * Create the new details according to the path's length. Do not * allocate with GFP_KERNEL_ACCOUNT because it is independent from the * caller. */ details = kzalloc(struct_size(details, exe_path, path_size), GFP_KERNEL); if (!details) return ERR_PTR(-ENOMEM); memcpy(details->exe_path, path_str, path_size); details->pid = get_pid(task_tgid(current)); details->uid = from_kuid(&init_user_ns, current_uid()); get_task_comm(details->comm, current); return details; } /** * landlock_init_hierarchy_log - Partially initialize landlock_hierarchy * * @hierarchy: The hierarchy to initialize. * * The current task is referenced as the domain that is enforcing the * restriction. The subjective credentials must not be in an overridden state. * * @hierarchy->parent and @hierarchy->usage should already be set. */ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy) { struct landlock_details *details; details = get_current_details(); if (IS_ERR(details)) return PTR_ERR(details); hierarchy->details = details; hierarchy->id = landlock_get_id_range(1); hierarchy->log_status = LANDLOCK_LOG_PENDING; hierarchy->log_same_exec = true; hierarchy->log_new_exec = false; atomic64_set(&hierarchy->num_denials, 0); return 0; } static deny_masks_t get_layer_deny_mask(const access_mask_t all_existing_optional_access, const unsigned long access_bit, const size_t layer) { unsigned long access_weight; /* This may require change with new object types. */ WARN_ON_ONCE(all_existing_optional_access != _LANDLOCK_ACCESS_FS_OPTIONAL); if (WARN_ON_ONCE(layer >= LANDLOCK_MAX_NUM_LAYERS)) return 0; access_weight = hweight_long(all_existing_optional_access & GENMASK(access_bit, 0)); if (WARN_ON_ONCE(access_weight < 1)) return 0; return layer << ((access_weight - 1) * HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1)); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_get_layer_deny_mask(struct kunit *const test) { const unsigned long truncate = BIT_INDEX(LANDLOCK_ACCESS_FS_TRUNCATE); const unsigned long ioctl_dev = BIT_INDEX(LANDLOCK_ACCESS_FS_IOCTL_DEV); KUNIT_EXPECT_EQ(test, 0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, truncate, 0)); KUNIT_EXPECT_EQ(test, 0x3, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, truncate, 3)); KUNIT_EXPECT_EQ(test, 0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, ioctl_dev, 0)); KUNIT_EXPECT_EQ(test, 0xf0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, ioctl_dev, 15)); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ deny_masks_t landlock_get_deny_masks(const access_mask_t all_existing_optional_access, const access_mask_t optional_access, const layer_mask_t (*const layer_masks)[], const size_t layer_masks_size) { const unsigned long access_opt = optional_access; unsigned long access_bit; deny_masks_t deny_masks = 0; /* This may require change with new object types. */ WARN_ON_ONCE(access_opt != (optional_access & all_existing_optional_access)); if (WARN_ON_ONCE(!layer_masks)) return 0; if (WARN_ON_ONCE(!access_opt)) return 0; for_each_set_bit(access_bit, &access_opt, layer_masks_size) { const layer_mask_t mask = (*layer_masks)[access_bit]; if (!mask) continue; /* __fls(1) == 0 */ deny_masks |= get_layer_deny_mask(all_existing_optional_access, access_bit, __fls(mask)); } return deny_masks; } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_landlock_get_deny_masks(struct kunit *const test) { const layer_mask_t layers1[BITS_PER_TYPE(access_mask_t)] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0) | BIT_ULL(9), [BIT_INDEX(LANDLOCK_ACCESS_FS_TRUNCATE)] = BIT_ULL(1), [BIT_INDEX(LANDLOCK_ACCESS_FS_IOCTL_DEV)] = BIT_ULL(2) | BIT_ULL(0), }; KUNIT_EXPECT_EQ(test, 0x1, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_TRUNCATE, &layers1, ARRAY_SIZE(layers1))); KUNIT_EXPECT_EQ(test, 0x20, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_IOCTL_DEV, &layers1, ARRAY_SIZE(layers1))); KUNIT_EXPECT_EQ( test, 0x21, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV, &layers1, ARRAY_SIZE(layers1))); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static struct kunit_case test_cases[] = { /* clang-format off */ KUNIT_CASE(test_get_layer_deny_mask), KUNIT_CASE(test_landlock_get_deny_masks), {} /* clang-format on */ }; static struct kunit_suite test_suite = { .name = "landlock_domain", .test_cases = test_cases, }; kunit_test_suite(test_suite); #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #endif /* CONFIG_AUDIT */ |
| 907 6746 7218 78 1081 1086 1089 19 636 19 638 182 65 2 3 2 22 2 21 23 254 3 105 6 111 105 6 110 111 111 116 3 113 116 217 1093 58 161 161 5 68 1 1 64 8 25 17 9 25 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <linux/atomic.h> #include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha1.h> #include <linux/u64_stats_sync.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark special ldsx instruction. Same as BPF_IND */ #define BPF_PROBE_MEMSX 0x40 /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 /* unused opcode to mark special atomic instruction */ #define BPF_PROBE_ATOMIC 0xe0 /* unused opcode to mark special ldsx instruction. Same as BPF_NOSPEC */ #define BPF_PROBE_MEM32SX 0xc0 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Spectre v1 and v4 */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU64_REG(OP, DST, SRC) \ BPF_ALU64_REG_OFF(OP, DST, SRC, 0) #define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ BPF_ALU32_REG_OFF(OP, DST, SRC, 0) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU64_IMM(OP, DST, IMM) \ BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) #define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Byte Swap, bswap16/32/64 */ #define BPF_BSWAP(DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */ #define BPF_ADDR_PERCPU (-1) #define BPF_MOV64_PERCPU_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = BPF_ADDR_PERCPU, \ .imm = 0 }) static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; } /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ #define BPF_MOVSX64_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_MOVSX32_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers * to pointers in user vma. */ static inline bool insn_is_cast_user(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1U << 16; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ #define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_AND *(uint *) (dst_reg + off16) &= src_reg * BPF_OR *(uint *) (dst_reg + off16) |= src_reg * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) * BPF_LOAD_ACQ dst_reg = smp_load_acquire(src_reg + off16) * BPF_STORE_REL smp_store_release(dst_reg + off16, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = OP }) /* Legacy alias */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Unconditional jumps, gotol pc + imm32 */ #define BPF_JMP32_A(IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = BPF_CALL_IMM(FUNC) }) /* Kfunc call */ #define BPF_CALL_KFUNC(OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_KFUNC_CALL, \ .off = OFF, \ .imm = IMM }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define __NOATTR #define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) #define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog_stats { u64_stats_t cnt; u64_stats_t nsecs; u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); struct bpf_timed_may_goto { u64 count; u64 timestamp; }; struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)); static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, const void *ctx, bpf_dispatcher_fn dfunc) { u32 ret; cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); duration = sched_clock() - start; if (likely(prog->stats)) { stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } return ret; } static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) { return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); } /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ #define BPF_RI_F_RI_INIT BIT(1) #define BPF_RI_F_CPU_MAP_INIT BIT(2) #define BPF_RI_F_DEV_MAP_INIT BIT(3) #define BPF_RI_F_XSK_MAP_INIT BIT(4) struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; u32 kern_flags; }; struct bpf_net_context { struct bpf_redirect_info ri; struct list_head cpu_map_flush_list; struct list_head dev_map_flush_list; struct list_head xskmap_map_flush_list; }; static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) { struct task_struct *tsk = current; if (tsk->bpf_net_context != NULL) return NULL; bpf_net_ctx->ri.kern_flags = 0; tsk->bpf_net_context = bpf_net_ctx; return bpf_net_ctx; } static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) { if (bpf_net_ctx) current->bpf_net_context = NULL; } static inline struct bpf_net_context *bpf_net_ctx_get(void) { return current->bpf_net_context; } static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; } return &bpf_net_ctx->ri; } static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; } return &bpf_net_ctx->cpu_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; } return &bpf_net_ctx->dev_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; } return &bpf_net_ctx->xskmap_map_flush_list; } static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, struct list_head **lh_dev, struct list_head **lh_xsk) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); u32 kern_flags = bpf_net_ctx->ri.kern_flags; struct list_head *lh; *lh_map = *lh_dev = *lh_xsk = NULL; if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) return; lh = &bpf_net_ctx->dev_map_flush_list; if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) *lh_dev = lh; lh = &bpf_net_ctx->cpu_map_flush_list; if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) *lh_map = lh; lh = &bpf_net_ctx->xskmap_map_flush_list; if (IS_ENABLED(CONFIG_XDP_SOCKETS) && kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) *lh_xsk = lh; } /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } static inline int bpf_prog_run_data_pointers( const struct bpf_prog *prog, struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; void *save_data_meta, *save_data_end; int res; save_data_meta = cb->data_meta; save_data_end = cb->data_end; bpf_compute_data_pointers(skb); res = bpf_prog_run(prog, skb); cb->data_meta = save_data_meta; cb->data_end = save_data_end; return res; } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, const void *ctx) { const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp); void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); return set_memory_ro((unsigned long)fp, fp->pages); } #endif return 0; } static inline int __must_check bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap, enum skb_drop_reason *reason); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason ignore_reason; return sk_filter_trim_cap(sk, skb, 1, &ignore_reason); } static inline int sk_filter_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { return sk_filter_trim_cap(sk, skb, 1, reason); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_jit_attempt_done(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); bool bpf_jit_supports_private_stack(void); bool bpf_jit_supports_timed_may_goto(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); u64 arch_bpf_timed_may_goto(void); u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *); bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *prog); void xdp_do_flush(void); void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, unsigned int alignment, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); const char *bpf_jit_get_prog_name(struct bpf_prog *prog); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { int ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; return ret; } void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return 0; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { return NULL; } static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { return 0; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr_unsized *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ u32 uaddrlen; }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 is_locked_tcp_sock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; #define BPF_SOCKOPT_KERN_BUF_SIZE 32 struct bpf_sockopt_buf { u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; /* for retval in struct bpf_cg_run_ctx */ struct task_struct *current_task; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; u32 ingress_ifindex; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; return flags & action_mask; } ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; if (flags & BPF_F_BROADCAST) { WRITE_ONCE(ri->map, map); ri->flags = flags; } else { WRITE_ONCE(ri->map, NULL); ri->flags = 0; } return XDP_REDIRECT; } #ifdef CONFIG_NET int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { return NULL; } static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { } static inline int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ |
| 5563 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BIO_INTEGRITY_H #define _LINUX_BIO_INTEGRITY_H #include <linux/bio.h> enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ BIP_DISK_NOCHECK = 1 << 2, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 3, /* IP checksum */ BIP_COPY_USER = 1 << 4, /* Kernel bounce buffer in use */ BIP_CHECK_GUARD = 1 << 5, /* guard check */ BIP_CHECK_REFTAG = 1 << 6, /* reftag check */ BIP_CHECK_APPTAG = 1 << 7, /* apptag check */ BIP_MEMPOOL = 1 << 15, /* buffer backed by mempool */ }; struct bio_integrity_payload { struct bvec_iter bip_iter; unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ u16 app_tag; /* application tag value */ struct bio_vec *bip_vec; }; #define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \ BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) #ifdef CONFIG_BLK_DEV_INTEGRITY #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip) return bip->bip_flags & flag; return false; } static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) { return bip->bip_iter.bi_sector; } static inline void bip_set_seed(struct bio_integrity_payload *bip, sector_t seed) { bip->bip_iter.bi_sector = seed; } void bio_integrity_init(struct bio *bio, struct bio_integrity_payload *bip, struct bio_vec *bvecs, unsigned int nr_vecs); struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr); int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter); int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta); void bio_integrity_unmap_user(struct bio *bio); bool bio_integrity_prep(struct bio *bio); void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); void bio_integrity_trim(struct bio *bio); int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { return NULL; } static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) { return -EINVAL; } static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) { return -EINVAL; } static inline void bio_integrity_unmap_user(struct bio *bio) { } static inline bool bio_integrity_prep(struct bio *bio) { return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { return 0; } static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { } static inline void bio_integrity_trim(struct bio *bio) { } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; } static inline struct bio_integrity_payload * bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr) { return ERR_PTR(-EINVAL); } static inline int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ void bio_integrity_alloc_buf(struct bio *bio, bool zero_buffer); void bio_integrity_free_buf(struct bio_integrity_payload *bip); #endif /* _LINUX_BIO_INTEGRITY_H */ |
| 8 1 1 10 10 10 10 8 8 8 9 1 8 8 3 3 4 1 1 1 1 1 2 3 1 2 7 2 1 7 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 | // SPDX-License-Identifier: GPL-2.0-only /* * 6pack.c This module implements the 6pack protocol for kernel-based * devices like TTY. It interfaces between a raw TTY and the * kernel's AX.25 protocol layers. * * Authors: Andreas Könsgen <ajk@comnets.uni-bremen.de> * Ralf Baechle DL5RB <ralf@linux-mips.org> * * Quite a lot of stuff "stolen" by Joerg Reuter from slip.c, written by * * Laurence Culhane, <loz@holmes.demon.co.uk> * Fred N. van Kempen, <waltje@uwalt.nl.mugnet.org> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/tty.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/timer.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/semaphore.h> #include <linux/refcount.h> /* sixpack priority commands */ #define SIXP_SEOF 0x40 /* start and end of a 6pack frame */ #define SIXP_TX_URUN 0x48 /* transmit overrun */ #define SIXP_RX_ORUN 0x50 /* receive overrun */ #define SIXP_RX_BUF_OVL 0x58 /* receive buffer overflow */ #define SIXP_CHKSUM 0xFF /* valid checksum of a 6pack frame */ /* masks to get certain bits out of the status bytes sent by the TNC */ #define SIXP_CMD_MASK 0xC0 #define SIXP_CHN_MASK 0x07 #define SIXP_PRIO_CMD_MASK 0x80 #define SIXP_STD_CMD_MASK 0x40 #define SIXP_PRIO_DATA_MASK 0x38 #define SIXP_TX_MASK 0x20 #define SIXP_RX_MASK 0x10 #define SIXP_RX_DCD_MASK 0x18 #define SIXP_LEDS_ON 0x78 #define SIXP_LEDS_OFF 0x60 #define SIXP_CON 0x08 #define SIXP_STA 0x10 #define SIXP_FOUND_TNC 0xe9 #define SIXP_CON_ON 0x68 #define SIXP_DCD_MASK 0x08 #define SIXP_DAMA_OFF 0 /* default level 2 parameters */ #define SIXP_TXDELAY 25 /* 250 ms */ #define SIXP_PERSIST 50 /* in 256ths */ #define SIXP_SLOTTIME 10 /* 100 ms */ #define SIXP_INIT_RESYNC_TIMEOUT (3*HZ/2) /* in 1 s */ #define SIXP_RESYNC_TIMEOUT 5*HZ /* in 1 s */ /* 6pack configuration. */ #define SIXP_NRUNIT 31 /* MAX number of 6pack channels */ #define SIXP_MTU 256 /* Default MTU */ enum sixpack_flags { SIXPF_ERROR, /* Parity, etc. error */ }; struct sixpack { /* Various fields. */ struct tty_struct *tty; /* ptr to TTY structure */ struct net_device *dev; /* easy for intr handling */ /* These are pointers to the malloc()ed frame buffers. */ int rcount; /* received chars counter */ unsigned char *xbuff; /* transmitter buffer */ unsigned char *xhead; /* next byte to XMIT */ int xleft; /* bytes left in XMIT queue */ u8 raw_buf[4]; u8 cooked_buf[400]; unsigned int rx_count; unsigned int rx_count_cooked; spinlock_t rxlock; unsigned long flags; /* Flag values/ mode etc */ unsigned char mode; /* 6pack mode */ /* 6pack stuff */ unsigned char tx_delay; unsigned char persistence; unsigned char slottime; unsigned char duplex; unsigned char led_state; u8 status; u8 status1; unsigned char status2; unsigned char tx_enable; unsigned char tnc_state; struct timer_list tx_t; struct timer_list resync_t; spinlock_t lock; }; #define AX25_6PACK_HEADER_LEN 0 static void sixpack_decode(struct sixpack *, const u8 *, size_t); static int encode_sixpack(unsigned char *, unsigned char *, int, unsigned char); /* * Perform the persistence/slottime algorithm for CSMA access. If the * persistence check was successful, write the data to the serial driver. * Note that in case of DAMA operation, the data is not sent here. */ static void sp_xmit_on_air(struct timer_list *t) { struct sixpack *sp = timer_container_of(sp, t, tx_t); int actual, when = sp->slottime; static unsigned char random; random = random * 17 + 41; if (((sp->status1 & SIXP_DCD_MASK) == 0) && (random < sp->persistence)) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, sp->status2); sp->xleft -= actual; sp->xhead += actual; sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->status2 = 0; } else mod_timer(&sp->tx_t, jiffies + ((when + 1) * HZ) / 100); } /* ----> 6pack timer interrupt handler and friends. <---- */ /* Encapsulate one AX.25 frame and stuff into a TTY queue. */ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len) { unsigned char *msg, *p = icp; int actual, count; if (len > AX25_MTU + 73) { msg = "oversized transmit packet!"; goto out_drop; } if (p[0] > 5) { msg = "invalid KISS command"; goto out_drop; } if ((p[0] != 0) && (len > 2)) { msg = "KISS control packet too long"; goto out_drop; } if ((p[0] == 0) && (len < 15)) { msg = "bad AX.25 packet to transmit"; goto out_drop; } count = encode_sixpack(p, sp->xbuff, len, sp->tx_delay); set_bit(TTY_DO_WRITE_WAKEUP, &sp->tty->flags); switch (p[0]) { case 1: sp->tx_delay = p[1]; return; case 2: sp->persistence = p[1]; return; case 3: sp->slottime = p[1]; return; case 4: /* ignored */ return; case 5: sp->duplex = p[1]; return; } if (p[0] != 0) return; /* * In case of fullduplex or DAMA operation, we don't take care about the * state of the DCD or of any timers, as the determination of the * correct time to send is the job of the AX.25 layer. We send * immediately after data has arrived. */ if (sp->duplex == 1) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, count); sp->xleft = count - actual; sp->xhead = sp->xbuff + actual; sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); } else { sp->xleft = count; sp->xhead = sp->xbuff; sp->status2 = count; sp_xmit_on_air(&sp->tx_t); } return; out_drop: sp->dev->stats.tx_dropped++; netif_start_queue(sp->dev); if (net_ratelimit()) printk(KERN_DEBUG "%s: %s - dropped.\n", sp->dev->name, msg); } /* Encapsulate an IP datagram and kick it into a TTY queue. */ static netdev_tx_t sp_xmit(struct sk_buff *skb, struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); if (skb->protocol == htons(ETH_P_IP)) return ax25_ip_xmit(skb); spin_lock_bh(&sp->lock); /* We were not busy, so we are now... :-) */ netif_stop_queue(dev); dev->stats.tx_bytes += skb->len; sp_encaps(sp, skb->data, skb->len); spin_unlock_bh(&sp->lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } static int sp_open_dev(struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); if (sp->tty == NULL) return -ENODEV; return 0; } /* Close the low-level part of the 6pack channel. */ static int sp_close(struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); spin_lock_bh(&sp->lock); if (sp->tty) { /* TTY discipline is running. */ clear_bit(TTY_DO_WRITE_WAKEUP, &sp->tty->flags); } netif_stop_queue(dev); spin_unlock_bh(&sp->lock); return 0; } static int sp_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr_ax25 *sa = addr; netif_tx_lock_bh(dev); netif_addr_lock(dev); __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); return 0; } static const struct net_device_ops sp_netdev_ops = { .ndo_open = sp_open_dev, .ndo_stop = sp_close, .ndo_start_xmit = sp_xmit, .ndo_set_mac_address = sp_set_mac_address, }; static void sp_setup(struct net_device *dev) { /* Finish setting up the DEVICE info. */ dev->netdev_ops = &sp_netdev_ops; dev->mtu = SIXP_MTU; dev->hard_header_len = AX25_MAX_HEADER_LEN; dev->header_ops = &ax25_header_ops; dev->addr_len = AX25_ADDR_LEN; dev->type = ARPHRD_AX25; dev->tx_queue_len = 10; /* Only activated in AX.25 mode */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = 0; } /* Send one completely decapsulated IP datagram to the IP layer. */ /* * This is the routine that sends the received data to the kernel AX.25. * 'cmd' is the KISS command. For AX.25 data, it is zero. */ static void sp_bump(struct sixpack *sp, char cmd) { struct sk_buff *skb; int count; u8 *ptr; count = sp->rcount + 1; sp->dev->stats.rx_bytes += count; if ((skb = dev_alloc_skb(count + 1)) == NULL) goto out_mem; ptr = skb_put(skb, count + 1); *ptr++ = cmd; /* KISS command */ memcpy(ptr, sp->cooked_buf + 1, count); skb->protocol = ax25_type_trans(skb, sp->dev); netif_rx(skb); sp->dev->stats.rx_packets++; return; out_mem: sp->dev->stats.rx_dropped++; } /* ----------------------------------------------------------------------- */ /* * Called by the TTY driver when there's room for more data. If we have * more packets to send, we send them here. */ static void sixpack_write_wakeup(struct tty_struct *tty) { struct sixpack *sp = tty->disc_data; int actual; if (!sp) return; if (sp->xleft <= 0) { /* Now serial buffer is almost free & we can start * transmission of another packet */ sp->dev->stats.tx_packets++; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); sp->tx_enable = 0; netif_wake_queue(sp->dev); return; } if (sp->tx_enable) { actual = tty->ops->write(tty, sp->xhead, sp->xleft); sp->xleft -= actual; sp->xhead += actual; } } /* ----------------------------------------------------------------------- */ /* * Handle the 'receiver data ready' interrupt. * This function is called by the tty module in the kernel when * a block of 6pack data has been received, which can now be decapsulated * and sent on to some IP layer for further processing. */ static void sixpack_receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, size_t count) { struct sixpack *sp; size_t count1; if (!count) return; sp = tty->disc_data; if (!sp) return; /* Read the characters out of the buffer */ count1 = count; while (count) { count--; if (fp && *fp++) { if (!test_and_set_bit(SIXPF_ERROR, &sp->flags)) sp->dev->stats.rx_errors++; continue; } } sixpack_decode(sp, cp, count1); tty_unthrottle(tty); } /* * Try to resync the TNC. Called by the resync timer defined in * decode_prio_command */ #define TNC_UNINITIALIZED 0 #define TNC_UNSYNC_STARTUP 1 #define TNC_UNSYNCED 2 #define TNC_IN_SYNC 3 static void __tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) { char *msg; switch (new_tnc_state) { default: /* gcc oh piece-o-crap ... */ case TNC_UNSYNC_STARTUP: msg = "Synchronizing with TNC"; break; case TNC_UNSYNCED: msg = "Lost synchronization with TNC\n"; break; case TNC_IN_SYNC: msg = "Found TNC"; break; } sp->tnc_state = new_tnc_state; printk(KERN_INFO "%s: %s\n", sp->dev->name, msg); } static inline void tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) { int old_tnc_state = sp->tnc_state; if (old_tnc_state != new_tnc_state) __tnc_set_sync_state(sp, new_tnc_state); } static void resync_tnc(struct timer_list *t) { struct sixpack *sp = timer_container_of(sp, t, resync_t); static char resync_cmd = 0xe8; /* clear any data that might have been received */ sp->rx_count = 0; sp->rx_count_cooked = 0; /* reset state machine */ sp->status = 1; sp->status1 = 1; sp->status2 = 0; /* resync the TNC */ sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tty->ops->write(sp->tty, &resync_cmd, 1); /* Start resync timer again -- the TNC might be still absent */ mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); } static inline int tnc_init(struct sixpack *sp) { unsigned char inbyte = 0xe8; tnc_set_sync_state(sp, TNC_UNSYNC_STARTUP); sp->tty->ops->write(sp->tty, &inbyte, 1); mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); return 0; } /* * Open the high-level part of the 6pack channel. * This function is called by the TTY module when the * 6pack line discipline is called for. Because we are * sure the tty line exists, we only have to link it to * a free 6pcack channel... */ static int sixpack_open(struct tty_struct *tty) { char *xbuff = NULL; struct net_device *dev; struct sixpack *sp; unsigned long len; int err = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (tty->ops->write == NULL) return -EOPNOTSUPP; dev = alloc_netdev(sizeof(struct sixpack), "sp%d", NET_NAME_UNKNOWN, sp_setup); if (!dev) { err = -ENOMEM; goto out; } sp = netdev_priv(dev); sp->dev = dev; spin_lock_init(&sp->lock); spin_lock_init(&sp->rxlock); /* !!! length of the buffers. MTU is IP MTU, not PACLEN! */ len = dev->mtu * 2; xbuff = kmalloc(len + 4, GFP_KERNEL); if (xbuff == NULL) { err = -ENOBUFS; goto out_free; } spin_lock_bh(&sp->lock); sp->tty = tty; sp->xbuff = xbuff; sp->rcount = 0; sp->rx_count = 0; sp->rx_count_cooked = 0; sp->xleft = 0; sp->flags = 0; /* Clear ESCAPE & ERROR flags */ sp->duplex = 0; sp->tx_delay = SIXP_TXDELAY; sp->persistence = SIXP_PERSIST; sp->slottime = SIXP_SLOTTIME; sp->led_state = 0x60; sp->status = 1; sp->status1 = 1; sp->status2 = 0; sp->tx_enable = 0; netif_start_queue(dev); timer_setup(&sp->tx_t, sp_xmit_on_air, 0); timer_setup(&sp->resync_t, resync_tnc, 0); spin_unlock_bh(&sp->lock); /* Done. We have linked the TTY line to a channel. */ tty->disc_data = sp; tty->receive_room = 65536; /* Now we're ready to register. */ err = register_netdev(dev); if (err) goto out_free; tnc_init(sp); return 0; out_free: kfree(xbuff); free_netdev(dev); out: return err; } /* * Close down a 6pack channel. * This means flushing out any pending queues, and then restoring the * TTY line discipline to what it was before it got hooked to 6pack * (which usually is TTY again). */ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; sp = tty->disc_data; if (!sp) return; tty->disc_data = NULL; /* We must stop the queue to avoid potentially scribbling * on the free buffers. The sp->dead completion is not sufficient * to protect us from sp->xbuff access. */ netif_stop_queue(sp->dev); unregister_netdev(sp->dev); timer_delete_sync(&sp->tx_t); timer_delete_sync(&sp->resync_t); /* Free all 6pack frame buffers after unreg. */ kfree(sp->xbuff); free_netdev(sp->dev); } /* Perform I/O control on an active 6pack channel. */ static int sixpack_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct sixpack *sp = tty->disc_data; struct net_device *dev; unsigned int tmp, err; if (!sp) return -ENXIO; dev = sp->dev; switch(cmd) { case SIOCGIFNAME: err = copy_to_user((void __user *) arg, dev->name, strlen(dev->name) + 1) ? -EFAULT : 0; break; case SIOCGIFENCAP: err = put_user(0, (int __user *) arg); break; case SIOCSIFENCAP: if (get_user(tmp, (int __user *) arg)) { err = -EFAULT; break; } sp->mode = tmp; dev->addr_len = AX25_ADDR_LEN; dev->hard_header_len = AX25_KISS_HEADER_LEN + AX25_MAX_HEADER_LEN + 3; dev->type = ARPHRD_AX25; err = 0; break; case SIOCSIFHWADDR: { char addr[AX25_ADDR_LEN]; if (copy_from_user(&addr, (void __user *)arg, AX25_ADDR_LEN)) { err = -EFAULT; break; } netif_tx_lock_bh(dev); __dev_addr_set(dev, &addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; break; } default: err = tty_mode_ioctl(tty, cmd, arg); } return err; } static struct tty_ldisc_ops sp_ldisc = { .owner = THIS_MODULE, .num = N_6PACK, .name = "6pack", .open = sixpack_open, .close = sixpack_close, .ioctl = sixpack_ioctl, .receive_buf = sixpack_receive_buf, .write_wakeup = sixpack_write_wakeup, }; /* Initialize 6pack control device -- register 6pack line discipline */ static int __init sixpack_init_driver(void) { int status; /* Register the provided line protocol discipline */ status = tty_register_ldisc(&sp_ldisc); if (status) pr_err("6pack: can't register line discipline (err = %d)\n", status); return status; } static void __exit sixpack_exit_driver(void) { tty_unregister_ldisc(&sp_ldisc); } /* encode an AX.25 packet into 6pack */ static int encode_sixpack(unsigned char *tx_buf, unsigned char *tx_buf_raw, int length, unsigned char tx_delay) { int count = 0; unsigned char checksum = 0, buf[400]; int raw_count = 0; tx_buf_raw[raw_count++] = SIXP_PRIO_CMD_MASK | SIXP_TX_MASK; tx_buf_raw[raw_count++] = SIXP_SEOF; buf[0] = tx_delay; for (count = 1; count < length; count++) buf[count] = tx_buf[count]; for (count = 0; count < length; count++) checksum += buf[count]; buf[length] = (unsigned char) 0xff - checksum; for (count = 0; count <= length; count++) { if ((count % 3) == 0) { tx_buf_raw[raw_count++] = (buf[count] & 0x3f); tx_buf_raw[raw_count] = ((buf[count] >> 2) & 0x30); } else if ((count % 3) == 1) { tx_buf_raw[raw_count++] |= (buf[count] & 0x0f); tx_buf_raw[raw_count] = ((buf[count] >> 2) & 0x3c); } else { tx_buf_raw[raw_count++] |= (buf[count] & 0x03); tx_buf_raw[raw_count++] = (buf[count] >> 2); } } if ((length % 3) != 2) raw_count++; tx_buf_raw[raw_count++] = SIXP_SEOF; return raw_count; } /* decode 4 sixpack-encoded bytes into 3 data bytes */ static void decode_data(struct sixpack *sp, u8 inbyte) { u8 *buf; if (sp->rx_count != 3) { sp->raw_buf[sp->rx_count++] = inbyte; return; } if (sp->rx_count_cooked + 2 >= sizeof(sp->cooked_buf)) { pr_err("6pack: cooked buffer overrun, data loss\n"); sp->rx_count = 0; return; } buf = sp->raw_buf; sp->cooked_buf[sp->rx_count_cooked++] = buf[0] | ((buf[1] << 2) & 0xc0); sp->cooked_buf[sp->rx_count_cooked++] = (buf[1] & 0x0f) | ((buf[2] << 2) & 0xf0); sp->cooked_buf[sp->rx_count_cooked++] = (buf[2] & 0x03) | (inbyte << 2); sp->rx_count = 0; } /* identify and execute a 6pack priority command byte */ static void decode_prio_command(struct sixpack *sp, u8 cmd) { ssize_t actual; if ((cmd & SIXP_PRIO_DATA_MASK) != 0) { /* idle ? */ /* RX and DCD flags can only be set in the same prio command, if the DCD flag has been set without the RX flag in the previous prio command. If DCD has not been set before, something in the transmission has gone wrong. In this case, RX and DCD are cleared in order to prevent the decode_data routine from reading further data that might be corrupt. */ if (((sp->status & SIXP_DCD_MASK) == 0) && ((cmd & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK)) { if (sp->status != 1) printk(KERN_DEBUG "6pack: protocol violation\n"); else sp->status = 0; cmd &= ~SIXP_RX_DCD_MASK; } sp->status = cmd & SIXP_PRIO_DATA_MASK; } else { /* output watchdog char if idle */ if ((sp->status2 != 0) && (sp->duplex == 1)) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, sp->status2); sp->xleft -= actual; sp->xhead += actual; sp->led_state = 0x60; sp->status2 = 0; } } /* needed to trigger the TNC watchdog */ sp->tty->ops->write(sp->tty, &sp->led_state, 1); /* if the state byte has been received, the TNC is present, so the resync timer can be reset. */ if (sp->tnc_state == TNC_IN_SYNC) mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT); sp->status1 = cmd & SIXP_PRIO_DATA_MASK; } /* identify and execute a standard 6pack command byte */ static void decode_std_command(struct sixpack *sp, u8 cmd) { u8 checksum = 0, rest = 0; short i; switch (cmd & SIXP_CMD_MASK) { /* normal command */ case SIXP_SEOF: if ((sp->rx_count == 0) && (sp->rx_count_cooked == 0)) { if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK) { sp->led_state = 0x68; sp->tty->ops->write(sp->tty, &sp->led_state, 1); } } else { sp->led_state = 0x60; /* fill trailing bytes with zeroes */ sp->tty->ops->write(sp->tty, &sp->led_state, 1); spin_lock_bh(&sp->rxlock); rest = sp->rx_count; if (rest != 0) for (i = rest; i <= 3; i++) decode_data(sp, 0); if (rest == 2) sp->rx_count_cooked -= 2; else if (rest == 3) sp->rx_count_cooked -= 1; for (i = 0; i < sp->rx_count_cooked; i++) checksum += sp->cooked_buf[i]; if (checksum != SIXP_CHKSUM) { printk(KERN_DEBUG "6pack: bad checksum %2.2x\n", checksum); } else { sp->rcount = sp->rx_count_cooked-2; sp_bump(sp, 0); } sp->rx_count_cooked = 0; spin_unlock_bh(&sp->rxlock); } break; case SIXP_TX_URUN: printk(KERN_DEBUG "6pack: TX underrun\n"); break; case SIXP_RX_ORUN: printk(KERN_DEBUG "6pack: RX overrun\n"); break; case SIXP_RX_BUF_OVL: printk(KERN_DEBUG "6pack: RX buffer overflow\n"); } } /* decode a 6pack packet */ static void sixpack_decode(struct sixpack *sp, const u8 *pre_rbuff, size_t count) { size_t count1; u8 inbyte; for (count1 = 0; count1 < count; count1++) { inbyte = pre_rbuff[count1]; if (inbyte == SIXP_FOUND_TNC) { tnc_set_sync_state(sp, TNC_IN_SYNC); timer_delete(&sp->resync_t); } if ((inbyte & SIXP_PRIO_CMD_MASK) != 0) decode_prio_command(sp, inbyte); else if ((inbyte & SIXP_STD_CMD_MASK) != 0) decode_std_command(sp, inbyte); else if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK) { spin_lock_bh(&sp->rxlock); decode_data(sp, inbyte); spin_unlock_bh(&sp->rxlock); } } } MODULE_AUTHOR("Ralf Baechle DO1GRB <ralf@linux-mips.org>"); MODULE_DESCRIPTION("6pack driver for AX.25"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_6PACK); module_init(sixpack_init_driver); module_exit(sixpack_exit_driver); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | // SPDX-License-Identifier: GPL-2.0-only /* ipv6header match - matches IPv6 packets based on whether they contain certain headers */ /* Original idea: Brad Chapman * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */ /* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> */ #include <linux/module.h> #include <linux/skbuff.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.h> #include <linux/netfilter_ipv6/ip6t_ipv6header.h> MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: IPv6 header types match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); static bool ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; unsigned int temp; int len; u8 nexthdr; unsigned int ptr; /* Make sure this isn't an evil packet */ /* type of the 1st exthdr */ nexthdr = ipv6_hdr(skb)->nexthdr; /* pointer to the 1st exthdr */ ptr = sizeof(struct ipv6hdr); /* available length */ len = skb->len - ptr; temp = 0; while (nf_ip6_ext_hdr(nexthdr)) { const struct ipv6_opt_hdr *hp; struct ipv6_opt_hdr _hdr; int hdrlen; /* No more exthdr -> evaluate */ if (nexthdr == NEXTHDR_NONE) { temp |= MASK_NONE; break; } /* Is there enough space for the next ext header? */ if (len < (int)sizeof(struct ipv6_opt_hdr)) return false; /* ESP -> evaluate */ if (nexthdr == NEXTHDR_ESP) { temp |= MASK_ESP; break; } hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); if (!hp) { par->hotdrop = true; return false; } /* Calculate the header length */ if (nexthdr == NEXTHDR_FRAGMENT) hdrlen = 8; else if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(hp); else hdrlen = ipv6_optlen(hp); /* set the flag */ switch (nexthdr) { case NEXTHDR_HOP: temp |= MASK_HOPOPTS; break; case NEXTHDR_ROUTING: temp |= MASK_ROUTING; break; case NEXTHDR_FRAGMENT: temp |= MASK_FRAGMENT; break; case NEXTHDR_AUTH: temp |= MASK_AH; break; case NEXTHDR_DEST: temp |= MASK_DSTOPTS; break; default: return false; } nexthdr = hp->nexthdr; len -= hdrlen; ptr += hdrlen; if (ptr > skb->len) break; } if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP) temp |= MASK_PROTO; if (info->modeflag) return !((temp ^ info->matchflags ^ info->invflags) & info->matchflags); else { if (info->invflags) return temp != info->matchflags; else return temp == info->matchflags; } } static int ipv6header_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; /* invflags is 0 or 0xff in hard mode */ if ((!info->modeflag) && info->invflags != 0x00 && info->invflags != 0xFF) return -EINVAL; return 0; } static struct xt_match ipv6header_mt6_reg __read_mostly = { .name = "ipv6header", .family = NFPROTO_IPV6, .match = ipv6header_mt6, .matchsize = sizeof(struct ip6t_ipv6header_info), .checkentry = ipv6header_mt6_check, .destroy = NULL, .me = THIS_MODULE, }; static int __init ipv6header_mt6_init(void) { return xt_register_match(&ipv6header_mt6_reg); } static void __exit ipv6header_mt6_exit(void) { xt_unregister_match(&ipv6header_mt6_reg); } module_init(ipv6header_mt6_init); module_exit(ipv6header_mt6_exit); |
| 7 7 7 67 67 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * f2fs sysfs interface * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2017 Chao Yu <chao@kernel.org> */ #include <linux/compiler.h> #include <linux/proc_fs.h> #include <linux/f2fs_fs.h> #include <linux/seq_file.h> #include <linux/unicode.h> #include <linux/ioprio.h> #include <linux/sysfs.h> #include "f2fs.h" #include "segment.h" #include "gc.h" #include "iostat.h" #include <trace/events/f2fs.h> static struct proc_dir_entry *f2fs_proc_root; /* Sysfs support for f2fs */ enum { GC_THREAD, /* struct f2fs_gc_thread */ SM_INFO, /* struct f2fs_sm_info */ DCC_INFO, /* struct discard_cmd_control */ NM_INFO, /* struct f2fs_nm_info */ F2FS_SBI, /* struct f2fs_sb_info */ #ifdef CONFIG_F2FS_STAT_FS STAT_INFO, /* struct f2fs_stat_info */ #endif #ifdef CONFIG_F2FS_FAULT_INJECTION FAULT_INFO_RATE, /* struct f2fs_fault_info */ FAULT_INFO_TYPE, /* struct f2fs_fault_info */ #endif RESERVED_BLOCKS, /* struct f2fs_sb_info */ CPRC_INFO, /* struct ckpt_req_control */ ATGC_INFO, /* struct atgc_management */ }; static const char *gc_mode_names[MAX_GC_MODE] = { "GC_NORMAL", "GC_IDLE_CB", "GC_IDLE_GREEDY", "GC_IDLE_AT", "GC_URGENT_HIGH", "GC_URGENT_LOW", "GC_URGENT_MID" }; struct f2fs_attr { struct attribute attr; ssize_t (*show)(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf); ssize_t (*store)(struct f2fs_attr *a, struct f2fs_sb_info *sbi, const char *buf, size_t len); int struct_type; int offset; int id; }; struct f2fs_base_attr { struct attribute attr; ssize_t (*show)(struct f2fs_base_attr *a, char *buf); ssize_t (*store)(struct f2fs_base_attr *a, const char *buf, size_t len); }; static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf); static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) { if (struct_type == GC_THREAD) return (unsigned char *)sbi->gc_thread; else if (struct_type == SM_INFO) return (unsigned char *)SM_I(sbi); else if (struct_type == DCC_INFO) return (unsigned char *)SM_I(sbi)->dcc_info; else if (struct_type == NM_INFO) return (unsigned char *)NM_I(sbi); else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS) return (unsigned char *)sbi; #ifdef CONFIG_F2FS_FAULT_INJECTION else if (struct_type == FAULT_INFO_RATE || struct_type == FAULT_INFO_TYPE) return (unsigned char *)&F2FS_OPTION(sbi).fault_info; #endif #ifdef CONFIG_F2FS_STAT_FS else if (struct_type == STAT_INFO) return (unsigned char *)F2FS_STAT(sbi); #endif else if (struct_type == CPRC_INFO) return (unsigned char *)&sbi->cprc_info; else if (struct_type == ATGC_INFO) return (unsigned char *)&sbi->am; return NULL; } static ssize_t dirty_segments_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)(dirty_segments(sbi))); } static ssize_t free_segments_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)(free_segments(sbi))); } static ssize_t ovp_segments_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)(overprovision_segments(sbi))); } static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)(sbi->kbytes_written + ((f2fs_get_sectors_written(sbi) - sbi->sectors_written_start) >> 1))); } static ssize_t sb_status_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%lx\n", sbi->s_flag); } static ssize_t cp_status_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%x\n", le32_to_cpu(F2FS_CKPT(sbi)->ckpt_flags)); } static ssize_t pending_discard_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { if (!SM_I(sbi)->dcc_info) return -EINVAL; return sysfs_emit(buf, "%llu\n", (unsigned long long)atomic_read( &SM_I(sbi)->dcc_info->discard_cmd_cnt)); } static ssize_t issued_discard_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { if (!SM_I(sbi)->dcc_info) return -EINVAL; return sysfs_emit(buf, "%llu\n", (unsigned long long)atomic_read( &SM_I(sbi)->dcc_info->issued_discard)); } static ssize_t queued_discard_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { if (!SM_I(sbi)->dcc_info) return -EINVAL; return sysfs_emit(buf, "%llu\n", (unsigned long long)atomic_read( &SM_I(sbi)->dcc_info->queued_discard)); } static ssize_t undiscard_blks_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { if (!SM_I(sbi)->dcc_info) return -EINVAL; return sysfs_emit(buf, "%u\n", SM_I(sbi)->dcc_info->undiscard_blks); } static ssize_t atgc_enabled_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%d\n", sbi->am.atgc_enabled ? 1 : 0); } static ssize_t gc_mode_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%s\n", gc_mode_names[sbi->gc_mode]); } static ssize_t features_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { int len = 0; if (f2fs_sb_has_encrypt(sbi)) len += sysfs_emit_at(buf, len, "%s", "encryption"); if (f2fs_sb_has_blkzoned(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "blkzoned"); if (f2fs_sb_has_extra_attr(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "extra_attr"); if (f2fs_sb_has_project_quota(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "projquota"); if (f2fs_sb_has_inode_chksum(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "inode_checksum"); if (f2fs_sb_has_flexible_inline_xattr(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "flexible_inline_xattr"); if (f2fs_sb_has_quota_ino(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "quota_ino"); if (f2fs_sb_has_inode_crtime(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "inode_crtime"); if (f2fs_sb_has_lost_found(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "lost_found"); if (f2fs_sb_has_verity(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "verity"); if (f2fs_sb_has_sb_chksum(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "sb_checksum"); if (f2fs_sb_has_casefold(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "casefold"); if (f2fs_sb_has_readonly(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "readonly"); if (f2fs_sb_has_compression(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "compression"); if (f2fs_sb_has_packed_ssa(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "packed_ssa"); len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "pin_file"); len += sysfs_emit_at(buf, len, "\n"); return len; } static ssize_t current_reserved_blocks_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%u\n", sbi->current_reserved_blocks); } static ssize_t unusable_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { block_t unusable; if (test_opt(sbi, DISABLE_CHECKPOINT)) unusable = sbi->unusable_block_count; else unusable = f2fs_get_unusable_blocks(sbi); return sysfs_emit(buf, "%llu\n", (unsigned long long)unusable); } static ssize_t encoding_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { #if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) return sysfs_emit(buf, "UTF-8 (%d.%d.%d)\n", (sb->s_encoding->version >> 16) & 0xff, (sb->s_encoding->version >> 8) & 0xff, sb->s_encoding->version & 0xff); #endif return sysfs_emit(buf, "(none)\n"); } static ssize_t encoding_flags_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%x\n", le16_to_cpu(F2FS_RAW_SUPER(sbi)->s_encoding_flags)); } static ssize_t effective_lookup_mode_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { switch (F2FS_OPTION(sbi).lookup_mode) { case LOOKUP_PERF: return sysfs_emit(buf, "perf\n"); case LOOKUP_COMPAT: return sysfs_emit(buf, "compat\n"); case LOOKUP_AUTO: if (sb_no_casefold_compat_fallback(sbi->sb)) return sysfs_emit(buf, "auto:perf\n"); return sysfs_emit(buf, "auto:compat\n"); } return 0; } static ssize_t mounted_time_sec_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", SIT_I(sbi)->mounted_time); } #ifdef CONFIG_F2FS_STAT_FS static ssize_t moved_blocks_foreground_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { struct f2fs_stat_info *si = F2FS_STAT(sbi); return sysfs_emit(buf, "%llu\n", (unsigned long long)(si->tot_blks - (si->bg_data_blks + si->bg_node_blks))); } static ssize_t moved_blocks_background_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { struct f2fs_stat_info *si = F2FS_STAT(sbi); return sysfs_emit(buf, "%llu\n", (unsigned long long)(si->bg_data_blks + si->bg_node_blks)); } static ssize_t avg_vblocks_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { struct f2fs_stat_info *si = F2FS_STAT(sbi); si->dirty_count = dirty_segments(sbi); f2fs_update_sit_info(sbi); return sysfs_emit(buf, "%llu\n", (unsigned long long)(si->avg_vblocks)); } #endif static ssize_t main_blkaddr_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)MAIN_BLKADDR(sbi)); } static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { unsigned char *ptr = NULL; unsigned int *ui; ptr = __struct_ptr(sbi, a->struct_type); if (!ptr) return -EINVAL; if (!strcmp(a->attr.name, "extension_list")) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; int cold_count = le32_to_cpu(sbi->raw_super->extension_count); int hot_count = sbi->raw_super->hot_ext_count; int len = 0, i; len += sysfs_emit_at(buf, len, "cold file extension:\n"); for (i = 0; i < cold_count; i++) len += sysfs_emit_at(buf, len, "%s\n", extlist[i]); len += sysfs_emit_at(buf, len, "hot file extension:\n"); for (i = cold_count; i < cold_count + hot_count; i++) len += sysfs_emit_at(buf, len, "%s\n", extlist[i]); return len; } if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) { struct ckpt_req_control *cprc = &sbi->cprc_info; int class = IOPRIO_PRIO_CLASS(cprc->ckpt_thread_ioprio); int level = IOPRIO_PRIO_LEVEL(cprc->ckpt_thread_ioprio); if (class != IOPRIO_CLASS_RT && class != IOPRIO_CLASS_BE) return -EINVAL; return sysfs_emit(buf, "%s,%d\n", class == IOPRIO_CLASS_RT ? "rt" : "be", level); } #ifdef CONFIG_F2FS_FS_COMPRESSION if (!strcmp(a->attr.name, "compr_written_block")) return sysfs_emit(buf, "%llu\n", sbi->compr_written_block); if (!strcmp(a->attr.name, "compr_saved_block")) return sysfs_emit(buf, "%llu\n", sbi->compr_saved_block); if (!strcmp(a->attr.name, "compr_new_inode")) return sysfs_emit(buf, "%u\n", sbi->compr_new_inode); #endif if (!strcmp(a->attr.name, "gc_segment_mode")) return sysfs_emit(buf, "%u\n", sbi->gc_segment_mode); if (!strcmp(a->attr.name, "gc_reclaimed_segments")) { return sysfs_emit(buf, "%u\n", sbi->gc_reclaimed_segs[sbi->gc_segment_mode]); } if (!strcmp(a->attr.name, "current_atomic_write")) { s64 current_write = atomic64_read(&sbi->current_atomic_write); return sysfs_emit(buf, "%lld\n", current_write); } if (!strcmp(a->attr.name, "peak_atomic_write")) return sysfs_emit(buf, "%lld\n", sbi->peak_atomic_write); if (!strcmp(a->attr.name, "committed_atomic_block")) return sysfs_emit(buf, "%llu\n", sbi->committed_atomic_block); if (!strcmp(a->attr.name, "revoked_atomic_block")) return sysfs_emit(buf, "%llu\n", sbi->revoked_atomic_block); #ifdef CONFIG_F2FS_STAT_FS if (!strcmp(a->attr.name, "cp_foreground_calls")) return sysfs_emit(buf, "%d\n", atomic_read(&sbi->cp_call_count[TOTAL_CALL]) - atomic_read(&sbi->cp_call_count[BACKGROUND])); if (!strcmp(a->attr.name, "cp_background_calls")) return sysfs_emit(buf, "%d\n", atomic_read(&sbi->cp_call_count[BACKGROUND])); #endif ui = (unsigned int *)(ptr + a->offset); return sysfs_emit(buf, "%u\n", *ui); } static ssize_t __sbi_store(struct f2fs_attr *a, struct f2fs_sb_info *sbi, const char *buf, size_t count) { unsigned char *ptr; unsigned long t; unsigned int *ui; ssize_t ret; ptr = __struct_ptr(sbi, a->struct_type); if (!ptr) return -EINVAL; if (!strcmp(a->attr.name, "extension_list")) { const char *name = strim((char *)buf); bool set = true, hot; if (!strncmp(name, "[h]", 3)) hot = true; else if (!strncmp(name, "[c]", 3)) hot = false; else return -EINVAL; name += 3; if (*name == '!') { name++; set = false; } if (!strlen(name) || strlen(name) >= F2FS_EXTENSION_LEN) return -EINVAL; f2fs_down_write(&sbi->sb_lock); ret = f2fs_update_extension_list(sbi, name, hot, set); if (ret) goto out; ret = f2fs_commit_super(sbi, false); if (ret) f2fs_update_extension_list(sbi, name, hot, !set); out: f2fs_up_write(&sbi->sb_lock); return ret ? ret : count; } if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) { const char *name = strim((char *)buf); struct ckpt_req_control *cprc = &sbi->cprc_info; int class; long level; int ret; if (!strncmp(name, "rt,", 3)) class = IOPRIO_CLASS_RT; else if (!strncmp(name, "be,", 3)) class = IOPRIO_CLASS_BE; else return -EINVAL; name += 3; ret = kstrtol(name, 10, &level); if (ret) return ret; if (level >= IOPRIO_NR_LEVELS || level < 0) return -EINVAL; cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, level); if (test_opt(sbi, MERGE_CHECKPOINT)) { ret = set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio); if (ret) return ret; } return count; } ui = (unsigned int *)(ptr + a->offset); ret = kstrtoul(skip_spaces(buf), 0, &t); if (ret < 0) return ret; #ifdef CONFIG_F2FS_FAULT_INJECTION if (a->struct_type == FAULT_INFO_TYPE) { if (f2fs_build_fault_attr(sbi, 0, t, FAULT_TYPE)) return -EINVAL; return count; } if (a->struct_type == FAULT_INFO_RATE) { if (f2fs_build_fault_attr(sbi, t, 0, FAULT_RATE)) return -EINVAL; return count; } #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); if (t > (unsigned long)(sbi->user_block_count - F2FS_OPTION(sbi).root_reserved_blocks)) { spin_unlock(&sbi->stat_lock); return -EINVAL; } *ui = t; sbi->current_reserved_blocks = min(sbi->reserved_blocks, sbi->user_block_count - valid_user_blocks(sbi)); spin_unlock(&sbi->stat_lock); return count; } if (!strcmp(a->attr.name, "discard_io_aware_gran")) { if (t > MAX_PLIST_NUM) return -EINVAL; if (!f2fs_block_unit_discard(sbi)) return -EINVAL; if (t == *ui) return count; *ui = t; return count; } if (!strcmp(a->attr.name, "discard_granularity")) { if (t == 0 || t > MAX_PLIST_NUM) return -EINVAL; if (!f2fs_block_unit_discard(sbi)) return -EINVAL; if (t == *ui) return count; *ui = t; return count; } if (!strcmp(a->attr.name, "max_ordered_discard")) { if (t == 0 || t > MAX_PLIST_NUM) return -EINVAL; if (!f2fs_block_unit_discard(sbi)) return -EINVAL; *ui = t; return count; } if (!strcmp(a->attr.name, "discard_urgent_util")) { if (t > 100) return -EINVAL; *ui = t; return count; } if (!strcmp(a->attr.name, "discard_io_aware")) { if (t >= DPOLICY_IO_AWARE_MAX) return -EINVAL; *ui = t; return count; } if (!strcmp(a->attr.name, "migration_granularity")) { if (t == 0 || t > SEGS_PER_SEC(sbi)) return -EINVAL; } if (!strcmp(a->attr.name, "migration_window_granularity")) { if (t == 0 || t > SEGS_PER_SEC(sbi)) return -EINVAL; } if (!strcmp(a->attr.name, "gc_urgent")) { if (t == 0) { sbi->gc_mode = GC_NORMAL; } else if (t == 1) { sbi->gc_mode = GC_URGENT_HIGH; if (sbi->gc_thread) { sbi->gc_thread->gc_wake = true; wake_up_interruptible_all( &sbi->gc_thread->gc_wait_queue_head); wake_up_discard_thread(sbi, true); } } else if (t == 2) { sbi->gc_mode = GC_URGENT_LOW; } else if (t == 3) { sbi->gc_mode = GC_URGENT_MID; if (sbi->gc_thread) { sbi->gc_thread->gc_wake = true; wake_up_interruptible_all( &sbi->gc_thread->gc_wait_queue_head); } } else { return -EINVAL; } return count; } if (!strcmp(a->attr.name, "gc_idle")) { if (t == GC_IDLE_CB) { sbi->gc_mode = GC_IDLE_CB; } else if (t == GC_IDLE_GREEDY) { sbi->gc_mode = GC_IDLE_GREEDY; } else if (t == GC_IDLE_AT) { if (!sbi->am.atgc_enabled) return -EINVAL; sbi->gc_mode = GC_IDLE_AT; } else { sbi->gc_mode = GC_NORMAL; } return count; } if (!strcmp(a->attr.name, "gc_remaining_trials")) { spin_lock(&sbi->gc_remaining_trials_lock); sbi->gc_remaining_trials = t; spin_unlock(&sbi->gc_remaining_trials_lock); return count; } if (!strcmp(a->attr.name, "gc_no_zoned_gc_percent")) { if (t > 100) return -EINVAL; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "gc_boost_zoned_gc_percent")) { if (t > 100) return -EINVAL; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "gc_valid_thresh_ratio")) { if (t > 100) return -EINVAL; *ui = (unsigned int)t; return count; } #ifdef CONFIG_F2FS_IOSTAT if (!strcmp(a->attr.name, "iostat_enable")) { sbi->iostat_enable = !!t; if (!sbi->iostat_enable) f2fs_reset_iostat(sbi); return count; } if (!strcmp(a->attr.name, "iostat_period_ms")) { if (t < MIN_IOSTAT_PERIOD_MS || t > MAX_IOSTAT_PERIOD_MS) return -EINVAL; spin_lock_irq(&sbi->iostat_lock); sbi->iostat_period_ms = (unsigned int)t; spin_unlock_irq(&sbi->iostat_lock); return count; } #endif #ifdef CONFIG_BLK_DEV_ZONED if (!strcmp(a->attr.name, "blkzone_alloc_policy")) { if (t < BLKZONE_ALLOC_PRIOR_SEQ || t > BLKZONE_ALLOC_PRIOR_CONV) return -EINVAL; sbi->blkzone_alloc_policy = t; return count; } #endif #ifdef CONFIG_F2FS_FS_COMPRESSION if (!strcmp(a->attr.name, "compr_written_block") || !strcmp(a->attr.name, "compr_saved_block")) { if (t != 0) return -EINVAL; sbi->compr_written_block = 0; sbi->compr_saved_block = 0; return count; } if (!strcmp(a->attr.name, "compr_new_inode")) { if (t != 0) return -EINVAL; sbi->compr_new_inode = 0; return count; } if (!strcmp(a->attr.name, "compress_percent")) { if (t == 0 || t > 100) return -EINVAL; *ui = t; return count; } if (!strcmp(a->attr.name, "compress_watermark")) { if (t == 0 || t > 100) return -EINVAL; *ui = t; return count; } #endif if (!strcmp(a->attr.name, "atgc_candidate_ratio")) { if (t > 100) return -EINVAL; sbi->am.candidate_ratio = t; return count; } if (!strcmp(a->attr.name, "atgc_age_weight")) { if (t > 100) return -EINVAL; sbi->am.age_weight = t; return count; } if (!strcmp(a->attr.name, "gc_segment_mode")) { if (t < MAX_GC_MODE) sbi->gc_segment_mode = t; else return -EINVAL; return count; } if (!strcmp(a->attr.name, "gc_pin_file_threshold")) { if (t > MAX_GC_FAILED_PINNED_FILES) return -EINVAL; sbi->gc_pin_file_threshold = t; return count; } if (!strcmp(a->attr.name, "gc_reclaimed_segments")) { if (t != 0) return -EINVAL; sbi->gc_reclaimed_segs[sbi->gc_segment_mode] = 0; return count; } if (!strcmp(a->attr.name, "seq_file_ra_mul")) { if (t >= MIN_RA_MUL && t <= MAX_RA_MUL) sbi->seq_file_ra_mul = t; else return -EINVAL; return count; } if (!strcmp(a->attr.name, "max_fragment_chunk")) { if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) sbi->max_fragment_chunk = t; else return -EINVAL; return count; } if (!strcmp(a->attr.name, "max_fragment_hole")) { if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) sbi->max_fragment_hole = t; else return -EINVAL; return count; } if (!strcmp(a->attr.name, "peak_atomic_write")) { if (t != 0) return -EINVAL; sbi->peak_atomic_write = 0; return count; } if (!strcmp(a->attr.name, "committed_atomic_block")) { if (t != 0) return -EINVAL; sbi->committed_atomic_block = 0; return count; } if (!strcmp(a->attr.name, "revoked_atomic_block")) { if (t != 0) return -EINVAL; sbi->revoked_atomic_block = 0; return count; } if (!strcmp(a->attr.name, "readdir_ra")) { sbi->readdir_ra = !!t; return count; } if (!strcmp(a->attr.name, "hot_data_age_threshold")) { if (t == 0 || t >= sbi->warm_data_age_threshold) return -EINVAL; if (t == *ui) return count; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "warm_data_age_threshold")) { if (t <= sbi->hot_data_age_threshold) return -EINVAL; if (t == *ui) return count; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "last_age_weight")) { if (t > 100) return -EINVAL; if (t == *ui) return count; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "max_read_extent_count")) { if (t > UINT_MAX) return -EINVAL; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "ipu_policy")) { if (t >= BIT(F2FS_IPU_MAX)) return -EINVAL; /* allow F2FS_IPU_NOCACHE only for IPU in the pinned file */ if (f2fs_lfs_mode(sbi) && (t & ~BIT(F2FS_IPU_NOCACHE))) return -EINVAL; SM_I(sbi)->ipu_policy = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "dir_level")) { if (t > MAX_DIR_HASH_DEPTH) return -EINVAL; sbi->dir_level = t; return count; } if (!strcmp(a->attr.name, "reserved_pin_section")) { if (t > GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi))) return -EINVAL; *ui = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "gc_boost_gc_multiple")) { if (t < 1 || t > SEGS_PER_SEC(sbi)) return -EINVAL; sbi->gc_thread->boost_gc_multiple = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "gc_boost_gc_greedy")) { if (t > GC_GREEDY) return -EINVAL; sbi->gc_thread->boost_gc_greedy = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "bggc_io_aware")) { if (t < AWARE_ALL_IO || t > AWARE_NONE) return -EINVAL; sbi->bggc_io_aware = t; return count; } if (!strcmp(a->attr.name, "allocate_section_hint")) { if (t < 0 || t > MAIN_SECS(sbi)) return -EINVAL; sbi->allocate_section_hint = t; return count; } if (!strcmp(a->attr.name, "allocate_section_policy")) { if (t < ALLOCATE_FORWARD_NOHINT || t > ALLOCATE_FORWARD_FROM_HINT) return -EINVAL; sbi->allocate_section_policy = t; return count; } *ui = (unsigned int)t; return count; } static ssize_t f2fs_sbi_store(struct f2fs_attr *a, struct f2fs_sb_info *sbi, const char *buf, size_t count) { ssize_t ret; bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") || a->struct_type == GC_THREAD); if (gc_entry) { if (!down_read_trylock(&sbi->sb->s_umount)) return -EAGAIN; } ret = __sbi_store(a, sbi, buf, count); if (gc_entry) up_read(&sbi->sb->s_umount); return ret; } static ssize_t f2fs_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_kobj); struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); return a->show ? a->show(a, sbi, buf) : 0; } static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_kobj); struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); return a->store ? a->store(a, sbi, buf, len) : 0; } static void f2fs_sb_release(struct kobject *kobj) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_kobj); complete(&sbi->s_kobj_unregister); } static ssize_t f2fs_base_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct f2fs_base_attr *a = container_of(attr, struct f2fs_base_attr, attr); return a->show ? a->show(a, buf) : 0; } static ssize_t f2fs_base_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { struct f2fs_base_attr *a = container_of(attr, struct f2fs_base_attr, attr); return a->store ? a->store(a, buf, len) : 0; } /* * Note that there are three feature list entries: * 1) /sys/fs/f2fs/features * : shows runtime features supported by in-kernel f2fs along with Kconfig. * - ref. F2FS_FEATURE_RO_ATTR() * * 2) /sys/fs/f2fs/$s_id/features <deprecated> * : shows on-disk features enabled by mkfs.f2fs, used for old kernels. This * won't add new feature anymore, and thus, users should check entries in 3) * instead of this 2). * * 3) /sys/fs/f2fs/$s_id/feature_list * : shows on-disk features enabled by mkfs.f2fs per instance, which follows * sysfs entry rule where each entry should expose single value. * This list covers old feature list provided by 2) and beyond. Therefore, * please add new on-disk feature in this list only. * - ref. F2FS_SB_FEATURE_RO_ATTR() */ static ssize_t f2fs_feature_show(struct f2fs_base_attr *a, char *buf) { return sysfs_emit(buf, "supported\n"); } #define F2FS_FEATURE_RO_ATTR(_name) \ static struct f2fs_base_attr f2fs_base_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = 0444 }, \ .show = f2fs_feature_show, \ } static ssize_t f2fs_tune_show(struct f2fs_base_attr *a, char *buf) { unsigned int res = 0; if (!strcmp(a->attr.name, "reclaim_caches_kb")) res = f2fs_donate_files(); return sysfs_emit(buf, "%u\n", res); } static ssize_t f2fs_tune_store(struct f2fs_base_attr *a, const char *buf, size_t count) { unsigned long t; int ret; ret = kstrtoul(skip_spaces(buf), 0, &t); if (ret) return ret; if (!strcmp(a->attr.name, "reclaim_caches_kb")) f2fs_reclaim_caches(t); return count; } #define F2FS_TUNE_RW_ATTR(_name) \ static struct f2fs_base_attr f2fs_base_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = 0644 }, \ .show = f2fs_tune_show, \ .store = f2fs_tune_store, \ } static ssize_t f2fs_sb_feature_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { if (F2FS_HAS_FEATURE(sbi, a->id)) return sysfs_emit(buf, "supported\n"); return sysfs_emit(buf, "unsupported\n"); } #define F2FS_SB_FEATURE_RO_ATTR(_name, _feat) \ static struct f2fs_attr f2fs_attr_sb_##_name = { \ .attr = {.name = __stringify(_name), .mode = 0444 }, \ .show = f2fs_sb_feature_show, \ .id = F2FS_FEATURE_##_feat, \ } #define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \ static struct f2fs_attr f2fs_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ .struct_type = _struct_type, \ .offset = _offset \ } #define F2FS_RO_ATTR(struct_type, struct_name, name, elname) \ F2FS_ATTR_OFFSET(struct_type, name, 0444, \ f2fs_sbi_show, NULL, \ offsetof(struct struct_name, elname)) #define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ F2FS_ATTR_OFFSET(struct_type, name, 0644, \ f2fs_sbi_show, f2fs_sbi_store, \ offsetof(struct struct_name, elname)) #define F2FS_GENERAL_RO_ATTR(name) \ static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) #ifdef CONFIG_F2FS_STAT_FS #define STAT_INFO_RO_ATTR(name, elname) \ F2FS_RO_ATTR(STAT_INFO, f2fs_stat_info, name, elname) #endif #define GC_THREAD_RW_ATTR(name, elname) \ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, name, elname) #define SM_INFO_RW_ATTR(name, elname) \ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, name, elname) #define SM_INFO_GENERAL_RW_ATTR(elname) \ SM_INFO_RW_ATTR(elname, elname) #define DCC_INFO_RW_ATTR(name, elname) \ F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, name, elname) #define DCC_INFO_GENERAL_RW_ATTR(elname) \ DCC_INFO_RW_ATTR(elname, elname) #define NM_INFO_RW_ATTR(name, elname) \ F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, name, elname) #define NM_INFO_GENERAL_RW_ATTR(elname) \ NM_INFO_RW_ATTR(elname, elname) #define F2FS_SBI_RW_ATTR(name, elname) \ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, name, elname) #define F2FS_SBI_GENERAL_RW_ATTR(elname) \ F2FS_SBI_RW_ATTR(elname, elname) #define F2FS_SBI_GENERAL_RO_ATTR(elname) \ F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, elname, elname) #ifdef CONFIG_F2FS_FAULT_INJECTION #define FAULT_INFO_GENERAL_RW_ATTR(type, elname) \ F2FS_RW_ATTR(type, f2fs_fault_info, elname, elname) #endif #define RESERVED_BLOCKS_GENERAL_RW_ATTR(elname) \ F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, elname, elname) #define CPRC_INFO_GENERAL_RW_ATTR(elname) \ F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, elname, elname) #define ATGC_INFO_RW_ATTR(name, elname) \ F2FS_RW_ATTR(ATGC_INFO, atgc_management, name, elname) /* GC_THREAD ATTR */ GC_THREAD_RW_ATTR(gc_urgent_sleep_time, urgent_sleep_time); GC_THREAD_RW_ATTR(gc_min_sleep_time, min_sleep_time); GC_THREAD_RW_ATTR(gc_max_sleep_time, max_sleep_time); GC_THREAD_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time); GC_THREAD_RW_ATTR(gc_no_zoned_gc_percent, no_zoned_gc_percent); GC_THREAD_RW_ATTR(gc_boost_zoned_gc_percent, boost_zoned_gc_percent); GC_THREAD_RW_ATTR(gc_valid_thresh_ratio, valid_thresh_ratio); GC_THREAD_RW_ATTR(gc_boost_gc_multiple, boost_gc_multiple); GC_THREAD_RW_ATTR(gc_boost_gc_greedy, boost_gc_greedy); /* SM_INFO ATTR */ SM_INFO_RW_ATTR(reclaim_segments, rec_prefree_segments); SM_INFO_GENERAL_RW_ATTR(ipu_policy); SM_INFO_GENERAL_RW_ATTR(min_ipu_util); SM_INFO_GENERAL_RW_ATTR(min_fsync_blocks); SM_INFO_GENERAL_RW_ATTR(min_seq_blocks); SM_INFO_GENERAL_RW_ATTR(min_hot_blocks); SM_INFO_GENERAL_RW_ATTR(min_ssr_sections); SM_INFO_GENERAL_RW_ATTR(reserved_segments); /* DCC_INFO ATTR */ DCC_INFO_RW_ATTR(max_small_discards, max_discards); DCC_INFO_GENERAL_RW_ATTR(max_discard_request); DCC_INFO_GENERAL_RW_ATTR(min_discard_issue_time); DCC_INFO_GENERAL_RW_ATTR(mid_discard_issue_time); DCC_INFO_GENERAL_RW_ATTR(max_discard_issue_time); DCC_INFO_GENERAL_RW_ATTR(discard_io_aware_gran); DCC_INFO_GENERAL_RW_ATTR(discard_urgent_util); DCC_INFO_GENERAL_RW_ATTR(discard_granularity); DCC_INFO_GENERAL_RW_ATTR(max_ordered_discard); DCC_INFO_GENERAL_RW_ATTR(discard_io_aware); /* NM_INFO ATTR */ NM_INFO_RW_ATTR(max_roll_forward_node_blocks, max_rf_node_blocks); NM_INFO_GENERAL_RW_ATTR(ram_thresh); NM_INFO_GENERAL_RW_ATTR(ra_nid_pages); NM_INFO_GENERAL_RW_ATTR(dirty_nats_ratio); /* F2FS_SBI ATTR */ F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list); F2FS_SBI_RW_ATTR(gc_idle, gc_mode); F2FS_SBI_RW_ATTR(gc_urgent, gc_mode); F2FS_SBI_RW_ATTR(cp_interval, interval_time[CP_TIME]); F2FS_SBI_RW_ATTR(idle_interval, interval_time[REQ_TIME]); F2FS_SBI_RW_ATTR(discard_idle_interval, interval_time[DISCARD_TIME]); F2FS_SBI_RW_ATTR(gc_idle_interval, interval_time[GC_TIME]); F2FS_SBI_RW_ATTR(umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); F2FS_SBI_RW_ATTR(gc_pin_file_thresh, gc_pin_file_threshold); F2FS_SBI_RW_ATTR(gc_reclaimed_segments, gc_reclaimed_segs); F2FS_SBI_GENERAL_RW_ATTR(max_victim_search); F2FS_SBI_GENERAL_RW_ATTR(migration_granularity); F2FS_SBI_GENERAL_RW_ATTR(migration_window_granularity); F2FS_SBI_GENERAL_RW_ATTR(dir_level); F2FS_SBI_GENERAL_RW_ATTR(allocate_section_hint); F2FS_SBI_GENERAL_RW_ATTR(allocate_section_policy); #ifdef CONFIG_F2FS_IOSTAT F2FS_SBI_GENERAL_RW_ATTR(iostat_enable); F2FS_SBI_GENERAL_RW_ATTR(iostat_period_ms); #endif F2FS_SBI_GENERAL_RW_ATTR(readdir_ra); F2FS_SBI_GENERAL_RW_ATTR(max_io_bytes); F2FS_SBI_GENERAL_RW_ATTR(data_io_flag); F2FS_SBI_GENERAL_RW_ATTR(node_io_flag); F2FS_SBI_GENERAL_RW_ATTR(gc_remaining_trials); F2FS_SBI_GENERAL_RW_ATTR(seq_file_ra_mul); F2FS_SBI_GENERAL_RW_ATTR(gc_segment_mode); F2FS_SBI_GENERAL_RW_ATTR(max_fragment_chunk); F2FS_SBI_GENERAL_RW_ATTR(max_fragment_hole); #ifdef CONFIG_F2FS_FS_COMPRESSION F2FS_SBI_GENERAL_RW_ATTR(compr_written_block); F2FS_SBI_GENERAL_RW_ATTR(compr_saved_block); F2FS_SBI_GENERAL_RW_ATTR(compr_new_inode); F2FS_SBI_GENERAL_RW_ATTR(compress_percent); F2FS_SBI_GENERAL_RW_ATTR(compress_watermark); #endif /* atomic write */ F2FS_SBI_GENERAL_RO_ATTR(current_atomic_write); F2FS_SBI_GENERAL_RW_ATTR(peak_atomic_write); F2FS_SBI_GENERAL_RW_ATTR(committed_atomic_block); F2FS_SBI_GENERAL_RW_ATTR(revoked_atomic_block); /* block age extent cache */ F2FS_SBI_GENERAL_RW_ATTR(hot_data_age_threshold); F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold); F2FS_SBI_GENERAL_RW_ATTR(last_age_weight); /* read extent cache */ F2FS_SBI_GENERAL_RW_ATTR(max_read_extent_count); #ifdef CONFIG_BLK_DEV_ZONED F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec); F2FS_SBI_GENERAL_RO_ATTR(max_open_zones); F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy); #endif F2FS_SBI_GENERAL_RW_ATTR(carve_out); F2FS_SBI_GENERAL_RW_ATTR(reserved_pin_section); F2FS_SBI_GENERAL_RW_ATTR(bggc_io_aware); /* STAT_INFO ATTR */ #ifdef CONFIG_F2FS_STAT_FS STAT_INFO_RO_ATTR(cp_foreground_calls, cp_call_count[FOREGROUND]); STAT_INFO_RO_ATTR(cp_background_calls, cp_call_count[BACKGROUND]); STAT_INFO_RO_ATTR(gc_foreground_calls, gc_call_count[FOREGROUND]); STAT_INFO_RO_ATTR(gc_background_calls, gc_call_count[BACKGROUND]); #endif /* FAULT_INFO ATTR */ #ifdef CONFIG_F2FS_FAULT_INJECTION FAULT_INFO_GENERAL_RW_ATTR(FAULT_INFO_RATE, inject_rate); FAULT_INFO_GENERAL_RW_ATTR(FAULT_INFO_TYPE, inject_type); #endif /* RESERVED_BLOCKS ATTR */ RESERVED_BLOCKS_GENERAL_RW_ATTR(reserved_blocks); /* CPRC_INFO ATTR */ CPRC_INFO_GENERAL_RW_ATTR(ckpt_thread_ioprio); /* ATGC_INFO ATTR */ ATGC_INFO_RW_ATTR(atgc_candidate_ratio, candidate_ratio); ATGC_INFO_RW_ATTR(atgc_candidate_count, max_candidate_count); ATGC_INFO_RW_ATTR(atgc_age_weight, age_weight); ATGC_INFO_RW_ATTR(atgc_age_threshold, age_threshold); F2FS_GENERAL_RO_ATTR(dirty_segments); F2FS_GENERAL_RO_ATTR(free_segments); F2FS_GENERAL_RO_ATTR(ovp_segments); F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(current_reserved_blocks); F2FS_GENERAL_RO_ATTR(unusable); F2FS_GENERAL_RO_ATTR(encoding); F2FS_GENERAL_RO_ATTR(encoding_flags); F2FS_GENERAL_RO_ATTR(effective_lookup_mode); F2FS_GENERAL_RO_ATTR(mounted_time_sec); F2FS_GENERAL_RO_ATTR(main_blkaddr); F2FS_GENERAL_RO_ATTR(pending_discard); F2FS_GENERAL_RO_ATTR(atgc_enabled); F2FS_GENERAL_RO_ATTR(gc_mode); #ifdef CONFIG_F2FS_STAT_FS F2FS_GENERAL_RO_ATTR(moved_blocks_background); F2FS_GENERAL_RO_ATTR(moved_blocks_foreground); F2FS_GENERAL_RO_ATTR(avg_vblocks); #endif #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption); F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2); #if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif #endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED F2FS_FEATURE_RO_ATTR(block_zoned); #endif F2FS_FEATURE_RO_ATTR(atomic_write); F2FS_FEATURE_RO_ATTR(extra_attr); F2FS_FEATURE_RO_ATTR(project_quota); F2FS_FEATURE_RO_ATTR(inode_checksum); F2FS_FEATURE_RO_ATTR(flexible_inline_xattr); F2FS_FEATURE_RO_ATTR(quota_ino); F2FS_FEATURE_RO_ATTR(inode_crtime); F2FS_FEATURE_RO_ATTR(lost_found); #ifdef CONFIG_FS_VERITY F2FS_FEATURE_RO_ATTR(verity); #endif F2FS_FEATURE_RO_ATTR(sb_checksum); #if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(casefold); #endif F2FS_FEATURE_RO_ATTR(readonly); #ifdef CONFIG_F2FS_FS_COMPRESSION F2FS_FEATURE_RO_ATTR(compression); #endif F2FS_FEATURE_RO_ATTR(pin_file); #ifdef CONFIG_UNICODE F2FS_FEATURE_RO_ATTR(linear_lookup); #endif F2FS_FEATURE_RO_ATTR(packed_ssa); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { ATTR_LIST(gc_urgent_sleep_time), ATTR_LIST(gc_min_sleep_time), ATTR_LIST(gc_max_sleep_time), ATTR_LIST(gc_no_gc_sleep_time), ATTR_LIST(gc_no_zoned_gc_percent), ATTR_LIST(gc_boost_zoned_gc_percent), ATTR_LIST(gc_valid_thresh_ratio), ATTR_LIST(gc_boost_gc_multiple), ATTR_LIST(gc_boost_gc_greedy), ATTR_LIST(gc_idle), ATTR_LIST(gc_urgent), ATTR_LIST(reclaim_segments), ATTR_LIST(main_blkaddr), ATTR_LIST(max_small_discards), ATTR_LIST(max_discard_request), ATTR_LIST(min_discard_issue_time), ATTR_LIST(mid_discard_issue_time), ATTR_LIST(max_discard_issue_time), ATTR_LIST(discard_io_aware_gran), ATTR_LIST(discard_urgent_util), ATTR_LIST(discard_granularity), ATTR_LIST(max_ordered_discard), ATTR_LIST(discard_io_aware), ATTR_LIST(pending_discard), ATTR_LIST(gc_mode), ATTR_LIST(ipu_policy), ATTR_LIST(min_ipu_util), ATTR_LIST(min_fsync_blocks), ATTR_LIST(min_seq_blocks), ATTR_LIST(min_hot_blocks), ATTR_LIST(min_ssr_sections), ATTR_LIST(reserved_segments), ATTR_LIST(max_victim_search), ATTR_LIST(migration_granularity), ATTR_LIST(migration_window_granularity), ATTR_LIST(dir_level), ATTR_LIST(ram_thresh), ATTR_LIST(ra_nid_pages), ATTR_LIST(dirty_nats_ratio), ATTR_LIST(max_roll_forward_node_blocks), ATTR_LIST(cp_interval), ATTR_LIST(idle_interval), ATTR_LIST(discard_idle_interval), ATTR_LIST(gc_idle_interval), ATTR_LIST(umount_discard_timeout), ATTR_LIST(bggc_io_aware), #ifdef CONFIG_F2FS_IOSTAT ATTR_LIST(iostat_enable), ATTR_LIST(iostat_period_ms), #endif ATTR_LIST(readdir_ra), ATTR_LIST(max_io_bytes), ATTR_LIST(gc_pin_file_thresh), ATTR_LIST(extension_list), #ifdef CONFIG_F2FS_FAULT_INJECTION ATTR_LIST(inject_rate), ATTR_LIST(inject_type), #endif ATTR_LIST(data_io_flag), ATTR_LIST(node_io_flag), ATTR_LIST(gc_remaining_trials), ATTR_LIST(ckpt_thread_ioprio), ATTR_LIST(dirty_segments), ATTR_LIST(free_segments), ATTR_LIST(ovp_segments), ATTR_LIST(unusable), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(features), ATTR_LIST(reserved_blocks), ATTR_LIST(current_reserved_blocks), ATTR_LIST(encoding), ATTR_LIST(encoding_flags), ATTR_LIST(effective_lookup_mode), ATTR_LIST(mounted_time_sec), #ifdef CONFIG_F2FS_STAT_FS ATTR_LIST(cp_foreground_calls), ATTR_LIST(cp_background_calls), ATTR_LIST(gc_foreground_calls), ATTR_LIST(gc_background_calls), ATTR_LIST(moved_blocks_foreground), ATTR_LIST(moved_blocks_background), ATTR_LIST(avg_vblocks), #endif #ifdef CONFIG_BLK_DEV_ZONED ATTR_LIST(unusable_blocks_per_sec), ATTR_LIST(max_open_zones), ATTR_LIST(blkzone_alloc_policy), #endif #ifdef CONFIG_F2FS_FS_COMPRESSION ATTR_LIST(compr_written_block), ATTR_LIST(compr_saved_block), ATTR_LIST(compr_new_inode), ATTR_LIST(compress_percent), ATTR_LIST(compress_watermark), #endif /* For ATGC */ ATTR_LIST(atgc_candidate_ratio), ATTR_LIST(atgc_candidate_count), ATTR_LIST(atgc_age_weight), ATTR_LIST(atgc_age_threshold), ATTR_LIST(atgc_enabled), ATTR_LIST(seq_file_ra_mul), ATTR_LIST(gc_segment_mode), ATTR_LIST(gc_reclaimed_segments), ATTR_LIST(max_fragment_chunk), ATTR_LIST(max_fragment_hole), ATTR_LIST(current_atomic_write), ATTR_LIST(peak_atomic_write), ATTR_LIST(committed_atomic_block), ATTR_LIST(revoked_atomic_block), ATTR_LIST(hot_data_age_threshold), ATTR_LIST(warm_data_age_threshold), ATTR_LIST(last_age_weight), ATTR_LIST(max_read_extent_count), ATTR_LIST(carve_out), ATTR_LIST(reserved_pin_section), ATTR_LIST(allocate_section_hint), ATTR_LIST(allocate_section_policy), NULL, }; ATTRIBUTE_GROUPS(f2fs); #define BASE_ATTR_LIST(name) (&f2fs_base_attr_##name.attr) static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION BASE_ATTR_LIST(encryption), BASE_ATTR_LIST(test_dummy_encryption_v2), #if IS_ENABLED(CONFIG_UNICODE) BASE_ATTR_LIST(encrypted_casefold), #endif #endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED BASE_ATTR_LIST(block_zoned), #endif BASE_ATTR_LIST(atomic_write), BASE_ATTR_LIST(extra_attr), BASE_ATTR_LIST(project_quota), BASE_ATTR_LIST(inode_checksum), BASE_ATTR_LIST(flexible_inline_xattr), BASE_ATTR_LIST(quota_ino), BASE_ATTR_LIST(inode_crtime), BASE_ATTR_LIST(lost_found), #ifdef CONFIG_FS_VERITY BASE_ATTR_LIST(verity), #endif BASE_ATTR_LIST(sb_checksum), #if IS_ENABLED(CONFIG_UNICODE) BASE_ATTR_LIST(casefold), #endif BASE_ATTR_LIST(readonly), #ifdef CONFIG_F2FS_FS_COMPRESSION BASE_ATTR_LIST(compression), #endif BASE_ATTR_LIST(pin_file), #ifdef CONFIG_UNICODE BASE_ATTR_LIST(linear_lookup), #endif BASE_ATTR_LIST(packed_ssa), NULL, }; ATTRIBUTE_GROUPS(f2fs_feat); F2FS_GENERAL_RO_ATTR(sb_status); F2FS_GENERAL_RO_ATTR(cp_status); F2FS_GENERAL_RO_ATTR(issued_discard); F2FS_GENERAL_RO_ATTR(queued_discard); F2FS_GENERAL_RO_ATTR(undiscard_blks); static struct attribute *f2fs_stat_attrs[] = { ATTR_LIST(sb_status), ATTR_LIST(cp_status), ATTR_LIST(issued_discard), ATTR_LIST(queued_discard), ATTR_LIST(undiscard_blks), NULL, }; ATTRIBUTE_GROUPS(f2fs_stat); F2FS_SB_FEATURE_RO_ATTR(encryption, ENCRYPT); F2FS_SB_FEATURE_RO_ATTR(block_zoned, BLKZONED); F2FS_SB_FEATURE_RO_ATTR(extra_attr, EXTRA_ATTR); F2FS_SB_FEATURE_RO_ATTR(project_quota, PRJQUOTA); F2FS_SB_FEATURE_RO_ATTR(inode_checksum, INODE_CHKSUM); F2FS_SB_FEATURE_RO_ATTR(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); F2FS_SB_FEATURE_RO_ATTR(quota_ino, QUOTA_INO); F2FS_SB_FEATURE_RO_ATTR(inode_crtime, INODE_CRTIME); F2FS_SB_FEATURE_RO_ATTR(lost_found, LOST_FOUND); F2FS_SB_FEATURE_RO_ATTR(verity, VERITY); F2FS_SB_FEATURE_RO_ATTR(sb_checksum, SB_CHKSUM); F2FS_SB_FEATURE_RO_ATTR(casefold, CASEFOLD); F2FS_SB_FEATURE_RO_ATTR(compression, COMPRESSION); F2FS_SB_FEATURE_RO_ATTR(readonly, RO); F2FS_SB_FEATURE_RO_ATTR(device_alias, DEVICE_ALIAS); F2FS_SB_FEATURE_RO_ATTR(packed_ssa, PACKED_SSA); static struct attribute *f2fs_sb_feat_attrs[] = { ATTR_LIST(sb_encryption), ATTR_LIST(sb_block_zoned), ATTR_LIST(sb_extra_attr), ATTR_LIST(sb_project_quota), ATTR_LIST(sb_inode_checksum), ATTR_LIST(sb_flexible_inline_xattr), ATTR_LIST(sb_quota_ino), ATTR_LIST(sb_inode_crtime), ATTR_LIST(sb_lost_found), ATTR_LIST(sb_verity), ATTR_LIST(sb_sb_checksum), ATTR_LIST(sb_casefold), ATTR_LIST(sb_compression), ATTR_LIST(sb_readonly), ATTR_LIST(sb_device_alias), ATTR_LIST(sb_packed_ssa), NULL, }; ATTRIBUTE_GROUPS(f2fs_sb_feat); F2FS_TUNE_RW_ATTR(reclaim_caches_kb); static struct attribute *f2fs_tune_attrs[] = { BASE_ATTR_LIST(reclaim_caches_kb), NULL, }; ATTRIBUTE_GROUPS(f2fs_tune); static const struct sysfs_ops f2fs_attr_ops = { .show = f2fs_attr_show, .store = f2fs_attr_store, }; static const struct kobj_type f2fs_sb_ktype = { .default_groups = f2fs_groups, .sysfs_ops = &f2fs_attr_ops, .release = f2fs_sb_release, }; static const struct kobj_type f2fs_ktype = { .sysfs_ops = &f2fs_attr_ops, }; static struct kset f2fs_kset = { .kobj = {.ktype = &f2fs_ktype}, }; static const struct sysfs_ops f2fs_feat_attr_ops = { .show = f2fs_base_attr_show, .store = f2fs_base_attr_store, }; static const struct kobj_type f2fs_feat_ktype = { .default_groups = f2fs_feat_groups, .sysfs_ops = &f2fs_feat_attr_ops, }; static struct kobject f2fs_feat = { .kset = &f2fs_kset, }; static const struct sysfs_ops f2fs_tune_attr_ops = { .show = f2fs_base_attr_show, .store = f2fs_base_attr_store, }; static const struct kobj_type f2fs_tune_ktype = { .default_groups = f2fs_tune_groups, .sysfs_ops = &f2fs_tune_attr_ops, }; static struct kobject f2fs_tune = { .kset = &f2fs_kset, }; static ssize_t f2fs_stat_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_stat_kobj); struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); return a->show ? a->show(a, sbi, buf) : 0; } static ssize_t f2fs_stat_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_stat_kobj); struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); return a->store ? a->store(a, sbi, buf, len) : 0; } static void f2fs_stat_kobj_release(struct kobject *kobj) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_stat_kobj); complete(&sbi->s_stat_kobj_unregister); } static const struct sysfs_ops f2fs_stat_attr_ops = { .show = f2fs_stat_attr_show, .store = f2fs_stat_attr_store, }; static const struct kobj_type f2fs_stat_ktype = { .default_groups = f2fs_stat_groups, .sysfs_ops = &f2fs_stat_attr_ops, .release = f2fs_stat_kobj_release, }; static ssize_t f2fs_sb_feat_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_feature_list_kobj); struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); return a->show ? a->show(a, sbi, buf) : 0; } static void f2fs_feature_list_kobj_release(struct kobject *kobj) { struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, s_feature_list_kobj); complete(&sbi->s_feature_list_kobj_unregister); } static const struct sysfs_ops f2fs_feature_list_attr_ops = { .show = f2fs_sb_feat_attr_show, }; static const struct kobj_type f2fs_feature_list_ktype = { .default_groups = f2fs_sb_feat_groups, .sysfs_ops = &f2fs_feature_list_attr_ops, .release = f2fs_feature_list_kobj_release, }; static int __maybe_unused segment_info_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main); int i; seq_puts(seq, "format: segment_type|valid_blocks\n" "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); for (i = 0; i < total_segs; i++) { struct seg_entry *se = get_seg_entry(sbi, i); if ((i % 10) == 0) seq_printf(seq, "%-10d", i); seq_printf(seq, "%d|%-3u", se->type, se->valid_blocks); if ((i % 10) == 9 || i == (total_segs - 1)) seq_putc(seq, '\n'); else seq_putc(seq, ' '); } return 0; } static int __maybe_unused segment_bits_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main); int i, j; seq_puts(seq, "format: segment_type|valid_blocks|bitmaps|mtime\n" "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); for (i = 0; i < total_segs; i++) { struct seg_entry *se = get_seg_entry(sbi, i); seq_printf(seq, "%-10d", i); seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks); for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) seq_printf(seq, " %.2x", se->cur_valid_map[j]); seq_printf(seq, "| %llx", se->mtime); seq_putc(seq, '\n'); } return 0; } static int __maybe_unused victim_bits_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); int i; seq_puts(seq, "format: victim_secmap bitmaps\n"); for (i = 0; i < MAIN_SECS(sbi); i++) { if ((i % 10) == 0) seq_printf(seq, "%-10d", i); seq_printf(seq, "%d", test_bit(i, dirty_i->victim_secmap) ? 1 : 0); if ((i % 10) == 9 || i == (MAIN_SECS(sbi) - 1)) seq_putc(seq, '\n'); else seq_putc(seq, ' '); } return 0; } static int __maybe_unused discard_plist_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; int i, count; seq_puts(seq, "Discard pend list(Show diacrd_cmd count on each entry, .:not exist):\n"); if (!f2fs_realtime_discard_enable(sbi)) return 0; if (dcc) { mutex_lock(&dcc->cmd_lock); for (i = 0; i < MAX_PLIST_NUM; i++) { struct list_head *pend_list; struct discard_cmd *dc, *tmp; if (i % 8 == 0) seq_printf(seq, " %-3d", i); count = 0; pend_list = &dcc->pend_list[i]; list_for_each_entry_safe(dc, tmp, pend_list, list) count++; if (count) seq_printf(seq, " %7d", count); else seq_puts(seq, " ."); if (i % 8 == 7) seq_putc(seq, '\n'); } seq_putc(seq, '\n'); mutex_unlock(&dcc->cmd_lock); } return 0; } static int __maybe_unused disk_map_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); int i; seq_printf(seq, "Address Layout : %5luB Block address (# of Segments)\n", F2FS_BLKSIZE); seq_printf(seq, " SB : %12s\n", "0/1024B"); seq_printf(seq, " seg0_blkaddr : 0x%010x\n", SEG0_BLKADDR(sbi)); seq_printf(seq, " Checkpoint : 0x%010x (%10d)\n", le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr), 2); seq_printf(seq, " SIT : 0x%010x (%10d)\n", SIT_I(sbi)->sit_base_addr, le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_sit)); seq_printf(seq, " NAT : 0x%010x (%10d)\n", NM_I(sbi)->nat_blkaddr, le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_nat)); seq_printf(seq, " SSA : 0x%010x (%10d)\n", SM_I(sbi)->ssa_blkaddr, le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_ssa)); seq_printf(seq, " Main : 0x%010x (%10d)\n", SM_I(sbi)->main_blkaddr, le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_main)); seq_printf(seq, " Block size : %12lu KB\n", F2FS_BLKSIZE >> 10); seq_printf(seq, " Segment size : %12d MB\n", (BLKS_PER_SEG(sbi) << (F2FS_BLKSIZE_BITS - 10)) >> 10); seq_printf(seq, " Segs/Sections : %12d\n", SEGS_PER_SEC(sbi)); seq_printf(seq, " Section size : %12d MB\n", (BLKS_PER_SEC(sbi) << (F2FS_BLKSIZE_BITS - 10)) >> 10); seq_printf(seq, " # of Sections : %12d\n", le32_to_cpu(F2FS_RAW_SUPER(sbi)->section_count)); if (!f2fs_is_multi_device(sbi)) return 0; seq_puts(seq, "\nDisk Map for multi devices:\n"); for (i = 0; i < sbi->s_ndevs; i++) seq_printf(seq, "Disk:%2d (zoned=%d): 0x%010x - 0x%010x on %s\n", i, bdev_is_zoned(FDEV(i).bdev), FDEV(i).start_blk, FDEV(i).end_blk, FDEV(i).path); return 0; } static int __maybe_unused donation_list_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); struct inode *inode; struct f2fs_inode_info *fi; struct dentry *dentry; char *buf, *path; int i; buf = f2fs_getname(sbi); if (!buf) return 0; seq_printf(seq, "Donation List\n"); seq_printf(seq, " # of files : %u\n", sbi->donate_files); seq_printf(seq, " %-50s %10s %20s %20s %22s\n", "File path", "Status", "Donation offset (kb)", "Donation size (kb)", "File cached size (kb)"); seq_printf(seq, "---\n"); for (i = 0; i < sbi->donate_files; i++) { spin_lock(&sbi->inode_lock[DONATE_INODE]); if (list_empty(&sbi->inode_list[DONATE_INODE])) { spin_unlock(&sbi->inode_lock[DONATE_INODE]); break; } fi = list_first_entry(&sbi->inode_list[DONATE_INODE], struct f2fs_inode_info, gdonate_list); list_move_tail(&fi->gdonate_list, &sbi->inode_list[DONATE_INODE]); inode = igrab(&fi->vfs_inode); spin_unlock(&sbi->inode_lock[DONATE_INODE]); if (!inode) continue; inode_lock_shared(inode); dentry = d_find_alias(inode); if (!dentry) { path = NULL; } else { path = dentry_path_raw(dentry, buf, PATH_MAX); if (IS_ERR(path)) goto next; } seq_printf(seq, " %-50s %10s %20llu %20llu %22llu\n", path ? path : "<unlinked>", is_inode_flag_set(inode, FI_DONATE_FINISHED) ? "Evicted" : "Donated", (loff_t)fi->donate_start << (PAGE_SHIFT - 10), (loff_t)(fi->donate_end + 1) << (PAGE_SHIFT - 10), (loff_t)inode->i_mapping->nrpages << (PAGE_SHIFT - 10)); next: dput(dentry); inode_unlock_shared(inode); iput(inode); } f2fs_putname(buf); return 0; } #ifdef CONFIG_F2FS_FAULT_INJECTION static int __maybe_unused inject_stats_seq_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct f2fs_sb_info *sbi = F2FS_SB(sb); struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; int i; seq_puts(seq, "fault_type injected_count\n"); for (i = 0; i < FAULT_MAX; i++) seq_printf(seq, "%-24s%-10u\n", f2fs_fault_name[i], ffi->inject_count[i]); return 0; } #endif int __init f2fs_init_sysfs(void) { int ret; kobject_set_name(&f2fs_kset.kobj, "f2fs"); f2fs_kset.kobj.parent = fs_kobj; ret = kset_register(&f2fs_kset); if (ret) return ret; ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype, NULL, "features"); if (ret) goto put_kobject; ret = kobject_init_and_add(&f2fs_tune, &f2fs_tune_ktype, NULL, "tuning"); if (ret) goto put_kobject; f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); if (!f2fs_proc_root) { ret = -ENOMEM; goto put_kobject; } return 0; put_kobject: kobject_put(&f2fs_tune); kobject_put(&f2fs_feat); kset_unregister(&f2fs_kset); return ret; } void f2fs_exit_sysfs(void) { kobject_put(&f2fs_tune); kobject_put(&f2fs_feat); kset_unregister(&f2fs_kset); remove_proc_entry("fs/f2fs", NULL); f2fs_proc_root = NULL; } int f2fs_register_sysfs(struct f2fs_sb_info *sbi) { struct super_block *sb = sbi->sb; int err; sbi->s_kobj.kset = &f2fs_kset; init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL, "%s", sb->s_id); if (err) goto put_sb_kobj; sbi->s_stat_kobj.kset = &f2fs_kset; init_completion(&sbi->s_stat_kobj_unregister); err = kobject_init_and_add(&sbi->s_stat_kobj, &f2fs_stat_ktype, &sbi->s_kobj, "stat"); if (err) goto put_stat_kobj; sbi->s_feature_list_kobj.kset = &f2fs_kset; init_completion(&sbi->s_feature_list_kobj_unregister); err = kobject_init_and_add(&sbi->s_feature_list_kobj, &f2fs_feature_list_ktype, &sbi->s_kobj, "feature_list"); if (err) goto put_feature_list_kobj; sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); if (!sbi->s_proc) { err = -ENOMEM; goto put_feature_list_kobj; } proc_create_single_data("segment_info", 0444, sbi->s_proc, segment_info_seq_show, sb); proc_create_single_data("segment_bits", 0444, sbi->s_proc, segment_bits_seq_show, sb); #ifdef CONFIG_F2FS_IOSTAT proc_create_single_data("iostat_info", 0444, sbi->s_proc, iostat_info_seq_show, sb); #endif proc_create_single_data("victim_bits", 0444, sbi->s_proc, victim_bits_seq_show, sb); proc_create_single_data("discard_plist_info", 0444, sbi->s_proc, discard_plist_seq_show, sb); proc_create_single_data("disk_map", 0444, sbi->s_proc, disk_map_seq_show, sb); proc_create_single_data("donation_list", 0444, sbi->s_proc, donation_list_seq_show, sb); #ifdef CONFIG_F2FS_FAULT_INJECTION proc_create_single_data("inject_stats", 0444, sbi->s_proc, inject_stats_seq_show, sb); #endif return 0; put_feature_list_kobj: kobject_put(&sbi->s_feature_list_kobj); wait_for_completion(&sbi->s_feature_list_kobj_unregister); put_stat_kobj: kobject_put(&sbi->s_stat_kobj); wait_for_completion(&sbi->s_stat_kobj_unregister); put_sb_kobj: kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); return err; } void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) { remove_proc_subtree(sbi->sb->s_id, f2fs_proc_root); kobject_put(&sbi->s_stat_kobj); wait_for_completion(&sbi->s_stat_kobj_unregister); kobject_put(&sbi->s_feature_list_kobj); wait_for_completion(&sbi->s_feature_list_kobj_unregister); kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VFIO core * * Copyright (C) 2012 Red Hat, Inc. All rights reserved. * Author: Alex Williamson <alex.williamson@redhat.com> * * Derived from original vfio: * Copyright 2010 Cisco Systems, Inc. All rights reserved. * Author: Tom Lyon, pugs@cisco.com */ #include <linux/cdev.h> #include <linux/compat.h> #include <linux/device.h> #include <linux/fs.h> #include <linux/idr.h> #include <linux/iommu.h> #if IS_ENABLED(CONFIG_KVM) #include <linux/kvm_host.h> #endif #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/mutex.h> #include <linux/pci.h> #include <linux/pseudo_fs.h> #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/vfio.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/pm_runtime.h> #include <linux/interval_tree.h> #include <linux/iova_bitmap.h> #include <linux/iommufd.h> #include "vfio.h" #define DRIVER_VERSION "0.3" #define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>" #define DRIVER_DESC "VFIO - User Level meta-driver" #define VFIO_MAGIC 0x5646494f /* "VFIO" */ static struct vfio { struct class *device_class; struct ida device_ida; struct vfsmount *vfs_mount; int fs_count; } vfio; #ifdef CONFIG_VFIO_NOIOMMU bool vfio_noiommu __read_mostly; module_param_named(enable_unsafe_noiommu_mode, vfio_noiommu, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); #endif static DEFINE_XARRAY(vfio_device_set_xa); int vfio_assign_device_set(struct vfio_device *device, void *set_id) { unsigned long idx = (unsigned long)set_id; struct vfio_device_set *new_dev_set; struct vfio_device_set *dev_set; if (WARN_ON(!set_id)) return -EINVAL; /* * Atomically acquire a singleton object in the xarray for this set_id */ xa_lock(&vfio_device_set_xa); dev_set = xa_load(&vfio_device_set_xa, idx); if (dev_set) goto found_get_ref; xa_unlock(&vfio_device_set_xa); new_dev_set = kzalloc(sizeof(*new_dev_set), GFP_KERNEL); if (!new_dev_set) return -ENOMEM; mutex_init(&new_dev_set->lock); INIT_LIST_HEAD(&new_dev_set->device_list); new_dev_set->set_id = set_id; xa_lock(&vfio_device_set_xa); dev_set = __xa_cmpxchg(&vfio_device_set_xa, idx, NULL, new_dev_set, GFP_KERNEL); if (!dev_set) { dev_set = new_dev_set; goto found_get_ref; } kfree(new_dev_set); if (xa_is_err(dev_set)) { xa_unlock(&vfio_device_set_xa); return xa_err(dev_set); } found_get_ref: dev_set->device_count++; xa_unlock(&vfio_device_set_xa); mutex_lock(&dev_set->lock); device->dev_set = dev_set; list_add_tail(&device->dev_set_list, &dev_set->device_list); mutex_unlock(&dev_set->lock); return 0; } EXPORT_SYMBOL_GPL(vfio_assign_device_set); static void vfio_release_device_set(struct vfio_device *device) { struct vfio_device_set *dev_set = device->dev_set; if (!dev_set) return; mutex_lock(&dev_set->lock); list_del(&device->dev_set_list); mutex_unlock(&dev_set->lock); xa_lock(&vfio_device_set_xa); if (!--dev_set->device_count) { __xa_erase(&vfio_device_set_xa, (unsigned long)dev_set->set_id); mutex_destroy(&dev_set->lock); kfree(dev_set); } xa_unlock(&vfio_device_set_xa); } unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set) { struct vfio_device *cur; unsigned int open_count = 0; lockdep_assert_held(&dev_set->lock); list_for_each_entry(cur, &dev_set->device_list, dev_set_list) open_count += cur->open_count; return open_count; } EXPORT_SYMBOL_GPL(vfio_device_set_open_count); struct vfio_device * vfio_find_device_in_devset(struct vfio_device_set *dev_set, struct device *dev) { struct vfio_device *cur; lockdep_assert_held(&dev_set->lock); list_for_each_entry(cur, &dev_set->device_list, dev_set_list) if (cur->dev == dev) return cur; return NULL; } EXPORT_SYMBOL_GPL(vfio_find_device_in_devset); /* * Device objects - create, release, get, put, search */ /* Device reference always implies a group reference */ void vfio_device_put_registration(struct vfio_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->comp); } EXPORT_SYMBOL_GPL(vfio_device_put_registration); bool vfio_device_try_get_registration(struct vfio_device *device) { return refcount_inc_not_zero(&device->refcount); } EXPORT_SYMBOL_GPL(vfio_device_try_get_registration); /* * VFIO driver API */ /* Release helper called by vfio_put_device() */ static void vfio_device_release(struct device *dev) { struct vfio_device *device = container_of(dev, struct vfio_device, device); vfio_release_device_set(device); ida_free(&vfio.device_ida, device->index); if (device->ops->release) device->ops->release(device); iput(device->inode); simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); kvfree(device); } static int vfio_init_device(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); /* * Allocate and initialize vfio_device so it can be registered to vfio * core. * * Drivers should use the wrapper vfio_alloc_device() for allocation. * @size is the size of the structure to be allocated, including any * private data used by the driver. * * Driver may provide an @init callback to cover device private data. * * Use vfio_put_device() to release the structure after success return. */ struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, const struct vfio_device_ops *ops) { struct vfio_device *device; int ret; if (WARN_ON(size < sizeof(struct vfio_device))) return ERR_PTR(-EINVAL); device = kvzalloc(size, GFP_KERNEL); if (!device) return ERR_PTR(-ENOMEM); ret = vfio_init_device(device, dev, ops); if (ret) goto out_free; return device; out_free: kvfree(device); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(_vfio_alloc_device); static int vfio_fs_init_fs_context(struct fs_context *fc) { return init_pseudo(fc, VFIO_MAGIC) ? 0 : -ENOMEM; } static struct file_system_type vfio_fs_type = { .name = "vfio", .owner = THIS_MODULE, .init_fs_context = vfio_fs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *vfio_fs_inode_new(void) { struct inode *inode; int ret; ret = simple_pin_fs(&vfio_fs_type, &vfio.vfs_mount, &vfio.fs_count); if (ret) return ERR_PTR(ret); inode = alloc_anon_inode(vfio.vfs_mount->mnt_sb); if (IS_ERR(inode)) simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); return inode; } /* * Initialize a vfio_device so it can be registered to vfio core. */ static int vfio_init_device(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops) { int ret; ret = ida_alloc_max(&vfio.device_ida, MINORMASK, GFP_KERNEL); if (ret < 0) { dev_dbg(dev, "Error to alloc index\n"); return ret; } device->index = ret; init_completion(&device->comp); device->dev = dev; device->ops = ops; device->inode = vfio_fs_inode_new(); if (IS_ERR(device->inode)) { ret = PTR_ERR(device->inode); goto out_inode; } if (ops->init) { ret = ops->init(device); if (ret) goto out_uninit; } device_initialize(&device->device); device->device.release = vfio_device_release; device->device.class = vfio.device_class; device->device.parent = device->dev; return 0; out_uninit: iput(device->inode); simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); out_inode: vfio_release_device_set(device); ida_free(&vfio.device_ida, device->index); return ret; } static int __vfio_register_dev(struct vfio_device *device, enum vfio_group_type type) { int ret; if (WARN_ON(IS_ENABLED(CONFIG_IOMMUFD) && (!device->ops->bind_iommufd || !device->ops->unbind_iommufd || !device->ops->attach_ioas || !device->ops->detach_ioas))) return -EINVAL; /* * If the driver doesn't specify a set then the device is added to a * singleton set just for itself. */ if (!device->dev_set) vfio_assign_device_set(device, device); ret = dev_set_name(&device->device, "vfio%d", device->index); if (ret) return ret; ret = vfio_device_set_group(device, type); if (ret) return ret; /* * VFIO always sets IOMMU_CACHE because we offer no way for userspace to * restore cache coherency. It has to be checked here because it is only * valid for cases where we are using iommu groups. */ if (type == VFIO_IOMMU && !vfio_device_is_noiommu(device) && !device_iommu_capable(device->dev, IOMMU_CAP_CACHE_COHERENCY)) { ret = -EINVAL; goto err_out; } ret = vfio_device_add(device); if (ret) goto err_out; /* Refcounting can't start until the driver calls register */ refcount_set(&device->refcount, 1); vfio_device_group_register(device); vfio_device_debugfs_init(device); return 0; err_out: vfio_device_remove_group(device); return ret; } int vfio_register_group_dev(struct vfio_device *device) { return __vfio_register_dev(device, VFIO_IOMMU); } EXPORT_SYMBOL_GPL(vfio_register_group_dev); /* * Register a virtual device without IOMMU backing. The user of this * device must not be able to directly trigger unmediated DMA. */ int vfio_register_emulated_iommu_dev(struct vfio_device *device) { return __vfio_register_dev(device, VFIO_EMULATED_IOMMU); } EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev); /* * Decrement the device reference count and wait for the device to be * removed. Open file descriptors for the device... */ void vfio_unregister_group_dev(struct vfio_device *device) { unsigned int i = 0; bool interrupted = false; long rc; /* * Prevent new device opened by userspace via the * VFIO_GROUP_GET_DEVICE_FD in the group path. */ vfio_device_group_unregister(device); /* * Balances vfio_device_add() in register path, also prevents * new device opened by userspace in the cdev path. */ vfio_device_del(device); vfio_device_put_registration(device); rc = try_wait_for_completion(&device->comp); while (rc <= 0) { if (device->ops->request) device->ops->request(device, i++); if (interrupted) { rc = wait_for_completion_timeout(&device->comp, HZ * 10); } else { rc = wait_for_completion_interruptible_timeout( &device->comp, HZ * 10); if (rc < 0) { interrupted = true; dev_warn(device->dev, "Device is currently in use, task" " \"%s\" (%d) " "blocked until device is released", current->comm, task_pid_nr(current)); } } } vfio_device_debugfs_exit(device); /* Balances vfio_device_set_group in register path */ vfio_device_remove_group(device); } EXPORT_SYMBOL_GPL(vfio_unregister_group_dev); #if IS_ENABLED(CONFIG_KVM) void vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm) { void (*pfn)(struct kvm *kvm); bool (*fn)(struct kvm *kvm); bool ret; lockdep_assert_held(&device->dev_set->lock); if (!kvm) return; pfn = symbol_get(kvm_put_kvm); if (WARN_ON(!pfn)) return; fn = symbol_get(kvm_get_kvm_safe); if (WARN_ON(!fn)) { symbol_put(kvm_put_kvm); return; } ret = fn(kvm); symbol_put(kvm_get_kvm_safe); if (!ret) { symbol_put(kvm_put_kvm); return; } device->put_kvm = pfn; device->kvm = kvm; } void vfio_device_put_kvm(struct vfio_device *device) { lockdep_assert_held(&device->dev_set->lock); if (!device->kvm) return; if (WARN_ON(!device->put_kvm)) goto clear; device->put_kvm(device->kvm); device->put_kvm = NULL; symbol_put(kvm_put_kvm); clear: device->kvm = NULL; } #endif /* true if the vfio_device has open_device() called but not close_device() */ static bool vfio_assert_device_open(struct vfio_device *device) { return !WARN_ON_ONCE(!READ_ONCE(device->open_count)); } struct vfio_device_file * vfio_allocate_device_file(struct vfio_device *device) { struct vfio_device_file *df; df = kzalloc(sizeof(*df), GFP_KERNEL_ACCOUNT); if (!df) return ERR_PTR(-ENOMEM); df->device = device; spin_lock_init(&df->kvm_ref_lock); return df; } static int vfio_df_device_first_open(struct vfio_device_file *df) { struct vfio_device *device = df->device; struct iommufd_ctx *iommufd = df->iommufd; int ret; lockdep_assert_held(&device->dev_set->lock); if (!try_module_get(device->dev->driver->owner)) return -ENODEV; if (iommufd) ret = vfio_df_iommufd_bind(df); else ret = vfio_device_group_use_iommu(device); if (ret) goto err_module_put; if (device->ops->open_device) { ret = device->ops->open_device(device); if (ret) goto err_unuse_iommu; } return 0; err_unuse_iommu: if (iommufd) vfio_df_iommufd_unbind(df); else vfio_device_group_unuse_iommu(device); err_module_put: module_put(device->dev->driver->owner); return ret; } static void vfio_df_device_last_close(struct vfio_device_file *df) { struct vfio_device *device = df->device; struct iommufd_ctx *iommufd = df->iommufd; lockdep_assert_held(&device->dev_set->lock); if (device->ops->close_device) device->ops->close_device(device); if (iommufd) vfio_df_iommufd_unbind(df); else vfio_device_group_unuse_iommu(device); module_put(device->dev->driver->owner); } int vfio_df_open(struct vfio_device_file *df) { struct vfio_device *device = df->device; int ret = 0; lockdep_assert_held(&device->dev_set->lock); /* * Only the group path allows the device to be opened multiple * times. The device cdev path doesn't have a secure way for it. */ if (device->open_count != 0 && !df->group) return -EINVAL; device->open_count++; if (device->open_count == 1) { ret = vfio_df_device_first_open(df); if (ret) device->open_count--; } return ret; } void vfio_df_close(struct vfio_device_file *df) { struct vfio_device *device = df->device; lockdep_assert_held(&device->dev_set->lock); if (!vfio_assert_device_open(device)) return; if (device->open_count == 1) vfio_df_device_last_close(df); device->open_count--; } /* * Wrapper around pm_runtime_resume_and_get(). * Return error code on failure or 0 on success. */ static inline int vfio_device_pm_runtime_get(struct vfio_device *device) { struct device *dev = device->dev; if (dev->driver && dev->driver->pm) { int ret; ret = pm_runtime_resume_and_get(dev); if (ret) { dev_info_ratelimited(dev, "vfio: runtime resume failed %d\n", ret); return -EIO; } } return 0; } /* * Wrapper around pm_runtime_put(). */ static inline void vfio_device_pm_runtime_put(struct vfio_device *device) { struct device *dev = device->dev; if (dev->driver && dev->driver->pm) pm_runtime_put(dev); } /* * VFIO Device fd */ static int vfio_device_fops_release(struct inode *inode, struct file *filep) { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; if (df->group) vfio_df_group_close(df); else vfio_df_unbind_iommufd(df); vfio_device_put_registration(device); kfree(df); return 0; } /* * vfio_mig_get_next_state - Compute the next step in the FSM * @cur_fsm - The current state the device is in * @new_fsm - The target state to reach * @next_fsm - Pointer to the next step to get to new_fsm * * Return 0 upon success, otherwise -errno * Upon success the next step in the state progression between cur_fsm and * new_fsm will be set in next_fsm. * * This breaks down requests for combination transitions into smaller steps and * returns the next step to get to new_fsm. The function may need to be called * multiple times before reaching new_fsm. * */ int vfio_mig_get_next_state(struct vfio_device *device, enum vfio_device_mig_state cur_fsm, enum vfio_device_mig_state new_fsm, enum vfio_device_mig_state *next_fsm) { enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_PRE_COPY_P2P + 1 }; /* * The coding in this table requires the driver to implement the * following FSM arcs: * RESUMING -> STOP * STOP -> RESUMING * STOP -> STOP_COPY * STOP_COPY -> STOP * * If P2P is supported then the driver must also implement these FSM * arcs: * RUNNING -> RUNNING_P2P * RUNNING_P2P -> RUNNING * RUNNING_P2P -> STOP * STOP -> RUNNING_P2P * * If precopy is supported then the driver must support these additional * FSM arcs: * RUNNING -> PRE_COPY * PRE_COPY -> RUNNING * PRE_COPY -> STOP_COPY * However, if precopy and P2P are supported together then the driver * must support these additional arcs beyond the P2P arcs above: * PRE_COPY -> RUNNING * PRE_COPY -> PRE_COPY_P2P * PRE_COPY_P2P -> PRE_COPY * PRE_COPY_P2P -> RUNNING_P2P * PRE_COPY_P2P -> STOP_COPY * RUNNING -> PRE_COPY * RUNNING_P2P -> PRE_COPY_P2P * * Without P2P and precopy the driver must implement: * RUNNING -> STOP * STOP -> RUNNING * * The coding will step through multiple states for some combination * transitions; if all optional features are supported, this means the * following ones: * PRE_COPY -> PRE_COPY_P2P -> STOP_COPY * PRE_COPY -> RUNNING -> RUNNING_P2P * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP -> RESUMING * PRE_COPY_P2P -> RUNNING_P2P -> RUNNING * PRE_COPY_P2P -> RUNNING_P2P -> STOP * PRE_COPY_P2P -> RUNNING_P2P -> STOP -> RESUMING * RESUMING -> STOP -> RUNNING_P2P * RESUMING -> STOP -> RUNNING_P2P -> PRE_COPY_P2P * RESUMING -> STOP -> RUNNING_P2P -> RUNNING * RESUMING -> STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY * RESUMING -> STOP -> STOP_COPY * RUNNING -> RUNNING_P2P -> PRE_COPY_P2P * RUNNING -> RUNNING_P2P -> STOP * RUNNING -> RUNNING_P2P -> STOP -> RESUMING * RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY * RUNNING_P2P -> RUNNING -> PRE_COPY * RUNNING_P2P -> STOP -> RESUMING * RUNNING_P2P -> STOP -> STOP_COPY * STOP -> RUNNING_P2P -> PRE_COPY_P2P * STOP -> RUNNING_P2P -> RUNNING * STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY * STOP_COPY -> STOP -> RESUMING * STOP_COPY -> STOP -> RUNNING_P2P * STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING * * The following transitions are blocked: * STOP_COPY -> PRE_COPY * STOP_COPY -> PRE_COPY_P2P */ static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = { [VFIO_DEVICE_STATE_STOP] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_RUNNING] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_PRE_COPY] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_PRE_COPY_P2P, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_STOP_COPY] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_RESUMING] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_RUNNING_P2P] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_ERROR] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, }; static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = { [VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY, [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P, [VFIO_DEVICE_STATE_ERROR] = ~0U, }; if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table) || (state_flags_table[cur_fsm] & device->migration_flags) != state_flags_table[cur_fsm])) return -EINVAL; if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table) || (state_flags_table[new_fsm] & device->migration_flags) != state_flags_table[new_fsm]) return -EINVAL; /* * Arcs touching optional and unsupported states are skipped over. The * driver will instead see an arc from the original state to the next * logical state, as per the above comment. */ *next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm]; while ((state_flags_table[*next_fsm] & device->migration_flags) != state_flags_table[*next_fsm]) *next_fsm = vfio_from_fsm_table[*next_fsm][new_fsm]; return (*next_fsm != VFIO_DEVICE_STATE_ERROR) ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(vfio_mig_get_next_state); /* * Convert the drivers's struct file into a FD number and return it to userspace */ static int vfio_ioct_mig_return_fd(struct file *filp, void __user *arg, struct vfio_device_feature_mig_state *mig) { int ret; int fd; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { ret = fd; goto out_fput; } mig->data_fd = fd; if (copy_to_user(arg, mig, sizeof(*mig))) { ret = -EFAULT; goto out_put_unused; } fd_install(fd, filp); return 0; out_put_unused: put_unused_fd(fd); out_fput: fput(filp); return ret; } static int vfio_ioctl_device_feature_mig_device_state(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { size_t minsz = offsetofend(struct vfio_device_feature_mig_state, data_fd); struct vfio_device_feature_mig_state mig; struct file *filp = NULL; int ret; if (!device->mig_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_GET, sizeof(mig)); if (ret != 1) return ret; if (copy_from_user(&mig, arg, minsz)) return -EFAULT; if (flags & VFIO_DEVICE_FEATURE_GET) { enum vfio_device_mig_state curr_state; ret = device->mig_ops->migration_get_state(device, &curr_state); if (ret) return ret; mig.device_state = curr_state; goto out_copy; } /* Handle the VFIO_DEVICE_FEATURE_SET */ filp = device->mig_ops->migration_set_state(device, mig.device_state); if (IS_ERR(filp) || !filp) goto out_copy; return vfio_ioct_mig_return_fd(filp, arg, &mig); out_copy: mig.data_fd = -1; if (copy_to_user(arg, &mig, sizeof(mig))) return -EFAULT; if (IS_ERR(filp)) return PTR_ERR(filp); return 0; } static int vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { struct vfio_device_feature_mig_data_size data_size = {}; unsigned long stop_copy_length; int ret; if (!device->mig_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, sizeof(data_size)); if (ret != 1) return ret; ret = device->mig_ops->migration_get_data_size(device, &stop_copy_length); if (ret) return ret; data_size.stop_copy_length = stop_copy_length; if (copy_to_user(arg, &data_size, sizeof(data_size))) return -EFAULT; return 0; } static int vfio_ioctl_device_feature_migration(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { struct vfio_device_feature_migration mig = { .flags = device->migration_flags, }; int ret; if (!device->mig_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, sizeof(mig)); if (ret != 1) return ret; if (copy_to_user(arg, &mig, sizeof(mig))) return -EFAULT; return 0; } void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes, u32 req_nodes) { struct interval_tree_node *prev, *curr, *comb_start, *comb_end; unsigned long min_gap, curr_gap; /* Special shortcut when a single range is required */ if (req_nodes == 1) { unsigned long last; comb_start = interval_tree_iter_first(root, 0, ULONG_MAX); /* Empty list */ if (WARN_ON_ONCE(!comb_start)) return; curr = comb_start; while (curr) { last = curr->last; prev = curr; curr = interval_tree_iter_next(curr, 0, ULONG_MAX); if (prev != comb_start) interval_tree_remove(prev, root); } comb_start->last = last; return; } /* Combine ranges which have the smallest gap */ while (cur_nodes > req_nodes) { prev = NULL; min_gap = ULONG_MAX; curr = interval_tree_iter_first(root, 0, ULONG_MAX); while (curr) { if (prev) { curr_gap = curr->start - prev->last; if (curr_gap < min_gap) { min_gap = curr_gap; comb_start = prev; comb_end = curr; } } prev = curr; curr = interval_tree_iter_next(curr, 0, ULONG_MAX); } /* Empty list or no nodes to combine */ if (WARN_ON_ONCE(min_gap == ULONG_MAX)) break; comb_start->last = comb_end->last; interval_tree_remove(comb_end, root); cur_nodes--; } } EXPORT_SYMBOL_GPL(vfio_combine_iova_ranges); /* Ranges should fit into a single kernel page */ #define LOG_MAX_RANGES \ (PAGE_SIZE / sizeof(struct vfio_device_feature_dma_logging_range)) static int vfio_ioctl_device_feature_logging_start(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { size_t minsz = offsetofend(struct vfio_device_feature_dma_logging_control, ranges); struct vfio_device_feature_dma_logging_range __user *ranges; struct vfio_device_feature_dma_logging_control control; struct vfio_device_feature_dma_logging_range range; struct rb_root_cached root = RB_ROOT_CACHED; struct interval_tree_node *nodes; u64 iova_end; u32 nnodes; int i, ret; if (!device->log_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, sizeof(control)); if (ret != 1) return ret; if (copy_from_user(&control, arg, minsz)) return -EFAULT; nnodes = control.num_ranges; if (!nnodes) return -EINVAL; if (nnodes > LOG_MAX_RANGES) return -E2BIG; ranges = u64_to_user_ptr(control.ranges); nodes = kmalloc_array(nnodes, sizeof(struct interval_tree_node), GFP_KERNEL); if (!nodes) return -ENOMEM; for (i = 0; i < nnodes; i++) { if (copy_from_user(&range, &ranges[i], sizeof(range))) { ret = -EFAULT; goto end; } if (!IS_ALIGNED(range.iova, control.page_size) || !IS_ALIGNED(range.length, control.page_size)) { ret = -EINVAL; goto end; } if (check_add_overflow(range.iova, range.length, &iova_end) || iova_end > ULONG_MAX) { ret = -EOVERFLOW; goto end; } nodes[i].start = range.iova; nodes[i].last = range.iova + range.length - 1; if (interval_tree_iter_first(&root, nodes[i].start, nodes[i].last)) { /* Range overlapping */ ret = -EINVAL; goto end; } interval_tree_insert(nodes + i, &root); } ret = device->log_ops->log_start(device, &root, nnodes, &control.page_size); if (ret) goto end; if (copy_to_user(arg, &control, sizeof(control))) { ret = -EFAULT; device->log_ops->log_stop(device); } end: kfree(nodes); return ret; } static int vfio_ioctl_device_feature_logging_stop(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { int ret; if (!device->log_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); if (ret != 1) return ret; return device->log_ops->log_stop(device); } static int vfio_device_log_read_and_clear(struct iova_bitmap *iter, unsigned long iova, size_t length, void *opaque) { struct vfio_device *device = opaque; return device->log_ops->log_read_and_clear(device, iova, length, iter); } static int vfio_ioctl_device_feature_logging_report(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { size_t minsz = offsetofend(struct vfio_device_feature_dma_logging_report, bitmap); struct vfio_device_feature_dma_logging_report report; struct iova_bitmap *iter; u64 iova_end; int ret; if (!device->log_ops) return -ENOTTY; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, sizeof(report)); if (ret != 1) return ret; if (copy_from_user(&report, arg, minsz)) return -EFAULT; if (report.page_size < SZ_4K || !is_power_of_2(report.page_size)) return -EINVAL; if (check_add_overflow(report.iova, report.length, &iova_end) || iova_end > ULONG_MAX) return -EOVERFLOW; iter = iova_bitmap_alloc(report.iova, report.length, report.page_size, u64_to_user_ptr(report.bitmap)); if (IS_ERR(iter)) return PTR_ERR(iter); ret = iova_bitmap_for_each(iter, device, vfio_device_log_read_and_clear); iova_bitmap_free(iter); return ret; } static int vfio_ioctl_device_feature(struct vfio_device *device, struct vfio_device_feature __user *arg) { size_t minsz = offsetofend(struct vfio_device_feature, flags); struct vfio_device_feature feature; if (copy_from_user(&feature, arg, minsz)) return -EFAULT; if (feature.argsz < minsz) return -EINVAL; /* Check unknown flags */ if (feature.flags & ~(VFIO_DEVICE_FEATURE_MASK | VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_PROBE)) return -EINVAL; /* GET & SET are mutually exclusive except with PROBE */ if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) && (feature.flags & VFIO_DEVICE_FEATURE_SET) && (feature.flags & VFIO_DEVICE_FEATURE_GET)) return -EINVAL; switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) { case VFIO_DEVICE_FEATURE_MIGRATION: return vfio_ioctl_device_feature_migration( device, feature.flags, arg->data, feature.argsz - minsz); case VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE: return vfio_ioctl_device_feature_mig_device_state( device, feature.flags, arg->data, feature.argsz - minsz); case VFIO_DEVICE_FEATURE_DMA_LOGGING_START: return vfio_ioctl_device_feature_logging_start( device, feature.flags, arg->data, feature.argsz - minsz); case VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP: return vfio_ioctl_device_feature_logging_stop( device, feature.flags, arg->data, feature.argsz - minsz); case VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT: return vfio_ioctl_device_feature_logging_report( device, feature.flags, arg->data, feature.argsz - minsz); case VFIO_DEVICE_FEATURE_MIG_DATA_SIZE: return vfio_ioctl_device_feature_migration_data_size( device, feature.flags, arg->data, feature.argsz - minsz); default: if (unlikely(!device->ops->device_feature)) return -ENOTTY; return device->ops->device_feature(device, feature.flags, arg->data, feature.argsz - minsz); } } static long vfio_get_region_info(struct vfio_device *device, struct vfio_region_info __user *arg) { unsigned long minsz = offsetofend(struct vfio_region_info, offset); struct vfio_region_info info = {}; struct vfio_info_cap caps = {}; int ret; if (unlikely(!device->ops->get_region_info_caps)) return -EINVAL; if (copy_from_user(&info, arg, minsz)) return -EFAULT; if (info.argsz < minsz) return -EINVAL; ret = device->ops->get_region_info_caps(device, &info, &caps); if (ret) goto out_free; if (caps.size) { info.flags |= VFIO_REGION_INFO_FLAG_CAPS; if (info.argsz < sizeof(info) + caps.size) { info.argsz = sizeof(info) + caps.size; info.cap_offset = 0; } else { vfio_info_cap_shift(&caps, sizeof(info)); if (copy_to_user(arg + 1, caps.buf, caps.size)) { ret = -EFAULT; goto out_free; } info.cap_offset = sizeof(info); } } if (copy_to_user(arg, &info, minsz)){ ret = -EFAULT; goto out_free; } out_free: kfree(caps.buf); return ret; } static long vfio_device_fops_unl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; void __user *uptr = (void __user *)arg; int ret; if (cmd == VFIO_DEVICE_BIND_IOMMUFD) return vfio_df_ioctl_bind_iommufd(df, uptr); /* Paired with smp_store_release() following vfio_df_open() */ if (!smp_load_acquire(&df->access_granted)) return -EINVAL; ret = vfio_device_pm_runtime_get(device); if (ret) return ret; /* cdev only ioctls */ if (IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) && !df->group) { switch (cmd) { case VFIO_DEVICE_ATTACH_IOMMUFD_PT: ret = vfio_df_ioctl_attach_pt(df, uptr); goto out; case VFIO_DEVICE_DETACH_IOMMUFD_PT: ret = vfio_df_ioctl_detach_pt(df, uptr); goto out; } } switch (cmd) { case VFIO_DEVICE_FEATURE: ret = vfio_ioctl_device_feature(device, uptr); break; case VFIO_DEVICE_GET_REGION_INFO: ret = vfio_get_region_info(device, uptr); break; default: if (unlikely(!device->ops->ioctl)) ret = -EINVAL; else ret = device->ops->ioctl(device, cmd, arg); break; } out: vfio_device_pm_runtime_put(device); return ret; } static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf, size_t count, loff_t *ppos) { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; /* Paired with smp_store_release() following vfio_df_open() */ if (!smp_load_acquire(&df->access_granted)) return -EINVAL; if (unlikely(!device->ops->read)) return -EINVAL; return device->ops->read(device, buf, count, ppos); } static ssize_t vfio_device_fops_write(struct file *filep, const char __user *buf, size_t count, loff_t *ppos) { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; /* Paired with smp_store_release() following vfio_df_open() */ if (!smp_load_acquire(&df->access_granted)) return -EINVAL; if (unlikely(!device->ops->write)) return -EINVAL; return device->ops->write(device, buf, count, ppos); } static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma) { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; /* Paired with smp_store_release() following vfio_df_open() */ if (!smp_load_acquire(&df->access_granted)) return -EINVAL; if (unlikely(!device->ops->mmap)) return -EINVAL; return device->ops->mmap(device, vma); } #ifdef CONFIG_PROC_FS static void vfio_device_show_fdinfo(struct seq_file *m, struct file *filep) { char *path; struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; path = kobject_get_path(&device->dev->kobj, GFP_KERNEL); if (!path) return; seq_printf(m, "vfio-device-syspath: /sys%s\n", path); kfree(path); } #endif const struct file_operations vfio_device_fops = { .owner = THIS_MODULE, .open = vfio_device_fops_cdev_open, .release = vfio_device_fops_release, .read = vfio_device_fops_read, .write = vfio_device_fops_write, .unlocked_ioctl = vfio_device_fops_unl_ioctl, .compat_ioctl = compat_ptr_ioctl, .mmap = vfio_device_fops_mmap, #ifdef CONFIG_PROC_FS .show_fdinfo = vfio_device_show_fdinfo, #endif }; static struct vfio_device *vfio_device_from_file(struct file *file) { struct vfio_device_file *df = file->private_data; if (file->f_op != &vfio_device_fops) return NULL; return df->device; } /** * vfio_file_is_valid - True if the file is valid vfio file * @file: VFIO group file or VFIO device file */ bool vfio_file_is_valid(struct file *file) { return vfio_group_from_file(file) || vfio_device_from_file(file); } EXPORT_SYMBOL_GPL(vfio_file_is_valid); /** * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file * is always CPU cache coherent * @file: VFIO group file or VFIO device file * * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop * bit in DMA transactions. A return of false indicates that the user has * rights to access additional instructions such as wbinvd on x86. */ bool vfio_file_enforced_coherent(struct file *file) { struct vfio_device *device; struct vfio_group *group; group = vfio_group_from_file(file); if (group) return vfio_group_enforced_coherent(group); device = vfio_device_from_file(file); if (device) return device_iommu_capable(device->dev, IOMMU_CAP_ENFORCE_CACHE_COHERENCY); return true; } EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent); static void vfio_device_file_set_kvm(struct file *file, struct kvm *kvm) { struct vfio_device_file *df = file->private_data; /* * The kvm is first recorded in the vfio_device_file, and will * be propagated to vfio_device::kvm when the file is bound to * iommufd successfully in the vfio device cdev path. */ spin_lock(&df->kvm_ref_lock); df->kvm = kvm; spin_unlock(&df->kvm_ref_lock); } /** * vfio_file_set_kvm - Link a kvm with VFIO drivers * @file: VFIO group file or VFIO device file * @kvm: KVM to link * * When a VFIO device is first opened the KVM will be available in * device->kvm if one was associated with the file. */ void vfio_file_set_kvm(struct file *file, struct kvm *kvm) { struct vfio_group *group; group = vfio_group_from_file(file); if (group) vfio_group_set_kvm(group, kvm); if (vfio_device_from_file(file)) vfio_device_file_set_kvm(file, kvm); } EXPORT_SYMBOL_GPL(vfio_file_set_kvm); /* * Sub-module support */ /* * Helper for managing a buffer of info chain capabilities, allocate or * reallocate a buffer with additional @size, filling in @id and @version * of the capability. A pointer to the new capability is returned. * * NB. The chain is based at the head of the buffer, so new entries are * added to the tail, vfio_info_cap_shift() should be called to fixup the * next offsets prior to copying to the user buffer. */ struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps, size_t size, u16 id, u16 version) { void *buf; struct vfio_info_cap_header *header, *tmp; /* Ensure that the next capability struct will be aligned */ size = ALIGN(size, sizeof(u64)); buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL); if (!buf) { kfree(caps->buf); caps->buf = NULL; caps->size = 0; return ERR_PTR(-ENOMEM); } caps->buf = buf; header = buf + caps->size; /* Eventually copied to user buffer, zero */ memset(header, 0, size); header->id = id; header->version = version; /* Add to the end of the capability chain */ for (tmp = buf; tmp->next; tmp = buf + tmp->next) ; /* nothing */ tmp->next = caps->size; caps->size += size; return header; } EXPORT_SYMBOL_GPL(vfio_info_cap_add); void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset) { struct vfio_info_cap_header *tmp; void *buf = (void *)caps->buf; /* Capability structs should start with proper alignment */ WARN_ON(!IS_ALIGNED(offset, sizeof(u64))); for (tmp = buf; tmp->next; tmp = buf + tmp->next - offset) tmp->next += offset; } EXPORT_SYMBOL(vfio_info_cap_shift); int vfio_info_add_capability(struct vfio_info_cap *caps, struct vfio_info_cap_header *cap, size_t size) { struct vfio_info_cap_header *header; header = vfio_info_cap_add(caps, size, cap->id, cap->version); if (IS_ERR(header)) return PTR_ERR(header); memcpy(header + 1, cap + 1, size - sizeof(*header)); return 0; } EXPORT_SYMBOL(vfio_info_add_capability); int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs, int max_irq_type, size_t *data_size) { unsigned long minsz; size_t size; minsz = offsetofend(struct vfio_irq_set, count); if ((hdr->argsz < minsz) || (hdr->index >= max_irq_type) || (hdr->count >= (U32_MAX - hdr->start)) || (hdr->flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK | VFIO_IRQ_SET_ACTION_TYPE_MASK))) return -EINVAL; if (data_size) *data_size = 0; if (hdr->start >= num_irqs || hdr->start + hdr->count > num_irqs) return -EINVAL; switch (hdr->flags & VFIO_IRQ_SET_DATA_TYPE_MASK) { case VFIO_IRQ_SET_DATA_NONE: size = 0; break; case VFIO_IRQ_SET_DATA_BOOL: size = sizeof(uint8_t); break; case VFIO_IRQ_SET_DATA_EVENTFD: size = sizeof(int32_t); break; default: return -EINVAL; } if (size) { if (hdr->argsz - minsz < hdr->count * size) return -EINVAL; if (!data_size) return -EINVAL; *data_size = hdr->count * size; } return 0; } EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare); /* * Pin contiguous user pages and return their associated host pages for local * domain only. * @device [in] : device * @iova [in] : starting IOVA of user pages to be pinned. * @npage [in] : count of pages to be pinned. This count should not * be greater than VFIO_PIN_PAGES_MAX_ENTRIES. * @prot [in] : protection flags * @pages[out] : array of host pages * Return error or number of pages pinned. * * A driver may only call this function if the vfio_device was created * by vfio_register_emulated_iommu_dev() due to vfio_device_container_pin_pages(). */ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, int npage, int prot, struct page **pages) { /* group->container cannot change while a vfio device is open */ if (!pages || !npage || WARN_ON(!vfio_assert_device_open(device))) return -EINVAL; if (!device->ops->dma_unmap) return -EINVAL; if (vfio_device_has_container(device)) return vfio_device_container_pin_pages(device, iova, npage, prot, pages); if (device->iommufd_access) { int ret; if (iova > ULONG_MAX) return -EINVAL; /* * VFIO ignores the sub page offset, npages is from the start of * a PAGE_SIZE chunk of IOVA. The caller is expected to recover * the sub page offset by doing: * pages[0] + (iova % PAGE_SIZE) */ ret = iommufd_access_pin_pages( device->iommufd_access, ALIGN_DOWN(iova, PAGE_SIZE), npage * PAGE_SIZE, pages, (prot & IOMMU_WRITE) ? IOMMUFD_ACCESS_RW_WRITE : 0); if (ret) return ret; return npage; } return -EINVAL; } EXPORT_SYMBOL(vfio_pin_pages); /* * Unpin contiguous host pages for local domain only. * @device [in] : device * @iova [in] : starting address of user pages to be unpinned. * @npage [in] : count of pages to be unpinned. This count should not * be greater than VFIO_PIN_PAGES_MAX_ENTRIES. */ void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage) { if (WARN_ON(!vfio_assert_device_open(device))) return; if (WARN_ON(!device->ops->dma_unmap)) return; if (vfio_device_has_container(device)) { vfio_device_container_unpin_pages(device, iova, npage); return; } if (device->iommufd_access) { if (WARN_ON(iova > ULONG_MAX)) return; iommufd_access_unpin_pages(device->iommufd_access, ALIGN_DOWN(iova, PAGE_SIZE), npage * PAGE_SIZE); return; } } EXPORT_SYMBOL(vfio_unpin_pages); /* * This interface allows the CPUs to perform some sort of virtual DMA on * behalf of the device. * * CPUs read/write from/into a range of IOVAs pointing to user space memory * into/from a kernel buffer. * * As the read/write of user space memory is conducted via the CPUs and is * not a real device DMA, it is not necessary to pin the user space memory. * * @device [in] : VFIO device * @iova [in] : base IOVA of a user space buffer * @data [in] : pointer to kernel buffer * @len [in] : kernel buffer length * @write : indicate read or write * Return error code on failure or 0 on success. */ int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data, size_t len, bool write) { if (!data || len <= 0 || !vfio_assert_device_open(device)) return -EINVAL; if (vfio_device_has_container(device)) return vfio_device_container_dma_rw(device, iova, data, len, write); if (device->iommufd_access) { unsigned int flags = 0; if (iova > ULONG_MAX) return -EINVAL; /* VFIO historically tries to auto-detect a kthread */ if (!current->mm) flags |= IOMMUFD_ACCESS_RW_KTHREAD; if (write) flags |= IOMMUFD_ACCESS_RW_WRITE; return iommufd_access_rw(device->iommufd_access, iova, data, len, flags); } return -EINVAL; } EXPORT_SYMBOL(vfio_dma_rw); /* * Module/class support */ static int __init vfio_init(void) { int ret; ida_init(&vfio.device_ida); ret = vfio_group_init(); if (ret) return ret; ret = vfio_virqfd_init(); if (ret) goto err_virqfd; /* /sys/class/vfio-dev/vfioX */ vfio.device_class = class_create("vfio-dev"); if (IS_ERR(vfio.device_class)) { ret = PTR_ERR(vfio.device_class); goto err_dev_class; } ret = vfio_cdev_init(vfio.device_class); if (ret) goto err_alloc_dev_chrdev; vfio_debugfs_create_root(); pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); return 0; err_alloc_dev_chrdev: class_destroy(vfio.device_class); vfio.device_class = NULL; err_dev_class: vfio_virqfd_exit(); err_virqfd: vfio_group_cleanup(); return ret; } static void __exit vfio_cleanup(void) { vfio_debugfs_remove_root(); ida_destroy(&vfio.device_ida); vfio_cdev_cleanup(); class_destroy(vfio.device_class); vfio.device_class = NULL; vfio_virqfd_exit(); vfio_group_cleanup(); xa_destroy(&vfio_device_set_xa); } module_init(vfio_init); module_exit(vfio_cleanup); MODULE_IMPORT_NS("IOMMUFD"); MODULE_VERSION(DRIVER_VERSION); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_SOFTDEP("post: vfio_iommu_type1 vfio_iommu_spapr_tce"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> * * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT * funded by Astaro. */ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/netfilter/nf_nat.h> struct ip6table_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; static unsigned int ip6table_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv6_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, }; static const struct nf_hook_ops nf_nat_ipv6_ops[] = { { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; static int ip6t_nat_register_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net; struct nf_hook_ops *ops; struct xt_table *table; int i, ret; table = xt_find_table(net, NFPROTO_IPV6, "nat"); if (WARN_ON_ONCE(!table)) return -ENOENT; xt_nat_net = net_generic(net, ip6table_nat_net_id); ops = kmemdup(nf_nat_ipv6_ops, sizeof(nf_nat_ipv6_ops), GFP_KERNEL); if (!ops) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { ops[i].priv = table; ret = nf_nat_ipv6_register_fn(net, &ops[i]); if (ret) { while (i) nf_nat_ipv6_unregister_fn(net, &ops[--i]); kfree(ops); return ret; } } xt_nat_net->nf_nat_ops = ops; return 0; } static void ip6t_nat_unregister_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net = net_generic(net, ip6table_nat_net_id); struct nf_hook_ops *ops = xt_nat_net->nf_nat_ops; int i; if (!ops) return; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) nf_nat_ipv6_unregister_fn(net, &ops[i]); kfree(ops); } static int ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, NULL); if (ret < 0) { kfree(repl); return ret; } ret = ip6t_nat_register_lookups(net); if (ret < 0) ip6t_unregister_table_exit(net, "nat"); kfree(repl); return ret; } static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); } static void __net_exit ip6table_nat_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "nat"); } static struct pernet_operations ip6table_nat_net_ops = { .pre_exit = ip6table_nat_net_pre_exit, .exit = ip6table_nat_net_exit, .id = &ip6table_nat_net_id, .size = sizeof(struct ip6table_nat_pernet), }; static int __init ip6table_nat_init(void) { int ret; /* net->gen->ptr[ip6table_nat_net_id] must be allocated * before calling ip6t_nat_register_lookups(). */ ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; ret = xt_register_template(&nf_nat_ipv6_table, ip6table_nat_table_init); if (ret) unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { xt_unregister_template(&nf_nat_ipv6_table); unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); module_exit(ip6table_nat_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Ip6tables legacy nat table"); |
| 1 38 39 39 55 189 45 4 189 184 183 4 181 97 188 4 188 43 155 128 55 154 156 129 45 4 162 127 189 189 151 92 155 90 188 189 190 21 189 45 133 160 188 188 9 9 188 102 86 9 38 38 1 37 188 190 190 38 190 47 186 188 188 43 188 189 188 102 102 102 102 102 2 85 102 85 58 58 11 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2010 Red Hat, Inc. All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_extent_busy.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_discard.h" /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to * recover, so we don't allow failure here. Also, we allocate in a context that * we don't want to be issuing transactions from, so we need to tell the * allocation code this as well. * * We don't reserve any space for the ticket - we are going to steal whatever * space we require from transactions as they commit. To ensure we reserve all * the space required, we need to set the current reservation of the ticket to * zero so that we know to steal the initial transaction overhead from the * first transaction commit. */ static struct xlog_ticket * xlog_cil_ticket_alloc( struct xlog *log) { struct xlog_ticket *tic; tic = xlog_ticket_alloc(log, 0, 1, 0); /* * set the current reservation to zero so we know to steal the basic * transaction overhead reservation from the first transaction commit. */ tic->t_curr_res = 0; tic->t_iclog_hdrs = 0; return tic; } static inline void xlog_cil_set_iclog_hdr_count(struct xfs_cil *cil) { struct xlog *log = cil->xc_log; atomic_set(&cil->xc_iclog_hdrs, (XLOG_CIL_BLOCKING_SPACE_LIMIT(log) / (log->l_iclog_size - log->l_iclog_hsize))); } /* * Check if the current log item was first committed in this sequence. * We can't rely on just the log item being in the CIL, we have to check * the recorded commit sequence number. * * Note: for this to be used in a non-racy manner, it has to be called with * CIL flushing locked out. As a result, it should only be used during the * transaction commit process when deciding what to format into the item. */ static bool xlog_item_in_current_chkpt( struct xfs_cil *cil, struct xfs_log_item *lip) { if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) return false; /* * li_seq is written on the first commit of a log item to record the * first checkpoint it is written to. Hence if it is different to the * current sequence, we're in a new checkpoint. */ return lip->li_seq == READ_ONCE(cil->xc_current_sequence); } bool xfs_log_item_in_current_chkpt( struct xfs_log_item *lip) { return xlog_item_in_current_chkpt(lip->li_log->l_cilp, lip); } /* * Unavoidable forward declaration - xlog_cil_push_work() calls * xlog_cil_ctx_alloc() itself. */ static void xlog_cil_push_work(struct work_struct *work); static struct xfs_cil_ctx * xlog_cil_ctx_alloc(void) { struct xfs_cil_ctx *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&ctx->committing); INIT_LIST_HEAD(&ctx->busy_extents.extent_list); INIT_LIST_HEAD(&ctx->log_items); INIT_LIST_HEAD(&ctx->lv_chain); INIT_WORK(&ctx->push_work, xlog_cil_push_work); return ctx; } /* * Aggregate the CIL per cpu structures into global counts, lists, etc and * clear the percpu state ready for the next context to use. This is called * from the push code with the context lock held exclusively, hence nothing else * will be accessing or modifying the per-cpu counters. */ static void xlog_cil_push_pcp_aggregate( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { struct xlog_cil_pcp *cilpcp; int cpu; for_each_cpu(cpu, &ctx->cil_pcpmask) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); ctx->ticket->t_curr_res += cilpcp->space_reserved; cilpcp->space_reserved = 0; if (!list_empty(&cilpcp->busy_extents)) { list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents.extent_list); } if (!list_empty(&cilpcp->log_items)) list_splice_init(&cilpcp->log_items, &ctx->log_items); /* * We're in the middle of switching cil contexts. Reset the * counter we use to detect when the current context is nearing * full. */ cilpcp->space_used = 0; } } /* * Aggregate the CIL per-cpu space used counters into the global atomic value. * This is called when the per-cpu counter aggregation will first pass the soft * limit threshold so we can switch to atomic counter aggregation for accurate * detection of hard limit traversal. */ static void xlog_cil_insert_pcp_aggregate( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { int cpu; int count = 0; /* Trigger atomic updates then aggregate only for the first caller */ if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) return; /* * We can race with other cpus setting cil_pcpmask. However, we've * atomically cleared PCP_SPACE which forces other threads to add to * the global space used count. cil_pcpmask is a superset of cilpcp * structures that could have a nonzero space_used. */ for_each_cpu(cpu, &ctx->cil_pcpmask) { struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); count += xchg(&cilpcp->space_used, 0); } atomic_add(count, &ctx->space_used); } static void xlog_cil_ctx_switch( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { xlog_cil_set_iclog_hdr_count(cil); set_bit(XLOG_CIL_EMPTY, &cil->xc_flags); set_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags); ctx->sequence = ++cil->xc_current_sequence; ctx->cil = cil; cil->xc_ctx = ctx; } /* * After the first stage of log recovery is done, we know where the head and * tail of the log are. We need this log initialisation done before we can * initialise the first CIL checkpoint context. * * Here we allocate a log ticket to track space usage during a CIL push. This * ticket is passed to xlog_write() directly so that we don't slowly leak log * space by failing to account for space used by log headers and additional * region headers for split regions. */ void xlog_cil_init_post_recovery( struct xlog *log) { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; xlog_cil_set_iclog_hdr_count(log->l_cilp); } static inline int xlog_cil_iovec_space( uint niovecs) { return round_up((sizeof(struct xfs_log_vec) + niovecs * sizeof(struct xfs_log_iovec)), sizeof(uint64_t)); } /* * Allocate or pin log vector buffers for CIL insertion. * * The CIL currently uses disposable buffers for copying a snapshot of the * modified items into the log during a push. The biggest problem with this is * the requirement to allocate the disposable buffer during the commit if: * a) does not exist; or * b) it is too small * * If we do this allocation within xlog_cil_insert_format_items(), it is done * under the xc_ctx_lock, which means that a CIL push cannot occur during * the memory allocation. This means that we have a potential deadlock situation * under low memory conditions when we have lots of dirty metadata pinned in * the CIL and we need a CIL commit to occur to free memory. * * To avoid this, we need to move the memory allocation outside the * xc_ctx_lock, but because the log vector buffers are disposable, that opens * up a TOCTOU race condition w.r.t. the CIL committing and removing the log * vector buffers between the check and the formatting of the item into the * log vector buffer within the xc_ctx_lock. * * Because the log vector buffer needs to be unchanged during the CIL push * process, we cannot share the buffer between the transaction commit (which * modifies the buffer) and the CIL push context that is writing the changes * into the log. This means skipping preallocation of buffer space is * unreliable, but we most definitely do not want to be allocating and freeing * buffers unnecessarily during commits when overwrites can be done safely. * * The simplest solution to this problem is to allocate a shadow buffer when a * log item is committed for the second time, and then to only use this buffer * if necessary. The buffer can remain attached to the log item until such time * it is needed, and this is the buffer that is reallocated to match the size of * the incoming modification. Then during the formatting of the item we can swap * the active buffer with the new one if we can't reuse the existing buffer. We * don't free the old buffer as it may be reused on the next modification if * it's size is right, otherwise we'll free and reallocate it at that point. * * This function builds a vector for the changes in each log item in the * transaction. It then works out the length of the buffer needed for each log * item, allocates them and attaches the vector to the log item in preparation * for the formatting step which occurs under the xc_ctx_lock. * * While this means the memory footprint goes up, it avoids the repeated * alloc/free pattern that repeated modifications of an item would otherwise * cause, and hence minimises the CPU overhead of such behaviour. */ static void xlog_cil_alloc_shadow_bufs( struct xlog *log, struct xfs_trans *tp) { struct xfs_log_item *lip; list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv; int niovecs = 0; int nbytes = 0; int alloc_size; bool ordered = false; /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; /* get number of vecs and size of data to be stored */ lip->li_ops->iop_size(lip, &niovecs, &nbytes); /* * Ordered items need to be tracked but we do not wish to write * them. We need a logvec to track the object, but we do not * need an iovec or buffer to be allocated for copying data. */ if (niovecs == XFS_LOG_VEC_ORDERED) { ordered = true; niovecs = 0; nbytes = 0; } /* * We 64-bit align the length of each iovec so that the start of * the next one is naturally aligned. We'll need to account for * that slack space here. * * We also add the xlog_op_header to each region when * formatting, but that's not accounted to the size of the item * at this point. Hence we'll need an addition number of bytes * for each vector to hold an opheader. * * Then round nbytes up to 64-bit alignment so that the initial * buffer alignment is easy to calculate and verify. */ nbytes = xlog_item_space(niovecs, nbytes); /* * The data buffer needs to start 64-bit aligned, so round up * that space to ensure we can align it appropriately and not * overrun the buffer. */ alloc_size = nbytes + xlog_cil_iovec_space(niovecs); /* * if we have no shadow buffer, or it is too small, we need to * reallocate it. */ if (!lip->li_lv_shadow || alloc_size > lip->li_lv_shadow->lv_alloc_size) { /* * We free and allocate here as a realloc would copy * unnecessary data. We don't use kvzalloc() for the * same reason - we don't need to zero the data area in * the buffer, only the log vector header and the iovec * storage. */ kvfree(lip->li_lv_shadow); lv = xlog_kvmalloc(alloc_size); memset(lv, 0, xlog_cil_iovec_space(niovecs)); INIT_LIST_HEAD(&lv->lv_list); lv->lv_item = lip; lv->lv_alloc_size = alloc_size; if (ordered) lv->lv_buf_used = XFS_LOG_VEC_ORDERED; else lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1]; lip->li_lv_shadow = lv; } else { /* same or smaller, optimise common overwrite case */ lv = lip->li_lv_shadow; if (ordered) lv->lv_buf_used = XFS_LOG_VEC_ORDERED; else lv->lv_buf_used = 0; lv->lv_bytes = 0; } /* Ensure the lv is set up according to ->iop_size */ lv->lv_niovecs = niovecs; /* The allocated data region lies beyond the iovec region */ lv->lv_buf = (char *)lv + xlog_cil_iovec_space(niovecs); } } /* * Prepare the log item for insertion into the CIL. Calculate the difference in * log space it will consume, and if it is a new item pin it as well. */ STATIC void xfs_cil_prepare_item( struct xlog *log, struct xfs_log_item *lip, struct xfs_log_vec *lv, int *diff_len) { /* Account for the new LV being passed in */ if (lv->lv_buf_used != XFS_LOG_VEC_ORDERED) *diff_len += lv->lv_bytes; /* * If there is no old LV, this is the first time we've seen the item in * this CIL context and so we need to pin it. If we are replacing the * old lv, then remove the space it accounts for and make it the shadow * buffer for later freeing. In both cases we are now switching to the * shadow buffer, so update the pointer to it appropriately. */ if (!lip->li_lv) { if (lv->lv_item->li_ops->iop_pin) lv->lv_item->li_ops->iop_pin(lv->lv_item); lv->lv_item->li_lv_shadow = NULL; } else if (lip->li_lv != lv) { ASSERT(lv->lv_buf_used != XFS_LOG_VEC_ORDERED); *diff_len -= lip->li_lv->lv_bytes; lv->lv_item->li_lv_shadow = lip->li_lv; } /* attach new log vector to log item */ lv->lv_item->li_lv = lv; /* * If this is the first time the item is being committed to the * CIL, store the sequence number on the log item so we can * tell in future commits whether this is the first checkpoint * the item is being committed into. */ if (!lv->lv_item->li_seq) lv->lv_item->li_seq = log->l_cilp->xc_ctx->sequence; } /* * Format log item into a flat buffers * * For delayed logging, we need to hold a formatted buffer containing all the * changes on the log item. This enables us to relog the item in memory and * write it out asynchronously without needing to relock the object that was * modified at the time it gets written into the iclog. * * This function takes the prepared log vectors attached to each log item, and * formats the changes into the log vector buffer. The buffer it uses is * dependent on the current state of the vector in the CIL - the shadow lv is * guaranteed to be large enough for the current modification, but we will only * use that if we can't reuse the existing lv. If we can't reuse the existing * lv, then simple swap it out for the shadow lv. We don't free it - that is * done lazily either by th enext modification or the freeing of the log item. * * We don't set up region headers during this process; we simply copy the * regions into the flat buffer. We can do this because we still have to do a * formatting step to write the regions into the iclog buffer. Writing the * ophdrs during the iclog write means that we can support splitting large * regions across iclog boundares without needing a change in the format of the * item/region encapsulation. * * Hence what we need to do now is change the rewrite the vector array to point * to the copied region inside the buffer we just allocated. This allows us to * format the regions into the iclog as though they are being formatted * directly out of the objects themselves. */ static void xlog_cil_insert_format_items( struct xlog *log, struct xfs_trans *tp, int *diff_len) { struct xfs_log_item *lip; /* Bail out if we didn't find a log item. */ if (list_empty(&tp->t_items)) { ASSERT(0); return; } list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv = lip->li_lv; struct xfs_log_vec *shadow = lip->li_lv_shadow; /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; /* * The formatting size information is already attached to * the shadow lv on the log item. */ if (shadow->lv_buf_used == XFS_LOG_VEC_ORDERED) { if (!lv) { lv = shadow; lv->lv_item = lip; } ASSERT(shadow->lv_alloc_size == lv->lv_alloc_size); xfs_cil_prepare_item(log, lip, lv, diff_len); continue; } /* Skip items that do not have any vectors for writing */ if (!shadow->lv_niovecs) continue; /* compare to existing item size */ if (lv && shadow->lv_alloc_size <= lv->lv_alloc_size) { /* same or smaller, optimise common overwrite case */ /* * set the item up as though it is a new insertion so * that the space reservation accounting is correct. */ *diff_len -= lv->lv_bytes; /* Ensure the lv is set up according to ->iop_size */ lv->lv_niovecs = shadow->lv_niovecs; /* reset the lv buffer information for new formatting */ lv->lv_buf_used = 0; lv->lv_bytes = 0; lv->lv_buf = (char *)lv + xlog_cil_iovec_space(lv->lv_niovecs); } else { /* switch to shadow buffer! */ lv = shadow; lv->lv_item = lip; } ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); lip->li_ops->iop_format(lip, lv); xfs_cil_prepare_item(log, lip, lv, diff_len); } } /* * The use of lockless waitqueue_active() requires that the caller has * serialised itself against the wakeup call in xlog_cil_push_work(). That * can be done by either holding the push lock or the context lock. */ static inline bool xlog_cil_over_hard_limit( struct xlog *log, int32_t space_used) { if (waitqueue_active(&log->l_cilp->xc_push_wait)) return true; if (space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) return true; return false; } /* * Insert the log items into the CIL and calculate the difference in space * consumed by the item. Add the space to the checkpoint ticket and calculate * if the change requires additional log metadata. If it does, take that space * as well. Remove the amount of space we added to the checkpoint ticket from * the current transaction ticket so that the accounting works out correctly. */ static void xlog_cil_insert_items( struct xlog *log, struct xfs_trans *tp, uint32_t released_space) { struct xfs_cil *cil = log->l_cilp; struct xfs_cil_ctx *ctx = cil->xc_ctx; struct xfs_log_item *lip; int len = 0; int iovhdr_res = 0, split_res = 0, ctx_res = 0; int space_used; int order; unsigned int cpu_nr; struct xlog_cil_pcp *cilpcp; ASSERT(tp); /* * We can do this safely because the context can't checkpoint until we * are done so it doesn't matter exactly how we update the CIL. */ xlog_cil_insert_format_items(log, tp, &len); /* * Subtract the space released by intent cancelation from the space we * consumed so that we remove it from the CIL space and add it back to * the current transaction reservation context. */ len -= released_space; /* * Grab the per-cpu pointer for the CIL before we start any accounting. * That ensures that we are running with pre-emption disabled and so we * can't be scheduled away between split sample/update operations that * are done without outside locking to serialise them. */ cpu_nr = get_cpu(); cilpcp = this_cpu_ptr(cil->xc_pcp); /* Tell the future push that there was work added by this CPU. */ if (!cpumask_test_cpu(cpu_nr, &ctx->cil_pcpmask)) cpumask_test_and_set_cpu(cpu_nr, &ctx->cil_pcpmask); /* * We need to take the CIL checkpoint unit reservation on the first * commit into the CIL. Test the XLOG_CIL_EMPTY bit first so we don't * unnecessarily do an atomic op in the fast path here. We can clear the * XLOG_CIL_EMPTY bit as we are under the xc_ctx_lock here and that * needs to be held exclusively to reset the XLOG_CIL_EMPTY bit. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) && test_and_clear_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) ctx_res = ctx->ticket->t_unit_res; /* * Check if we need to steal iclog headers. atomic_read() is not a * locked atomic operation, so we can check the value before we do any * real atomic ops in the fast path. If we've already taken the CIL unit * reservation from this commit, we've already got one iclog header * space reserved so we have to account for that otherwise we risk * overrunning the reservation on this ticket. * * If the CIL is already at the hard limit, we might need more header * space that originally reserved. So steal more header space from every * commit that occurs once we are over the hard limit to ensure the CIL * push won't run out of reservation space. * * This can steal more than we need, but that's OK. * * The cil->xc_ctx_lock provides the serialisation necessary for safely * calling xlog_cil_over_hard_limit() in this context. */ space_used = atomic_read(&ctx->space_used) + cilpcp->space_used + len; if (atomic_read(&cil->xc_iclog_hdrs) > 0 || xlog_cil_over_hard_limit(log, space_used)) { split_res = log->l_iclog_hsize + sizeof(struct xlog_op_header); if (ctx_res) ctx_res += split_res * (tp->t_ticket->t_iclog_hdrs - 1); else ctx_res = split_res * tp->t_ticket->t_iclog_hdrs; atomic_sub(tp->t_ticket->t_iclog_hdrs, &cil->xc_iclog_hdrs); } cilpcp->space_reserved += ctx_res; /* * Accurately account when over the soft limit, otherwise fold the * percpu count into the global count if over the per-cpu threshold. */ if (!test_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) { atomic_add(len, &ctx->space_used); } else if (cilpcp->space_used + len > (XLOG_CIL_SPACE_LIMIT(log) / num_online_cpus())) { space_used = atomic_add_return(cilpcp->space_used + len, &ctx->space_used); cilpcp->space_used = 0; /* * If we just transitioned over the soft limit, we need to * transition to the global atomic counter. */ if (space_used >= XLOG_CIL_SPACE_LIMIT(log)) xlog_cil_insert_pcp_aggregate(cil, ctx); } else { cilpcp->space_used += len; } /* attach the transaction to the CIL if it has any busy extents */ if (!list_empty(&tp->t_busy)) list_splice_init(&tp->t_busy, &cilpcp->busy_extents); /* * Now update the order of everything modified in the transaction * and insert items into the CIL if they aren't already there. * We do this here so we only need to take the CIL lock once during * the transaction commit. */ order = atomic_inc_return(&ctx->order_id); list_for_each_entry(lip, &tp->t_items, li_trans) { /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; lip->li_order_id = order; if (!list_empty(&lip->li_cil)) continue; list_add_tail(&lip->li_cil, &cilpcp->log_items); } put_cpu(); /* * If we've overrun the reservation, dump the tx details before we move * the log items. Shutdown is imminent... */ tp->t_ticket->t_curr_res -= ctx_res + len; if (WARN_ON(tp->t_ticket->t_curr_res < 0)) { xfs_warn(log->l_mp, "Transaction log reservation overrun:"); xfs_warn(log->l_mp, " log items: %d bytes (iov hdrs: %d bytes)", len, iovhdr_res); xfs_warn(log->l_mp, " split region headers: %d bytes", split_res); xfs_warn(log->l_mp, " ctx ticket: %d bytes", ctx_res); xlog_print_trans(tp); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } } static inline void xlog_cil_ail_insert_batch( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t commit_lsn) { int i; spin_lock(&ailp->ail_lock); /* xfs_trans_ail_update_bulk drops ailp->ail_lock */ xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn); for (i = 0; i < nr_items; i++) { struct xfs_log_item *lip = log_items[i]; if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 0); } } /* * Take the checkpoint's log vector chain of items and insert the attached log * items into the AIL. This uses bulk insertion techniques to minimise AIL lock * traffic. * * The AIL tracks log items via the start record LSN of the checkpoint, * not the commit record LSN. This is because we can pipeline multiple * checkpoints, and so the start record of checkpoint N+1 can be * written before the commit record of checkpoint N. i.e: * * start N commit N * +-------------+------------+----------------+ * start N+1 commit N+1 * * The tail of the log cannot be moved to the LSN of commit N when all * the items of that checkpoint are written back, because then the * start record for N+1 is no longer in the active portion of the log * and recovery will fail/corrupt the filesystem. * * Hence when all the log items in checkpoint N are written back, the * tail of the log most now only move as far forwards as the start LSN * of checkpoint N+1. * * If we are called with the aborted flag set, it is because a log write during * a CIL checkpoint commit has failed. In this case, all the items in the * checkpoint have already gone through iop_committed and iop_committing, which * means that checkpoint commit abort handling is treated exactly the same as an * iclog write error even though we haven't started any IO yet. Hence in this * case all we need to do is iop_committed processing, followed by an * iop_unpin(aborted) call. * * The AIL cursor is used to optimise the insert process. If commit_lsn is not * at the end of the AIL, the insert cursor avoids the need to walk the AIL to * find the insertion point on every xfs_log_item_batch_insert() call. This * saves a lot of needless list walking and is a net win, even though it * slightly increases that amount of AIL lock traffic to set it up and tear it * down. */ static void xlog_cil_ail_insert( struct xfs_cil_ctx *ctx, bool aborted) { #define LOG_ITEM_BATCH_SIZE 32 struct xfs_ail *ailp = ctx->cil->xc_log->l_ailp; struct xfs_log_item *log_items[LOG_ITEM_BATCH_SIZE]; struct xfs_log_vec *lv; struct xfs_ail_cursor cur; xfs_lsn_t old_head; int i = 0; /* * Update the AIL head LSN with the commit record LSN of this * checkpoint. As iclogs are always completed in order, this should * always be the same (as iclogs can contain multiple commit records) or * higher LSN than the current head. We do this before insertion of the * items so that log space checks during insertion will reflect the * space that this checkpoint has already consumed. We call * xfs_ail_update_finish() so that tail space and space-based wakeups * will be recalculated appropriately. */ ASSERT(XFS_LSN_CMP(ctx->commit_lsn, ailp->ail_head_lsn) >= 0 || aborted); spin_lock(&ailp->ail_lock); xfs_trans_ail_cursor_last(ailp, &cur, ctx->start_lsn); old_head = ailp->ail_head_lsn; ailp->ail_head_lsn = ctx->commit_lsn; /* xfs_ail_update_finish() drops the ail_lock */ xfs_ail_update_finish(ailp, NULLCOMMITLSN); /* * We move the AIL head forwards to account for the space used in the * log before we remove that space from the grant heads. This prevents a * transient condition where reservation space appears to become * available on return, only for it to disappear again immediately as * the AIL head update accounts in the log tail space. */ smp_wmb(); /* paired with smp_rmb in xlog_grant_space_left */ xlog_grant_return_space(ailp->ail_log, old_head, ailp->ail_head_lsn); /* unpin all the log items */ list_for_each_entry(lv, &ctx->lv_chain, lv_list) { struct xfs_log_item *lip = lv->lv_item; xfs_lsn_t item_lsn; if (aborted) { trace_xlog_ail_insert_abort(lip); set_bit(XFS_LI_ABORTED, &lip->li_flags); } if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) { lip->li_ops->iop_release(lip); continue; } if (lip->li_ops->iop_committed) item_lsn = lip->li_ops->iop_committed(lip, ctx->start_lsn); else item_lsn = ctx->start_lsn; /* item_lsn of -1 means the item needs no further processing */ if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) continue; /* * if we are aborting the operation, no point in inserting the * object into the AIL as we are in a shutdown situation. */ if (aborted) { ASSERT(xlog_is_shutdown(ailp->ail_log)); if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 1); continue; } if (item_lsn != ctx->start_lsn) { /* * Not a bulk update option due to unusual item_lsn. * Push into AIL immediately, rechecking the lsn once * we have the ail lock. Then unpin the item. This does * not affect the AIL cursor the bulk insert path is * using. */ spin_lock(&ailp->ail_lock); if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0) xfs_trans_ail_update(ailp, lip, item_lsn); else spin_unlock(&ailp->ail_lock); if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 0); continue; } /* Item is a candidate for bulk AIL insert. */ log_items[i++] = lv->lv_item; if (i >= LOG_ITEM_BATCH_SIZE) { xlog_cil_ail_insert_batch(ailp, &cur, log_items, LOG_ITEM_BATCH_SIZE, ctx->start_lsn); i = 0; } } /* make sure we insert the remainder! */ if (i) xlog_cil_ail_insert_batch(ailp, &cur, log_items, i, ctx->start_lsn); spin_lock(&ailp->ail_lock); xfs_trans_ail_cursor_done(&cur); spin_unlock(&ailp->ail_lock); } static void xlog_cil_free_logvec( struct list_head *lv_chain) { struct xfs_log_vec *lv; while (!list_empty(lv_chain)) { lv = list_first_entry(lv_chain, struct xfs_log_vec, lv_list); list_del_init(&lv->lv_list); kvfree(lv); } } /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as * possible. */ static void xlog_cil_committed( struct xfs_cil_ctx *ctx) { struct xfs_mount *mp = ctx->cil->xc_log->l_mp; bool abort = xlog_is_shutdown(ctx->cil->xc_log); /* * If the I/O failed, we're aborting the commit and already shutdown. * Wake any commit waiters before aborting the log items so we don't * block async log pushers on callbacks. Async log pushers explicitly do * not wait on log force completion because they may be holding locks * required to unpin items. */ if (abort) { spin_lock(&ctx->cil->xc_push_lock); wake_up_all(&ctx->cil->xc_start_wait); wake_up_all(&ctx->cil->xc_commit_wait); spin_unlock(&ctx->cil->xc_push_lock); } xlog_cil_ail_insert(ctx, abort); xfs_extent_busy_sort(&ctx->busy_extents.extent_list); xfs_extent_busy_clear(&ctx->busy_extents.extent_list, xfs_has_discard(mp) && !abort); spin_lock(&ctx->cil->xc_push_lock); list_del(&ctx->committing); spin_unlock(&ctx->cil->xc_push_lock); xlog_cil_free_logvec(&ctx->lv_chain); if (!list_empty(&ctx->busy_extents.extent_list)) { ctx->busy_extents.owner = ctx; xfs_discard_extents(mp, &ctx->busy_extents); return; } kfree(ctx); } void xlog_cil_process_committed( struct list_head *list) { struct xfs_cil_ctx *ctx; while ((ctx = list_first_entry_or_null(list, struct xfs_cil_ctx, iclog_entry))) { list_del(&ctx->iclog_entry); xlog_cil_committed(ctx); } } /* * Record the LSN of the iclog we were just granted space to start writing into. * If the context doesn't have a start_lsn recorded, then this iclog will * contain the start record for the checkpoint. Otherwise this write contains * the commit record for the checkpoint. */ void xlog_cil_set_ctx_write_state( struct xfs_cil_ctx *ctx, struct xlog_in_core *iclog) { struct xfs_cil *cil = ctx->cil; xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header->h_lsn); ASSERT(!ctx->commit_lsn); if (!ctx->start_lsn) { spin_lock(&cil->xc_push_lock); /* * The LSN we need to pass to the log items on transaction * commit is the LSN reported by the first log vector write, not * the commit lsn. If we use the commit record lsn then we can * move the grant write head beyond the tail LSN and overwrite * it. */ ctx->start_lsn = lsn; wake_up_all(&cil->xc_start_wait); spin_unlock(&cil->xc_push_lock); /* * Make sure the metadata we are about to overwrite in the log * has been flushed to stable storage before this iclog is * issued. */ spin_lock(&cil->xc_log->l_icloglock); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; spin_unlock(&cil->xc_log->l_icloglock); return; } /* * Take a reference to the iclog for the context so that we still hold * it when xlog_write is done and has released it. This means the * context controls when the iclog is released for IO. */ atomic_inc(&iclog->ic_refcnt); /* * xlog_state_get_iclog_space() guarantees there is enough space in the * iclog for an entire commit record, so we can attach the context * callbacks now. This needs to be done before we make the commit_lsn * visible to waiters so that checkpoints with commit records in the * same iclog order their IO completion callbacks in the same order that * the commit records appear in the iclog. */ spin_lock(&cil->xc_log->l_icloglock); list_add_tail(&ctx->iclog_entry, &iclog->ic_callbacks); spin_unlock(&cil->xc_log->l_icloglock); /* * Now we can record the commit LSN and wake anyone waiting for this * sequence to have the ordered commit record assigned to a physical * location in the log. */ spin_lock(&cil->xc_push_lock); ctx->commit_iclog = iclog; ctx->commit_lsn = lsn; wake_up_all(&cil->xc_commit_wait); spin_unlock(&cil->xc_push_lock); } /* * Ensure that the order of log writes follows checkpoint sequence order. This * relies on the context LSN being zero until the log write has guaranteed the * LSN that the log write will start at via xlog_state_get_iclog_space(). */ enum _record_type { _START_RECORD, _COMMIT_RECORD, }; static int xlog_cil_order_write( struct xfs_cil *cil, xfs_csn_t sequence, enum _record_type record) { struct xfs_cil_ctx *ctx; restart: spin_lock(&cil->xc_push_lock); list_for_each_entry(ctx, &cil->xc_committing, committing) { /* * Avoid getting stuck in this loop because we were woken by the * shutdown, but then went back to sleep once already in the * shutdown state. */ if (xlog_is_shutdown(cil->xc_log)) { spin_unlock(&cil->xc_push_lock); return -EIO; } /* * Higher sequences will wait for this one so skip them. * Don't wait for our own sequence, either. */ if (ctx->sequence >= sequence) continue; /* Wait until the LSN for the record has been recorded. */ switch (record) { case _START_RECORD: if (!ctx->start_lsn) { xlog_wait(&cil->xc_start_wait, &cil->xc_push_lock); goto restart; } break; case _COMMIT_RECORD: if (!ctx->commit_lsn) { xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock); goto restart; } break; } } spin_unlock(&cil->xc_push_lock); return 0; } /* * Write out the log vector change now attached to the CIL context. This will * write a start record that needs to be strictly ordered in ascending CIL * sequence order so that log recovery will always use in-order start LSNs when * replaying checkpoints. */ static int xlog_cil_write_chain( struct xfs_cil_ctx *ctx, uint32_t chain_len) { struct xlog *log = ctx->cil->xc_log; int error; error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD); if (error) return error; return xlog_write(log, ctx, &ctx->lv_chain, ctx->ticket, chain_len); } /* * Write out the commit record of a checkpoint transaction to close off a * running log write. These commit records are strictly ordered in ascending CIL * sequence order so that log recovery will always replay the checkpoints in the * correct order. */ static int xlog_cil_write_commit_record( struct xfs_cil_ctx *ctx) { struct xlog *log = ctx->cil->xc_log; struct xlog_op_header ophdr = { .oh_clientid = XFS_TRANSACTION, .oh_tid = cpu_to_be32(ctx->ticket->t_tid), .oh_flags = XLOG_COMMIT_TRANS, }; struct xfs_log_iovec reg = { .i_addr = &ophdr, .i_len = sizeof(struct xlog_op_header), .i_type = XLOG_REG_TYPE_COMMIT, }; struct xfs_log_vec vec = { .lv_niovecs = 1, .lv_iovecp = ®, }; int error; LIST_HEAD(lv_chain); list_add(&vec.lv_list, &lv_chain); if (xlog_is_shutdown(log)) return -EIO; error = xlog_cil_order_write(ctx->cil, ctx->sequence, _COMMIT_RECORD); if (error) return error; /* account for space used by record data */ ctx->ticket->t_curr_res -= reg.i_len; error = xlog_write(log, ctx, &lv_chain, ctx->ticket, reg.i_len); if (error) xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return error; } struct xlog_cil_trans_hdr { struct xlog_op_header oph[2]; struct xfs_trans_header thdr; struct xfs_log_iovec lhdr[2]; }; /* * Build a checkpoint transaction header to begin the journal transaction. We * need to account for the space used by the transaction header here as it is * not accounted for in xlog_write(). * * This is the only place we write a transaction header, so we also build the * log opheaders that indicate the start of a log transaction and wrap the * transaction header. We keep the start record in it's own log vector rather * than compacting them into a single region as this ends up making the logic * in xlog_write() for handling empty opheaders for start, commit and unmount * records much simpler. */ static void xlog_cil_build_trans_hdr( struct xfs_cil_ctx *ctx, struct xlog_cil_trans_hdr *hdr, struct xfs_log_vec *lvhdr, int num_iovecs) { struct xlog_ticket *tic = ctx->ticket; __be32 tid = cpu_to_be32(tic->t_tid); memset(hdr, 0, sizeof(*hdr)); /* Log start record */ hdr->oph[0].oh_tid = tid; hdr->oph[0].oh_clientid = XFS_TRANSACTION; hdr->oph[0].oh_flags = XLOG_START_TRANS; /* log iovec region pointer */ hdr->lhdr[0].i_addr = &hdr->oph[0]; hdr->lhdr[0].i_len = sizeof(struct xlog_op_header); hdr->lhdr[0].i_type = XLOG_REG_TYPE_LRHEADER; /* log opheader */ hdr->oph[1].oh_tid = tid; hdr->oph[1].oh_clientid = XFS_TRANSACTION; hdr->oph[1].oh_len = cpu_to_be32(sizeof(struct xfs_trans_header)); /* transaction header in host byte order format */ hdr->thdr.th_magic = XFS_TRANS_HEADER_MAGIC; hdr->thdr.th_type = XFS_TRANS_CHECKPOINT; hdr->thdr.th_tid = tic->t_tid; hdr->thdr.th_num_items = num_iovecs; /* log iovec region pointer */ hdr->lhdr[1].i_addr = &hdr->oph[1]; hdr->lhdr[1].i_len = sizeof(struct xlog_op_header) + sizeof(struct xfs_trans_header); hdr->lhdr[1].i_type = XLOG_REG_TYPE_TRANSHDR; lvhdr->lv_niovecs = 2; lvhdr->lv_iovecp = &hdr->lhdr[0]; lvhdr->lv_bytes = hdr->lhdr[0].i_len + hdr->lhdr[1].i_len; tic->t_curr_res -= lvhdr->lv_bytes; } /* * CIL item reordering compare function. We want to order in ascending ID order, * but we want to leave items with the same ID in the order they were added to * the list. This is important for operations like reflink where we log 4 order * dependent intents in a single transaction when we overwrite an existing * shared extent with a new shared extent. i.e. BUI(unmap), CUI(drop), * CUI (inc), BUI(remap)... */ static int xlog_cil_order_cmp( void *priv, const struct list_head *a, const struct list_head *b) { struct xfs_log_vec *l1 = container_of(a, struct xfs_log_vec, lv_list); struct xfs_log_vec *l2 = container_of(b, struct xfs_log_vec, lv_list); return l1->lv_order_id > l2->lv_order_id; } /* * Pull all the log vectors off the items in the CIL, and remove the items from * the CIL. We don't need the CIL lock here because it's only needed on the * transaction commit side which is currently locked out by the flush lock. * * If a log item is marked with a whiteout, we do not need to write it to the * journal and so we just move them to the whiteout list for the caller to * dispose of appropriately. */ static void xlog_cil_build_lv_chain( struct xfs_cil_ctx *ctx, struct list_head *whiteouts, uint32_t *num_iovecs, uint32_t *num_bytes) { while (!list_empty(&ctx->log_items)) { struct xfs_log_item *item; struct xfs_log_vec *lv; item = list_first_entry(&ctx->log_items, struct xfs_log_item, li_cil); if (test_bit(XFS_LI_WHITEOUT, &item->li_flags)) { list_move(&item->li_cil, whiteouts); trace_xfs_cil_whiteout_skip(item); continue; } lv = item->li_lv; lv->lv_order_id = item->li_order_id; /* we don't write ordered log vectors */ if (lv->lv_buf_used != XFS_LOG_VEC_ORDERED) *num_bytes += lv->lv_bytes; *num_iovecs += lv->lv_niovecs; list_add_tail(&lv->lv_list, &ctx->lv_chain); list_del_init(&item->li_cil); item->li_order_id = 0; item->li_lv = NULL; } } static void xlog_cil_cleanup_whiteouts( struct list_head *whiteouts) { while (!list_empty(whiteouts)) { struct xfs_log_item *item = list_first_entry(whiteouts, struct xfs_log_item, li_cil); list_del_init(&item->li_cil); trace_xfs_cil_whiteout_unpin(item); item->li_ops->iop_unpin(item, 1); } } /* * Push the Committed Item List to the log. * * If the current sequence is the same as xc_push_seq we need to do a flush. If * xc_push_seq is less than the current sequence, then it has already been * flushed and we don't need to do anything - the caller will wait for it to * complete if necessary. * * xc_push_seq is checked unlocked against the sequence number for a match. * Hence we can allow log forces to run racily and not issue pushes for the * same sequence twice. If we get a race between multiple pushes for the same * sequence they will block on the first one and then abort, hence avoiding * needless pushes. * * This runs from a workqueue so it does not inherent any specific memory * allocation context. However, we do not want to block on memory reclaim * recursing back into the filesystem because this push may have been triggered * by memory reclaim itself. Hence we really need to run under full GFP_NOFS * contraints here. */ static void xlog_cil_push_work( struct work_struct *work) { unsigned int nofs_flags = memalloc_nofs_save(); struct xfs_cil_ctx *ctx = container_of(work, struct xfs_cil_ctx, push_work); struct xfs_cil *cil = ctx->cil; struct xlog *log = cil->xc_log; struct xfs_cil_ctx *new_ctx; int num_iovecs = 0; int num_bytes = 0; int error = 0; struct xlog_cil_trans_hdr thdr; struct xfs_log_vec lvhdr = {}; xfs_csn_t push_seq; bool push_commit_stable; LIST_HEAD (whiteouts); struct xlog_ticket *ticket; new_ctx = xlog_cil_ctx_alloc(); new_ctx->ticket = xlog_cil_ticket_alloc(log); down_write(&cil->xc_ctx_lock); spin_lock(&cil->xc_push_lock); push_seq = cil->xc_push_seq; ASSERT(push_seq <= ctx->sequence); push_commit_stable = cil->xc_push_commit_stable; cil->xc_push_commit_stable = false; /* * As we are about to switch to a new, empty CIL context, we no longer * need to throttle tasks on CIL space overruns. Wake any waiters that * the hard push throttle may have caught so they can start committing * to the new context. The ctx->xc_push_lock provides the serialisation * necessary for safely using the lockless waitqueue_active() check in * this context. */ if (waitqueue_active(&cil->xc_push_wait)) wake_up_all(&cil->xc_push_wait); xlog_cil_push_pcp_aggregate(cil, ctx); /* * Check if we've anything to push. If there is nothing, then we don't * move on to a new sequence number and so we have to be able to push * this sequence again later. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { cil->xc_push_seq = 0; spin_unlock(&cil->xc_push_lock); goto out_skip; } /* check for a previously pushed sequence */ if (push_seq < ctx->sequence) { spin_unlock(&cil->xc_push_lock); goto out_skip; } /* * We are now going to push this context, so add it to the committing * list before we do anything else. This ensures that anyone waiting on * this push can easily detect the difference between a "push in * progress" and "CIL is empty, nothing to do". * * IOWs, a wait loop can now check for: * the current sequence not being found on the committing list; * an empty CIL; and * an unchanged sequence number * to detect a push that had nothing to do and therefore does not need * waiting on. If the CIL is not empty, we get put on the committing * list before emptying the CIL and bumping the sequence number. Hence * an empty CIL and an unchanged sequence number means we jumped out * above after doing nothing. * * Hence the waiter will either find the commit sequence on the * committing list or the sequence number will be unchanged and the CIL * still dirty. In that latter case, the push has not yet started, and * so the waiter will have to continue trying to check the CIL * committing list until it is found. In extreme cases of delay, the * sequence may fully commit between the attempts the wait makes to wait * on the commit sequence. */ list_add(&ctx->committing, &cil->xc_committing); spin_unlock(&cil->xc_push_lock); xlog_cil_build_lv_chain(ctx, &whiteouts, &num_iovecs, &num_bytes); /* * Switch the contexts so we can drop the context lock and move out * of a shared context. We can't just go straight to the commit record, * though - we need to synchronise with previous and future commits so * that the commit records are correctly ordered in the log to ensure * that we process items during log IO completion in the correct order. * * For example, if we get an EFI in one checkpoint and the EFD in the * next (e.g. due to log forces), we do not want the checkpoint with * the EFD to be committed before the checkpoint with the EFI. Hence * we must strictly order the commit records of the checkpoints so * that: a) the checkpoint callbacks are attached to the iclogs in the * correct order; and b) the checkpoints are replayed in correct order * in log recovery. * * Hence we need to add this context to the committing context list so * that higher sequences will wait for us to write out a commit record * before they do. * * xfs_log_force_seq requires us to mirror the new sequence into the cil * structure atomically with the addition of this sequence to the * committing list. This also ensures that we can do unlocked checks * against the current sequence in log forces without risking * deferencing a freed context pointer. */ spin_lock(&cil->xc_push_lock); xlog_cil_ctx_switch(cil, new_ctx); spin_unlock(&cil->xc_push_lock); up_write(&cil->xc_ctx_lock); /* * Sort the log vector chain before we add the transaction headers. * This ensures we always have the transaction headers at the start * of the chain. */ list_sort(NULL, &ctx->lv_chain, xlog_cil_order_cmp); /* * Build a checkpoint transaction header and write it to the log to * begin the transaction. We need to account for the space used by the * transaction header here as it is not accounted for in xlog_write(). * Add the lvhdr to the head of the lv chain we pass to xlog_write() so * it gets written into the iclog first. */ xlog_cil_build_trans_hdr(ctx, &thdr, &lvhdr, num_iovecs); num_bytes += lvhdr.lv_bytes; list_add(&lvhdr.lv_list, &ctx->lv_chain); /* * Take the lvhdr back off the lv_chain immediately after calling * xlog_cil_write_chain() as it should not be passed to log IO * completion. */ error = xlog_cil_write_chain(ctx, num_bytes); list_del(&lvhdr.lv_list); if (error) goto out_abort_free_ticket; error = xlog_cil_write_commit_record(ctx); if (error) goto out_abort_free_ticket; /* * Grab the ticket from the ctx so we can ungrant it after releasing the * commit_iclog. The ctx may be freed by the time we return from * releasing the commit_iclog (i.e. checkpoint has been completed and * callback run) so we can't reference the ctx after the call to * xlog_state_release_iclog(). */ ticket = ctx->ticket; /* * If the checkpoint spans multiple iclogs, wait for all previous iclogs * to complete before we submit the commit_iclog. We can't use state * checks for this - ACTIVE can be either a past completed iclog or a * future iclog being filled, while WANT_SYNC through SYNC_DONE can be a * past or future iclog awaiting IO or ordered IO completion to be run. * In the latter case, if it's a future iclog and we wait on it, the we * will hang because it won't get processed through to ic_force_wait * wakeup until this commit_iclog is written to disk. Hence we use the * iclog header lsn and compare it to the commit lsn to determine if we * need to wait on iclogs or not. */ spin_lock(&log->l_icloglock); if (ctx->start_lsn != ctx->commit_lsn) { xfs_lsn_t plsn = be64_to_cpu( ctx->commit_iclog->ic_prev->ic_header->h_lsn); if (plsn && XFS_LSN_CMP(plsn, ctx->commit_lsn) < 0) { /* * Waiting on ic_force_wait orders the completion of * iclogs older than ic_prev. Hence we only need to wait * on the most recent older iclog here. */ xlog_wait_on_iclog(ctx->commit_iclog->ic_prev); spin_lock(&log->l_icloglock); } /* * We need to issue a pre-flush so that the ordering for this * checkpoint is correctly preserved down to stable storage. */ ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; } /* * The commit iclog must be written to stable storage to guarantee * journal IO vs metadata writeback IO is correctly ordered on stable * storage. * * If the push caller needs the commit to be immediately stable and the * commit_iclog is not yet marked as XLOG_STATE_WANT_SYNC to indicate it * will be written when released, switch it's state to WANT_SYNC right * now. */ ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA; if (push_commit_stable && ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(log, ctx->commit_iclog, 0); ticket = ctx->ticket; xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); xlog_cil_cleanup_whiteouts(&whiteouts); xfs_log_ticket_ungrant(log, ticket); memalloc_nofs_restore(nofs_flags); return; out_skip: up_write(&cil->xc_ctx_lock); xfs_log_ticket_put(new_ctx->ticket); kfree(new_ctx); memalloc_nofs_restore(nofs_flags); return; out_abort_free_ticket: ASSERT(xlog_is_shutdown(log)); xlog_cil_cleanup_whiteouts(&whiteouts); if (!ctx->commit_iclog) { xfs_log_ticket_ungrant(log, ctx->ticket); xlog_cil_committed(ctx); memalloc_nofs_restore(nofs_flags); return; } spin_lock(&log->l_icloglock); ticket = ctx->ticket; xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); xfs_log_ticket_ungrant(log, ticket); memalloc_nofs_restore(nofs_flags); } /* * We need to push CIL every so often so we don't cache more than we can fit in * the log. The limit really is that a checkpoint can't be more than half the * log (the current checkpoint is not allowed to overwrite the previous * checkpoint), but commit latency and memory usage limit this to a smaller * size. */ static void xlog_cil_push_background( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; int space_used = atomic_read(&cil->xc_ctx->space_used); /* * The cil won't be empty because we are called while holding the * context lock so whatever we added to the CIL will still be there. */ ASSERT(!test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); /* * We are done if: * - we haven't used up all the space available yet; or * - we've already queued up a push; and * - we're not over the hard limit; and * - nothing has been over the hard limit. * * If so, we don't need to take the push lock as there's nothing to do. */ if (space_used < XLOG_CIL_SPACE_LIMIT(log) || (cil->xc_push_seq == cil->xc_current_sequence && space_used < XLOG_CIL_BLOCKING_SPACE_LIMIT(log) && !waitqueue_active(&cil->xc_push_wait))) { up_read(&cil->xc_ctx_lock); return; } spin_lock(&cil->xc_push_lock); if (cil->xc_push_seq < cil->xc_current_sequence) { cil->xc_push_seq = cil->xc_current_sequence; queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work); } /* * Drop the context lock now, we can't hold that if we need to sleep * because we are over the blocking threshold. The push_lock is still * held, so blocking threshold sleep/wakeup is still correctly * serialised here. */ up_read(&cil->xc_ctx_lock); /* * If we are well over the space limit, throttle the work that is being * done until the push work on this context has begun. Enforce the hard * throttle on all transaction commits once it has been activated, even * if the committing transactions have resulted in the space usage * dipping back down under the hard limit. * * The ctx->xc_push_lock provides the serialisation necessary for safely * calling xlog_cil_over_hard_limit() in this context. */ if (xlog_cil_over_hard_limit(log, space_used)) { trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket); ASSERT(space_used < log->l_logsize); xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock); return; } spin_unlock(&cil->xc_push_lock); } /* * xlog_cil_push_now() is used to trigger an immediate CIL push to the sequence * number that is passed. When it returns, the work will be queued for * @push_seq, but it won't be completed. * * If the caller is performing a synchronous force, we will flush the workqueue * to get previously queued work moving to minimise the wait time they will * undergo waiting for all outstanding pushes to complete. The caller is * expected to do the required waiting for push_seq to complete. * * If the caller is performing an async push, we need to ensure that the * checkpoint is fully flushed out of the iclogs when we finish the push. If we * don't do this, then the commit record may remain sitting in memory in an * ACTIVE iclog. This then requires another full log force to push to disk, * which defeats the purpose of having an async, non-blocking CIL force * mechanism. Hence in this case we need to pass a flag to the push work to * indicate it needs to flush the commit record itself. */ static void xlog_cil_push_now( struct xlog *log, xfs_lsn_t push_seq, bool async) { struct xfs_cil *cil = log->l_cilp; if (!cil) return; ASSERT(push_seq && push_seq <= cil->xc_current_sequence); /* start on any pending background push to minimise wait time on it */ if (!async) flush_workqueue(cil->xc_push_wq); spin_lock(&cil->xc_push_lock); /* * If this is an async flush request, we always need to set the * xc_push_commit_stable flag even if something else has already queued * a push. The flush caller is asking for the CIL to be on stable * storage when the next push completes, so regardless of who has queued * the push, the flush requires stable semantics from it. */ cil->xc_push_commit_stable = async; /* * If the CIL is empty or we've already pushed the sequence then * there's no more work that we need to do. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) || push_seq <= cil->xc_push_seq) { spin_unlock(&cil->xc_push_lock); return; } cil->xc_push_seq = push_seq; queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work); spin_unlock(&cil->xc_push_lock); } bool xlog_cil_empty( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; bool empty = false; spin_lock(&cil->xc_push_lock); if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) empty = true; spin_unlock(&cil->xc_push_lock); return empty; } /* * If there are intent done items in this transaction and the related intent was * committed in the current (same) CIL checkpoint, we don't need to write either * the intent or intent done item to the journal as the change will be * journalled atomically within this checkpoint. As we cannot remove items from * the CIL here, mark the related intent with a whiteout so that the CIL push * can remove it rather than writing it to the journal. Then remove the intent * done item from the current transaction and release it so it doesn't get put * into the CIL at all. */ static uint32_t xlog_cil_process_intents( struct xfs_cil *cil, struct xfs_trans *tp) { struct xfs_log_item *lip, *ilip, *next; uint32_t len = 0; list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { if (!(lip->li_ops->flags & XFS_ITEM_INTENT_DONE)) continue; ilip = lip->li_ops->iop_intent(lip); if (!ilip || !xlog_item_in_current_chkpt(cil, ilip)) continue; set_bit(XFS_LI_WHITEOUT, &ilip->li_flags); trace_xfs_cil_whiteout_mark(ilip); len += ilip->li_lv->lv_bytes; kvfree(ilip->li_lv); ilip->li_lv = NULL; xfs_trans_del_item(lip); lip->li_ops->iop_release(lip); } return len; } /* * Commit a transaction with the given vector to the Committed Item List. * * To do this, we need to format the item, pin it in memory if required and * account for the space used by the transaction. Once we have done that we * need to release the unused reservation for the transaction, attach the * transaction to the checkpoint context so we carry the busy extents through * to checkpoint completion, and then unlock all the items in the transaction. * * Called with the context lock already held in read mode to lock out * background commit, returns without it held once background commits are * allowed again. */ void xlog_cil_commit( struct xlog *log, struct xfs_trans *tp, xfs_csn_t *commit_seq, bool regrant) { struct xfs_cil *cil = log->l_cilp; struct xfs_log_item *lip, *next; uint32_t released_space = 0; /* * Do all necessary memory allocation before we lock the CIL. * This ensures the allocation does not deadlock with a CIL * push in memory reclaim (e.g. from kswapd). */ xlog_cil_alloc_shadow_bufs(log, tp); /* lock out background commit */ down_read(&cil->xc_ctx_lock); if (tp->t_flags & XFS_TRANS_HAS_INTENT_DONE) released_space = xlog_cil_process_intents(cil, tp); xlog_cil_insert_items(log, tp, released_space); if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); else xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; xfs_trans_unreserve_and_mod_sb(tp); /* * Once all the items of the transaction have been copied to the CIL, * the items can be unlocked and possibly freed. * * This needs to be done before we drop the CIL context lock because we * have to update state in the log items and unlock them before they go * to disk. If we don't, then the CIL checkpoint can race with us and * we can run checkpoint completion before we've updated and unlocked * the log items. This affects (at least) processing of stale buffers, * inodes and EFIs. */ trace_xfs_trans_commit_items(tp, _RET_IP_); list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { xfs_trans_del_item(lip); if (lip->li_ops->iop_committing) lip->li_ops->iop_committing(lip, cil->xc_ctx->sequence); } if (commit_seq) *commit_seq = cil->xc_ctx->sequence; /* xlog_cil_push_background() releases cil->xc_ctx_lock */ xlog_cil_push_background(log); } /* * Flush the CIL to stable storage but don't wait for it to complete. This * requires the CIL push to ensure the commit record for the push hits the disk, * but otherwise is no different to a push done from a log force. */ void xlog_cil_flush( struct xlog *log) { xfs_csn_t seq = log->l_cilp->xc_current_sequence; trace_xfs_log_force(log->l_mp, seq, _RET_IP_); xlog_cil_push_now(log, seq, true); /* * If the CIL is empty, make sure that any previous checkpoint that may * still be in an active iclog is pushed to stable storage. */ if (test_bit(XLOG_CIL_EMPTY, &log->l_cilp->xc_flags)) xfs_log_force(log->l_mp, 0); } /* * Conditionally push the CIL based on the sequence passed in. * * We only need to push if we haven't already pushed the sequence number given. * Hence the only time we will trigger a push here is if the push sequence is * the same as the current context. * * We return the current commit lsn to allow the callers to determine if a * iclog flush is necessary following this call. */ xfs_lsn_t xlog_cil_force_seq( struct xlog *log, xfs_csn_t sequence) { struct xfs_cil *cil = log->l_cilp; struct xfs_cil_ctx *ctx; xfs_lsn_t commit_lsn = NULLCOMMITLSN; ASSERT(sequence <= cil->xc_current_sequence); if (!sequence) sequence = cil->xc_current_sequence; trace_xfs_log_force(log->l_mp, sequence, _RET_IP_); /* * check to see if we need to force out the current context. * xlog_cil_push() handles racing pushes for the same sequence, * so no need to deal with it here. */ restart: xlog_cil_push_now(log, sequence, false); /* * See if we can find a previous sequence still committing. * We need to wait for all previous sequence commits to complete * before allowing the force of push_seq to go ahead. Hence block * on commits for those as well. */ spin_lock(&cil->xc_push_lock); list_for_each_entry(ctx, &cil->xc_committing, committing) { /* * Avoid getting stuck in this loop because we were woken by the * shutdown, but then went back to sleep once already in the * shutdown state. */ if (xlog_is_shutdown(log)) goto out_shutdown; if (ctx->sequence > sequence) continue; if (!ctx->commit_lsn) { /* * It is still being pushed! Wait for the push to * complete, then start again from the beginning. */ XFS_STATS_INC(log->l_mp, xs_log_force_sleep); xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock); goto restart; } if (ctx->sequence != sequence) continue; /* found it! */ commit_lsn = ctx->commit_lsn; } /* * The call to xlog_cil_push_now() executes the push in the background. * Hence by the time we have got here it our sequence may not have been * pushed yet. This is true if the current sequence still matches the * push sequence after the above wait loop and the CIL still contains * dirty objects. This is guaranteed by the push code first adding the * context to the committing list before emptying the CIL. * * Hence if we don't find the context in the committing list and the * current sequence number is unchanged then the CIL contents are * significant. If the CIL is empty, if means there was nothing to push * and that means there is nothing to wait for. If the CIL is not empty, * it means we haven't yet started the push, because if it had started * we would have found the context on the committing list. */ if (sequence == cil->xc_current_sequence && !test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { spin_unlock(&cil->xc_push_lock); goto restart; } spin_unlock(&cil->xc_push_lock); return commit_lsn; /* * We detected a shutdown in progress. We need to trigger the log force * to pass through it's iclog state machine error handling, even though * we are already in a shutdown state. Hence we can't return * NULLCOMMITLSN here as that has special meaning to log forces (i.e. * LSN is already stable), so we return a zero LSN instead. */ out_shutdown: spin_unlock(&cil->xc_push_lock); return 0; } /* * Perform initial CIL structure initialisation. */ int xlog_cil_init( struct xlog *log) { struct xfs_cil *cil; struct xfs_cil_ctx *ctx; struct xlog_cil_pcp *cilpcp; int cpu; cil = kzalloc(sizeof(*cil), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!cil) return -ENOMEM; /* * Limit the CIL pipeline depth to 4 concurrent works to bound the * concurrency the log spinlocks will be exposed to. */ cil->xc_push_wq = alloc_workqueue("xfs-cil/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND), 4, log->l_mp->m_super->s_id); if (!cil->xc_push_wq) goto out_destroy_cil; cil->xc_log = log; cil->xc_pcp = alloc_percpu(struct xlog_cil_pcp); if (!cil->xc_pcp) goto out_destroy_wq; for_each_possible_cpu(cpu) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); INIT_LIST_HEAD(&cilpcp->busy_extents); INIT_LIST_HEAD(&cilpcp->log_items); } INIT_LIST_HEAD(&cil->xc_committing); spin_lock_init(&cil->xc_push_lock); init_waitqueue_head(&cil->xc_push_wait); init_rwsem(&cil->xc_ctx_lock); init_waitqueue_head(&cil->xc_start_wait); init_waitqueue_head(&cil->xc_commit_wait); log->l_cilp = cil; ctx = xlog_cil_ctx_alloc(); xlog_cil_ctx_switch(cil, ctx); return 0; out_destroy_wq: destroy_workqueue(cil->xc_push_wq); out_destroy_cil: kfree(cil); return -ENOMEM; } void xlog_cil_destroy( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; if (cil->xc_ctx) { if (cil->xc_ctx->ticket) xfs_log_ticket_put(cil->xc_ctx->ticket); kfree(cil->xc_ctx); } ASSERT(test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); free_percpu(cil->xc_pcp); destroy_workqueue(cil->xc_push_wq); kfree(cil); } |
| 293 280 280 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_NAMESPACE_H #define _LINUX_CGROUP_NAMESPACE_H #include <linux/ns_common.h> struct cgroup_namespace { struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; struct css_set *root_cset; }; extern struct cgroup_namespace init_cgroup_ns; #ifdef CONFIG_CGROUPS static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) { return container_of(ns, struct cgroup_namespace, ns); } void free_cgroup_ns(struct cgroup_namespace *ns); struct cgroup_namespace *copy_cgroup_ns(u64 flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns); int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); static inline void get_cgroup_ns(struct cgroup_namespace *ns) { ns_ref_inc(ns); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { if (ns_ref_put(ns)) free_cgroup_ns(ns); } #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } static inline struct cgroup_namespace * copy_cgroup_ns(u64 flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { return old_ns; } static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } #endif /* !CONFIG_CGROUPS */ #endif /* _LINUX_CGROUP_NAMESPACE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * iptables module for DCCP protocol header matching * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/ip.h> #include <linux/dccp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_dccp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: DCCP protocol packet match"); MODULE_ALIAS("ipt_dccp"); MODULE_ALIAS("ip6t_dccp"); #define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ || (!!((invflag) & (option)) ^ (cond))) static unsigned char *dccp_optbuf; static DEFINE_SPINLOCK(dccp_buflock); static inline bool dccp_find_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ const unsigned char *op; unsigned int optoff = __dccp_hdr_len(dh); unsigned int optlen = dh->dccph_doff*4 - __dccp_hdr_len(dh); unsigned int i; if (dh->dccph_doff * 4 < __dccp_hdr_len(dh)) goto invalid; if (!optlen) return false; spin_lock_bh(&dccp_buflock); op = skb_header_pointer(skb, protoff + optoff, optlen, dccp_optbuf); if (op == NULL) { /* If we don't have the whole header, drop packet. */ goto partial; } for (i = 0; i < optlen; ) { if (op[i] == option) { spin_unlock_bh(&dccp_buflock); return true; } if (op[i] < 2) i++; else i += op[i+1]?:1; } spin_unlock_bh(&dccp_buflock); return false; partial: spin_unlock_bh(&dccp_buflock); invalid: *hotdrop = true; return false; } static inline bool match_types(const struct dccp_hdr *dh, u_int16_t typemask) { return typemask & (1 << dh->dccph_type); } static inline bool match_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { return dccp_find_option(option, skb, protoff, dh, hotdrop); } static bool dccp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_dccp_info *info = par->matchinfo; const struct dccp_hdr *dh; struct dccp_hdr _dh; if (par->fragoff != 0) return false; dh = skb_header_pointer(skb, par->thoff, sizeof(_dh), &_dh); if (dh == NULL) { par->hotdrop = true; return false; } return DCCHECK(ntohs(dh->dccph_sport) >= info->spts[0] && ntohs(dh->dccph_sport) <= info->spts[1], XT_DCCP_SRC_PORTS, info->flags, info->invflags) && DCCHECK(ntohs(dh->dccph_dport) >= info->dpts[0] && ntohs(dh->dccph_dport) <= info->dpts[1], XT_DCCP_DEST_PORTS, info->flags, info->invflags) && DCCHECK(match_types(dh, info->typemask), XT_DCCP_TYPE, info->flags, info->invflags) && DCCHECK(match_option(info->option, skb, par->thoff, dh, &par->hotdrop), XT_DCCP_OPTION, info->flags, info->invflags); } static int dccp_mt_check(const struct xt_mtchk_param *par) { const struct xt_dccp_info *info = par->matchinfo; if (info->flags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~info->flags) return -EINVAL; return 0; } static struct xt_match dccp_mt_reg[] __read_mostly = { { .name = "dccp", .family = NFPROTO_IPV4, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, { .name = "dccp", .family = NFPROTO_IPV6, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, }; static int __init dccp_mt_init(void) { int ret; /* doff is 8 bits, so the maximum option size is (4*256). Don't put * this in BSS since DaveM is worried about locked TLB's for kernel * BSS. */ dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); if (!dccp_optbuf) return -ENOMEM; ret = xt_register_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); if (ret) goto out_kfree; return ret; out_kfree: kfree(dccp_optbuf); return ret; } static void __exit dccp_mt_exit(void) { xt_unregister_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); kfree(dccp_optbuf); } module_init(dccp_mt_init); module_exit(dccp_mt_exit); |
| 25 1 25 25 6 4 2 3 3 3 3 3 3 3 3 3 3 3 3 3 1 3 19 25 8 9 2 4 13 37 37 22 19 6 6 7 18 21 1 26 26 24 6 6 18 6 1 21 7 2 20 21 27 24 24 3 3 3 3 3 2 1 1 1 2 3 3 27 1 10 16 16 1 16 16 6 29 29 28 29 1 1 1 29 29 24 6 3 29 2 2 28 3 13 16 16 16 16 27 28 13 26 1 38 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Tino Reichardt, 2012 */ #include <linux/fs.h> #include <linux/slab.h> #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_dmap.h" #include "jfs_imap.h" #include "jfs_lock.h" #include "jfs_metapage.h" #include "jfs_debug.h" #include "jfs_discard.h" /* * SERIALIZATION of the Block Allocation Map. * * the working state of the block allocation map is accessed in * two directions: * * 1) allocation and free requests that start at the dmap * level and move up through the dmap control pages (i.e. * the vast majority of requests). * * 2) allocation requests that start at dmap control page * level and work down towards the dmaps. * * the serialization scheme used here is as follows. * * requests which start at the bottom are serialized against each * other through buffers and each requests holds onto its buffers * as it works it way up from a single dmap to the required level * of dmap control page. * requests that start at the top are serialized against each other * and request that start from the bottom by the multiple read/single * write inode lock of the bmap inode. requests starting at the top * take this lock in write mode while request starting at the bottom * take the lock in read mode. a single top-down request may proceed * exclusively while multiple bottoms-up requests may proceed * simultaneously (under the protection of busy buffers). * * in addition to information found in dmaps and dmap control pages, * the working state of the block allocation map also includes read/ * write information maintained in the bmap descriptor (i.e. total * free block count, allocation group level free block counts). * a single exclusive lock (BMAP_LOCK) is used to guard this information * in the face of multiple-bottoms up requests. * (lock ordering: IREAD_LOCK, BMAP_LOCK); * * accesses to the persistent state of the block allocation map (limited * to the persistent bitmaps in dmaps) is guarded by (busy) buffers. */ #define BMAP_LOCK_INIT(bmp) mutex_init(&bmp->db_bmaplock) #define BMAP_LOCK(bmp) mutex_lock(&bmp->db_bmaplock) #define BMAP_UNLOCK(bmp) mutex_unlock(&bmp->db_bmaplock) /* * forward references */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbAllocNear(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks, int l2nb, s64 * results); static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbAllocDmapLev(struct bmap * bmp, struct dmap * dp, int nblocks, int l2nb, s64 * results); static int dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results); static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results); static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbMaxBud(u8 * cp); static int blkstol2(s64 nb); static int cntlz(u32 value); static int cnttz(u32 word); static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbInitDmap(struct dmap * dp, s64 blkno, int nblocks); static int dbInitDmapTree(struct dmap * dp); static int dbInitTree(struct dmaptree * dtp); static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i); static int dbGetL2AGSize(s64 nblocks); /* * buddy table * * table used for determining buddy sizes within characters of * dmap bitmap words. the characters themselves serve as indexes * into the table, with the table elements yielding the maximum * binary buddy of free bits within the character. */ static const s8 budtab[256] = { 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, -1 }; /* * NAME: dbMount() * * FUNCTION: initializate the block allocation map. * * memory is allocated for the in-core bmap descriptor and * the in-core descriptor is initialized from disk. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * 0 - success * -ENOMEM - insufficient memory * -EIO - i/o error * -EINVAL - wrong bmap data */ int dbMount(struct inode *ipbmap) { struct bmap *bmp; struct dbmap_disk *dbmp_le; struct metapage *mp; int i, err; /* * allocate/initialize the in-memory bmap descriptor */ /* allocate memory for the in-memory bmap descriptor */ bmp = kmalloc(sizeof(struct bmap), GFP_KERNEL); if (bmp == NULL) return -ENOMEM; /* read the on-disk bmap descriptor. */ mp = read_metapage(ipbmap, BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { err = -EIO; goto err_kfree_bmp; } /* copy the on-disk bmap descriptor to its in-memory version. */ dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); if ((bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) || (bmp->db_l2nbperpage < 0) || !bmp->db_numag || (bmp->db_numag > MAXAG) || (bmp->db_maxag >= MAXAG) || (bmp->db_maxag < 0) || (bmp->db_agpref >= MAXAG) || (bmp->db_agpref < 0) || (bmp->db_agheight < 0) || (bmp->db_agheight > (L2LPERCTL >> 1)) || (bmp->db_agwidth < 1) || (bmp->db_agwidth > (LPERCTL / MAXAG)) || (bmp->db_agwidth > (1 << (L2LPERCTL - (bmp->db_agheight << 1)))) || (bmp->db_agstart < 0) || (bmp->db_agstart > (CTLTREESIZE - 1 - bmp->db_agwidth * (MAXAG - 1))) || (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG) || (bmp->db_agl2size < 0) || ((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { err = -EINVAL; goto err_release_metapage; } for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); bmp->db_maxfreebud = dbmp_le->dn_maxfreebud; /* release the buffer. */ release_metapage(mp); /* bind the bmap inode and the bmap descriptor to each other. */ bmp->db_ipbmap = ipbmap; JFS_SBI(ipbmap->i_sb)->bmap = bmp; memset(bmp->db_active, 0, sizeof(bmp->db_active)); /* * allocate/initialize the bmap lock */ BMAP_LOCK_INIT(bmp); return (0); err_release_metapage: release_metapage(mp); err_kfree_bmp: kfree(bmp); return err; } /* * NAME: dbUnmount() * * FUNCTION: terminate the block allocation map in preparation for * file system unmount. * * the in-core bmap descriptor is written to disk and * the memory for this descriptor is freed. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbUnmount(struct inode *ipbmap, int mounterror) { struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; if (!(mounterror || isReadOnly(ipbmap))) dbSync(ipbmap); /* * Invalidate the page cache buffers */ truncate_inode_pages(ipbmap->i_mapping, 0); /* free the memory for the in-memory bmap. */ kfree(bmp); JFS_SBI(ipbmap->i_sb)->bmap = NULL; return (0); } /* * dbSync() */ int dbSync(struct inode *ipbmap) { struct dbmap_disk *dbmp_le; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; struct metapage *mp; int i; /* * write bmap global control page */ /* get the buffer for the on-disk bmap descriptor. */ mp = read_metapage(ipbmap, BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { jfs_err("dbSync: read_metapage failed!"); return -EIO; } /* copy the in-memory version of the bmap to the on-disk version */ dbmp_le = (struct dbmap_disk *) mp->data; dbmp_le->dn_mapsize = cpu_to_le64(bmp->db_mapsize); dbmp_le->dn_nfree = cpu_to_le64(bmp->db_nfree); dbmp_le->dn_l2nbperpage = cpu_to_le32(bmp->db_l2nbperpage); dbmp_le->dn_numag = cpu_to_le32(bmp->db_numag); dbmp_le->dn_maxlevel = cpu_to_le32(bmp->db_maxlevel); dbmp_le->dn_maxag = cpu_to_le32(bmp->db_maxag); dbmp_le->dn_agpref = cpu_to_le32(bmp->db_agpref); dbmp_le->dn_aglevel = cpu_to_le32(bmp->db_aglevel); dbmp_le->dn_agheight = cpu_to_le32(bmp->db_agheight); dbmp_le->dn_agwidth = cpu_to_le32(bmp->db_agwidth); dbmp_le->dn_agstart = cpu_to_le32(bmp->db_agstart); dbmp_le->dn_agl2size = cpu_to_le32(bmp->db_agl2size); for (i = 0; i < MAXAG; i++) dbmp_le->dn_agfree[i] = cpu_to_le64(bmp->db_agfree[i]); dbmp_le->dn_agsize = cpu_to_le64(bmp->db_agsize); dbmp_le->dn_maxfreebud = bmp->db_maxfreebud; /* write the buffer */ write_metapage(mp); /* * write out dirty pages of bmap */ filemap_write_and_wait(ipbmap->i_mapping); diWriteSpecial(ipbmap, 0); return (0); } /* * NAME: dbFree() * * FUNCTION: free the specified block range from the working block * allocation map. * * the blocks will be free from the working map one dmap * at a time. * * PARAMETERS: * ip - pointer to in-core inode; * blkno - starting block number to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) { struct metapage *mp; struct dmap *dp; int nb, rc; s64 lblkno, rem; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; struct super_block *sb = ipbmap->i_sb; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* block to be freed better be within the mapsize. */ if (unlikely((blkno == 0) || (blkno + nblocks > bmp->db_mapsize))) { IREAD_UNLOCK(ipbmap); printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(ip->i_sb, "block to be freed is outside the map\n"); return -EIO; } /** * TRIM the blocks, when mounted with discard option */ if (JFS_SBI(sb)->flag & JFS_DISCARD) if (JFS_SBI(sb)->minblks_trim <= nblocks) jfs_issue_discard(ipbmap, blkno, nblocks); /* * free the blocks a dmap at a time. */ mp = NULL; for (rem = nblocks; rem > 0; rem -= nb, blkno += nb) { /* release previous dmap if any */ if (mp) { write_metapage(mp); } /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* determine the number of blocks to be freed from * this dmap. */ nb = min(rem, BPERDMAP - (blkno & (BPERDMAP - 1))); /* free the blocks. */ if ((rc = dbFreeDmap(bmp, dp, blkno, nb))) { jfs_error(ip->i_sb, "error in block map\n"); release_metapage(mp); IREAD_UNLOCK(ipbmap); return (rc); } } /* write the last buffer. */ if (mp) write_metapage(mp); IREAD_UNLOCK(ipbmap); return (0); } /* * NAME: dbUpdatePMap() * * FUNCTION: update the allocation state (free or allocate) of the * specified block range in the persistent block allocation map. * * the blocks will be updated in the persistent map one * dmap at a time. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * free - 'true' if block range is to be freed from the persistent * map; 'false' if it is to be allocated. * blkno - starting block number of the range. * nblocks - number of contiguous blocks in the range. * tblk - transaction block; * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbUpdatePMap(struct inode *ipbmap, int free, s64 blkno, s64 nblocks, struct tblock * tblk) { int nblks, dbitno, wbitno, rbits; int word, nbits, nwords; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; s64 lblkno, rem, lastlblkno; u32 mask; struct dmap *dp; struct metapage *mp; struct jfs_log *log; int lsn, difft, diffp; unsigned long flags; /* the blocks better be within the mapsize. */ if (blkno + nblocks > bmp->db_mapsize) { printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(ipbmap->i_sb, "blocks are outside the map\n"); return -EIO; } /* compute delta of transaction lsn from log syncpt */ lsn = tblk->lsn; log = (struct jfs_log *) JFS_SBI(tblk->sb)->log; logdiff(difft, lsn, log); /* * update the block state a dmap at a time. */ mp = NULL; lastlblkno = 0; for (rem = nblocks; rem > 0; rem -= nblks, blkno += nblks) { /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); if (lblkno != lastlblkno) { if (mp) { write_metapage(mp); } mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; metapage_wait_for_io(mp); } dp = (struct dmap *) mp->data; /* determine the bit number and word within the dmap of * the starting block. also determine how many blocks * are to be updated within this dmap. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; nblks = min(rem, (s64)BPERDMAP - dbitno); /* update the bits of the dmap words. the first and last * words may only have a subset of their bits updated. if * this is the case, we'll work against that word (i.e. * partial first and/or last) only in a single pass. a * single pass will also be used to update all words that * are to have all their bits updated. */ for (rbits = nblks; rbits > 0; rbits -= nbits, dbitno += nbits) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nbits = min(rbits, DBWORD - wbitno); /* check if only part of the word is to be updated. */ if (nbits < DBWORD) { /* update (free or allocate) the bits * in this word. */ mask = (ONES << (DBWORD - nbits) >> wbitno); if (free) dp->pmap[word] &= cpu_to_le32(~mask); else dp->pmap[word] |= cpu_to_le32(mask); word += 1; } else { /* one or more words are to have all * their bits updated. determine how * many words and how many bits. */ nwords = rbits >> L2DBWORD; nbits = nwords << L2DBWORD; /* update (free or allocate) the bits * in these words. */ if (free) memset(&dp->pmap[word], 0, nwords * 4); else memset(&dp->pmap[word], (int) ONES, nwords * 4); word += nwords; } } /* * update dmap lsn */ if (lblkno == lastlblkno) continue; lastlblkno = lblkno; LOGSYNC_LOCK(log, flags); if (mp->lsn != 0) { /* inherit older/smaller lsn */ logdiff(diffp, mp->lsn, log); if (difft < diffp) { mp->lsn = lsn; /* move bp after tblock in logsync list */ list_move(&mp->synclist, &tblk->synclist); } /* inherit younger/larger clsn */ logdiff(difft, tblk->clsn, log); logdiff(diffp, mp->clsn, log); if (difft > diffp) mp->clsn = tblk->clsn; } else { mp->log = log; mp->lsn = lsn; /* insert bp after tblock in logsync list */ log->count++; list_add(&mp->synclist, &tblk->synclist); mp->clsn = tblk->clsn; } LOGSYNC_UNLOCK(log, flags); } /* write the last buffer. */ if (mp) { write_metapage(mp); } return (0); } /* * NAME: dbNextAG() * * FUNCTION: find the preferred allocation group for new allocations. * * Within the allocation groups, we maintain a preferred * allocation group which consists of a group with at least * average free space. It is the preferred group that we target * new inode allocation towards. The tie-in between inode * allocation and block allocation occurs as we allocate the * first (data) block of an inode and specify the inode (block) * as the allocation hint for this block. * * We try to avoid having more than one open file growing in * an allocation group, as this will lead to fragmentation. * This differs from the old OS/2 method of trying to keep * empty ags around for large allocations. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * the preferred allocation group number. */ int dbNextAG(struct inode *ipbmap) { s64 avgfree; int agpref; s64 hwm = 0; int i; int next_best = -1; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; BMAP_LOCK(bmp); /* determine the average number of free blocks within the ags. */ avgfree = (u32)bmp->db_nfree / bmp->db_numag; /* * if the current preferred ag does not have an active allocator * and has at least average freespace, return it */ agpref = bmp->db_agpref; if ((atomic_read(&bmp->db_active[agpref]) == 0) && (bmp->db_agfree[agpref] >= avgfree)) goto unlock; /* From the last preferred ag, find the next one with at least * average free space. */ for (i = 0 ; i < bmp->db_numag; i++, agpref++) { if (agpref >= bmp->db_numag) agpref = 0; if (atomic_read(&bmp->db_active[agpref])) /* open file is currently growing in this ag */ continue; if (bmp->db_agfree[agpref] >= avgfree) { /* Return this one */ bmp->db_agpref = agpref; goto unlock; } else if (bmp->db_agfree[agpref] > hwm) { /* Less than avg. freespace, but best so far */ hwm = bmp->db_agfree[agpref]; next_best = agpref; } } /* * If no inactive ag was found with average freespace, use the * next best */ if (next_best != -1) bmp->db_agpref = next_best; /* else leave db_agpref unchanged */ unlock: BMAP_UNLOCK(bmp); /* return the preferred group. */ return (bmp->db_agpref); } /* * NAME: dbAlloc() * * FUNCTION: attempt to allocate a specified number of contiguous free * blocks from the working allocation block map. * * the block allocation policy uses hints and a multi-step * approach. * * for allocation requests smaller than the number of blocks * per dmap, we first try to allocate the new blocks * immediately following the hint. if these blocks are not * available, we try to allocate blocks near the hint. if * no blocks near the hint are available, we next try to * allocate within the same dmap as contains the hint. * * if no blocks are available in the dmap or the allocation * request is larger than the dmap size, we try to allocate * within the same allocation group as contains the hint. if * this does not succeed, we finally try to allocate anywhere * within the aggregate. * * we also try to allocate anywhere within the aggregate * for allocation requests larger than the allocation group * size or requests that specify no hint value. * * PARAMETERS: * ip - pointer to in-core inode; * hint - allocation hint. * nblocks - number of contiguous blocks in the range. * results - on successful return, set to the starting block number * of the newly allocated contiguous range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) { int rc, agno; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp; struct metapage *mp; s64 lblkno, blkno; struct dmap *dp; int l2nb; s64 mapSize; int writers; /* assert that nblocks is valid */ assert(nblocks > 0); /* get the log2 number of blocks to be allocated. * if the number of blocks is not a log2 multiple, * it will be rounded up to the next log2 multiple. */ l2nb = BLKSTOL2(nblocks); bmp = JFS_SBI(ip->i_sb)->bmap; mapSize = bmp->db_mapsize; /* the hint should be within the map */ if (hint >= mapSize) { jfs_error(ip->i_sb, "the hint is outside the map\n"); return -EIO; } /* if the number of blocks to be allocated is greater than the * allocation group size, try to allocate anywhere. */ if (l2nb > bmp->db_agl2size) { IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); rc = dbAllocAny(bmp, nblocks, l2nb, results); goto write_unlock; } /* * If no hint, let dbNextAG recommend an allocation group */ if (hint == 0) goto pref_ag; /* we would like to allocate close to the hint. adjust the * hint to the block following the hint since the allocators * will start looking for free space starting at this point. */ blkno = hint + 1; if (blkno >= bmp->db_mapsize) goto pref_ag; agno = blkno >> bmp->db_agl2size; /* check if blkno crosses over into a new allocation group. * if so, check if we should allow allocations within this * allocation group. */ if ((blkno & (bmp->db_agsize - 1)) == 0) /* check if the AG is currently being written to. * if so, call dbNextAG() to find a non-busy * AG with sufficient free space. */ if (atomic_read(&bmp->db_active[agno])) goto pref_ag; /* check if the allocation request size can be satisfied from a * single dmap. if so, try to allocate from the dmap containing * the hint using a tiered strategy. */ if (nblocks <= BPERDMAP) { IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* get the buffer for the dmap containing the hint. */ rc = -EIO; lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) goto read_unlock; dp = (struct dmap *) mp->data; /* first, try to satisfy the allocation request with the * blocks beginning at the hint. */ if ((rc = dbAllocNext(bmp, dp, blkno, (int) nblocks)) != -ENOSPC) { if (rc == 0) { *results = blkno; mark_metapage_dirty(mp); } release_metapage(mp); goto read_unlock; } writers = atomic_read(&bmp->db_active[agno]); if ((writers > 1) || ((writers == 1) && (JFS_IP(ip)->active_ag != agno))) { /* * Someone else is writing in this allocation * group. To avoid fragmenting, try another ag */ release_metapage(mp); IREAD_UNLOCK(ipbmap); goto pref_ag; } /* next, try to satisfy the allocation request with blocks * near the hint. */ if ((rc = dbAllocNear(bmp, dp, blkno, (int) nblocks, l2nb, results)) != -ENOSPC) { if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); goto read_unlock; } /* try to satisfy the allocation request with blocks within * the same dmap as the hint. */ if ((rc = dbAllocDmapLev(bmp, dp, (int) nblocks, l2nb, results)) != -ENOSPC) { if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); goto read_unlock; } release_metapage(mp); IREAD_UNLOCK(ipbmap); } /* try to satisfy the allocation request with blocks within * the same allocation group as the hint. */ IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); if ((rc = dbAllocAG(bmp, agno, nblocks, l2nb, results)) != -ENOSPC) goto write_unlock; IWRITE_UNLOCK(ipbmap); pref_ag: /* * Let dbNextAG recommend a preferred allocation group */ agno = dbNextAG(ipbmap); IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); /* Try to allocate within this allocation group. if that fails, try to * allocate anywhere in the map. */ if ((rc = dbAllocAG(bmp, agno, nblocks, l2nb, results)) == -ENOSPC) rc = dbAllocAny(bmp, nblocks, l2nb, results); write_unlock: IWRITE_UNLOCK(ipbmap); return (rc); read_unlock: IREAD_UNLOCK(ipbmap); return (rc); } /* * NAME: dbReAlloc() * * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request * by first trying to extend the existing allocation in * place by allocating the additional blocks as the blocks * immediately following the current allocation. if these * blocks are not available, this routine will attempt to * allocate a new set of contiguous blocks large enough * to cover the existing allocation plus the additional * number of blocks required. * * PARAMETERS: * ip - pointer to in-core inode requiring allocation. * blkno - starting block of the current allocation. * nblocks - number of contiguous blocks within the current * allocation. * addnblocks - number of blocks to add to the allocation. * results - on successful return, set to the starting block number * of the existing allocation if the existing allocation * was extended in place or to a newly allocated contiguous * range if the existing allocation could not be extended * in place. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ int dbReAlloc(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks, s64 * results) { int rc; /* try to extend the allocation in place. */ if ((rc = dbExtend(ip, blkno, nblocks, addnblocks)) == 0) { *results = blkno; return (0); } else { if (rc != -ENOSPC) return (rc); } /* could not extend the allocation in place, so allocate a * new set of blocks for the entire request (i.e. try to get * a range of contiguous blocks large enough to cover the * existing allocation plus the additional blocks.) */ return (dbAlloc (ip, blkno + nblocks - 1, addnblocks + nblocks, results)); } /* * NAME: dbExtend() * * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request * by first trying to extend the existing allocation in * place by allocating the additional blocks as the blocks * immediately following the current allocation. * * PARAMETERS: * ip - pointer to in-core inode requiring allocation. * blkno - starting block of the current allocation. * nblocks - number of contiguous blocks within the current * allocation. * addnblocks - number of blocks to add to the allocation. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); s64 lblkno, lastblkno, extblkno; uint rel_block; struct metapage *mp; struct dmap *dp; int rc; struct inode *ipbmap = sbi->ipbmap; struct bmap *bmp; /* * We don't want a non-aligned extent to cross a page boundary */ if (((rel_block = blkno & (sbi->nbperpage - 1))) && (rel_block + nblocks + addnblocks > sbi->nbperpage)) return -ENOSPC; /* get the last block of the current allocation */ lastblkno = blkno + nblocks - 1; /* determine the block number of the block following * the existing allocation. */ extblkno = lastblkno + 1; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* better be within the file system */ bmp = sbi->bmap; if (lastblkno < 0 || lastblkno >= bmp->db_mapsize) { IREAD_UNLOCK(ipbmap); jfs_error(ip->i_sb, "the block is outside the filesystem\n"); return -EIO; } /* we'll attempt to extend the current allocation in place by * allocating the additional blocks as the blocks immediately * following the current allocation. we only try to extend the * current allocation in place if the number of additional blocks * can fit into a dmap, the last block of the current allocation * is not the last block of the file system, and the start of the * inplace extension is not on an allocation group boundary. */ if (addnblocks > BPERDMAP || extblkno >= bmp->db_mapsize || (extblkno & (bmp->db_agsize - 1)) == 0) { IREAD_UNLOCK(ipbmap); return -ENOSPC; } /* get the buffer for the dmap containing the first block * of the extension. */ lblkno = BLKTODMAP(extblkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* try to allocate the blocks immediately following the * current allocation. */ rc = dbAllocNext(bmp, dp, extblkno, (int) addnblocks); IREAD_UNLOCK(ipbmap); /* were we successful ? */ if (rc == 0) write_metapage(mp); else /* we were not successful */ release_metapage(mp); return (rc); } /* * NAME: dbAllocNext() * * FUNCTION: attempt to allocate the blocks of the specified block * range within a dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap. * blkno - starting block number of the range. * nblocks - number of contiguous free blocks of the range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw; int l2size; s8 *leaf; u32 mask; if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n"); return -EIO; } /* pick up a pointer to the leaves of the dmap tree. */ leaf = dp->tree.stree + le32_to_cpu(dp->tree.leafidx); /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* check if the specified block range is contained within * this dmap. */ if (dbitno + nblocks > BPERDMAP) return -ENOSPC; /* check if the starting leaf indicates that anything * is free. */ if (leaf[word] == NOFREE) return -ENOSPC; /* check the dmaps words corresponding to block range to see * if the block range is free. not all bits of the first and * last words may be contained within the block range. if this * is the case, we'll work against those words (i.e. partial first * and/or last) on an individual basis (a single pass) and examine * the actual bits to determine if they are free. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the leaves of the dmap * tree will be examined to determine if the blocks are free. a * single leaf may describe the free space of multiple dmap * words, so we may visit only a subset of the actual leaves * corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of the word is to be examined. */ if (nb < DBWORD) { /* check if the bits are free. */ mask = (ONES << (DBWORD - nb) >> wbitno); if ((mask & ~le32_to_cpu(dp->wmap[word])) != mask) return -ENOSPC; word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and how many bits. */ nwords = rembits >> L2DBWORD; nb = nwords << L2DBWORD; /* now examine the appropriate leaves to determine * if the blocks are free. */ while (nwords > 0) { /* does the leaf describe any free space ? */ if (leaf[word] < BUDMIN) return -ENOSPC; /* determine the l2 number of bits provided * by this leaf. */ l2size = min_t(int, leaf[word], NLSTOL2BSZ(nwords)); /* determine how many words were handled. */ nw = BUDSIZE(l2size, BUDMIN); nwords -= nw; word += nw; } } } /* allocate the blocks. */ return (dbAllocDmap(bmp, dp, blkno, nblocks)); } /* * NAME: dbAllocNear() * * FUNCTION: attempt to allocate a number of contiguous free blocks near * a specified block (hint) within a dmap. * * starting with the dmap leaf that covers the hint, we'll * check the next four contiguous leaves for sufficient free * space. if sufficient free space is found, we'll allocate * the desired free space. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap. * blkno - block number to allocate near. * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ static int dbAllocNear(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks, int l2nb, s64 * results) { int word, lword, rc; s8 *leaf; if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n"); return -EIO; } leaf = dp->tree.stree + le32_to_cpu(dp->tree.leafidx); /* determine the word within the dmap that holds the hint * (i.e. blkno). also, determine the last word in the dmap * that we'll include in our examination. */ word = (blkno & (BPERDMAP - 1)) >> L2DBWORD; lword = min(word + 4, LPERDMAP); /* examine the leaves for sufficient free space. */ for (; word < lword; word++) { /* does the leaf describe sufficient free space ? */ if (leaf[word] < l2nb) continue; /* determine the block number within the file system * of the first block described by this dmap word. */ blkno = le64_to_cpu(dp->start) + (word << L2DBWORD); /* if not all bits of the dmap word are free, get the * starting bit number within the dmap word of the required * string of free bits and adjust the block number with the * value. */ if (leaf[word] < BUDMIN) blkno += dbFindBits(le32_to_cpu(dp->wmap[word]), l2nb); /* allocate the blocks. */ if ((rc = dbAllocDmap(bmp, dp, blkno, nblocks)) == 0) *results = blkno; return (rc); } return -ENOSPC; } /* * NAME: dbAllocAG() * * FUNCTION: attempt to allocate the specified number of contiguous * free blocks within the specified allocation group. * * unless the allocation group size is equal to the number * of blocks per dmap, the dmap control pages will be used to * find the required free space, if available. we start the * search at the highest dmap control page level which * distinctly describes the allocation group's free space * (i.e. the highest level at which the allocation group's * free space is not mixed in with that of any other group). * in addition, we start the search within this level at a * height of the dmapctl dmtree at which the nodes distinctly * describe the allocation group's free space. at this height, * the allocation group's free space may be represented by 1 * or two sub-trees, depending on the allocation group size. * we search the top nodes of these subtrees left to right for * sufficient free space. if sufficient free space is found, * the subtree is searched to find the leftmost leaf that * has free space. once we have made it to the leaf, we * move the search to the next lower level dmap control page * corresponding to this leaf. we continue down the dmap control * pages until we find the dmap that contains or starts the * sufficient free space and we allocate at this dmap. * * if the allocation group size is equal to the dmap size, * we'll start at the dmap corresponding to the allocation * group and attempt the allocation at this level. * * the dmap control page search is also not performed if the * allocation group is completely free and we go to the first * dmap of the allocation group to do the allocation. this is * done because the allocation group may be part (not the first * part) of a larger binary buddy system, causing the dmap * control pages to indicate no free space (NOFREE) within * the allocation group. * * PARAMETERS: * bmp - pointer to bmap descriptor * agno - allocation group number. * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * note: IWRITE_LOCK(ipmap) held on entry/exit; */ static int dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) { struct metapage *mp; struct dmapctl *dcp; int rc, ti, i, k, m, n, agperlev; s64 blkno, lblkno; int budmin; /* allocation request should not be for more than the * allocation group size. */ if (l2nb > bmp->db_agl2size) { jfs_error(bmp->db_ipbmap->i_sb, "allocation request is larger than the allocation group size\n"); return -EIO; } /* determine the starting block number of the allocation * group. */ blkno = (s64) agno << bmp->db_agl2size; /* check if the allocation group size is the minimum allocation * group size or if the allocation group is completely free. if * the allocation group size is the minimum size of BPERDMAP (i.e. * 1 dmap), there is no need to search the dmap control page (below) * that fully describes the allocation group since the allocation * group is already fully described by a dmap. in this case, we * just call dbAllocCtl() to search the dmap tree and allocate the * required space if available. * * if the allocation group is completely free, dbAllocCtl() is * also called to allocate the required space. this is done for * two reasons. first, it makes no sense searching the dmap control * pages for free space when we know that free space exists. second, * the dmap control pages may indicate that the allocation group * has no free space if the allocation group is part (not the first * part) of a larger binary buddy system. */ if (bmp->db_agsize == BPERDMAP || bmp->db_agfree[agno] == bmp->db_agsize) { rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if ((rc == -ENOSPC) && (bmp->db_agfree[agno] == bmp->db_agsize)) { printk(KERN_ERR "blkno = %Lx, blocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(bmp->db_ipbmap->i_sb, "dbAllocCtl failed in free AG\n"); } return (rc); } /* the buffer for the dmap control page that fully describes the * allocation group. */ lblkno = BLKTOCTL(blkno, bmp->db_l2nbperpage, bmp->db_aglevel); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; budmin = dcp->budmin; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* search the subtree(s) of the dmap control page that describes * the allocation group, looking for sufficient free space. to begin, * determine how many allocation groups are represented in a dmap * control page at the control page level (i.e. L0, L1, L2) that * fully describes an allocation group. next, determine the starting * tree index of this allocation group within the control page. */ agperlev = (1 << (L2LPERCTL - (bmp->db_agheight << 1))) / bmp->db_agwidth; ti = bmp->db_agstart + bmp->db_agwidth * (agno & (agperlev - 1)); if (ti < 0 || ti >= le32_to_cpu(dcp->nleafs)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* dmap control page trees fan-out by 4 and a single allocation * group may be described by 1 or 2 subtrees within the ag level * dmap control page, depending upon the ag size. examine the ag's * subtrees for sufficient free space, starting with the leftmost * subtree. */ for (i = 0; i < bmp->db_agwidth; i++, ti++) { /* is there sufficient free space ? */ if (l2nb > dcp->stree[ti]) continue; /* sufficient free space found in a subtree. now search down * the subtree to find the leftmost leaf that describes this * free space. */ for (k = bmp->db_agheight; k > 0; k--) { for (n = 0, m = (ti << 2) + 1; n < 4; n++) { if (l2nb <= dcp->stree[m + n]) { ti = m + n; break; } } if (n == 4) { jfs_error(bmp->db_ipbmap->i_sb, "failed descending stree\n"); release_metapage(mp); return -EIO; } } /* determine the block number within the file system * that corresponds to this leaf. */ if (bmp->db_aglevel == 2) blkno = 0; else if (bmp->db_aglevel == 1) blkno &= ~(MAXL1SIZE - 1); else /* bmp->db_aglevel == 0 */ blkno &= ~(MAXL0SIZE - 1); blkno += ((s64) (ti - le32_to_cpu(dcp->leafidx))) << budmin; /* release the buffer in preparation for going down * the next level of dmap control pages. */ release_metapage(mp); /* check if we need to continue to search down the lower * level dmap control pages. we need to if the number of * blocks required is less than maximum number of blocks * described at the next lower level. */ if (l2nb < budmin) { /* search the lower level dmap control pages to get * the starting block number of the dmap that * contains or starts off the free space. */ if ((rc = dbFindCtl(bmp, l2nb, bmp->db_aglevel - 1, &blkno))) { if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "control page inconsistent\n"); return -EIO; } return (rc); } } /* allocate the blocks. */ rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "unable to allocate blocks\n"); rc = -EIO; } return (rc); } /* no space in the allocation group. release the buffer and * return -ENOSPC. */ release_metapage(mp); return -ENOSPC; } /* * NAME: dbAllocAny() * * FUNCTION: attempt to allocate the specified number of contiguous * free blocks anywhere in the file system. * * dbAllocAny() attempts to find the sufficient free space by * searching down the dmap control pages, starting with the * highest level (i.e. L0, L1, L2) control page. if free space * large enough to satisfy the desired free space is found, the * desired free space is allocated. * * PARAMETERS: * bmp - pointer to bmap descriptor * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results) { int rc; s64 blkno = 0; /* starting with the top level dmap control page, search * down the dmap control levels for sufficient free space. * if free space is found, dbFindCtl() returns the starting * block number of the dmap that contains or starts off the * range of free space. */ if ((rc = dbFindCtl(bmp, l2nb, bmp->db_maxlevel, &blkno))) return (rc); /* allocate the blocks. */ rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "unable to allocate blocks\n"); return -EIO; } return (rc); } /* * NAME: dbDiscardAG() * * FUNCTION: attempt to discard (TRIM) all free blocks of specific AG * * algorithm: * 1) allocate blocks, as large as possible and save them * while holding IWRITE_LOCK on ipbmap * 2) trim all these saved block/length values * 3) mark the blocks free again * * benefit: * - we work only on one ag at some time, minimizing how long we * need to lock ipbmap * - reading / writing the fs is possible most time, even on * trimming * * downside: * - we write two times to the dmapctl and dmap pages * - but for me, this seems the best way, better ideas? * /TR 2012 * * PARAMETERS: * ip - pointer to in-core inode * agno - ag to trim * minlen - minimum value of contiguous blocks * * RETURN VALUES: * s64 - actual number of blocks trimmed */ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) { struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; s64 nblocks, blkno; u64 trimmed = 0; int rc, l2nb; struct super_block *sb = ipbmap->i_sb; struct range2trim { u64 blkno; u64 nblocks; } *totrim, *tt; /* max blkno / nblocks pairs to trim */ int count = 0, range_cnt; u64 max_ranges; /* prevent others from writing new stuff here, while trimming */ IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); nblocks = bmp->db_agfree[agno]; max_ranges = nblocks; do_div(max_ranges, minlen); range_cnt = min_t(u64, max_ranges + 1, 32 * 1024); totrim = kmalloc_array(range_cnt, sizeof(struct range2trim), GFP_NOFS); if (totrim == NULL) { jfs_error(bmp->db_ipbmap->i_sb, "no memory for trim array\n"); IWRITE_UNLOCK(ipbmap); return 0; } tt = totrim; while (nblocks >= minlen) { l2nb = BLKSTOL2(nblocks); /* 0 = okay, -EIO = fatal, -ENOSPC -> try smaller block */ rc = dbAllocAG(bmp, agno, nblocks, l2nb, &blkno); if (rc == 0) { tt->blkno = blkno; tt->nblocks = nblocks; tt++; count++; /* the whole ag is free, trim now */ if (bmp->db_agfree[agno] == 0) break; /* give a hint for the next while */ nblocks = bmp->db_agfree[agno]; continue; } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; if (unlikely(l2nb < 0)) break; nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n"); break; } /* check, if our trim array is full */ if (unlikely(count >= range_cnt - 1)) break; } IWRITE_UNLOCK(ipbmap); tt->nblocks = 0; /* mark the current end */ for (tt = totrim; tt->nblocks != 0; tt++) { /* when mounted with online discard, dbFree() will * call jfs_issue_discard() itself */ if (!(JFS_SBI(sb)->flag & JFS_DISCARD)) jfs_issue_discard(ip, tt->blkno, tt->nblocks); dbFree(ip, tt->blkno, tt->nblocks); trimmed += tt->nblocks; } kfree(totrim); return trimmed; } /* * NAME: dbFindCtl() * * FUNCTION: starting at a specified dmap control page level and block * number, search down the dmap control levels for a range of * contiguous free blocks large enough to satisfy an allocation * request for the specified number of free blocks. * * if sufficient contiguous free blocks are found, this routine * returns the starting block number within a dmap page that * contains or starts a range of contiqious free blocks that * is sufficient in size. * * PARAMETERS: * bmp - pointer to bmap descriptor * level - starting dmap control page level. * l2nb - log2 number of contiguous free blocks desired. * *blkno - on entry, starting block number for conducting the search. * on successful return, the first block within a dmap page * that contains or starts a range of contiguous free blocks. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) { int rc, leafidx, lev; s64 b, lblkno; struct dmapctl *dcp; int budmin; struct metapage *mp; /* starting at the specified dmap control page level and block * number, search down the dmap control levels for the starting * block number of a dmap page that contains or starts off * sufficient free blocks. */ for (lev = level, b = *blkno; lev >= 0; lev--) { /* get the buffer of the dmap control page for the block * number and level (i.e. L0, L1, L2). */ lblkno = BLKTOCTL(b, bmp->db_l2nbperpage, lev); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; budmin = dcp->budmin; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* search the tree within the dmap control page for * sufficient free space. if sufficient free space is found, * dbFindLeaf() returns the index of the leaf at which * free space was found. */ rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ release_metapage(mp); /* space found ? */ if (rc) { if (lev != level) { jfs_error(bmp->db_ipbmap->i_sb, "dmap inconsistent\n"); return -EIO; } return -ENOSPC; } /* adjust the block number to reflect the location within * the dmap control page (i.e. the leaf) at which free * space was found. */ b += (((s64) leafidx) << budmin); /* we stop the search at this dmap control page level if * the number of blocks required is greater than or equal * to the maximum number of blocks described at the next * (lower) level. */ if (l2nb >= budmin) break; } *blkno = b; return (0); } /* * NAME: dbAllocCtl() * * FUNCTION: attempt to allocate a specified number of contiguous * blocks starting within a specific dmap. * * this routine is called by higher level routines that search * the dmap control pages above the actual dmaps for contiguous * free space. the result of successful searches by these * routines are the starting block numbers within dmaps, with * the dmaps themselves containing the desired contiguous free * space or starting a contiguous free space of desired size * that is made up of the blocks of one or more dmaps. these * calls should not fail due to insufficent resources. * * this routine is called in some cases where it is not known * whether it will fail due to insufficient resources. more * specifically, this occurs when allocating from an allocation * group whose size is equal to the number of blocks per dmap. * in this case, the dmap control pages are not examined prior * to calling this routine (to save pathlength) and the call * might fail. * * for a request size that fits within a dmap, this routine relies * upon the dmap's dmtree to find the requested contiguous free * space. for request sizes that are larger than a dmap, the * requested free space will start at the first block of the * first dmap (i.e. blkno). * * PARAMETERS: * bmp - pointer to bmap descriptor * nblocks - actual number of contiguous free blocks to allocate. * l2nb - log2 number of contiguous free blocks to allocate. * blkno - starting block number of the dmap to start the allocation * from. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) { int rc, nb; s64 b, lblkno, n; struct metapage *mp; struct dmap *dp; /* check if the allocation request is confined to a single dmap. */ if (l2nb <= L2BPERDMAP) { /* get the buffer for the dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dp = (struct dmap *) mp->data; if (dp->tree.budmin < 0) { release_metapage(mp); return -EIO; } /* try to allocate the blocks. */ rc = dbAllocDmapLev(bmp, dp, (int) nblocks, l2nb, results); if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); return (rc); } /* allocation request involving multiple dmaps. it must start on * a dmap boundary. */ assert((blkno & (BPERDMAP - 1)) == 0); /* allocate the blocks dmap by dmap. */ for (n = nblocks, b = blkno; n > 0; n -= nb, b += nb) { /* get the buffer for the dmap. */ lblkno = BLKTODMAP(b, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { rc = -EIO; goto backout; } dp = (struct dmap *) mp->data; /* the dmap better be all free. */ if (dp->tree.stree[ROOT] != L2BPERDMAP) { release_metapage(mp); jfs_error(bmp->db_ipbmap->i_sb, "the dmap is not all free\n"); rc = -EIO; goto backout; } /* determine how many blocks to allocate from this dmap. */ nb = min_t(s64, n, BPERDMAP); /* allocate the blocks from the dmap. */ if ((rc = dbAllocDmap(bmp, dp, b, nb))) { release_metapage(mp); goto backout; } /* write the buffer. */ write_metapage(mp); } /* set the results (starting block number) and return. */ *results = blkno; return (0); /* something failed in handling an allocation request involving * multiple dmaps. we'll try to clean up by backing out any * allocation that has already happened for this request. if * we fail in backing out the allocation, we'll mark the file * system to indicate that blocks have been leaked. */ backout: /* try to backout the allocations dmap by dmap. */ for (n = nblocks - n, b = blkno; n > 0; n -= BPERDMAP, b += BPERDMAP) { /* get the buffer for this dmap. */ lblkno = BLKTODMAP(b, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { /* could not back out. mark the file system * to indicate that we have leaked blocks. */ jfs_error(bmp->db_ipbmap->i_sb, "I/O Error: Block Leakage\n"); continue; } dp = (struct dmap *) mp->data; /* free the blocks is this dmap. */ if (dbFreeDmap(bmp, dp, b, BPERDMAP)) { /* could not back out. mark the file system * to indicate that we have leaked blocks. */ release_metapage(mp); jfs_error(bmp->db_ipbmap->i_sb, "Block Leakage\n"); continue; } /* write the buffer. */ write_metapage(mp); } return (rc); } /* * NAME: dbAllocDmapLev() * * FUNCTION: attempt to allocate a specified number of contiguous blocks * from a specified dmap. * * this routine checks if the contiguous blocks are available. * if so, nblocks of blocks are allocated; otherwise, ENOSPC is * returned. * * PARAMETERS: * mp - pointer to bmap descriptor * dp - pointer to dmap to attempt to allocate blocks from. * l2nb - log2 number of contiguous block desired. * nblocks - actual number of contiguous block desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap), e.g., from dbAlloc(), or * IWRITE_LOCK(ipbmap), e.g., dbAllocCtl(), held on entry/exit; */ static int dbAllocDmapLev(struct bmap * bmp, struct dmap * dp, int nblocks, int l2nb, s64 * results) { s64 blkno; int leafidx, rc; /* can't be more than a dmaps worth of blocks */ assert(l2nb <= L2BPERDMAP); /* search the tree within the dmap page for sufficient * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; if (leafidx < 0) return -EIO; /* determine the block number within the file system corresponding * to the leaf at which free space was found. */ blkno = le64_to_cpu(dp->start) + (leafidx << L2DBWORD); /* if not all bits of the dmap word are free, get the starting * bit number within the dmap word of the required string of free * bits and adjust the block number with this value. */ if (dp->tree.stree[leafidx + LEAFIND] < BUDMIN) blkno += dbFindBits(le32_to_cpu(dp->wmap[leafidx]), l2nb); /* allocate the blocks */ if ((rc = dbAllocDmap(bmp, dp, blkno, nblocks)) == 0) *results = blkno; return (rc); } /* * NAME: dbAllocDmap() * * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine allocates the specified blocks from the dmap * through a call to dbAllocBits(). if the allocation of the * block range causes the maximum string of free blocks within * the dmap to change (i.e. the value of the root of the dmap's * dmtree), this routine will cause this change to be reflected * up through the appropriate levels of the dmap control pages * by a call to dbAdjCtl() for the L0 dmap control page that * covers this dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to allocate the block range from. * blkno - starting block number of the block to be allocated. * nblocks - number of blocks to be allocated. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { s8 oldroot; int rc; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = dp->tree.stree[ROOT]; /* allocate the specified (blocks) bits */ dbAllocBits(bmp, dp, blkno, nblocks); /* if the root has not changed, done. */ if (dp->tree.stree[ROOT] == oldroot) return (0); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the bit allocation (thus making everything consistent). */ if ((rc = dbAdjCtl(bmp, blkno, dp->tree.stree[ROOT], 1, 0))) dbFreeBits(bmp, dp, blkno, nblocks); return (rc); } /* * NAME: dbFreeDmap() * * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine frees the specified blocks from the dmap through * a call to dbFreeBits(). if the deallocation of the block range * causes the maximum string of free blocks within the dmap to * change (i.e. the value of the root of the dmap's dmtree), this * routine will cause this change to be reflected up through the * appropriate levels of the dmap control pages by a call to * dbAdjCtl() for the L0 dmap control page that covers this dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to free the block range from. * blkno - starting block number of the block to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { s8 oldroot; int rc = 0, word; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = dp->tree.stree[ROOT]; /* free the specified (blocks) bits */ rc = dbFreeBits(bmp, dp, blkno, nblocks); /* if error or the root has not changed, done. */ if (rc || (dp->tree.stree[ROOT] == oldroot)) return (rc); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the deallocation. */ if ((rc = dbAdjCtl(bmp, blkno, dp->tree.stree[ROOT], 0, 0))) { word = (blkno & (BPERDMAP - 1)) >> L2DBWORD; /* as part of backing out the deallocation, we will have * to back split the dmap tree if the deallocation caused * the freed blocks to become part of a larger binary buddy * system. */ if (dp->tree.stree[word] == NOFREE) dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } return (rc); } /* * NAME: dbAllocBits() * * FUNCTION: allocate a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly * updates the bits of the working map and causes the adjustment * of the binary buddy system described by the dmap's dmtree * leaves to reflect the bits allocated. it also causes the * dmap's dmtree, as a whole, to reflect the allocated range. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to allocate bits from. * blkno - starting block number of the bits to be allocated. * nblocks - number of bits to be allocated. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw, agno; dmtree_t *tp = (dmtree_t *) & dp->tree; int size; s8 *leaf; /* pick up a pointer to the leaves of the dmap tree */ leaf = dp->tree.stree + LEAFIND; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap */ assert(dbitno + nblocks <= BPERDMAP); /* allocate the bits of the dmap's words corresponding to the block * range. not all bits of the first and last words may be contained * within the block range. if this is the case, we'll work against * those words (i.e. partial first and/or last) on an individual basis * (a single pass), allocating the bits of interest by hand and * updating the leaf corresponding to the dmap word. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the bits of all fully contained * dmap words will be marked as free in a single shot and the leaves * will be updated. a single leaf may describe the free space of * multiple dmap words, so we may update only a subset of the actual * leaves corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be allocated. */ if (nb < DBWORD) { /* allocate (set to 1) the appropriate bits within * this dmap word. */ dp->wmap[word] |= cpu_to_le32(ONES << (DBWORD - nb) >> wbitno); /* update the leaf for this dmap word. in addition * to setting the leaf value to the binary buddy max * of the updated dmap word, dbSplit() will split * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and allocate (set to 1) the bits of these * words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], (int) ONES, nwords * 4); /* determine how many bits. */ nb = nwords << L2DBWORD; /* now update the appropriate leaves to reflect * the allocated words. */ for (; nwords > 0; nwords -= nw) { if (leaf[word] < BUDMIN) { jfs_error(bmp->db_ipbmap->i_sb, "leaf page corrupt\n"); break; } /* determine what the leaf value should be * updated to as the minimum of the l2 number * of bits being allocated and the l2 number * of bits currently described by this leaf. */ size = min_t(int, leaf[word], NLSTOL2BSZ(nwords)); /* update the leaf to reflect the allocation. * in addition to setting the leaf value to * NOFREE, dbSplit() will split the binary * system of the leaves to reflect the current * allocation (size). */ dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); word += nw; } } } /* update the free count for this dmap */ le32_add_cpu(&dp->nfree, -nblocks); BMAP_LOCK(bmp); /* if this allocation group is completely free, * update the maximum allocation group number if this allocation * group is the new max. */ agno = blkno >> bmp->db_agl2size; if (agno > bmp->db_maxag) bmp->db_maxag = agno; /* update the free count for the allocation group and map */ bmp->db_agfree[agno] -= nblocks; bmp->db_nfree -= nblocks; BMAP_UNLOCK(bmp); } /* * NAME: dbFreeBits() * * FUNCTION: free a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly * updates the bits of the working map and causes the adjustment * of the binary buddy system described by the dmap's dmtree * leaves to reflect the bits freed. it also causes the dmap's * dmtree, as a whole, to reflect the deallocated range. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to free bits from. * blkno - starting block number of the bits to be freed. * nblocks - number of bits to be freed. * * RETURN VALUES: 0 for success * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw, agno; dmtree_t *tp = (dmtree_t *) & dp->tree; int rc = 0; int size; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap. */ assert(dbitno + nblocks <= BPERDMAP); /* free the bits of the dmaps words corresponding to the block range. * not all bits of the first and last words may be contained within * the block range. if this is the case, we'll work against those * words (i.e. partial first and/or last) on an individual basis * (a single pass), freeing the bits of interest by hand and updating * the leaf corresponding to the dmap word. a single pass will be used * for all dmap words fully contained within the specified range. * within this pass, the bits of all fully contained dmap words will * be marked as free in a single shot and the leaves will be updated. a * single leaf may describe the free space of multiple dmap words, * so we may update only a subset of the actual leaves corresponding * to the dmap words of the block range. * * dbJoin() is used to update leaf values and will join the binary * buddy system of the leaves if the new leaf values indicate this * should be done. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be freed. */ if (nb < DBWORD) { /* free (zero) the appropriate bits within this * dmap word. */ dp->wmap[word] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> wbitno)); /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and free (zero) the bits of these words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], 0, nwords * 4); /* determine how many bits. */ nb = nwords << L2DBWORD; /* now update the appropriate leaves to reflect * the freed words. */ for (; nwords > 0; nwords -= nw) { /* determine what the leaf value should be * updated to as the minimum of the l2 number * of bits being freed and the l2 (max) number * of bits that can be described by this leaf. */ size = min(LITOL2BSZ (word, L2LPERDMAP, BUDMIN), NLSTOL2BSZ(nwords)); /* update the leaf. */ rc = dbJoin(tp, word, size, false); if (rc) return rc; /* get the number of dmap words handled. */ nw = BUDSIZE(size, BUDMIN); word += nw; } } } /* update the free count for this dmap. */ le32_add_cpu(&dp->nfree, nblocks); BMAP_LOCK(bmp); /* update the free count for the allocation group and * map. */ agno = blkno >> bmp->db_agl2size; bmp->db_nfree += nblocks; bmp->db_agfree[agno] += nblocks; /* check if this allocation group is not completely free and * if it is currently the maximum (rightmost) allocation group. * if so, establish the new maximum allocation group number by * searching left for the first allocation group with allocation. */ if ((bmp->db_agfree[agno] == bmp->db_agsize && agno == bmp->db_maxag) || (agno == bmp->db_numag - 1 && bmp->db_agfree[agno] == (bmp-> db_mapsize & (BPERDMAP - 1)))) { while (bmp->db_maxag > 0) { bmp->db_maxag -= 1; if (bmp->db_agfree[bmp->db_maxag] != bmp->db_agsize) break; } /* re-establish the allocation group preference if the * current preference is right of the maximum allocation * group. */ if (bmp->db_agpref > bmp->db_maxag) bmp->db_agpref = bmp->db_maxag; } BMAP_UNLOCK(bmp); return 0; } /* * NAME: dbAdjCtl() * * FUNCTION: adjust a dmap control page at a specified level to reflect * the change in a lower level dmap or dmap control page's * maximum string of free blocks (i.e. a change in the root * of the lower level object's dmtree) due to the allocation * or deallocation of a range of blocks with a single dmap. * * on entry, this routine is provided with the new value of * the lower level dmap or dmap control page root and the * starting block number of the block range whose allocation * or deallocation resulted in the root change. this range * is respresented by a single leaf of the current dmapctl * and the leaf will be updated with this value, possibly * causing a binary buddy system within the leaves to be * split or joined. the update may also cause the dmapctl's * dmtree to be updated. * * if the adjustment of the dmap control page, itself, causes its * root to change, this change will be bubbled up to the next dmap * control level by a recursive call to this routine, specifying * the new root value and the next dmap control page level to * be adjusted. * PARAMETERS: * bmp - pointer to bmap descriptor * blkno - the first block of a block range within a dmap. it is * the allocation or deallocation of this block range that * requires the dmap control page to be adjusted. * newval - the new value of the lower level dmap or dmap control * page root. * alloc - 'true' if adjustment is due to an allocation. * level - current level of dmap control page (i.e. L0, L1, L2) to * be adjusted. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) { struct metapage *mp; s8 oldroot; int oldval; s64 lblkno; struct dmapctl *dcp; int rc, leafno, ti; /* get the buffer for the dmap control page for the specified * block number and control page level. */ lblkno = BLKTOCTL(blkno, bmp->db_l2nbperpage, level); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* determine the leaf number corresponding to the block and * the index within the dmap control tree. */ leafno = BLKTOCTLLEAF(blkno, dcp->budmin); ti = leafno + le32_to_cpu(dcp->leafidx); /* save the current leaf value and the current root level (i.e. * maximum l2 free string described by this dmapctl). */ oldval = dcp->stree[ti]; oldroot = dcp->stree[ROOT]; /* check if this is a control page update for an allocation. * if so, update the leaf to reflect the new leaf value using * dbSplit(); otherwise (deallocation), use dbJoin() to update * the leaf with the new value. in addition to updating the * leaf, dbSplit() will also split the binary buddy system of * the leaves, if required, and bubble new values within the * dmapctl tree, if required. similarly, dbJoin() will join * the binary buddy system of leaves and bubble new values up * the dmapctl tree as required by the new leaf value. */ if (alloc) { /* check if we are in the middle of a binary buddy * system. this happens when we are performing the * first allocation out of an allocation group that * is part (not the first part) of a larger binary * buddy system. if we are in the middle, back split * the system prior to calling dbSplit() which assumes * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) { release_metapage(mp); return rc; } oldval = dcp->stree[ti]; } dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) { release_metapage(mp); return rc; } } /* check if the root of the current dmap control page changed due * to the update and if the current dmap control page is not at * the current top level (i.e. L0, L1, L2) of the map. if so (i.e. * root changed and this is not the top level), call this routine * again (recursion) for the next higher level of the mapping to * reflect the change in root for the current dmap control page. */ if (dcp->stree[ROOT] != oldroot) { /* are we below the top level of the map. if so, * bubble the root up to the next higher level. */ if (level < bmp->db_maxlevel) { /* bubble up the new root of this dmap control page to * the next level. */ if ((rc = dbAdjCtl(bmp, blkno, dcp->stree[ROOT], alloc, level + 1))) { /* something went wrong in bubbling up the new * root value, so backout the changes to the * current dmap control page. */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system * to form and we may now be in the * middle of it. if this is the case, * back split the buddies. */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, oldval, true); } /* release the buffer and return the error. */ release_metapage(mp); return (rc); } } else { /* we're at the top level of the map. update * the bmap control page to reflect the size * of the maximum free buddy system. */ assert(level == bmp->db_maxlevel); if (bmp->db_maxfreebud != oldroot) { jfs_error(bmp->db_ipbmap->i_sb, "the maximum free buddy is not the old root\n"); } bmp->db_maxfreebud = dcp->stree[ROOT]; } } /* write the buffer. */ write_metapage(mp); return (0); } /* * NAME: dbSplit() * * FUNCTION: update the leaf of a dmtree with a new value, splitting * the leaf from the binary buddy system of the dmtree's * leaves, as required. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * splitsz - the size the binary buddy system starting at the leaf * must be split to, specified as the log2 number of blocks. * newval - the new value for the leaf. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; s8 *leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* check if the leaf needs to be split. */ if (leaf[leafno] > tp->dmt_budmin) { /* the split occurs by cutting the buddy system in half * at the specified leaf until we reach the specified * size. pick up the starting split size (current size * - 1 in l2) and the corresponding buddy size. */ cursz = leaf[leafno] - 1; budsz = BUDSIZE(cursz, tp->dmt_budmin); /* split until we reach the specified size. */ while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ cursz -= 1; budsz >>= 1; } } /* adjust the dmap tree to reflect the specified leaf's new * value. */ dbAdjTree(tp, leafno, newval, is_ctl); } /* * NAME: dbBackSplit() * * FUNCTION: back split the binary buddy system of dmtree leaves * that hold a specified leaf until the specified leaf * starts its own binary buddy system. * * the allocators typically perform allocations at the start * of binary buddy systems and dbSplit() is used to accomplish * any required splits. in some cases, however, allocation * may occur in the middle of a binary system and requires a * back split, with the split proceeding out from the middle of * the system (less efficient) rather than the start of the * system (more efficient). the cases in which a back split * is required are rare and are limited to the first allocation * within an allocation group which is a part (not first part) * of a larger binary buddy system and a few exception cases * in which a previous join operation must be backed out. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; s8 *leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* leaf should be part (not first part) of a binary * buddy system. */ assert(leaf[leafno] == NOFREE); /* the back split is accomplished by iteratively finding the leaf * that starts the buddy system that contains the specified leaf and * splitting that system in two. this iteration continues until * the specified leaf becomes the start of a buddy system. * * determine maximum possible l2 size for the specified leaf. */ size = LITOL2BSZ(leafno, le32_to_cpu(tp->dmt_l2nleafs), tp->dmt_budmin); /* determine the number of leaves covered by this size. this * is the buddy size that we will start with as we search for * the buddy system that contains the specified leaf. */ budsz = BUDSIZE(size, tp->dmt_budmin); /* back split. */ while (leaf[leafno] == NOFREE) { /* find the leftmost buddy leaf. */ for (w = leafno, bsz = budsz;; bsz <<= 1, w = (w < bud) ? w : bud) { if (bsz >= le32_to_cpu(tp->dmt_nleafs)) { jfs_err("JFS: block map error in dbBackSplit"); return -EIO; } /* determine the buddy. */ bud = w ^ bsz; /* check if this buddy is the start of the system. */ if (leaf[bud] != NOFREE) { /* split the leaf at the start of the * system in two. */ cursz = leaf[bud] - 1; dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } } if (leaf[leafno] != size) { jfs_err("JFS: wrong leaf value in dbBackSplit"); return -EIO; } return 0; } /* * NAME: dbJoin() * * FUNCTION: update the leaf of a dmtree with a new value, joining * the leaf with other leaves of the dmtree into a multi-leaf * binary buddy system, as required. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * newval - the new value for the leaf. * * RETURN VALUES: none */ static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; /* can the new leaf value require a join with other leaves ? */ if (newval >= tp->dmt_budmin) { /* pickup a pointer to the leaves of the tree. */ leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* try to join the specified leaf into a large binary * buddy system. the join proceeds by attempting to join * the specified leafno with its buddy (leaf) at new value. * if the join occurs, we attempt to join the left leaf * of the joined buddies with its buddy at new value + 1. * we continue to join until we find a buddy that cannot be * joined (does not have a value equal to the size of the * last join) or until all leaves have been joined into a * single system. * * get the buddy size (number of words covered) of * the new value. */ budsz = BUDSIZE(newval, tp->dmt_budmin); /* try to join. */ while (budsz < le32_to_cpu(tp->dmt_nleafs)) { /* get the buddy leaf. */ buddy = leafno ^ budsz; /* if the leaf's new value is greater than its * buddy's value, we join no more. */ if (newval > leaf[buddy]) break; /* It shouldn't be less */ if (newval < leaf[buddy]) return -EIO; /* check which (leafno or buddy) is the left buddy. * the left buddy gets to claim the blocks resulting * from the join while the right gets to claim none. * the left buddy is also eligible to participate in * a join at the next higher level while the right * is not. * */ if (leafno < buddy) { /* leafno is the left buddy. */ dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } /* on to try the next join. */ newval += 1; budsz <<= 1; } } /* update the leaf value. */ dbAdjTree(tp, leafno, newval, is_ctl); return 0; } /* * NAME: dbAdjTree() * * FUNCTION: update a leaf of a dmtree with a new value, adjusting * the dmtree, as required, to reflect the new leaf value. * the combination of any buddies must already be done before * this is called. * * PARAMETERS: * tp - pointer to the tree to be adjusted. * leafno - the number of the leaf to be updated. * newval - the new value for the leaf. * * RETURN VALUES: none */ static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; int max, size; size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); if (WARN_ON_ONCE(lp >= size || lp < 0)) return; /* is the current value the same as the old value ? if so, * there is nothing to do. */ if (tp->dmt_stree[lp] == newval) return; /* set the new value. */ tp->dmt_stree[lp] = newval; /* bubble the new value up the tree as required. */ for (k = 0; k < le32_to_cpu(tp->dmt_height); k++) { if (lp == 0) break; /* get the index of the first leaf of the 4 leaf * group containing the specified leaf (leafno). */ lp = ((lp - 1) & ~0x03) + 1; /* get the index of the parent of this 4 leaf group. */ pp = (lp - 1) >> 2; /* determine the maximum of the 4 leaves. */ max = TREEMAX(&tp->dmt_stree[lp]); /* if the maximum of the 4 is the same as the * parent's value, we're done. */ if (tp->dmt_stree[pp] == max) break; /* parent gets new value. */ tp->dmt_stree[pp] = max; /* parent becomes leaf for next go-round. */ lp = pp; } } /* * NAME: dbFindLeaf() * * FUNCTION: search a dmtree_t for sufficient free blocks, returning * the index of a leaf describing the free blocks if * sufficient free blocks are found. * * the search starts at the top of the dmtree_t tree and * proceeds down the tree to the leftmost leaf with sufficient * free space. * * PARAMETERS: * tp - pointer to the tree to be searched. * l2nb - log2 number of free blocks to search for. * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; int max_size, max_idx; max_size = is_ctl ? CTLTREESIZE : TREESIZE; max_idx = is_ctl ? LPERCTL : LPERDMAP; /* first check the root of the tree to see if there is * sufficient free space. */ if (l2nb > tp->dmt_stree[ROOT]) return -ENOSPC; /* sufficient free space available. now search down the tree * starting at the next level for the leftmost leaf that * describes sufficient free space. */ for (k = le32_to_cpu(tp->dmt_height), ti = 1; k > 0; k--, ti = ((ti + n) << 2) + 1) { /* search the four nodes at this level, starting from * the left. */ for (x = ti, n = 0; n < 4; n++) { /* sufficient free space found. move to the next * level (or quit if this is the last level). */ if (x + n > max_size) return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } /* better have found something since the higher * levels of the tree said it was here. */ assert(n < 4); } if (le32_to_cpu(tp->dmt_leafidx) >= max_idx) return -ENOSPC; /* set the return to the leftmost leaf describing sufficient * free space. */ *leafidx = x + n - le32_to_cpu(tp->dmt_leafidx); return (0); } /* * NAME: dbFindBits() * * FUNCTION: find a specified number of binary buddy free bits within a * dmap bitmap word value. * * this routine searches the bitmap value for (1 << l2nb) free * bits at (1 << l2nb) alignments within the value. * * PARAMETERS: * word - dmap bitmap word value. * l2nb - number of free bits specified as a log2 number. * * RETURN VALUES: * starting bit number of free bits. */ static int dbFindBits(u32 word, int l2nb) { int bitno, nb; u32 mask; /* get the number of bits. */ nb = 1 << l2nb; assert(nb <= DBWORD); /* complement the word so we can use a mask (i.e. 0s represent * free bits) and compute the mask. */ word = ~word; mask = ONES << (DBWORD - nb); /* scan the word for nb free bits at nb alignments. */ for (bitno = 0; mask != 0; bitno += nb, mask = (mask >> nb)) { if ((mask & word) == mask) break; } ASSERT(bitno < 32); /* return the bit number. */ return (bitno); } /* * NAME: dbMaxBud(u8 *cp) * * FUNCTION: determine the largest binary buddy string of free * bits within 32-bits of the map. * * PARAMETERS: * cp - pointer to the 32-bit value. * * RETURN VALUES: * largest binary buddy of free bits within a dmap word. */ static int dbMaxBud(u8 * cp) { signed char tmp1, tmp2; /* check if the wmap word is all free. if so, the * free buddy size is BUDMIN. */ if (*((uint *) cp) == 0) return (BUDMIN); /* check if the wmap word is half free. if so, the * free buddy size is BUDMIN-1. */ if (*((u16 *) cp) == 0 || *((u16 *) cp + 1) == 0) return (BUDMIN - 1); /* not all free or half free. determine the free buddy * size thru table lookup using quarters of the wmap word. */ tmp1 = max(budtab[cp[2]], budtab[cp[3]]); tmp2 = max(budtab[cp[0]], budtab[cp[1]]); return (max(tmp1, tmp2)); } /* * NAME: cnttz(uint word) * * FUNCTION: determine the number of trailing zeros within a 32-bit * value. * * PARAMETERS: * value - 32-bit value to be examined. * * RETURN VALUES: * count of trailing zeros */ static int cnttz(u32 word) { int n; for (n = 0; n < 32; n++, word >>= 1) { if (word & 0x01) break; } return (n); } /* * NAME: cntlz(u32 value) * * FUNCTION: determine the number of leading zeros within a 32-bit * value. * * PARAMETERS: * value - 32-bit value to be examined. * * RETURN VALUES: * count of leading zeros */ static int cntlz(u32 value) { int n; for (n = 0; n < 32; n++, value <<= 1) { if (value & HIGHORDER) break; } return (n); } /* * NAME: blkstol2(s64 nb) * * FUNCTION: convert a block count to its log2 value. if the block * count is not a l2 multiple, it is rounded up to the next * larger l2 multiple. * * PARAMETERS: * nb - number of blocks * * RETURN VALUES: * log2 number of blocks */ static int blkstol2(s64 nb) { int l2nb; s64 mask; /* meant to be signed */ mask = (s64) 1 << (64 - 1); /* count the leading bits. */ for (l2nb = 0; l2nb < 64; l2nb++, mask >>= 1) { /* leading bit found. */ if (nb & mask) { /* determine the l2 value. */ l2nb = (64 - 1) - l2nb; /* check if we need to round up. */ if (~mask & nb) l2nb++; return (l2nb); } } assert(0); return 0; /* fix compiler warning */ } /* * NAME: dbAllocBottomUp() * * FUNCTION: alloc the specified block range from the working block * allocation map. * * the blocks will be alloc from the working map one dmap * at a time. * * PARAMETERS: * ip - pointer to in-core inode; * blkno - starting block number to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbAllocBottomUp(struct inode *ip, s64 blkno, s64 nblocks) { struct metapage *mp; struct dmap *dp; int nb, rc; s64 lblkno, rem; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* block to be allocated better be within the mapsize. */ ASSERT(nblocks <= bmp->db_mapsize - blkno); /* * allocate the blocks a dmap at a time. */ mp = NULL; for (rem = nblocks; rem > 0; rem -= nb, blkno += nb) { /* release previous dmap if any */ if (mp) { write_metapage(mp); } /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* determine the number of blocks to be allocated from * this dmap. */ nb = min(rem, BPERDMAP - (blkno & (BPERDMAP - 1))); /* allocate the blocks. */ if ((rc = dbAllocDmapBU(bmp, dp, blkno, nb))) { release_metapage(mp); IREAD_UNLOCK(ipbmap); return (rc); } } /* write the last buffer. */ write_metapage(mp); IREAD_UNLOCK(ipbmap); return (0); } static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int rc; int dbitno, word, rembits, nb, nwords, wbitno, agno; s8 oldroot; struct dmaptree *tp = (struct dmaptree *) & dp->tree; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = tp->stree[ROOT]; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap */ assert(dbitno + nblocks <= BPERDMAP); /* allocate the bits of the dmap's words corresponding to the block * range. not all bits of the first and last words may be contained * within the block range. if this is the case, we'll work against * those words (i.e. partial first and/or last) on an individual basis * (a single pass), allocating the bits of interest by hand and * updating the leaf corresponding to the dmap word. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the bits of all fully contained * dmap words will be marked as free in a single shot and the leaves * will be updated. a single leaf may describe the free space of * multiple dmap words, so we may update only a subset of the actual * leaves corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be allocated. */ if (nb < DBWORD) { /* allocate (set to 1) the appropriate bits within * this dmap word. */ dp->wmap[word] |= cpu_to_le32(ONES << (DBWORD - nb) >> wbitno); word++; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and allocate (set to 1) the bits of these * words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], (int) ONES, nwords * 4); /* determine how many bits */ nb = nwords << L2DBWORD; word += nwords; } } /* update the free count for this dmap */ le32_add_cpu(&dp->nfree, -nblocks); /* reconstruct summary tree */ dbInitDmapTree(dp); BMAP_LOCK(bmp); /* if this allocation group is completely free, * update the highest active allocation group number * if this allocation group is the new max. */ agno = blkno >> bmp->db_agl2size; if (agno > bmp->db_maxag) bmp->db_maxag = agno; /* update the free count for the allocation group and map */ bmp->db_agfree[agno] -= nblocks; bmp->db_nfree -= nblocks; BMAP_UNLOCK(bmp); /* if the root has not changed, done. */ if (tp->stree[ROOT] == oldroot) return (0); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the bit allocation (thus making everything consistent). */ if ((rc = dbAdjCtl(bmp, blkno, tp->stree[ROOT], 1, 0))) dbFreeBits(bmp, dp, blkno, nblocks); return (rc); } /* * NAME: dbExtendFS() * * FUNCTION: extend bmap from blkno for nblocks; * dbExtendFS() updates bmap ready for dbAllocBottomUp(); * * L2 * | * L1---------------------------------L1 * | | * L0---------L0---------L0 L0---------L0---------L0 * | | | | | | * d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,.,dm; * L2L1L0d0,...,dnL0d0,...,dnL0d0,...,dnL1L0d0,...,dnL0d0,...,dnL0d0,..dm * * <---old---><----------------------------extend-----------------------> */ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) { struct jfs_sb_info *sbi = JFS_SBI(ipbmap->i_sb); int nbperpage = sbi->nbperpage; int i, i0 = true, j, j0 = true, k, n; s64 newsize; s64 p; struct metapage *mp, *l2mp, *l1mp = NULL, *l0mp = NULL; struct dmapctl *l2dcp, *l1dcp, *l0dcp; struct dmap *dp; s8 *l0leaf, *l1leaf, *l2leaf; struct bmap *bmp = sbi->bmap; int agno, l2agsize, oldl2agsize; s64 ag_rem; newsize = blkno + nblocks; jfs_info("dbExtendFS: blkno:%Ld nblocks:%Ld newsize:%Ld", (long long) blkno, (long long) nblocks, (long long) newsize); /* * initialize bmap control page. * * all the data in bmap control page should exclude * the mkfs hidden dmap page. */ /* update mapsize */ bmp->db_mapsize = newsize; bmp->db_maxlevel = BMAPSZTOLEV(bmp->db_mapsize); /* compute new AG size */ l2agsize = dbGetL2AGSize(newsize); oldl2agsize = bmp->db_agl2size; bmp->db_agl2size = l2agsize; bmp->db_agsize = (s64)1 << l2agsize; /* compute new number of AG */ agno = bmp->db_numag; bmp->db_numag = newsize >> l2agsize; bmp->db_numag += ((u32) newsize % (u32) bmp->db_agsize) ? 1 : 0; /* * reconfigure db_agfree[] * from old AG configuration to new AG configuration; * * coalesce contiguous k (newAGSize/oldAGSize) AGs; * i.e., (AGi, ..., AGj) where i = k*n and j = k*(n+1) - 1 to AGn; * note: new AG size = old AG size * (2**x). */ if (l2agsize == oldl2agsize) goto extend; k = 1 << (l2agsize - oldl2agsize); ag_rem = bmp->db_agfree[0]; /* save agfree[0] */ for (i = 0, n = 0; i < agno; n++) { bmp->db_agfree[n] = 0; /* init collection point */ /* coalesce contiguous k AGs; */ for (j = 0; j < k && i < agno; j++, i++) { /* merge AGi to AGn */ bmp->db_agfree[n] += bmp->db_agfree[i]; } } bmp->db_agfree[0] += ag_rem; /* restore agfree[0] */ for (; n < MAXAG; n++) bmp->db_agfree[n] = 0; /* * update highest active ag number */ bmp->db_maxag = bmp->db_maxag / k; /* * extend bmap * * update bit maps and corresponding level control pages; * global control page db_nfree, db_agfree[agno], db_maxfreebud; */ extend: /* get L2 page */ p = BMAPBLKNO + nbperpage; /* L2 page */ l2mp = read_metapage(ipbmap, p, PSIZE, 0); if (!l2mp) { jfs_error(ipbmap->i_sb, "L2 page could not be read\n"); return -EIO; } l2dcp = (struct dmapctl *) l2mp->data; /* compute start L1 */ k = blkno >> L2MAXL1SIZE; l2leaf = l2dcp->stree + CTLLEAFIND + k; p = BLKTOL1(blkno, sbi->l2nbperpage); /* L1 page */ /* * extend each L1 in L2 */ for (; k < LPERCTL; k++, p += nbperpage) { /* get L1 page */ if (j0) { /* read in L1 page: (blkno & (MAXL1SIZE - 1)) */ l1mp = read_metapage(ipbmap, p, PSIZE, 0); if (l1mp == NULL) goto errout; l1dcp = (struct dmapctl *) l1mp->data; /* compute start L0 */ j = (blkno & (MAXL1SIZE - 1)) >> L2MAXL0SIZE; l1leaf = l1dcp->stree + CTLLEAFIND + j; p = BLKTOL0(blkno, sbi->l2nbperpage); j0 = false; } else { /* assign/init L1 page */ l1mp = get_metapage(ipbmap, p, PSIZE, 0); if (l1mp == NULL) goto errout; l1dcp = (struct dmapctl *) l1mp->data; /* compute start L0 */ j = 0; l1leaf = l1dcp->stree + CTLLEAFIND; p += nbperpage; /* 1st L0 of L1.k */ } /* * extend each L0 in L1 */ for (; j < LPERCTL; j++) { /* get L0 page */ if (i0) { /* read in L0 page: (blkno & (MAXL0SIZE - 1)) */ l0mp = read_metapage(ipbmap, p, PSIZE, 0); if (l0mp == NULL) goto errout; l0dcp = (struct dmapctl *) l0mp->data; /* compute start dmap */ i = (blkno & (MAXL0SIZE - 1)) >> L2BPERDMAP; l0leaf = l0dcp->stree + CTLLEAFIND + i; p = BLKTODMAP(blkno, sbi->l2nbperpage); i0 = false; } else { /* assign/init L0 page */ l0mp = get_metapage(ipbmap, p, PSIZE, 0); if (l0mp == NULL) goto errout; l0dcp = (struct dmapctl *) l0mp->data; /* compute start dmap */ i = 0; l0leaf = l0dcp->stree + CTLLEAFIND; p += nbperpage; /* 1st dmap of L0.j */ } /* * extend each dmap in L0 */ for (; i < LPERCTL; i++) { /* * reconstruct the dmap page, and * initialize corresponding parent L0 leaf */ if ((n = blkno & (BPERDMAP - 1))) { /* read in dmap page: */ mp = read_metapage(ipbmap, p, PSIZE, 0); if (mp == NULL) goto errout; n = min(nblocks, (s64)BPERDMAP - n); } else { /* assign/init dmap page */ mp = read_metapage(ipbmap, p, PSIZE, 0); if (mp == NULL) goto errout; n = min_t(s64, nblocks, BPERDMAP); } dp = (struct dmap *) mp->data; *l0leaf = dbInitDmap(dp, blkno, n); bmp->db_nfree += n; agno = le64_to_cpu(dp->start) >> l2agsize; bmp->db_agfree[agno] += n; write_metapage(mp); l0leaf++; p += nbperpage; blkno += n; nblocks -= n; if (nblocks == 0) break; } /* for each dmap in a L0 */ /* * build current L0 page from its leaves, and * initialize corresponding parent L1 leaf */ *l1leaf = dbInitDmapCtl(l0dcp, 0, ++i); write_metapage(l0mp); l0mp = NULL; if (nblocks) l1leaf++; /* continue for next L0 */ else { /* more than 1 L0 ? */ if (j > 0) break; /* build L1 page */ else { /* summarize in global bmap page */ bmp->db_maxfreebud = *l1leaf; release_metapage(l1mp); release_metapage(l2mp); goto finalize; } } } /* for each L0 in a L1 */ /* * build current L1 page from its leaves, and * initialize corresponding parent L2 leaf */ *l2leaf = dbInitDmapCtl(l1dcp, 1, ++j); write_metapage(l1mp); l1mp = NULL; if (nblocks) l2leaf++; /* continue for next L1 */ else { /* more than 1 L1 ? */ if (k > 0) break; /* build L2 page */ else { /* summarize in global bmap page */ bmp->db_maxfreebud = *l2leaf; release_metapage(l2mp); goto finalize; } } } /* for each L1 in a L2 */ jfs_error(ipbmap->i_sb, "function has not returned as expected\n"); errout: if (l0mp) release_metapage(l0mp); if (l1mp) release_metapage(l1mp); release_metapage(l2mp); return -EIO; /* * finalize bmap control page */ finalize: return 0; } /* * dbFinalizeBmap() */ void dbFinalizeBmap(struct inode *ipbmap) { struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; int actags, inactags, l2nl; s64 ag_rem, actfree, inactfree, avgfree; int i, n; /* * finalize bmap control page */ //finalize: /* * compute db_agpref: preferred ag to allocate from * (the leftmost ag with average free space in it); */ //agpref: /* get the number of active ags and inactive ags */ actags = bmp->db_maxag + 1; inactags = bmp->db_numag - actags; ag_rem = bmp->db_mapsize & (bmp->db_agsize - 1); /* ??? */ /* determine how many blocks are in the inactive allocation * groups. in doing this, we must account for the fact that * the rightmost group might be a partial group (i.e. file * system size is not a multiple of the group size). */ inactfree = (inactags && ag_rem) ? (((s64)inactags - 1) << bmp->db_agl2size) + ag_rem : ((s64)inactags << bmp->db_agl2size); /* determine how many free blocks are in the active * allocation groups plus the average number of free blocks * within the active ags. */ actfree = bmp->db_nfree - inactfree; avgfree = (u32) actfree / (u32) actags; /* if the preferred allocation group has not average free space. * re-establish the preferred group as the leftmost * group with average free space. */ if (bmp->db_agfree[bmp->db_agpref] < avgfree) { for (bmp->db_agpref = 0; bmp->db_agpref < actags; bmp->db_agpref++) { if (bmp->db_agfree[bmp->db_agpref] >= avgfree) break; } if (bmp->db_agpref >= bmp->db_numag) { jfs_error(ipbmap->i_sb, "cannot find ag with average freespace\n"); } } /* * compute db_aglevel, db_agheight, db_width, db_agstart: * an ag is covered in aglevel dmapctl summary tree, * at agheight level height (from leaf) with agwidth number of nodes * each, which starts at agstart index node of the smmary tree node * array; */ bmp->db_aglevel = BMAPSZTOLEV(bmp->db_agsize); l2nl = bmp->db_agl2size - (L2BPERDMAP + bmp->db_aglevel * L2LPERCTL); bmp->db_agheight = l2nl >> 1; bmp->db_agwidth = 1 << (l2nl - (bmp->db_agheight << 1)); for (i = 5 - bmp->db_agheight, bmp->db_agstart = 0, n = 1; i > 0; i--) { bmp->db_agstart += n; n <<= 2; } } /* * NAME: dbInitDmap()/ujfs_idmap_page() * * FUNCTION: initialize working/persistent bitmap of the dmap page * for the specified number of blocks: * * at entry, the bitmaps had been initialized as free (ZEROS); * The number of blocks will only account for the actually * existing blocks. Blocks which don't actually exist in * the aggregate will be marked as allocated (ONES); * * PARAMETERS: * dp - pointer to page of map * nblocks - number of blocks this page * * RETURNS: NONE */ static int dbInitDmap(struct dmap * dp, s64 Blkno, int nblocks) { int blkno, w, b, r, nw, nb, i; /* starting block number within the dmap */ blkno = Blkno & (BPERDMAP - 1); if (blkno == 0) { dp->nblocks = dp->nfree = cpu_to_le32(nblocks); dp->start = cpu_to_le64(Blkno); if (nblocks == BPERDMAP) { memset(&dp->wmap[0], 0, LPERDMAP * 4); memset(&dp->pmap[0], 0, LPERDMAP * 4); goto initTree; } } else { le32_add_cpu(&dp->nblocks, nblocks); le32_add_cpu(&dp->nfree, nblocks); } /* word number containing start block number */ w = blkno >> L2DBWORD; /* * free the bits corresponding to the block range (ZEROS): * note: not all bits of the first and last words may be contained * within the block range. */ for (r = nblocks; r > 0; r -= nb, blkno += nb) { /* number of bits preceding range to be freed in the word */ b = blkno & (DBWORD - 1); /* number of bits to free in the word */ nb = min(r, DBWORD - b); /* is partial word to be freed ? */ if (nb < DBWORD) { /* free (set to 0) from the bitmap word */ dp->wmap[w] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> b)); dp->pmap[w] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> b)); /* skip the word freed */ w++; } else { /* free (set to 0) contiguous bitmap words */ nw = r >> L2DBWORD; memset(&dp->wmap[w], 0, nw * 4); memset(&dp->pmap[w], 0, nw * 4); /* skip the words freed */ nb = nw << L2DBWORD; w += nw; } } /* * mark bits following the range to be freed (non-existing * blocks) as allocated (ONES) */ if (blkno == BPERDMAP) goto initTree; /* the first word beyond the end of existing blocks */ w = blkno >> L2DBWORD; /* does nblocks fall on a 32-bit boundary ? */ b = blkno & (DBWORD - 1); if (b) { /* mark a partial word allocated */ dp->wmap[w] = dp->pmap[w] = cpu_to_le32(ONES >> b); w++; } /* set the rest of the words in the page to allocated (ONES) */ for (i = w; i < LPERDMAP; i++) dp->pmap[i] = dp->wmap[i] = cpu_to_le32(ONES); /* * init tree */ initTree: return (dbInitDmapTree(dp)); } /* * NAME: dbInitDmapTree()/ujfs_complete_dmap() * * FUNCTION: initialize summary tree of the specified dmap: * * at entry, bitmap of the dmap has been initialized; * * PARAMETERS: * dp - dmap to complete * blkno - starting block number for this dmap * treemax - will be filled in with max free for this dmap * * RETURNS: max free string at the root of the tree */ static int dbInitDmapTree(struct dmap * dp) { struct dmaptree *tp; s8 *cp; int i; /* init fixed info of tree */ tp = &dp->tree; tp->nleafs = cpu_to_le32(LPERDMAP); tp->l2nleafs = cpu_to_le32(L2LPERDMAP); tp->leafidx = cpu_to_le32(LEAFIND); tp->height = cpu_to_le32(4); tp->budmin = BUDMIN; /* init each leaf from corresponding wmap word: * note: leaf is set to NOFREE(-1) if all blocks of corresponding * bitmap word are allocated. */ cp = tp->stree + le32_to_cpu(tp->leafidx); for (i = 0; i < LPERDMAP; i++) *cp++ = dbMaxBud((u8 *) & dp->wmap[i]); /* build the dmap's binary buddy summary tree */ return (dbInitTree(tp)); } /* * NAME: dbInitTree()/ujfs_adjtree() * * FUNCTION: initialize binary buddy summary tree of a dmap or dmapctl. * * at entry, the leaves of the tree has been initialized * from corresponding bitmap word or root of summary tree * of the child control page; * configure binary buddy system at the leaf level, then * bubble up the values of the leaf nodes up the tree. * * PARAMETERS: * cp - Pointer to the root of the tree * l2leaves- Number of leaf nodes as a power of 2 * l2min - Number of blocks that can be covered by a leaf * as a power of 2 * * RETURNS: max free string at the root of the tree */ static int dbInitTree(struct dmaptree * dtp) { int l2max, l2free, bsize, nextb, i; int child, parent, nparent; s8 *tp, *cp, *cp1; tp = dtp->stree; /* Determine the maximum free string possible for the leaves */ l2max = le32_to_cpu(dtp->l2nleafs) + dtp->budmin; /* * configure the leaf level into binary buddy system * * Try to combine buddies starting with a buddy size of 1 * (i.e. two leaves). At a buddy size of 1 two buddy leaves * can be combined if both buddies have a maximum free of l2min; * the combination will result in the left-most buddy leaf having * a maximum free of l2min+1. * After processing all buddies for a given size, process buddies * at the next higher buddy size (i.e. current size * 2) and * the next maximum free (current free + 1). * This continues until the maximum possible buddy combination * yields maximum free. */ for (l2free = dtp->budmin, bsize = 1; l2free < l2max; l2free++, bsize = nextb) { /* get next buddy size == current buddy pair size */ nextb = bsize << 1; /* scan each adjacent buddy pair at current buddy size */ for (i = 0, cp = tp + le32_to_cpu(dtp->leafidx); i < le32_to_cpu(dtp->nleafs); i += nextb, cp += nextb) { /* coalesce if both adjacent buddies are max free */ if (*cp == l2free && *(cp + bsize) == l2free) { *cp = l2free + 1; /* left take right */ *(cp + bsize) = -1; /* right give left */ } } } /* * bubble summary information of leaves up the tree. * * Starting at the leaf node level, the four nodes described by * the higher level parent node are compared for a maximum free and * this maximum becomes the value of the parent node. * when all lower level nodes are processed in this fashion then * move up to the next level (parent becomes a lower level node) and * continue the process for that level. */ for (child = le32_to_cpu(dtp->leafidx), nparent = le32_to_cpu(dtp->nleafs) >> 2; nparent > 0; nparent >>= 2, child = parent) { /* get index of 1st node of parent level */ parent = (child - 1) >> 2; /* set the value of the parent node as the maximum * of the four nodes of the current level. */ for (i = 0, cp = tp + child, cp1 = tp + parent; i < nparent; i++, cp += 4, cp1++) *cp1 = TREEMAX(cp); } return (*tp); } /* * dbInitDmapCtl() * * function: initialize dmapctl page */ static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i) { /* start leaf index not covered by range */ s8 *cp; dcp->nleafs = cpu_to_le32(LPERCTL); dcp->l2nleafs = cpu_to_le32(L2LPERCTL); dcp->leafidx = cpu_to_le32(CTLLEAFIND); dcp->height = cpu_to_le32(5); dcp->budmin = L2BPERDMAP + L2LPERCTL * level; /* * initialize the leaves of current level that were not covered * by the specified input block range (i.e. the leaves have no * low level dmapctl or dmap). */ cp = &dcp->stree[CTLLEAFIND + i]; for (; i < LPERCTL; i++) *cp++ = NOFREE; /* build the dmap's binary buddy summary tree */ return (dbInitTree((struct dmaptree *) dcp)); } /* * NAME: dbGetL2AGSize()/ujfs_getagl2size() * * FUNCTION: Determine log2(allocation group size) from aggregate size * * PARAMETERS: * nblocks - Number of blocks in aggregate * * RETURNS: log2(allocation group size) in aggregate blocks */ static int dbGetL2AGSize(s64 nblocks) { s64 sz; s64 m; int l2sz; if (nblocks < BPERDMAP * MAXAG) return (L2BPERDMAP); /* round up aggregate size to power of 2 */ m = ((u64) 1 << (64 - 1)); for (l2sz = 64; l2sz >= 0; l2sz--, m >>= 1) { if (m & nblocks) break; } sz = (s64) 1 << l2sz; if (sz < nblocks) l2sz += 1; /* agsize = roundupSize/max_number_of_ag */ return (l2sz - L2MAXAG); } /* * NAME: dbMapFileSizeToMapSize() * * FUNCTION: compute number of blocks the block allocation map file * can cover from the map file size; * * RETURNS: Number of blocks which can be covered by this block map file; */ /* * maximum number of map pages at each level including control pages */ #define MAXL0PAGES (1 + LPERCTL) #define MAXL1PAGES (1 + LPERCTL * MAXL0PAGES) /* * convert number of map pages to the zero origin top dmapctl level */ #define BMAPPGTOLEV(npages) \ (((npages) <= 3 + MAXL0PAGES) ? 0 : \ ((npages) <= 2 + MAXL1PAGES) ? 1 : 2) s64 dbMapFileSizeToMapSize(struct inode * ipbmap) { struct super_block *sb = ipbmap->i_sb; s64 nblocks; s64 npages, ndmaps; int level, i; int complete, factor; nblocks = ipbmap->i_size >> JFS_SBI(sb)->l2bsize; npages = nblocks >> JFS_SBI(sb)->l2nbperpage; level = BMAPPGTOLEV(npages); /* At each level, accumulate the number of dmap pages covered by * the number of full child levels below it; * repeat for the last incomplete child level. */ ndmaps = 0; npages--; /* skip the first global control page */ /* skip higher level control pages above top level covered by map */ npages -= (2 - level); npages--; /* skip top level's control page */ for (i = level; i >= 0; i--) { factor = (i == 2) ? MAXL1PAGES : ((i == 1) ? MAXL0PAGES : 1); complete = (u32) npages / factor; ndmaps += complete * ((i == 2) ? LPERCTL * LPERCTL : ((i == 1) ? LPERCTL : 1)); /* pages in last/incomplete child */ npages = (u32) npages % factor; /* skip incomplete child's level control page */ npages--; } /* convert the number of dmaps into the number of blocks * which can be covered by the dmaps; */ nblocks = ndmaps << L2BPERDMAP; return (nblocks); } |
| 16 49 7 41 47 8 3 41 42 5 27 3 5 27 39 28 11 1 36 23 26 2 17 2 2 12 11 22 10 6 29 15 14 41 50 13 13 11 40 40 2 3 41 54 77 5 13 4 15 46 33 1 41 31 59 8 53 14 39 28 15 3 54 7 6 55 8 2 58 45 6 13 9 3 14 14 2 3 74 3 57 57 2 37 20 92 7 85 79 82 81 37 39 7 1 6 6 6 1 1 1 7 11 11 1 2 11 4 2 2 2 10 1 11 4 6 78 15 4 14 74 3 74 74 13 72 22 58 22 68 10 10 37 20 6 13 5 3 3 3 1 2 9 6 3 7 2 6 3 7 2 7 2 8 1 7 2 7 2 7 2 6 3 7 2 1 1 48 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2002-2013 Jozsef Kadlecsik <kadlec@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> #include <linux/unaligned.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ static const char *const tcp_conntrack_names[] = { "NONE", "SYN_SENT", "SYN_RECV", "ESTABLISHED", "FIN_WAIT", "CLOSE_WAIT", "LAST_ACK", "TIME_WAIT", "CLOSE", "SYN_SENT2", }; enum nf_ct_tcp_action { NFCT_TCP_IGNORE, NFCT_TCP_INVALID, NFCT_TCP_ACCEPT, }; #define SECS * HZ #define MINS * 60 SECS #define HOURS * 60 MINS #define DAYS * 24 HOURS static const unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] = { [TCP_CONNTRACK_SYN_SENT] = 2 MINS, [TCP_CONNTRACK_SYN_RECV] = 60 SECS, [TCP_CONNTRACK_ESTABLISHED] = 5 DAYS, [TCP_CONNTRACK_FIN_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE_WAIT] = 60 SECS, [TCP_CONNTRACK_LAST_ACK] = 30 SECS, [TCP_CONNTRACK_TIME_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE] = 10 SECS, [TCP_CONNTRACK_SYN_SENT2] = 2 MINS, /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ [TCP_CONNTRACK_RETRANS] = 5 MINS, [TCP_CONNTRACK_UNACK] = 5 MINS, }; #define sNO TCP_CONNTRACK_NONE #define sSS TCP_CONNTRACK_SYN_SENT #define sSR TCP_CONNTRACK_SYN_RECV #define sES TCP_CONNTRACK_ESTABLISHED #define sFW TCP_CONNTRACK_FIN_WAIT #define sCW TCP_CONNTRACK_CLOSE_WAIT #define sLA TCP_CONNTRACK_LAST_ACK #define sTW TCP_CONNTRACK_TIME_WAIT #define sCL TCP_CONNTRACK_CLOSE #define sS2 TCP_CONNTRACK_SYN_SENT2 #define sIV TCP_CONNTRACK_MAX #define sIG TCP_CONNTRACK_IGNORE /* What TCP flags are set from RST/SYN/FIN/ACK. */ enum tcp_bit_set { TCP_SYN_SET, TCP_SYNACK_SET, TCP_FIN_SET, TCP_ACK_SET, TCP_RST_SET, TCP_NONE_SET, }; /* * The TCP state transition table needs a few words... * * We are the man in the middle. All the packets go through us * but might get lost in transit to the destination. * It is assumed that the destinations can't receive segments * we haven't seen. * * The checked segment is in window, but our windows are *not* * equivalent with the ones of the sender/receiver. We always * try to guess the state of the current sender. * * The meaning of the states are: * * NONE: initial state * SYN_SENT: SYN-only packet seen * SYN_SENT2: SYN-only packet seen from reply dir, simultaneous open * SYN_RECV: SYN-ACK packet seen * ESTABLISHED: ACK packet seen * FIN_WAIT: FIN packet seen * CLOSE_WAIT: ACK seen (after FIN) * LAST_ACK: FIN seen (after FIN) * TIME_WAIT: last ACK seen * CLOSE: closed connection (RST) * * Packets marked as IGNORED (sIG): * if they may be either invalid or valid * and the receiver may send back a connection * closing RST or a SYN/ACK. * * Packets marked as INVALID (sIV): * if we regard them as truly invalid packets */ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 }, /* * sNO -> sSS Initialize a new connection * sSS -> sSS Retransmitted SYN * sS2 -> sS2 Late retransmitted SYN * sSR -> sIG * sES -> sIG Error: SYNs in window outside the SYN_SENT state * are errors. Receiver will reply with RST * and close the connection. * Or we are not in sync and hold a dead connection. * sFW -> sIG * sCW -> sIG * sLA -> sIG * sTW -> sSS Reopened connection (RFC 1122). * sCL -> sSS */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*synack*/ { sIV, sIV, sSR, sIV, sIV, sIV, sIV, sIV, sIV, sSR }, /* * sNO -> sIV Too late and no reason to do anything * sSS -> sIV Client can't send SYN and then SYN/ACK * sS2 -> sSR SYN/ACK sent to SYN2 in simultaneous open * sSR -> sSR Late retransmitted SYN/ACK in simultaneous open * sES -> sIV Invalid SYN/ACK packets sent by the client * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sIV * sCL -> sIV */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sNO -> sIV Too late and no reason to do anything... * sSS -> sIV Client migth not send FIN in this state: * we enforce waiting for a SYN/ACK reply first. * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions, waiting for * the last ACK. * Migth be a retransmitted FIN as well... * sCW -> sLA * sLA -> sLA Retransmitted FIN. Remain in the same state. * sTW -> sTW * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV }, /* * sNO -> sES Assumed. * sSS -> sIV ACK is invalid: we haven't seen a SYN/ACK yet. * sS2 -> sIV * sSR -> sES Established state is reached. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } }, { /* REPLY */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sSS, sIV, sS2 }, /* * sNO -> sIV Never reached. * sSS -> sS2 Simultaneous open * sS2 -> sS2 Retransmitted simultaneous SYN * sSR -> sIV Invalid SYN packets sent by the server * sES -> sIV * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sSS Reopened connection, but server may have switched role * sCL -> sIV */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*synack*/ { sIV, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* * sSS -> sSR Standard open. * sS2 -> sSR Simultaneous open * sSR -> sIG Retransmitted SYN/ACK, ignore it. * sES -> sIG Late retransmitted SYN/ACK? * sFW -> sIG Might be SYN/ACK answering ignored SYN * sCW -> sIG * sLA -> sIG * sTW -> sIG * sCL -> sIG */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sSS -> sIV Server might not send FIN in this state. * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions. * sCW -> sLA * sLA -> sLA Retransmitted FIN. * sTW -> sTW * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG }, /* * sSS -> sIG Might be a half-open connection. * sS2 -> sIG * sSR -> sSR Might answer late resent SYN. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } } }; #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) return; seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]); } #endif static unsigned int get_conntrack_index(const struct tcphdr *tcph) { if (tcph->rst) return TCP_RST_SET; else if (tcph->syn) return (tcph->ack ? TCP_SYNACK_SET : TCP_SYN_SET); else if (tcph->fin) return TCP_FIN_SET; else if (tcph->ack) return TCP_ACK_SET; else return TCP_NONE_SET; } /* TCP connection tracking based on 'Real Stateful TCP Packet Filtering in IP Filter' by Guido van Rooij. http://www.sane.nl/events/sane2000/papers.html http://www.darkart.com/mirrors/www.obfuscation.org/ipf/ The boundaries and the conditions are changed according to RFC793: the packet must intersect the window (i.e. segments may be after the right or before the left edge) and thus receivers may ACK segments after the right edge of the window. td_maxend = max(sack + max(win,1)) seen in reply packets td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets td_maxwin += seq + len - sender.td_maxend if seq + len > sender.td_maxend td_end = max(seq + len) seen in sent packets I. Upper bound for valid data: seq <= sender.td_maxend II. Lower bound for valid data: seq + len >= sender.td_end - receiver.td_maxwin III. Upper bound for valid (s)ack: sack <= receiver.td_end IV. Lower bound for valid (s)ack: sack >= receiver.td_end - MAXACKWINDOW where sack is the highest right edge of sack block found in the packet or ack in the case of packet without SACK option. The upper bound limit for a valid (s)ack is not ignored - we doesn't have to deal with fragments. */ static inline __u32 segment_seq_plus_len(__u32 seq, size_t len, unsigned int dataoff, const struct tcphdr *tcph) { /* XXX Should I use payload length field in IP/IPv6 header ? * - YK */ return (seq + len - dataoff - tcph->doff*4 + (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0)); } /* Fixme: what about big packets? */ #define MAXACKWINCONST 66000 #define MAXACKWINDOW(sender) \ ((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin \ : MAXACKWINCONST) /* * Simplified tcp_parse_options routine from tcp_input.c */ static void tcp_options(const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, struct ip_ct_tcp_state *state) { unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; const unsigned char *ptr; int length = (tcph->doff*4) - sizeof(struct tcphdr); if (!length) return; ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr), length, buff); if (!ptr) return; state->td_scale = 0; state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; while (length > 0) { int opcode=*ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: if (length < 2) return; opsize=*ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_SACK_PERM && opsize == TCPOLEN_SACK_PERM) state->flags |= IP_CT_TCP_FLAG_SACK_PERM; else if (opcode == TCPOPT_WINDOW && opsize == TCPOLEN_WINDOW) { state->td_scale = *(u_int8_t *)ptr; if (state->td_scale > TCP_MAX_WSCALE) state->td_scale = TCP_MAX_WSCALE; state->flags |= IP_CT_TCP_FLAG_WINDOW_SCALE; } ptr += opsize - 2; length -= opsize; } } } static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, __u32 *sack) { unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; const unsigned char *ptr; int length = (tcph->doff*4) - sizeof(struct tcphdr); __u32 tmp; if (!length) return; ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr), length, buff); if (!ptr) return; /* Fast path for timestamp-only option */ if (length == TCPOLEN_TSTAMP_ALIGNED && *(__be32 *)ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) return; while (length > 0) { int opcode = *ptr++; int opsize, i; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: if (length < 2) return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_SACK && opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK) && !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK)) { for (i = 0; i < (opsize - TCPOLEN_SACK_BASE); i += TCPOLEN_SACK_PERBLOCK) { tmp = get_unaligned_be32((__be32 *)(ptr+i)+1); if (after(tmp, *sack)) *sack = tmp; } return; } ptr += opsize - 2; length -= opsize; } } } static void tcp_init_sender(struct ip_ct_tcp_state *sender, struct ip_ct_tcp_state *receiver, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, u32 end, u32 win, enum ip_conntrack_dir dir) { /* SYN-ACK in reply to a SYN * or SYN from reply direction in simultaneous open. */ sender->td_end = sender->td_maxend = end; sender->td_maxwin = (win == 0 ? 1 : win); tcp_options(skb, dataoff, tcph, sender); /* RFC 1323: * Both sides must send the Window Scale option * to enable window scaling in either direction. */ if (dir == IP_CT_DIR_REPLY && !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { sender->td_scale = 0; receiver->td_scale = 0; } } __printf(6, 7) static enum nf_ct_tcp_action nf_tcp_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, const struct nf_hook_state *state, const struct ip_ct_tcp_state *sender, enum nf_ct_tcp_action ret, const char *fmt, ...) { const struct nf_tcp_net *tn = nf_tcp_pernet(nf_ct_net(ct)); struct va_format vaf; va_list args; bool be_liberal; be_liberal = sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal; if (be_liberal) return NFCT_TCP_ACCEPT; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; nf_ct_l4proto_log_invalid(skb, ct, state, "%pV", &vaf); va_end(args); return ret; } static enum nf_ct_tcp_action tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, const struct nf_hook_state *hook_state) { struct ip_ct_tcp *state = &ct->proto.tcp; struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; __u32 seq, ack, sack, end, win, swin; bool in_recv_win, seq_ok; s32 receiver_offset; u16 win_raw; /* * Get the required data from the packet. */ seq = ntohl(tcph->seq); ack = sack = ntohl(tcph->ack_seq); win_raw = ntohs(tcph->window); win = win_raw; end = segment_seq_plus_len(seq, skb->len, dataoff, tcph); if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ receiver_offset = nf_ct_seq_offset(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; if (sender->td_maxwin == 0) { /* * Initialize sender data. */ if (tcph->syn) { tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win, dir); if (!tcph->ack) /* Simultaneous open */ return NFCT_TCP_ACCEPT; } else { /* * We are in the middle of a connection, * its history is lost for us. * Let's try to use the data from the packet. */ sender->td_end = end; swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; if (receiver->td_maxwin == 0) { /* We haven't seen traffic in the other * direction yet but we have to tweak window * tracking to pass III and IV until that * happens. */ receiver->td_end = receiver->td_maxend = sack; } else if (sack == receiver->td_end + 1) { /* Likely a reply to a keepalive. * Needed for III. */ receiver->td_end++; } } } else if (tcph->syn && after(end, sender->td_end) && (state->state == TCP_CONNTRACK_SYN_SENT || state->state == TCP_CONNTRACK_SYN_RECV)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." * * Re-init state for this direction, just like for the first * syn(-ack) reply, it might differ in seq, ack or tcp options. */ tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win, dir); if (dir == IP_CT_DIR_REPLY && !tcph->ack) return NFCT_TCP_ACCEPT; } if (!(tcph->ack)) { /* * If there is no ACK, just pretend it was set and OK. */ ack = sack = receiver->td_end; } else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) == (TCP_FLAG_ACK|TCP_FLAG_RST)) && (ack == 0)) { /* * Broken TCP stacks, that set ACK in RST packets as well * with zero ack value. */ ack = sack = receiver->td_end; } if (tcph->rst && seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT) /* * RST sent answering SYN. */ seq = end = sender->td_end; seq_ok = before(seq, sender->td_maxend + 1); if (!seq_ok) { u32 overshot = end - sender->td_maxend + 1; bool ack_ok; ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1); in_recv_win = receiver->td_maxwin && after(end, sender->td_end - receiver->td_maxwin - 1); if (in_recv_win && ack_ok && overshot <= receiver->td_maxwin && before(sack, receiver->td_end + 1)) { /* Work around TCPs that send more bytes than allowed by * the receive window. * * If the (marked as invalid) packet is allowed to pass by * the ruleset and the peer acks this data, then its possible * all future packets will trigger 'ACK is over upper bound' check. * * Thus if only the sequence check fails then do update td_end so * possible ACK for this data can update internal state. */ sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, "%u bytes more than expected", overshot); } return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, "SEQ is over upper bound %u (over the window of the receiver)", sender->td_maxend + 1); } if (!before(sack, receiver->td_end + 1)) return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, "ACK is over upper bound %u (ACKed data not seen yet)", receiver->td_end + 1); /* Is the ending sequence in the receive window (if available)? */ in_recv_win = !receiver->td_maxwin || after(end, sender->td_end - receiver->td_maxwin - 1); if (!in_recv_win) return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, "SEQ is under lower bound %u (already ACKed data retransmitted)", sender->td_end - receiver->td_maxwin - 1); if (!after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, "ignored ACK under lower bound %u (possible overly delayed)", receiver->td_end - MAXACKWINDOW(sender) - 1); /* Take into account window scaling (RFC 1323). */ if (!tcph->syn) win <<= sender->td_scale; /* Update sender data. */ swin = win + (sack - ack); if (sender->td_maxwin < swin) sender->td_maxwin = swin; if (after(end, sender->td_end)) { sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; } if (tcph->ack) { if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) { sender->td_maxack = ack; sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET; } else if (after(ack, sender->td_maxack)) { sender->td_maxack = ack; } } /* Update receiver data. */ if (receiver->td_maxwin != 0 && after(end, sender->td_maxend)) receiver->td_maxwin += end - sender->td_maxend; if (after(sack + win, receiver->td_maxend - 1)) { receiver->td_maxend = sack + win; if (win == 0) receiver->td_maxend++; } if (ack == receiver->td_end) receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; /* Check retransmissions. */ if (index == TCP_ACK_SET) { if (state->last_dir == dir && state->last_seq == seq && state->last_ack == ack && state->last_end == end && state->last_win == win_raw) { state->retrans++; } else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; state->last_win = win_raw; state->retrans = 0; } } return NFCT_TCP_ACCEPT; } static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, enum ip_conntrack_dir dir, int index, const struct sk_buff *skb, const struct nf_hook_state *hook_state) { const unsigned int *timeouts; const struct nf_tcp_net *tn; unsigned int timeout; u32 expires; if (!test_bit(IPS_ASSURED_BIT, &ct->status) || test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) return; /* We don't want to have connections hanging around in ESTABLISHED * state for long time 'just because' conntrack deemed a FIN/RST * out-of-window. * * Shrink the timeout just like when there is unacked data. * This speeds up eviction of 'dead' connections where the * connection and conntracks internal state are out of sync. */ switch (index) { case TCP_RST_SET: case TCP_FIN_SET: break; default: return; } if (ct->proto.tcp.last_dir != dir && (ct->proto.tcp.last_index == TCP_FIN_SET || ct->proto.tcp.last_index == TCP_RST_SET)) { expires = nf_ct_expires(ct); if (expires < 120 * HZ) return; tn = nf_tcp_pernet(nf_ct_net(ct)); timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = tn->timeouts; timeout = READ_ONCE(timeouts[TCP_CONNTRACK_UNACK]); if (expires > timeout) { nf_ct_l4proto_log_invalid(skb, ct, hook_state, "packet (index %d, dir %d) response for index %d lower timeout to %u", index, dir, ct->proto.tcp.last_index, timeout); WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); } } else { ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; } } /* table of valid flag combinations - PUSH, ECE and CWR are always valid */ static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK| TCPHDR_URG) + 1] = { [TCPHDR_SYN] = 1, [TCPHDR_SYN|TCPHDR_URG] = 1, [TCPHDR_SYN|TCPHDR_ACK] = 1, [TCPHDR_RST] = 1, [TCPHDR_RST|TCPHDR_ACK] = 1, [TCPHDR_FIN|TCPHDR_ACK] = 1, [TCPHDR_FIN|TCPHDR_ACK|TCPHDR_URG] = 1, [TCPHDR_ACK] = 1, [TCPHDR_ACK|TCPHDR_URG] = 1, }; static void tcp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_TCP, "%s", msg); } /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ static bool tcp_error(const struct tcphdr *th, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { unsigned int tcplen = skb->len - dataoff; u8 tcpflags; /* Not whole TCP header or malformed packet */ if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) { tcp_error_log(skb, state, "truncated packet"); return true; } /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path * because the checksum is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_checksum(skb, state->hook, dataoff, IPPROTO_TCP, state->pf)) { tcp_error_log(skb, state, "bad checksum"); return true; } /* Check TCP flags. */ tcpflags = (tcp_flag_byte(th) & ~(TCPHDR_ECE|TCPHDR_CWR|TCPHDR_PSH)); if (!tcp_valid_flags[tcpflags]) { tcp_error_log(skb, state, "invalid tcp flag combination"); return true; } return false; } static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *th, const struct nf_hook_state *state) { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); const struct nf_tcp_net *tn = nf_tcp_pernet(net); /* Don't need lock here: this conntrack not in circulation yet */ new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE]; /* Invalid: delete conntrack */ if (new_state >= TCP_CONNTRACK_MAX) { tcp_error_log(skb, state, "invalid new"); return false; } if (new_state == TCP_CONNTRACK_SYN_SENT) { memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* SYN packet */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window); if (ct->proto.tcp.seen[0].td_maxwin == 0) ct->proto.tcp.seen[0].td_maxwin = 1; ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end; tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]); } else if (tn->tcp_loose == 0) { /* Don't try to pick up connections. */ return false; } else { memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* * We are in the middle of a connection, * its history is lost for us. * Let's try to use the data from the packet. */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window); if (ct->proto.tcp.seen[0].td_maxwin == 0) ct->proto.tcp.seen[0].td_maxwin = 1; ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end + ct->proto.tcp.seen[0].td_maxwin; /* We assume SACK and liberal window checking to handle * window scaling */ ct->proto.tcp.seen[0].flags = ct->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM | IP_CT_TCP_FLAG_BE_LIBERAL; } /* tcp_packet will set them */ ct->proto.tcp.last_index = TCP_NONE_SET; return true; } static bool tcp_can_early_drop(const struct nf_conn *ct) { switch (ct->proto.tcp.state) { case TCP_CONNTRACK_FIN_WAIT: case TCP_CONNTRACK_LAST_ACK: case TCP_CONNTRACK_TIME_WAIT: case TCP_CONNTRACK_CLOSE: case TCP_CONNTRACK_CLOSE_WAIT: return true; default: break; } return false; } void nf_conntrack_tcp_set_closing(struct nf_conn *ct) { enum tcp_conntrack old_state; const unsigned int *timeouts; u32 timeout; if (!nf_ct_is_confirmed(ct)) return; spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; ct->proto.tcp.state = TCP_CONNTRACK_CLOSE; if (old_state == TCP_CONNTRACK_CLOSE || test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { spin_unlock_bh(&ct->lock); return; } timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) { const struct nf_tcp_net *tn; tn = nf_tcp_pernet(nf_ct_net(ct)); timeouts = tn->timeouts; } timeout = timeouts[TCP_CONNTRACK_CLOSE]; WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); spin_unlock_bh(&ct->lock); nf_conntrack_event_cache(IPCT_PROTOINFO, ct); } static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) { state->td_end = 0; state->td_maxend = 0; state->td_maxwin = 0; state->td_maxack = 0; state->td_scale = 0; state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; enum nf_ct_tcp_action res; enum ip_conntrack_dir dir; const struct tcphdr *th; struct tcphdr _tcph; unsigned long timeout; th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); if (th == NULL) return -NF_ACCEPT; if (tcp_error(th, skb, dataoff, state)) return -NF_ACCEPT; if (!nf_ct_is_confirmed(ct) && !tcp_new(ct, skb, dataoff, th, state)) return -NF_ACCEPT; spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; dir = CTINFO2DIR(ctinfo); index = get_conntrack_index(th); new_state = tcp_conntracks[dir][index][old_state]; switch (new_state) { case TCP_CONNTRACK_SYN_SENT: if (old_state < TCP_CONNTRACK_TIME_WAIT) break; /* RFC 1122: "When a connection is closed actively, * it MUST linger in TIME-WAIT state for a time 2xMSL * (Maximum Segment Lifetime). However, it MAY accept * a new SYN from the remote TCP to reopen the connection * directly from TIME-WAIT state, if..." * We ignore the conditions because we are in the * TIME-WAIT state anyway. * * Handle aborted connections: we and the server * think there is an existing connection but the client * aborts it and starts a new one. */ if (((ct->proto.tcp.seen[dir].flags | ct->proto.tcp.seen[!dir].flags) & IP_CT_TCP_FLAG_CLOSE_INIT) || (ct->proto.tcp.last_dir == dir && ct->proto.tcp.last_index == TCP_RST_SET)) { /* Attempt to reopen a closed/aborted connection. * Delete this connection and look up again. */ spin_unlock_bh(&ct->lock); /* Only repeat if we can actually remove the timer. * Destruction may already be in progress in process * context and we must give it a chance to terminate. */ if (nf_ct_kill(ct)) return -NF_REPEAT; return NF_DROP; } fallthrough; case TCP_CONNTRACK_IGNORE: /* Ignored packets: * * Our connection entry may be out of sync, so ignore * packets which may signal the real connection between * the client and the server. * * a) SYN in ORIGINAL * b) SYN/ACK in REPLY * c) ACK in reply direction after initial SYN in original. * * If the ignored packet is invalid, the receiver will send * a RST we'll catch below. */ if (index == TCP_SYNACK_SET && ct->proto.tcp.last_index == TCP_SYN_SET && ct->proto.tcp.last_dir != dir && ntohl(th->ack_seq) == ct->proto.tcp.last_end) { /* b) This SYN/ACK acknowledges a SYN that we earlier * ignored as invalid. This means that the client and * the server are both in sync, while the firewall is * not. We get in sync from the previously annotated * values. */ old_state = TCP_CONNTRACK_SYN_SENT; new_state = TCP_CONNTRACK_SYN_RECV; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end = ct->proto.tcp.last_end; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend = ct->proto.tcp.last_end; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin = ct->proto.tcp.last_win == 0 ? 1 : ct->proto.tcp.last_win; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = ct->proto.tcp.last_wscale; ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; nf_ct_tcp_state_reset(&ct->proto.tcp.seen[dir]); break; } ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; ct->proto.tcp.last_seq = ntohl(th->seq); ct->proto.tcp.last_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.last_win = ntohs(th->window); /* a) This is a SYN in ORIGINAL. The client and the server * may be in sync but we are not. In that case, we annotate * the TCP options and let the packet go through. If it is a * valid SYN packet, the server will reply with a SYN/ACK, and * then we'll get in sync. Otherwise, the server potentially * responds with a challenge ACK if implementing RFC5961. */ if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { struct ip_ct_tcp_state seen = {}; ct->proto.tcp.last_flags = ct->proto.tcp.last_wscale = 0; tcp_options(skb, dataoff, th, &seen); if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) { ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_WINDOW_SCALE; ct->proto.tcp.last_wscale = seen.td_scale; } if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) { ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_SACK_PERM; } /* Mark the potential for RFC5961 challenge ACK, * this pose a special problem for LAST_ACK state * as ACK is intrepretated as ACKing last FIN. */ if (old_state == TCP_CONNTRACK_LAST_ACK) ct->proto.tcp.last_flags |= IP_CT_EXP_CHALLENGE_ACK; } /* possible challenge ack reply to syn */ if (old_state == TCP_CONNTRACK_SYN_SENT && index == TCP_ACK_SET && dir == IP_CT_DIR_REPLY) ct->proto.tcp.last_ack = ntohl(th->ack_seq); spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", index, dir, tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Special case for SYN proxy: when the SYN to the server or * the SYN/ACK from the server is lost, the client may transmit * a keep-alive packet while in SYN_SENT state. This needs to * be associated with the original conntrack entry in order to * generate a new SYN with the correct sequence number. */ if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT && index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL && ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL && ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) { pr_debug("nf_ct_tcp: SYN proxy client keep alive\n"); spin_unlock_bh(&ct->lock); return NF_ACCEPT; } /* Invalid packet */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d invalid, state %s", index, dir, tcp_conntrack_names[old_state]); return -NF_ACCEPT; case TCP_CONNTRACK_TIME_WAIT: /* RFC5961 compliance cause stack to send "challenge-ACK" * e.g. in response to spurious SYNs. Conntrack MUST * not believe this ACK is acking last FIN. */ if (old_state == TCP_CONNTRACK_LAST_ACK && index == TCP_ACK_SET && ct->proto.tcp.last_dir != dir && ct->proto.tcp.last_index == TCP_SYN_SET && (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) { /* Detected RFC5961 challenge ACK */ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "challenge-ack ignored"); return NF_ACCEPT; /* Don't change state */ } break; case TCP_CONNTRACK_SYN_SENT2: /* tcp_conntracks table is not smart enough to handle * simultaneous open. */ ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN; break; case TCP_CONNTRACK_SYN_RECV: if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET && ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN) new_state = TCP_CONNTRACK_ESTABLISHED; break; case TCP_CONNTRACK_CLOSE: if (index != TCP_RST_SET) break; /* If we are closing, tuple might have been re-used already. * last_index, last_ack, and all other ct fields used for * sequence/window validation are outdated in that case. * * As the conntrack can already be expired by GC under pressure, * just skip validation checks. */ if (tcp_can_early_drop(ct)) goto in_window; /* td_maxack might be outdated if we let a SYN through earlier */ if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && ct->proto.tcp.last_index != TCP_SYN_SET) { u32 seq = ntohl(th->seq); /* If we are not in established state and SEQ=0 this is most * likely an answer to a SYN we let go through above (last_index * can be updated due to out-of-order ACKs). */ if (seq == 0 && !nf_conntrack_tcp_established(ct)) break; if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) && !tn->tcp_ignore_invalid_rst) { /* Invalid RST */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); return -NF_ACCEPT; } if (!nf_conntrack_tcp_established(ct) || seq == ct->proto.tcp.seen[!dir].td_maxack) break; /* Check if rst is part of train, such as * foo:80 > bar:4379: P, 235946583:235946602(19) ack 42 * foo:80 > bar:4379: R, 235946602:235946602(0) ack 42 */ if (ct->proto.tcp.last_index == TCP_ACK_SET && ct->proto.tcp.last_dir == dir && seq == ct->proto.tcp.last_end) break; /* ... RST sequence number doesn't match exactly, keep * established state to allow a possible challenge ACK. */ new_state = old_state; } if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) || (!test_bit(IPS_ASSURED_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_ACK_SET)) && ntohl(th->ack_seq) == ct->proto.tcp.last_end) { /* RST sent to invalid SYN or ACK we had let through * at a) and c) above: * * a) SYN was in window then * c) we hold a half-open connection. * * Delete our connection entry. * We skip window checking, because packet might ACK * segments we ignored. */ goto in_window; } /* Reset in response to a challenge-ack we let through earlier */ if (old_state == TCP_CONNTRACK_SYN_SENT && ct->proto.tcp.last_index == TCP_ACK_SET && ct->proto.tcp.last_dir == IP_CT_DIR_REPLY && ntohl(th->seq) == ct->proto.tcp.last_ack) goto in_window; break; default: /* Keep compilers happy. */ break; } res = tcp_in_window(ct, dir, index, skb, dataoff, th, state); switch (res) { case NFCT_TCP_IGNORE: spin_unlock_bh(&ct->lock); return NF_ACCEPT; case NFCT_TCP_INVALID: nf_tcp_handle_invalid(ct, dir, index, skb, state); spin_unlock_bh(&ct->lock); return -NF_ACCEPT; case NFCT_TCP_ACCEPT: break; } in_window: /* From now on we have got in-window packets */ ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; ct->proto.tcp.state = new_state; if (old_state != new_state && new_state == TCP_CONNTRACK_FIN_WAIT) ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = tn->timeouts; if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; else if (unlikely(index == TCP_RST_SET)) timeout = timeouts[TCP_CONNTRACK_CLOSE]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; else if (ct->proto.tcp.last_win == 0 && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; else timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { /* If only reply is a RST, we can consider ourselves not to have an established connection: this is a fairly common problem case, so we can delete the conntrack immediately. --RR */ if (th->rst) { nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { /* do not renew timeout on SYN retransmit. * * Else port reuse by client or NAT middlebox can keep * entry alive indefinitely (including nat info). */ return NF_ACCEPT; } /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ if (new_state == TCP_CONNTRACK_ESTABLISHED && timeout > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; } else if (!test_bit(IPS_ASSURED_BIT, &ct->status) && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { /* Set ASSURED if we see valid ack in ESTABLISHED after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); nf_conntrack_event_cache(IPCT_ASSURED, ct); } nf_ct_refresh_acct(ct, ctinfo, skb, timeout); return NF_ACCEPT; } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy) { struct nlattr *nest_parms; struct nf_ct_tcp_flags tmp = {}; spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state)) goto nla_put_failure; if (destroy) goto skip_state; if (nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL, ct->proto.tcp.seen[0].td_scale) || nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY, ct->proto.tcp.seen[1].td_scale)) goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[0].flags; if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, sizeof(struct nf_ct_tcp_flags), &tmp)) goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[1].flags; if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, sizeof(struct nf_ct_tcp_flags), &tmp)) goto nla_put_failure; skip_state: spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { [CTA_PROTOINFO_TCP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) }, [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, }; #define TCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags))) static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) { struct nlattr *pattr = cda[CTA_PROTOINFO_TCP]; struct nlattr *tb[CTA_PROTOINFO_TCP_MAX+1]; int err; /* updates could not contain anything about the private * protocol info, in that case skip the parsing */ if (!pattr) return 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_TCP_MAX, pattr, tcp_nla_policy, NULL); if (err < 0) return err; if (tb[CTA_PROTOINFO_TCP_STATE] && nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) return -EINVAL; spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); if (tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]) { struct nf_ct_tcp_flags *attr = nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]); ct->proto.tcp.seen[0].flags &= ~attr->mask; ct->proto.tcp.seen[0].flags |= attr->flags & attr->mask; } if (tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]) { struct nf_ct_tcp_flags *attr = nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]); ct->proto.tcp.seen[1].flags &= ~attr->mask; ct->proto.tcp.seen[1].flags |= attr->flags & attr->mask; } if (tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] && tb[CTA_PROTOINFO_TCP_WSCALE_REPLY] && ct->proto.tcp.seen[0].flags & IP_CT_TCP_FLAG_WINDOW_SCALE && ct->proto.tcp.seen[1].flags & IP_CT_TCP_FLAG_WINDOW_SCALE) { ct->proto.tcp.seen[0].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL]); ct->proto.tcp.seen[1].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]); } spin_unlock_bh(&ct->lock); return 0; } static unsigned int tcp_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; if (!timeouts) timeouts = tn->timeouts; /* set default TCP timeouts. */ for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++) timeouts[i] = tn->timeouts[i]; if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) { timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; } if (tb[CTA_TIMEOUT_TCP_ESTABLISHED]) { timeouts[TCP_CONNTRACK_ESTABLISHED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_ESTABLISHED]))*HZ; } if (tb[CTA_TIMEOUT_TCP_FIN_WAIT]) { timeouts[TCP_CONNTRACK_FIN_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_FIN_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]) { timeouts[TCP_CONNTRACK_CLOSE_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_LAST_ACK]) { timeouts[TCP_CONNTRACK_LAST_ACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_LAST_ACK]))*HZ; } if (tb[CTA_TIMEOUT_TCP_TIME_WAIT]) { timeouts[TCP_CONNTRACK_TIME_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_TIME_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_CLOSE]) { timeouts[TCP_CONNTRACK_CLOSE] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE]))*HZ; } if (tb[CTA_TIMEOUT_TCP_SYN_SENT2]) { timeouts[TCP_CONNTRACK_SYN_SENT2] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT2]))*HZ; } if (tb[CTA_TIMEOUT_TCP_RETRANS]) { timeouts[TCP_CONNTRACK_RETRANS] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_RETRANS]))*HZ; } if (tb[CTA_TIMEOUT_TCP_UNACK]) { timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } static int tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; if (nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT, htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_RECV, htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_LAST_ACK, htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE, htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_RETRANS, htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_UNACK, htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_SYN_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_SYN_RECV] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_ESTABLISHED] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_FIN_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_CLOSE_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_LAST_ACK] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_TIME_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_CLOSE] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_SYN_SENT2] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_tcp_init_net(struct net *net) { struct nf_tcp_net *tn = nf_tcp_pernet(net); int i; for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; /* timeouts[0] is unused, make it same as SYN_SENT so * ->timeouts[0] contains 'new' timeout, like udp or icmp. */ tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; /* If it is set to zero, we disable picking up already established * connections. */ tn->tcp_loose = 1; /* "Be conservative in what you do, * be liberal in what you accept from others." * If it's non-zero, we mark only out of window RST segments as INVALID. */ tn->tcp_be_liberal = 0; /* If it's non-zero, we turn off RST sequence number check */ tn->tcp_ignore_invalid_rst = 0; /* Max number of the retransmitted packets without receiving an (acceptable) * ACK from the destination. If this number is reached, a shorter timer * will be started. */ tn->tcp_max_retrans = 3; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; #endif } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = { .l4proto = IPPROTO_TCP, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = tcp_print_conntrack, #endif .can_early_drop = tcp_can_early_drop, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .to_nlattr = tcp_to_nlattr, .from_nlattr = nlattr_to_tcp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nlattr_tuple_size = tcp_nlattr_tuple_size, .nlattr_size = TCP_NLATTR_SIZE, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_TCP_MAX, .obj_size = sizeof(unsigned int) * TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 114 114 97 3 3 2 2 122 11 111 2 1 3 111 123 9 111 3 3 3 121 128 8 121 120 1 1 1 1 120 57 128 8 120 115 5 4 5 5 5 123 44 79 79 79 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 1996-2000 Russell King. * * Scan ADFS partitions on hard disk drives. Unfortunately, there * isn't a standard for partitioning drives on Acorn machines, so * every single manufacturer of SCSI and IDE cards created their own * method. */ #include <linux/buffer_head.h> #include <linux/adfs_fs.h> #include "check.h" /* * Partition types. (Oh for reusability) */ #define PARTITION_RISCIX_MFM 1 #define PARTITION_RISCIX_SCSI 2 #define PARTITION_LINUX 9 #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static struct adfs_discrecord * adfs_partition(struct parsed_partitions *state, char *name, char *data, unsigned long first_sector, int slot) { struct adfs_discrecord *dr; unsigned int nr_sects; if (adfs_checkbblk(data)) return NULL; dr = (struct adfs_discrecord *)(data + 0x1c0); if (dr->disc_size == 0 && dr->disc_size_high == 0) return NULL; nr_sects = (le32_to_cpu(dr->disc_size_high) << 23) | (le32_to_cpu(dr->disc_size) >> 9); if (name) { strlcat(state->pp_buf, " [", PAGE_SIZE); strlcat(state->pp_buf, name, PAGE_SIZE); strlcat(state->pp_buf, "]", PAGE_SIZE); } put_partition(state, slot, first_sector, nr_sects); return dr; } #endif #ifdef CONFIG_ACORN_PARTITION_RISCIX struct riscix_part { __le32 start; __le32 length; __le32 one; char name[16]; }; struct riscix_record { __le32 magic; #define RISCIX_MAGIC cpu_to_le32(0x4a657320) __le32 date; struct riscix_part part[8]; }; #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static int riscix_partition(struct parsed_partitions *state, unsigned long first_sect, int slot, unsigned long nr_sects) { Sector sect; struct riscix_record *rr; rr = read_part_sector(state, first_sect, §); if (!rr) return -1; strlcat(state->pp_buf, " [RISCiX]", PAGE_SIZE); if (rr->magic == RISCIX_MAGIC) { unsigned long size = nr_sects > 2 ? 2 : nr_sects; int part; strlcat(state->pp_buf, " <", PAGE_SIZE); put_partition(state, slot++, first_sect, size); for (part = 0; part < 8; part++) { if (rr->part[part].one && memcmp(rr->part[part].name, "All\0", 4)) { put_partition(state, slot++, le32_to_cpu(rr->part[part].start), le32_to_cpu(rr->part[part].length)); strlcat(state->pp_buf, "(", PAGE_SIZE); strlcat(state->pp_buf, rr->part[part].name, PAGE_SIZE); strlcat(state->pp_buf, ")", PAGE_SIZE); } } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } else { put_partition(state, slot++, first_sect, nr_sects); } put_dev_sector(sect); return slot; } #endif #endif #define LINUX_NATIVE_MAGIC 0xdeafa1de #define LINUX_SWAP_MAGIC 0xdeafab1e struct linux_part { __le32 magic; __le32 start_sect; __le32 nr_sects; }; #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static int linux_partition(struct parsed_partitions *state, unsigned long first_sect, int slot, unsigned long nr_sects) { Sector sect; struct linux_part *linuxp; unsigned long size = nr_sects > 2 ? 2 : nr_sects; strlcat(state->pp_buf, " [Linux]", PAGE_SIZE); put_partition(state, slot++, first_sect, size); linuxp = read_part_sector(state, first_sect, §); if (!linuxp) return -1; strlcat(state->pp_buf, " <", PAGE_SIZE); while (linuxp->magic == cpu_to_le32(LINUX_NATIVE_MAGIC) || linuxp->magic == cpu_to_le32(LINUX_SWAP_MAGIC)) { if (slot == state->limit) break; put_partition(state, slot++, first_sect + le32_to_cpu(linuxp->start_sect), le32_to_cpu(linuxp->nr_sects)); linuxp ++; } strlcat(state->pp_buf, " >", PAGE_SIZE); put_dev_sector(sect); return slot; } #endif #ifdef CONFIG_ACORN_PARTITION_CUMANA int adfspart_check_CUMANA(struct parsed_partitions *state) { unsigned long first_sector = 0; unsigned int start_blk = 0; Sector sect; unsigned char *data; char *name = "CUMANA/ADFS"; int first = 1; int slot = 1; /* * Try Cumana style partitions - sector 6 contains ADFS boot block * with pointer to next 'drive'. * * There are unknowns in this code - is the 'cylinder number' of the * next partition relative to the start of this one - I'm assuming * it is. * * Also, which ID did Cumana use? * * This is totally unfinished, and will require more work to get it * going. Hence it is totally untested. */ do { struct adfs_discrecord *dr; unsigned int nr_sects; data = read_part_sector(state, start_blk * 2 + 6, §); if (!data) return -1; if (slot == state->limit) break; dr = adfs_partition(state, name, data, first_sector, slot++); if (!dr) break; name = NULL; nr_sects = (data[0x1fd] + (data[0x1fe] << 8)) * (dr->heads + (dr->lowsector & 0x40 ? 1 : 0)) * dr->secspertrack; if (!nr_sects) break; first = 0; first_sector += nr_sects; start_blk += nr_sects >> (BLOCK_SIZE_BITS - 9); nr_sects = 0; /* hmm - should be partition size */ switch (data[0x1fc] & 15) { case 0: /* No partition / ADFS? */ break; #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: /* RISCiX - we don't know how to find the next one. */ slot = riscix_partition(state, first_sector, slot, nr_sects); break; #endif case PARTITION_LINUX: slot = linux_partition(state, first_sector, slot, nr_sects); break; } put_dev_sector(sect); if (slot == -1) return -1; } while (1); put_dev_sector(sect); return first ? 0 : 1; } #endif #ifdef CONFIG_ACORN_PARTITION_ADFS /* * Purpose: allocate ADFS partitions. * * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * * Returns: -1 on error, 0 for no ADFS boot sector, 1 for ok. * * Alloc : hda = whole drive * hda1 = ADFS partition on first drive. * hda2 = non-ADFS partition. */ int adfspart_check_ADFS(struct parsed_partitions *state) { unsigned long start_sect, nr_sects, sectscyl, heads; Sector sect; unsigned char *data; struct adfs_discrecord *dr; unsigned char id; int slot = 1; data = read_part_sector(state, 6, §); if (!data) return -1; dr = adfs_partition(state, "ADFS", data, 0, slot++); if (!dr) { put_dev_sector(sect); return 0; } heads = dr->heads + ((dr->lowsector >> 6) & 1); sectscyl = dr->secspertrack * heads; start_sect = ((data[0x1fe] << 8) + data[0x1fd]) * sectscyl; id = data[0x1fc] & 15; put_dev_sector(sect); /* * Work out start of non-adfs partition. */ nr_sects = get_capacity(state->disk) - start_sect; if (start_sect) { switch (id) { #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: case PARTITION_RISCIX_MFM: riscix_partition(state, start_sect, slot, nr_sects); break; #endif case PARTITION_LINUX: linux_partition(state, start_sect, slot, nr_sects); break; } } strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_ICS struct ics_part { __le32 start; __le32 size; }; static int adfspart_check_ICSLinux(struct parsed_partitions *state, unsigned long block) { Sector sect; unsigned char *data = read_part_sector(state, block, §); int result = 0; if (data) { if (memcmp(data, "LinuxPart", 9) == 0) result = 1; put_dev_sector(sect); } return result; } /* * Check for a valid ICS partition using the checksum. */ static inline int valid_ics_sector(const unsigned char *data) { unsigned long sum; int i; for (i = 0, sum = 0x50617274; i < 508; i++) sum += data[i]; sum -= le32_to_cpu(*(__le32 *)(&data[508])); return sum == 0; } /* * Purpose: allocate ICS partitions. * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * Returns: -1 on error, 0 for no ICS table, 1 for partitions ok. * Alloc : hda = whole drive * hda1 = ADFS partition 0 on first drive. * hda2 = ADFS partition 1 on first drive. * ..etc.. */ int adfspart_check_ICS(struct parsed_partitions *state) { const unsigned char *data; const struct ics_part *p; int slot; Sector sect; /* * Try ICS style partitions - sector 0 contains partition info. */ data = read_part_sector(state, 0, §); if (!data) return -1; if (!valid_ics_sector(data)) { put_dev_sector(sect); return 0; } strlcat(state->pp_buf, " [ICS]", PAGE_SIZE); for (slot = 1, p = (const struct ics_part *)data; p->size; p++) { u32 start = le32_to_cpu(p->start); s32 size = le32_to_cpu(p->size); /* yes, it's signed. */ if (slot == state->limit) break; /* * Negative sizes tell the RISC OS ICS driver to ignore * this partition - in effect it says that this does not * contain an ADFS filesystem. */ if (size < 0) { size = -size; /* * Our own extension - We use the first sector * of the partition to identify what type this * partition is. We must not make this visible * to the filesystem. */ if (size > 1 && adfspart_check_ICSLinux(state, start)) { start += 1; size -= 1; } } if (size) put_partition(state, slot++, start, size); } put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC struct ptec_part { __le32 unused1; __le32 unused2; __le32 start; __le32 size; __le32 unused5; char type[8]; }; static inline int valid_ptec_sector(const unsigned char *data) { unsigned char checksum = 0x2a; int i; /* * If it looks like a PC/BIOS partition, then it * probably isn't PowerTec. */ if (data[510] == 0x55 && data[511] == 0xaa) return 0; for (i = 0; i < 511; i++) checksum += data[i]; return checksum == data[511]; } /* * Purpose: allocate ICS partitions. * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * Returns: -1 on error, 0 for no ICS table, 1 for partitions ok. * Alloc : hda = whole drive * hda1 = ADFS partition 0 on first drive. * hda2 = ADFS partition 1 on first drive. * ..etc.. */ int adfspart_check_POWERTEC(struct parsed_partitions *state) { Sector sect; const unsigned char *data; const struct ptec_part *p; int slot = 1; int i; data = read_part_sector(state, 0, §); if (!data) return -1; if (!valid_ptec_sector(data)) { put_dev_sector(sect); return 0; } strlcat(state->pp_buf, " [POWERTEC]", PAGE_SIZE); for (i = 0, p = (const struct ptec_part *)data; i < 12; i++, p++) { u32 start = le32_to_cpu(p->start); u32 size = le32_to_cpu(p->size); if (size) put_partition(state, slot++, start, size); } put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_EESOX struct eesox_part { char magic[6]; char name[10]; __le32 start; __le32 unused6; __le32 unused7; __le32 unused8; }; /* * Guess who created this format? */ static const char eesox_name[] = { 'N', 'e', 'i', 'l', ' ', 'C', 'r', 'i', 't', 'c', 'h', 'e', 'l', 'l', ' ', ' ' }; /* * EESOX SCSI partition format. * * This is a goddamned awful partition format. We don't seem to store * the size of the partition in this table, only the start addresses. * * There are two possibilities where the size comes from: * 1. The individual ADFS boot block entries that are placed on the disk. * 2. The start address of the next entry. */ int adfspart_check_EESOX(struct parsed_partitions *state) { Sector sect; const unsigned char *data; unsigned char buffer[256]; struct eesox_part *p; sector_t start = 0; int i, slot = 1; data = read_part_sector(state, 7, §); if (!data) return -1; /* * "Decrypt" the partition table. God knows why... */ for (i = 0; i < 256; i++) buffer[i] = data[i] ^ eesox_name[i & 15]; put_dev_sector(sect); for (i = 0, p = (struct eesox_part *)buffer; i < 8; i++, p++) { sector_t next; if (memcmp(p->magic, "Eesox", 6)) break; next = le32_to_cpu(p->start); if (i) put_partition(state, slot++, start, next - start); start = next; } if (i != 0) { sector_t size; size = get_capacity(state->disk); put_partition(state, slot++, start, size - start); strlcat(state->pp_buf, "\n", PAGE_SIZE); } return i ? 1 : 0; } #endif |
| 5 5 2 2 2 2 5 5 2 2 5 5 5 5 5 5 1 5 5 5 1 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 1 1 5 5 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 6 6 6 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2016 Oracle. All Rights Reserved. * Author: Darrick J. Wong <darrick.wong@oracle.com> */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_btree.h" #include "xfs_bmap.h" #include "xfs_refcount_btree.h" #include "xfs_alloc.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_bit.h" #include "xfs_refcount.h" #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_refcount_item.h" #include "xfs_rtgroup.h" #include "xfs_rtalloc.h" #include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_refcount_intent_cache; /* Allowable refcount adjustment amounts. */ enum xfs_refc_adjust_op { XFS_REFCOUNT_ADJUST_INCREASE = 1, XFS_REFCOUNT_ADJUST_DECREASE = -1, XFS_REFCOUNT_ADJUST_COW_ALLOC = 0, XFS_REFCOUNT_ADJUST_COW_FREE = -1, }; STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur, xfs_agblock_t agbno, xfs_extlen_t aglen); STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur, xfs_agblock_t agbno, xfs_extlen_t aglen); /* * Look up the first record less than or equal to [bno, len] in the btree * given by cur. */ int xfs_refcount_lookup_le( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat); } /* * Look up the first record greater than or equal to [bno, len] in the btree * given by cur. */ int xfs_refcount_lookup_ge( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_GE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); } /* * Look up the first record equal to [bno, len] in the btree * given by cur. */ int xfs_refcount_lookup_eq( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); } /* Convert on-disk record to in-core format. */ void xfs_refcount_btrec_to_irec( const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec) { uint32_t start; start = be32_to_cpu(rec->refc.rc_startblock); if (start & XFS_REFC_COWFLAG) { start &= ~XFS_REFC_COWFLAG; irec->rc_domain = XFS_REFC_DOMAIN_COW; } else { irec->rc_domain = XFS_REFC_DOMAIN_SHARED; } irec->rc_startblock = start; irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount); irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); } /* Simple checks for refcount records. */ xfs_failaddr_t xfs_refcount_check_irec( struct xfs_perag *pag, const struct xfs_refcount_irec *irec) { if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) return __this_address; if (!xfs_refcount_check_domain(irec)) return __this_address; /* check for valid extent range, including overflow */ if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) return __this_address; if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) return __this_address; return NULL; } xfs_failaddr_t xfs_rtrefcount_check_irec( struct xfs_rtgroup *rtg, const struct xfs_refcount_irec *irec) { if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) return __this_address; if (!xfs_refcount_check_domain(irec)) return __this_address; /* check for valid extent range, including overflow */ if (!xfs_verify_rgbext(rtg, irec->rc_startblock, irec->rc_blockcount)) return __this_address; if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) return __this_address; return NULL; } static inline xfs_failaddr_t xfs_refcount_check_btrec( struct xfs_btree_cur *cur, const struct xfs_refcount_irec *irec) { if (xfs_btree_is_rtrefcount(cur->bc_ops)) return xfs_rtrefcount_check_irec(to_rtg(cur->bc_group), irec); return xfs_refcount_check_irec(to_perag(cur->bc_group), irec); } static inline int xfs_refcount_complain_bad_rec( struct xfs_btree_cur *cur, xfs_failaddr_t fa, const struct xfs_refcount_irec *irec) { struct xfs_mount *mp = cur->bc_mp; if (xfs_btree_is_rtrefcount(cur->bc_ops)) { xfs_warn(mp, "RT Refcount BTree record corruption in rtgroup %u detected at %pS!", cur->bc_group->xg_gno, fa); } else { xfs_warn(mp, "Refcount BTree record corruption in AG %d detected at %pS!", cur->bc_group->xg_gno, fa); } xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } /* * Get the data from the pointed-to record. */ int xfs_refcount_get_rec( struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat) { union xfs_btree_rec *rec; xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !*stat) return error; xfs_refcount_btrec_to_irec(rec, irec); fa = xfs_refcount_check_btrec(cur, irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, irec); trace_xfs_refcount_get(cur, irec); return 0; } /* * Update the record referred to by cur to the value given * by [bno, len, refcount]. * This either works (return 0) or gets an EFSCORRUPTED error. */ STATIC int xfs_refcount_update( struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec) { union xfs_btree_rec rec; uint32_t start; int error; trace_xfs_refcount_update(cur, irec); start = xfs_refcount_encode_startblock(irec->rc_startblock, irec->rc_domain); rec.refc.rc_startblock = cpu_to_be32(start); rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount); rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount); error = xfs_btree_update(cur, &rec); if (error) trace_xfs_refcount_update_error(cur, error, _RET_IP_); return error; } /* * Insert the record referred to by cur to the value given * by [bno, len, refcount]. * This either works (return 0) or gets an EFSCORRUPTED error. */ int xfs_refcount_insert( struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *i) { int error; trace_xfs_refcount_insert(cur, irec); cur->bc_rec.rc.rc_startblock = irec->rc_startblock; cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount; cur->bc_rec.rc.rc_refcount = irec->rc_refcount; cur->bc_rec.rc.rc_domain = irec->rc_domain; error = xfs_btree_insert(cur, i); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } out_error: if (error) trace_xfs_refcount_insert_error(cur, error, _RET_IP_); return error; } /* * Remove the record referred to by cur, then set the pointer to the spot * where the record could be re-inserted, in case we want to increment or * decrement the cursor. * This either works (return 0) or gets an EFSCORRUPTED error. */ STATIC int xfs_refcount_delete( struct xfs_btree_cur *cur, int *i) { struct xfs_refcount_irec irec; int found_rec; int error; error = xfs_refcount_get_rec(cur, &irec, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } trace_xfs_refcount_delete(cur, &irec); error = xfs_btree_delete(cur, i); if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (error) goto out_error; error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock, &found_rec); out_error: if (error) trace_xfs_refcount_delete_error(cur, error, _RET_IP_); return error; } /* * Adjusting the Reference Count * * As stated elsewhere, the reference count btree (refcbt) stores * >1 reference counts for extents of physical blocks. In this * operation, we're either raising or lowering the reference count of * some subrange stored in the tree: * * <------ adjustment range ------> * ----+ +---+-----+ +--+--------+--------- * 2 | | 3 | 4 | |17| 55 | 10 * ----+ +---+-----+ +--+--------+--------- * X axis is physical blocks number; * reference counts are the numbers inside the rectangles * * The first thing we need to do is to ensure that there are no * refcount extents crossing either boundary of the range to be * adjusted. For any extent that does cross a boundary, split it into * two extents so that we can increment the refcount of one of the * pieces later: * * <------ adjustment range ------> * ----+ +---+-----+ +--+--------+----+---- * 2 | | 3 | 2 | |17| 55 | 10 | 10 * ----+ +---+-----+ +--+--------+----+---- * * For this next step, let's assume that all the physical blocks in * the adjustment range are mapped to a file and are therefore in use * at least once. Therefore, we can infer that any gap in the * refcount tree within the adjustment range represents a physical * extent with refcount == 1: * * <------ adjustment range ------> * ----+---+---+-----+-+--+--------+----+---- * 2 |"1"| 3 | 2 |1|17| 55 | 10 | 10 * ----+---+---+-----+-+--+--------+----+---- * ^ * * For each extent that falls within the interval range, figure out * which extent is to the left or the right of that extent. Now we * have a left, current, and right extent. If the new reference count * of the center extent enables us to merge left, center, and right * into one record covering all three, do so. If the center extent is * at the left end of the range, abuts the left extent, and its new * reference count matches the left extent's record, then merge them. * If the center extent is at the right end of the range, abuts the * right extent, and the reference counts match, merge those. In the * example, we can left merge (assuming an increment operation): * * <------ adjustment range ------> * --------+---+-----+-+--+--------+----+---- * 2 | 3 | 2 |1|17| 55 | 10 | 10 * --------+---+-----+-+--+--------+----+---- * ^ * * For all other extents within the range, adjust the reference count * or delete it if the refcount falls below 2. If we were * incrementing, the end result looks like this: * * <------ adjustment range ------> * --------+---+-----+-+--+--------+----+---- * 2 | 4 | 3 |2|18| 56 | 11 | 10 * --------+---+-----+-+--+--------+----+---- * * The result of a decrement operation looks as such: * * <------ adjustment range ------> * ----+ +---+ +--+--------+----+---- * 2 | | 2 | |16| 54 | 9 | 10 * ----+ +---+ +--+--------+----+---- * DDDD 111111DD * * The blocks marked "D" are freed; the blocks marked "1" are only * referenced once and therefore the record is removed from the * refcount btree. */ /* Next block after this extent. */ static inline xfs_agblock_t xfs_refc_next( struct xfs_refcount_irec *rc) { return rc->rc_startblock + rc->rc_blockcount; } /* * Split a refcount extent that crosses agbno. */ STATIC int xfs_refcount_split_extent( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t agbno, bool *shape_changed) { struct xfs_refcount_irec rcext, tmp; int found_rec; int error; *shape_changed = false; error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec); if (error) goto out_error; if (!found_rec) return 0; error = xfs_refcount_get_rec(cur, &rcext, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (rcext.rc_domain != domain) return 0; if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno) return 0; *shape_changed = true; trace_xfs_refcount_split_extent(cur, &rcext, agbno); /* Establish the right extent. */ tmp = rcext; tmp.rc_startblock = agbno; tmp.rc_blockcount -= (agbno - rcext.rc_startblock); error = xfs_refcount_update(cur, &tmp); if (error) goto out_error; /* Insert the left extent. */ tmp = rcext; tmp.rc_blockcount = agbno - rcext.rc_startblock; error = xfs_refcount_insert(cur, &tmp, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } return error; out_error: trace_xfs_refcount_split_extent_error(cur, error, _RET_IP_); return error; } /* * Merge the left, center, and right extents. */ STATIC int xfs_refcount_merge_center_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *left, struct xfs_refcount_irec *center, struct xfs_refcount_irec *right, unsigned long long extlen, xfs_extlen_t *aglen) { int error; int found_rec; trace_xfs_refcount_merge_center_extents(cur, left, center, right); ASSERT(left->rc_domain == center->rc_domain); ASSERT(right->rc_domain == center->rc_domain); /* * Make sure the center and right extents are not in the btree. * If the center extent was synthesized, the first delete call * removes the right extent and we skip the second deletion. * If center and right were in the btree, then the first delete * call removes the center and the second one removes the right * extent. */ error = xfs_refcount_lookup_ge(cur, center->rc_domain, center->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (center->rc_refcount > 1) { error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } /* Enlarge the left extent. */ error = xfs_refcount_lookup_le(cur, left->rc_domain, left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } left->rc_blockcount = extlen; error = xfs_refcount_update(cur, left); if (error) goto out_error; *aglen = 0; return error; out_error: trace_xfs_refcount_merge_center_extents_error(cur, error, _RET_IP_); return error; } /* * Merge with the left extent. */ STATIC int xfs_refcount_merge_left_extent( struct xfs_btree_cur *cur, struct xfs_refcount_irec *left, struct xfs_refcount_irec *cleft, xfs_agblock_t *agbno, xfs_extlen_t *aglen) { int error; int found_rec; trace_xfs_refcount_merge_left_extent(cur, left, cleft); ASSERT(left->rc_domain == cleft->rc_domain); /* If the extent at agbno (cleft) wasn't synthesized, remove it. */ if (cleft->rc_refcount > 1) { error = xfs_refcount_lookup_le(cur, cleft->rc_domain, cleft->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } /* Enlarge the left extent. */ error = xfs_refcount_lookup_le(cur, left->rc_domain, left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } left->rc_blockcount += cleft->rc_blockcount; error = xfs_refcount_update(cur, left); if (error) goto out_error; *agbno += cleft->rc_blockcount; *aglen -= cleft->rc_blockcount; return error; out_error: trace_xfs_refcount_merge_left_extent_error(cur, error, _RET_IP_); return error; } /* * Merge with the right extent. */ STATIC int xfs_refcount_merge_right_extent( struct xfs_btree_cur *cur, struct xfs_refcount_irec *right, struct xfs_refcount_irec *cright, xfs_extlen_t *aglen) { int error; int found_rec; trace_xfs_refcount_merge_right_extent(cur, cright, right); ASSERT(right->rc_domain == cright->rc_domain); /* * If the extent ending at agbno+aglen (cright) wasn't synthesized, * remove it. */ if (cright->rc_refcount > 1) { error = xfs_refcount_lookup_le(cur, cright->rc_domain, cright->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } /* Enlarge the right extent. */ error = xfs_refcount_lookup_le(cur, right->rc_domain, right->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } right->rc_startblock -= cright->rc_blockcount; right->rc_blockcount += cright->rc_blockcount; error = xfs_refcount_update(cur, right); if (error) goto out_error; *aglen -= cright->rc_blockcount; return error; out_error: trace_xfs_refcount_merge_right_extent_error(cur, error, _RET_IP_); return error; } /* * Find the left extent and the one after it (cleft). This function assumes * that we've already split any extent crossing agbno. */ STATIC int xfs_refcount_find_left_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *left, struct xfs_refcount_irec *cleft, enum xfs_refc_domain domain, xfs_agblock_t agbno, xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK; error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec); if (error) goto out_error; if (!found_rec) return 0; error = xfs_refcount_get_rec(cur, &tmp, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != domain) return 0; if (xfs_refc_next(&tmp) != agbno) return 0; /* We have a left extent; retrieve (or invent) the next right one */ *left = tmp; error = xfs_btree_increment(cur, 0, &found_rec); if (error) goto out_error; if (found_rec) { error = xfs_refcount_get_rec(cur, &tmp, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != domain) goto not_found; /* if tmp starts at the end of our range, just use that */ if (tmp.rc_startblock == agbno) *cleft = tmp; else { /* * There's a gap in the refcntbt at the start of the * range we're interested in (refcount == 1) so * synthesize the implied extent and pass it back. * We assume here that the agbno/aglen range was * passed in from a data fork extent mapping and * therefore is allocated to exactly one owner. */ cleft->rc_startblock = agbno; cleft->rc_blockcount = min(aglen, tmp.rc_startblock - agbno); cleft->rc_refcount = 1; cleft->rc_domain = domain; } } else { not_found: /* * No extents, so pretend that there's one covering the whole * range. */ cleft->rc_startblock = agbno; cleft->rc_blockcount = aglen; cleft->rc_refcount = 1; cleft->rc_domain = domain; } trace_xfs_refcount_find_left_extent(cur, left, cleft, agbno); return error; out_error: trace_xfs_refcount_find_left_extent_error(cur, error, _RET_IP_); return error; } /* * Find the right extent and the one before it (cright). This function * assumes that we've already split any extents crossing agbno + aglen. */ STATIC int xfs_refcount_find_right_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *right, struct xfs_refcount_irec *cright, enum xfs_refc_domain domain, xfs_agblock_t agbno, xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; right->rc_startblock = cright->rc_startblock = NULLAGBLOCK; error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec); if (error) goto out_error; if (!found_rec) return 0; error = xfs_refcount_get_rec(cur, &tmp, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != domain) return 0; if (tmp.rc_startblock != agbno + aglen) return 0; /* We have a right extent; retrieve (or invent) the next left one */ *right = tmp; error = xfs_btree_decrement(cur, 0, &found_rec); if (error) goto out_error; if (found_rec) { error = xfs_refcount_get_rec(cur, &tmp, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != domain) goto not_found; /* if tmp ends at the end of our range, just use that */ if (xfs_refc_next(&tmp) == agbno + aglen) *cright = tmp; else { /* * There's a gap in the refcntbt at the end of the * range we're interested in (refcount == 1) so * create the implied extent and pass it back. * We assume here that the agbno/aglen range was * passed in from a data fork extent mapping and * therefore is allocated to exactly one owner. */ cright->rc_startblock = max(agbno, xfs_refc_next(&tmp)); cright->rc_blockcount = right->rc_startblock - cright->rc_startblock; cright->rc_refcount = 1; cright->rc_domain = domain; } } else { not_found: /* * No extents, so pretend that there's one covering the whole * range. */ cright->rc_startblock = agbno; cright->rc_blockcount = aglen; cright->rc_refcount = 1; cright->rc_domain = domain; } trace_xfs_refcount_find_right_extent(cur, cright, right, agbno + aglen); return error; out_error: trace_xfs_refcount_find_right_extent_error(cur, error, _RET_IP_); return error; } /* Is this extent valid? */ static inline bool xfs_refc_valid( const struct xfs_refcount_irec *rc) { return rc->rc_startblock != NULLAGBLOCK; } static inline xfs_nlink_t xfs_refc_merge_refcount( const struct xfs_refcount_irec *irec, enum xfs_refc_adjust_op adjust) { /* Once a record hits XFS_REFC_REFCOUNT_MAX, it is pinned forever */ if (irec->rc_refcount == XFS_REFC_REFCOUNT_MAX) return XFS_REFC_REFCOUNT_MAX; return irec->rc_refcount + adjust; } static inline bool xfs_refc_want_merge_center( const struct xfs_refcount_irec *left, const struct xfs_refcount_irec *cleft, const struct xfs_refcount_irec *cright, const struct xfs_refcount_irec *right, bool cleft_is_cright, enum xfs_refc_adjust_op adjust, unsigned long long *ulenp) { unsigned long long ulen = left->rc_blockcount; xfs_nlink_t new_refcount; /* * To merge with a center record, both shoulder records must be * adjacent to the record we want to adjust. This is only true if * find_left and find_right made all four records valid. */ if (!xfs_refc_valid(left) || !xfs_refc_valid(right) || !xfs_refc_valid(cleft) || !xfs_refc_valid(cright)) return false; /* There must only be one record for the entire range. */ if (!cleft_is_cright) return false; /* The shoulder record refcounts must match the new refcount. */ new_refcount = xfs_refc_merge_refcount(cleft, adjust); if (left->rc_refcount != new_refcount) return false; if (right->rc_refcount != new_refcount) return false; /* * The new record cannot exceed the max length. ulen is a ULL as the * individual record block counts can be up to (u32 - 1) in length * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount + right->rc_blockcount; if (ulen >= XFS_REFC_LEN_MAX) return false; *ulenp = ulen; return true; } static inline bool xfs_refc_want_merge_left( const struct xfs_refcount_irec *left, const struct xfs_refcount_irec *cleft, enum xfs_refc_adjust_op adjust) { unsigned long long ulen = left->rc_blockcount; xfs_nlink_t new_refcount; /* * For a left merge, the left shoulder record must be adjacent to the * start of the range. If this is true, find_left made left and cleft * contain valid contents. */ if (!xfs_refc_valid(left) || !xfs_refc_valid(cleft)) return false; /* Left shoulder record refcount must match the new refcount. */ new_refcount = xfs_refc_merge_refcount(cleft, adjust); if (left->rc_refcount != new_refcount) return false; /* * The new record cannot exceed the max length. ulen is a ULL as the * individual record block counts can be up to (u32 - 1) in length * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount; if (ulen >= XFS_REFC_LEN_MAX) return false; return true; } static inline bool xfs_refc_want_merge_right( const struct xfs_refcount_irec *cright, const struct xfs_refcount_irec *right, enum xfs_refc_adjust_op adjust) { unsigned long long ulen = right->rc_blockcount; xfs_nlink_t new_refcount; /* * For a right merge, the right shoulder record must be adjacent to the * end of the range. If this is true, find_right made cright and right * contain valid contents. */ if (!xfs_refc_valid(right) || !xfs_refc_valid(cright)) return false; /* Right shoulder record refcount must match the new refcount. */ new_refcount = xfs_refc_merge_refcount(cright, adjust); if (right->rc_refcount != new_refcount) return false; /* * The new record cannot exceed the max length. ulen is a ULL as the * individual record block counts can be up to (u32 - 1) in length * hence we need to catch u32 addition overflows here. */ ulen += cright->rc_blockcount; if (ulen >= XFS_REFC_LEN_MAX) return false; return true; } /* * Try to merge with any extents on the boundaries of the adjustment range. */ STATIC int xfs_refcount_merge_extents( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t *agbno, xfs_extlen_t *aglen, enum xfs_refc_adjust_op adjust, bool *shape_changed) { struct xfs_refcount_irec left = {0}, cleft = {0}; struct xfs_refcount_irec cright = {0}, right = {0}; int error; unsigned long long ulen; bool cequal; *shape_changed = false; /* * Find the extent just below agbno [left], just above agbno [cleft], * just below (agbno + aglen) [cright], and just above (agbno + aglen) * [right]. */ error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain, *agbno, *aglen); if (error) return error; error = xfs_refcount_find_right_extents(cur, &right, &cright, domain, *agbno, *aglen); if (error) return error; /* No left or right extent to merge; exit. */ if (!xfs_refc_valid(&left) && !xfs_refc_valid(&right)) return 0; cequal = (cleft.rc_startblock == cright.rc_startblock) && (cleft.rc_blockcount == cright.rc_blockcount); /* Try to merge left, cleft, and right. cleft must == cright. */ if (xfs_refc_want_merge_center(&left, &cleft, &cright, &right, cequal, adjust, &ulen)) { *shape_changed = true; return xfs_refcount_merge_center_extents(cur, &left, &cleft, &right, ulen, aglen); } /* Try to merge left and cleft. */ if (xfs_refc_want_merge_left(&left, &cleft, adjust)) { *shape_changed = true; error = xfs_refcount_merge_left_extent(cur, &left, &cleft, agbno, aglen); if (error) return error; /* * If we just merged left + cleft and cleft == cright, * we no longer have a cright to merge with right. We're done. */ if (cequal) return 0; } /* Try to merge cright and right. */ if (xfs_refc_want_merge_right(&cright, &right, adjust)) { *shape_changed = true; return xfs_refcount_merge_right_extent(cur, &right, &cright, aglen); } return 0; } /* * XXX: This is a pretty hand-wavy estimate. The penalty for guessing * true incorrectly is a shutdown FS; the penalty for guessing false * incorrectly is more transaction rolls than might be necessary. * Be conservative here. */ static bool xfs_refcount_still_have_space( struct xfs_btree_cur *cur) { unsigned long overhead; /* * Worst case estimate: full splits of the free space and rmap btrees * to handle each of the shape changes to the refcount btree. */ overhead = xfs_allocfree_block_count(cur->bc_mp, cur->bc_refc.shape_changes); overhead += cur->bc_maxlevels; overhead *= cur->bc_mp->m_sb.sb_blocksize; /* * Only allow 2 refcount extent updates per transaction if the * refcount continue update "error" has been injected. */ if (cur->bc_refc.nr_ops > 2 && XFS_TEST_ERROR(cur->bc_mp, XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE)) return false; if (cur->bc_refc.nr_ops == 0) return true; else if (overhead > cur->bc_tp->t_log_res) return false; return cur->bc_tp->t_log_res - overhead > cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } /* Schedule an extent free. */ static int xrefc_free_extent( struct xfs_btree_cur *cur, struct xfs_refcount_irec *rec) { unsigned int flags = 0; if (xfs_btree_is_rtrefcount(cur->bc_ops)) flags |= XFS_FREE_EXTENT_REALTIME; return xfs_free_extent_later(cur->bc_tp, xfs_gbno_to_fsb(cur->bc_group, rec->rc_startblock), rec->rc_blockcount, NULL, XFS_AG_RESV_NONE, flags); } /* * Adjust the refcounts of middle extents. At this point we should have * split extents that crossed the adjustment range; merged with adjacent * extents; and updated agbno/aglen to reflect the merges. Therefore, * all we have to do is update the extents inside [agbno, agbno + aglen]. */ STATIC int xfs_refcount_adjust_extents( struct xfs_btree_cur *cur, xfs_agblock_t *agbno, xfs_extlen_t *aglen, enum xfs_refc_adjust_op adj) { struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; /* Merging did all the work already. */ if (*aglen == 0) return 0; error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno, &found_rec); if (error) goto out_error; while (*aglen > 0 && xfs_refcount_still_have_space(cur)) { error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_SHARED; } /* * Deal with a hole in the refcount tree; if a file maps to * these blocks and there's no refcountbt record, pretend that * there is one with refcount == 1. */ if (ext.rc_startblock != *agbno) { tmp.rc_startblock = *agbno; tmp.rc_blockcount = min(*aglen, ext.rc_startblock - *agbno); tmp.rc_refcount = 1 + adj; tmp.rc_domain = XFS_REFC_DOMAIN_SHARED; trace_xfs_refcount_modify_extent(cur, &tmp); /* * Either cover the hole (increment) or * delete the range (decrement). */ cur->bc_refc.nr_ops++; if (tmp.rc_refcount) { error = xfs_refcount_insert(cur, &tmp, &found_tmp); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } else { error = xrefc_free_extent(cur, &tmp); if (error) goto out_error; } (*agbno) += tmp.rc_blockcount; (*aglen) -= tmp.rc_blockcount; /* Stop if there's nothing left to modify */ if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) break; /* Move the cursor to the start of ext. */ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno, &found_rec); if (error) goto out_error; } /* * A previous step trimmed agbno/aglen such that the end of the * range would not be in the middle of the record. If this is * no longer the case, something is seriously wrong with the * btree. Make sure we never feed the synthesized record into * the processing loop below. */ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) || XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } /* * Adjust the reference count and either update the tree * (incr) or free the blocks (decr). */ if (ext.rc_refcount == XFS_REFC_REFCOUNT_MAX) goto skip; ext.rc_refcount += adj; trace_xfs_refcount_modify_extent(cur, &ext); cur->bc_refc.nr_ops++; if (ext.rc_refcount > 1) { error = xfs_refcount_update(cur, &ext); if (error) goto out_error; } else if (ext.rc_refcount == 1) { error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } goto advloop; } else { error = xrefc_free_extent(cur, &ext); if (error) goto out_error; } skip: error = xfs_btree_increment(cur, 0, &found_rec); if (error) goto out_error; advloop: (*agbno) += ext.rc_blockcount; (*aglen) -= ext.rc_blockcount; } return error; out_error: trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_); return error; } /* Adjust the reference count of a range of AG blocks. */ STATIC int xfs_refcount_adjust( struct xfs_btree_cur *cur, xfs_agblock_t *agbno, xfs_extlen_t *aglen, enum xfs_refc_adjust_op adj) { bool shape_changed; int shape_changes = 0; int error; if (adj == XFS_REFCOUNT_ADJUST_INCREASE) trace_xfs_refcount_increase(cur, *agbno, *aglen); else trace_xfs_refcount_decrease(cur, *agbno, *aglen); /* * Ensure that no rcextents cross the boundary of the adjustment range. */ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, *agbno, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, *agbno + *aglen, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; /* * Try to merge with the left or right extents of the range. */ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, agbno, aglen, adj, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; if (shape_changes) cur->bc_refc.shape_changes++; /* Now that we've taken care of the ends, adjust the middle extents */ error = xfs_refcount_adjust_extents(cur, agbno, aglen, adj); if (error) goto out_error; return 0; out_error: trace_xfs_refcount_adjust_error(cur, error, _RET_IP_); return error; } /* * Set up a continuation a deferred refcount operation by updating the intent. * Checks to make sure we're not going to run off the end of the AG. */ static inline int xfs_refcount_continue_op( struct xfs_btree_cur *cur, struct xfs_refcount_intent *ri, xfs_agblock_t new_agbno) { struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = to_perag(cur->bc_group); if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, ri->ri_blockcount))) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } ri->ri_startblock = xfs_agbno_to_fsb(pag, new_agbno); ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount)); ASSERT(pag_agno(pag) == XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); return 0; } /* * Process one of the deferred refcount operations. We pass back the * btree cursor to maintain our lock on the btree between calls. * This saves time and eliminates a buffer deadlock between the * superblock and the AGF because we'll always grab them in the same * order. */ int xfs_refcount_finish_one( struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur) { struct xfs_mount *mp = tp->t_mountp; struct xfs_btree_cur *rcur = *pcur; struct xfs_buf *agbp = NULL; int error = 0; xfs_agblock_t bno; unsigned long nr_ops = 0; int shape_changes = 0; bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock); trace_xfs_refcount_deferred(mp, ri); if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ if (rcur != NULL && rcur->bc_group != ri->ri_group) { nr_ops = rcur->bc_refc.nr_ops; shape_changes = rcur->bc_refc.shape_changes; xfs_btree_del_cursor(rcur, 0); rcur = NULL; *pcur = NULL; } if (rcur == NULL) { struct xfs_perag *pag = to_perag(ri->ri_group); error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING, &agbp); if (error) return error; *pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); rcur->bc_refc.nr_ops = nr_ops; rcur->bc_refc.shape_changes = shape_changes; } switch (ri->ri_type) { case XFS_REFCOUNT_INCREASE: error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_INCREASE); if (error) return error; if (ri->ri_blockcount > 0) error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_DECREASE: error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_DECREASE); if (error) return error; if (ri->ri_blockcount > 0) error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_ALLOC_COW: error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); if (error) return error; ri->ri_blockcount = 0; break; case XFS_REFCOUNT_FREE_COW: error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); if (error) return error; ri->ri_blockcount = 0; break; default: ASSERT(0); return -EFSCORRUPTED; } if (!error && ri->ri_blockcount > 0) trace_xfs_refcount_finish_one_leftover(mp, ri); return error; } /* * Set up a continuation a deferred rtrefcount operation by updating the * intent. Checks to make sure we're not going to run off the end of the * rtgroup. */ static inline int xfs_rtrefcount_continue_op( struct xfs_btree_cur *cur, struct xfs_refcount_intent *ri, xfs_agblock_t new_agbno) { struct xfs_mount *mp = cur->bc_mp; struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); if (XFS_IS_CORRUPT(mp, !xfs_verify_rgbext(rtg, new_agbno, ri->ri_blockcount))) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } ri->ri_startblock = xfs_rgbno_to_rtb(rtg, new_agbno); ASSERT(xfs_verify_rtbext(mp, ri->ri_startblock, ri->ri_blockcount)); return 0; } /* * Process one of the deferred realtime refcount operations. We pass back the * btree cursor to maintain our lock on the btree between calls. */ int xfs_rtrefcount_finish_one( struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur) { struct xfs_mount *mp = tp->t_mountp; struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); struct xfs_btree_cur *rcur = *pcur; int error = 0; xfs_rgblock_t bno; unsigned long nr_ops = 0; int shape_changes = 0; bno = xfs_rtb_to_rgbno(mp, ri->ri_startblock); trace_xfs_refcount_deferred(mp, ri); if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ if (rcur != NULL && rcur->bc_group != ri->ri_group) { nr_ops = rcur->bc_refc.nr_ops; shape_changes = rcur->bc_refc.shape_changes; xfs_btree_del_cursor(rcur, 0); rcur = NULL; *pcur = NULL; } if (rcur == NULL) { xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_REFCOUNT); *pcur = rcur = xfs_rtrefcountbt_init_cursor(tp, rtg); rcur->bc_refc.nr_ops = nr_ops; rcur->bc_refc.shape_changes = shape_changes; } switch (ri->ri_type) { case XFS_REFCOUNT_INCREASE: error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_INCREASE); if (error) return error; if (ri->ri_blockcount > 0) error = xfs_rtrefcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_DECREASE: error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_DECREASE); if (error) return error; if (ri->ri_blockcount > 0) error = xfs_rtrefcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_ALLOC_COW: error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); if (error) return error; ri->ri_blockcount = 0; break; case XFS_REFCOUNT_FREE_COW: error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); if (error) return error; ri->ri_blockcount = 0; break; default: ASSERT(0); return -EFSCORRUPTED; } if (!error && ri->ri_blockcount > 0) trace_xfs_refcount_finish_one_leftover(mp, ri); return error; } /* * Record a refcount intent for later processing. */ static void __xfs_refcount_add( struct xfs_trans *tp, enum xfs_refcount_intent_type type, bool isrt, xfs_fsblock_t startblock, xfs_extlen_t blockcount) { struct xfs_refcount_intent *ri; ri = kmem_cache_alloc(xfs_refcount_intent_cache, GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&ri->ri_list); ri->ri_type = type; ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; ri->ri_realtime = isrt; xfs_refcount_defer_add(tp, ri); } /* * Increase the reference count of the blocks backing a file's extent. */ void xfs_refcount_increase_extent( struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } /* * Decrease the reference count of the blocks backing a file's extent. */ void xfs_refcount_decrease_extent( struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } /* * Given an AG extent, find the lowest-numbered run of shared blocks * within that range and return the range in fbno/flen. If * find_end_of_shared is set, return the longest contiguous extent of * shared blocks; if not, just return the first extent we find. If no * shared blocks are found, fbno and flen will be set to NULLAGBLOCK * and 0, respectively. */ int xfs_refcount_find_shared( struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared) { struct xfs_refcount_irec tmp; int i; int have; int error; trace_xfs_refcount_find_shared(cur, agbno, aglen); /* By default, skip the whole range */ *fbno = NULLAGBLOCK; *flen = 0; /* Try to find a refcount extent that crosses the start */ error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno, &have); if (error) goto out_error; if (!have) { /* No left extent, look at the next one */ error = xfs_btree_increment(cur, 0, &have); if (error) goto out_error; if (!have) goto done; } error = xfs_refcount_get_rec(cur, &tmp, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) goto done; /* If the extent ends before the start, look at the next one */ if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) { error = xfs_btree_increment(cur, 0, &have); if (error) goto out_error; if (!have) goto done; error = xfs_refcount_get_rec(cur, &tmp, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) goto done; } /* If the extent starts after the range we want, bail out */ if (tmp.rc_startblock >= agbno + aglen) goto done; /* We found the start of a shared extent! */ if (tmp.rc_startblock < agbno) { tmp.rc_blockcount -= (agbno - tmp.rc_startblock); tmp.rc_startblock = agbno; } *fbno = tmp.rc_startblock; *flen = min(tmp.rc_blockcount, agbno + aglen - *fbno); if (!find_end_of_shared) goto done; /* Otherwise, find the end of this shared extent */ while (*fbno + *flen < agbno + aglen) { error = xfs_btree_increment(cur, 0, &have); if (error) goto out_error; if (!have) break; error = xfs_refcount_get_rec(cur, &tmp, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED || tmp.rc_startblock >= agbno + aglen || tmp.rc_startblock != *fbno + *flen) break; *flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno); } done: trace_xfs_refcount_find_shared_result(cur, *fbno, *flen); out_error: if (error) trace_xfs_refcount_find_shared_error(cur, error, _RET_IP_); return error; } /* * Recovering CoW Blocks After a Crash * * Due to the way that the copy on write mechanism works, there's a window of * opportunity in which we can lose track of allocated blocks during a crash. * Because CoW uses delayed allocation in the in-core CoW fork, writeback * causes blocks to be allocated and stored in the CoW fork. The blocks are * no longer in the free space btree but are not otherwise recorded anywhere * until the write completes and the blocks are mapped into the file. A crash * in between allocation and remapping results in the replacement blocks being * lost. This situation is exacerbated by the CoW extent size hint because * allocations can hang around for long time. * * However, there is a place where we can record these allocations before they * become mappings -- the reference count btree. The btree does not record * extents with refcount == 1, so we can record allocations with a refcount of * 1. Blocks being used for CoW writeout cannot be shared, so there should be * no conflict with shared block records. These mappings should be created * when we allocate blocks to the CoW fork and deleted when they're removed * from the CoW fork. * * Minor nit: records for in-progress CoW allocations and records for shared * extents must never be merged, to preserve the property that (except for CoW * allocations) there are no refcount btree entries with refcount == 1. The * only time this could potentially happen is when unsharing a block that's * adjacent to CoW allocations, so we must be careful to avoid this. * * At mount time we recover lost CoW allocations by searching the refcount * btree for these refcount == 1 mappings. These represent CoW allocations * that were in progress at the time the filesystem went down, so we can free * them to get the space back. * * This mechanism is superior to creating EFIs for unmapped CoW extents for * several reasons -- first, EFIs pin the tail of the log and would have to be * periodically relogged to avoid filling up the log. Second, CoW completions * will have to file an EFD and create new EFIs for whatever remains in the * CoW fork; this partially takes care of (1) but extent-size reservations * will have to periodically relog even if there's no writeout in progress. * This can happen if the CoW extent size hint is set, which you really want. * Third, EFIs cannot currently be automatically relogged into newer * transactions to advance the log tail. Fourth, stuffing the log full of * EFIs places an upper bound on the number of CoW allocations that can be * held filesystem-wide at any given time. Recording them in the refcount * btree doesn't require us to maintain any state in memory and doesn't pin * the log. */ /* * Adjust the refcounts of CoW allocations. These allocations are "magic" * in that they're not referenced anywhere else in the filesystem, so we * stash them in the refcount btree with a refcount of 1 until either file * remapping (or CoW cancellation) happens. */ STATIC int xfs_refcount_adjust_cow_extents( struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, enum xfs_refc_adjust_op adj) { struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; if (aglen == 0) return 0; /* Find any overlapping refcount records */ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno, &found_rec); if (error) goto out_error; error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec && ext.rc_domain != XFS_REFC_DOMAIN_COW)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (!found_rec) { ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_COW; } switch (adj) { case XFS_REFCOUNT_ADJUST_COW_ALLOC: /* Adding a CoW reservation, there should be nothing here. */ if (XFS_IS_CORRUPT(cur->bc_mp, agbno + aglen > ext.rc_startblock)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } tmp.rc_startblock = agbno; tmp.rc_blockcount = aglen; tmp.rc_refcount = 1; tmp.rc_domain = XFS_REFC_DOMAIN_COW; trace_xfs_refcount_modify_extent(cur, &tmp); error = xfs_refcount_insert(cur, &tmp, &found_tmp); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } break; case XFS_REFCOUNT_ADJUST_COW_FREE: /* Removing a CoW reservation, there should be one extent. */ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } ext.rc_refcount = 0; trace_xfs_refcount_modify_extent(cur, &ext); error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } break; default: ASSERT(0); } return error; out_error: trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_); return error; } /* * Add or remove refcount btree entries for CoW reservations. */ STATIC int xfs_refcount_adjust_cow( struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, enum xfs_refc_adjust_op adj) { bool shape_changed; int error; /* * Ensure that no rcextents cross the boundary of the adjustment range. */ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, agbno, &shape_changed); if (error) goto out_error; error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, agbno + aglen, &shape_changed); if (error) goto out_error; /* * Try to merge with the left or right extents of the range. */ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno, &aglen, adj, &shape_changed); if (error) goto out_error; /* Now that we've taken care of the ends, adjust the middle extents */ error = xfs_refcount_adjust_cow_extents(cur, agbno, aglen, adj); if (error) goto out_error; return 0; out_error: trace_xfs_refcount_adjust_cow_error(cur, error, _RET_IP_); return error; } /* * Record a CoW allocation in the refcount btree. */ STATIC int __xfs_refcount_cow_alloc( struct xfs_btree_cur *rcur, xfs_agblock_t agbno, xfs_extlen_t aglen) { trace_xfs_refcount_cow_increase(rcur, agbno, aglen); /* Add refcount btree reservation */ return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_ALLOC); } /* * Remove a CoW allocation from the refcount btree. */ STATIC int __xfs_refcount_cow_free( struct xfs_btree_cur *rcur, xfs_agblock_t agbno, xfs_extlen_t aglen) { trace_xfs_refcount_cow_decrease(rcur, agbno, aglen); /* Remove refcount btree reservation */ return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_FREE); } /* Record a CoW staging extent in the refcount btree. */ void xfs_refcount_alloc_cow_extent( struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { struct xfs_mount *mp = tp->t_mountp; if (!xfs_has_reflink(mp)) return; __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, isrt, fsb, len); /* Add rmap entry */ xfs_rmap_alloc_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ void xfs_refcount_free_cow_extent( struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { struct xfs_mount *mp = tp->t_mountp; if (!xfs_has_reflink(mp)) return; /* Remove rmap entry */ xfs_rmap_free_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, isrt, fsb, len); } struct xfs_refcount_recovery { struct list_head rr_list; struct xfs_refcount_irec rr_rrec; }; /* Stuff an extent on the recovery list. */ STATIC int xfs_refcount_recover_extent( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { struct list_head *debris = priv; struct xfs_refcount_recovery *rr; if (XFS_IS_CORRUPT(cur->bc_mp, be32_to_cpu(rec->refc.rc_refcount) != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } rr = kmalloc(sizeof(struct xfs_refcount_recovery), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); if (xfs_refcount_check_btrec(cur, &rr->rr_rrec) != NULL || XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { xfs_btree_mark_sick(cur); kfree(rr); return -EFSCORRUPTED; } list_add_tail(&rr->rr_list, debris); return 0; } /* Find and remove leftover CoW reservations. */ int xfs_refcount_recover_cow_leftovers( struct xfs_group *xg) { struct xfs_mount *mp = xg->xg_mount; bool isrt = xg->xg_type == XG_TYPE_RTG; struct xfs_trans *tp; struct xfs_btree_cur *cur; struct xfs_buf *agbp = NULL; struct xfs_refcount_recovery *rr, *n; struct list_head debris; union xfs_btree_irec low = { .rc.rc_domain = XFS_REFC_DOMAIN_COW, }; union xfs_btree_irec high = { .rc.rc_domain = XFS_REFC_DOMAIN_COW, .rc.rc_startblock = -1U, }; xfs_fsblock_t fsb; int error; /* reflink filesystems must not have groups larger than 2^31-1 blocks */ BUILD_BUG_ON(XFS_MAX_RGBLOCKS >= XFS_REFC_COWFLAG); BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); if (isrt) { if (!xfs_has_rtgroups(mp)) return 0; if (xfs_group_max_blocks(xg) >= XFS_MAX_RGBLOCKS) return -EOPNOTSUPP; } else { if (xfs_group_max_blocks(xg) > XFS_MAX_CRC_AG_BLOCKS) return -EOPNOTSUPP; } INIT_LIST_HEAD(&debris); /* * In this first part, we use an empty transaction to gather up * all the leftover CoW extents so that we can subsequently * delete them. The empty transaction is used to avoid * a buffer lock deadlock if there happens to be a loop in the * refcountbt because we're allowed to re-grab a buffer that is * already attached to our transaction. When we're done * recording the CoW debris we cancel the (empty) transaction * and everything goes away cleanly. */ tp = xfs_trans_alloc_empty(mp); if (isrt) { xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(xg)); } else { error = xfs_alloc_read_agf(to_perag(xg), tp, 0, &agbp); if (error) goto out_trans; cur = xfs_refcountbt_init_cursor(mp, tp, agbp, to_perag(xg)); } /* Find all the leftover CoW staging extents. */ error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); if (agbp) xfs_trans_brelse(tp, agbp); else xfs_rtgroup_unlock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); xfs_trans_cancel(tp); if (error) goto out_free; /* Now iterate the list to free the leftovers */ list_for_each_entry_safe(rr, n, &debris, rr_list) { /* Set up transaction. */ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp); if (error) goto out_free; /* Free the orphan record */ fsb = xfs_gbno_to_fsb(xg, rr->rr_rrec.rc_startblock); xfs_refcount_free_cow_extent(tp, isrt, fsb, rr->rr_rrec.rc_blockcount); /* Free the block. */ error = xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL, XFS_AG_RESV_NONE, isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) goto out_trans; error = xfs_trans_commit(tp); if (error) goto out_free; list_del(&rr->rr_list); kfree(rr); } return error; out_trans: xfs_trans_cancel(tp); out_free: /* Free the leftover list */ list_for_each_entry_safe(rr, n, &debris, rr_list) { list_del(&rr->rr_list); kfree(rr); } return error; } /* * Scan part of the keyspace of the refcount records and tell us if the area * has no records, is fully mapped by records, or is partially filled. */ int xfs_refcount_has_records( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; memset(&low, 0, sizeof(low)); low.rc.rc_startblock = bno; memset(&high, 0xFF, sizeof(high)); high.rc.rc_startblock = bno + len - 1; low.rc.rc_domain = high.rc.rc_domain = domain; return xfs_btree_has_records(cur, &low, &high, NULL, outcome); } struct xfs_refcount_query_range_info { xfs_refcount_query_range_fn fn; void *priv; }; /* Format btree record and pass to our callback. */ STATIC int xfs_refcount_query_range_helper( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { struct xfs_refcount_query_range_info *query = priv; struct xfs_refcount_irec irec; xfs_failaddr_t fa; xfs_refcount_btrec_to_irec(rec, &irec); fa = xfs_refcount_check_btrec(cur, &irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, &irec); return query->fn(cur, &irec, query->priv); } /* Find all refcount records between two keys. */ int xfs_refcount_query_range( struct xfs_btree_cur *cur, const struct xfs_refcount_irec *low_rec, const struct xfs_refcount_irec *high_rec, xfs_refcount_query_range_fn fn, void *priv) { union xfs_btree_irec low_brec = { .rc = *low_rec }; union xfs_btree_irec high_brec = { .rc = *high_rec }; struct xfs_refcount_query_range_info query = { .priv = priv, .fn = fn }; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_refcount_query_range_helper, &query); } int __init xfs_refcount_intent_init_cache(void) { xfs_refcount_intent_cache = kmem_cache_create("xfs_refc_intent", sizeof(struct xfs_refcount_intent), 0, 0, NULL); return xfs_refcount_intent_cache != NULL ? 0 : -ENOMEM; } void xfs_refcount_intent_destroy_cache(void) { kmem_cache_destroy(xfs_refcount_intent_cache); xfs_refcount_intent_cache = NULL; } |
| 2 2 2 2 6 6 6 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 1 2 2 2 2 2 2 1 2 1 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/clnt.c * * This file contains the high-level RPC interface. * It is modeled as a finite state machine to support both synchronous * and asynchronous requests. * * - RPC header generation and argument serialization. * - Credential refresh. * - TCP connect handling. * - Retry of operation when it is suspected the operation failed because * of uid squashing on the server, or when the credentials were stale * and need to be refreshed, or when a packet was damaged in transit. * This may be have to be moved to the VFS layer. * * Copyright (C) 1992,1993 Rick Sladkey <jrs@world.std.com> * Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/types.h> #include <linux/kallsyms.h> #include <linux/mm.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/metrics.h> #include <linux/sunrpc/bc_xprt.h> #include <trace/events/sunrpc.h> #include "sunrpc.h" #include "sysfs.h" #include "netns.h" #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_CALL #endif static DECLARE_WAIT_QUEUE_HEAD(destroy_wait); static void call_start(struct rpc_task *task); static void call_reserve(struct rpc_task *task); static void call_reserveresult(struct rpc_task *task); static void call_allocate(struct rpc_task *task); static void call_encode(struct rpc_task *task); static void call_decode(struct rpc_task *task); static void call_bind(struct rpc_task *task); static void call_bind_status(struct rpc_task *task); static void call_transmit(struct rpc_task *task); static void call_status(struct rpc_task *task); static void call_transmit_status(struct rpc_task *task); static void call_refresh(struct rpc_task *task); static void call_refreshresult(struct rpc_task *task); static void call_connect(struct rpc_task *task); static void call_connect_status(struct rpc_task *task); static int rpc_encode_header(struct rpc_task *task, struct xdr_stream *xdr); static int rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr); static int rpc_ping(struct rpc_clnt *clnt); static int rpc_ping_noreply(struct rpc_clnt *clnt); static void rpc_check_timeout(struct rpc_task *task); static void rpc_register_client(struct rpc_clnt *clnt) { struct net *net = rpc_net_ns(clnt); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); spin_lock(&sn->rpc_client_lock); list_add(&clnt->cl_clients, &sn->all_clients); spin_unlock(&sn->rpc_client_lock); } static void rpc_unregister_client(struct rpc_clnt *clnt) { struct net *net = rpc_net_ns(clnt); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); spin_lock(&sn->rpc_client_lock); list_del(&clnt->cl_clients); spin_unlock(&sn->rpc_client_lock); } static void __rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) { rpc_remove_client_dir(clnt); } static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) { struct net *net = rpc_net_ns(clnt); struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { if (pipefs_sb == clnt->pipefs_sb) __rpc_clnt_remove_pipedir(clnt); rpc_put_sb_net(net); } } static int rpc_setup_pipedir_sb(struct super_block *sb, struct rpc_clnt *clnt) { static uint32_t clntid; const char *dir_name = clnt->cl_program->pipe_dir_name; char name[15]; struct dentry *dir; int err; dir = rpc_d_lookup_sb(sb, dir_name); if (dir == NULL) { pr_info("RPC: pipefs directory doesn't exist: %s\n", dir_name); return -ENOENT; } for (;;) { snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); name[sizeof(name) - 1] = '\0'; err = rpc_create_client_dir(dir, name, clnt); if (!err) break; if (err == -EEXIST) continue; printk(KERN_INFO "RPC: Couldn't create pipefs entry" " %s/%s, error %d\n", dir_name, name, err); break; } dput(dir); return err; } static int rpc_setup_pipedir(struct super_block *pipefs_sb, struct rpc_clnt *clnt) { clnt->pipefs_sb = pipefs_sb; if (clnt->cl_program->pipe_dir_name != NULL) { int err = rpc_setup_pipedir_sb(pipefs_sb, clnt); if (err && err != -ENOENT) return err; } return 0; } static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) { if (clnt->cl_program->pipe_dir_name == NULL) return 1; switch (event) { case RPC_PIPEFS_MOUNT: if (clnt->cl_pipedir_objects.pdh_dentry != NULL) return 1; if (refcount_read(&clnt->cl_count) == 0) return 1; break; case RPC_PIPEFS_UMOUNT: if (clnt->cl_pipedir_objects.pdh_dentry == NULL) return 1; break; } return 0; } static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event, struct super_block *sb) { switch (event) { case RPC_PIPEFS_MOUNT: return rpc_setup_pipedir_sb(sb, clnt); case RPC_PIPEFS_UMOUNT: __rpc_clnt_remove_pipedir(clnt); break; default: printk(KERN_ERR "%s: unknown event: %ld\n", __func__, event); return -ENOTSUPP; } return 0; } static int __rpc_pipefs_event(struct rpc_clnt *clnt, unsigned long event, struct super_block *sb) { int error = 0; for (;; clnt = clnt->cl_parent) { if (!rpc_clnt_skip_event(clnt, event)) error = __rpc_clnt_handle_event(clnt, event, sb); if (error || clnt == clnt->cl_parent) break; } return error; } static struct rpc_clnt *rpc_get_client_for_event(struct net *net, int event) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt; spin_lock(&sn->rpc_client_lock); list_for_each_entry(clnt, &sn->all_clients, cl_clients) { if (rpc_clnt_skip_event(clnt, event)) continue; spin_unlock(&sn->rpc_client_lock); return clnt; } spin_unlock(&sn->rpc_client_lock); return NULL; } static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct super_block *sb = ptr; struct rpc_clnt *clnt; int error = 0; while ((clnt = rpc_get_client_for_event(sb->s_fs_info, event))) { error = __rpc_pipefs_event(clnt, event, sb); if (error) break; } return error; } static struct notifier_block rpc_clients_block = { .notifier_call = rpc_pipefs_event, .priority = SUNRPC_PIPEFS_RPC_PRIO, }; int rpc_clients_notifier_register(void) { return rpc_pipefs_notifier_register(&rpc_clients_block); } void rpc_clients_notifier_unregister(void) { return rpc_pipefs_notifier_unregister(&rpc_clients_block); } static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, struct rpc_xprt *xprt, const struct rpc_timeout *timeout) { struct rpc_xprt *old; spin_lock(&clnt->cl_lock); old = rcu_dereference_protected(clnt->cl_xprt, lockdep_is_held(&clnt->cl_lock)); clnt->cl_timeout = timeout; rcu_assign_pointer(clnt->cl_xprt, xprt); spin_unlock(&clnt->cl_lock); return old; } static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { ssize_t copied; copied = strscpy(clnt->cl_nodename, nodename, sizeof(clnt->cl_nodename)); clnt->cl_nodelen = copied < 0 ? sizeof(clnt->cl_nodename) - 1 : copied; } static int rpc_client_register(struct rpc_clnt *clnt, rpc_authflavor_t pseudoflavor, const char *client_name) { struct rpc_auth_create_args auth_args = { .pseudoflavor = pseudoflavor, .target_name = client_name, }; struct rpc_auth *auth; struct net *net = rpc_net_ns(clnt); struct super_block *pipefs_sb; int err; rpc_clnt_debugfs_register(clnt); pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { err = rpc_setup_pipedir(pipefs_sb, clnt); if (err) goto out; } rpc_register_client(clnt); if (pipefs_sb) rpc_put_sb_net(net); auth = rpcauth_create(&auth_args, clnt); if (IS_ERR(auth)) { dprintk("RPC: Couldn't create auth handle (flavor %u)\n", pseudoflavor); err = PTR_ERR(auth); goto err_auth; } return 0; err_auth: pipefs_sb = rpc_get_sb_net(net); rpc_unregister_client(clnt); __rpc_clnt_remove_pipedir(clnt); out: if (pipefs_sb) rpc_put_sb_net(net); rpc_sysfs_client_destroy(clnt); rpc_clnt_debugfs_unregister(clnt); return err; } static DEFINE_IDA(rpc_clids); void rpc_cleanup_clids(void) { ida_destroy(&rpc_clids); } static int rpc_alloc_clid(struct rpc_clnt *clnt) { int clid; clid = ida_alloc(&rpc_clids, GFP_KERNEL); if (clid < 0) return clid; clnt->cl_clid = clid; return 0; } static void rpc_free_clid(struct rpc_clnt *clnt) { ida_free(&rpc_clids, clnt->cl_clid); } static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, struct rpc_clnt *parent) { const struct rpc_program *program = args->program; const struct rpc_version *version; struct rpc_clnt *clnt = NULL; const struct rpc_timeout *timeout; const char *nodename = args->nodename; int err; err = rpciod_up(); if (err) goto out_no_rpciod; err = -EINVAL; if (args->version >= program->nrvers) goto out_err; version = program->version[args->version]; if (version == NULL) goto out_err; err = -ENOMEM; clnt = kzalloc(sizeof(*clnt), GFP_KERNEL); if (!clnt) goto out_err; clnt->cl_parent = parent ? : clnt; clnt->cl_xprtsec = args->xprtsec; err = rpc_alloc_clid(clnt); if (err) goto out_no_clid; clnt->cl_cred = get_cred(args->cred); clnt->cl_procinfo = version->procs; clnt->cl_maxproc = version->nrprocs; clnt->cl_prog = args->prognumber ? : program->number; clnt->cl_vers = version->number; clnt->cl_stats = args->stats ? : program->stats; clnt->cl_metrics = rpc_alloc_iostats(clnt); rpc_init_pipe_dir_head(&clnt->cl_pipedir_objects); err = -ENOMEM; if (clnt->cl_metrics == NULL) goto out_no_stats; clnt->cl_program = program; INIT_LIST_HEAD(&clnt->cl_tasks); spin_lock_init(&clnt->cl_lock); timeout = xprt->timeout; if (args->timeout != NULL) { memcpy(&clnt->cl_timeout_default, args->timeout, sizeof(clnt->cl_timeout_default)); timeout = &clnt->cl_timeout_default; } rpc_clnt_set_transport(clnt, xprt, timeout); xprt->main = true; xprt_iter_init(&clnt->cl_xpi, xps); xprt_switch_put(xps); clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); refcount_set(&clnt->cl_count, 1); if (nodename == NULL) nodename = utsname()->nodename; /* save the nodename */ rpc_clnt_set_nodename(clnt, nodename); rpc_sysfs_client_setup(clnt, xps, rpc_net_ns(clnt)); err = rpc_client_register(clnt, args->authflavor, args->client_name); if (err) goto out_no_path; if (parent) refcount_inc(&parent->cl_count); trace_rpc_clnt_new(clnt, xprt, args); return clnt; out_no_path: rpc_free_iostats(clnt->cl_metrics); out_no_stats: put_cred(clnt->cl_cred); rpc_free_clid(clnt); out_no_clid: kfree(clnt); out_err: rpciod_down(); out_no_rpciod: xprt_switch_put(xps); xprt_put(xprt); trace_rpc_clnt_new_err(program->name, args->servername, err); return ERR_PTR(err); } static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt *xprt) { struct rpc_clnt *clnt = NULL; struct rpc_xprt_switch *xps; if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) { WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xps = args->bc_xprt->xpt_bc_xps; xprt_switch_get(xps); } else { xps = xprt_switch_alloc(xprt, GFP_KERNEL); if (xps == NULL) { xprt_put(xprt); return ERR_PTR(-ENOMEM); } if (xprt->bc_xprt) { xprt_switch_get(xps); xprt->bc_xprt->xpt_bc_xps = xps; } } clnt = rpc_new_client(args, xps, xprt, NULL); if (IS_ERR(clnt)) return clnt; if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { int err = rpc_ping(clnt); if (err != 0) { rpc_shutdown_client(clnt); return ERR_PTR(err); } } else if (args->flags & RPC_CLNT_CREATE_CONNECTED) { int err = rpc_ping_noreply(clnt); if (err != 0) { rpc_shutdown_client(clnt); return ERR_PTR(err); } } clnt->cl_softrtry = 1; if (args->flags & (RPC_CLNT_CREATE_HARDRTRY|RPC_CLNT_CREATE_SOFTERR)) { clnt->cl_softrtry = 0; if (args->flags & RPC_CLNT_CREATE_SOFTERR) clnt->cl_softerr = 1; } if (args->flags & RPC_CLNT_CREATE_AUTOBIND) clnt->cl_autobind = 1; if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT) clnt->cl_noretranstimeo = 1; if (args->flags & RPC_CLNT_CREATE_DISCRTRY) clnt->cl_discrtry = 1; if (!(args->flags & RPC_CLNT_CREATE_QUIET)) clnt->cl_chatty = 1; if (args->flags & RPC_CLNT_CREATE_NETUNREACH_FATAL) clnt->cl_netunreach_fatal = 1; return clnt; } /** * rpc_create - create an RPC client and transport with one call * @args: rpc_clnt create argument structure * * Creates and initializes an RPC transport and an RPC client. * * It can ping the server in order to determine if it is up, and to see if * it supports this program and version. RPC_CLNT_CREATE_NOPING disables * this behavior so asynchronous tasks can also use rpc_create. */ struct rpc_clnt *rpc_create(struct rpc_create_args *args) { struct rpc_xprt *xprt; struct xprt_create xprtargs = { .net = args->net, .ident = args->protocol, .srcaddr = args->saddress, .dstaddr = args->address, .addrlen = args->addrsize, .servername = args->servername, .bc_xprt = args->bc_xprt, .xprtsec = args->xprtsec, .connect_timeout = args->connect_timeout, .reconnect_timeout = args->reconnect_timeout, }; char servername[RPC_MAXNETNAMELEN]; struct rpc_clnt *clnt; int i; if (args->bc_xprt) { WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xprt = args->bc_xprt->xpt_bc_xprt; if (xprt) { xprt_get(xprt); return rpc_create_xprt(args, xprt); } } if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS) xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS; if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT) xprtargs.flags |= XPRT_CREATE_NO_IDLE_TIMEOUT; /* * If the caller chooses not to specify a hostname, whip * up a string representation of the passed-in address. */ if (xprtargs.servername == NULL) { struct sockaddr_un *sun = (struct sockaddr_un *)args->address; struct sockaddr_in *sin = (struct sockaddr_in *)args->address; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)args->address; servername[0] = '\0'; switch (args->address->sa_family) { case AF_LOCAL: if (sun->sun_path[0]) snprintf(servername, sizeof(servername), "%s", sun->sun_path); else snprintf(servername, sizeof(servername), "@%s", sun->sun_path+1); break; case AF_INET: snprintf(servername, sizeof(servername), "%pI4", &sin->sin_addr.s_addr); break; case AF_INET6: snprintf(servername, sizeof(servername), "%pI6", &sin6->sin6_addr); break; default: /* caller wants default server name, but * address family isn't recognized. */ return ERR_PTR(-EINVAL); } xprtargs.servername = servername; } xprt = xprt_create_transport(&xprtargs); if (IS_ERR(xprt)) return (struct rpc_clnt *)xprt; /* * By default, kernel RPC client connects from a reserved port. * CAP_NET_BIND_SERVICE will not be set for unprivileged requesters, * but it is always enabled for rpciod, which handles the connect * operation. */ xprt->resvport = 1; if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; xprt->reuseport = 0; if (args->flags & RPC_CLNT_CREATE_REUSEPORT) xprt->reuseport = 1; clnt = rpc_create_xprt(args, xprt); if (IS_ERR(clnt) || args->nconnect <= 1) return clnt; for (i = 0; i < args->nconnect - 1; i++) { if (rpc_clnt_add_xprt(clnt, &xprtargs, NULL, NULL) < 0) break; } return clnt; } EXPORT_SYMBOL_GPL(rpc_create); /* * This function clones the RPC client structure. It allows us to share the * same transport while varying parameters such as the authentication * flavour. */ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, struct rpc_clnt *clnt) { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; struct rpc_clnt *new; int err; err = -ENOMEM; rcu_read_lock(); xprt = xprt_get(rcu_dereference(clnt->cl_xprt)); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); rcu_read_unlock(); if (xprt == NULL || xps == NULL) { xprt_put(xprt); xprt_switch_put(xps); goto out_err; } args->servername = xprt->servername; args->nodename = clnt->cl_nodename; new = rpc_new_client(args, xps, xprt, clnt); if (IS_ERR(new)) return new; /* Turn off autobind on clones */ new->cl_autobind = 0; new->cl_softrtry = clnt->cl_softrtry; new->cl_softerr = clnt->cl_softerr; new->cl_noretranstimeo = clnt->cl_noretranstimeo; new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; new->cl_netunreach_fatal = clnt->cl_netunreach_fatal; new->cl_principal = clnt->cl_principal; new->cl_max_connect = clnt->cl_max_connect; return new; out_err: trace_rpc_clnt_clone_err(clnt, err); return ERR_PTR(err); } /** * rpc_clone_client - Clone an RPC client structure * * @clnt: RPC client whose parameters are copied * * Returns a fresh RPC client or an ERR_PTR. */ struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt) { struct rpc_create_args args = { .program = clnt->cl_program, .prognumber = clnt->cl_prog, .version = clnt->cl_vers, .authflavor = clnt->cl_auth->au_flavor, .cred = clnt->cl_cred, .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } EXPORT_SYMBOL_GPL(rpc_clone_client); /** * rpc_clone_client_set_auth - Clone an RPC client structure and set its auth * * @clnt: RPC client whose parameters are copied * @flavor: security flavor for new client * * Returns a fresh RPC client or an ERR_PTR. */ struct rpc_clnt * rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) { struct rpc_create_args args = { .program = clnt->cl_program, .prognumber = clnt->cl_prog, .version = clnt->cl_vers, .authflavor = flavor, .cred = clnt->cl_cred, .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth); /** * rpc_switch_client_transport: switch the RPC transport on the fly * @clnt: pointer to a struct rpc_clnt * @args: pointer to the new transport arguments * @timeout: pointer to the new timeout parameters * * This function allows the caller to switch the RPC transport for the * rpc_clnt structure 'clnt' to allow it to connect to a mirrored NFS * server, for instance. It assumes that the caller has ensured that * there are no active RPC tasks by using some form of locking. * * Returns zero if "clnt" is now using the new xprt. Otherwise a * negative errno is returned, and "clnt" continues to use the old * xprt. */ int rpc_switch_client_transport(struct rpc_clnt *clnt, struct xprt_create *args, const struct rpc_timeout *timeout) { const struct rpc_timeout *old_timeo; rpc_authflavor_t pseudoflavor; struct rpc_xprt_switch *xps, *oldxps; struct rpc_xprt *xprt, *old; struct rpc_clnt *parent; int err; args->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(args); if (IS_ERR(xprt)) return PTR_ERR(xprt); xps = xprt_switch_alloc(xprt, GFP_KERNEL); if (xps == NULL) { xprt_put(xprt); return -ENOMEM; } pseudoflavor = clnt->cl_auth->au_flavor; old_timeo = clnt->cl_timeout; old = rpc_clnt_set_transport(clnt, xprt, timeout); oldxps = xprt_iter_xchg_switch(&clnt->cl_xpi, xps); rpc_unregister_client(clnt); __rpc_clnt_remove_pipedir(clnt); rpc_sysfs_client_destroy(clnt); rpc_clnt_debugfs_unregister(clnt); /* * A new transport was created. "clnt" therefore * becomes the root of a new cl_parent tree. clnt's * children, if it has any, still point to the old xprt. */ parent = clnt->cl_parent; clnt->cl_parent = clnt; /* * The old rpc_auth cache cannot be re-used. GSS * contexts in particular are between a single * client and server. */ err = rpc_client_register(clnt, pseudoflavor, NULL); if (err) goto out_revert; synchronize_rcu(); if (parent != clnt) rpc_release_client(parent); xprt_switch_put(oldxps); xprt_put(old); trace_rpc_clnt_replace_xprt(clnt); return 0; out_revert: xps = xprt_iter_xchg_switch(&clnt->cl_xpi, oldxps); rpc_clnt_set_transport(clnt, old, old_timeo); clnt->cl_parent = parent; rpc_client_register(clnt, pseudoflavor, NULL); xprt_switch_put(xps); xprt_put(xprt); trace_rpc_clnt_replace_xprt_err(clnt); return err; } EXPORT_SYMBOL_GPL(rpc_switch_client_transport); static struct rpc_xprt_switch *rpc_clnt_xprt_switch_get(struct rpc_clnt *clnt) { struct rpc_xprt_switch *xps; rcu_read_lock(); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); rcu_read_unlock(); return xps; } static int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi, void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps)) { struct rpc_xprt_switch *xps; xps = rpc_clnt_xprt_switch_get(clnt); if (xps == NULL) return -EAGAIN; func(xpi, xps); xprt_switch_put(xps); return 0; } static int rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi) { return _rpc_clnt_xprt_iter_init(clnt, xpi, xprt_iter_init_listall); } static int rpc_clnt_xprt_iter_offline_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi) { return _rpc_clnt_xprt_iter_init(clnt, xpi, xprt_iter_init_listoffline); } /** * rpc_clnt_iterate_for_each_xprt - Apply a function to all transports * @clnt: pointer to client * @fn: function to apply * @data: void pointer to function data * * Iterates through the list of RPC transports currently attached to the * client and applies the function fn(clnt, xprt, data). * * On error, the iteration stops, and the function returns the error value. */ int rpc_clnt_iterate_for_each_xprt(struct rpc_clnt *clnt, int (*fn)(struct rpc_clnt *, struct rpc_xprt *, void *), void *data) { struct rpc_xprt_iter xpi; int ret; ret = rpc_clnt_xprt_iter_init(clnt, &xpi); if (ret) return ret; for (;;) { struct rpc_xprt *xprt = xprt_iter_get_next(&xpi); if (!xprt) break; ret = fn(clnt, xprt, data); xprt_put(xprt); if (ret < 0) break; } xprt_iter_destroy(&xpi); return ret; } EXPORT_SYMBOL_GPL(rpc_clnt_iterate_for_each_xprt); /* * Kill all tasks for the given client. * XXX: kill their descendants as well? */ void rpc_killall_tasks(struct rpc_clnt *clnt) { struct rpc_task *rovr; if (list_empty(&clnt->cl_tasks)) return; /* * Spin lock all_tasks to prevent changes... */ trace_rpc_clnt_killall(clnt); spin_lock(&clnt->cl_lock); list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) rpc_signal_task(rovr); spin_unlock(&clnt->cl_lock); } EXPORT_SYMBOL_GPL(rpc_killall_tasks); /** * rpc_cancel_tasks - try to cancel a set of RPC tasks * @clnt: Pointer to RPC client * @error: RPC task error value to set * @fnmatch: Pointer to selector function * @data: User data * * Uses @fnmatch to define a set of RPC tasks that are to be cancelled. * The argument @error must be a negative error value. */ unsigned long rpc_cancel_tasks(struct rpc_clnt *clnt, int error, bool (*fnmatch)(const struct rpc_task *, const void *), const void *data) { struct rpc_task *task; unsigned long count = 0; if (list_empty(&clnt->cl_tasks)) return 0; /* * Spin lock all_tasks to prevent changes... */ spin_lock(&clnt->cl_lock); list_for_each_entry(task, &clnt->cl_tasks, tk_task) { if (!RPC_IS_ACTIVATED(task)) continue; if (!fnmatch(task, data)) continue; rpc_task_try_cancel(task, error); count++; } spin_unlock(&clnt->cl_lock); return count; } EXPORT_SYMBOL_GPL(rpc_cancel_tasks); static int rpc_clnt_disconnect_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *dummy) { if (xprt_connected(xprt)) xprt_force_disconnect(xprt); return 0; } void rpc_clnt_disconnect(struct rpc_clnt *clnt) { rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_disconnect_xprt, NULL); } EXPORT_SYMBOL_GPL(rpc_clnt_disconnect); /* * Properly shut down an RPC client, terminating all outstanding * requests. */ void rpc_shutdown_client(struct rpc_clnt *clnt) { might_sleep(); trace_rpc_clnt_shutdown(clnt); clnt->cl_shutdown = 1; while (!list_empty(&clnt->cl_tasks)) { rpc_killall_tasks(clnt); wait_event_timeout(destroy_wait, list_empty(&clnt->cl_tasks), 1*HZ); } /* wait for tasks still in workqueue or waitqueue */ wait_event_timeout(destroy_wait, atomic_read(&clnt->cl_task_count) == 0, 1 * HZ); rpc_release_client(clnt); } EXPORT_SYMBOL_GPL(rpc_shutdown_client); /* * Free an RPC client */ static void rpc_free_client_work(struct work_struct *work) { struct rpc_clnt *clnt = container_of(work, struct rpc_clnt, cl_work); trace_rpc_clnt_free(clnt); /* These might block on processes that might allocate memory, * so they cannot be called in rpciod, so they are handled separately * here. */ rpc_sysfs_client_destroy(clnt); rpc_clnt_debugfs_unregister(clnt); rpc_free_clid(clnt); rpc_clnt_remove_pipedir(clnt); xprt_put(rcu_dereference_raw(clnt->cl_xprt)); kfree(clnt); rpciod_down(); } static struct rpc_clnt * rpc_free_client(struct rpc_clnt *clnt) { struct rpc_clnt *parent = NULL; trace_rpc_clnt_release(clnt); if (clnt->cl_parent != clnt) parent = clnt->cl_parent; rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); clnt->cl_metrics = NULL; xprt_iter_destroy(&clnt->cl_xpi); put_cred(clnt->cl_cred); INIT_WORK(&clnt->cl_work, rpc_free_client_work); schedule_work(&clnt->cl_work); return parent; } /* * Free an RPC client */ static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { /* * Note: RPCSEC_GSS may need to send NULL RPC calls in order to * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ if (clnt->cl_auth != NULL) { rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; } if (refcount_dec_and_test(&clnt->cl_count)) return rpc_free_client(clnt); return NULL; } /* * Release reference to the RPC client */ void rpc_release_client(struct rpc_clnt *clnt) { do { if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); if (refcount_dec_not_one(&clnt->cl_count)) break; clnt = rpc_free_auth(clnt); } while (clnt != NULL); } EXPORT_SYMBOL_GPL(rpc_release_client); /** * rpc_bind_new_program - bind a new RPC program to an existing client * @old: old rpc_client * @program: rpc program to set * @vers: rpc program version * * Clones the rpc client and sets up a new RPC program. This is mainly * of use for enabling different RPC programs to share the same transport. * The Sun NFSv2/v3 ACL protocol can do this. */ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, const struct rpc_program *program, u32 vers) { struct rpc_create_args args = { .program = program, .prognumber = program->number, .version = vers, .authflavor = old->cl_auth->au_flavor, .cred = old->cl_cred, .stats = old->cl_stats, .timeout = old->cl_timeout, }; struct rpc_clnt *clnt; int err; clnt = __rpc_clone_client(&args, old); if (IS_ERR(clnt)) goto out; err = rpc_ping(clnt); if (err != 0) { rpc_shutdown_client(clnt); clnt = ERR_PTR(err); } out: return clnt; } EXPORT_SYMBOL_GPL(rpc_bind_new_program); struct rpc_xprt * rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; if (!xprt) return NULL; rcu_read_lock(); xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); atomic_long_inc(&xps->xps_queuelen); rcu_read_unlock(); atomic_long_inc(&xprt->queuelen); return xprt; } static void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; atomic_long_dec(&xprt->queuelen); rcu_read_lock(); xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); atomic_long_dec(&xps->xps_queuelen); rcu_read_unlock(); xprt_put(xprt); } void rpc_task_release_transport(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; if (xprt) { task->tk_xprt = NULL; if (task->tk_client) rpc_task_release_xprt(task->tk_client, xprt); else xprt_put(xprt); } } EXPORT_SYMBOL_GPL(rpc_task_release_transport); void rpc_task_release_client(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; rpc_task_release_transport(task); if (clnt != NULL) { /* Remove from client task list */ spin_lock(&clnt->cl_lock); list_del(&task->tk_task); spin_unlock(&clnt->cl_lock); task->tk_client = NULL; atomic_dec(&clnt->cl_task_count); rpc_release_client(clnt); } } static struct rpc_xprt * rpc_task_get_first_xprt(struct rpc_clnt *clnt) { struct rpc_xprt *xprt; rcu_read_lock(); xprt = xprt_get(rcu_dereference(clnt->cl_xprt)); rcu_read_unlock(); return rpc_task_get_xprt(clnt, xprt); } static struct rpc_xprt * rpc_task_get_next_xprt(struct rpc_clnt *clnt) { return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi)); } static void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) { if (task->tk_xprt) { if (!(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && (task->tk_flags & RPC_TASK_MOVEABLE))) return; xprt_release(task); xprt_put(task->tk_xprt); } if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) task->tk_xprt = rpc_task_get_first_xprt(clnt); else task->tk_xprt = rpc_task_get_next_xprt(clnt); } static void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) { rpc_task_set_transport(task, clnt); task->tk_client = clnt; refcount_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; if (clnt->cl_softerr) task->tk_flags |= RPC_TASK_TIMEOUT; if (clnt->cl_noretranstimeo) task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; if (clnt->cl_netunreach_fatal) task->tk_flags |= RPC_TASK_NETUNREACH_FATAL; atomic_inc(&clnt->cl_task_count); } static void rpc_task_set_rpc_message(struct rpc_task *task, const struct rpc_message *msg) { if (msg != NULL) { task->tk_msg.rpc_proc = msg->rpc_proc; task->tk_msg.rpc_argp = msg->rpc_argp; task->tk_msg.rpc_resp = msg->rpc_resp; task->tk_msg.rpc_cred = msg->rpc_cred; if (!(task->tk_flags & RPC_TASK_CRED_NOREF)) get_cred(task->tk_msg.rpc_cred); } } /* * Default callback for async RPC calls */ static void rpc_default_callback(struct rpc_task *task, void *data) { } static const struct rpc_call_ops rpc_default_ops = { .rpc_call_done = rpc_default_callback, }; /** * rpc_run_task - Allocate a new RPC task, then run rpc_execute against it * @task_setup_data: pointer to task initialisation data */ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) { struct rpc_task *task; task = rpc_new_task(task_setup_data); if (IS_ERR(task)) return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; rpc_task_set_client(task, task_setup_data->rpc_client); rpc_task_set_rpc_message(task, task_setup_data->rpc_message); if (task->tk_action == NULL) rpc_call_start(task); atomic_inc(&task->tk_count); rpc_execute(task); return task; } EXPORT_SYMBOL_GPL(rpc_run_task); /** * rpc_call_sync - Perform a synchronous RPC call * @clnt: pointer to RPC client * @msg: RPC call parameters * @flags: RPC call flags */ int rpc_call_sync(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags) { struct rpc_task *task; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, .rpc_message = msg, .callback_ops = &rpc_default_ops, .flags = flags, }; int status; WARN_ON_ONCE(flags & RPC_TASK_ASYNC); if (flags & RPC_TASK_ASYNC) { rpc_release_calldata(task_setup_data.callback_ops, task_setup_data.callback_data); return -EINVAL; } task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); status = task->tk_status; rpc_put_task(task); return status; } EXPORT_SYMBOL_GPL(rpc_call_sync); /** * rpc_call_async - Perform an asynchronous RPC call * @clnt: pointer to RPC client * @msg: RPC call parameters * @flags: RPC call flags * @tk_ops: RPC call ops * @data: user call data */ int rpc_call_async(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags, const struct rpc_call_ops *tk_ops, void *data) { struct rpc_task *task; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, .rpc_message = msg, .callback_ops = tk_ops, .callback_data = data, .flags = flags|RPC_TASK_ASYNC, }; task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); rpc_put_task(task); return 0; } EXPORT_SYMBOL_GPL(rpc_call_async); #if defined(CONFIG_SUNRPC_BACKCHANNEL) static void call_bc_encode(struct rpc_task *task); /** * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run * rpc_execute against it * @req: RPC request * @timeout: timeout values to use for this task */ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, struct rpc_timeout *timeout) { struct rpc_task *task; struct rpc_task_setup task_setup_data = { .callback_ops = &rpc_default_ops, .flags = RPC_TASK_SOFTCONN | RPC_TASK_NO_RETRANS_TIMEOUT, }; dprintk("RPC: rpc_run_bc_task req= %p\n", req); /* * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); if (IS_ERR(task)) { xprt_free_bc_request(req); return task; } xprt_init_bc_request(req, task, timeout); task->tk_action = call_bc_encode; atomic_inc(&task->tk_count); WARN_ON_ONCE(atomic_read(&task->tk_count) != 2); rpc_execute(task); dprintk("RPC: rpc_run_bc_task: task= %p\n", task); return task; } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** * rpc_prepare_reply_pages - Prepare to receive a reply data payload into pages * @req: RPC request to prepare * @pages: vector of struct page pointers * @base: offset in first page where receive should start, in bytes * @len: expected size of the upper layer data payload, in bytes * @hdrsize: expected size of upper layer reply header, in XDR words * */ void rpc_prepare_reply_pages(struct rpc_rqst *req, struct page **pages, unsigned int base, unsigned int len, unsigned int hdrsize) { hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign; xdr_inline_pages(&req->rq_rcv_buf, hdrsize << 2, pages, base, len); trace_rpc_xdr_reply_pages(req->rq_task, &req->rq_rcv_buf); } EXPORT_SYMBOL_GPL(rpc_prepare_reply_pages); void rpc_call_start(struct rpc_task *task) { task->tk_action = call_start; } EXPORT_SYMBOL_GPL(rpc_call_start); /** * rpc_peeraddr - extract remote peer address from clnt's xprt * @clnt: RPC client structure * @buf: target buffer * @bufsize: length of target buffer * * Returns the number of bytes that are actually in the stored address. */ size_t rpc_peeraddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t bufsize) { size_t bytes; struct rpc_xprt *xprt; rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); bytes = xprt->addrlen; if (bytes > bufsize) bytes = bufsize; memcpy(buf, &xprt->addr, bytes); rcu_read_unlock(); return bytes; } EXPORT_SYMBOL_GPL(rpc_peeraddr); /** * rpc_peeraddr2str - return remote peer address in printable format * @clnt: RPC client structure * @format: address format * * NB: the lifetime of the memory referenced by the returned pointer is * the same as the rpc_xprt itself. As long as the caller uses this * pointer, it must hold the RCU read lock. */ const char *rpc_peeraddr2str(struct rpc_clnt *clnt, enum rpc_display_format_t format) { struct rpc_xprt *xprt; xprt = rcu_dereference(clnt->cl_xprt); if (xprt->address_strings[format] != NULL) return xprt->address_strings[format]; else return "unprintable"; } EXPORT_SYMBOL_GPL(rpc_peeraddr2str); static const struct sockaddr_in rpc_inaddr_loopback = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; static const struct sockaddr_in6 rpc_in6addr_loopback = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_ANY_INIT, }; /* * Try a getsockname() on a connected datagram socket. Using a * connected datagram socket prevents leaving a socket in TIME_WAIT. * This conserves the ephemeral port number space. * * Returns zero and fills in "buf" if successful; otherwise, a * negative errno is returned. */ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, struct sockaddr *buf) { struct socket *sock; int err; err = __sock_create(net, sap->sa_family, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); if (err < 0) { dprintk("RPC: can't create UDP socket (%d)\n", err); goto out; } switch (sap->sa_family) { case AF_INET: err = kernel_bind(sock, (struct sockaddr_unsized *)&rpc_inaddr_loopback, sizeof(rpc_inaddr_loopback)); break; case AF_INET6: err = kernel_bind(sock, (struct sockaddr_unsized *)&rpc_in6addr_loopback, sizeof(rpc_in6addr_loopback)); break; default: err = -EAFNOSUPPORT; goto out_release; } if (err < 0) { dprintk("RPC: can't bind UDP socket (%d)\n", err); goto out_release; } err = kernel_connect(sock, (struct sockaddr_unsized *)sap, salen, 0); if (err < 0) { dprintk("RPC: can't connect UDP socket (%d)\n", err); goto out_release; } err = kernel_getsockname(sock, buf); if (err < 0) { dprintk("RPC: getsockname failed (%d)\n", err); goto out_release; } err = 0; if (buf->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)buf; sin6->sin6_scope_id = 0; } dprintk("RPC: %s succeeded\n", __func__); out_release: sock_release(sock); out: return err; } /* * Scraping a connected socket failed, so we don't have a useable * local address. Fallback: generate an address that will prevent * the server from calling us back. * * Returns zero and fills in "buf" if successful; otherwise, a * negative errno is returned. */ static int rpc_anyaddr(int family, struct sockaddr *buf, size_t buflen) { switch (family) { case AF_INET: if (buflen < sizeof(rpc_inaddr_loopback)) return -EINVAL; memcpy(buf, &rpc_inaddr_loopback, sizeof(rpc_inaddr_loopback)); break; case AF_INET6: if (buflen < sizeof(rpc_in6addr_loopback)) return -EINVAL; memcpy(buf, &rpc_in6addr_loopback, sizeof(rpc_in6addr_loopback)); break; default: dprintk("RPC: %s: address family not supported\n", __func__); return -EAFNOSUPPORT; } dprintk("RPC: %s: succeeded\n", __func__); return 0; } /** * rpc_localaddr - discover local endpoint address for an RPC client * @clnt: RPC client structure * @buf: target buffer * @buflen: size of target buffer, in bytes * * Returns zero and fills in "buf" and "buflen" if successful; * otherwise, a negative errno is returned. * * This works even if the underlying transport is not currently connected, * or if the upper layer never previously provided a source address. * * The result of this function call is transient: multiple calls in * succession may give different results, depending on how local * networking configuration changes over time. */ int rpc_localaddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t buflen) { struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; struct rpc_xprt *xprt; struct net *net; size_t salen; int err; rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); salen = xprt->addrlen; memcpy(sap, &xprt->addr, salen); net = get_net(xprt->xprt_net); rcu_read_unlock(); rpc_set_port(sap, 0); err = rpc_sockname(net, sap, salen, buf); put_net(net); if (err != 0) /* Couldn't discover local address, return ANYADDR */ return rpc_anyaddr(sap->sa_family, buf, buflen); return 0; } EXPORT_SYMBOL_GPL(rpc_localaddr); void rpc_setbufsize(struct rpc_clnt *clnt, unsigned int sndsize, unsigned int rcvsize) { struct rpc_xprt *xprt; rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); if (xprt->ops->set_buffer_size) xprt->ops->set_buffer_size(xprt, sndsize, rcvsize); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rpc_setbufsize); /** * rpc_net_ns - Get the network namespace for this RPC client * @clnt: RPC client to query * */ struct net *rpc_net_ns(struct rpc_clnt *clnt) { struct net *ret; rcu_read_lock(); ret = rcu_dereference(clnt->cl_xprt)->xprt_net; rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rpc_net_ns); /** * rpc_max_payload - Get maximum payload size for a transport, in bytes * @clnt: RPC client to query * * For stream transports, this is one RPC record fragment (see RFC * 1831), as we don't support multi-record requests yet. For datagram * transports, this is the size of an IP packet minus the IP, UDP, and * RPC header sizes. */ size_t rpc_max_payload(struct rpc_clnt *clnt) { size_t ret; rcu_read_lock(); ret = rcu_dereference(clnt->cl_xprt)->max_payload; rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rpc_max_payload); /** * rpc_max_bc_payload - Get maximum backchannel payload size, in bytes * @clnt: RPC client to query */ size_t rpc_max_bc_payload(struct rpc_clnt *clnt) { struct rpc_xprt *xprt; size_t ret; rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); ret = xprt->ops->bc_maxpayload(xprt); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rpc_max_bc_payload); unsigned int rpc_num_bc_slots(struct rpc_clnt *clnt) { struct rpc_xprt *xprt; unsigned int ret; rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); ret = xprt->ops->bc_num_slots(xprt); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rpc_num_bc_slots); /** * rpc_force_rebind - force transport to check that remote port is unchanged * @clnt: client to rebind * */ void rpc_force_rebind(struct rpc_clnt *clnt) { if (clnt->cl_autobind) { rcu_read_lock(); xprt_clear_bound(rcu_dereference(clnt->cl_xprt)); rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(rpc_force_rebind); static int __rpc_restart_call(struct rpc_task *task, void (*action)(struct rpc_task *)) { task->tk_status = 0; task->tk_rpc_status = 0; task->tk_action = action; return 1; } /* * Restart an (async) RPC call. Usually called from within the * exit handler. */ int rpc_restart_call(struct rpc_task *task) { return __rpc_restart_call(task, call_start); } EXPORT_SYMBOL_GPL(rpc_restart_call); /* * Restart an (async) RPC call from the call_prepare state. * Usually called from within the exit handler. */ int rpc_restart_call_prepare(struct rpc_task *task) { if (task->tk_ops->rpc_call_prepare != NULL) return __rpc_restart_call(task, rpc_prepare_task); return rpc_restart_call(task); } EXPORT_SYMBOL_GPL(rpc_restart_call_prepare); const char *rpc_proc_name(const struct rpc_task *task) { const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; if (proc) { if (proc->p_name) return proc->p_name; else return "NULL"; } else return "no proc"; } static void __rpc_call_rpcerror(struct rpc_task *task, int tk_status, int rpc_status) { trace_rpc_call_rpcerror(task, tk_status, rpc_status); rpc_task_set_rpc_status(task, rpc_status); rpc_exit(task, tk_status); } static void rpc_call_rpcerror(struct rpc_task *task, int status) { __rpc_call_rpcerror(task, status, status); } /* * 0. Initial state * * Other FSM states can be visited zero or more times, but * this state is visited exactly once for each RPC. */ static void call_start(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; int idx = task->tk_msg.rpc_proc->p_statidx; trace_rpc_request(task); if (task->tk_client->cl_shutdown) { rpc_call_rpcerror(task, -EIO); return; } /* Increment call count (version might not be valid for ping) */ if (clnt->cl_program->version[clnt->cl_vers]) clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; rpc_task_set_transport(task, clnt); } /* * 1. Reserve an RPC call slot */ static void call_reserve(struct rpc_task *task) { task->tk_status = 0; task->tk_action = call_reserveresult; xprt_reserve(task); } static void call_retry_reserve(struct rpc_task *task); /* * 1b. Grok the result of xprt_reserve() */ static void call_reserveresult(struct rpc_task *task) { int status = task->tk_status; /* * After a call to xprt_reserve(), we must have either * a request slot or else an error status. */ task->tk_status = 0; if (status >= 0) { if (task->tk_rqstp) { task->tk_action = call_refresh; /* Add to the client's list of all tasks */ spin_lock(&task->tk_client->cl_lock); if (list_empty(&task->tk_task)) list_add_tail(&task->tk_task, &task->tk_client->cl_tasks); spin_unlock(&task->tk_client->cl_lock); return; } rpc_call_rpcerror(task, -EIO); return; } switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); fallthrough; case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; return; default: rpc_call_rpcerror(task, status); } } /* * 1c. Retry reserving an RPC call slot */ static void call_retry_reserve(struct rpc_task *task) { task->tk_status = 0; task->tk_action = call_reserveresult; xprt_retry_reserve(task); } /* * 2. Bind and/or refresh the credentials */ static void call_refresh(struct rpc_task *task) { task->tk_action = call_refreshresult; task->tk_status = 0; task->tk_client->cl_stats->rpcauthrefresh++; rpcauth_refreshcred(task); } /* * 2a. Process the results of a credential refresh */ static void call_refreshresult(struct rpc_task *task) { int status = task->tk_status; task->tk_status = 0; task->tk_action = call_refresh; switch (status) { case 0: if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; return; } /* Use rate-limiting and a max number of retries if refresh * had status 0 but failed to update the cred. */ fallthrough; case -ETIMEDOUT: rpc_delay(task, 3*HZ); fallthrough; case -EAGAIN: status = -EACCES; if (!task->tk_cred_retry) break; task->tk_cred_retry--; trace_rpc_retry_refresh_status(task); return; case -EKEYEXPIRED: break; case -ENOMEM: rpc_delay(task, HZ >> 4); return; } trace_rpc_refresh_status(task); rpc_call_rpcerror(task, status); } /* * 2b. Allocate the buffer. For details, see sched.c:rpc_malloc. * (Note: buffer memory is freed in xprt_release). */ static void call_allocate(struct rpc_task *task) { const struct rpc_auth *auth = task->tk_rqstp->rq_cred->cr_auth; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; int status; task->tk_status = 0; task->tk_action = call_encode; if (req->rq_buffer) return; /* * Calculate the size (in quads) of the RPC call * and reply headers, and convert both values * to byte sizes. */ req->rq_callsize = RPC_CALLHDRSIZE + (auth->au_cslack << 1) + proc->p_arglen; req->rq_callsize <<= 2; /* * Note: the reply buffer must at minimum allocate enough space * for the 'struct accepted_reply' from RFC5531. */ req->rq_rcvsize = RPC_REPHDRSIZE + auth->au_rslack + \ max_t(size_t, proc->p_replen, 2); req->rq_rcvsize <<= 2; status = xprt->ops->buf_alloc(task); trace_rpc_buf_alloc(task, status); if (status == 0) return; if (status != -ENOMEM) { rpc_call_rpcerror(task, status); return; } if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) { task->tk_action = call_allocate; rpc_delay(task, HZ>>4); return; } rpc_call_rpcerror(task, -ERESTARTSYS); } static int rpc_task_need_encode(struct rpc_task *task) { return test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) == 0 && (!(task->tk_flags & RPC_TASK_SENT) || !(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) || xprt_request_need_retransmit(task)); } static void rpc_xdr_encode(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct xdr_stream xdr; xdr_buf_init(&req->rq_snd_buf, req->rq_buffer, req->rq_callsize); xdr_buf_init(&req->rq_rcv_buf, req->rq_rbuffer, req->rq_rcvsize); req->rq_reply_bytes_recvd = 0; req->rq_snd_buf.head[0].iov_len = 0; xdr_init_encode(&xdr, &req->rq_snd_buf, req->rq_snd_buf.head[0].iov_base, req); if (rpc_encode_header(task, &xdr)) return; task->tk_status = rpcauth_wrap_req(task, &xdr); } /* * 3. Encode arguments of an RPC call */ static void call_encode(struct rpc_task *task) { if (!rpc_task_need_encode(task)) goto out; /* Dequeue task from the receive queue while we're encoding */ xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); /* Add task to reply queue before transmission to avoid races */ if (task->tk_status == 0 && rpc_reply_expected(task)) task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ switch (task->tk_status) { case -EAGAIN: case -ENOMEM: rpc_delay(task, HZ >> 4); break; case -EKEYEXPIRED: if (!task->tk_cred_retry) { rpc_call_rpcerror(task, task->tk_status); } else { task->tk_action = call_refresh; task->tk_cred_retry--; trace_rpc_retry_refresh_status(task); } break; default: rpc_call_rpcerror(task, task->tk_status); } return; } xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; /* Check that the connection is OK */ if (!xprt_bound(task->tk_xprt)) task->tk_action = call_bind; else if (!xprt_connected(task->tk_xprt)) task->tk_action = call_connect; } /* * Helpers to check if the task was already transmitted, and * to take action when that is the case. */ static bool rpc_task_transmitted(struct rpc_task *task) { return !test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); } static void rpc_task_handle_transmitted(struct rpc_task *task) { xprt_end_transmit(task); task->tk_action = call_transmit_status; } /* * 4. Get the server port number if not yet set */ static void call_bind(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; if (rpc_task_transmitted(task)) { rpc_task_handle_transmitted(task); return; } if (xprt_bound(xprt)) { task->tk_action = call_connect; return; } task->tk_action = call_bind_status; if (!xprt_prepare_transmit(task)) return; xprt->ops->rpcbind(task); } /* * 4a. Sort out bind result */ static void call_bind_status(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; int status = -EIO; if (rpc_task_transmitted(task)) { rpc_task_handle_transmitted(task); return; } if (task->tk_status >= 0) goto out_next; if (xprt_bound(xprt)) { task->tk_status = 0; goto out_next; } switch (task->tk_status) { case -ENOMEM: rpc_delay(task, HZ >> 2); goto retry_timeout; case -EACCES: trace_rpcb_prog_unavail_err(task); /* fail immediately if this is an RPC ping */ if (task->tk_msg.rpc_proc->p_proc == 0) { status = -EOPNOTSUPP; break; } rpc_delay(task, 3*HZ); goto retry_timeout; case -ENOBUFS: rpc_delay(task, HZ >> 2); goto retry_timeout; case -EAGAIN: goto retry_timeout; case -ETIMEDOUT: trace_rpcb_timeout_err(task); goto retry_timeout; case -EPFNOSUPPORT: /* server doesn't support any rpcbind version we know of */ trace_rpcb_bind_version_err(task); break; case -EPROTONOSUPPORT: trace_rpcb_bind_version_err(task); goto retry_timeout; case -ENETDOWN: case -ENETUNREACH: if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL) break; fallthrough; case -ECONNREFUSED: /* connection problems */ case -ECONNRESET: case -ECONNABORTED: case -ENOTCONN: case -EHOSTDOWN: case -EHOSTUNREACH: case -EPIPE: trace_rpcb_unreachable_err(task); if (!RPC_IS_SOFTCONN(task)) { rpc_delay(task, 5*HZ); goto retry_timeout; } status = task->tk_status; break; default: trace_rpcb_unrecognized_err(task); } rpc_call_rpcerror(task, status); return; out_next: task->tk_action = call_connect; return; retry_timeout: task->tk_status = 0; task->tk_action = call_bind; rpc_check_timeout(task); } /* * 4b. Connect to the RPC server */ static void call_connect(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; if (rpc_task_transmitted(task)) { rpc_task_handle_transmitted(task); return; } if (xprt_connected(xprt)) { task->tk_action = call_transmit; return; } task->tk_action = call_connect_status; if (task->tk_status < 0) return; if (task->tk_flags & RPC_TASK_NOCONNECT) { rpc_call_rpcerror(task, -ENOTCONN); return; } if (!xprt_prepare_transmit(task)) return; xprt_connect(task); } /* * 4c. Sort out connect result */ static void call_connect_status(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; struct rpc_clnt *clnt = task->tk_client; int status = task->tk_status; if (rpc_task_transmitted(task)) { rpc_task_handle_transmitted(task); return; } trace_rpc_connect_status(task); if (task->tk_status == 0) { clnt->cl_stats->netreconn++; goto out_next; } if (xprt_connected(xprt)) { task->tk_status = 0; goto out_next; } task->tk_status = 0; switch (status) { case -ENETDOWN: case -ENETUNREACH: if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL) break; fallthrough; case -ECONNREFUSED: case -ECONNRESET: /* A positive refusal suggests a rebind is needed. */ if (clnt->cl_autobind) { rpc_force_rebind(clnt); if (RPC_IS_SOFTCONN(task)) break; goto out_retry; } fallthrough; case -ECONNABORTED: case -EHOSTUNREACH: case -EPIPE: case -EPROTO: xprt_conditional_disconnect(task->tk_rqstp->rq_xprt, task->tk_rqstp->rq_connect_cookie); if (RPC_IS_SOFTCONN(task)) break; /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); fallthrough; case -EADDRINUSE: case -ENOTCONN: case -EAGAIN: case -ETIMEDOUT: if (!(task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) && (task->tk_flags & RPC_TASK_MOVEABLE) && test_bit(XPRT_REMOVE, &xprt->state)) { struct rpc_xprt *saved = task->tk_xprt; struct rpc_xprt_switch *xps; xps = rpc_clnt_xprt_switch_get(clnt); if (xps->xps_nxprts > 1) { long value; xprt_release(task); value = atomic_long_dec_return(&xprt->queuelen); if (value == 0) rpc_xprt_switch_remove_xprt(xps, saved, true); xprt_put(saved); task->tk_xprt = NULL; task->tk_action = call_start; } xprt_switch_put(xps); if (!task->tk_xprt) goto out; } goto out_retry; case -ENOBUFS: rpc_delay(task, HZ >> 2); goto out_retry; } rpc_call_rpcerror(task, status); return; out_next: task->tk_action = call_transmit; return; out_retry: /* Check for timeouts before looping back to call_bind */ task->tk_action = call_bind; out: rpc_check_timeout(task); } /* * 5. Transmit the RPC request, and wait for reply */ static void call_transmit(struct rpc_task *task) { if (rpc_task_transmitted(task)) { rpc_task_handle_transmitted(task); return; } task->tk_action = call_transmit_status; if (!xprt_prepare_transmit(task)) return; task->tk_status = 0; if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) { if (!xprt_connected(task->tk_xprt)) { task->tk_status = -ENOTCONN; return; } xprt_transmit(task); } xprt_end_transmit(task); } /* * 5a. Handle cleanup after a transmission */ static void call_transmit_status(struct rpc_task *task) { task->tk_action = call_status; /* * Common case: success. Force the compiler to put this * test first. */ if (rpc_task_transmitted(task)) { task->tk_status = 0; xprt_request_wait_receive(task); return; } switch (task->tk_status) { default: break; case -EBADMSG: task->tk_status = 0; task->tk_action = call_encode; break; /* * Special cases: if we've been waiting on the * socket's write_space() callback, or if the * socket just returned a connection error, * then hold onto the transport lock. */ case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; case -EBADSLT: case -EAGAIN: task->tk_action = call_transmit; task->tk_status = 0; break; case -EHOSTDOWN: case -ENETDOWN: case -EHOSTUNREACH: case -ENETUNREACH: case -EPERM: break; case -ECONNREFUSED: if (RPC_IS_SOFTCONN(task)) { if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, task->tk_status); rpc_call_rpcerror(task, task->tk_status); return; } fallthrough; case -ECONNRESET: case -ECONNABORTED: case -EADDRINUSE: case -ENOTCONN: case -EPIPE: task->tk_action = call_bind; task->tk_status = 0; break; } rpc_check_timeout(task); } #if defined(CONFIG_SUNRPC_BACKCHANNEL) static void call_bc_transmit(struct rpc_task *task); static void call_bc_transmit_status(struct rpc_task *task); static void call_bc_encode(struct rpc_task *task) { xprt_request_enqueue_transmit(task); task->tk_action = call_bc_transmit; } /* * 5b. Send the backchannel RPC reply. On error, drop the reply. In * addition, disconnect on connectivity errors. */ static void call_bc_transmit(struct rpc_task *task) { task->tk_action = call_bc_transmit_status; if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) { if (!xprt_prepare_transmit(task)) return; task->tk_status = 0; xprt_transmit(task); } xprt_end_transmit(task); } static void call_bc_transmit_status(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; if (rpc_task_transmitted(task)) task->tk_status = 0; switch (task->tk_status) { case 0: /* Success */ case -ENETDOWN: case -EHOSTDOWN: case -EHOSTUNREACH: case -ENETUNREACH: case -ECONNRESET: case -ECONNREFUSED: case -EADDRINUSE: case -ENOTCONN: case -EPIPE: break; case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; case -EBADSLT: case -EAGAIN: task->tk_status = 0; task->tk_action = call_bc_transmit; return; case -ETIMEDOUT: /* * Problem reaching the server. Disconnect and let the * forechannel reestablish the connection. The server will * have to retransmit the backchannel request and we'll * reprocess it. Since these ops are idempotent, there's no * need to cache our reply at this time. */ printk(KERN_NOTICE "RPC: Could not send backchannel reply " "error: %d\n", task->tk_status); xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); break; default: /* * We were unable to reply and will have to drop the * request. The server should reconnect and retransmit. */ printk(KERN_NOTICE "RPC: Could not send backchannel reply " "error: %d\n", task->tk_status); break; } task->tk_action = rpc_exit_task; } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * 6. Sort out the RPC call status */ static void call_status(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; int status; if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, task->tk_status); status = task->tk_status; if (status >= 0) { task->tk_action = call_decode; return; } trace_rpc_call_status(task); task->tk_status = 0; switch(status) { case -ENETDOWN: case -ENETUNREACH: if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL) goto out_exit; fallthrough; case -EHOSTDOWN: case -EHOSTUNREACH: case -EPERM: if (RPC_IS_SOFTCONN(task)) goto out_exit; /* * Delay any retries for 3 seconds, then handle as if it * were a timeout. */ rpc_delay(task, 3*HZ); fallthrough; case -ETIMEDOUT: break; case -ECONNREFUSED: case -ECONNRESET: case -ECONNABORTED: case -ENOTCONN: rpc_force_rebind(clnt); break; case -EADDRINUSE: rpc_delay(task, 3*HZ); fallthrough; case -EPIPE: case -EAGAIN: break; case -ENFILE: case -ENOBUFS: case -ENOMEM: rpc_delay(task, HZ>>2); break; case -EIO: /* shutdown or soft timeout */ goto out_exit; default: if (clnt->cl_chatty) printk("%s: RPC call returned error %d\n", clnt->cl_program->name, -status); goto out_exit; } task->tk_action = call_encode; rpc_check_timeout(task); return; out_exit: rpc_call_rpcerror(task, status); } static bool rpc_check_connected(const struct rpc_rqst *req) { /* No allocated request or transport? return true */ if (!req || !req->rq_xprt) return true; return xprt_connected(req->rq_xprt); } static void rpc_check_timeout(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; if (RPC_SIGNALLED(task)) return; if (xprt_adjust_timeout(task->tk_rqstp) == 0) return; trace_rpc_timeout_status(task); task->tk_timeouts++; if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) { rpc_call_rpcerror(task, -ETIMEDOUT); return; } if (RPC_IS_SOFT(task)) { /* * Once a "no retrans timeout" soft tasks (a.k.a NFSv4) has * been sent, it should time out only if the transport * connection gets terminally broken. */ if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) && rpc_check_connected(task->tk_rqstp)) return; if (clnt->cl_chatty) { pr_notice_ratelimited( "%s: server %s not responding, timed out\n", clnt->cl_program->name, task->tk_xprt->servername); } if (task->tk_flags & RPC_TASK_TIMEOUT) rpc_call_rpcerror(task, -ETIMEDOUT); else __rpc_call_rpcerror(task, -EIO, -ETIMEDOUT); return; } if (!(task->tk_flags & RPC_CALL_MAJORSEEN)) { task->tk_flags |= RPC_CALL_MAJORSEEN; if (clnt->cl_chatty) { pr_notice_ratelimited( "%s: server %s not responding, still trying\n", clnt->cl_program->name, task->tk_xprt->servername); } } rpc_force_rebind(clnt); /* * Did our request time out due to an RPCSEC_GSS out-of-sequence * event? RFC2203 requires the server to drop all such requests. */ rpcauth_invalcred(task); } /* * 7. Decode the RPC reply */ static void call_decode(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; struct xdr_stream xdr; int err; if (!task->tk_msg.rpc_proc->p_decode) { task->tk_action = rpc_exit_task; return; } if (task->tk_flags & RPC_CALL_MAJORSEEN) { if (clnt->cl_chatty) { pr_notice_ratelimited("%s: server %s OK\n", clnt->cl_program->name, task->tk_xprt->servername); } task->tk_flags &= ~RPC_CALL_MAJORSEEN; } /* * Did we ever call xprt_complete_rqst()? If not, we should assume * the message is incomplete. */ err = -EAGAIN; if (!req->rq_reply_bytes_recvd) goto out; /* Ensure that we see all writes made by xprt_complete_rqst() * before it changed req->rq_reply_bytes_recvd. */ smp_rmb(); req->rq_rcv_buf.len = req->rq_private_buf.len; trace_rpc_xdr_recvfrom(task, &req->rq_rcv_buf); /* Check that the softirq receive buffer is valid */ WARN_ON(memcmp(&req->rq_rcv_buf, &req->rq_private_buf, sizeof(req->rq_rcv_buf)) != 0); xdr_init_decode(&xdr, &req->rq_rcv_buf, req->rq_rcv_buf.head[0].iov_base, req); err = rpc_decode_header(task, &xdr); out: switch (err) { case 0: task->tk_action = rpc_exit_task; task->tk_status = rpcauth_unwrap_resp(task, &xdr); xdr_finish_decode(&xdr); return; case -EAGAIN: task->tk_status = 0; if (task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); task->tk_action = call_encode; rpc_check_timeout(task); break; case -EKEYREJECTED: task->tk_action = call_reserve; rpc_check_timeout(task); rpcauth_invalcred(task); /* Ensure we obtain a new XID if we retry! */ xprt_release(task); } } static int rpc_encode_header(struct rpc_task *task, struct xdr_stream *xdr) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; __be32 *p; int error; error = -EMSGSIZE; p = xdr_reserve_space(xdr, RPC_CALLHDRSIZE << 2); if (!p) goto out_fail; *p++ = req->rq_xid; *p++ = rpc_call; *p++ = cpu_to_be32(RPC_VERSION); *p++ = cpu_to_be32(clnt->cl_prog); *p++ = cpu_to_be32(clnt->cl_vers); *p = cpu_to_be32(task->tk_msg.rpc_proc->p_proc); error = rpcauth_marshcred(task, xdr); if (error < 0) goto out_fail; return 0; out_fail: trace_rpc_bad_callhdr(task); rpc_call_rpcerror(task, error); return error; } static noinline int rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr) { struct rpc_clnt *clnt = task->tk_client; int error; __be32 *p; /* RFC-1014 says that the representation of XDR data must be a * multiple of four bytes * - if it isn't pointer subtraction in the NFS client may give * undefined results */ if (task->tk_rqstp->rq_rcv_buf.len & 3) goto out_unparsable; p = xdr_inline_decode(xdr, 3 * sizeof(*p)); if (!p) goto out_unparsable; p++; /* skip XID */ if (*p++ != rpc_reply) goto out_unparsable; if (*p++ != rpc_msg_accepted) goto out_msg_denied; error = rpcauth_checkverf(task, xdr); if (error) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; if (!test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags)) { rpcauth_invalcred(task); if (!task->tk_cred_retry) goto out_err; task->tk_cred_retry--; trace_rpc__stale_creds(task); return -EKEYREJECTED; } goto out_verifier; } p = xdr_inline_decode(xdr, sizeof(*p)); if (!p) goto out_unparsable; switch (*p) { case rpc_success: return 0; case rpc_prog_unavail: trace_rpc__prog_unavail(task); error = -EPFNOSUPPORT; goto out_err; case rpc_prog_mismatch: trace_rpc__prog_mismatch(task); error = -EPROTONOSUPPORT; goto out_err; case rpc_proc_unavail: trace_rpc__proc_unavail(task); error = -EOPNOTSUPP; goto out_err; case rpc_garbage_args: case rpc_system_err: trace_rpc__garbage_args(task); error = -EIO; break; default: goto out_unparsable; } out_garbage: clnt->cl_stats->rpcgarbage++; if (task->tk_garb_retry) { task->tk_garb_retry--; task->tk_action = call_encode; return -EAGAIN; } out_err: rpc_call_rpcerror(task, error); return error; out_unparsable: trace_rpc__unparsable(task); error = -EIO; goto out_garbage; out_verifier: trace_rpc_bad_verifier(task); switch (error) { case -EPROTONOSUPPORT: goto out_err; case -EACCES: /* possible RPCSEC_GSS out-of-sequence event (RFC2203), * reset recv state and keep waiting, don't retransmit */ task->tk_rqstp->rq_reply_bytes_recvd = 0; task->tk_status = xprt_request_enqueue_receive(task); task->tk_action = call_transmit_status; return -EBADMSG; default: goto out_garbage; } out_msg_denied: error = -EACCES; p = xdr_inline_decode(xdr, sizeof(*p)); if (!p) goto out_unparsable; switch (*p++) { case rpc_auth_error: break; case rpc_mismatch: trace_rpc__mismatch(task); error = -EPROTONOSUPPORT; goto out_err; default: goto out_unparsable; } p = xdr_inline_decode(xdr, sizeof(*p)); if (!p) goto out_unparsable; switch (*p++) { case rpc_autherr_rejectedcred: case rpc_autherr_rejectedverf: case rpcsec_gsserr_credproblem: case rpcsec_gsserr_ctxproblem: rpcauth_invalcred(task); if (!task->tk_cred_retry) break; task->tk_cred_retry--; trace_rpc__stale_creds(task); return -EKEYREJECTED; case rpc_autherr_badcred: case rpc_autherr_badverf: /* possibly garbled cred/verf? */ if (!task->tk_garb_retry) break; task->tk_garb_retry--; trace_rpc__bad_creds(task); task->tk_action = call_encode; return -EAGAIN; case rpc_autherr_tooweak: trace_rpc__auth_tooweak(task); pr_warn("RPC: server %s requires stronger authentication.\n", task->tk_xprt->servername); break; default: goto out_unparsable; } goto out_err; } static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, const void *obj) { } static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, void *obj) { return 0; } static const struct rpc_procinfo rpcproc_null = { .p_encode = rpcproc_encode_null, .p_decode = rpcproc_decode_null, }; static const struct rpc_procinfo rpcproc_null_noreply = { .p_encode = rpcproc_encode_null, }; static void rpc_null_call_prepare(struct rpc_task *task, void *data) { task->tk_flags &= ~RPC_TASK_NO_RETRANS_TIMEOUT; rpc_call_start(task); } static const struct rpc_call_ops rpc_null_ops = { .rpc_call_prepare = rpc_null_call_prepare, .rpc_call_done = rpc_default_callback, }; static struct rpc_task *rpc_call_null_helper(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct rpc_cred *cred, int flags, const struct rpc_call_ops *ops, void *data) { struct rpc_message msg = { .rpc_proc = &rpcproc_null, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, .rpc_xprt = xprt, .rpc_message = &msg, .rpc_op_cred = cred, .callback_ops = ops ?: &rpc_null_ops, .callback_data = data, .flags = flags | RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, }; return rpc_run_task(&task_setup_data); } struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int flags) { return rpc_call_null_helper(clnt, NULL, cred, flags, NULL, NULL); } EXPORT_SYMBOL_GPL(rpc_call_null); static int rpc_ping(struct rpc_clnt *clnt) { struct rpc_task *task; int status; if (clnt->cl_auth->au_ops->ping) return clnt->cl_auth->au_ops->ping(clnt); task = rpc_call_null_helper(clnt, NULL, NULL, 0, NULL, NULL); if (IS_ERR(task)) return PTR_ERR(task); status = task->tk_status; rpc_put_task(task); return status; } static int rpc_ping_noreply(struct rpc_clnt *clnt) { struct rpc_message msg = { .rpc_proc = &rpcproc_null_noreply, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, .rpc_message = &msg, .callback_ops = &rpc_null_ops, .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, }; struct rpc_task *task; int status; task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); status = task->tk_status; rpc_put_task(task); return status; } struct rpc_cb_add_xprt_calldata { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; }; static void rpc_cb_add_xprt_done(struct rpc_task *task, void *calldata) { struct rpc_cb_add_xprt_calldata *data = calldata; if (task->tk_status == 0) rpc_xprt_switch_add_xprt(data->xps, data->xprt); } static void rpc_cb_add_xprt_release(void *calldata) { struct rpc_cb_add_xprt_calldata *data = calldata; xprt_put(data->xprt); xprt_switch_put(data->xps); kfree(data); } static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = { .rpc_call_prepare = rpc_null_call_prepare, .rpc_call_done = rpc_cb_add_xprt_done, .rpc_release = rpc_cb_add_xprt_release, }; /** * rpc_clnt_test_and_add_xprt - Test and add a new transport to a rpc_clnt * @clnt: pointer to struct rpc_clnt * @xps: pointer to struct rpc_xprt_switch, * @xprt: pointer struct rpc_xprt * @in_max_connect: pointer to the max_connect value for the passed in xprt transport */ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, void *in_max_connect) { struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; int max_connect = clnt->cl_max_connect; if (in_max_connect) max_connect = *(int *)in_max_connect; if (xps->xps_nunique_destaddr_xprts + 1 > max_connect) { rcu_read_lock(); pr_warn("SUNRPC: reached max allowed number (%d) did not add " "transport to server: %s\n", max_connect, rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); rcu_read_unlock(); return -EINVAL; } data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->xps = xprt_switch_get(xps); data->xprt = xprt_get(xprt); if (rpc_xprt_switch_has_addr(data->xps, (struct sockaddr *)&xprt->addr)) { rpc_cb_add_xprt_release(data); goto success; } task = rpc_call_null_helper(clnt, xprt, NULL, RPC_TASK_ASYNC, &rpc_cb_add_xprt_call_ops, data); if (IS_ERR(task)) return PTR_ERR(task); data->xps->xps_nunique_destaddr_xprts++; rpc_put_task(task); success: return 1; } EXPORT_SYMBOL_GPL(rpc_clnt_test_and_add_xprt); static int rpc_clnt_add_xprt_helper(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct rpc_add_xprt_test *data) { struct rpc_task *task; int status = -EADDRINUSE; /* Test the connection */ task = rpc_call_null_helper(clnt, xprt, NULL, 0, NULL, NULL); if (IS_ERR(task)) return PTR_ERR(task); status = task->tk_status; rpc_put_task(task); if (status < 0) return status; /* rpc_xprt_switch and rpc_xprt are deferrenced by add_xprt_test() */ data->add_xprt_test(clnt, xprt, data->data); return 0; } /** * rpc_clnt_setup_test_and_add_xprt() * * This is an rpc_clnt_add_xprt setup() function which returns 1 so: * 1) caller of the test function must dereference the rpc_xprt_switch * and the rpc_xprt. * 2) test function must call rpc_xprt_switch_add_xprt, usually in * the rpc_call_done routine. * * Upon success (return of 1), the test function adds the new * transport to the rpc_clnt xprt switch * * @clnt: struct rpc_clnt to get the new transport * @xps: the rpc_xprt_switch to hold the new transport * @xprt: the rpc_xprt to test * @data: a struct rpc_add_xprt_test pointer that holds the test function * and test function call data */ int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, void *data) { int status = -EADDRINUSE; xprt = xprt_get(xprt); xprt_switch_get(xps); if (rpc_xprt_switch_has_addr(xps, (struct sockaddr *)&xprt->addr)) goto out_err; status = rpc_clnt_add_xprt_helper(clnt, xprt, data); if (status < 0) goto out_err; status = 1; out_err: xprt_put(xprt); xprt_switch_put(xps); if (status < 0) pr_info("RPC: rpc_clnt_test_xprt failed: %d addr %s not " "added\n", status, xprt->address_strings[RPC_DISPLAY_ADDR]); /* so that rpc_clnt_add_xprt does not call rpc_xprt_switch_add_xprt */ return status; } EXPORT_SYMBOL_GPL(rpc_clnt_setup_test_and_add_xprt); /** * rpc_clnt_add_xprt - Add a new transport to a rpc_clnt * @clnt: pointer to struct rpc_clnt * @xprtargs: pointer to struct xprt_create * @setup: callback to test and/or set up the connection * @data: pointer to setup function data * * Creates a new transport using the parameters set in args and * adds it to clnt. * If ping is set, then test that connectivity succeeds before * adding the new transport. * */ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, struct xprt_create *xprtargs, int (*setup)(struct rpc_clnt *, struct rpc_xprt_switch *, struct rpc_xprt *, void *), void *data) { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; unsigned long connect_timeout; unsigned long reconnect_timeout; unsigned char resvport, reuseport; int ret = 0, ident; rcu_read_lock(); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); xprt = xprt_iter_xprt(&clnt->cl_xpi); if (xps == NULL || xprt == NULL) { rcu_read_unlock(); xprt_switch_put(xps); return -EAGAIN; } resvport = xprt->resvport; reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; ident = xprt->xprt_class->ident; rcu_read_unlock(); if (!xprtargs->ident) xprtargs->ident = ident; xprtargs->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(xprtargs); if (IS_ERR(xprt)) { ret = PTR_ERR(xprt); goto out_put_switch; } xprt->resvport = resvport; xprt->reuseport = reuseport; if (xprtargs->connect_timeout) connect_timeout = xprtargs->connect_timeout; if (xprtargs->reconnect_timeout) reconnect_timeout = xprtargs->reconnect_timeout; if (xprt->ops->set_connect_timeout != NULL) xprt->ops->set_connect_timeout(xprt, connect_timeout, reconnect_timeout); rpc_xprt_switch_set_roundrobin(xps); if (setup) { ret = setup(clnt, xps, xprt, data); if (ret != 0) goto out_put_xprt; } rpc_xprt_switch_add_xprt(xps, xprt); out_put_xprt: xprt_put(xprt); out_put_switch: xprt_switch_put(xps); return ret; } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct rpc_add_xprt_test *data) { struct rpc_xprt *main_xprt; int status = 0; xprt_get(xprt); rcu_read_lock(); main_xprt = xprt_get(rcu_dereference(clnt->cl_xprt)); status = rpc_cmp_addr_port((struct sockaddr *)&xprt->addr, (struct sockaddr *)&main_xprt->addr); rcu_read_unlock(); xprt_put(main_xprt); if (status || !test_bit(XPRT_OFFLINE, &xprt->state)) goto out; status = rpc_clnt_add_xprt_helper(clnt, xprt, data); out: xprt_put(xprt); return status; } /* rpc_clnt_probe_trunked_xprt -- probe offlined transport for session trunking * @clnt rpc_clnt structure * * For each offlined transport found in the rpc_clnt structure call * the function rpc_xprt_probe_trunked() which will determine if this * transport still belongs to the trunking group. */ void rpc_clnt_probe_trunked_xprts(struct rpc_clnt *clnt, struct rpc_add_xprt_test *data) { struct rpc_xprt_iter xpi; int ret; ret = rpc_clnt_xprt_iter_offline_init(clnt, &xpi); if (ret) return; for (;;) { struct rpc_xprt *xprt = xprt_iter_get_next(&xpi); if (!xprt) break; ret = rpc_xprt_probe_trunked(clnt, xprt, data); xprt_put(xprt); if (ret < 0) break; xprt_iter_rewind(&xpi); } xprt_iter_destroy(&xpi); } EXPORT_SYMBOL_GPL(rpc_clnt_probe_trunked_xprts); static int rpc_xprt_offline(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { struct rpc_xprt *main_xprt; struct rpc_xprt_switch *xps; int err = 0; xprt_get(xprt); rcu_read_lock(); main_xprt = xprt_get(rcu_dereference(clnt->cl_xprt)); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); err = rpc_cmp_addr_port((struct sockaddr *)&xprt->addr, (struct sockaddr *)&main_xprt->addr); rcu_read_unlock(); xprt_put(main_xprt); if (err) goto out; if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) { err = -EINTR; goto out; } xprt_set_offline_locked(xprt, xps); xprt_release_write(xprt, NULL); out: xprt_put(xprt); xprt_switch_put(xps); return err; } /* rpc_clnt_manage_trunked_xprts -- offline trunked transports * @clnt rpc_clnt structure * * For each active transport found in the rpc_clnt structure call * the function rpc_xprt_offline() which will identify trunked transports * and will mark them offline. */ void rpc_clnt_manage_trunked_xprts(struct rpc_clnt *clnt) { rpc_clnt_iterate_for_each_xprt(clnt, rpc_xprt_offline, NULL); } EXPORT_SYMBOL_GPL(rpc_clnt_manage_trunked_xprts); struct connect_timeout_data { unsigned long connect_timeout; unsigned long reconnect_timeout; }; static int rpc_xprt_set_connect_timeout(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { struct connect_timeout_data *timeo = data; if (xprt->ops->set_connect_timeout) xprt->ops->set_connect_timeout(xprt, timeo->connect_timeout, timeo->reconnect_timeout); return 0; } void rpc_set_connect_timeout(struct rpc_clnt *clnt, unsigned long connect_timeout, unsigned long reconnect_timeout) { struct connect_timeout_data timeout = { .connect_timeout = connect_timeout, .reconnect_timeout = reconnect_timeout, }; rpc_clnt_iterate_for_each_xprt(clnt, rpc_xprt_set_connect_timeout, &timeout); } EXPORT_SYMBOL_GPL(rpc_set_connect_timeout); void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; xps = rpc_clnt_xprt_switch_get(clnt); xprt_set_online_locked(xprt, xps); xprt_switch_put(xps); } void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; if (rpc_clnt_xprt_switch_has_addr(clnt, (const struct sockaddr *)&xprt->addr)) { return rpc_clnt_xprt_set_online(clnt, xprt); } xps = rpc_clnt_xprt_switch_get(clnt); rpc_xprt_switch_add_xprt(xps, xprt); xprt_switch_put(xps); } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt); void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; rcu_read_lock(); xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); rpc_xprt_switch_remove_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch), xprt, 0); xps->xps_nunique_destaddr_xprts--; rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_remove_xprt); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap) { struct rpc_xprt_switch *xps; bool ret; rcu_read_lock(); xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ret = rpc_xprt_switch_has_addr(xps, sap); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_has_addr); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(struct rpc_clnt *clnt) { printk(KERN_INFO "clnt[%pISpc] RPC tasks[%d]\n", (struct sockaddr *)&clnt->cl_xprt->addr, atomic_read(&clnt->cl_task_count)); printk(KERN_INFO "-pid- flgs status -client- --rqstp- " "-timeout ---ops--\n"); } static void rpc_show_task(const struct rpc_clnt *clnt, const struct rpc_task *task) { const char *rpc_waitq = "none"; if (RPC_IS_QUEUED(task)) rpc_waitq = rpc_qname(task->tk_waitqueue); printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%ps q:%s\n", task->tk_pid, task->tk_flags, task->tk_status, clnt, task->tk_rqstp, rpc_task_timeout(task), task->tk_ops, clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), task->tk_action, rpc_waitq); } void rpc_show_tasks(struct net *net) { struct rpc_clnt *clnt; struct rpc_task *task; int header = 0; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); spin_lock(&sn->rpc_client_lock); list_for_each_entry(clnt, &sn->all_clients, cl_clients) { spin_lock(&clnt->cl_lock); list_for_each_entry(task, &clnt->cl_tasks, tk_task) { if (!header) { rpc_show_header(clnt); header++; } rpc_show_task(clnt, task); } spin_unlock(&clnt->cl_lock); } spin_unlock(&sn->rpc_client_lock); } #endif #if IS_ENABLED(CONFIG_SUNRPC_SWAP) static int rpc_clnt_swap_activate_callback(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *dummy) { return xprt_enable_swap(xprt); } int rpc_clnt_swap_activate(struct rpc_clnt *clnt) { while (clnt != clnt->cl_parent) clnt = clnt->cl_parent; if (atomic_inc_return(&clnt->cl_swapper) == 1) return rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_swap_activate_callback, NULL); return 0; } EXPORT_SYMBOL_GPL(rpc_clnt_swap_activate); static int rpc_clnt_swap_deactivate_callback(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *dummy) { xprt_disable_swap(xprt); return 0; } void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) { while (clnt != clnt->cl_parent) clnt = clnt->cl_parent; if (atomic_dec_if_positive(&clnt->cl_swapper) == 0) rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_swap_deactivate_callback, NULL); } EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate); #endif /* CONFIG_SUNRPC_SWAP */ |
| 18 18 1 7 2 1 1 2 1 9 1 2 2 2 1 1 2 1 1 48 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Management Component Transport Protocol (MCTP) - routing * implementation. * * This is currently based on a simple routing table, with no dst cache. The * number of routes should stay fairly small, so the lookup cost is small. * * Copyright (c) 2021 Code Construct * Copyright (c) 2021 Google */ #include <linux/idr.h> #include <linux/mctp.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/mctp.h> #include <net/mctpdevice.h> #include <net/netlink.h> #include <net/sock.h> static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid, enum mctp_neigh_source source, size_t lladdr_len, const void *lladdr) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh; int rc; mutex_lock(&net->mctp.neigh_lock); if (mctp_neigh_lookup(mdev, eid, NULL) == 0) { rc = -EEXIST; goto out; } if (lladdr_len > sizeof(neigh->ha)) { rc = -EINVAL; goto out; } neigh = kzalloc(sizeof(*neigh), GFP_KERNEL); if (!neigh) { rc = -ENOMEM; goto out; } INIT_LIST_HEAD(&neigh->list); neigh->dev = mdev; mctp_dev_hold(neigh->dev); neigh->eid = eid; neigh->source = source; memcpy(neigh->ha, lladdr, lladdr_len); list_add_rcu(&neigh->list, &net->mctp.neighbours); rc = 0; out: mutex_unlock(&net->mctp.neigh_lock); return rc; } static void __mctp_neigh_free(struct rcu_head *rcu) { struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu); mctp_dev_put(neigh->dev); kfree(neigh); } /* Removes all neighbour entries referring to a device */ void mctp_neigh_remove_dev(struct mctp_dev *mdev) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh, *tmp; mutex_lock(&net->mctp.neigh_lock); list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { if (neigh->dev == mdev) { list_del_rcu(&neigh->list); /* TODO: immediate RTM_DELNEIGH */ call_rcu(&neigh->rcu, __mctp_neigh_free); } } mutex_unlock(&net->mctp.neigh_lock); } static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid, enum mctp_neigh_source source) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh, *tmp; bool dropped = false; mutex_lock(&net->mctp.neigh_lock); list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { if (neigh->dev == mdev && neigh->eid == eid && neigh->source == source) { list_del_rcu(&neigh->list); /* TODO: immediate RTM_DELNEIGH */ call_rcu(&neigh->rcu, __mctp_neigh_free); dropped = true; } } mutex_unlock(&net->mctp.neigh_lock); return dropped ? 0 : -ENOENT; } static const struct nla_policy nd_mctp_policy[NDA_MAX + 1] = { [NDA_DST] = { .type = NLA_U8 }, [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, }; static int mctp_rtm_newneigh(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct net_device *dev; struct mctp_dev *mdev; struct ndmsg *ndm; struct nlattr *tb[NDA_MAX + 1]; int rc; mctp_eid_t eid; void *lladdr; int lladdr_len; rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, extack); if (rc < 0) { NL_SET_ERR_MSG(extack, "lladdr too large?"); return rc; } if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); return -EINVAL; } if (!tb[NDA_LLADDR]) { NL_SET_ERR_MSG(extack, "Neighbour lladdr must be specified"); return -EINVAL; } eid = nla_get_u8(tb[NDA_DST]); if (!mctp_address_unicast(eid)) { NL_SET_ERR_MSG(extack, "Invalid neighbour EID"); return -EINVAL; } lladdr = nla_data(tb[NDA_LLADDR]); lladdr_len = nla_len(tb[NDA_LLADDR]); ndm = nlmsg_data(nlh); dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; if (lladdr_len != dev->addr_len) { NL_SET_ERR_MSG(extack, "Wrong lladdr length"); return -EINVAL; } return mctp_neigh_add(mdev, eid, MCTP_NEIGH_STATIC, lladdr_len, lladdr); } static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NDA_MAX + 1]; struct net_device *dev; struct mctp_dev *mdev; struct ndmsg *ndm; int rc; mctp_eid_t eid; rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, extack); if (rc < 0) { NL_SET_ERR_MSG(extack, "incorrect format"); return rc; } if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); return -EINVAL; } eid = nla_get_u8(tb[NDA_DST]); ndm = nlmsg_data(nlh); dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC); } static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event, unsigned int flags, struct mctp_neigh *neigh) { struct net_device *dev = neigh->dev->dev; struct nlmsghdr *nlh; struct ndmsg *hdr; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ndm_family = AF_MCTP; hdr->ndm_ifindex = dev->ifindex; hdr->ndm_state = 0; // TODO other state bits? if (neigh->source == MCTP_NEIGH_STATIC) hdr->ndm_state |= NUD_PERMANENT; hdr->ndm_flags = 0; hdr->ndm_type = RTN_UNICAST; // TODO: is loopback RTN_LOCAL? if (nla_put_u8(skb, NDA_DST, neigh->eid)) goto cancel; if (nla_put(skb, NDA_LLADDR, dev->addr_len, neigh->ha)) goto cancel; nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mctp_rtm_getneigh(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int rc, idx, req_ifindex; struct mctp_neigh *neigh; struct ndmsg *ndmsg; struct { int idx; } *cbctx = (void *)cb->ctx; ndmsg = nlmsg_payload(cb->nlh, sizeof(*ndmsg)); if (!ndmsg) return -EINVAL; req_ifindex = ndmsg->ndm_ifindex; idx = 0; rcu_read_lock(); list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { if (idx < cbctx->idx) goto cont; rc = 0; if (req_ifindex == 0 || req_ifindex == neigh->dev->dev->ifindex) rc = mctp_fill_neigh(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, neigh); if (rc) break; cont: idx++; } rcu_read_unlock(); cbctx->idx = idx; return skb->len; } int mctp_neigh_lookup(struct mctp_dev *mdev, mctp_eid_t eid, void *ret_hwaddr) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh; int rc = -EHOSTUNREACH; // TODO: or ENOENT? rcu_read_lock(); list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { if (mdev == neigh->dev && eid == neigh->eid) { if (ret_hwaddr) memcpy(ret_hwaddr, neigh->ha, sizeof(neigh->ha)); rc = 0; break; } } rcu_read_unlock(); return rc; } /* namespace registration */ static int __net_init mctp_neigh_net_init(struct net *net) { struct netns_mctp *ns = &net->mctp; INIT_LIST_HEAD(&ns->neighbours); mutex_init(&ns->neigh_lock); return 0; } static void __net_exit mctp_neigh_net_exit(struct net *net) { struct netns_mctp *ns = &net->mctp; struct mctp_neigh *neigh; list_for_each_entry(neigh, &ns->neighbours, list) call_rcu(&neigh->rcu, __mctp_neigh_free); } /* net namespace implementation */ static struct pernet_operations mctp_net_ops = { .init = mctp_neigh_net_init, .exit = mctp_neigh_net_exit, }; static const struct rtnl_msg_handler mctp_neigh_rtnl_msg_handlers[] = { {THIS_MODULE, PF_MCTP, RTM_NEWNEIGH, mctp_rtm_newneigh, NULL, 0}, {THIS_MODULE, PF_MCTP, RTM_DELNEIGH, mctp_rtm_delneigh, NULL, 0}, {THIS_MODULE, PF_MCTP, RTM_GETNEIGH, NULL, mctp_rtm_getneigh, 0}, }; int __init mctp_neigh_init(void) { int err; err = register_pernet_subsys(&mctp_net_ops); if (err) return err; err = rtnl_register_many(mctp_neigh_rtnl_msg_handlers); if (err) unregister_pernet_subsys(&mctp_net_ops); return err; } void mctp_neigh_exit(void) { rtnl_unregister_many(mctp_neigh_rtnl_msg_handlers); unregister_pernet_subsys(&mctp_net_ops); } |
| 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * USB Attached SCSI * Note that this is not the same as the USB Mass Storage driver * * Copyright Hans de Goede <hdegoede@redhat.com> for Red Hat, Inc. 2013 - 2016 * Copyright Matthew Wilcox for Intel Corp, 2010 * Copyright Sarah Sharp for Intel Corp, 2010 */ #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb_usual.h> #include <linux/usb/hcd.h> #include <linux/usb/storage.h> #include <linux/usb/uas.h> #include <scsi/scsi.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_devinfo.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> #include <scsi/scsi_tcq.h> #include "uas-detect.h" #include "scsiglue.h" #define MAX_CMNDS 256 struct uas_dev_info { struct usb_interface *intf; struct usb_device *udev; struct usb_anchor cmd_urbs; struct usb_anchor sense_urbs; struct usb_anchor data_urbs; u64 flags; int qdepth, resetting; unsigned cmd_pipe, status_pipe, data_in_pipe, data_out_pipe; unsigned use_streams:1; unsigned shutdown:1; struct scsi_cmnd *cmnd[MAX_CMNDS]; spinlock_t lock; struct work_struct work; struct work_struct scan_work; /* for async scanning */ }; enum { SUBMIT_STATUS_URB = BIT(1), ALLOC_DATA_IN_URB = BIT(2), SUBMIT_DATA_IN_URB = BIT(3), ALLOC_DATA_OUT_URB = BIT(4), SUBMIT_DATA_OUT_URB = BIT(5), ALLOC_CMD_URB = BIT(6), SUBMIT_CMD_URB = BIT(7), COMMAND_INFLIGHT = BIT(8), DATA_IN_URB_INFLIGHT = BIT(9), DATA_OUT_URB_INFLIGHT = BIT(10), COMMAND_ABORTED = BIT(11), IS_IN_WORK_LIST = BIT(12), }; /* Overrides scsi_pointer */ struct uas_cmd_info { unsigned int state; unsigned int uas_tag; struct urb *cmd_urb; struct urb *data_in_urb; struct urb *data_out_urb; }; /* I hate forward declarations, but I actually have a loop */ static int uas_submit_urbs(struct scsi_cmnd *cmnd, struct uas_dev_info *devinfo); static void uas_do_work(struct work_struct *work); static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller); static void uas_free_streams(struct uas_dev_info *devinfo); static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix, int status); /* * This driver needs its own workqueue, as we need to control memory allocation. * * In the course of error handling and power management uas_wait_for_pending_cmnds() * needs to flush pending work items. In these contexts we cannot allocate memory * by doing block IO as we would deadlock. For the same reason we cannot wait * for anything allocating memory not heeding these constraints. * * So we have to control all work items that can be on the workqueue we flush. * Hence we cannot share a queue and need our own. */ static struct workqueue_struct *workqueue; static void uas_do_work(struct work_struct *work) { struct uas_dev_info *devinfo = container_of(work, struct uas_dev_info, work); struct uas_cmd_info *cmdinfo; struct scsi_cmnd *cmnd; unsigned long flags; int i, err; spin_lock_irqsave(&devinfo->lock, flags); if (devinfo->resetting) goto out; for (i = 0; i < devinfo->qdepth; i++) { if (!devinfo->cmnd[i]) continue; cmnd = devinfo->cmnd[i]; cmdinfo = scsi_cmd_priv(cmnd); if (!(cmdinfo->state & IS_IN_WORK_LIST)) continue; err = uas_submit_urbs(cmnd, cmnd->device->hostdata); if (!err) cmdinfo->state &= ~IS_IN_WORK_LIST; else queue_work(workqueue, &devinfo->work); } out: spin_unlock_irqrestore(&devinfo->lock, flags); } static void uas_scan_work(struct work_struct *work) { struct uas_dev_info *devinfo = container_of(work, struct uas_dev_info, scan_work); struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf); dev_dbg(&devinfo->intf->dev, "starting scan\n"); scsi_scan_host(shost); dev_dbg(&devinfo->intf->dev, "scan complete\n"); } static void uas_add_work(struct scsi_cmnd *cmnd) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = cmnd->device->hostdata; lockdep_assert_held(&devinfo->lock); cmdinfo->state |= IS_IN_WORK_LIST; queue_work(workqueue, &devinfo->work); } static void uas_zap_pending(struct uas_dev_info *devinfo, int result) { struct uas_cmd_info *cmdinfo; struct scsi_cmnd *cmnd; unsigned long flags; int i, err; spin_lock_irqsave(&devinfo->lock, flags); for (i = 0; i < devinfo->qdepth; i++) { if (!devinfo->cmnd[i]) continue; cmnd = devinfo->cmnd[i]; cmdinfo = scsi_cmd_priv(cmnd); uas_log_cmd_state(cmnd, __func__, 0); /* Sense urbs were killed, clear COMMAND_INFLIGHT manually */ cmdinfo->state &= ~COMMAND_INFLIGHT; cmnd->result = result << 16; err = uas_try_complete(cmnd, __func__); WARN_ON(err != 0); } spin_unlock_irqrestore(&devinfo->lock, flags); } static void uas_sense(struct urb *urb, struct scsi_cmnd *cmnd) { struct sense_iu *sense_iu = urb->transfer_buffer; struct scsi_device *sdev = cmnd->device; if (urb->actual_length > 16) { unsigned len = be16_to_cpup(&sense_iu->len); if (len + 16 != urb->actual_length) { int newlen = min(len + 16, urb->actual_length) - 16; if (newlen < 0) newlen = 0; sdev_printk(KERN_INFO, sdev, "%s: urb length %d " "disagrees with IU sense data length %d, " "using %d bytes of sense data\n", __func__, urb->actual_length, len, newlen); len = newlen; } memcpy(cmnd->sense_buffer, sense_iu->sense, len); } cmnd->result = sense_iu->status; } static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix, int status) { struct uas_cmd_info *ci = scsi_cmd_priv(cmnd); if (status == -ENODEV) /* too late */ return; scmd_printk(KERN_INFO, cmnd, "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ", prefix, status, ci->uas_tag, (ci->state & SUBMIT_STATUS_URB) ? " s-st" : "", (ci->state & ALLOC_DATA_IN_URB) ? " a-in" : "", (ci->state & SUBMIT_DATA_IN_URB) ? " s-in" : "", (ci->state & ALLOC_DATA_OUT_URB) ? " a-out" : "", (ci->state & SUBMIT_DATA_OUT_URB) ? " s-out" : "", (ci->state & ALLOC_CMD_URB) ? " a-cmd" : "", (ci->state & SUBMIT_CMD_URB) ? " s-cmd" : "", (ci->state & COMMAND_INFLIGHT) ? " CMD" : "", (ci->state & DATA_IN_URB_INFLIGHT) ? " IN" : "", (ci->state & DATA_OUT_URB_INFLIGHT) ? " OUT" : "", (ci->state & COMMAND_ABORTED) ? " abort" : "", (ci->state & IS_IN_WORK_LIST) ? " work" : ""); scsi_print_command(cmnd); } static void uas_free_unsubmitted_urbs(struct scsi_cmnd *cmnd) { struct uas_cmd_info *cmdinfo; if (!cmnd) return; cmdinfo = scsi_cmd_priv(cmnd); if (cmdinfo->state & SUBMIT_CMD_URB) usb_free_urb(cmdinfo->cmd_urb); /* data urbs may have never gotten their submit flag set */ if (!(cmdinfo->state & DATA_IN_URB_INFLIGHT)) usb_free_urb(cmdinfo->data_in_urb); if (!(cmdinfo->state & DATA_OUT_URB_INFLIGHT)) usb_free_urb(cmdinfo->data_out_urb); } static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; lockdep_assert_held(&devinfo->lock); if (cmdinfo->state & (COMMAND_INFLIGHT | DATA_IN_URB_INFLIGHT | DATA_OUT_URB_INFLIGHT | COMMAND_ABORTED)) return -EBUSY; devinfo->cmnd[cmdinfo->uas_tag - 1] = NULL; uas_free_unsubmitted_urbs(cmnd); scsi_done(cmnd); return 0; } static void uas_xfer_data(struct urb *urb, struct scsi_cmnd *cmnd, unsigned direction) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); int err; cmdinfo->state |= direction | SUBMIT_STATUS_URB; err = uas_submit_urbs(cmnd, cmnd->device->hostdata); if (err) { uas_add_work(cmnd); } } static bool uas_evaluate_response_iu(struct response_iu *riu, struct scsi_cmnd *cmnd) { u8 response_code = riu->response_code; switch (response_code) { case RC_INCORRECT_LUN: set_host_byte(cmnd, DID_BAD_TARGET); break; case RC_TMF_SUCCEEDED: set_host_byte(cmnd, DID_OK); break; case RC_TMF_NOT_SUPPORTED: set_host_byte(cmnd, DID_BAD_TARGET); break; default: uas_log_cmd_state(cmnd, "response iu", response_code); set_host_byte(cmnd, DID_ERROR); break; } return response_code == RC_TMF_SUCCEEDED; } static void uas_stat_cmplt(struct urb *urb) { struct iu *iu = urb->transfer_buffer; struct Scsi_Host *shost = urb->context; struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; struct urb *data_in_urb = NULL; struct urb *data_out_urb = NULL; struct scsi_cmnd *cmnd; struct uas_cmd_info *cmdinfo; unsigned long flags; unsigned int idx; int status = urb->status; bool success; if (status) { if (status != -ENOENT && status != -ECONNRESET && status != -ESHUTDOWN) dev_err(&urb->dev->dev, "stat urb: status %d\n", status); goto bail; } idx = be16_to_cpup(&iu->tag) - 1; spin_lock_irqsave(&devinfo->lock, flags); if (devinfo->resetting) goto out; if (idx >= MAX_CMNDS || !devinfo->cmnd[idx]) { dev_err(&urb->dev->dev, "stat urb: no pending cmd for uas-tag %d\n", idx + 1); goto out; } cmnd = devinfo->cmnd[idx]; cmdinfo = scsi_cmd_priv(cmnd); if (!(cmdinfo->state & COMMAND_INFLIGHT)) { uas_log_cmd_state(cmnd, "unexpected status cmplt", 0); goto out; } switch (iu->iu_id) { case IU_ID_STATUS: uas_sense(urb, cmnd); if (cmnd->result != 0) { /* cancel data transfers on error */ data_in_urb = usb_get_urb(cmdinfo->data_in_urb); data_out_urb = usb_get_urb(cmdinfo->data_out_urb); } cmdinfo->state &= ~COMMAND_INFLIGHT; uas_try_complete(cmnd, __func__); break; case IU_ID_READ_READY: if (!cmdinfo->data_in_urb || (cmdinfo->state & DATA_IN_URB_INFLIGHT)) { uas_log_cmd_state(cmnd, "unexpected read rdy", 0); break; } uas_xfer_data(urb, cmnd, SUBMIT_DATA_IN_URB); break; case IU_ID_WRITE_READY: if (!cmdinfo->data_out_urb || (cmdinfo->state & DATA_OUT_URB_INFLIGHT)) { uas_log_cmd_state(cmnd, "unexpected write rdy", 0); break; } uas_xfer_data(urb, cmnd, SUBMIT_DATA_OUT_URB); break; case IU_ID_RESPONSE: cmdinfo->state &= ~COMMAND_INFLIGHT; success = uas_evaluate_response_iu((struct response_iu *)iu, cmnd); if (!success) { /* Error, cancel data transfers */ data_in_urb = usb_get_urb(cmdinfo->data_in_urb); data_out_urb = usb_get_urb(cmdinfo->data_out_urb); } uas_try_complete(cmnd, __func__); break; default: uas_log_cmd_state(cmnd, "bogus IU", iu->iu_id); } spin_unlock_irqrestore(&devinfo->lock, flags); usb_free_urb(urb); /* Unlinking of data urbs must be done without holding the lock */ if (data_in_urb) { usb_unlink_urb(data_in_urb); usb_put_urb(data_in_urb); } if (data_out_urb) { usb_unlink_urb(data_out_urb); usb_put_urb(data_out_urb); } return; out: spin_unlock_irqrestore(&devinfo->lock, flags); bail: usb_free_urb(urb); } static void uas_data_cmplt(struct urb *urb) { struct scsi_cmnd *cmnd = urb->context; struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned long flags; int status = urb->status; spin_lock_irqsave(&devinfo->lock, flags); if (cmdinfo->data_in_urb == urb) { cmdinfo->state &= ~DATA_IN_URB_INFLIGHT; cmdinfo->data_in_urb = NULL; } else if (cmdinfo->data_out_urb == urb) { cmdinfo->state &= ~DATA_OUT_URB_INFLIGHT; cmdinfo->data_out_urb = NULL; } if (devinfo->resetting) goto out; /* Data urbs should not complete before the cmd urb is submitted */ if (cmdinfo->state & SUBMIT_CMD_URB) { uas_log_cmd_state(cmnd, "unexpected data cmplt", 0); goto out; } if (status) { if (status != -ENOENT && status != -ECONNRESET && status != -ESHUTDOWN) uas_log_cmd_state(cmnd, "data cmplt err", status); /* error: no data transfered */ scsi_set_resid(cmnd, sdb->length); set_host_byte(cmnd, DID_ERROR); } else { scsi_set_resid(cmnd, sdb->length - urb->actual_length); } uas_try_complete(cmnd, __func__); out: spin_unlock_irqrestore(&devinfo->lock, flags); usb_free_urb(urb); } static void uas_cmd_cmplt(struct urb *urb) { if (urb->status) dev_err(&urb->dev->dev, "cmd cmplt err %d\n", urb->status); usb_free_urb(urb); } static struct urb *uas_alloc_data_urb(struct uas_dev_info *devinfo, gfp_t gfp, struct scsi_cmnd *cmnd, enum dma_data_direction dir) { struct usb_device *udev = devinfo->udev; struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned int pipe = (dir == DMA_FROM_DEVICE) ? devinfo->data_in_pipe : devinfo->data_out_pipe; if (!urb) goto out; usb_fill_bulk_urb(urb, udev, pipe, NULL, sdb->length, uas_data_cmplt, cmnd); if (devinfo->use_streams) urb->stream_id = cmdinfo->uas_tag; urb->num_sgs = udev->bus->sg_tablesize ? sdb->table.nents : 0; urb->sg = sdb->table.sgl; out: return urb; } static struct urb *uas_alloc_sense_urb(struct uas_dev_info *devinfo, gfp_t gfp, struct scsi_cmnd *cmnd) { struct usb_device *udev = devinfo->udev; struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct sense_iu *iu; if (!urb) goto out; iu = kzalloc(sizeof(*iu), gfp); if (!iu) goto free; usb_fill_bulk_urb(urb, udev, devinfo->status_pipe, iu, sizeof(*iu), uas_stat_cmplt, cmnd->device->host); if (devinfo->use_streams) urb->stream_id = cmdinfo->uas_tag; urb->transfer_flags |= URB_FREE_BUFFER; out: return urb; free: usb_free_urb(urb); return NULL; } static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, struct scsi_cmnd *cmnd) { struct usb_device *udev = devinfo->udev; struct scsi_device *sdev = cmnd->device; struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct command_iu *iu; int len; if (!urb) goto out; len = cmnd->cmd_len - 16; if (len < 0) len = 0; len = ALIGN(len, 4); iu = kzalloc(sizeof(*iu) + len, gfp); if (!iu) goto free; iu->iu_id = IU_ID_COMMAND; iu->tag = cpu_to_be16(cmdinfo->uas_tag); iu->prio_attr = UAS_SIMPLE_TAG; iu->len = len; int_to_scsilun(sdev->lun, &iu->lun); memcpy(iu->cdb, cmnd->cmnd, cmnd->cmd_len); usb_fill_bulk_urb(urb, udev, devinfo->cmd_pipe, iu, sizeof(*iu) + len, uas_cmd_cmplt, NULL); urb->transfer_flags |= URB_FREE_BUFFER; out: return urb; free: usb_free_urb(urb); return NULL; } /* * Why should I request the Status IU before sending the Command IU? Spec * says to, but also says the device may receive them in any order. Seems * daft to me. */ static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) { struct uas_dev_info *devinfo = cmnd->device->hostdata; struct urb *urb; int err; urb = uas_alloc_sense_urb(devinfo, gfp, cmnd); if (!urb) return -ENOMEM; usb_anchor_urb(urb, &devinfo->sense_urbs); err = usb_submit_urb(urb, gfp); if (err) { usb_unanchor_urb(urb); uas_log_cmd_state(cmnd, "sense submit err", err); usb_free_urb(urb); } return err; } static int uas_submit_urbs(struct scsi_cmnd *cmnd, struct uas_dev_info *devinfo) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); int err; lockdep_assert_held(&devinfo->lock); if (cmdinfo->state & SUBMIT_STATUS_URB) { err = uas_submit_sense_urb(cmnd, GFP_ATOMIC); if (err) return err; cmdinfo->state &= ~SUBMIT_STATUS_URB; } if (cmdinfo->state & ALLOC_DATA_IN_URB) { cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_FROM_DEVICE); if (!cmdinfo->data_in_urb) return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_IN_URB; } if (cmdinfo->state & SUBMIT_DATA_IN_URB) { usb_anchor_urb(cmdinfo->data_in_urb, &devinfo->data_urbs); err = usb_submit_urb(cmdinfo->data_in_urb, GFP_ATOMIC); if (err) { usb_unanchor_urb(cmdinfo->data_in_urb); uas_log_cmd_state(cmnd, "data in submit err", err); return err; } cmdinfo->state &= ~SUBMIT_DATA_IN_URB; cmdinfo->state |= DATA_IN_URB_INFLIGHT; } if (cmdinfo->state & ALLOC_DATA_OUT_URB) { cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_TO_DEVICE); if (!cmdinfo->data_out_urb) return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_OUT_URB; } if (cmdinfo->state & SUBMIT_DATA_OUT_URB) { usb_anchor_urb(cmdinfo->data_out_urb, &devinfo->data_urbs); err = usb_submit_urb(cmdinfo->data_out_urb, GFP_ATOMIC); if (err) { usb_unanchor_urb(cmdinfo->data_out_urb); uas_log_cmd_state(cmnd, "data out submit err", err); return err; } cmdinfo->state &= ~SUBMIT_DATA_OUT_URB; cmdinfo->state |= DATA_OUT_URB_INFLIGHT; } if (cmdinfo->state & ALLOC_CMD_URB) { cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd); if (!cmdinfo->cmd_urb) return -ENOMEM; cmdinfo->state &= ~ALLOC_CMD_URB; } if (cmdinfo->state & SUBMIT_CMD_URB) { usb_anchor_urb(cmdinfo->cmd_urb, &devinfo->cmd_urbs); err = usb_submit_urb(cmdinfo->cmd_urb, GFP_ATOMIC); if (err) { usb_unanchor_urb(cmdinfo->cmd_urb); uas_log_cmd_state(cmnd, "cmd submit err", err); return err; } cmdinfo->cmd_urb = NULL; cmdinfo->state &= ~SUBMIT_CMD_URB; cmdinfo->state |= COMMAND_INFLIGHT; } return 0; } static int uas_queuecommand_lck(struct scsi_cmnd *cmnd) { struct scsi_device *sdev = cmnd->device; struct uas_dev_info *devinfo = sdev->hostdata; struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); unsigned long flags; int idx, err; /* Re-check scsi_block_requests now that we've the host-lock */ if (cmnd->device->host->host_self_blocked) return SCSI_MLQUEUE_DEVICE_BUSY; if ((devinfo->flags & US_FL_NO_ATA_1X) && (cmnd->cmnd[0] == ATA_12 || cmnd->cmnd[0] == ATA_16)) { memcpy(cmnd->sense_buffer, usb_stor_sense_invalidCDB, sizeof(usb_stor_sense_invalidCDB)); cmnd->result = SAM_STAT_CHECK_CONDITION; scsi_done(cmnd); return 0; } spin_lock_irqsave(&devinfo->lock, flags); if (devinfo->resetting) { set_host_byte(cmnd, DID_ERROR); scsi_done(cmnd); goto zombie; } /* Find a free uas-tag */ for (idx = 0; idx < devinfo->qdepth; idx++) { if (!devinfo->cmnd[idx]) break; } if (idx == devinfo->qdepth) { spin_unlock_irqrestore(&devinfo->lock, flags); return SCSI_MLQUEUE_DEVICE_BUSY; } memset(cmdinfo, 0, sizeof(*cmdinfo)); cmdinfo->uas_tag = idx + 1; /* uas-tag == usb-stream-id, so 1 based */ cmdinfo->state = SUBMIT_STATUS_URB | ALLOC_CMD_URB | SUBMIT_CMD_URB; switch (cmnd->sc_data_direction) { case DMA_FROM_DEVICE: cmdinfo->state |= ALLOC_DATA_IN_URB | SUBMIT_DATA_IN_URB; break; case DMA_BIDIRECTIONAL: cmdinfo->state |= ALLOC_DATA_IN_URB | SUBMIT_DATA_IN_URB; fallthrough; case DMA_TO_DEVICE: cmdinfo->state |= ALLOC_DATA_OUT_URB | SUBMIT_DATA_OUT_URB; break; case DMA_NONE: break; } if (!devinfo->use_streams) cmdinfo->state &= ~(SUBMIT_DATA_IN_URB | SUBMIT_DATA_OUT_URB); err = uas_submit_urbs(cmnd, devinfo); /* * in case of fatal errors the SCSI layer is peculiar * a command that has finished is a success for the purpose * of queueing, no matter how fatal the error */ if (err == -ENODEV) { if (cmdinfo->state & (COMMAND_INFLIGHT | DATA_IN_URB_INFLIGHT | DATA_OUT_URB_INFLIGHT)) goto out; set_host_byte(cmnd, DID_NO_CONNECT); scsi_done(cmnd); goto zombie; } if (err) { /* If we did nothing, give up now */ if (cmdinfo->state & SUBMIT_STATUS_URB) { spin_unlock_irqrestore(&devinfo->lock, flags); return SCSI_MLQUEUE_DEVICE_BUSY; } uas_add_work(cmnd); } out: devinfo->cmnd[idx] = cmnd; zombie: spin_unlock_irqrestore(&devinfo->lock, flags); return 0; } static DEF_SCSI_QCMD(uas_queuecommand) /* * For now we do not support actually sending an abort to the device, so * this eh always fails. Still we must define it to make sure that we've * dropped all references to the cmnd in question once this function exits. */ static int uas_eh_abort_handler(struct scsi_cmnd *cmnd) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; struct urb *data_in_urb = NULL; struct urb *data_out_urb = NULL; unsigned long flags; spin_lock_irqsave(&devinfo->lock, flags); uas_log_cmd_state(cmnd, __func__, 0); /* Ensure that try_complete does not call scsi_done */ cmdinfo->state |= COMMAND_ABORTED; /* Drop all refs to this cmnd, kill data urbs to break their ref */ devinfo->cmnd[cmdinfo->uas_tag - 1] = NULL; if (cmdinfo->state & DATA_IN_URB_INFLIGHT) data_in_urb = usb_get_urb(cmdinfo->data_in_urb); if (cmdinfo->state & DATA_OUT_URB_INFLIGHT) data_out_urb = usb_get_urb(cmdinfo->data_out_urb); uas_free_unsubmitted_urbs(cmnd); spin_unlock_irqrestore(&devinfo->lock, flags); if (data_in_urb) { usb_kill_urb(data_in_urb); usb_put_urb(data_in_urb); } if (data_out_urb) { usb_kill_urb(data_out_urb); usb_put_urb(data_out_urb); } return FAILED; } static int uas_eh_device_reset_handler(struct scsi_cmnd *cmnd) { struct scsi_device *sdev = cmnd->device; struct uas_dev_info *devinfo = sdev->hostdata; struct usb_device *udev = devinfo->udev; unsigned long flags; int err; err = usb_lock_device_for_reset(udev, devinfo->intf); if (err) { shost_printk(KERN_ERR, sdev->host, "%s FAILED to get lock err %d\n", __func__, err); return FAILED; } shost_printk(KERN_INFO, sdev->host, "%s start\n", __func__); spin_lock_irqsave(&devinfo->lock, flags); devinfo->resetting = 1; spin_unlock_irqrestore(&devinfo->lock, flags); usb_kill_anchored_urbs(&devinfo->cmd_urbs); usb_kill_anchored_urbs(&devinfo->sense_urbs); usb_kill_anchored_urbs(&devinfo->data_urbs); uas_zap_pending(devinfo, DID_RESET); err = usb_reset_device(udev); spin_lock_irqsave(&devinfo->lock, flags); devinfo->resetting = 0; spin_unlock_irqrestore(&devinfo->lock, flags); usb_unlock_device(udev); if (err) { shost_printk(KERN_INFO, sdev->host, "%s FAILED err %d\n", __func__, err); return FAILED; } shost_printk(KERN_INFO, sdev->host, "%s success\n", __func__); return SUCCESS; } static int uas_target_alloc(struct scsi_target *starget) { struct uas_dev_info *devinfo = (struct uas_dev_info *) dev_to_shost(starget->dev.parent)->hostdata; if (devinfo->flags & US_FL_NO_REPORT_LUNS) starget->no_report_luns = 1; return 0; } static int uas_sdev_init(struct scsi_device *sdev) { struct uas_dev_info *devinfo = (struct uas_dev_info *)sdev->host->hostdata; /* * Some USB storage devices reset if the IO advice hints grouping mode * page is queried. Hence skip that mode page. */ sdev->sdev_bflags |= BLIST_SKIP_IO_HINTS; sdev->hostdata = devinfo; return 0; } static int uas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct uas_dev_info *devinfo = sdev->hostdata; if (devinfo->flags & US_FL_MAX_SECTORS_64) lim->max_hw_sectors = 64; else if (devinfo->flags & US_FL_MAX_SECTORS_240) lim->max_hw_sectors = 240; if (devinfo->flags & US_FL_NO_REPORT_OPCODES) sdev->no_report_opcodes = 1; /* A few buggy USB-ATA bridges don't understand FUA */ if (devinfo->flags & US_FL_BROKEN_FUA) sdev->broken_fua = 1; /* UAS also needs to support FL_ALWAYS_SYNC */ if (devinfo->flags & US_FL_ALWAYS_SYNC) { sdev->skip_ms_page_3f = 1; sdev->skip_ms_page_8 = 1; sdev->wce_default_on = 1; } /* Some disks cannot handle READ_CAPACITY_16 */ if (devinfo->flags & US_FL_NO_READ_CAPACITY_16) sdev->no_read_capacity_16 = 1; /* Some disks cannot handle WRITE_SAME */ if (devinfo->flags & US_FL_NO_SAME) sdev->no_write_same = 1; /* * Some disks return the total number of blocks in response * to READ CAPACITY rather than the highest block number. * If this device makes that mistake, tell the sd driver. */ if (devinfo->flags & US_FL_FIX_CAPACITY) sdev->fix_capacity = 1; /* * in some cases we have to guess */ if (devinfo->flags & US_FL_CAPACITY_HEURISTICS) sdev->guess_capacity = 1; /* * Some devices report generic values until the media has been * accessed. Force a READ(10) prior to querying device * characteristics. */ sdev->read_before_ms = 1; /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device * is write-protected. Now that we tell the sd driver * to do a 192-byte transfer with this command the * majority of devices work fine, but a few still can't * handle it. The sd driver will simply assume those * devices are write-enabled. */ if (devinfo->flags & US_FL_NO_WP_DETECT) sdev->skip_ms_page_3f = 1; scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } static const struct scsi_host_template uas_host_template = { .module = THIS_MODULE, .name = "uas", .queuecommand = uas_queuecommand, .target_alloc = uas_target_alloc, .sdev_init = uas_sdev_init, .sdev_configure = uas_sdev_configure, .eh_abort_handler = uas_eh_abort_handler, .eh_device_reset_handler = uas_eh_device_reset_handler, .this_id = -1, .skip_settle_delay = 1, /* * The protocol has no requirements on alignment in the strict sense. * Controllers may or may not have alignment restrictions. * As this is not exported, we use an extremely conservative guess. */ .dma_alignment = 511, .dma_boundary = PAGE_SIZE - 1, .cmd_size = sizeof(struct uas_cmd_info), }; #define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \ vendorName, productName, useProtocol, useTransport, \ initFunction, flags) \ { USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax), \ .driver_info = (flags) } static const struct usb_device_id uas_usb_ids[] = { # include "unusual_uas.h" { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, USB_SC_SCSI, USB_PR_BULK) }, { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, USB_SC_SCSI, USB_PR_UAS) }, { } }; MODULE_DEVICE_TABLE(usb, uas_usb_ids); #undef UNUSUAL_DEV static int uas_switch_interface(struct usb_device *udev, struct usb_interface *intf) { struct usb_host_interface *alt; alt = uas_find_uas_alt_setting(intf); if (!alt) return -ENODEV; return usb_set_interface(udev, alt->desc.bInterfaceNumber, alt->desc.bAlternateSetting); } static int uas_configure_endpoints(struct uas_dev_info *devinfo) { struct usb_host_endpoint *eps[4] = { }; struct usb_device *udev = devinfo->udev; int r; r = uas_find_endpoints(devinfo->intf->cur_altsetting, eps); if (r) return r; devinfo->cmd_pipe = usb_sndbulkpipe(udev, usb_endpoint_num(&eps[0]->desc)); devinfo->status_pipe = usb_rcvbulkpipe(udev, usb_endpoint_num(&eps[1]->desc)); devinfo->data_in_pipe = usb_rcvbulkpipe(udev, usb_endpoint_num(&eps[2]->desc)); devinfo->data_out_pipe = usb_sndbulkpipe(udev, usb_endpoint_num(&eps[3]->desc)); if (udev->speed < USB_SPEED_SUPER) { devinfo->qdepth = 32; devinfo->use_streams = 0; } else { devinfo->qdepth = usb_alloc_streams(devinfo->intf, eps + 1, 3, MAX_CMNDS, GFP_NOIO); if (devinfo->qdepth < 0) return devinfo->qdepth; devinfo->use_streams = 1; } return 0; } static void uas_free_streams(struct uas_dev_info *devinfo) { struct usb_device *udev = devinfo->udev; struct usb_host_endpoint *eps[3]; eps[0] = usb_pipe_endpoint(udev, devinfo->status_pipe); eps[1] = usb_pipe_endpoint(udev, devinfo->data_in_pipe); eps[2] = usb_pipe_endpoint(udev, devinfo->data_out_pipe); usb_free_streams(devinfo->intf, eps, 3, GFP_NOIO); } static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) { int result = -ENOMEM; struct Scsi_Host *shost = NULL; struct uas_dev_info *devinfo; struct usb_device *udev = interface_to_usbdev(intf); u64 dev_flags; if (!uas_use_uas_driver(intf, id, &dev_flags)) return -ENODEV; if (uas_switch_interface(udev, intf)) return -ENODEV; shost = scsi_host_alloc(&uas_host_template, sizeof(struct uas_dev_info)); if (!shost) goto set_alt0; shost->max_cmd_len = 16 + 252; shost->max_id = 1; shost->max_lun = 256; shost->max_channel = 0; shost->sg_tablesize = udev->bus->sg_tablesize; devinfo = (struct uas_dev_info *)shost->hostdata; devinfo->intf = intf; devinfo->udev = udev; devinfo->resetting = 0; devinfo->shutdown = 0; devinfo->flags = dev_flags; init_usb_anchor(&devinfo->cmd_urbs); init_usb_anchor(&devinfo->sense_urbs); init_usb_anchor(&devinfo->data_urbs); spin_lock_init(&devinfo->lock); INIT_WORK(&devinfo->work, uas_do_work); INIT_WORK(&devinfo->scan_work, uas_scan_work); result = uas_configure_endpoints(devinfo); if (result) goto set_alt0; /* * 1 tag is reserved for untagged commands + * 1 tag to avoid off by one errors in some bridge firmwares */ shost->can_queue = devinfo->qdepth - 2; usb_set_intfdata(intf, shost); result = scsi_add_host(shost, &intf->dev); if (result) goto free_streams; /* Submit the delayed_work for SCSI-device scanning */ schedule_work(&devinfo->scan_work); return result; free_streams: uas_free_streams(devinfo); usb_set_intfdata(intf, NULL); set_alt0: usb_set_interface(udev, intf->altsetting[0].desc.bInterfaceNumber, 0); if (shost) scsi_host_put(shost); return result; } static int uas_cmnd_list_empty(struct uas_dev_info *devinfo) { unsigned long flags; int i, r = 1; spin_lock_irqsave(&devinfo->lock, flags); for (i = 0; i < devinfo->qdepth; i++) { if (devinfo->cmnd[i]) { r = 0; /* Not empty */ break; } } spin_unlock_irqrestore(&devinfo->lock, flags); return r; } /* * Wait for any pending cmnds to complete, on usb-2 sense_urbs may temporarily * get empty while there still is more work to do due to sense-urbs completing * with a READ/WRITE_READY iu code, so keep waiting until the list gets empty. */ static int uas_wait_for_pending_cmnds(struct uas_dev_info *devinfo) { unsigned long start_time; int r; start_time = jiffies; do { flush_work(&devinfo->work); r = usb_wait_anchor_empty_timeout(&devinfo->sense_urbs, 5000); if (r == 0) return -ETIME; r = usb_wait_anchor_empty_timeout(&devinfo->data_urbs, 500); if (r == 0) return -ETIME; if (time_after(jiffies, start_time + 5 * HZ)) return -ETIME; } while (!uas_cmnd_list_empty(devinfo)); return 0; } static int uas_pre_reset(struct usb_interface *intf) { struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; unsigned long flags; if (devinfo->shutdown) return 0; /* Block new requests */ spin_lock_irqsave(shost->host_lock, flags); scsi_block_requests(shost); spin_unlock_irqrestore(shost->host_lock, flags); if (uas_wait_for_pending_cmnds(devinfo) != 0) { shost_printk(KERN_ERR, shost, "%s: timed out\n", __func__); scsi_unblock_requests(shost); return 1; } uas_free_streams(devinfo); return 0; } static int uas_post_reset(struct usb_interface *intf) { struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; unsigned long flags; int err; if (devinfo->shutdown) return 0; err = uas_configure_endpoints(devinfo); if (err && err != -ENODEV) shost_printk(KERN_ERR, shost, "%s: alloc streams error %d after reset", __func__, err); /* we must unblock the host in every case lest we deadlock */ spin_lock_irqsave(shost->host_lock, flags); scsi_report_bus_reset(shost, 0); spin_unlock_irqrestore(shost->host_lock, flags); scsi_unblock_requests(shost); return err ? 1 : 0; } static int uas_suspend(struct usb_interface *intf, pm_message_t message) { struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; if (uas_wait_for_pending_cmnds(devinfo) != 0) { shost_printk(KERN_ERR, shost, "%s: timed out\n", __func__); return -ETIME; } return 0; } static int uas_resume(struct usb_interface *intf) { return 0; } static int uas_reset_resume(struct usb_interface *intf) { struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; unsigned long flags; int err; err = uas_configure_endpoints(devinfo); if (err) { shost_printk(KERN_ERR, shost, "%s: alloc streams error %d after reset", __func__, err); return -EIO; } spin_lock_irqsave(shost->host_lock, flags); scsi_report_bus_reset(shost, 0); spin_unlock_irqrestore(shost->host_lock, flags); return 0; } static void uas_disconnect(struct usb_interface *intf) { struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; unsigned long flags; spin_lock_irqsave(&devinfo->lock, flags); devinfo->resetting = 1; spin_unlock_irqrestore(&devinfo->lock, flags); cancel_work_sync(&devinfo->work); usb_kill_anchored_urbs(&devinfo->cmd_urbs); usb_kill_anchored_urbs(&devinfo->sense_urbs); usb_kill_anchored_urbs(&devinfo->data_urbs); uas_zap_pending(devinfo, DID_NO_CONNECT); /* * Prevent SCSI scanning (if it hasn't started yet) * or wait for the SCSI-scanning routine to stop. */ cancel_work_sync(&devinfo->scan_work); scsi_remove_host(shost); uas_free_streams(devinfo); scsi_host_put(shost); } /* * Put the device back in usb-storage mode on shutdown, as some BIOS-es * hang on reboot when the device is still in uas mode. Note the reset is * necessary as some devices won't revert to usb-storage mode without it. */ static void uas_shutdown(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); struct Scsi_Host *shost = usb_get_intfdata(intf); struct uas_dev_info *devinfo = (struct uas_dev_info *)shost->hostdata; if (system_state != SYSTEM_RESTART) return; devinfo->shutdown = 1; uas_free_streams(devinfo); usb_set_interface(udev, intf->altsetting[0].desc.bInterfaceNumber, 0); usb_reset_device(udev); } static struct usb_driver uas_driver = { .name = "uas", .probe = uas_probe, .disconnect = uas_disconnect, .pre_reset = uas_pre_reset, .post_reset = uas_post_reset, .suspend = uas_suspend, .resume = uas_resume, .reset_resume = uas_reset_resume, .shutdown = uas_shutdown, .id_table = uas_usb_ids, }; static int __init uas_init(void) { int rv; workqueue = alloc_workqueue("uas", WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!workqueue) return -ENOMEM; rv = usb_register(&uas_driver); if (rv) { destroy_workqueue(workqueue); return -ENOMEM; } return 0; } static void __exit uas_exit(void) { usb_deregister(&uas_driver); destroy_workqueue(workqueue); } module_init(uas_init); module_exit(uas_exit); MODULE_DESCRIPTION("USB Attached SCSI driver"); MODULE_LICENSE("GPL"); MODULE_IMPORT_NS("USB_STORAGE"); MODULE_AUTHOR( "Hans de Goede <hdegoede@redhat.com>, Matthew Wilcox and Sarah Sharp"); |
| 91 16 124 1 74 115 4 115 79 75 75 4 4 75 75 75 207 33 115 4 148 4 147 4 115 33 4 4 148 143 147 145 147 12 12 1 1 134 50 1 40 48 67 97 96 94 96 94 2 96 97 80 122 81 81 1 1 5 33 21 17 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * fs/f2fs/segment.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #include <linux/blkdev.h> #include <linux/backing-dev.h> /* constant macro */ #define NULL_SEGNO ((unsigned int)(~0)) #define NULL_SECNO ((unsigned int)(~0)) #define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */ #define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */ #define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */ #define F2FS_MIN_META_SEGMENTS 8 /* SB + 2 (CP + SIT + NAT) + SSA */ #define INVALID_MTIME ULLONG_MAX /* no valid blocks in a segment/section */ /* L: Logical segment # in volume, R: Relative segment # in main area */ #define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno) #define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno) #define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA) #define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE && (t) <= CURSEG_COLD_NODE) #define SE_PAGETYPE(se) ((IS_NODESEG((se)->type) ? NODE : DATA)) static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, unsigned short seg_type) { f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG); } #define MAIN_BLKADDR(sbi) \ (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \ le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr)) #define SEG0_BLKADDR(sbi) \ (SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr)) #define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments) #define MAIN_SECS(sbi) ((sbi)->total_sections) #define TOTAL_SEGS(sbi) \ (SM_I(sbi) ? SM_I(sbi)->segment_count : \ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count)) #define TOTAL_BLKS(sbi) (SEGS_TO_BLKS(sbi, TOTAL_SEGS(sbi))) #define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi)) #define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \ (sbi)->log_blocks_per_seg)) #define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \ (SEGS_TO_BLKS(sbi, GET_R2L_SEGNO(FREE_I(sbi), segno)))) #define NEXT_FREE_BLKADDR(sbi, curseg) \ (START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff) #define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi)) #define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \ (BLKS_TO_SEGS(sbi, GET_SEGOFF_FROM_SEG0(sbi, blk_addr))) #define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (BLKS_PER_SEG(sbi) - 1)) #define GET_SEGNO(sbi, blk_addr) \ ((!__is_valid_data_blkaddr(blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #ifdef CONFIG_BLK_DEV_ZONED #define CAP_BLKS_PER_SEC(sbi) \ (BLKS_PER_SEC(sbi) - (sbi)->unusable_blocks_per_sec) #define CAP_SEGS_PER_SEC(sbi) \ (SEGS_PER_SEC(sbi) - \ BLKS_TO_SEGS(sbi, (sbi)->unusable_blocks_per_sec)) #else #define CAP_BLKS_PER_SEC(sbi) BLKS_PER_SEC(sbi) #define CAP_SEGS_PER_SEC(sbi) SEGS_PER_SEC(sbi) #endif #define GET_START_SEG_FROM_SEC(sbi, segno) \ (rounddown(segno, SEGS_PER_SEC(sbi))) #define GET_SEC_FROM_SEG(sbi, segno) \ (((segno) == -1) ? -1 : (segno) / SEGS_PER_SEC(sbi)) #define GET_SEG_FROM_SEC(sbi, secno) \ ((secno) * SEGS_PER_SEC(sbi)) #define GET_ZONE_FROM_SEC(sbi, secno) \ (((secno) == -1) ? -1 : (secno) / (sbi)->secs_per_zone) #define GET_ZONE_FROM_SEG(sbi, segno) \ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno)) #define SUMS_PER_BLOCK (F2FS_BLKSIZE / F2FS_SUM_BLKSIZE) #define GET_SUM_BLOCK(sbi, segno) \ (SM_I(sbi)->ssa_blkaddr + (segno / SUMS_PER_BLOCK)) #define GET_SUM_BLKOFF(segno) (segno % SUMS_PER_BLOCK) #define SUM_BLK_PAGE_ADDR(folio, segno) \ (folio_address(folio) + GET_SUM_BLKOFF(segno) * F2FS_SUM_BLKSIZE) #define GET_SUM_TYPE(footer) ((footer)->entry_type) #define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type)) #define SIT_ENTRY_OFFSET(sit_i, segno) \ ((segno) % (sit_i)->sents_per_block) #define SIT_BLOCK_OFFSET(segno) \ ((segno) / SIT_ENTRY_PER_BLOCK) #define START_SEGNO(segno) \ (SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK) #define SIT_BLK_CNT(sbi) \ DIV_ROUND_UP(MAIN_SEGS(sbi), SIT_ENTRY_PER_BLOCK) #define f2fs_bitmap_size(nr) \ (BITS_TO_LONGS(nr) * sizeof(unsigned long)) #define SECTOR_FROM_BLOCK(blk_addr) \ (((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK) #define SECTOR_TO_BLOCK(sectors) \ ((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK) /* * In the victim_sel_policy->alloc_mode, there are three block allocation modes. * LFS writes data sequentially with cleaning operations. * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations. * AT_SSR (Age Threshold based Slack Space Recycle) merges fragments into * fragmented segment which has similar aging degree. */ enum { LFS = 0, SSR, AT_SSR, }; /* * In the victim_sel_policy->gc_mode, there are three gc, aka cleaning, modes. * GC_CB is based on cost-benefit algorithm. * GC_GREEDY is based on greedy algorithm. * GC_AT is based on age-threshold algorithm. */ enum { GC_CB = 0, GC_GREEDY, GC_AT, ALLOC_NEXT, FLUSH_DEVICE, MAX_GC_POLICY, }; /* * BG_GC means the background cleaning job. * FG_GC means the on-demand cleaning job. */ enum { BG_GC = 0, FG_GC, }; /* for a function parameter to select a victim segment */ struct victim_sel_policy { int alloc_mode; /* LFS or SSR */ int gc_mode; /* GC_CB or GC_GREEDY */ unsigned long *dirty_bitmap; /* dirty segment/section bitmap */ unsigned int max_search; /* * maximum # of segments/sections * to search */ unsigned int offset; /* last scanned bitmap offset */ unsigned int ofs_unit; /* bitmap search unit */ unsigned int min_cost; /* minimum cost */ unsigned long long oldest_age; /* oldest age of segments having the same min cost */ unsigned int min_segno; /* segment # having min. cost */ unsigned long long age; /* mtime of GCed section*/ unsigned long long age_threshold;/* age threshold */ bool one_time_gc; /* one time GC */ }; struct seg_entry { unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */ unsigned int valid_blocks:10; /* # of valid blocks */ unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */ unsigned int padding:6; /* padding */ unsigned char *cur_valid_map; /* validity bitmap of blocks */ #ifdef CONFIG_F2FS_CHECK_FS unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */ #endif /* * # of valid blocks and the validity bitmap stored in the last * checkpoint pack. This information is used by the SSR mode. */ unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */ unsigned char *discard_map; unsigned long long mtime; /* modification time of the segment */ }; struct sec_entry { unsigned int valid_blocks; /* # of valid blocks in a section */ unsigned int ckpt_valid_blocks; /* # of valid blocks last cp in a section */ }; #define MAX_SKIP_GC_COUNT 16 struct revoke_entry { struct list_head list; block_t old_addr; /* for revoking when fail to commit */ pgoff_t index; }; struct sit_info { block_t sit_base_addr; /* start block address of SIT area */ block_t sit_blocks; /* # of blocks used by SIT area */ block_t written_valid_blocks; /* # of valid blocks in main area */ char *bitmap; /* all bitmaps pointer */ char *sit_bitmap; /* SIT bitmap pointer */ #ifdef CONFIG_F2FS_CHECK_FS char *sit_bitmap_mir; /* SIT bitmap mirror */ /* bitmap of segments to be ignored by GC in case of errors */ unsigned long *invalid_segmap; #endif unsigned int bitmap_size; /* SIT bitmap size */ unsigned long *tmp_map; /* bitmap for temporal use */ unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */ unsigned int dirty_sentries; /* # of dirty sentries */ unsigned int sents_per_block; /* # of SIT entries per block */ struct rw_semaphore sentry_lock; /* to protect SIT cache */ struct seg_entry *sentries; /* SIT segment-level cache */ struct sec_entry *sec_entries; /* SIT section-level cache */ /* for cost-benefit algorithm in cleaning procedure */ unsigned long long elapsed_time; /* elapsed time after mount */ unsigned long long mounted_time; /* mount time */ unsigned long long min_mtime; /* min. modification time */ unsigned long long max_mtime; /* max. modification time */ unsigned long long dirty_min_mtime; /* rerange candidates in GC_AT */ unsigned long long dirty_max_mtime; /* rerange candidates in GC_AT */ unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */ }; struct free_segmap_info { unsigned int start_segno; /* start segment number logically */ unsigned int free_segments; /* # of free segments */ unsigned int free_sections; /* # of free sections */ spinlock_t segmap_lock; /* free segmap lock */ unsigned long *free_segmap; /* free segment bitmap */ unsigned long *free_secmap; /* free section bitmap */ }; /* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */ enum dirty_type { DIRTY_HOT_DATA, /* dirty segments assigned as hot data logs */ DIRTY_WARM_DATA, /* dirty segments assigned as warm data logs */ DIRTY_COLD_DATA, /* dirty segments assigned as cold data logs */ DIRTY_HOT_NODE, /* dirty segments assigned as hot node logs */ DIRTY_WARM_NODE, /* dirty segments assigned as warm node logs */ DIRTY_COLD_NODE, /* dirty segments assigned as cold node logs */ DIRTY, /* to count # of dirty segments */ PRE, /* to count # of entirely obsolete segments */ NR_DIRTY_TYPE }; struct dirty_seglist_info { unsigned long *dirty_segmap[NR_DIRTY_TYPE]; unsigned long *dirty_secmap; struct mutex seglist_lock; /* lock for segment bitmaps */ int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */ unsigned long *victim_secmap; /* background GC victims */ unsigned long *pinned_secmap; /* pinned victims from foreground GC */ unsigned int pinned_secmap_cnt; /* count of victims which has pinned data */ bool enable_pin_section; /* enable pinning section */ }; /* for active log information */ struct curseg_info { struct mutex curseg_mutex; /* lock for consistency */ struct f2fs_summary_block *sum_blk; /* cached summary block */ struct rw_semaphore journal_rwsem; /* protect journal area */ struct f2fs_journal *journal; /* cached journal info */ unsigned char alloc_type; /* current allocation type */ unsigned short seg_type; /* segment type like CURSEG_XXX_TYPE */ unsigned int segno; /* current segment number */ unsigned short next_blkoff; /* next block offset to write */ unsigned int zone; /* current zone number */ unsigned int next_segno; /* preallocated segment */ int fragment_remained_chunk; /* remained block size in a chunk for block fragmentation mode */ bool inited; /* indicate inmem log is inited */ }; struct sit_entry_set { struct list_head set_list; /* link with all sit sets */ unsigned int start_segno; /* start segno of sits in set */ unsigned int entry_cnt; /* the # of sit entries in set */ }; /* * inline functions */ static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type) { return (struct curseg_info *)(SM_I(sbi)->curseg_array + type); } static inline bool is_curseg(struct f2fs_sb_info *sbi, unsigned int segno) { int i; for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { if (segno == CURSEG_I(sbi, i)->segno) return true; } return false; } static inline bool is_cursec(struct f2fs_sb_info *sbi, unsigned int secno) { int i; for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { if (secno == GET_SEC_FROM_SEG(sbi, CURSEG_I(sbi, i)->segno)) return true; } return false; } static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi, unsigned int segno) { struct sit_info *sit_i = SIT_I(sbi); return &sit_i->sentries[segno]; } static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi, unsigned int segno) { struct sit_info *sit_i = SIT_I(sbi); return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)]; } static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno, bool use_section) { /* * In order to get # of valid blocks in a section instantly from many * segments, f2fs manages two counting structures separately. */ if (use_section && __is_large_section(sbi)) return get_sec_entry(sbi, segno)->valid_blocks; else return get_seg_entry(sbi, segno)->valid_blocks; } static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno, bool use_section) { if (use_section && __is_large_section(sbi)) return get_sec_entry(sbi, segno)->ckpt_valid_blocks; else return get_seg_entry(sbi, segno)->ckpt_valid_blocks; } static inline void set_ckpt_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno) { unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int blocks = 0; int i; for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) { struct seg_entry *se = get_seg_entry(sbi, start_segno); blocks += se->ckpt_valid_blocks; } get_sec_entry(sbi, segno)->ckpt_valid_blocks = blocks; } #ifdef CONFIG_F2FS_CHECK_FS static inline void sanity_check_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno) { unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int blocks = 0; int i; for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) { struct seg_entry *se = get_seg_entry(sbi, start_segno); blocks += se->ckpt_valid_blocks; } if (blocks != get_sec_entry(sbi, segno)->ckpt_valid_blocks) { f2fs_err(sbi, "Inconsistent ckpt valid blocks: " "seg entry(%d) vs sec entry(%d) at secno %d", blocks, get_sec_entry(sbi, segno)->ckpt_valid_blocks, secno); f2fs_bug_on(sbi, 1); } } #else static inline void sanity_check_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno) { } #endif static inline void seg_info_from_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { se->valid_blocks = GET_SIT_VBLOCKS(rs); se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs); memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); #ifdef CONFIG_F2FS_CHECK_FS memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE); #endif se->type = GET_SIT_TYPE(rs); se->mtime = le64_to_cpu(rs->mtime); } static inline void __seg_info_to_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) | se->valid_blocks; rs->vblocks = cpu_to_le16(raw_vblocks); memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); rs->mtime = cpu_to_le64(se->mtime); } static inline void seg_info_to_sit_folio(struct f2fs_sb_info *sbi, struct folio *folio, unsigned int start) { struct f2fs_sit_block *raw_sit; struct seg_entry *se; struct f2fs_sit_entry *rs; unsigned int end = min(start + SIT_ENTRY_PER_BLOCK, (unsigned long)MAIN_SEGS(sbi)); int i; raw_sit = folio_address(folio); memset(raw_sit, 0, PAGE_SIZE); for (i = 0; i < end - start; i++) { rs = &raw_sit->entries[i]; se = get_seg_entry(sbi, start + i); __seg_info_to_raw_sit(se, rs); } } static inline void seg_info_to_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { __seg_info_to_raw_sit(se, rs); memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); se->ckpt_valid_blocks = se->valid_blocks; } static inline unsigned int find_next_inuse(struct free_segmap_info *free_i, unsigned int max, unsigned int segno) { unsigned int ret; spin_lock(&free_i->segmap_lock); ret = find_next_bit(free_i->free_segmap, max, segno); spin_unlock(&free_i->segmap_lock); return ret; } static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int next; spin_lock(&free_i->segmap_lock); clear_bit(segno, free_i->free_segmap); free_i->free_segments++; next = find_next_bit(free_i->free_segmap, start_segno + SEGS_PER_SEC(sbi), start_segno); if (next >= start_segno + f2fs_usable_segs_in_sec(sbi)) { clear_bit(secno, free_i->free_secmap); free_i->free_sections++; } spin_unlock(&free_i->segmap_lock); } static inline void __set_inuse(struct f2fs_sb_info *sbi, unsigned int segno) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); set_bit(segno, free_i->free_segmap); free_i->free_segments--; if (!test_and_set_bit(secno, free_i->free_secmap)) free_i->free_sections--; } static inline void __set_test_and_free(struct f2fs_sb_info *sbi, unsigned int segno, bool inmem) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int next; bool ret; spin_lock(&free_i->segmap_lock); ret = test_and_clear_bit(segno, free_i->free_segmap); if (!ret) goto unlock_out; free_i->free_segments++; if (!inmem && is_cursec(sbi, secno)) goto unlock_out; /* check large section */ next = find_next_bit(free_i->free_segmap, start_segno + SEGS_PER_SEC(sbi), start_segno); if (next < start_segno + f2fs_usable_segs_in_sec(sbi)) goto unlock_out; ret = test_and_clear_bit(secno, free_i->free_secmap); if (!ret) goto unlock_out; free_i->free_sections++; if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[BG_GC]) == secno) sbi->next_victim_seg[BG_GC] = NULL_SEGNO; if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[FG_GC]) == secno) sbi->next_victim_seg[FG_GC] = NULL_SEGNO; unlock_out: spin_unlock(&free_i->segmap_lock); } static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi, unsigned int segno) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); spin_lock(&free_i->segmap_lock); if (!test_and_set_bit(segno, free_i->free_segmap)) { free_i->free_segments--; if (!test_and_set_bit(secno, free_i->free_secmap)) free_i->free_sections--; } spin_unlock(&free_i->segmap_lock); } static inline void get_sit_bitmap(struct f2fs_sb_info *sbi, void *dst_addr) { struct sit_info *sit_i = SIT_I(sbi); #ifdef CONFIG_F2FS_CHECK_FS if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir, sit_i->bitmap_size)) f2fs_bug_on(sbi, 1); #endif memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size); } static inline block_t written_block_count(struct f2fs_sb_info *sbi) { return SIT_I(sbi)->written_valid_blocks; } static inline unsigned int free_segments(struct f2fs_sb_info *sbi) { return FREE_I(sbi)->free_segments; } static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi) { return SM_I(sbi)->reserved_segments; } static inline unsigned int free_sections(struct f2fs_sb_info *sbi) { return FREE_I(sbi)->free_sections; } static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi) { return DIRTY_I(sbi)->nr_dirty[PRE]; } static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi) { return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] + DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE]; } static inline int overprovision_segments(struct f2fs_sb_info *sbi) { return SM_I(sbi)->ovp_segments; } static inline int reserved_sections(struct f2fs_sb_info *sbi) { return GET_SEC_FROM_SEG(sbi, reserved_segments(sbi)); } static inline unsigned int get_left_section_blocks(struct f2fs_sb_info *sbi, enum log_type type, unsigned int segno) { if (f2fs_lfs_mode(sbi)) { unsigned int used_blocks = __is_large_section(sbi) ? SEGS_TO_BLKS(sbi, (segno - GET_START_SEG_FROM_SEC(sbi, segno))) : 0; return CAP_BLKS_PER_SEC(sbi) - used_blocks - CURSEG_I(sbi, type)->next_blkoff; } return CAP_BLKS_PER_SEC(sbi) - get_ckpt_valid_blocks(sbi, segno, true); } static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int data_blocks, unsigned int dent_blocks) { unsigned int segno, left_blocks, blocks; int i; /* check current data/node sections in the worst case. */ for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) { segno = CURSEG_I(sbi, i)->segno; if (unlikely(segno == NULL_SEGNO)) return false; left_blocks = get_left_section_blocks(sbi, i, segno); blocks = i <= CURSEG_COLD_DATA ? data_blocks : node_blocks; if (blocks > left_blocks) return false; } /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; if (unlikely(segno == NULL_SEGNO)) return false; left_blocks = get_left_section_blocks(sbi, CURSEG_HOT_DATA, segno); if (dent_blocks > left_blocks) return false; return true; } /* * calculate needed sections for dirty node/dentry and call * has_curseg_enough_space, please note that, it needs to account * dirty data as well in lfs mode when checkpoint is disabled. */ static inline void __get_secs_required(struct f2fs_sb_info *sbi, unsigned int *lower_p, unsigned int *upper_p, bool *curseg_p) { unsigned int total_node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) + get_pages(sbi, F2FS_DIRTY_DENTS) + get_pages(sbi, F2FS_DIRTY_IMETA); unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS); unsigned int total_data_blocks = 0; unsigned int node_secs = total_node_blocks / CAP_BLKS_PER_SEC(sbi); unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi); unsigned int data_secs = 0; unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi); unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi); unsigned int data_blocks = 0; if (f2fs_lfs_mode(sbi)) { total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA); data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi); data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi); } if (lower_p) *lower_p = node_secs + dent_secs + data_secs; if (upper_p) *upper_p = node_secs + dent_secs + data_secs + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) + (data_blocks ? 1 : 0); if (curseg_p) *curseg_p = has_curseg_enough_space(sbi, node_blocks, data_blocks, dent_blocks); } static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed, int needed) { unsigned int free_secs, lower_secs, upper_secs; bool curseg_space; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return false; __get_secs_required(sbi, &lower_secs, &upper_secs, &curseg_space); free_secs = free_sections(sbi) + freed; lower_secs += needed + reserved_sections(sbi); upper_secs += needed + reserved_sections(sbi); if (free_secs > upper_secs) return false; if (free_secs <= lower_secs) return true; return !curseg_space; } static inline bool has_enough_free_secs(struct f2fs_sb_info *sbi, int freed, int needed) { return !has_not_enough_free_secs(sbi, freed, needed); } static inline bool has_enough_free_blks(struct f2fs_sb_info *sbi) { unsigned int total_free_blocks = 0; unsigned int avail_user_block_count; spin_lock(&sbi->stat_lock); avail_user_block_count = get_available_block_count(sbi, NULL, true); total_free_blocks = avail_user_block_count - (unsigned int)valid_user_blocks(sbi); spin_unlock(&sbi->stat_lock); return total_free_blocks > 0; } static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) { if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; if (likely(has_enough_free_secs(sbi, 0, 0))) return true; if (!f2fs_lfs_mode(sbi) && likely(has_enough_free_blks(sbi))) return true; return false; } static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) { return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; } static inline int utilization(struct f2fs_sb_info *sbi) { return div_u64((u64)valid_user_blocks(sbi) * 100, sbi->user_block_count); } /* * Sometimes f2fs may be better to drop out-of-place update policy. * And, users can control the policy through sysfs entries. * There are five policies with triggering conditions as follows. * F2FS_IPU_FORCE - all the time, * F2FS_IPU_SSR - if SSR mode is activated, * F2FS_IPU_UTIL - if FS utilization is over threashold, * F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over * threashold, * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash * storages. IPU will be triggered only if the # of dirty * pages over min_fsync_blocks. (=default option) * F2FS_IPU_ASYNC - do IPU given by asynchronous write requests. * F2FS_IPU_NOCACHE - disable IPU bio cache. * F2FS_IPU_HONOR_OPU_WRITE - use OPU write prior to IPU write if inode has * FI_OPU_WRITE flag. * F2FS_IPU_DISABLE - disable IPU. (=default option in LFS mode) */ #define DEF_MIN_IPU_UTIL 70 #define DEF_MIN_FSYNC_BLOCKS 8 #define DEF_MIN_HOT_BLOCKS 16 #define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */ #define F2FS_IPU_DISABLE 0 /* Modification on enum should be synchronized with ipu_mode_names array */ enum { F2FS_IPU_FORCE, F2FS_IPU_SSR, F2FS_IPU_UTIL, F2FS_IPU_SSR_UTIL, F2FS_IPU_FSYNC, F2FS_IPU_ASYNC, F2FS_IPU_NOCACHE, F2FS_IPU_HONOR_OPU_WRITE, F2FS_IPU_MAX, }; static inline bool IS_F2FS_IPU_DISABLE(struct f2fs_sb_info *sbi) { return SM_I(sbi)->ipu_policy == F2FS_IPU_DISABLE; } #define F2FS_IPU_POLICY(name) \ static inline bool IS_##name(struct f2fs_sb_info *sbi) \ { \ return SM_I(sbi)->ipu_policy & BIT(name); \ } F2FS_IPU_POLICY(F2FS_IPU_FORCE); F2FS_IPU_POLICY(F2FS_IPU_SSR); F2FS_IPU_POLICY(F2FS_IPU_UTIL); F2FS_IPU_POLICY(F2FS_IPU_SSR_UTIL); F2FS_IPU_POLICY(F2FS_IPU_FSYNC); F2FS_IPU_POLICY(F2FS_IPU_ASYNC); F2FS_IPU_POLICY(F2FS_IPU_NOCACHE); F2FS_IPU_POLICY(F2FS_IPU_HONOR_OPU_WRITE); static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); return curseg->segno; } static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); return curseg->alloc_type; } static inline bool valid_main_segno(struct f2fs_sb_info *sbi, unsigned int segno) { return segno <= (MAIN_SEGS(sbi) - 1); } static inline void verify_fio_blkaddr(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; if (__is_valid_data_blkaddr(fio->old_blkaddr)) verify_blkaddr(sbi, fio->old_blkaddr, __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC); verify_blkaddr(sbi, fio->new_blkaddr, __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC_ENHANCE); } /* * Summary block is always treated as an invalid block */ static inline int check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; unsigned int usable_blks_per_seg = f2fs_usable_blks_in_seg(sbi, segno); /* check bitmap with valid block count */ do { if (is_valid) { next_pos = find_next_zero_bit_le(&raw_sit->valid_map, usable_blks_per_seg, cur_pos); valid_blocks += next_pos - cur_pos; } else next_pos = find_next_bit_le(&raw_sit->valid_map, usable_blks_per_seg, cur_pos); cur_pos = next_pos; is_valid = !is_valid; } while (cur_pos < usable_blks_per_seg); if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) { f2fs_err(sbi, "Mismatch valid blocks %d vs. %d", GET_SIT_VBLOCKS(raw_sit), valid_blocks); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT); return -EFSCORRUPTED; } if (usable_blks_per_seg < BLKS_PER_SEG(sbi)) f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map, BLKS_PER_SEG(sbi), usable_blks_per_seg) != BLKS_PER_SEG(sbi)); /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg || !valid_main_segno(sbi, segno))) { f2fs_err(sbi, "Wrong valid blocks %d or segno %u", GET_SIT_VBLOCKS(raw_sit), segno); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT); return -EFSCORRUPTED; } return 0; } static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi, unsigned int start) { struct sit_info *sit_i = SIT_I(sbi); unsigned int offset = SIT_BLOCK_OFFSET(start); block_t blk_addr = sit_i->sit_base_addr + offset; f2fs_bug_on(sbi, !valid_main_segno(sbi, start)); #ifdef CONFIG_F2FS_CHECK_FS if (f2fs_test_bit(offset, sit_i->sit_bitmap) != f2fs_test_bit(offset, sit_i->sit_bitmap_mir)) f2fs_bug_on(sbi, 1); #endif /* calculate sit block address */ if (f2fs_test_bit(offset, sit_i->sit_bitmap)) blk_addr += sit_i->sit_blocks; return blk_addr; } static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi, pgoff_t block_addr) { struct sit_info *sit_i = SIT_I(sbi); block_addr -= sit_i->sit_base_addr; if (block_addr < sit_i->sit_blocks) block_addr += sit_i->sit_blocks; else block_addr -= sit_i->sit_blocks; return block_addr + sit_i->sit_base_addr; } static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) { unsigned int block_off = SIT_BLOCK_OFFSET(start); f2fs_change_bit(block_off, sit_i->sit_bitmap); #ifdef CONFIG_F2FS_CHECK_FS f2fs_change_bit(block_off, sit_i->sit_bitmap_mir); #endif } static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi, bool base_time) { struct sit_info *sit_i = SIT_I(sbi); time64_t diff, now = ktime_get_boottime_seconds(); if (now >= sit_i->mounted_time) return sit_i->elapsed_time + now - sit_i->mounted_time; /* system time is set to the past */ if (!base_time) { diff = sit_i->mounted_time - now; if (sit_i->elapsed_time >= diff) return sit_i->elapsed_time - diff; return 0; } return sit_i->elapsed_time; } static inline void set_summary(struct f2fs_summary *sum, nid_t nid, unsigned int ofs_in_node, unsigned char version) { sum->nid = cpu_to_le32(nid); sum->ofs_in_node = cpu_to_le16(ofs_in_node); sum->version = version; } static inline block_t start_sum_block(struct f2fs_sb_info *sbi) { return __start_cp_addr(sbi) + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); } static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) { return __start_cp_addr(sbi) + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count) - (base + 1) + type; } static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) { if (is_cursec(sbi, secno) || (sbi->cur_victim_sec == secno)) return true; return false; } /* * It is very important to gather dirty pages and write at once, so that we can * submit a big bio without interfering other data writes. * By default, 512 pages for directory data, * 512 pages (2MB) * 8 for nodes, and * 256 pages * 8 for meta are set. */ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) { if (sbi->sb->s_bdi->wb.dirty_exceeded) return 0; if (type == DATA) return BLKS_PER_SEG(sbi); else if (type == NODE) return SEGS_TO_BLKS(sbi, 8); else if (type == META) return 8 * BIO_MAX_VECS; else return 0; } /* * When writing pages, it'd better align nr_to_write for segment size. */ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type, struct writeback_control *wbc) { long nr_to_write, desired; if (wbc->sync_mode != WB_SYNC_NONE) return 0; nr_to_write = wbc->nr_to_write; desired = BIO_MAX_VECS; if (type == NODE) desired <<= 1; wbc->nr_to_write = desired; return desired - nr_to_write; } static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; bool wakeup = false; int i; if (force) goto wake_up; mutex_lock(&dcc->cmd_lock); for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { if (i + 1 < dcc->discard_granularity) break; if (!list_empty(&dcc->pend_list[i])) { wakeup = true; break; } } mutex_unlock(&dcc->cmd_lock); if (!wakeup || !is_idle(sbi, DISCARD_TIME)) return; wake_up: dcc->discard_wake = true; wake_up_interruptible_all(&dcc->discard_wait_queue); } |
| 441 2078 28 5299 63 198 32 64 5600 1018 32 5544 5600 1 1 202 13148 11547 1879 3004 18075 6286 7155 10397 251 9 462 12 464 5 12 486 13075 64 395 3843 145 316 18 4 4 7633 15522 12567 11 2 8 3 3 1 780 | 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #if defined(arch_xchg) #define raw_xchg arch_xchg #elif defined(arch_xchg_relaxed) #define raw_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #else extern void raw_xchg_not_implemented(void); #define raw_xchg(...) raw_xchg_not_implemented() #endif #if defined(arch_xchg_acquire) #define raw_xchg_acquire arch_xchg_acquire #elif defined(arch_xchg_relaxed) #define raw_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_acquire arch_xchg #else extern void raw_xchg_acquire_not_implemented(void); #define raw_xchg_acquire(...) raw_xchg_acquire_not_implemented() #endif #if defined(arch_xchg_release) #define raw_xchg_release arch_xchg_release #elif defined(arch_xchg_relaxed) #define raw_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_release arch_xchg #else extern void raw_xchg_release_not_implemented(void); #define raw_xchg_release(...) raw_xchg_release_not_implemented() #endif #if defined(arch_xchg_relaxed) #define raw_xchg_relaxed arch_xchg_relaxed #elif defined(arch_xchg) #define raw_xchg_relaxed arch_xchg #else extern void raw_xchg_relaxed_not_implemented(void); #define raw_xchg_relaxed(...) raw_xchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg) #define raw_cmpxchg arch_cmpxchg #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #else extern void raw_cmpxchg_not_implemented(void); #define raw_cmpxchg(...) raw_cmpxchg_not_implemented() #endif #if defined(arch_cmpxchg_acquire) #define raw_cmpxchg_acquire arch_cmpxchg_acquire #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_acquire arch_cmpxchg #else extern void raw_cmpxchg_acquire_not_implemented(void); #define raw_cmpxchg_acquire(...) raw_cmpxchg_acquire_not_implemented() #endif #if defined(arch_cmpxchg_release) #define raw_cmpxchg_release arch_cmpxchg_release #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_release arch_cmpxchg #else extern void raw_cmpxchg_release_not_implemented(void); #define raw_cmpxchg_release(...) raw_cmpxchg_release_not_implemented() #endif #if defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_relaxed arch_cmpxchg_relaxed #elif defined(arch_cmpxchg) #define raw_cmpxchg_relaxed arch_cmpxchg #else extern void raw_cmpxchg_relaxed_not_implemented(void); #define raw_cmpxchg_relaxed(...) raw_cmpxchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg64) #define raw_cmpxchg64 arch_cmpxchg64 #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #else extern void raw_cmpxchg64_not_implemented(void); #define raw_cmpxchg64(...) raw_cmpxchg64_not_implemented() #endif #if defined(arch_cmpxchg64_acquire) #define raw_cmpxchg64_acquire arch_cmpxchg64_acquire #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_acquire arch_cmpxchg64 #else extern void raw_cmpxchg64_acquire_not_implemented(void); #define raw_cmpxchg64_acquire(...) raw_cmpxchg64_acquire_not_implemented() #endif #if defined(arch_cmpxchg64_release) #define raw_cmpxchg64_release arch_cmpxchg64_release #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_release arch_cmpxchg64 #else extern void raw_cmpxchg64_release_not_implemented(void); #define raw_cmpxchg64_release(...) raw_cmpxchg64_release_not_implemented() #endif #if defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_relaxed arch_cmpxchg64_relaxed #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_relaxed arch_cmpxchg64 #else extern void raw_cmpxchg64_relaxed_not_implemented(void); #define raw_cmpxchg64_relaxed(...) raw_cmpxchg64_relaxed_not_implemented() #endif #if defined(arch_cmpxchg128) #define raw_cmpxchg128 arch_cmpxchg128 #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128(...) \ __atomic_op_fence(arch_cmpxchg128, __VA_ARGS__) #else extern void raw_cmpxchg128_not_implemented(void); #define raw_cmpxchg128(...) raw_cmpxchg128_not_implemented() #endif #if defined(arch_cmpxchg128_acquire) #define raw_cmpxchg128_acquire arch_cmpxchg128_acquire #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_acquire arch_cmpxchg128 #else extern void raw_cmpxchg128_acquire_not_implemented(void); #define raw_cmpxchg128_acquire(...) raw_cmpxchg128_acquire_not_implemented() #endif #if defined(arch_cmpxchg128_release) #define raw_cmpxchg128_release arch_cmpxchg128_release #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_release(...) \ __atomic_op_release(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_release arch_cmpxchg128 #else extern void raw_cmpxchg128_release_not_implemented(void); #define raw_cmpxchg128_release(...) raw_cmpxchg128_release_not_implemented() #endif #if defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_relaxed arch_cmpxchg128_relaxed #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_relaxed arch_cmpxchg128 #else extern void raw_cmpxchg128_relaxed_not_implemented(void); #define raw_cmpxchg128_relaxed(...) raw_cmpxchg128_relaxed_not_implemented() #endif #if defined(arch_try_cmpxchg) #define raw_try_cmpxchg arch_try_cmpxchg #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg(...) \ __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) #else #define raw_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_acquire) #define raw_try_cmpxchg_acquire arch_try_cmpxchg_acquire #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_acquire arch_try_cmpxchg #else #define raw_try_cmpxchg_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_release) #define raw_try_cmpxchg_release arch_try_cmpxchg_release #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_release(...) \ __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_release arch_try_cmpxchg #else #define raw_try_cmpxchg_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg_relaxed #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg #else #define raw_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64 arch_try_cmpxchg64 #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64(...) \ __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) #else #define raw_try_cmpxchg64(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_acquire) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64_acquire #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_release) #define raw_try_cmpxchg64_release arch_try_cmpxchg64_release #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_release(...) \ __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_release arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64_relaxed #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128 arch_try_cmpxchg128 #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128(...) \ __atomic_op_fence(arch_try_cmpxchg128, __VA_ARGS__) #else #define raw_try_cmpxchg128(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_acquire) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128_acquire #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_release) #define raw_try_cmpxchg128_release arch_try_cmpxchg128_release #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_release(...) \ __atomic_op_release(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_release arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128_relaxed #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg_local arch_cmpxchg_local #ifdef arch_try_cmpxchg_local #define raw_try_cmpxchg_local arch_try_cmpxchg_local #else #define raw_try_cmpxchg_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg64_local arch_cmpxchg64_local #ifdef arch_try_cmpxchg64_local #define raw_try_cmpxchg64_local arch_try_cmpxchg64_local #else #define raw_try_cmpxchg64_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg128_local arch_cmpxchg128_local #ifdef arch_try_cmpxchg128_local #define raw_try_cmpxchg128_local arch_try_cmpxchg128_local #else #define raw_try_cmpxchg128_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_sync_cmpxchg arch_sync_cmpxchg #ifdef arch_sync_try_cmpxchg #define raw_sync_try_cmpxchg arch_sync_try_cmpxchg #else #define raw_sync_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_sync_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif /** * raw_atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read(const atomic_t *v) { return arch_atomic_read(v); } /** * raw_atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); #else int ret; if (__native_word(atomic_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set(atomic_t *v, int i) { arch_atomic_set(v, i); } /** * raw_atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic_set(v, i); } #endif } /** * raw_atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_add(int i, atomic_t *v) { arch_atomic_add(i, v); } /** * raw_atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return(int i, atomic_t *v) { #if defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_add_return" #endif } /** * raw_atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_return_acquire) return arch_atomic_add_return_acquire(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_acquire" #endif } /** * raw_atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_release(int i, atomic_t *v) { #if defined(arch_atomic_add_return_release) return arch_atomic_add_return_release(i, v); #elif defined(arch_atomic_add_return_relaxed) __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_release" #endif } /** * raw_atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_return_relaxed) return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_relaxed" #endif } /** * raw_atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_add" #endif } /** * raw_atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_acquire) return arch_atomic_fetch_add_acquire(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_acquire" #endif } /** * raw_atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_release) return arch_atomic_fetch_add_release(i, v); #elif defined(arch_atomic_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_release" #endif } /** * raw_atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_relaxed) return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_relaxed" #endif } /** * raw_atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_sub(int i, atomic_t *v) { arch_atomic_sub(i, v); } /** * raw_atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return(int i, atomic_t *v) { #if defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_sub_return" #endif } /** * raw_atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_acquire) return arch_atomic_sub_return_acquire(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_acquire" #endif } /** * raw_atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_release(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_release) return arch_atomic_sub_return_release(i, v); #elif defined(arch_atomic_sub_return_relaxed) __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_release" #endif } /** * raw_atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_relaxed) return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_relaxed" #endif } /** * raw_atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_sub" #endif } /** * raw_atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_acquire) return arch_atomic_fetch_sub_acquire(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_acquire" #endif } /** * raw_atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_release) return arch_atomic_fetch_sub_release(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_release" #endif } /** * raw_atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_relaxed) return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_relaxed" #endif } /** * raw_atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_inc(atomic_t *v) { #if defined(arch_atomic_inc) arch_atomic_inc(v); #else raw_atomic_add(1, v); #endif } /** * raw_atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return(atomic_t *v) { #if defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #elif defined(arch_atomic_inc_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(1, v); #endif } /** * raw_atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_acquire(atomic_t *v) { #if defined(arch_atomic_inc_return_acquire) return arch_atomic_inc_return_acquire(v); #elif defined(arch_atomic_inc_return_relaxed) int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_acquire(1, v); #endif } /** * raw_atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_release(atomic_t *v) { #if defined(arch_atomic_inc_return_release) return arch_atomic_inc_return_release(v); #elif defined(arch_atomic_inc_return_relaxed) __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_release(1, v); #endif } /** * raw_atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_relaxed(atomic_t *v) { #if defined(arch_atomic_inc_return_relaxed) return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc(atomic_t *v) { #if defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_add(1, v); #endif } /** * raw_atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_inc_acquire) return arch_atomic_fetch_inc_acquire(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_acquire(1, v); #endif } /** * raw_atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_release(atomic_t *v) { #if defined(arch_atomic_fetch_inc_release) return arch_atomic_fetch_inc_release(v); #elif defined(arch_atomic_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_release(1, v); #endif } /** * raw_atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_inc_relaxed) return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_relaxed(1, v); #endif } /** * raw_atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_dec(atomic_t *v) { #if defined(arch_atomic_dec) arch_atomic_dec(v); #else raw_atomic_sub(1, v); #endif } /** * raw_atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return(atomic_t *v) { #if defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #elif defined(arch_atomic_dec_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_sub_return(1, v); #endif } /** * raw_atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_acquire(atomic_t *v) { #if defined(arch_atomic_dec_return_acquire) return arch_atomic_dec_return_acquire(v); #elif defined(arch_atomic_dec_return_relaxed) int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_acquire(1, v); #endif } /** * raw_atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_release(atomic_t *v) { #if defined(arch_atomic_dec_return_release) return arch_atomic_dec_return_release(v); #elif defined(arch_atomic_dec_return_relaxed) __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_release(1, v); #endif } /** * raw_atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_relaxed(atomic_t *v) { #if defined(arch_atomic_dec_return_relaxed) return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec(atomic_t *v) { #if defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_sub(1, v); #endif } /** * raw_atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_dec_acquire) return arch_atomic_fetch_dec_acquire(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_acquire(1, v); #endif } /** * raw_atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_release(atomic_t *v) { #if defined(arch_atomic_fetch_dec_release) return arch_atomic_fetch_dec_release(v); #elif defined(arch_atomic_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_release(1, v); #endif } /** * raw_atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_dec_relaxed) return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_and(int i, atomic_t *v) { arch_atomic_and(i, v); } /** * raw_atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_and" #endif } /** * raw_atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_acquire) return arch_atomic_fetch_and_acquire(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_acquire" #endif } /** * raw_atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_release) return arch_atomic_fetch_and_release(i, v); #elif defined(arch_atomic_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_release" #endif } /** * raw_atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_relaxed) return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_relaxed" #endif } /** * raw_atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_andnot(int i, atomic_t *v) { #if defined(arch_atomic_andnot) arch_atomic_andnot(i, v); #else raw_atomic_and(~i, v); #endif } /** * raw_atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_and(~i, v); #endif } /** * raw_atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_acquire) return arch_atomic_fetch_andnot_acquire(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_acquire(~i, v); #endif } /** * raw_atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_release) return arch_atomic_fetch_andnot_release(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_release(~i, v); #endif } /** * raw_atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_relaxed) return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_or(int i, atomic_t *v) { arch_atomic_or(i, v); } /** * raw_atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_or" #endif } /** * raw_atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_acquire) return arch_atomic_fetch_or_acquire(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_acquire" #endif } /** * raw_atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_release) return arch_atomic_fetch_or_release(i, v); #elif defined(arch_atomic_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_release" #endif } /** * raw_atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_relaxed) return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_relaxed" #endif } /** * raw_atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_xor(int i, atomic_t *v) { arch_atomic_xor(i, v); } /** * raw_atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_xor" #endif } /** * raw_atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_acquire) return arch_atomic_fetch_xor_acquire(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_acquire" #endif } /** * raw_atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_release) return arch_atomic_fetch_xor_release(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_release" #endif } /** * raw_atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_relaxed) return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_relaxed" #endif } /** * raw_atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg(atomic_t *v, int new) { #if defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_acquire(atomic_t *v, int new) { #if defined(arch_atomic_xchg_acquire) return arch_atomic_xchg_acquire(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret = arch_atomic_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_release(atomic_t *v, int new) { #if defined(arch_atomic_xchg_release) return arch_atomic_xchg_release(v, new); #elif defined(arch_atomic_xchg_relaxed) __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_relaxed(atomic_t *v, int new) { #if defined(arch_atomic_xchg_relaxed) return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_acquire) return arch_atomic_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_release(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_release) return arch_atomic_cmpxchg_release(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_relaxed) return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else int r, o = *old; r = raw_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_acquire) return arch_atomic_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_release) return arch_atomic_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_relaxed) return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_sub_and_test(int i, atomic_t *v) { #if defined(arch_atomic_sub_and_test) return arch_atomic_sub_and_test(i, v); #else return raw_atomic_sub_return(i, v) == 0; #endif } /** * raw_atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_dec_and_test(atomic_t *v) { #if defined(arch_atomic_dec_and_test) return arch_atomic_dec_and_test(v); #else return raw_atomic_dec_return(v) == 0; #endif } /** * raw_atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_inc_and_test(atomic_t *v) { #if defined(arch_atomic_inc_and_test) return arch_atomic_inc_and_test(v); #else return raw_atomic_inc_return(v) == 0; #endif } /** * raw_atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative(int i, atomic_t *v) { #if defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(i, v) < 0; #endif } /** * raw_atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_acquire) return arch_atomic_add_negative_acquire(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret = arch_atomic_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_release(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_release) return arch_atomic_add_negative_release(i, v); #elif defined(arch_atomic_add_negative_relaxed) __atomic_release_fence(); return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_release(i, v) < 0; #endif } /** * raw_atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_relaxed) return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_fetch_add_unless) return arch_atomic_fetch_add_unless(v, a, u); #else int c = raw_atomic_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_add_unless) return arch_atomic_add_unless(v, a, u); #else return raw_atomic_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_not_zero(atomic_t *v) { #if defined(arch_atomic_inc_not_zero) return arch_atomic_inc_not_zero(v); #else return raw_atomic_add_unless(v, 1, 0); #endif } /** * raw_atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_unless_negative(atomic_t *v) { #if defined(arch_atomic_inc_unless_negative) return arch_atomic_inc_unless_negative(v); #else int c = raw_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_dec_unless_positive(atomic_t *v) { #if defined(arch_atomic_dec_unless_positive) return arch_atomic_dec_unless_positive(v); #else int c = raw_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int raw_atomic_dec_if_positive(atomic_t *v) { #if defined(arch_atomic_dec_if_positive) return arch_atomic_dec_if_positive(v); #else int dec, c = raw_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic_try_cmpxchg(v, &c, dec)); return dec; #endif } #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif /** * raw_atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read(const atomic64_t *v) { return arch_atomic64_read(v); } /** * raw_atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); #else s64 ret; if (__native_word(atomic64_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic64_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set(atomic64_t *v, s64 i) { arch_atomic64_set(v, i); } /** * raw_atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic64_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic64_set(v, i); } #endif } /** * raw_atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_add(s64 i, atomic64_t *v) { arch_atomic64_add(i, v); } /** * raw_atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_add_return" #endif } /** * raw_atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_acquire) return arch_atomic64_add_return_acquire(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_acquire" #endif } /** * raw_atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_release) return arch_atomic64_add_return_release(i, v); #elif defined(arch_atomic64_add_return_relaxed) __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_release" #endif } /** * raw_atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_relaxed) return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_relaxed" #endif } /** * raw_atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_add" #endif } /** * raw_atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_acquire) return arch_atomic64_fetch_add_acquire(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_acquire" #endif } /** * raw_atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_release) return arch_atomic64_fetch_add_release(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_release" #endif } /** * raw_atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_relaxed) return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_relaxed" #endif } /** * raw_atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_sub(s64 i, atomic64_t *v) { arch_atomic64_sub(i, v); } /** * raw_atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_sub_return" #endif } /** * raw_atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_acquire) return arch_atomic64_sub_return_acquire(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_acquire" #endif } /** * raw_atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_release) return arch_atomic64_sub_return_release(i, v); #elif defined(arch_atomic64_sub_return_relaxed) __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_release" #endif } /** * raw_atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_relaxed) return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_relaxed" #endif } /** * raw_atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_sub" #endif } /** * raw_atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_acquire) return arch_atomic64_fetch_sub_acquire(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_acquire" #endif } /** * raw_atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_release) return arch_atomic64_fetch_sub_release(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_release" #endif } /** * raw_atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_relaxed) return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_relaxed" #endif } /** * raw_atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_inc(atomic64_t *v) { #if defined(arch_atomic64_inc) arch_atomic64_inc(v); #else raw_atomic64_add(1, v); #endif } /** * raw_atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return(atomic64_t *v) { #if defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(1, v); #endif } /** * raw_atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_inc_return_acquire) return arch_atomic64_inc_return_acquire(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_acquire(1, v); #endif } /** * raw_atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_release(atomic64_t *v) { #if defined(arch_atomic64_inc_return_release) return arch_atomic64_inc_return_release(v); #elif defined(arch_atomic64_inc_return_relaxed) __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_release(1, v); #endif } /** * raw_atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_inc_return_relaxed) return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_add(1, v); #endif } /** * raw_atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_acquire) return arch_atomic64_fetch_inc_acquire(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_acquire(1, v); #endif } /** * raw_atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_release) return arch_atomic64_fetch_inc_release(v); #elif defined(arch_atomic64_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_release(1, v); #endif } /** * raw_atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_relaxed) return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_relaxed(1, v); #endif } /** * raw_atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_dec(atomic64_t *v) { #if defined(arch_atomic64_dec) arch_atomic64_dec(v); #else raw_atomic64_sub(1, v); #endif } /** * raw_atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return(atomic64_t *v) { #if defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_sub_return(1, v); #endif } /** * raw_atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_dec_return_acquire) return arch_atomic64_dec_return_acquire(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_acquire(1, v); #endif } /** * raw_atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_release(atomic64_t *v) { #if defined(arch_atomic64_dec_return_release) return arch_atomic64_dec_return_release(v); #elif defined(arch_atomic64_dec_return_relaxed) __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_release(1, v); #endif } /** * raw_atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_dec_return_relaxed) return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_sub(1, v); #endif } /** * raw_atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_acquire) return arch_atomic64_fetch_dec_acquire(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_acquire(1, v); #endif } /** * raw_atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_release) return arch_atomic64_fetch_dec_release(v); #elif defined(arch_atomic64_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_release(1, v); #endif } /** * raw_atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_relaxed) return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_and(s64 i, atomic64_t *v) { arch_atomic64_and(i, v); } /** * raw_atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_and" #endif } /** * raw_atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_acquire) return arch_atomic64_fetch_and_acquire(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_acquire" #endif } /** * raw_atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_release) return arch_atomic64_fetch_and_release(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_release" #endif } /** * raw_atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_relaxed) return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_relaxed" #endif } /** * raw_atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_andnot) arch_atomic64_andnot(i, v); #else raw_atomic64_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_acquire) return arch_atomic64_fetch_andnot_acquire(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_acquire(~i, v); #endif } /** * raw_atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_release) return arch_atomic64_fetch_andnot_release(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_release(~i, v); #endif } /** * raw_atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_relaxed) return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_or(s64 i, atomic64_t *v) { arch_atomic64_or(i, v); } /** * raw_atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_or" #endif } /** * raw_atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_acquire) return arch_atomic64_fetch_or_acquire(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_acquire" #endif } /** * raw_atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_release) return arch_atomic64_fetch_or_release(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_release" #endif } /** * raw_atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_relaxed) return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_relaxed" #endif } /** * raw_atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_xor(s64 i, atomic64_t *v) { arch_atomic64_xor(i, v); } /** * raw_atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_xor" #endif } /** * raw_atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_acquire) return arch_atomic64_fetch_xor_acquire(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_acquire" #endif } /** * raw_atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_release) return arch_atomic64_fetch_xor_release(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_release" #endif } /** * raw_atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_relaxed) return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_relaxed" #endif } /** * raw_atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic64_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_acquire(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_acquire) return arch_atomic64_xchg_acquire(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret = arch_atomic64_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_release(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_release) return arch_atomic64_xchg_release(v, new); #elif defined(arch_atomic64_xchg_relaxed) __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_relaxed) return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_acquire) return arch_atomic64_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_release) return arch_atomic64_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_relaxed) return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else s64 r, o = *old; r = raw_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_acquire) return arch_atomic64_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_release) return arch_atomic64_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_relaxed) return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_sub_and_test(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_and_test) return arch_atomic64_sub_and_test(i, v); #else return raw_atomic64_sub_return(i, v) == 0; #endif } /** * raw_atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_dec_and_test(atomic64_t *v) { #if defined(arch_atomic64_dec_and_test) return arch_atomic64_dec_and_test(v); #else return raw_atomic64_dec_return(v) == 0; #endif } /** * raw_atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_inc_and_test(atomic64_t *v) { #if defined(arch_atomic64_inc_and_test) return arch_atomic64_inc_and_test(v); #else return raw_atomic64_inc_return(v) == 0; #endif } /** * raw_atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(i, v) < 0; #endif } /** * raw_atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_acquire) return arch_atomic64_add_negative_acquire(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_release) return arch_atomic64_add_negative_release(i, v); #elif defined(arch_atomic64_add_negative_relaxed) __atomic_release_fence(); return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_release(i, v) < 0; #endif } /** * raw_atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_relaxed) return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_fetch_add_unless) return arch_atomic64_fetch_add_unless(v, a, u); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_add_unless) return arch_atomic64_add_unless(v, a, u); #else return raw_atomic64_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_not_zero(atomic64_t *v) { #if defined(arch_atomic64_inc_not_zero) return arch_atomic64_inc_not_zero(v); #else return raw_atomic64_add_unless(v, 1, 0); #endif } /** * raw_atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_unless_negative(atomic64_t *v) { #if defined(arch_atomic64_inc_unless_negative) return arch_atomic64_inc_unless_negative(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_dec_unless_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_unless_positive) return arch_atomic64_dec_unless_positive(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 raw_atomic64_dec_if_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_if_positive) return arch_atomic64_dec_if_positive(v); #else s64 dec, c = raw_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, dec)); return dec; #endif } #endif /* _LINUX_ATOMIC_FALLBACK_H */ // b565db590afeeff0d7c9485ccbca5bb6e155749f |
| 20 40 39 18 18 3 21 21 3 12 54 20 46 20 22 23 22 22 3 4 2 2 66 65 20 20 9 3 6 16 6 16 5 4 1 12 12 3 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * synth device handlers * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "../seq_lock.h" #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> /* * constants */ #define SNDRV_SEQ_OSS_MAX_SYNTH_NAME 30 #define MAX_SYSEX_BUFLEN 128 /* * definition of synth info records */ /* synth info */ struct seq_oss_synth { int seq_device; /* for synth_info */ int synth_type; int synth_subtype; int nr_voices; char name[SNDRV_SEQ_OSS_MAX_SYNTH_NAME]; struct snd_seq_oss_callback oper; int opened; void *private_data; snd_use_lock_t use_lock; }; DEFINE_FREE(seq_oss_synth, struct seq_oss_synth *, if (!IS_ERR_OR_NULL(_T)) snd_use_lock_free(&(_T)->use_lock)) /* * device table */ static int max_synth_devs; static struct seq_oss_synth *synth_devs[SNDRV_SEQ_OSS_MAX_SYNTH_DEVS]; static struct seq_oss_synth midi_synth_dev = { .seq_device = -1, .synth_type = SYNTH_TYPE_MIDI, .synth_subtype = 0, .nr_voices = 16, .name = "MIDI", }; static DEFINE_SPINLOCK(register_lock); /* * prototypes */ static struct seq_oss_synth *get_synthdev(struct seq_oss_devinfo *dp, int dev); static void reset_channels(struct seq_oss_synthinfo *info); /* * global initialization */ void __init snd_seq_oss_synth_init(void) { snd_use_lock_init(&midi_synth_dev.use_lock); } /* * registration of the synth device */ int snd_seq_oss_synth_probe(struct device *_dev) { struct snd_seq_device *dev = to_seq_dev(_dev); int i; struct seq_oss_synth *rec; struct snd_seq_oss_reg *reg = SNDRV_SEQ_DEVICE_ARGPTR(dev); rec = kzalloc(sizeof(*rec), GFP_KERNEL); if (!rec) return -ENOMEM; rec->seq_device = -1; rec->synth_type = reg->type; rec->synth_subtype = reg->subtype; rec->nr_voices = reg->nvoices; rec->oper = reg->oper; rec->private_data = reg->private_data; rec->opened = 0; snd_use_lock_init(&rec->use_lock); /* copy and truncate the name of synth device */ strscpy(rec->name, dev->name, sizeof(rec->name)); /* registration */ scoped_guard(spinlock_irqsave, ®ister_lock) { for (i = 0; i < max_synth_devs; i++) { if (synth_devs[i] == NULL) break; } if (i >= max_synth_devs) { if (max_synth_devs >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) { pr_err("ALSA: seq_oss: no more synth slot\n"); kfree(rec); return -ENOMEM; } max_synth_devs++; } rec->seq_device = i; synth_devs[i] = rec; } dev->driver_data = rec; #ifdef SNDRV_OSS_INFO_DEV_SYNTH if (i < SNDRV_CARDS) snd_oss_info_register(SNDRV_OSS_INFO_DEV_SYNTH, i, rec->name); #endif return 0; } int snd_seq_oss_synth_remove(struct device *_dev) { struct snd_seq_device *dev = to_seq_dev(_dev); int index; struct seq_oss_synth *rec = dev->driver_data; scoped_guard(spinlock_irqsave, ®ister_lock) { for (index = 0; index < max_synth_devs; index++) { if (synth_devs[index] == rec) break; } if (index >= max_synth_devs) { pr_err("ALSA: seq_oss: can't unregister synth\n"); return -EINVAL; } synth_devs[index] = NULL; if (index == max_synth_devs - 1) { for (index--; index >= 0; index--) { if (synth_devs[index]) break; } max_synth_devs = index + 1; } } #ifdef SNDRV_OSS_INFO_DEV_SYNTH if (rec->seq_device < SNDRV_CARDS) snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_SYNTH, rec->seq_device); #endif snd_use_lock_sync(&rec->use_lock); kfree(rec); return 0; } /* */ static struct seq_oss_synth * get_sdev(int dev) { struct seq_oss_synth *rec; guard(spinlock_irqsave)(®ister_lock); rec = synth_devs[dev]; if (rec) snd_use_lock_use(&rec->use_lock); return rec; } /* * set up synth tables */ void snd_seq_oss_synth_setup(struct seq_oss_devinfo *dp) { int i; struct seq_oss_synthinfo *info; dp->max_synthdev = max_synth_devs; dp->synth_opened = 0; memset(dp->synths, 0, sizeof(dp->synths)); for (i = 0; i < dp->max_synthdev; i++) { struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(i); if (rec == NULL) continue; if (rec->oper.open == NULL || rec->oper.close == NULL) continue; info = &dp->synths[i]; info->arg.app_index = dp->port; info->arg.file_mode = dp->file_mode; info->arg.seq_mode = dp->seq_mode; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) info->arg.event_passing = SNDRV_SEQ_OSS_PROCESS_EVENTS; else info->arg.event_passing = SNDRV_SEQ_OSS_PASS_EVENTS; info->opened = 0; if (!try_module_get(rec->oper.owner)) continue; if (rec->oper.open(&info->arg, rec->private_data) < 0) { module_put(rec->oper.owner); continue; } info->nr_voices = rec->nr_voices; if (info->nr_voices > 0) { info->ch = kcalloc(info->nr_voices, sizeof(struct seq_oss_chinfo), GFP_KERNEL); if (!info->ch) { rec->oper.close(&info->arg); module_put(rec->oper.owner); continue; } reset_channels(info); } info->opened++; rec->opened++; dp->synth_opened++; } } /* * set up synth tables for MIDI emulation - /dev/music mode only */ void snd_seq_oss_synth_setup_midi(struct seq_oss_devinfo *dp) { int i; if (dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) return; for (i = 0; i < dp->max_mididev; i++) { struct seq_oss_synthinfo *info; info = &dp->synths[dp->max_synthdev]; if (snd_seq_oss_midi_open(dp, i, dp->file_mode) < 0) continue; info->arg.app_index = dp->port; info->arg.file_mode = dp->file_mode; info->arg.seq_mode = dp->seq_mode; info->arg.private_data = info; info->is_midi = 1; info->midi_mapped = i; info->arg.event_passing = SNDRV_SEQ_OSS_PASS_EVENTS; snd_seq_oss_midi_get_addr(dp, i, &info->arg.addr); info->opened = 1; midi_synth_dev.opened++; dp->max_synthdev++; if (dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) break; } } /* * clean up synth tables */ void snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) { int i; struct seq_oss_synthinfo *info; if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; if (! info->opened) continue; if (info->is_midi) { if (midi_synth_dev.opened > 0) { snd_seq_oss_midi_close(dp, info->midi_mapped); midi_synth_dev.opened--; } } else { struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(i); if (rec == NULL) continue; if (rec->opened > 0) { rec->oper.close(&info->arg); module_put(rec->oper.owner); rec->opened = 0; } } kfree(info->ch); info->ch = NULL; } dp->synth_opened = 0; dp->max_synthdev = 0; } static struct seq_oss_synthinfo * get_synthinfo_nospec(struct seq_oss_devinfo *dp, int dev) { if (dev < 0 || dev >= dp->max_synthdev) return NULL; dev = array_index_nospec(dev, SNDRV_SEQ_OSS_MAX_SYNTH_DEVS); return &dp->synths[dev]; } /* * return synth device information pointer */ static struct seq_oss_synth * get_synthdev(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synth *rec; struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev); if (!info) return NULL; if (!info->opened) return NULL; if (info->is_midi) { rec = &midi_synth_dev; snd_use_lock_use(&rec->use_lock); } else { rec = get_sdev(dev); if (!rec) return NULL; } if (! rec->opened) { snd_use_lock_free(&rec->use_lock); return NULL; } return rec; } /* * reset note and velocity on each channel. */ static void reset_channels(struct seq_oss_synthinfo *info) { int i; if (info->ch == NULL || ! info->nr_voices) return; for (i = 0; i < info->nr_voices; i++) { info->ch[i].note = -1; info->ch[i].vel = 0; } } /* * reset synth device: * call reset callback. if no callback is defined, send a heartbeat * event to the corresponding port. */ void snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synth *rec __free(seq_oss_synth) = NULL; struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info || !info->opened) return; reset_channels(info); if (info->is_midi) { if (midi_synth_dev.opened <= 0) return; snd_seq_oss_midi_reset(dp, info->midi_mapped); /* reopen the device */ snd_seq_oss_midi_close(dp, dev); if (snd_seq_oss_midi_open(dp, info->midi_mapped, dp->file_mode) < 0) { midi_synth_dev.opened--; info->opened = 0; kfree(info->ch); info->ch = NULL; } return; } rec = get_sdev(dev); if (rec == NULL) return; if (rec->oper.reset) { rec->oper.reset(&info->arg); } else { struct snd_seq_event ev; memset(&ev, 0, sizeof(ev)); snd_seq_oss_fill_addr(dp, &ev, info->arg.addr.client, info->arg.addr.port); ev.type = SNDRV_SEQ_EVENT_RESET; snd_seq_oss_dispatch(dp, &ev, 0, 0); } } /* * load a patch record: * call load_patch callback function */ int snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt, const char __user *buf, int p, int c) { struct seq_oss_synth *rec __free(seq_oss_synth) = NULL; struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info) return -ENXIO; if (info->is_midi) return 0; rec = get_synthdev(dp, dev); if (!rec) return -ENXIO; if (rec->oper.load_patch == NULL) return -ENXIO; else return rec->oper.load_patch(&info->arg, fmt, buf, p, c); } /* * check if the device is valid synth device and return the synth info */ struct seq_oss_synthinfo * snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synth *rec __free(seq_oss_synth) = NULL; rec = get_synthdev(dp, dev); if (rec) return get_synthinfo_nospec(dp, dev); return NULL; } /* * receive OSS 6 byte sysex packet: * the event is filled and prepared for sending immediately * (i.e. sysex messages are fragmented) */ int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, struct snd_seq_event *ev) { unsigned char *p; int len = 6; p = memchr(buf, 0xff, 6); if (p) len = p - buf + 1; /* copy the data to event record and send it */ if (snd_seq_oss_synth_addr(dp, dev, ev)) return -EINVAL; ev->flags = SNDRV_SEQ_EVENT_LENGTH_VARIABLE; ev->data.ext.len = len; ev->data.ext.ptr = buf; return 0; } /* * fill the event source/destination addresses */ int snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info = snd_seq_oss_synth_info(dp, dev); if (!info) return -EINVAL; snd_seq_oss_fill_addr(dp, ev, info->arg.addr.client, info->arg.addr.port); return 0; } /* * OSS compatible ioctl */ int snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, unsigned long addr) { struct seq_oss_synth *rec __free(seq_oss_synth) = NULL; struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info || info->is_midi) return -ENXIO; rec = get_synthdev(dp, dev); if (!rec) return -ENXIO; if (rec->oper.ioctl == NULL) return -ENXIO; else return rec->oper.ioctl(&info->arg, cmd, addr); } /* * send OSS raw events - SEQ_PRIVATE and SEQ_VOLUME */ int snd_seq_oss_synth_raw_event(struct seq_oss_devinfo *dp, int dev, unsigned char *data, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info || info->is_midi) return -ENXIO; ev->type = SNDRV_SEQ_EVENT_OSS; memcpy(ev->data.raw8.d, data, 8); return snd_seq_oss_synth_addr(dp, dev, ev); } /* * create OSS compatible synth_info record */ int snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_info *inf) { struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev); if (!info) return -ENXIO; if (info->is_midi) { struct midi_info minf; if (snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf)) return -ENXIO; inf->synth_type = SYNTH_TYPE_MIDI; inf->synth_subtype = 0; inf->nr_voices = 16; inf->device = dev; strscpy(inf->name, minf.name, sizeof(inf->name)); } else { struct seq_oss_synth *rec __free(seq_oss_synth) = get_synthdev(dp, dev); if (!rec) return -ENXIO; inf->synth_type = rec->synth_type; inf->synth_subtype = rec->synth_subtype; inf->nr_voices = rec->nr_voices; inf->device = dev; strscpy(inf->name, rec->name, sizeof(inf->name)); } return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ void snd_seq_oss_synth_info_read(struct snd_info_buffer *buf) { int i; snd_iprintf(buf, "\nNumber of synth devices: %d\n", max_synth_devs); for (i = 0; i < max_synth_devs; i++) { struct seq_oss_synth *rec __free(seq_oss_synth) = NULL; snd_iprintf(buf, "\nsynth %d: ", i); rec = get_sdev(i); if (rec == NULL) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "[%s]\n", rec->name); snd_iprintf(buf, " type 0x%x : subtype 0x%x : voices %d\n", rec->synth_type, rec->synth_subtype, rec->nr_voices); snd_iprintf(buf, " capabilities : ioctl %s / load_patch %s\n", str_enabled_disabled((long)rec->oper.ioctl), str_enabled_disabled((long)rec->oper.load_patch)); } } #endif /* CONFIG_SND_PROC_FS */ |
| 9 10 1 1 25 25 5 8 13 13 10 10 7 7 7 7 10 12 1 1 1 1 1 10 5 2072 2054 22 17 5 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007, 2008, 2009 Siemens AG */ #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <net/cfg802154.h> #include <net/rtnetlink.h> #include "ieee802154.h" #include "nl802154.h" #include "sysfs.h" #include "core.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" /* RCU-protected (and RTNL for writers) */ LIST_HEAD(cfg802154_rdev_list); int cfg802154_rdev_list_generation; struct wpan_phy *wpan_phy_find(const char *str) { struct device *dev; if (WARN_ON(!str)) return NULL; dev = class_find_device_by_name(&wpan_phy_class, str); if (!dev) return NULL; return container_of(dev, struct wpan_phy, dev); } EXPORT_SYMBOL(wpan_phy_find); struct wpan_phy_iter_data { int (*fn)(struct wpan_phy *phy, void *data); void *data; }; static int wpan_phy_iter(struct device *dev, void *_data) { struct wpan_phy_iter_data *wpid = _data; struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); return wpid->fn(phy, wpid->data); } int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data) { struct wpan_phy_iter_data wpid = { .fn = fn, .data = data, }; return class_for_each_device(&wpan_phy_class, NULL, &wpid, wpan_phy_iter); } EXPORT_SYMBOL(wpan_phy_for_each); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx) { struct cfg802154_registered_device *result = NULL, *rdev; ASSERT_RTNL(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (rdev->wpan_phy_idx == wpan_phy_idx) { result = rdev; break; } } return result; } struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx) { struct cfg802154_registered_device *rdev; ASSERT_RTNL(); rdev = cfg802154_rdev_by_wpan_phy_idx(wpan_phy_idx); if (!rdev) return NULL; return &rdev->wpan_phy; } struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) { static atomic_t wpan_phy_counter = ATOMIC_INIT(0); struct cfg802154_registered_device *rdev; size_t alloc_size; alloc_size = sizeof(*rdev) + priv_size; rdev = kzalloc(alloc_size, GFP_KERNEL); if (!rdev) return NULL; rdev->ops = ops; rdev->wpan_phy_idx = atomic_inc_return(&wpan_phy_counter); if (unlikely(rdev->wpan_phy_idx < 0)) { /* ugh, wrapped! */ atomic_dec(&wpan_phy_counter); kfree(rdev); return NULL; } /* atomic_inc_return makes it start at 1, make it start at 0 */ rdev->wpan_phy_idx--; INIT_LIST_HEAD(&rdev->wpan_dev_list); device_initialize(&rdev->wpan_phy.dev); dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx); rdev->wpan_phy.dev.class = &wpan_phy_class; rdev->wpan_phy.dev.platform_data = rdev; wpan_phy_net_set(&rdev->wpan_phy, &init_net); init_waitqueue_head(&rdev->dev_wait); init_waitqueue_head(&rdev->wpan_phy.sync_txq); spin_lock_init(&rdev->wpan_phy.queue_lock); return &rdev->wpan_phy; } EXPORT_SYMBOL(wpan_phy_new); int wpan_phy_register(struct wpan_phy *phy) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy); int ret; rtnl_lock(); ret = device_add(&phy->dev); if (ret) { rtnl_unlock(); return ret; } list_add_rcu(&rdev->list, &cfg802154_rdev_list); cfg802154_rdev_list_generation++; /* TODO phy registered lock */ rtnl_unlock(); /* TODO nl802154 phy notify */ return 0; } EXPORT_SYMBOL(wpan_phy_register); void wpan_phy_unregister(struct wpan_phy *phy) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy); wait_event(rdev->dev_wait, ({ int __count; rtnl_lock(); __count = rdev->opencount; rtnl_unlock(); __count == 0; })); rtnl_lock(); /* TODO nl802154 phy notify */ /* TODO phy registered lock */ WARN_ON(!list_empty(&rdev->wpan_dev_list)); /* First remove the hardware from everywhere, this makes * it impossible to find from userspace. */ list_del_rcu(&rdev->list); synchronize_rcu(); cfg802154_rdev_list_generation++; device_del(&phy->dev); rtnl_unlock(); } EXPORT_SYMBOL(wpan_phy_unregister); void wpan_phy_free(struct wpan_phy *phy) { put_device(&phy->dev); } EXPORT_SYMBOL(wpan_phy_free); static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev) { struct ieee802154_pan_device *child, *tmp; mutex_lock(&wpan_dev->association_lock); kfree(wpan_dev->parent); wpan_dev->parent = NULL; list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) { list_del(&child->node); kfree(child); } wpan_dev->nchildren = 0; mutex_unlock(&wpan_dev->association_lock); } int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, struct net *net) { struct wpan_dev *wpan_dev; int err = 0; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; wpan_dev->netdev->netns_immutable = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); if (err) break; wpan_dev->netdev->netns_immutable = true; } if (err) { /* failed -- clean up to old netns */ net = wpan_phy_net(&rdev->wpan_phy); list_for_each_entry_continue_reverse(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; wpan_dev->netdev->netns_immutable = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); WARN_ON(err); wpan_dev->netdev->netns_immutable = true; } return err; } wpan_phy_net_set(&rdev->wpan_phy, net); err = device_rename(&rdev->wpan_phy.dev, dev_name(&rdev->wpan_phy.dev)); WARN_ON(err); return 0; } void cfg802154_dev_free(struct cfg802154_registered_device *rdev) { kfree(rdev); } static void cfg802154_update_iface_num(struct cfg802154_registered_device *rdev, int iftype, int num) { ASSERT_RTNL(); rdev->num_running_ifaces += num; } static int cfg802154_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct cfg802154_registered_device *rdev; if (!wpan_dev) return NOTIFY_DONE; rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); /* TODO WARN_ON unspec type */ switch (state) { /* TODO NETDEV_DEVTYPE */ case NETDEV_REGISTER: dev->netns_immutable = true; wpan_dev->identifier = ++rdev->wpan_dev_id; list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list); rdev->devlist_generation++; mutex_init(&wpan_dev->association_lock); INIT_LIST_HEAD(&wpan_dev->children); wpan_dev->max_associations = SZ_16K; wpan_dev->netdev = dev; break; case NETDEV_DOWN: cfg802154_update_iface_num(rdev, wpan_dev->iftype, -1); rdev->opencount--; wake_up(&rdev->dev_wait); break; case NETDEV_UP: cfg802154_update_iface_num(rdev, wpan_dev->iftype, 1); rdev->opencount++; break; case NETDEV_UNREGISTER: cfg802154_free_peer_structures(wpan_dev); /* It is possible to get NETDEV_UNREGISTER * multiple times. To detect that, check * that the interface is still on the list * of registered interfaces, and only then * remove and clean it up. */ if (!list_empty(&wpan_dev->list)) { list_del_rcu(&wpan_dev->list); rdev->devlist_generation++; } /* synchronize (so that we won't find this netdev * from other code any more) and then clear the list * head so that the above code can safely check for * !list_empty() to avoid double-cleanup. */ synchronize_rcu(); INIT_LIST_HEAD(&wpan_dev->list); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block cfg802154_netdev_notifier = { .notifier_call = cfg802154_netdev_notifier_call, }; static void __net_exit cfg802154_pernet_exit(struct net *net) { struct cfg802154_registered_device *rdev; rtnl_lock(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (net_eq(wpan_phy_net(&rdev->wpan_phy), net)) WARN_ON(cfg802154_switch_netns(rdev, &init_net)); } rtnl_unlock(); } static struct pernet_operations cfg802154_pernet_ops = { .exit = cfg802154_pernet_exit, }; static int __init wpan_phy_class_init(void) { int rc; rc = register_pernet_device(&cfg802154_pernet_ops); if (rc) goto err; rc = wpan_phy_sysfs_init(); if (rc) goto err_sysfs; rc = register_netdevice_notifier(&cfg802154_netdev_notifier); if (rc) goto err_nl; rc = ieee802154_nl_init(); if (rc) goto err_notifier; rc = nl802154_init(); if (rc) goto err_ieee802154_nl; return 0; err_ieee802154_nl: ieee802154_nl_exit(); err_notifier: unregister_netdevice_notifier(&cfg802154_netdev_notifier); err_nl: wpan_phy_sysfs_exit(); err_sysfs: unregister_pernet_device(&cfg802154_pernet_ops); err: return rc; } subsys_initcall(wpan_phy_class_init); static void __exit wpan_phy_class_exit(void) { nl802154_exit(); ieee802154_nl_exit(); unregister_netdevice_notifier(&cfg802154_netdev_notifier); wpan_phy_sysfs_exit(); unregister_pernet_device(&cfg802154_pernet_ops); } module_exit(wpan_phy_class_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface"); MODULE_AUTHOR("Dmitry Eremin-Solenikov"); |
| 8 12 2 11 3 10 11 2 13 2 1 2 1 2 2 1 3 3 3 7 3 10 10 10 10 10 3 2 6 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static int get_ifindex(const struct net_device *dev) { return dev ? dev->ifindex : 0; } static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv, const struct nft_pktinfo *pkt, const struct net_device *dev, struct ipv6hdr *iph) { int lookup_flags = 0; if (priv->flags & NFTA_FIB_F_DADDR) { fl6->daddr = iph->daddr; fl6->saddr = iph->saddr; } else { if (nft_hook(pkt) == NF_INET_FORWARD && priv->flags & NFTA_FIB_F_IIF) fl6->flowi6_iif = nft_out(pkt)->ifindex; fl6->daddr = iph->saddr; fl6->saddr = iph->daddr; } if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev); } if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST) lookup_flags |= RT6_LOOKUP_F_HAS_SADDR; if (priv->flags & NFTA_FIB_F_MARK) fl6->flowi6_mark = pkt->skb->mark; fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK; fl6->flowi6_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, dev); return lookup_flags; } static u32 __nft_fib6_eval_type(const struct nft_fib *priv, const struct nft_pktinfo *pkt, struct ipv6hdr *iph) { const struct net_device *dev = NULL; int route_err, addrtype; struct rt6_info *rt; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; u32 ret = 0; if (priv->flags & NFTA_FIB_F_IIF) dev = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) dev = nft_out(pkt); nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph); if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) ret = RTN_LOCAL; route_err = nf_ip6_route(nft_net(pkt), (struct dst_entry **)&rt, flowi6_to_flowi(&fl6), false); if (route_err) goto err; if (rt->rt6i_flags & RTF_REJECT) { route_err = rt->dst.error; dst_release(&rt->dst); goto err; } if (ipv6_anycast_destination((struct dst_entry *)rt, &fl6.daddr)) ret = RTN_ANYCAST; else if (!dev && rt->rt6i_flags & RTF_LOCAL) ret = RTN_LOCAL; dst_release(&rt->dst); if (ret) return ret; addrtype = ipv6_addr_type(&fl6.daddr); if (addrtype & IPV6_ADDR_MULTICAST) return RTN_MULTICAST; if (addrtype & IPV6_ADDR_UNICAST) return RTN_UNICAST; return RTN_UNSPEC; err: switch (route_err) { case -EINVAL: return RTN_BLACKHOLE; case -EACCES: return RTN_PROHIBIT; case -EAGAIN: return RTN_THROW; default: break; } return RTN_UNREACHABLE; } void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); u32 *dest = ®s->data[priv->dreg]; struct ipv6hdr *iph, _iph; iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } *dest = __nft_fib6_eval_type(priv, pkt, iph); } EXPORT_SYMBOL_GPL(nft_fib6_eval_type); static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) { if (likely(next != IPPROTO_ICMPV6)) return false; if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) return false; return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; } void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); const struct net_device *found = NULL; const struct net_device *oif = NULL; u32 *dest = ®s->data[priv->dreg]; struct ipv6hdr *iph, _iph; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; struct rt6_info *rt; int lookup_flags; if (nft_fib_can_skip(pkt)) { nft_fib_store_result(dest, priv, nft_in(pkt)); return; } if (priv->flags & NFTA_FIB_F_IIF) oif = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) oif = nft_out(pkt); iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } if (nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { nft_fib_store_result(dest, priv, nft_in(pkt)); return; } lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); *dest = 0; rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb, lookup_flags); if (rt->dst.error) goto put_rt_err; /* Should not see RTF_LOCAL here */ if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; if (!oif) { found = rt->rt6i_idev->dev; } else { if (oif == rt->rt6i_idev->dev || l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex) found = oif; } nft_fib_store_result(dest, priv, found); put_rt_err: ip6_rt_put(rt); } EXPORT_SYMBOL_GPL(nft_fib6_eval); static struct nft_expr_type nft_fib6_type; static const struct nft_expr_ops nft_fib6_type_ops = { .type = &nft_fib6_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib6_eval_type, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, .reduce = nft_fib_reduce, }; static const struct nft_expr_ops nft_fib6_ops = { .type = &nft_fib6_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib6_eval, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, .reduce = nft_fib_reduce, }; static const struct nft_expr_ops * nft_fib6_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { enum nft_fib_result result; if (!tb[NFTA_FIB_RESULT]) return ERR_PTR(-EINVAL); result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (result) { case NFT_FIB_RESULT_OIF: return &nft_fib6_ops; case NFT_FIB_RESULT_OIFNAME: return &nft_fib6_ops; case NFT_FIB_RESULT_ADDRTYPE: return &nft_fib6_type_ops; default: return ERR_PTR(-EOPNOTSUPP); } } static struct nft_expr_type nft_fib6_type __read_mostly = { .name = "fib", .select_ops = nft_fib6_select_ops, .policy = nft_fib_policy, .maxattr = NFTA_FIB_MAX, .family = NFPROTO_IPV6, .owner = THIS_MODULE, }; static int __init nft_fib6_module_init(void) { return nft_register_expr(&nft_fib6_type); } static void __exit nft_fib6_module_exit(void) { nft_unregister_expr(&nft_fib6_type); } module_init(nft_fib6_module_init); module_exit(nft_fib6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(10, "fib"); MODULE_DESCRIPTION("nftables fib / ipv6 route lookup support"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 'raw' table, which is the very first hooked in at PRE_ROUTING and LOCAL_OUT . * * Copyright (C) 2003 Jozsef Kadlecsik <kadlec@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/slab.h> #include <net/ip.h> #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW, }; static const struct xt_table packet_raw_before_defrag = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW_BEFORE_DEFRAG, }; static struct nf_hook_ops *rawtable_ops __read_mostly; static int iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; const struct xt_table *table = &packet_raw; int ret; if (raw_before_defrag) table = &packet_raw_before_defrag; repl = ipt_alloc_initial_table(table); if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, table, repl, rawtable_ops); kfree(repl); return ret; } static void __net_exit iptable_raw_net_pre_exit(struct net *net) { ipt_unregister_table_pre_exit(net, "raw"); } static void __net_exit iptable_raw_net_exit(struct net *net) { ipt_unregister_table_exit(net, "raw"); } static struct pernet_operations iptable_raw_net_ops = { .pre_exit = iptable_raw_net_pre_exit, .exit = iptable_raw_net_exit, }; static int __init iptable_raw_init(void) { int ret; const struct xt_table *table = &packet_raw; if (raw_before_defrag) { table = &packet_raw_before_defrag; pr_info("Enabling raw table before defrag\n"); } ret = xt_register_template(table, iptable_raw_table_init); if (ret < 0) return ret; rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); } ret = register_pernet_subsys(&iptable_raw_net_ops); if (ret < 0) { xt_unregister_template(table); kfree(rawtable_ops); return ret; } return ret; } static void __exit iptable_raw_fini(void) { unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); module_exit(iptable_raw_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("iptables legacy raw table"); |
| 420 420 3946 57 176 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sched #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCHED_H #include <linux/kthread.h> #include <linux/sched/numa_balancing.h> #include <linux/tracepoint.h> #include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: */ TRACE_EVENT(sched_kthread_stop, TP_PROTO(struct task_struct *t), TP_ARGS(t), TP_STRUCT__entry( __string( comm, t->comm ) __field( pid_t, pid ) ), TP_fast_assign( __assign_str(comm); __entry->pid = t->pid; ), TP_printk("comm=%s pid=%d", __get_str(comm), __entry->pid) ); /* * Tracepoint for the return value of the kthread stopping: */ TRACE_EVENT(sched_kthread_stop_ret, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( int, ret ) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); /** * sched_kthread_work_queue_work - called when a work gets queued * @worker: pointer to the kthread_worker * @work: pointer to struct kthread_work * * This event occurs when a work is queued immediately or once a * delayed work is actually queued (ie: once the delay has been * reached). */ TRACE_EVENT(sched_kthread_work_queue_work, TP_PROTO(struct kthread_worker *worker, struct kthread_work *work), TP_ARGS(worker, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __field( void *, worker) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __entry->worker = worker; ), TP_printk("work struct=%p function=%ps worker=%p", __entry->work, __entry->function, __entry->worker) ); /** * sched_kthread_work_execute_start - called immediately before the work callback * @work: pointer to struct kthread_work * * Allows to track kthread work execution. */ TRACE_EVENT(sched_kthread_work_execute_start, TP_PROTO(struct kthread_work *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * sched_kthread_work_execute_end - called immediately after the work callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(sched_kthread_work_execute_end, TP_PROTO(struct kthread_work *work, kthread_work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /* * Tracepoint for waking up a task: */ DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct task_struct *p), TP_ARGS(__perf_task(p)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, target_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->target_cpu = task_cpu(p); ), TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d", __entry->comm, __entry->pid, __entry->prio, __entry->target_cpu) ); /* * Tracepoint called when waking a task; this tracepoint is guaranteed to be * called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waking up a new task: */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p), TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS static inline long __trace_sched_switch_state(bool preempt, unsigned int prev_state, struct task_struct *p) { unsigned int state; BUG_ON(p != current); /* * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ if (preempt) return TASK_REPORT_MAX; /* * task_state_index() uses fls() and returns a value from 0-8 range. * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using * it for left shift operation to get the correct task->state * mapping. */ state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } #endif /* CREATE_TRACE_POINTS */ /* * Tracepoint for task switches, performed by the scheduler: */ TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, struct task_struct *prev, struct task_struct *next, unsigned int prev_state), TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) __field( pid_t, prev_pid ) __field( int, prev_prio ) __field( long, prev_state ) __array( char, next_comm, TASK_COMM_LEN ) __field( pid_t, next_pid ) __field( int, next_prio ) ), TP_fast_assign( memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { TASK_INTERRUPTIBLE, "S" }, { TASK_UNINTERRUPTIBLE, "D" }, { __TASK_STOPPED, "T" }, { __TASK_TRACED, "t" }, { EXIT_DEAD, "X" }, { EXIT_ZOMBIE, "Z" }, { TASK_PARKED, "P" }, { TASK_DEAD, "I" }) : "R", __entry->prev_state & TASK_REPORT_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); /* * Tracepoint for a task being migrated: */ TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu), TP_ARGS(p, dest_cpu), TP_STRUCT__entry( __string( comm, p->comm ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) ), TP_fast_assign( __assign_str(comm); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d", __get_str(comm), __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu) ); DECLARE_EVENT_CLASS(sched_process_template, TP_PROTO(struct task_struct *p), TP_ARGS(p), TP_STRUCT__entry( __string( comm, p->comm ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __get_str(comm), __entry->pid, __entry->prio) ); /* * Tracepoint for freeing a task: */ DEFINE_EVENT(sched_process_template, sched_process_free, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a task exiting. * Note, it's a superset of sched_process_template and should be kept * compatible as much as possible. sched_process_exits has an extra * `group_dead` argument, so sched_process_template can't be used, * unfortunately, just like sched_migrate_task above. */ TRACE_EVENT(sched_process_exit, TP_PROTO(struct task_struct *p, bool group_dead), TP_ARGS(p, group_dead), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( bool, group_dead ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->group_dead = group_dead; ), TP_printk("comm=%s pid=%d prio=%d group_dead=%s", __entry->comm, __entry->pid, __entry->prio, __entry->group_dead ? "true" : "false" ) ); /* * Tracepoint for waiting on task to unschedule: */ DEFINE_EVENT(sched_process_template, sched_wait_task, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a waiting task: */ TRACE_EVENT(sched_process_wait, TP_PROTO(struct pid *pid), TP_ARGS(pid), TP_STRUCT__entry( __string( comm, current->comm ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = pid_nr(pid); __entry->prio = current->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __get_str(comm), __entry->pid, __entry->prio) ); /* * Tracepoint for kernel_clone: */ TRACE_EVENT(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child), TP_ARGS(parent, child), TP_STRUCT__entry( __string( parent_comm, parent->comm ) __field( pid_t, parent_pid ) __string( child_comm, child->comm ) __field( pid_t, child_pid ) ), TP_fast_assign( __assign_str(parent_comm); __entry->parent_pid = parent->pid; __assign_str(child_comm); __entry->child_pid = child->pid; ), TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d", __get_str(parent_comm), __entry->parent_pid, __get_str(child_comm), __entry->child_pid) ); /* * Tracepoint for exec: */ TRACE_EVENT(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm), TP_ARGS(p, old_pid, bprm), TP_STRUCT__entry( __string( filename, bprm->filename ) __field( pid_t, pid ) __field( pid_t, old_pid ) ), TP_fast_assign( __assign_str(filename); __entry->pid = p->pid; __entry->old_pid = old_pid; ), TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), __entry->pid, __entry->old_pid) ); /** * sched_prepare_exec - called before setting up new exec * @task: pointer to the current task * @bprm: pointer to linux_binprm used for new exec * * Called before flushing the old exec, where @task is still unchanged, but at * the point of no return during switching to the new exec. At the point it is * called the exec will either succeed, or on failure terminate the task. Also * see the "sched_process_exec" tracepoint, which is called right after @task * has successfully switched to the new exec. */ TRACE_EVENT(sched_prepare_exec, TP_PROTO(struct task_struct *task, struct linux_binprm *bprm), TP_ARGS(task, bprm), TP_STRUCT__entry( __string( interp, bprm->interp ) __string( filename, bprm->filename ) __field( pid_t, pid ) __string( comm, task->comm ) ), TP_fast_assign( __assign_str(interp); __assign_str(filename); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("interp=%s filename=%s pid=%d comm=%s", __get_str(interp), __get_str(filename), __entry->pid, __get_str(comm)) ); #ifdef CONFIG_SCHEDSTATS #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS #else #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT_NOP #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS_NOP #endif /* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ DECLARE_EVENT_CLASS_SCHEDSTAT(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(__perf_task(tsk), __perf_count(delay)), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( u64, delay ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->delay = delay; ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", __get_str(comm), __entry->pid, (unsigned long long)__entry->delay) ); /* * Tracepoint for accounting wait time (time the task is runnable * but not actually running due to scheduler contention). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_wait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting sleep time (time the task is not runnable, * including iowait, see below). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_sleep, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting iowait time (time the task is not runnable * due to waiting on IO to complete). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_iowait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting blocked time (time the task is in uninterruptible). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ DECLARE_EVENT_CLASS(sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, __perf_count(runtime)), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( u64, runtime ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->runtime = runtime; ), TP_printk("comm=%s pid=%d runtime=%Lu [ns]", __get_str(comm), __entry->pid, (unsigned long long)__entry->runtime) ); DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, runtime)); /* * Tracepoint for showing priority inheritance modifying a tasks * priority. */ TRACE_EVENT(sched_pi_setprio, TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task), TP_ARGS(tsk, pi_task), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( int, oldprio ) __field( int, newprio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->oldprio = tsk->prio; __entry->newprio = pi_task ? min(tsk->normal_prio, pi_task->prio) : tsk->normal_prio; /* XXX SCHED_DEADLINE bits missing */ ), TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", __get_str(comm), __entry->pid, __entry->oldprio, __entry->newprio) ); #ifdef CONFIG_DETECT_HUNG_TASK TRACE_EVENT(sched_process_hang, TP_PROTO(struct task_struct *tsk), TP_ARGS(tsk), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; ), TP_printk("comm=%s pid=%d", __get_str(comm), __entry->pid) ); #endif /* CONFIG_DETECT_HUNG_TASK */ #ifdef CONFIG_NUMA_BALANCING /* * Tracks migration of tasks from one runqueue to another. Can be used to * detect if automatic NUMA balancing is bouncing between nodes. */ TRACE_EVENT(sched_move_numa, TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), TP_ARGS(tsk, src_cpu, dst_cpu), TP_STRUCT__entry( __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_cpu = dst_cpu; __entry->dst_nid = cpu_to_node(dst_cpu); ), TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", __entry->pid, __entry->tgid, __entry->ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_cpu, __entry->dst_nid) ); DECLARE_EVENT_CLASS(sched_numa_pair_template, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), TP_STRUCT__entry( __field( pid_t, src_pid ) __field( pid_t, src_tgid ) __field( pid_t, src_ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( pid_t, dst_pid ) __field( pid_t, dst_tgid ) __field( pid_t, dst_ngid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->src_pid = task_pid_nr(src_tsk); __entry->src_tgid = task_tgid_nr(src_tsk); __entry->src_ngid = task_numa_group_id(src_tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0; __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0; __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0; __entry->dst_cpu = dst_cpu; __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1; ), TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", __entry->src_pid, __entry->src_tgid, __entry->src_ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, __entry->dst_cpu, __entry->dst_nid) ); DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); #define NUMAB_SKIP_REASON \ EM( NUMAB_SKIP_UNSUITABLE, "unsuitable" ) \ EM( NUMAB_SKIP_SHARED_RO, "shared_ro" ) \ EM( NUMAB_SKIP_INACCESSIBLE, "inaccessible" ) \ EM( NUMAB_SKIP_SCAN_DELAY, "scan_delay" ) \ EM( NUMAB_SKIP_PID_INACTIVE, "pid_inactive" ) \ EM( NUMAB_SKIP_IGNORE_PID, "ignore_pid_inactive" ) \ EMe(NUMAB_SKIP_SEQ_COMPLETED, "seq_completed" ) /* Redefine for export. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); NUMAB_SKIP_REASON /* Redefine for symbolic printing. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } TRACE_EVENT(sched_skip_vma_numa, TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma, enum numa_vmaskip_reason reason), TP_ARGS(mm, vma, reason), TP_STRUCT__entry( __field(unsigned long, numa_scan_offset) __field(unsigned long, vm_start) __field(unsigned long, vm_end) __field(enum numa_vmaskip_reason, reason) ), TP_fast_assign( __entry->numa_scan_offset = mm->numa_scan_offset; __entry->vm_start = vma->vm_start; __entry->vm_end = vma->vm_end; __entry->reason = reason; ), TP_printk("numa_scan_offset=%lX vm_start=%lX vm_end=%lX reason=%s", __entry->numa_scan_offset, __entry->vm_start, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); TRACE_EVENT(sched_skip_cpuset_numa, TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr), TP_ARGS(tsk, mem_allowed_ptr), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __array( unsigned long, mem_allowed, BITS_TO_LONGS(MAX_NUMNODES)) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); BUILD_BUG_ON(sizeof(nodemask_t) != \ BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long)); memcpy(__entry->mem_allowed, mem_allowed_ptr->bits, sizeof(__entry->mem_allowed)); ), TP_printk("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl", __entry->comm, __entry->pid, __entry->tgid, __entry->ngid, MAX_NUMNODES, __entry->mem_allowed) ); #endif /* CONFIG_NUMA_BALANCING */ /* * Tracepoint for waking a polling cpu without an IPI. */ TRACE_EVENT(sched_wake_idle_without_ipi, TP_PROTO(int cpu), TP_ARGS(cpu), TP_STRUCT__entry( __field( int, cpu ) ), TP_fast_assign( __entry->cpu = cpu; ), TP_printk("cpu=%d", __entry->cpu) ); /* * Following tracepoints are not exported in tracefs and provide hooking * mechanisms only for testing and debugging purposes. */ DECLARE_TRACE(pelt_cfs, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(pelt_rt, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_dl, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_hw, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_irq, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_se, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_cpu_capacity, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(sched_overutilized, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); DECLARE_TRACE(sched_util_est_cfs, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(sched_util_est_se, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_update_nr_running, TP_PROTO(struct rq *rq, int change), TP_ARGS(rq, change)); DECLARE_TRACE(sched_compute_energy, TP_PROTO(struct task_struct *p, int dst_cpu, unsigned long energy, unsigned long max_util, unsigned long busy_time), TP_ARGS(p, dst_cpu, energy, max_util, busy_time)); DECLARE_TRACE(sched_entry, TP_PROTO(bool preempt), TP_ARGS(preempt)); DECLARE_TRACE(sched_exit, TP_PROTO(bool is_switch), TP_ARGS(is_switch)); DECLARE_TRACE_CONDITION(sched_set_state, TP_PROTO(struct task_struct *tsk, int state), TP_ARGS(tsk, state), TP_CONDITION(!!(tsk->__state) != !!state)); DECLARE_TRACE(sched_set_need_resched, TP_PROTO(struct task_struct *tsk, int cpu, int tif), TP_ARGS(tsk, cpu, tif)); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | /* SPDX-License-Identifier: GPL-2.0 */ /* * RT Mutexes: blocking mutual exclusion locks with PI support * * started by Ingo Molnar and Thomas Gleixner: * * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * This file contains the private data structure and API definitions. */ #ifndef __KERNEL_RTMUTEX_COMMON_H #define __KERNEL_RTMUTEX_COMMON_H #include <linux/debug_locks.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> /* * This is a helper for the struct rt_mutex_waiter below. A waiter goes in two * separate trees and they need their own copy of the sort keys because of * different locking requirements. * * @entry: rbtree node to enqueue into the waiters tree * @prio: Priority of the waiter * @deadline: Deadline of the waiter if applicable * * See rt_waiter_node_less() and waiter_*_prio(). */ struct rt_waiter_node { struct rb_node entry; int prio; u64 deadline; }; /* * This is the control structure for tasks blocked on a rt_mutex, * which is allocated on the kernel stack on of the blocked task. * * @tree: node to enqueue into the mutex waiters tree * @pi_tree: node to enqueue into the mutex owner waiters tree * @task: task reference to the blocked task * @lock: Pointer to the rt_mutex on which the waiter blocks * @wake_state: Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT) * @ww_ctx: WW context pointer * * @tree is ordered by @lock->wait_lock * @pi_tree is ordered by rt_mutex_owner(@lock)->pi_lock */ struct rt_mutex_waiter { struct rt_waiter_node tree; struct rt_waiter_node pi_tree; struct task_struct *task; struct rt_mutex_base *lock; unsigned int wake_state; struct ww_acquire_ctx *ww_ctx; }; /** * struct rt_wake_q_head - Wrapper around regular wake_q_head to support * "sleeping" spinlocks on RT * @head: The regular wake_q_head for sleeping lock variants * @rtlock_task: Task pointer for RT lock (spin/rwlock) wakeups */ struct rt_wake_q_head { struct wake_q_head head; struct task_struct *rtlock_task; }; #define DEFINE_RT_WAKE_Q(name) \ struct rt_wake_q_head name = { \ .head = WAKE_Q_HEAD_INITIALIZER(name.head), \ .rtlock_task = NULL, \ } /* * PI-futex support (proxy locking functions, etc.): */ extern void rt_mutex_init_proxy_locked(struct rt_mutex_base *lock, struct task_struct *proxy_owner); extern void rt_mutex_proxy_unlock(struct rt_mutex_base *lock); extern int __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task, struct wake_q_head *); extern int rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); extern int rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter); extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_futex_trylock(struct rt_mutex_base *l); extern int __rt_mutex_futex_trylock(struct rt_mutex_base *l); extern void rt_mutex_futex_unlock(struct rt_mutex_base *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex_base *lock, struct rt_wake_q_head *wqh); extern void rt_mutex_postunlock(struct rt_wake_q_head *wqh); /* * Must be guarded because this header is included from rcu/tree_plugin.h * unconditionally. */ #ifdef CONFIG_RT_MUTEXES static inline int rt_mutex_has_waiters(struct rt_mutex_base *lock) { return !RB_EMPTY_ROOT(&lock->waiters.rb_root); } /* * Lockless speculative check whether @waiter is still the top waiter on * @lock. This is solely comparing pointers and not derefencing the * leftmost entry which might be about to vanish. */ static inline bool rt_mutex_waiter_is_top_waiter(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) { struct rb_node *leftmost = rb_first_cached(&lock->waiters); return rb_entry(leftmost, struct rt_mutex_waiter, tree.entry) == waiter; } static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock) { struct rb_node *leftmost = rb_first_cached(&lock->waiters); struct rt_mutex_waiter *w = NULL; lockdep_assert_held(&lock->wait_lock); if (leftmost) { w = rb_entry(leftmost, struct rt_mutex_waiter, tree.entry); BUG_ON(w->lock != lock); } return w; } static inline int task_has_pi_waiters(struct task_struct *p) { return !RB_EMPTY_ROOT(&p->pi_waiters.rb_root); } static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p) { lockdep_assert_held(&p->pi_lock); return rb_entry(p->pi_waiters.rb_leftmost, struct rt_mutex_waiter, pi_tree.entry); } /* * Constants for rt mutex functions which have a selectable deadlock * detection. * * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are * no further PI adjustments to be made. * * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full * walk of the lock chain. */ enum rtmutex_chainwalk { RT_MUTEX_MIN_CHAINWALK, RT_MUTEX_FULL_CHAINWALK, }; static inline void __rt_mutex_base_init(struct rt_mutex_base *lock) { raw_spin_lock_init(&lock->wait_lock); lock->waiters = RB_ROOT_CACHED; lock->owner = NULL; } /* Debug functions */ static inline void debug_rt_mutex_unlock(struct rt_mutex_base *lock) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current); } static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)); } static inline void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) memset(waiter, 0x11, sizeof(*waiter)); } static inline void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) memset(waiter, 0x22, sizeof(*waiter)); } static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) { debug_rt_mutex_init_waiter(waiter); RB_CLEAR_NODE(&waiter->pi_tree.entry); RB_CLEAR_NODE(&waiter->tree.entry); waiter->wake_state = TASK_NORMAL; waiter->task = NULL; } static inline void rt_mutex_init_rtlock_waiter(struct rt_mutex_waiter *waiter) { rt_mutex_init_waiter(waiter); waiter->wake_state = TASK_RTLOCK_WAIT; } #else /* CONFIG_RT_MUTEXES */ /* Used in rcu/tree_plugin.h */ static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock) { return NULL; } #endif /* !CONFIG_RT_MUTEXES */ #endif |
| 53 2 3 48 50 50 48 48 47 47 47 46 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 * Phillip Lougher <phillip@squashfs.org.uk> * * xz_wrapper.c */ #include <linux/mutex.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/xz.h> #include <linux/bitops.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" #include "page_actor.h" struct squashfs_xz { struct xz_dec *state; struct xz_buf buf; }; struct disk_comp_opts { __le32 dictionary_size; __le32 flags; }; struct comp_opts { int dict_size; }; static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, void *buff, int len) { struct disk_comp_opts *comp_opts = buff; struct comp_opts *opts; int err = 0, n; opts = kmalloc(sizeof(*opts), GFP_KERNEL); if (opts == NULL) { err = -ENOMEM; goto out2; } if (comp_opts) { /* check compressor options are the expected length */ if (len < sizeof(*comp_opts)) { err = -EIO; goto out; } opts->dict_size = le32_to_cpu(comp_opts->dictionary_size); /* the dictionary size should be 2^n or 2^n+2^(n+1) */ n = ffs(opts->dict_size) - 1; if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) + (1 << (n + 1))) { err = -EIO; goto out; } } else /* use defaults */ opts->dict_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); return opts; out: kfree(opts); out2: return ERR_PTR(err); } static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff) { struct comp_opts *comp_opts = buff; struct squashfs_xz *stream; int err; stream = kmalloc(sizeof(*stream), GFP_KERNEL); if (stream == NULL) { err = -ENOMEM; goto failed; } stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size); if (stream->state == NULL) { kfree(stream); err = -ENOMEM; goto failed; } return stream; failed: ERROR("Failed to initialise xz decompressor\n"); return ERR_PTR(err); } static void squashfs_xz_free(void *strm) { struct squashfs_xz *stream = strm; if (stream) { xz_dec_end(stream->state); kfree(stream); } } static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, struct bio *bio, int offset, int length, struct squashfs_page_actor *output) { struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); int total = 0, error = 0; struct squashfs_xz *stream = strm; xz_dec_reset(stream->state); stream->buf.in_pos = 0; stream->buf.in_size = 0; stream->buf.out_pos = 0; stream->buf.out_size = PAGE_SIZE; stream->buf.out = squashfs_first_page(output); if (IS_ERR(stream->buf.out)) { error = PTR_ERR(stream->buf.out); goto finish; } for (;;) { enum xz_ret xz_err; if (stream->buf.in_pos == stream->buf.in_size) { const void *data; int avail; if (!bio_next_segment(bio, &iter_all)) { /* XZ_STREAM_END must be reached. */ error = -EIO; break; } avail = min(length, ((int)bvec->bv_len) - offset); data = bvec_virt(bvec); length -= avail; stream->buf.in = data + offset; stream->buf.in_size = avail; stream->buf.in_pos = 0; offset = 0; } if (stream->buf.out_pos == stream->buf.out_size) { stream->buf.out = squashfs_next_page(output); if (IS_ERR(stream->buf.out)) { error = PTR_ERR(stream->buf.out); break; } else if (stream->buf.out != NULL) { stream->buf.out_pos = 0; total += PAGE_SIZE; } } xz_err = xz_dec_run(stream->state, &stream->buf); if (xz_err == XZ_STREAM_END) break; if (xz_err != XZ_OK) { error = -EIO; break; } } finish: squashfs_finish_page(output); return error ? error : total + stream->buf.out_pos; } const struct squashfs_decompressor squashfs_xz_comp_ops = { .init = squashfs_xz_init, .comp_opts = squashfs_xz_comp_opts, .free = squashfs_xz_free, .decompress = squashfs_xz_uncompress, .id = XZ_COMPRESSION, .name = "xz", .alloc_buffer = 1, .supported = 1 }; |
| 106 93 180 181 178 1392 1308 179 1305 185 1307 1311 1305 109 111 111 112 110 1 9 2 1 2 12 2 4 1 8 3 8 1 1 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "tctx.h" static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, struct task_struct *task) { struct io_wq_hash *hash; struct io_wq_data data; unsigned int concurrency; mutex_lock(&ctx->uring_lock); hash = ctx->hash_map; if (!hash) { hash = kzalloc(sizeof(*hash), GFP_KERNEL); if (!hash) { mutex_unlock(&ctx->uring_lock); return ERR_PTR(-ENOMEM); } refcount_set(&hash->refs, 1); init_waitqueue_head(&hash->wait); ctx->hash_map = hash; } mutex_unlock(&ctx->uring_lock); data.hash = hash; data.task = task; /* Do QD, or 4 * CPUS, whatever is smallest */ concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); return io_wq_create(concurrency, &data); } void __io_uring_free(struct task_struct *tsk) { struct io_uring_task *tctx = tsk->io_uring; struct io_tctx_node *node; unsigned long index; /* * Fault injection forcing allocation errors in the xa_store() path * can lead to xa_empty() returning false, even though no actual * node is stored in the xarray. Until that gets sorted out, attempt * an iteration here and warn if any entries are found. */ xa_for_each(&tctx->xa, index, node) { WARN_ON_ONCE(1); break; } WARN_ON_ONCE(tctx->io_wq); WARN_ON_ONCE(tctx->cached_refs); percpu_counter_destroy(&tctx->inflight); kfree(tctx); tsk->io_uring = NULL; } __cold int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); if (unlikely(!tctx)) return -ENOMEM; ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL); if (unlikely(ret)) { kfree(tctx); return ret; } tctx->io_wq = io_init_wq_offload(ctx, task); if (IS_ERR(tctx->io_wq)) { ret = PTR_ERR(tctx->io_wq); percpu_counter_destroy(&tctx->inflight); kfree(tctx); return ret; } tctx->task = task; xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_cancel, 0); atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; init_llist_head(&tctx->task_list); init_task_work(&tctx->task_work, tctx_task_work); return 0; } int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; int ret; if (unlikely(!tctx)) { ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) return ret; tctx = current->io_uring; if (ctx->iowq_limits_set) { unsigned int limits[2] = { ctx->iowq_limits[0], ctx->iowq_limits[1], }; ret = io_wq_max_workers(tctx->io_wq, limits); if (ret) return ret; } } if (!xa_load(&tctx->xa, (unsigned long)ctx)) { node = kmalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->ctx = ctx; node->task = current; ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, node, GFP_KERNEL)); if (ret) { kfree(node); return ret; } mutex_lock(&ctx->tctx_lock); list_add(&node->ctx_node, &ctx->tctx_list); mutex_unlock(&ctx->tctx_lock); } return 0; } int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx) { int ret; if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && ctx->submitter_task != current) return -EEXIST; ret = __io_uring_add_tctx_node(ctx); if (ret) return ret; current->io_uring->last = ctx; return 0; } /* * Remove this io_uring_file -> task mapping. */ __cold void io_uring_del_tctx_node(unsigned long index) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; if (!tctx) return; node = xa_erase(&tctx->xa, index); if (!node) return; WARN_ON_ONCE(current != node->task); WARN_ON_ONCE(list_empty(&node->ctx_node)); mutex_lock(&node->ctx->tctx_lock); list_del(&node->ctx_node); mutex_unlock(&node->ctx->tctx_lock); if (tctx->last == node->ctx) tctx->last = NULL; kfree(node); } __cold void io_uring_clean_tctx(struct io_uring_task *tctx) { struct io_wq *wq = tctx->io_wq; struct io_tctx_node *node; unsigned long index; xa_for_each(&tctx->xa, index, node) { io_uring_del_tctx_node(index); cond_resched(); } if (wq) { /* * Must be after io_uring_del_tctx_node() (removes nodes under * uring_lock) to avoid race with io_uring_try_cancel_iowq(). */ io_wq_put_and_exit(wq); tctx->io_wq = NULL; } } void io_uring_unreg_ringfd(void) { struct io_uring_task *tctx = current->io_uring; int i; for (i = 0; i < IO_RINGFD_REG_MAX; i++) { if (tctx->registered_rings[i]) { fput(tctx->registered_rings[i]); tctx->registered_rings[i] = NULL; } } } int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, int start, int end) { int offset; for (offset = start; offset < end; offset++) { offset = array_index_nospec(offset, IO_RINGFD_REG_MAX); if (tctx->registered_rings[offset]) continue; tctx->registered_rings[offset] = file; return offset; } return -EBUSY; } static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, int start, int end) { struct file *file; int offset; file = fget(fd); if (!file) { return -EBADF; } else if (!io_is_uring_fops(file)) { fput(file); return -EOPNOTSUPP; } offset = io_ring_add_registered_file(tctx, file, start, end); if (offset < 0) fput(file); return offset; } /* * Register a ring fd to avoid fdget/fdput for each io_uring_enter() * invocation. User passes in an array of struct io_uring_rsrc_update * with ->data set to the ring_fd, and ->offset given for the desired * index. If no index is desired, application may set ->offset == -1U * and we'll find an available index. Returns number of entries * successfully processed, or < 0 on error if none were processed. */ int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args) { struct io_uring_rsrc_update __user *arg = __arg; struct io_uring_rsrc_update reg; struct io_uring_task *tctx; int ret, i; if (!nr_args || nr_args > IO_RINGFD_REG_MAX) return -EINVAL; mutex_unlock(&ctx->uring_lock); ret = __io_uring_add_tctx_node(ctx); mutex_lock(&ctx->uring_lock); if (ret) return ret; tctx = current->io_uring; for (i = 0; i < nr_args; i++) { int start, end; if (copy_from_user(®, &arg[i], sizeof(reg))) { ret = -EFAULT; break; } if (reg.resv) { ret = -EINVAL; break; } if (reg.offset == -1U) { start = 0; end = IO_RINGFD_REG_MAX; } else { if (reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } start = reg.offset; end = start + 1; } ret = io_ring_add_registered_fd(tctx, reg.data, start, end); if (ret < 0) break; reg.offset = ret; if (copy_to_user(&arg[i], ®, sizeof(reg))) { fput(tctx->registered_rings[reg.offset]); tctx->registered_rings[reg.offset] = NULL; ret = -EFAULT; break; } } return i ? i : ret; } int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args) { struct io_uring_rsrc_update __user *arg = __arg; struct io_uring_task *tctx = current->io_uring; struct io_uring_rsrc_update reg; int ret = 0, i; if (!nr_args || nr_args > IO_RINGFD_REG_MAX) return -EINVAL; if (!tctx) return 0; for (i = 0; i < nr_args; i++) { if (copy_from_user(®, &arg[i], sizeof(reg))) { ret = -EFAULT; break; } if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } reg.offset = array_index_nospec(reg.offset, IO_RINGFD_REG_MAX); if (tctx->registered_rings[reg.offset]) { fput(tctx->registered_rings[reg.offset]); tctx->registered_rings[reg.offset] = NULL; } } return i ? i : ret; } |
| 69 61 187 186 3 187 1038 51 240 239 11 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NDISC_H #define _NDISC_H #include <net/ipv6_stubs.h> /* * ICMP codes for neighbour discovery messages */ #define NDISC_ROUTER_SOLICITATION 133 #define NDISC_ROUTER_ADVERTISEMENT 134 #define NDISC_NEIGHBOUR_SOLICITATION 135 #define NDISC_NEIGHBOUR_ADVERTISEMENT 136 #define NDISC_REDIRECT 137 /* * Router type: cross-layer information from link-layer to * IPv6 layer reported by certain link types (e.g., RFC4214). */ #define NDISC_NODETYPE_UNSPEC 0 /* unspecified (default) */ #define NDISC_NODETYPE_HOST 1 /* host or unauthorized router */ #define NDISC_NODETYPE_NODEFAULT 2 /* non-default router */ #define NDISC_NODETYPE_DEFAULT 3 /* default router */ /* * ndisc options */ enum { __ND_OPT_PREFIX_INFO_END = 0, ND_OPT_SOURCE_LL_ADDR = 1, /* RFC2461 */ ND_OPT_TARGET_LL_ADDR = 2, /* RFC2461 */ ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ ND_OPT_PREF64 = 38, /* RFC8781 */ __ND_OPT_MAX }; #define MAX_RTR_SOLICITATION_DELAY HZ #define ND_REACHABLE_TIME (30*HZ) #define ND_RETRANS_TIMER HZ #include <linux/compiler.h> #include <linux/icmpv6.h> #include <linux/in6.h> #include <linux/types.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/hash.h> #include <net/neighbour.h> struct ctl_table; struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; struct prefix_info; extern struct neigh_table nd_tbl; struct nd_msg { struct icmp6hdr icmph; struct in6_addr target; __u8 opt[]; }; struct rs_msg { struct icmp6hdr icmph; __u8 opt[]; }; struct ra_msg { struct icmp6hdr icmph; __be32 reachable_time; __be32 retrans_timer; }; struct rd_msg { struct icmp6hdr icmph; struct in6_addr target; struct in6_addr dest; __u8 opt[]; }; struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; } __packed; /* ND options */ struct ndisc_options { struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; #ifdef CONFIG_IPV6_ROUTE_INFO struct nd_opt_hdr *nd_opts_ri; struct nd_opt_hdr *nd_opts_ri_end; #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; #endif }; #define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] #define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] #define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 /* * This structure defines the hooks for IPv6 neighbour discovery. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): * This function is called while parsing ndisc ops and put each position * as pointer into ndopts. If this function return unequal 0, then this * function took care about the ndisc option, if 0 then the IPv6 ndisc * option parser will take care about that option. * * void (*update)(const struct net_device *dev, struct neighbour *n, * u32 flags, u8 icmp6_type, * const struct ndisc_options *ndopts): * This function is called when IPv6 ndisc updates the neighbour cache * entry. Additional options which can be updated may be previously * parsed by parse_opts callback and accessible over ndopts parameter. * * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, * struct neighbour *neigh, u8 *ha_buf, * u8 **ha): * This function is called when the necessary option space will be * calculated before allocating a skb. The parameters neigh, ha_buf * abd ha are available on NDISC_REDIRECT messages only. * * void (*fill_addr_option)(const struct net_device *dev, * struct sk_buff *skb, u8 icmp6_type, * const u8 *ha): * This function is called when the skb will finally fill the option * fields inside skb. NOTE: this callback should fill the option * fields to the skb which are previously indicated by opt_space * parameter. That means the decision to add such option should * not lost between these two callbacks, e.g. protected by interface * up state. * * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, * const struct prefix_info *pinfo, * struct inet6_dev *in6_dev, * struct in6_addr *addr, * int addr_type, u32 addr_flags, * bool sllao, bool tokenized, * __u32 valid_lft, u32 prefered_lft, * bool dev_addr_generated): * This function is called when a RA messages is received with valid * PIO option fields and an IPv6 address will be added to the interface * for autoconfiguration. The parameter dev_addr_generated reports about * if the address was based on dev->dev_addr or not. This can be used * to add a second address if link-layer operates with two link layer * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); void (*update)(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts); int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, struct neighbour *neigh, u8 *ha_buf, u8 **ha); void (*fill_addr_option)(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type, const u8 *ha); void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated); }; #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->parse_options) return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); else return 0; } static inline void ndisc_ops_update(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->update) dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); } static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && icmp6_type != NDISC_REDIRECT) return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, NULL, NULL); else return 0; } static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, struct neighbour *neigh, u8 *ha_buf, u8 **ha) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, neigh, ha_buf, ha); else return 0; } static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && icmp6_type != NDISC_REDIRECT) dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); } static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, struct sk_buff *skb, const u8 *ha) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); } static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated) { if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } #endif /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may * also need a pad of 2. */ static inline int ndisc_addr_option_pad(unsigned short type) { switch (type) { case ARPHRD_INFINIBAND: return 2; default: return 0; } } static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) { return NDISC_OPT_SPACE(addr_len + pad); } #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_opt_addr_space(dev, icmp6_type); } static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, struct neighbour *neigh, u8 *ops_data_buf, u8 **ops_data) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, ops_data); } #endif static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, struct net_device *dev) { return __ndisc_opt_addr_data(p, dev->addr_len, ndisc_addr_option_pad(dev->type)); } static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; return (((p32[0] ^ hash32_ptr(dev)) * hash_rnd[0]) + (p32[1] * hash_rnd[1]) + (p32[2] * hash_rnd[2]) + (p32[3] * hash_rnd[3])); } static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static inline void __ipv6_confirm_neigh(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); neigh_confirm(n); rcu_read_unlock(); } static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(dev, pkey); neigh_confirm(n); rcu_read_unlock(); } /* uses ipv6_stub and is meant for use outside of IPv6 core */ static inline struct neighbour *ip_neigh_gw6(struct net_device *dev, const void *addr) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref_stub(dev, addr); if (unlikely(!neigh)) neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false); return neigh; } int ndisc_init(void); int ndisc_late_init(void); void ndisc_late_cleanup(void); void ndisc_cleanup(void); enum skb_drop_reason ndisc_rcv(struct sk_buff *skb); struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce); void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts); /* * IGMP */ int igmp6_init(void); int igmp6_late_init(void); void igmp6_cleanup(void); void igmp6_late_cleanup(void); void igmp6_event_query(struct sk_buff *skb); void igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif void inet6_ifinfo_notify(int event, struct inet6_dev *idev); #endif |
| 5 1 4 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2021 NXP */ #include "netlink.h" #include "common.h" struct phc_vclocks_req_info { struct ethnl_req_info base; }; struct phc_vclocks_reply_data { struct ethnl_reply_data base; int num; int *index; }; #define PHC_VCLOCKS_REPDATA(__reply_base) \ container_of(__reply_base, struct phc_vclocks_reply_data, base) const struct nla_policy ethnl_phc_vclocks_get_policy[] = { [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->num = ethtool_get_phc_vclocks(dev, &data->index); ethnl_ops_complete(dev); return ret; } static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); int len = 0; if (data->num > 0) { len += nla_total_size(sizeof(u32)); len += nla_total_size(sizeof(s32) * data->num); } return len; } static int phc_vclocks_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); if (data->num <= 0) return 0; if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) || nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX, sizeof(s32) * data->num, data->index)) return -EMSGSIZE; return 0; } static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); kfree(data->index); } const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = { .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER, .req_info_size = sizeof(struct phc_vclocks_req_info), .reply_data_size = sizeof(struct phc_vclocks_reply_data), .prepare_data = phc_vclocks_prepare_data, .reply_size = phc_vclocks_reply_size, .fill_reply = phc_vclocks_fill_reply, .cleanup_data = phc_vclocks_cleanup_data, }; |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 | // SPDX-License-Identifier: GPL-2.0+ /* * LEGO USB Tower driver * * Copyright (C) 2003 David Glance <davidgsf@sourceforge.net> * 2001-2004 Juergen Stuber <starblue@users.sourceforge.net> * * derived from USB Skeleton driver - 0.5 * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com) * * History: * * 2001-10-13 - 0.1 js * - first version * 2001-11-03 - 0.2 js * - simplified buffering, one-shot URBs for writing * 2001-11-10 - 0.3 js * - removed IOCTL (setting power/mode is more complicated, postponed) * 2001-11-28 - 0.4 js * - added vendor commands for mode of operation and power level in open * 2001-12-04 - 0.5 js * - set IR mode by default (by oversight 0.4 set VLL mode) * 2002-01-11 - 0.5? pcchan * - make read buffer reusable and work around bytes_to_write issue between * uhci and legusbtower * 2002-09-23 - 0.52 david (david@csse.uwa.edu.au) * - imported into lejos project * - changed wake_up to wake_up_interruptible * - changed to use lego0 rather than tower0 * - changed dbg() to use __func__ rather than deprecated __func__ * 2003-01-12 - 0.53 david (david@csse.uwa.edu.au) * - changed read and write to write everything or * timeout (from a patch by Chris Riesen and Brett Thaeler driver) * - added ioctl functionality to set timeouts * 2003-07-18 - 0.54 davidgsf (david@csse.uwa.edu.au) * - initial import into LegoUSB project * - merge of existing LegoUSB.c driver * 2003-07-18 - 0.56 davidgsf (david@csse.uwa.edu.au) * - port to 2.6 style driver * 2004-02-29 - 0.6 Juergen Stuber <starblue@users.sourceforge.net> * - fix locking * - unlink read URBs which are no longer needed * - allow increased buffer size, eliminates need for timeout on write * - have read URB running continuously * - added poll * - forbid seeking * - added nonblocking I/O * - changed back __func__ to __func__ * - read and log tower firmware version * - reset tower on probe, avoids failure of first write * 2004-03-09 - 0.7 Juergen Stuber <starblue@users.sourceforge.net> * - timeout read now only after inactivity, shorten default accordingly * 2004-03-11 - 0.8 Juergen Stuber <starblue@users.sourceforge.net> * - log major, minor instead of possibly confusing device filename * - whitespace cleanup * 2004-03-12 - 0.9 Juergen Stuber <starblue@users.sourceforge.net> * - normalize whitespace in debug messages * - take care about endianness in control message responses * 2004-03-13 - 0.91 Juergen Stuber <starblue@users.sourceforge.net> * - make default intervals longer to accommodate current EHCI driver * 2004-03-19 - 0.92 Juergen Stuber <starblue@users.sourceforge.net> * - replaced atomic_t by memory barriers * 2004-04-21 - 0.93 Juergen Stuber <starblue@users.sourceforge.net> * - wait for completion of write urb in release (needed for remotecontrol) * - corrected poll for write direction (missing negation) * 2004-04-22 - 0.94 Juergen Stuber <starblue@users.sourceforge.net> * - make device locking interruptible * 2004-04-30 - 0.95 Juergen Stuber <starblue@users.sourceforge.net> * - check for valid udev on resubmitting and unlinking urbs * 2004-08-03 - 0.96 Juergen Stuber <starblue@users.sourceforge.net> * - move reset into open to clean out spurious data */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/completion.h> #include <linux/mutex.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/poll.h> #define DRIVER_AUTHOR "Juergen Stuber <starblue@sourceforge.net>" #define DRIVER_DESC "LEGO USB Tower Driver" /* The defaults are chosen to work with the latest versions of leJOS and NQC. */ /* Some legacy software likes to receive packets in one piece. * In this case read_buffer_size should exceed the maximal packet length * (417 for datalog uploads), and packet_timeout should be set. */ static int read_buffer_size = 480; module_param(read_buffer_size, int, 0); MODULE_PARM_DESC(read_buffer_size, "Read buffer size"); /* Some legacy software likes to send packets in one piece. * In this case write_buffer_size should exceed the maximal packet length * (417 for firmware and program downloads). * A problem with long writes is that the following read may time out * if the software is not prepared to wait long enough. */ static int write_buffer_size = 480; module_param(write_buffer_size, int, 0); MODULE_PARM_DESC(write_buffer_size, "Write buffer size"); /* Some legacy software expects reads to contain whole LASM packets. * To achieve this, characters which arrive before a packet timeout * occurs will be returned in a single read operation. * A problem with long reads is that the software may time out * if it is not prepared to wait long enough. * The packet timeout should be greater than the time between the * reception of subsequent characters, which should arrive about * every 5ms for the standard 2400 baud. * Set it to 0 to disable. */ static int packet_timeout = 50; module_param(packet_timeout, int, 0); MODULE_PARM_DESC(packet_timeout, "Packet timeout in ms"); /* Some legacy software expects blocking reads to time out. * Timeout occurs after the specified time of read and write inactivity. * Set it to 0 to disable. */ static int read_timeout = 200; module_param(read_timeout, int, 0); MODULE_PARM_DESC(read_timeout, "Read timeout in ms"); /* As of kernel version 2.6.4 ehci-hcd uses an * "only one interrupt transfer per frame" shortcut * to simplify the scheduling of periodic transfers. * This conflicts with our standard 1ms intervals for in and out URBs. * We use default intervals of 2ms for in and 8ms for out transfers, * which is fast enough for 2400 baud and allows a small additional load. * Increase the interval to allow more devices that do interrupt transfers, * or set to 0 to use the standard interval from the endpoint descriptors. */ static int interrupt_in_interval = 2; module_param(interrupt_in_interval, int, 0); MODULE_PARM_DESC(interrupt_in_interval, "Interrupt in interval in ms"); static int interrupt_out_interval = 8; module_param(interrupt_out_interval, int, 0); MODULE_PARM_DESC(interrupt_out_interval, "Interrupt out interval in ms"); /* Define these values to match your device */ #define LEGO_USB_TOWER_VENDOR_ID 0x0694 #define LEGO_USB_TOWER_PRODUCT_ID 0x0001 /* Vendor requests */ #define LEGO_USB_TOWER_REQUEST_RESET 0x04 #define LEGO_USB_TOWER_REQUEST_GET_VERSION 0xFD struct tower_reset_reply { __le16 size; __u8 err_code; __u8 spare; }; struct tower_get_version_reply { __le16 size; __u8 err_code; __u8 spare; __u8 major; __u8 minor; __le16 build_no; }; /* table of devices that work with this driver */ static const struct usb_device_id tower_table[] = { { USB_DEVICE(LEGO_USB_TOWER_VENDOR_ID, LEGO_USB_TOWER_PRODUCT_ID) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, tower_table); #define LEGO_USB_TOWER_MINOR_BASE 160 /* Structure to hold all of our device specific stuff */ struct lego_usb_tower { struct mutex lock; /* locks this structure */ struct usb_device *udev; /* save off the usb device pointer */ unsigned char minor; /* the starting minor number for this device */ int open_count; /* number of times this port has been opened */ unsigned long disconnected:1; char *read_buffer; size_t read_buffer_length; /* this much came in */ size_t read_packet_length; /* this much will be returned on read */ spinlock_t read_buffer_lock; int packet_timeout_jiffies; unsigned long read_last_arrival; wait_queue_head_t read_wait; wait_queue_head_t write_wait; char *interrupt_in_buffer; struct usb_endpoint_descriptor *interrupt_in_endpoint; struct urb *interrupt_in_urb; int interrupt_in_interval; int interrupt_in_done; char *interrupt_out_buffer; struct usb_endpoint_descriptor *interrupt_out_endpoint; struct urb *interrupt_out_urb; int interrupt_out_interval; int interrupt_out_busy; }; /* local function prototypes */ static ssize_t tower_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos); static ssize_t tower_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos); static inline void tower_delete(struct lego_usb_tower *dev); static int tower_open(struct inode *inode, struct file *file); static int tower_release(struct inode *inode, struct file *file); static __poll_t tower_poll(struct file *file, poll_table *wait); static loff_t tower_llseek(struct file *file, loff_t off, int whence); static void tower_check_for_read_packet(struct lego_usb_tower *dev); static void tower_interrupt_in_callback(struct urb *urb); static void tower_interrupt_out_callback(struct urb *urb); static int tower_probe(struct usb_interface *interface, const struct usb_device_id *id); static void tower_disconnect(struct usb_interface *interface); /* file operations needed when we register this driver */ static const struct file_operations tower_fops = { .owner = THIS_MODULE, .read = tower_read, .write = tower_write, .open = tower_open, .release = tower_release, .poll = tower_poll, .llseek = tower_llseek, }; static char *legousbtower_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "usb/%s", dev_name(dev)); } /* * usb class driver info in order to get a minor number from the usb core, * and to have the device registered with the driver core */ static struct usb_class_driver tower_class = { .name = "legousbtower%d", .devnode = legousbtower_devnode, .fops = &tower_fops, .minor_base = LEGO_USB_TOWER_MINOR_BASE, }; /* usb specific object needed to register this driver with the usb subsystem */ static struct usb_driver tower_driver = { .name = "legousbtower", .probe = tower_probe, .disconnect = tower_disconnect, .id_table = tower_table, }; /* * lego_usb_tower_debug_data */ static inline void lego_usb_tower_debug_data(struct device *dev, const char *function, int size, const unsigned char *data) { dev_dbg(dev, "%s - length = %d, data = %*ph\n", function, size, size, data); } /* * tower_delete */ static inline void tower_delete(struct lego_usb_tower *dev) { /* free data structures */ usb_free_urb(dev->interrupt_in_urb); usb_free_urb(dev->interrupt_out_urb); kfree(dev->read_buffer); kfree(dev->interrupt_in_buffer); kfree(dev->interrupt_out_buffer); usb_put_dev(dev->udev); kfree(dev); } /* * tower_open */ static int tower_open(struct inode *inode, struct file *file) { struct lego_usb_tower *dev = NULL; int subminor; int retval = 0; struct usb_interface *interface; struct tower_reset_reply reset_reply; int result; nonseekable_open(inode, file); subminor = iminor(inode); interface = usb_find_interface(&tower_driver, subminor); if (!interface) { pr_err("error, can't find device for minor %d\n", subminor); retval = -ENODEV; goto exit; } dev = usb_get_intfdata(interface); if (!dev) { retval = -ENODEV; goto exit; } /* lock this device */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* allow opening only once */ if (dev->open_count) { retval = -EBUSY; goto unlock_exit; } /* reset the tower */ result = usb_control_msg_recv(dev->udev, 0, LEGO_USB_TOWER_REQUEST_RESET, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, &reset_reply, sizeof(reset_reply), 1000, GFP_KERNEL); if (result < 0) { dev_err(&dev->udev->dev, "LEGO USB Tower reset control request failed\n"); retval = result; goto unlock_exit; } /* initialize in direction */ dev->read_buffer_length = 0; dev->read_packet_length = 0; usb_fill_int_urb(dev->interrupt_in_urb, dev->udev, usb_rcvintpipe(dev->udev, dev->interrupt_in_endpoint->bEndpointAddress), dev->interrupt_in_buffer, usb_endpoint_maxp(dev->interrupt_in_endpoint), tower_interrupt_in_callback, dev, dev->interrupt_in_interval); dev->interrupt_in_done = 0; mb(); retval = usb_submit_urb(dev->interrupt_in_urb, GFP_KERNEL); if (retval) { dev_err(&dev->udev->dev, "Couldn't submit interrupt_in_urb %d\n", retval); goto unlock_exit; } /* save device in the file's private structure */ file->private_data = dev; dev->open_count = 1; unlock_exit: mutex_unlock(&dev->lock); exit: return retval; } /* * tower_release */ static int tower_release(struct inode *inode, struct file *file) { struct lego_usb_tower *dev; int retval = 0; dev = file->private_data; if (dev == NULL) { retval = -ENODEV; goto exit; } mutex_lock(&dev->lock); if (dev->disconnected) { /* the device was unplugged before the file was released */ /* unlock here as tower_delete frees dev */ mutex_unlock(&dev->lock); tower_delete(dev); goto exit; } /* wait until write transfer is finished */ if (dev->interrupt_out_busy) { wait_event_interruptible_timeout(dev->write_wait, !dev->interrupt_out_busy, 2 * HZ); } /* shutdown transfers */ usb_kill_urb(dev->interrupt_in_urb); usb_kill_urb(dev->interrupt_out_urb); dev->open_count = 0; mutex_unlock(&dev->lock); exit: return retval; } /* * tower_check_for_read_packet * * To get correct semantics for signals and non-blocking I/O * with packetizing we pretend not to see any data in the read buffer * until it has been there unchanged for at least * dev->packet_timeout_jiffies, or until the buffer is full. */ static void tower_check_for_read_packet(struct lego_usb_tower *dev) { spin_lock_irq(&dev->read_buffer_lock); if (!packet_timeout || time_after(jiffies, dev->read_last_arrival + dev->packet_timeout_jiffies) || dev->read_buffer_length == read_buffer_size) { dev->read_packet_length = dev->read_buffer_length; } dev->interrupt_in_done = 0; spin_unlock_irq(&dev->read_buffer_lock); } /* * tower_poll */ static __poll_t tower_poll(struct file *file, poll_table *wait) { struct lego_usb_tower *dev; __poll_t mask = 0; dev = file->private_data; if (dev->disconnected) return EPOLLERR | EPOLLHUP; poll_wait(file, &dev->read_wait, wait); poll_wait(file, &dev->write_wait, wait); tower_check_for_read_packet(dev); if (dev->read_packet_length > 0) mask |= EPOLLIN | EPOLLRDNORM; if (!dev->interrupt_out_busy) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } /* * tower_llseek */ static loff_t tower_llseek(struct file *file, loff_t off, int whence) { return -ESPIPE; /* unseekable */ } /* * tower_read */ static ssize_t tower_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct lego_usb_tower *dev; size_t bytes_to_read; int i; int retval = 0; unsigned long timeout = 0; dev = file->private_data; /* lock this object */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* verify that the device wasn't unplugged */ if (dev->disconnected) { retval = -ENODEV; goto unlock_exit; } /* verify that we actually have some data to read */ if (count == 0) { dev_dbg(&dev->udev->dev, "read request of 0 bytes\n"); goto unlock_exit; } if (read_timeout) timeout = jiffies + msecs_to_jiffies(read_timeout); /* wait for data */ tower_check_for_read_packet(dev); while (dev->read_packet_length == 0) { if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto unlock_exit; } retval = wait_event_interruptible_timeout(dev->read_wait, dev->interrupt_in_done, dev->packet_timeout_jiffies); if (retval < 0) goto unlock_exit; /* reset read timeout during read or write activity */ if (read_timeout && (dev->read_buffer_length || dev->interrupt_out_busy)) { timeout = jiffies + msecs_to_jiffies(read_timeout); } /* check for read timeout */ if (read_timeout && time_after(jiffies, timeout)) { retval = -ETIMEDOUT; goto unlock_exit; } tower_check_for_read_packet(dev); } /* copy the data from read_buffer into userspace */ bytes_to_read = min(count, dev->read_packet_length); if (copy_to_user(buffer, dev->read_buffer, bytes_to_read)) { retval = -EFAULT; goto unlock_exit; } spin_lock_irq(&dev->read_buffer_lock); dev->read_buffer_length -= bytes_to_read; dev->read_packet_length -= bytes_to_read; for (i = 0; i < dev->read_buffer_length; i++) dev->read_buffer[i] = dev->read_buffer[i+bytes_to_read]; spin_unlock_irq(&dev->read_buffer_lock); retval = bytes_to_read; unlock_exit: /* unlock the device */ mutex_unlock(&dev->lock); exit: return retval; } /* * tower_write */ static ssize_t tower_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct lego_usb_tower *dev; size_t bytes_to_write; int retval = 0; dev = file->private_data; /* lock this object */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* verify that the device wasn't unplugged */ if (dev->disconnected) { retval = -ENODEV; goto unlock_exit; } /* verify that we actually have some data to write */ if (count == 0) { dev_dbg(&dev->udev->dev, "write request of 0 bytes\n"); goto unlock_exit; } /* wait until previous transfer is finished */ while (dev->interrupt_out_busy) { if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto unlock_exit; } retval = wait_event_interruptible(dev->write_wait, !dev->interrupt_out_busy); if (retval) goto unlock_exit; } /* write the data into interrupt_out_buffer from userspace */ bytes_to_write = min_t(int, count, write_buffer_size); dev_dbg(&dev->udev->dev, "%s: count = %zd, bytes_to_write = %zd\n", __func__, count, bytes_to_write); if (copy_from_user(dev->interrupt_out_buffer, buffer, bytes_to_write)) { retval = -EFAULT; goto unlock_exit; } /* send off the urb */ usb_fill_int_urb(dev->interrupt_out_urb, dev->udev, usb_sndintpipe(dev->udev, dev->interrupt_out_endpoint->bEndpointAddress), dev->interrupt_out_buffer, bytes_to_write, tower_interrupt_out_callback, dev, dev->interrupt_out_interval); dev->interrupt_out_busy = 1; wmb(); retval = usb_submit_urb(dev->interrupt_out_urb, GFP_KERNEL); if (retval) { dev->interrupt_out_busy = 0; dev_err(&dev->udev->dev, "Couldn't submit interrupt_out_urb %d\n", retval); goto unlock_exit; } retval = bytes_to_write; unlock_exit: /* unlock the device */ mutex_unlock(&dev->lock); exit: return retval; } /* * tower_interrupt_in_callback */ static void tower_interrupt_in_callback(struct urb *urb) { struct lego_usb_tower *dev = urb->context; int status = urb->status; int retval; unsigned long flags; lego_usb_tower_debug_data(&dev->udev->dev, __func__, urb->actual_length, urb->transfer_buffer); if (status) { if (status == -ENOENT || status == -ECONNRESET || status == -ESHUTDOWN) { goto exit; } else { dev_dbg(&dev->udev->dev, "%s: nonzero status received: %d\n", __func__, status); goto resubmit; /* maybe we can recover */ } } if (urb->actual_length > 0) { spin_lock_irqsave(&dev->read_buffer_lock, flags); if (dev->read_buffer_length + urb->actual_length < read_buffer_size) { memcpy(dev->read_buffer + dev->read_buffer_length, dev->interrupt_in_buffer, urb->actual_length); dev->read_buffer_length += urb->actual_length; dev->read_last_arrival = jiffies; dev_dbg(&dev->udev->dev, "%s: received %d bytes\n", __func__, urb->actual_length); } else { pr_warn("read_buffer overflow, %d bytes dropped\n", urb->actual_length); } spin_unlock_irqrestore(&dev->read_buffer_lock, flags); } resubmit: retval = usb_submit_urb(dev->interrupt_in_urb, GFP_ATOMIC); if (retval) { dev_err(&dev->udev->dev, "%s: usb_submit_urb failed (%d)\n", __func__, retval); } exit: dev->interrupt_in_done = 1; wake_up_interruptible(&dev->read_wait); } /* * tower_interrupt_out_callback */ static void tower_interrupt_out_callback(struct urb *urb) { struct lego_usb_tower *dev = urb->context; int status = urb->status; lego_usb_tower_debug_data(&dev->udev->dev, __func__, urb->actual_length, urb->transfer_buffer); /* sync/async unlink faults aren't errors */ if (status && !(status == -ENOENT || status == -ECONNRESET || status == -ESHUTDOWN)) { dev_dbg(&dev->udev->dev, "%s: nonzero write bulk status received: %d\n", __func__, status); } dev->interrupt_out_busy = 0; wake_up_interruptible(&dev->write_wait); } /* * tower_probe * * Called by the usb core when a new device is connected that it thinks * this driver might be interested in. */ static int tower_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct device *idev = &interface->dev; struct usb_device *udev = interface_to_usbdev(interface); struct lego_usb_tower *dev; struct tower_get_version_reply get_version_reply; int retval = -ENOMEM; int result; /* allocate memory for our device state and initialize it */ dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto exit; mutex_init(&dev->lock); dev->udev = usb_get_dev(udev); spin_lock_init(&dev->read_buffer_lock); dev->packet_timeout_jiffies = msecs_to_jiffies(packet_timeout); dev->read_last_arrival = jiffies; init_waitqueue_head(&dev->read_wait); init_waitqueue_head(&dev->write_wait); result = usb_find_common_endpoints_reverse(interface->cur_altsetting, NULL, NULL, &dev->interrupt_in_endpoint, &dev->interrupt_out_endpoint); if (result) { dev_err(idev, "interrupt endpoints not found\n"); retval = result; goto error; } dev->read_buffer = kmalloc(read_buffer_size, GFP_KERNEL); if (!dev->read_buffer) goto error; dev->interrupt_in_buffer = kmalloc(usb_endpoint_maxp(dev->interrupt_in_endpoint), GFP_KERNEL); if (!dev->interrupt_in_buffer) goto error; dev->interrupt_in_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt_in_urb) goto error; dev->interrupt_out_buffer = kmalloc(write_buffer_size, GFP_KERNEL); if (!dev->interrupt_out_buffer) goto error; dev->interrupt_out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt_out_urb) goto error; dev->interrupt_in_interval = interrupt_in_interval ? interrupt_in_interval : dev->interrupt_in_endpoint->bInterval; dev->interrupt_out_interval = interrupt_out_interval ? interrupt_out_interval : dev->interrupt_out_endpoint->bInterval; /* get the firmware version and log it */ result = usb_control_msg_recv(udev, 0, LEGO_USB_TOWER_REQUEST_GET_VERSION, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, &get_version_reply, sizeof(get_version_reply), 1000, GFP_KERNEL); if (result) { dev_err(idev, "get version request failed: %d\n", result); retval = result; goto error; } dev_info(&interface->dev, "LEGO USB Tower firmware version is %d.%d build %d\n", get_version_reply.major, get_version_reply.minor, le16_to_cpu(get_version_reply.build_no)); /* we can register the device now, as it is ready */ usb_set_intfdata(interface, dev); retval = usb_register_dev(interface, &tower_class); if (retval) { /* something prevented us from registering this driver */ dev_err(idev, "Not able to get a minor for this device.\n"); goto error; } dev->minor = interface->minor; /* let the user know what node this device is now attached to */ dev_info(&interface->dev, "LEGO USB Tower #%d now attached to major " "%d minor %d\n", (dev->minor - LEGO_USB_TOWER_MINOR_BASE), USB_MAJOR, dev->minor); exit: return retval; error: tower_delete(dev); return retval; } /* * tower_disconnect * * Called by the usb core when the device is removed from the system. */ static void tower_disconnect(struct usb_interface *interface) { struct lego_usb_tower *dev; int minor; dev = usb_get_intfdata(interface); minor = dev->minor; /* give back our minor and prevent further open() */ usb_deregister_dev(interface, &tower_class); /* stop I/O */ usb_poison_urb(dev->interrupt_in_urb); usb_poison_urb(dev->interrupt_out_urb); mutex_lock(&dev->lock); /* if the device is not opened, then we clean up right now */ if (!dev->open_count) { mutex_unlock(&dev->lock); tower_delete(dev); } else { dev->disconnected = 1; /* wake up pollers */ wake_up_interruptible_all(&dev->read_wait); wake_up_interruptible_all(&dev->write_wait); mutex_unlock(&dev->lock); } dev_info(&interface->dev, "LEGO USB Tower #%d now disconnected\n", (minor - LEGO_USB_TOWER_MINOR_BASE)); } module_usb_driver(tower_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 1475 1481 902 902 902 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * blk-integrity.c - Block layer data integrity extensions * * Copyright (C) 2007, 2008 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> */ #include <linux/blk-integrity.h> #include <linux/backing-dev.h> #include <linux/mempool.h> #include <linux/bio.h> #include <linux/scatterlist.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/t10-pi.h> #include "blk.h" /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements * @q: request queue * @bio: bio with integrity metadata attached * * Description: Returns the number of elements required in a * scatterlist corresponding to the integrity metadata in a bio. */ int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { struct bio_vec iv, ivprv = { NULL }; unsigned int segments = 0; unsigned int seg_size = 0; struct bvec_iter iter; int prev = 0; bio_for_each_integrity_vec(iv, bio, iter) { if (prev) { if (!biovec_phys_mergeable(q, &ivprv, &iv)) goto new_segment; if (seg_size + iv.bv_len > queue_max_segment_size(q)) goto new_segment; seg_size += iv.bv_len; } else { new_segment: segments++; seg_size = iv.bv_len; } prev = 1; ivprv = iv; } return segments; } int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, struct logical_block_metadata_cap __user *argp) { struct blk_integrity *bi; struct logical_block_metadata_cap meta_cap = {}; size_t usize = _IOC_SIZE(cmd); if (!extensible_ioctl_valid(cmd, FS_IOC_GETLBMD_CAP, LBMD_SIZE_VER0)) return -ENOIOCTLCMD; bi = blk_get_integrity(bdev->bd_disk); if (!bi) goto out; if (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) meta_cap.lbmd_flags |= LBMD_PI_CAP_INTEGRITY; if (bi->flags & BLK_INTEGRITY_REF_TAG) meta_cap.lbmd_flags |= LBMD_PI_CAP_REFTAG; meta_cap.lbmd_interval = 1 << bi->interval_exp; meta_cap.lbmd_size = bi->metadata_size; meta_cap.lbmd_pi_size = bi->pi_tuple_size; meta_cap.lbmd_pi_offset = bi->pi_offset; meta_cap.lbmd_opaque_size = bi->metadata_size - bi->pi_tuple_size; if (meta_cap.lbmd_opaque_size && !bi->pi_offset) meta_cap.lbmd_opaque_offset = bi->pi_tuple_size; switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_NONE; break; case BLK_INTEGRITY_CSUM_IP: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_IP; break; case BLK_INTEGRITY_CSUM_CRC: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC16_T10DIF; break; case BLK_INTEGRITY_CSUM_CRC64: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC64_NVME; break; } if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE) meta_cap.lbmd_app_tag_size = 2; if (bi->flags & BLK_INTEGRITY_REF_TAG) { switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_CRC64: meta_cap.lbmd_ref_tag_size = sizeof_field(struct crc64_pi_tuple, ref_tag); break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: meta_cap.lbmd_ref_tag_size = sizeof_field(struct t10_pi_tuple, ref_tag); break; default: break; } } out: return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap), NULL); } int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes) { int ret; struct iov_iter iter; iov_iter_ubuf(&iter, rq_data_dir(rq), ubuf, bytes); ret = bio_integrity_map_user(rq->bio, &iter); if (ret) return ret; rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, rq->bio); rq->cmd_flags |= REQ_INTEGRITY; return 0; } EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user); bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { struct bio_integrity_payload *bip, *bip_next; if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0) return true; if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0) return false; bip = bio_integrity(req->bio); bip_next = bio_integrity(next->bio); if (bip->bip_flags != bip_next->bip_flags) return false; if (bip->bip_flags & BIP_CHECK_APPTAG && bip->app_tag != bip_next->app_tag) return false; if (req->nr_integrity_segments + next->nr_integrity_segments > q->limits.max_integrity_segments) return false; if (integrity_req_gap_back_merge(req, next->bio)) return false; return true; } bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) { struct bio_integrity_payload *bip, *bip_bio = bio_integrity(bio); int nr_integrity_segs; if (blk_integrity_rq(req) == 0 && bip_bio == NULL) return true; if (blk_integrity_rq(req) == 0 || bip_bio == NULL) return false; bip = bio_integrity(req->bio); if (bip->bip_flags != bip_bio->bip_flags) return false; if (bip->bip_flags & BIP_CHECK_APPTAG && bip->app_tag != bip_bio->app_tag) return false; nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); if (req->nr_integrity_segments + nr_integrity_segs > q->limits.max_integrity_segments) return false; return true; } static inline struct blk_integrity *dev_to_bi(struct device *dev) { return &dev_to_disk(dev)->queue->limits.integrity; } const char *blk_integrity_profile_name(struct blk_integrity *bi) { switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_IP: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-IP"; return "T10-DIF-TYPE3-IP"; case BLK_INTEGRITY_CSUM_CRC: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-CRC"; return "T10-DIF-TYPE3-CRC"; case BLK_INTEGRITY_CSUM_CRC64: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "EXT-DIF-TYPE1-CRC64"; return "EXT-DIF-TYPE3-CRC64"; case BLK_INTEGRITY_CSUM_NONE: break; } return "nop"; } EXPORT_SYMBOL_GPL(blk_integrity_profile_name); static ssize_t flag_store(struct device *dev, const char *page, size_t count, unsigned char flag) { struct request_queue *q = dev_to_disk(dev)->queue; struct queue_limits lim; unsigned long val; int err; err = kstrtoul(page, 10, &val); if (err) return err; /* note that the flags are inverted vs the values in the sysfs files */ lim = queue_limits_start_update(q); if (val) lim.integrity.flags &= ~flag; else lim.integrity.flags |= flag; err = queue_limits_commit_update_frozen(q, &lim); if (err) return err; return count; } static ssize_t flag_show(struct device *dev, char *page, unsigned char flag) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%d\n", !(bi->flags & flag)); } static ssize_t format_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); if (!bi->metadata_size) return sysfs_emit(page, "none\n"); return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi)); } static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->tag_size); } static ssize_t protection_interval_bytes_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->interval_exp ? 1 << bi->interval_exp : 0); } static ssize_t read_verify_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY); } static ssize_t read_verify_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY); } static ssize_t write_generate_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE); } static ssize_t write_generate_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE); } static ssize_t device_is_integrity_capable_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } static DEVICE_ATTR_RO(format); static DEVICE_ATTR_RO(tag_size); static DEVICE_ATTR_RO(protection_interval_bytes); static DEVICE_ATTR_RW(read_verify); static DEVICE_ATTR_RW(write_generate); static DEVICE_ATTR_RO(device_is_integrity_capable); static struct attribute *integrity_attrs[] = { &dev_attr_format.attr, &dev_attr_tag_size.attr, &dev_attr_protection_interval_bytes.attr, &dev_attr_read_verify.attr, &dev_attr_write_generate.attr, &dev_attr_device_is_integrity_capable.attr, NULL }; const struct attribute_group blk_integrity_attr_group = { .name = "integrity", .attrs = integrity_attrs, }; |
| 14 117 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_TABLES_IPV6_H_ #define _NF_TABLES_IPV6_H_ #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/ipv6.h> #include <net/netfilter/nf_tables.h> static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt) { unsigned int flags = IP6_FH_F_AUTH; int protohdr, thoff = 0; unsigned short frag_off; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0 || thoff > U16_MAX) { nft_set_pktinfo_unspec(pkt); return; } pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; } static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; struct ipv6hdr *ip6h, _ip6h; unsigned int thoff = 0; unsigned short frag_off; u32 pkt_len, skb_len; int protohdr; ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*ip6h), &_ip6h); if (!ip6h) return -1; if (ip6h->version != 6) return -1; pkt_len = ntohs(ip6h->payload_len); skb_len = pkt->skb->len - skb_network_offset(pkt->skb); if (pkt_len + sizeof(*ip6h) > skb_len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0 || thoff > U16_MAX) return -1; pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; return 0; #else return -1; #endif } static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { if (__nft_set_pktinfo_ipv6_validate(pkt) < 0) nft_set_pktinfo_unspec(pkt); } static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; unsigned short frag_off; unsigned int thoff = 0; struct inet6_dev *idev; struct ipv6hdr *ip6h; int protohdr; u32 pkt_len; if (!pskb_may_pull(pkt->skb, sizeof(*ip6h))) return -1; ip6h = ipv6_hdr(pkt->skb); if (ip6h->version != 6) goto inhdr_error; pkt_len = ntohs(ip6h->payload_len); if (pkt_len + sizeof(*ip6h) > pkt->skb->len) { idev = __in6_dev_get(nft_in(pkt)); __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); return -1; } protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0 || thoff > U16_MAX) goto inhdr_error; pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = protohdr; pkt->thoff = thoff; pkt->fragoff = frag_off; return 0; inhdr_error: idev = __in6_dev_get(nft_in(pkt)); __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INHDRERRORS); return -1; #else return -1; #endif } #endif |
| 316 6 28 6 1 245 201 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov */ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> #include <linux/gfp_types.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/math.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/xarray.h> #include <linux/local_lock.h> /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node struct radix_tree_preload { local_lock_t lock; unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer * 10 - internal entry * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). * This means that storing a NULL entry in the tree is the same as deleting * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL #define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) == RADIX_TREE_INTERNAL_NODE; } /*** radix-tree API starts here ***/ #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) #define RADIX_TREE_MAX_TAGS XA_MAX_MARKS #define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) #define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->xa_head == NULL; } /** * struct radix_tree_iter - radix tree iterator state * * @index: index of current slot * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is * described by a pointer to its first slot and a struct radix_tree_iter * which holds the chunk's position in the tree and its size. For tagged * iteration radix_tree_iter also holds the slots' bit-mask for one chosen * radix tree tag. */ struct radix_tree_iter { unsigned long index; unsigned long next_index; unsigned long tags; struct radix_tree_node *node; }; /** * Radix-tree synchronization * * The radix-tree API requires that users provide all synchronisation (with * specific exceptions, noted below). * * Synchronization of access to the data items being stored in the tree, and * management of their lifetimes must be completely managed by API users. * * For API usage, in general, * - any function _modifying_ the tree or tags (inserting or deleting * items, setting or clearing tags) must exclude other modifications, and * exclude any functions reading the tree. * - any function _reading_ the tree or tags (looking up items or tags, * gang lookups) must exclude modifications to the tree, but may occur * concurrently with other readers. * * The notable exceptions to this rule are the following functions: * __radix_tree_lookup * radix_tree_lookup * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. * * It is still required that the caller manage the synchronization and lifetimes * of the items. So if RCU lock-free lookups are used, typically this would mean * that the items have their own locks, or are amenable to lock-free access; and * that the items are freed by RCU (or only freed after having been deleted from * the radix tree *and* a synchronize_rcu() grace period). * * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * * Note that the value returned by radix_tree_tag_get() may not be relied upon * if only the RCU read lock is held. Functions to set/clear tags and to * delete nodes running concurrently with it may affect its result such that * two consecutive reads in the same locked section may return different * values. If reliability is required, modification functions must also be * excluded from concurrency. * * radix_tree_tagged is able to be called without locking or RCU. */ /** * radix_tree_deref_slot - dereference a slot * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is * held (ie. items cannot be concurrently inserted). * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot(void __rcu **slot) { return rcu_dereference(*slot); } /** * radix_tree_deref_slot_protected - dereference a slot with tree lock held * @slot: slot pointer, returned by radix_tree_lookup_slot * * Similar to radix_tree_deref_slot. The caller does not hold the RCU read * lock but it must hold the tree lock to prevent parallel updates. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required * * radix_tree_deref_retry must be used with radix_tree_deref_slot. */ static inline int radix_tree_deref_retry(void *arg) { return unlikely(radix_tree_is_internal_node(arg)); } /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. */ static inline int radix_tree_exception(void *arg) { return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } int radix_tree_insert(struct radix_tree_root *, unsigned long index, void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ }; /** * radix_tree_iter_init - initialize radix tree iterator * * @iter: pointer to iterator state * @start: iteration starting index * Returns: NULL */ static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it * in the case of a successful tagged chunk lookup. If the lookup was * unsuccessful or non-tagged then nobody cares about ->tags. * * Set index to zero to bypass next_index overflow protection. * See the comment in radix_tree_next_chunk() for details. */ iter->index = 0; iter->next_index = start; return NULL; } /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if there no more left * * This function looks up the next chunk in the radix tree starting from * @iter->next_index. It returns a pointer to the chunk's first slot. * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** * radix_tree_iter_lookup - look up an index in the radix tree * @root: radix tree root * @iter: iterator state * @index: key to look up * * If @index is present in the radix tree, this function returns the slot * containing it and updates @iter to describe the entry. If @index is not * present, it returns NULL. */ static inline void __rcu ** radix_tree_iter_lookup(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned long index) { radix_tree_iter_init(iter, index); return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); } /** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * * If we iterate over a tree protected only by the RCU lock, a race * against deletion or creation may result in seeing a slot for which * radix_tree_deref_retry() returns true. If so, call this function * and continue the iteration. */ static inline __must_check void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; return NULL; } static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { return iter->index + slots; } /** * radix_tree_iter_resume - resume iterating when the chunk may be invalid * @slot: pointer to current slot * @iter: iterator state * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; } /** * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); slot++; goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); iter->tags >>= offset++; iter->index = __radix_tree_iter_add(iter, offset); slot += offset; goto found; } } else { long count = radix_tree_chunk_size(iter); while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); if (likely(*slot)) goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; break; } } } return NULL; found: return slot; } /** * radix_tree_for_each_slot - iterate over non-empty slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_slot(slot, root, iter, start) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) /** * radix_tree_for_each_tagged - iterate over tagged slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * @tag: tag index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_tagged(slot, root, iter, start, tag) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_H */ |
| 129 128 61 32 37 17 47 47 36 27 47 1 46 46 1 45 46 46 46 2 2 2 1 1 58 78 61 29 37 22 45 2271 129 32 3 34 36 25 61 61 2439 2438 17 2437 2398 60 128 58 8 121 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King * Copyright (C) 2020 Christoph Hellwig */ #include <linux/fs.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/vmalloc.h> #include <linux/raid/detect.h> #include "check.h" static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. */ #ifdef CONFIG_ACORN_PARTITION_ICS adfspart_check_ICS, #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC adfspart_check_POWERTEC, #endif #ifdef CONFIG_ACORN_PARTITION_EESOX adfspart_check_EESOX, #endif /* * Now move on to formats that only have partition info at * disk address 0xdc0. Since these may also have stale * PC/BIOS partition tables, they need to come before * the msdos entry. */ #ifdef CONFIG_ACORN_PARTITION_CUMANA adfspart_check_CUMANA, #endif #ifdef CONFIG_ACORN_PARTITION_ADFS adfspart_check_ADFS, #endif #ifdef CONFIG_CMDLINE_PARTITION cmdline_partition, #endif #ifdef CONFIG_OF_PARTITION of_partition, /* cmdline have priority to OF */ #endif #ifdef CONFIG_EFI_PARTITION efi_partition, /* this must come before msdos */ #endif #ifdef CONFIG_SGI_PARTITION sgi_partition, #endif #ifdef CONFIG_LDM_PARTITION ldm_partition, /* this must come before msdos */ #endif #ifdef CONFIG_MSDOS_PARTITION msdos_partition, #endif #ifdef CONFIG_OSF_PARTITION osf_partition, #endif #ifdef CONFIG_SUN_PARTITION sun_partition, #endif #ifdef CONFIG_AMIGA_PARTITION amiga_partition, #endif #ifdef CONFIG_ATARI_PARTITION atari_partition, #endif #ifdef CONFIG_MAC_PARTITION mac_partition, #endif #ifdef CONFIG_ULTRIX_PARTITION ultrix_partition, #endif #ifdef CONFIG_IBM_PARTITION ibm_partition, #endif #ifdef CONFIG_KARMA_PARTITION karma_partition, #endif #ifdef CONFIG_SYSV68_PARTITION sysv68_partition, #endif NULL }; static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; int nr = DISK_MAX_PARTS; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return NULL; state->parts = vzalloc(array_size(nr, sizeof(state->parts[0]))); if (!state->parts) { kfree(state); return NULL; } state->limit = nr; return state; } static void free_partitions(struct parsed_partitions *state) { vfree(state->parts); kfree(state); } static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; state = allocate_partitions(hd); if (!state) return NULL; state->pp_buf = (char *)__get_free_page(GFP_KERNEL); if (!state->pp_buf) { free_partitions(state); return NULL; } state->pp_buf[0] = '\0'; state->disk = hd; snprintf(state->name, BDEVNAME_SIZE, "%s", hd->disk_name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) sprintf(state->name, "p"); i = res = err = 0; while (!res && check_part[i]) { memset(state->parts, 0, state->limit * sizeof(state->parts[0])); res = check_part[i++](state); if (res < 0) { /* * We have hit an I/O error which we don't report now. * But record it, and let the others do their job. */ err = res; res = 0; } } if (res > 0) { printk(KERN_INFO "%s", state->pp_buf); free_page((unsigned long)state->pp_buf); return state; } if (state->access_beyond_eod) err = -ENOSPC; /* * The partition is unrecognized. So report I/O errors if there were any */ if (err) res = err; if (res) { strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE); printk(KERN_INFO "%s", state->pp_buf); } free_page((unsigned long)state->pp_buf); free_partitions(state); return ERR_PTR(res); } static ssize_t part_partition_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev))); } static ssize_t part_start_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect); } static ssize_t part_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_read_only(dev_to_bdev(dev))); } static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); static DEVICE_ATTR(start, 0444, part_start_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(ro, 0444, part_ro_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif static struct attribute *part_attrs[] = { &dev_attr_partition.attr, &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_ro.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif NULL }; static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; static const struct attribute_group *part_attr_groups[] = { &part_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, #endif NULL }; static void part_release(struct device *dev) { put_disk(dev_to_bdev(dev)->bd_disk); bdev_drop(dev_to_bdev(dev)); } static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct block_device *part = dev_to_bdev(dev); add_uevent_var(env, "PARTN=%u", bdev_partno(part)); if (part->bd_meta_info && part->bd_meta_info->volname[0]) add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname); if (part->bd_meta_info && part->bd_meta_info->uuid[0]) add_uevent_var(env, "PARTUUID=%s", part->bd_meta_info->uuid); return 0; } const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); xa_erase(&part->bd_disk->part_tbl, bdev_partno(part)); kobject_put(part->bd_holder_dir); device_del(&part->bd_device); put_device(&part->bd_device); } static ssize_t whole_disk_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, struct partition_meta_info *info) { dev_t devt = MKDEV(0, 0); struct device *ddev = disk_to_dev(disk); struct device *pdev; struct block_device *bdev; const char *dname; int err; lockdep_assert_held(&disk->open_mutex); if (partno >= DISK_MAX_PARTS) return ERR_PTR(-EINVAL); /* * Partitions are not supported on zoned block devices that are used as * such. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: partitions not supported on host managed zoned block device\n", disk->disk_name); return ERR_PTR(-ENXIO); } if (xa_load(&disk->part_tbl, partno)) return ERR_PTR(-EBUSY); /* ensure we always have a reference to the whole disk */ get_device(disk_to_dev(disk)); err = -ENOMEM; bdev = bdev_alloc(disk, partno); if (!bdev) goto out_put_disk; bdev->bd_start_sect = start; bdev_set_nr_sectors(bdev, len); pdev = &bdev->bd_device; dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) dev_set_name(pdev, "%sp%d", dname, partno); else dev_set_name(pdev, "%s%d", dname, partno); device_initialize(pdev); pdev->class = &block_class; pdev->type = &part_type; pdev->parent = ddev; /* in consecutive minor range? */ if (bdev_partno(bdev) < disk->minors) { devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev)); } else { err = blk_alloc_ext_minor(); if (err < 0) goto out_put; devt = MKDEV(BLOCK_EXT_MAJOR, err); } pdev->devt = devt; if (info) { err = -ENOMEM; bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); if (!bdev->bd_meta_info) goto out_put; } /* delay uevent until 'holders' subdir is created */ dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; err = -ENOMEM; bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj); if (!bdev->bd_holder_dir) goto out_del; dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) goto out_del; } if (flags & ADDPART_FLAG_READONLY) bdev_set_flag(bdev, BD_READ_ONLY); /* everything is up and running, commence */ err = xa_insert(&disk->part_tbl, partno, bdev, GFP_KERNEL); if (err) goto out_del; bdev_add(bdev, devt); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return bdev; out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); out_put: put_device(pdev); return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); } static bool partition_overlaps(struct gendisk *disk, sector_t start, sector_t length, int skip_partno) { struct block_device *part; bool overlap = false; unsigned long idx; rcu_read_lock(); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (bdev_partno(part) != skip_partno && start < part->bd_start_sect + bdev_nr_sectors(part) && start + length > part->bd_start_sect) { overlap = true; break; } } rcu_read_unlock(); return overlap; } int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part; int ret; mutex_lock(&disk->open_mutex); if (!disk_live(disk)) { ret = -ENXIO; goto out; } if (disk->flags & GENHD_FL_NO_PART) { ret = -EINVAL; goto out; } if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; } part = add_partition(disk, partno, start, length, ADDPART_FLAG_NONE, NULL); ret = PTR_ERR_OR_ZERO(part); out: mutex_unlock(&disk->open_mutex); return ret; } int bdev_del_partition(struct gendisk *disk, int partno) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EBUSY; if (atomic_read(&part->bd_openers)) goto out_unlock; /* * We verified that @part->bd_openers is zero above and so * @part->bd_holder{_ops} can't be set. And since we hold * @disk->open_mutex the device can't be claimed by anyone. * * So no need to call @part->bd_holder_ops->mark_dead() here. * Just delete the partition and invalidate it. */ bdev_unhash(part); invalidate_bdev(part); drop_partition(part); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; ret = -EBUSY; if (partition_overlaps(disk, start, length, partno)) goto out_unlock; bdev_set_nr_sectors(part, length); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } static bool disk_unlock_native_capacity(struct gendisk *disk) { if (!disk->fops->unlock_native_capacity || test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) { printk(KERN_CONT "truncated\n"); return false; } printk(KERN_CONT "enabling native capacity\n"); disk->fops->unlock_native_capacity(disk); return true; } static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; sector_t from = state->parts[p].from; struct block_device *part; if (!size) return true; if (from >= get_capacity(disk)) { printk(KERN_WARNING "%s: p%d start %llu is beyond EOD, ", disk->disk_name, p, (unsigned long long) from); if (disk_unlock_native_capacity(disk)) return false; return true; } if (from + size > get_capacity(disk)) { printk(KERN_WARNING "%s: p%d size %llu extends beyond EOD, ", disk->disk_name, p, (unsigned long long) size); if (disk_unlock_native_capacity(disk)) return false; /* * We can not ignore partitions of broken tables created by for * example camera firmware, but we limit them to the end of the * disk to avoid creating invalid block devices. */ size = get_capacity(disk) - from; } part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); if (IS_ERR(part)) { if (PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %pe\n", disk->disk_name, p, part); } return true; } if (IS_BUILTIN(CONFIG_BLK_DEV_MD) && (state->parts[p].flags & ADDPART_FLAG_RAID)) md_autodetect_dev(part->bd_dev); return true; } static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { /* * I/O error reading the partition table. If we tried to read * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) return -EAGAIN; } return -EIO; } /* * Partitions are not supported on host managed zoned block devices. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; } /* * If we read beyond EOD, try unlocking native capacity even if the * partition table was successfully read as we could be missing some * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; out_free_state: free_partitions(state); return ret; } int bdev_disk_changed(struct gendisk *disk, bool invalidate) { struct block_device *part; unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); if (!disk_live(disk)) return -ENXIO; rescan: if (disk->open_partitions) return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); xa_for_each_start(&disk->part_tbl, idx, part, 1) { /* * Remove the block device from the inode hash, so that * it cannot be looked up any more even when openers * still hold references. */ bdev_unhash(part); /* * If @disk->open_partitions isn't elevated but there's * still an active holder of that block device things * are broken. */ WARN_ON_ONCE(atomic_read(&part->bd_openers)); invalidate_bdev(part); drop_partition(part); } clear_bit(GD_NEED_PART_SCAN, &disk->state); /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). * Doing that is rather inconsistent, but changing it broke legacy * udisks polling for legacy ide-cdrom devices. Use the crude check * below to get the sane behavior for most device while not breaking * userspace for this particular setup. */ if (invalidate) { if (!(disk->flags & GENHD_FL_NO_PART) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } if (get_capacity(disk)) { ret = blk_add_partitions(disk); if (ret == -EAGAIN) goto rescan; } else if (invalidate) { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); } return ret; } /* * Only exported for loop and dasd for historic reasons. Don't use in new * code! */ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->disk->part0->bd_mapping; struct folio *folio; if (n >= get_capacity(state->disk)) { state->access_beyond_eod = true; goto out; } folio = read_mapping_folio(mapping, n >> PAGE_SECTORS_SHIFT, NULL); if (IS_ERR(folio)) goto out; p->v = folio; return folio_address(folio) + offset_in_folio(folio, n * SECTOR_SIZE); out: p->v = NULL; return NULL; } |
| 21 16 4 4 2 14 13 8 6 14 8 8 8 9 2 7 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * UDPv6 GSO support */ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" #include <net/gro.h> #include <net/gso.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; int err; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); else { const struct ipv6hdr *ipv6h; struct udphdr *uh; if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ uh = udp_hdr(skb); ipv6h = ipv6_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v6_check(skb->len, &ipv6h->saddr, &ipv6h->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) return ERR_PTR(err); unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + unfrag_ip6hlen + tnl_hlen; packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() */ segs = skb_segment(skb, features); } out: return segs; } static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); struct net *net = dev_net_rcu(skb->dev); struct sock *sk; int iif, sdif; sk = udp_tunnel_sk(net, true); if (sk && dport == htons(sk->sk_num)) return sk; inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, ip6_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: if (static_branch_unlikely(&udpv6_encap_needed_key)) sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } int __init udpv6_offload_init(void) { net_hotdata.udpv6_offload = (struct net_offload) { .callbacks = { .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, }; return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } |
| 481 496 501 503 11 496 496 | 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 | /* * kmod - the kernel module loader * * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <trace/events/module.h> #include "internal.h" /* * Assuming: * * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, * (u64) THREAD_SIZE * 8UL); * * If you need less than 50 threads would mean we're dealing with systems * smaller than 3200 pages. This assumes you are capable of having ~13M memory, * and this would only be an upper limit, after which the OOM killer would take * effect. Systems like these are very unlikely if modules are enabled. */ #define MAX_KMOD_CONCURRENT 50 static DEFINE_SEMAPHORE(kmod_concurrent_max, MAX_KMOD_CONCURRENT); /* * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads * running at the same time without returning. When this happens we * believe you've somehow ended up with a recursive module dependency * creating a loop. * * We have no option but to fail. * * Userspace should proactively try to detect and prevent these. */ #define MAX_KMOD_ALL_BUSY_TIMEOUT 5 /* modprobe_path is set via /proc/sys. */ char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH; static void free_modprobe_argv(struct subprocess_info *info) { kfree(info->argv[3]); /* check call_modprobe() */ kfree(info->argv); } static int call_modprobe(char *orig_module_name, int wait) { struct subprocess_info *info; static char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; char *module_name; int ret; char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); if (!argv) goto out; module_name = kstrdup(orig_module_name, GFP_KERNEL); if (!module_name) goto free_argv; argv[0] = modprobe_path; argv[1] = "-q"; argv[2] = "--"; argv[3] = module_name; /* check free_modprobe_argv() */ argv[4] = NULL; info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, NULL, free_modprobe_argv, NULL); if (!info) goto free_module_name; ret = call_usermodehelper_exec(info, wait | UMH_KILLABLE); kmod_dup_request_announce(orig_module_name, ret); return ret; free_module_name: kfree(module_name); free_argv: kfree(argv); out: kmod_dup_request_announce(orig_module_name, -ENOMEM); return -ENOMEM; } /** * __request_module - try to load a kernel module * @wait: wait (or not) for the operation to complete * @fmt: printf style format string for the name of the module * @...: arguments as specified in the format string * * Load a module using the user mode module loader. The function returns * zero on success or a negative errno code or positive exit code from * "modprobe" on failure. Note that a successful module load does not mean * the module did not then unload and exit on an error of its own. Callers * must check that the service they requested is now available not blindly * invoke it. * * If module auto-loading support is disabled then this function * simply returns -ENOENT. */ int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; int ret, dup_ret; /* * We don't allow synchronous module loading from async. Module * init may invoke async_synchronize_full() which will end up * waiting for this task which already is waiting for the module * loading to complete, leading to a deadlock. */ WARN_ON_ONCE(wait && current_is_async()); if (!modprobe_path[0]) return -ENOENT; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return -ENAMETOOLONG; ret = security_kernel_module_request(module_name); if (ret) return ret; ret = down_timeout(&kmod_concurrent_max, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); if (ret) { pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); return ret; } trace_module_request(module_name, wait, _RET_IP_); if (kmod_dup_request_exists_wait(module_name, wait, &dup_ret)) { ret = dup_ret; goto out; } ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); out: up(&kmod_concurrent_max); return ret; } EXPORT_SYMBOL(__request_module); |
| 1 1 2 1 1 2 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_icache.h" int xfs_qm_scall_quotaoff( xfs_mount_t *mp, uint flags) { /* * No file system can have quotas enabled on disk but not in core. * Note that quota utilities (like quotaoff) _expect_ * errno == -EEXIST here. */ if ((mp->m_qflags & flags) == 0) return -EEXIST; /* * We do not support actually turning off quota accounting any more. * Just log a warning and ignore the accounting related flags. */ if (flags & XFS_ALL_QUOTA_ACCT) xfs_info(mp, "disabling of quota accounting not supported."); mutex_lock(&mp->m_quotainfo->qi_quotaofflock); mp->m_qflags &= ~(flags & XFS_ALL_QUOTA_ENFD); spin_lock(&mp->m_sb_lock); mp->m_sb.sb_qflags = mp->m_qflags; spin_unlock(&mp->m_sb_lock); mutex_unlock(&mp->m_quotainfo->qi_quotaofflock); /* XXX what to do if error ? Revert back to old vals incore ? */ return xfs_sync_sb(mp, false); } STATIC int xfs_qm_scall_trunc_qfile( struct xfs_mount *mp, xfs_dqtype_t type) { struct xfs_inode *ip; struct xfs_trans *tp; int error; error = xfs_qm_qino_load(mp, type, &ip); if (error == -ENOENT) return 0; if (error) return error; xfs_ilock(ip, XFS_IOLOCK_EXCL); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { xfs_iunlock(ip, XFS_IOLOCK_EXCL); goto out_put; } xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); ip->i_disk_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); if (error) { xfs_trans_cancel(tp); goto out_unlock; } ASSERT(ip->i_df.if_nextents == 0); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); error = xfs_trans_commit(tp); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); out_put: xfs_irele(ip); return error; } int xfs_qm_scall_trunc_qfiles( xfs_mount_t *mp, uint flags) { int error = -EINVAL; if (!xfs_has_quota(mp) || flags == 0 || (flags & ~XFS_QMOPT_QUOTALL)) { xfs_debug(mp, "%s: flags=%x m_qflags=%x", __func__, flags, mp->m_qflags); return -EINVAL; } if (flags & XFS_QMOPT_UQUOTA) { error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_USER); if (error) return error; } if (flags & XFS_QMOPT_GQUOTA) { error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_GROUP); if (error) return error; } if (flags & XFS_QMOPT_PQUOTA) error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_PROJ); return error; } /* * Switch on (a given) quota enforcement for a filesystem. This takes * effect immediately. * (Switching on quota accounting must be done at mount time.) */ int xfs_qm_scall_quotaon( xfs_mount_t *mp, uint flags) { int error; uint qf; /* * Switching on quota accounting must be done at mount time, * only consider quota enforcement stuff here. */ flags &= XFS_ALL_QUOTA_ENFD; if (flags == 0) { xfs_debug(mp, "%s: zero flags, m_qflags=%x", __func__, mp->m_qflags); return -EINVAL; } /* * Can't enforce without accounting. We check the superblock * qflags here instead of m_qflags because rootfs can have * quota acct on ondisk without m_qflags' knowing. */ if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && (flags & XFS_UQUOTA_ENFD)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && (flags & XFS_GQUOTA_ENFD)) || ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && (flags & XFS_PQUOTA_ENFD))) { xfs_debug(mp, "%s: Can't enforce without acct, flags=%x sbflags=%x", __func__, flags, mp->m_sb.sb_qflags); return -EINVAL; } /* * If everything's up to-date incore, then don't waste time. */ if ((mp->m_qflags & flags) == flags) return -EEXIST; /* * Change sb_qflags on disk but not incore mp->qflags * if this is the root filesystem. */ spin_lock(&mp->m_sb_lock); qf = mp->m_sb.sb_qflags; mp->m_sb.sb_qflags = qf | flags; spin_unlock(&mp->m_sb_lock); /* * There's nothing to change if it's the same. */ if ((qf & flags) == flags) return -EEXIST; error = xfs_sync_sb(mp, false); if (error) return error; /* * If we aren't trying to switch on quota enforcement, we are done. */ if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) != (mp->m_qflags & XFS_UQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) != (mp->m_qflags & XFS_PQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) != (mp->m_qflags & XFS_GQUOTA_ACCT))) return 0; if (!XFS_IS_QUOTA_ON(mp)) return -ESRCH; /* * Switch on quota enforcement in core. */ mutex_lock(&mp->m_quotainfo->qi_quotaofflock); mp->m_qflags |= (flags & XFS_ALL_QUOTA_ENFD); mutex_unlock(&mp->m_quotainfo->qi_quotaofflock); return 0; } #define XFS_QC_MASK (QC_LIMIT_MASK | QC_TIMER_MASK) /* * Adjust limits of this quota, and the defaults if passed in. Returns true * if the new limits made sense and were applied, false otherwise. */ static inline bool xfs_setqlim_limits( struct xfs_mount *mp, struct xfs_dquot_res *res, struct xfs_quota_limits *qlim, xfs_qcnt_t hard, xfs_qcnt_t soft, const char *tag) { /* The hard limit can't be less than the soft limit. */ if (hard != 0 && hard < soft) { xfs_debug(mp, "%shard %lld < %ssoft %lld", tag, hard, tag, soft); return false; } res->hardlimit = hard; res->softlimit = soft; if (qlim) { qlim->hard = hard; qlim->soft = soft; } return true; } static inline void xfs_setqlim_timer( struct xfs_mount *mp, struct xfs_dquot_res *res, struct xfs_quota_limits *qlim, s64 timer) { if (qlim) { /* Set the length of the default grace period. */ res->timer = xfs_dquot_set_grace_period(timer); qlim->time = res->timer; } else { /* Set the grace period expiration on a quota. */ res->timer = xfs_dquot_set_timeout(mp, timer); } } /* * Adjust quota limits, and start/stop timers accordingly. */ int xfs_qm_scall_setqlim( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct qc_dqblk *newlim) { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_dquot *dqp; struct xfs_trans *tp; struct xfs_def_quota *defq; struct xfs_dquot_res *res; struct xfs_quota_limits *qlim; int error; xfs_qcnt_t hard, soft; if (newlim->d_fieldmask & ~XFS_QC_MASK) return -EINVAL; if ((newlim->d_fieldmask & XFS_QC_MASK) == 0) return 0; /* * Get the dquot (locked) before we start, as we need to do a * transaction to allocate it if it doesn't exist. Once we have the * dquot, unlock it so we can start the next transaction safely. We hold * a reference to the dquot, so it's safe to do this unlock/lock without * it being reclaimed in the mean time. */ error = xfs_qm_dqget(mp, id, type, true, &dqp); if (error) { ASSERT(error != -ENOENT); return error; } defq = xfs_get_defquota(q, xfs_dquot_type(dqp)); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_setqlim, 0, 0, 0, &tp); if (error) goto out_rele; mutex_lock(&dqp->q_qlock); xfs_trans_dqjoin(tp, dqp); /* * Update quota limits, warnings, and timers, and the defaults * if we're touching id == 0. * * Make sure that hardlimits are >= soft limits before changing. * * Update warnings counter(s) if requested. * * Timelimits for the super user set the relative time the other users * can be over quota for this file system. If it is zero a default is * used. Ditto for the default soft and hard limit values (already * done, above), and for warnings. * * For other IDs, userspace can bump out the grace period if over * the soft limit. */ /* Blocks on the data device. */ hard = (newlim->d_fieldmask & QC_SPC_HARD) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) : dqp->q_blk.hardlimit; soft = (newlim->d_fieldmask & QC_SPC_SOFT) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) : dqp->q_blk.softlimit; res = &dqp->q_blk; qlim = id == 0 ? &defq->blk : NULL; if (xfs_setqlim_limits(mp, res, qlim, hard, soft, "blk")) xfs_dquot_set_prealloc_limits(dqp); if (newlim->d_fieldmask & QC_SPC_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_spc_timer); /* Blocks on the realtime device. */ hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) : dqp->q_rtb.hardlimit; soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) : dqp->q_rtb.softlimit; res = &dqp->q_rtb; qlim = id == 0 ? &defq->rtb : NULL; xfs_setqlim_limits(mp, res, qlim, hard, soft, "rtb"); if (newlim->d_fieldmask & QC_RT_SPC_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_rt_spc_timer); /* Inodes */ hard = (newlim->d_fieldmask & QC_INO_HARD) ? (xfs_qcnt_t) newlim->d_ino_hardlimit : dqp->q_ino.hardlimit; soft = (newlim->d_fieldmask & QC_INO_SOFT) ? (xfs_qcnt_t) newlim->d_ino_softlimit : dqp->q_ino.softlimit; res = &dqp->q_ino; qlim = id == 0 ? &defq->ino : NULL; xfs_setqlim_limits(mp, res, qlim, hard, soft, "ino"); if (newlim->d_fieldmask & QC_INO_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_ino_timer); if (id != 0) { /* * If the user is now over quota, start the timelimit. * The user will not be 'warned'. * Note that we keep the timers ticking, whether enforcement * is on or off. We don't really want to bother with iterating * over all ondisk dquots and turning the timers on/off. */ xfs_qm_adjust_dqtimers(dqp); } dqp->q_flags |= XFS_DQFLAG_DIRTY; xfs_trans_log_dquot(tp, dqp); error = xfs_trans_commit(tp); out_rele: xfs_qm_dqrele(dqp); return error; } /* Fill out the quota context. */ static void xfs_qm_scall_getquota_fill_qc( struct xfs_mount *mp, xfs_dqtype_t type, const struct xfs_dquot *dqp, struct qc_dqblk *dst) { memset(dst, 0, sizeof(*dst)); dst->d_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_blk.hardlimit); dst->d_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_blk.softlimit); dst->d_ino_hardlimit = dqp->q_ino.hardlimit; dst->d_ino_softlimit = dqp->q_ino.softlimit; dst->d_space = XFS_FSB_TO_B(mp, dqp->q_blk.reserved); dst->d_ino_count = dqp->q_ino.reserved; dst->d_spc_timer = dqp->q_blk.timer; dst->d_ino_timer = dqp->q_ino.timer; dst->d_ino_warns = 0; dst->d_spc_warns = 0; dst->d_rt_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.hardlimit); dst->d_rt_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.softlimit); dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_rtb.reserved); dst->d_rt_spc_timer = dqp->q_rtb.timer; dst->d_rt_spc_warns = 0; /* * Internally, we don't reset all the timers when quota enforcement * gets turned off. No need to confuse the user level code, * so return zeroes in that case. */ if (!xfs_dquot_is_enforced(dqp)) { dst->d_spc_timer = 0; dst->d_ino_timer = 0; dst->d_rt_spc_timer = 0; } } /* Return the quota information for the dquot matching id. */ int xfs_qm_scall_getquota( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; /* * Expedite pending inodegc work at the start of a quota reporting * scan but don't block waiting for it to complete. */ if (id == 0) xfs_inodegc_push(mp); /* * Try to get the dquot. We don't want it allocated on disk, so don't * set doalloc. If it doesn't exist, we'll get ENOENT back. */ error = xfs_qm_dqget(mp, id, type, false, &dqp); if (error) return error; /* * If everything's NULL, this dquot doesn't quite exist as far as * our utility programs are concerned. */ mutex_lock(&dqp->q_qlock); if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { error = -ENOENT; goto out_put; } xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst); out_put: mutex_unlock(&dqp->q_qlock); xfs_qm_dqrele(dqp); return error; } /* * Return the quota information for the first initialized dquot whose id * is at least as high as id. */ int xfs_qm_scall_getquota_next( struct xfs_mount *mp, xfs_dqid_t *id, xfs_dqtype_t type, struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; /* Flush inodegc work at the start of a quota reporting scan. */ if (*id == 0) xfs_inodegc_push(mp); error = xfs_qm_dqget_next(mp, *id, type, &dqp); if (error) return error; /* Fill in the ID we actually read from disk */ *id = dqp->q_id; xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst); mutex_unlock(&dqp->q_qlock); xfs_qm_dqrele(dqp); return error; } |
| 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/gc.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/kthread.h> #include <linux/slab.h> /** * tomoyo_memory_free - Free memory for elements. * * @ptr: Pointer to allocated memory. * * Returns nothing. * * Caller holds tomoyo_policy_lock mutex. */ static inline void tomoyo_memory_free(void *ptr) { tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= ksize(ptr); kfree(ptr); } /* The list for "struct tomoyo_io_buffer". */ static LIST_HEAD(tomoyo_io_buffer_list); /* Lock for protecting tomoyo_io_buffer_list. */ static DEFINE_SPINLOCK(tomoyo_io_buffer_list_lock); /** * tomoyo_struct_used_by_io_buffer - Check whether the list element is used by /sys/kernel/security/tomoyo/ users or not. * * @element: Pointer to "struct list_head". * * Returns true if @element is used by /sys/kernel/security/tomoyo/ users, * false otherwise. */ static bool tomoyo_struct_used_by_io_buffer(const struct list_head *element) { struct tomoyo_io_buffer *head; bool in_use = false; spin_lock(&tomoyo_io_buffer_list_lock); list_for_each_entry(head, &tomoyo_io_buffer_list, list) { head->users++; spin_unlock(&tomoyo_io_buffer_list_lock); mutex_lock(&head->io_sem); if (head->r.domain == element || head->r.group == element || head->r.acl == element || &head->w.domain->list == element) in_use = true; mutex_unlock(&head->io_sem); spin_lock(&tomoyo_io_buffer_list_lock); head->users--; if (in_use) break; } spin_unlock(&tomoyo_io_buffer_list_lock); return in_use; } /** * tomoyo_name_used_by_io_buffer - Check whether the string is used by /sys/kernel/security/tomoyo/ users or not. * * @string: String to check. * * Returns true if @string is used by /sys/kernel/security/tomoyo/ users, * false otherwise. */ static bool tomoyo_name_used_by_io_buffer(const char *string) { struct tomoyo_io_buffer *head; const size_t size = strlen(string) + 1; bool in_use = false; spin_lock(&tomoyo_io_buffer_list_lock); list_for_each_entry(head, &tomoyo_io_buffer_list, list) { int i; head->users++; spin_unlock(&tomoyo_io_buffer_list_lock); mutex_lock(&head->io_sem); for (i = 0; i < TOMOYO_MAX_IO_READ_QUEUE; i++) { const char *w = head->r.w[i]; if (w < string || w > string + size) continue; in_use = true; break; } mutex_unlock(&head->io_sem); spin_lock(&tomoyo_io_buffer_list_lock); head->users--; if (in_use) break; } spin_unlock(&tomoyo_io_buffer_list_lock); return in_use; } /** * tomoyo_del_transition_control - Delete members in "struct tomoyo_transition_control". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_transition_control(struct list_head *element) { struct tomoyo_transition_control *ptr = container_of(element, typeof(*ptr), head.list); tomoyo_put_name(ptr->domainname); tomoyo_put_name(ptr->program); } /** * tomoyo_del_aggregator - Delete members in "struct tomoyo_aggregator". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_aggregator(struct list_head *element) { struct tomoyo_aggregator *ptr = container_of(element, typeof(*ptr), head.list); tomoyo_put_name(ptr->original_name); tomoyo_put_name(ptr->aggregated_name); } /** * tomoyo_del_manager - Delete members in "struct tomoyo_manager". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_manager(struct list_head *element) { struct tomoyo_manager *ptr = container_of(element, typeof(*ptr), head.list); tomoyo_put_name(ptr->manager); } /** * tomoyo_del_acl - Delete members in "struct tomoyo_acl_info". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static void tomoyo_del_acl(struct list_head *element) { struct tomoyo_acl_info *acl = container_of(element, typeof(*acl), list); tomoyo_put_condition(acl->cond); switch (acl->type) { case TOMOYO_TYPE_PATH_ACL: { struct tomoyo_path_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->name); } break; case TOMOYO_TYPE_PATH2_ACL: { struct tomoyo_path2_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->name1); tomoyo_put_name_union(&entry->name2); } break; case TOMOYO_TYPE_PATH_NUMBER_ACL: { struct tomoyo_path_number_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->name); tomoyo_put_number_union(&entry->number); } break; case TOMOYO_TYPE_MKDEV_ACL: { struct tomoyo_mkdev_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->name); tomoyo_put_number_union(&entry->mode); tomoyo_put_number_union(&entry->major); tomoyo_put_number_union(&entry->minor); } break; case TOMOYO_TYPE_MOUNT_ACL: { struct tomoyo_mount_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->dev_name); tomoyo_put_name_union(&entry->dir_name); tomoyo_put_name_union(&entry->fs_type); tomoyo_put_number_union(&entry->flags); } break; case TOMOYO_TYPE_ENV_ACL: { struct tomoyo_env_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name(entry->env); } break; case TOMOYO_TYPE_INET_ACL: { struct tomoyo_inet_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_group(entry->address.group); tomoyo_put_number_union(&entry->port); } break; case TOMOYO_TYPE_UNIX_ACL: { struct tomoyo_unix_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name_union(&entry->name); } break; case TOMOYO_TYPE_MANUAL_TASK_ACL: { struct tomoyo_task_acl *entry = container_of(acl, typeof(*entry), head); tomoyo_put_name(entry->domainname); } break; } } /** * tomoyo_del_domain - Delete members in "struct tomoyo_domain_info". * * @element: Pointer to "struct list_head". * * Returns nothing. * * Caller holds tomoyo_policy_lock mutex. */ static inline void tomoyo_del_domain(struct list_head *element) { struct tomoyo_domain_info *domain = container_of(element, typeof(*domain), list); struct tomoyo_acl_info *acl; struct tomoyo_acl_info *tmp; /* * Since this domain is referenced from neither * "struct tomoyo_io_buffer" nor "struct cred"->security, we can delete * elements without checking for is_deleted flag. */ list_for_each_entry_safe(acl, tmp, &domain->acl_info_list, list) { tomoyo_del_acl(&acl->list); tomoyo_memory_free(acl); } tomoyo_put_name(domain->domainname); } /** * tomoyo_del_condition - Delete members in "struct tomoyo_condition". * * @element: Pointer to "struct list_head". * * Returns nothing. */ void tomoyo_del_condition(struct list_head *element) { struct tomoyo_condition *cond = container_of(element, typeof(*cond), head.list); const u16 condc = cond->condc; const u16 numbers_count = cond->numbers_count; const u16 names_count = cond->names_count; const u16 argc = cond->argc; const u16 envc = cond->envc; unsigned int i; const struct tomoyo_condition_element *condp = (const struct tomoyo_condition_element *) (cond + 1); struct tomoyo_number_union *numbers_p = (struct tomoyo_number_union *) (condp + condc); struct tomoyo_name_union *names_p = (struct tomoyo_name_union *) (numbers_p + numbers_count); const struct tomoyo_argv *argv = (const struct tomoyo_argv *) (names_p + names_count); const struct tomoyo_envp *envp = (const struct tomoyo_envp *) (argv + argc); for (i = 0; i < numbers_count; i++) tomoyo_put_number_union(numbers_p++); for (i = 0; i < names_count; i++) tomoyo_put_name_union(names_p++); for (i = 0; i < argc; argv++, i++) tomoyo_put_name(argv->value); for (i = 0; i < envc; envp++, i++) { tomoyo_put_name(envp->name); tomoyo_put_name(envp->value); } } /** * tomoyo_del_name - Delete members in "struct tomoyo_name". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_name(struct list_head *element) { /* Nothing to do. */ } /** * tomoyo_del_path_group - Delete members in "struct tomoyo_path_group". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_path_group(struct list_head *element) { struct tomoyo_path_group *member = container_of(element, typeof(*member), head.list); tomoyo_put_name(member->member_name); } /** * tomoyo_del_group - Delete "struct tomoyo_group". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_group(struct list_head *element) { struct tomoyo_group *group = container_of(element, typeof(*group), head.list); tomoyo_put_name(group->group_name); } /** * tomoyo_del_address_group - Delete members in "struct tomoyo_address_group". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_address_group(struct list_head *element) { /* Nothing to do. */ } /** * tomoyo_del_number_group - Delete members in "struct tomoyo_number_group". * * @element: Pointer to "struct list_head". * * Returns nothing. */ static inline void tomoyo_del_number_group(struct list_head *element) { /* Nothing to do. */ } /** * tomoyo_try_to_gc - Try to kfree() an entry. * * @type: One of values in "enum tomoyo_policy_id". * @element: Pointer to "struct list_head". * * Returns nothing. * * Caller holds tomoyo_policy_lock mutex. */ static void tomoyo_try_to_gc(const enum tomoyo_policy_id type, struct list_head *element) { /* * __list_del_entry() guarantees that the list element became no longer * reachable from the list which the element was originally on (e.g. * tomoyo_domain_list). Also, synchronize_srcu() guarantees that the * list element became no longer referenced by syscall users. */ __list_del_entry(element); mutex_unlock(&tomoyo_policy_lock); synchronize_srcu(&tomoyo_ss); /* * However, there are two users which may still be using the list * element. We need to defer until both users forget this element. * * Don't kfree() until "struct tomoyo_io_buffer"->r.{domain,group,acl} * and "struct tomoyo_io_buffer"->w.domain forget this element. */ if (tomoyo_struct_used_by_io_buffer(element)) goto reinject; switch (type) { case TOMOYO_ID_TRANSITION_CONTROL: tomoyo_del_transition_control(element); break; case TOMOYO_ID_MANAGER: tomoyo_del_manager(element); break; case TOMOYO_ID_AGGREGATOR: tomoyo_del_aggregator(element); break; case TOMOYO_ID_GROUP: tomoyo_del_group(element); break; case TOMOYO_ID_PATH_GROUP: tomoyo_del_path_group(element); break; case TOMOYO_ID_ADDRESS_GROUP: tomoyo_del_address_group(element); break; case TOMOYO_ID_NUMBER_GROUP: tomoyo_del_number_group(element); break; case TOMOYO_ID_CONDITION: tomoyo_del_condition(element); break; case TOMOYO_ID_NAME: /* * Don't kfree() until all "struct tomoyo_io_buffer"->r.w[] * forget this element. */ if (tomoyo_name_used_by_io_buffer (container_of(element, typeof(struct tomoyo_name), head.list)->entry.name)) goto reinject; tomoyo_del_name(element); break; case TOMOYO_ID_ACL: tomoyo_del_acl(element); break; case TOMOYO_ID_DOMAIN: /* * Don't kfree() until all "struct cred"->security forget this * element. */ if (atomic_read(&container_of (element, typeof(struct tomoyo_domain_info), list)->users)) goto reinject; break; case TOMOYO_MAX_POLICY: break; } mutex_lock(&tomoyo_policy_lock); if (type == TOMOYO_ID_DOMAIN) tomoyo_del_domain(element); tomoyo_memory_free(element); return; reinject: /* * We can safely reinject this element here because * (1) Appending list elements and removing list elements are protected * by tomoyo_policy_lock mutex. * (2) Only this function removes list elements and this function is * exclusively executed by tomoyo_gc_mutex mutex. * are true. */ mutex_lock(&tomoyo_policy_lock); list_add_rcu(element, element->prev); } /** * tomoyo_collect_member - Delete elements with "struct tomoyo_acl_head". * * @id: One of values in "enum tomoyo_policy_id". * @member_list: Pointer to "struct list_head". * * Returns nothing. */ static void tomoyo_collect_member(const enum tomoyo_policy_id id, struct list_head *member_list) { struct tomoyo_acl_head *member; struct tomoyo_acl_head *tmp; list_for_each_entry_safe(member, tmp, member_list, list) { if (!member->is_deleted) continue; member->is_deleted = TOMOYO_GC_IN_PROGRESS; tomoyo_try_to_gc(id, &member->list); } } /** * tomoyo_collect_acl - Delete elements in "struct tomoyo_domain_info". * * @list: Pointer to "struct list_head". * * Returns nothing. */ static void tomoyo_collect_acl(struct list_head *list) { struct tomoyo_acl_info *acl; struct tomoyo_acl_info *tmp; list_for_each_entry_safe(acl, tmp, list, list) { if (!acl->is_deleted) continue; acl->is_deleted = TOMOYO_GC_IN_PROGRESS; tomoyo_try_to_gc(TOMOYO_ID_ACL, &acl->list); } } /** * tomoyo_collect_entry - Try to kfree() deleted elements. * * Returns nothing. */ static void tomoyo_collect_entry(void) { int i; enum tomoyo_policy_id id; struct tomoyo_policy_namespace *ns; mutex_lock(&tomoyo_policy_lock); { struct tomoyo_domain_info *domain; struct tomoyo_domain_info *tmp; list_for_each_entry_safe(domain, tmp, &tomoyo_domain_list, list) { tomoyo_collect_acl(&domain->acl_info_list); if (!domain->is_deleted || atomic_read(&domain->users)) continue; tomoyo_try_to_gc(TOMOYO_ID_DOMAIN, &domain->list); } } list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { for (id = 0; id < TOMOYO_MAX_POLICY; id++) tomoyo_collect_member(id, &ns->policy_list[id]); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) tomoyo_collect_acl(&ns->acl_group[i]); } { struct tomoyo_shared_acl_head *ptr; struct tomoyo_shared_acl_head *tmp; list_for_each_entry_safe(ptr, tmp, &tomoyo_condition_list, list) { if (atomic_read(&ptr->users) > 0) continue; atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS); tomoyo_try_to_gc(TOMOYO_ID_CONDITION, &ptr->list); } } list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { for (i = 0; i < TOMOYO_MAX_GROUP; i++) { struct list_head *list = &ns->group_list[i]; struct tomoyo_group *group; struct tomoyo_group *tmp; switch (i) { case 0: id = TOMOYO_ID_PATH_GROUP; break; case 1: id = TOMOYO_ID_NUMBER_GROUP; break; default: id = TOMOYO_ID_ADDRESS_GROUP; break; } list_for_each_entry_safe(group, tmp, list, head.list) { tomoyo_collect_member(id, &group->member_list); if (!list_empty(&group->member_list) || atomic_read(&group->head.users) > 0) continue; atomic_set(&group->head.users, TOMOYO_GC_IN_PROGRESS); tomoyo_try_to_gc(TOMOYO_ID_GROUP, &group->head.list); } } } for (i = 0; i < TOMOYO_MAX_HASH; i++) { struct list_head *list = &tomoyo_name_list[i]; struct tomoyo_shared_acl_head *ptr; struct tomoyo_shared_acl_head *tmp; list_for_each_entry_safe(ptr, tmp, list, list) { if (atomic_read(&ptr->users) > 0) continue; atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS); tomoyo_try_to_gc(TOMOYO_ID_NAME, &ptr->list); } } mutex_unlock(&tomoyo_policy_lock); } /** * tomoyo_gc_thread - Garbage collector thread function. * * @unused: Unused. * * Returns 0. */ static int tomoyo_gc_thread(void *unused) { /* Garbage collector thread is exclusive. */ static DEFINE_MUTEX(tomoyo_gc_mutex); if (!mutex_trylock(&tomoyo_gc_mutex)) goto out; tomoyo_collect_entry(); { struct tomoyo_io_buffer *head; struct tomoyo_io_buffer *tmp; spin_lock(&tomoyo_io_buffer_list_lock); list_for_each_entry_safe(head, tmp, &tomoyo_io_buffer_list, list) { if (head->users) continue; list_del(&head->list); kfree(head->read_buf); kfree(head->write_buf); kfree(head); } spin_unlock(&tomoyo_io_buffer_list_lock); } mutex_unlock(&tomoyo_gc_mutex); out: /* This acts as do_exit(0). */ return 0; } /** * tomoyo_notify_gc - Register/unregister /sys/kernel/security/tomoyo/ users. * * @head: Pointer to "struct tomoyo_io_buffer". * @is_register: True if register, false if unregister. * * Returns nothing. */ void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register) { bool is_write = false; spin_lock(&tomoyo_io_buffer_list_lock); if (is_register) { head->users = 1; list_add(&head->list, &tomoyo_io_buffer_list); } else { is_write = head->write_buf != NULL; if (!--head->users) { list_del(&head->list); kfree(head->read_buf); kfree(head->write_buf); kfree(head); } } spin_unlock(&tomoyo_io_buffer_list_lock); if (is_write) kthread_run(tomoyo_gc_thread, NULL, "GC for TOMOYO"); } |
| 31 76 35 48 3 72 67 3 2 65 14 52 28 6 26 26 26 13 13 13 5 5 5 5 43 35 9 9 44 44 56 57 38 36 36 33 35 17 17 17 17 28 28 27 10 27 13 13 13 8 2 6 26 26 26 9 25 26 26 10 10 10 10 10 7 8 2 2 2 11 5 11 3 8 11 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li <huajun.li@intel.com> * Haicheng Li <haicheng.li@intel.com> */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/fiemap.h> #include "f2fs.h" #include "node.h" #include <trace/events/f2fs.h> static bool support_inline_data(struct inode *inode) { if (f2fs_used_in_atomic_write(inode)) return false; if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; if (i_size_read(inode) > MAX_INLINE_DATA(inode)) return false; return true; } bool f2fs_may_inline_data(struct inode *inode) { if (!support_inline_data(inode)) return false; return !f2fs_post_read_required(inode); } static bool inode_has_blocks(struct inode *inode, struct folio *ifolio) { struct f2fs_inode *ri = F2FS_INODE(ifolio); int i; if (F2FS_HAS_BLOCKS(inode)) return true; for (i = 0; i < DEF_NIDS_PER_INODE; i++) { if (ri->i_nid[i]) return true; } return false; } bool f2fs_sanity_check_inline_data(struct inode *inode, struct folio *ifolio) { if (!f2fs_has_inline_data(inode)) return false; if (inode_has_blocks(inode, ifolio)) return false; if (!support_inline_data(inode)) return true; /* * used by sanity_check_inode(), when disk layout fields has not * been synchronized to inmem fields. */ return (S_ISREG(inode->i_mode) && (file_is_encrypt(inode) || file_is_verity(inode) || (F2FS_I(inode)->i_flags & F2FS_COMPR_FL))); } bool f2fs_may_inline_dentry(struct inode *inode) { if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY)) return false; if (!S_ISDIR(inode->i_mode)) return false; return true; } void f2fs_do_read_inline_data(struct folio *folio, struct folio *ifolio) { struct inode *inode = folio->mapping->host; if (folio_test_uptodate(folio)) return; f2fs_bug_on(F2FS_I_SB(inode), folio->index); folio_zero_segment(folio, MAX_INLINE_DATA(inode), folio_size(folio)); /* Copy the whole inline data block */ memcpy_to_folio(folio, 0, inline_data_addr(inode, ifolio), MAX_INLINE_DATA(inode)); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); } void f2fs_truncate_inline_inode(struct inode *inode, struct folio *ifolio, u64 from) { void *addr; if (from >= MAX_INLINE_DATA(inode)) return; addr = inline_data_addr(inode, ifolio); f2fs_folio_wait_writeback(ifolio, NODE, true, true); memset(addr + from, 0, MAX_INLINE_DATA(inode) - from); folio_mark_dirty(ifolio); if (from == 0) clear_inode_flag(inode, FI_DATA_EXIST); } int f2fs_read_inline_data(struct inode *inode, struct folio *folio) { struct folio *ifolio; ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ifolio)) { folio_unlock(folio); return PTR_ERR(ifolio); } if (!f2fs_has_inline_data(inode)) { f2fs_folio_put(ifolio, true); return -EAGAIN; } if (folio->index) folio_zero_segment(folio, 0, folio_size(folio)); else f2fs_do_read_inline_data(folio, ifolio); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); f2fs_folio_put(ifolio, true); folio_unlock(folio); return 0; } int f2fs_convert_inline_folio(struct dnode_of_data *dn, struct folio *folio) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(dn->inode), .ino = dn->inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, .folio = folio, .encrypted_page = NULL, .io_type = FS_DATA_IO, }; struct node_info ni; int dirty, err; if (!f2fs_exist_data(dn->inode)) goto clear_out; err = f2fs_reserve_block(dn, 0); if (err) return err; err = f2fs_get_node_info(fio.sbi, dn->nid, &ni, false); if (err) { f2fs_truncate_data_blocks_range(dn, 1); f2fs_put_dnode(dn); return err; } fio.version = ni.version; if (unlikely(dn->data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(dn); set_sbi_flag(fio.sbi, SBI_NEED_FSCK); f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", __func__, dn->inode->i_ino, dn->data_blkaddr); f2fs_handle_error(fio.sbi, ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; } f2fs_bug_on(F2FS_F_SB(folio), folio_test_writeback(folio)); f2fs_do_read_inline_data(folio, dn->inode_folio); folio_mark_dirty(folio); /* clear dirty state */ dirty = folio_clear_dirty_for_io(folio); /* write data page to try to make data consistent */ folio_start_writeback(folio); fio.old_blkaddr = dn->data_blkaddr; set_inode_flag(dn->inode, FI_HOT_DATA); f2fs_outplace_write_data(dn, &fio); f2fs_folio_wait_writeback(folio, DATA, true, true); if (dirty) { inode_dec_dirty_pages(dn->inode); f2fs_remove_dirty_inode(dn->inode); } /* this converted inline_data should be recovered. */ set_inode_flag(dn->inode, FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ f2fs_truncate_inline_inode(dn->inode, dn->inode_folio, 0); folio_clear_f2fs_inline(dn->inode_folio); clear_out: stat_dec_inline_inode(dn->inode); clear_inode_flag(dn->inode, FI_INLINE_DATA); f2fs_put_dnode(dn); return 0; } int f2fs_convert_inline_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; struct folio *ifolio, *folio; int err = 0; if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) return -EROFS; if (!f2fs_has_inline_data(inode)) return 0; err = f2fs_dquot_initialize(inode); if (err) return err; folio = f2fs_grab_cache_folio(inode->i_mapping, 0, false); if (IS_ERR(folio)) return PTR_ERR(folio); f2fs_lock_op(sbi); ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); if (IS_ERR(ifolio)) { err = PTR_ERR(ifolio); goto out; } set_new_dnode(&dn, inode, ifolio, ifolio, 0); if (f2fs_has_inline_data(inode)) err = f2fs_convert_inline_folio(&dn, folio); f2fs_put_dnode(&dn); out: f2fs_unlock_op(sbi); f2fs_folio_put(folio, true); if (!err) f2fs_balance_fs(sbi, dn.node_changed); return err; } int f2fs_write_inline_data(struct inode *inode, struct folio *folio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct folio *ifolio; ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); if (!f2fs_has_inline_data(inode)) { f2fs_folio_put(ifolio, true); return -EAGAIN; } f2fs_bug_on(F2FS_I_SB(inode), folio->index); f2fs_folio_wait_writeback(ifolio, NODE, true, true); memcpy_from_folio(inline_data_addr(inode, ifolio), folio, 0, MAX_INLINE_DATA(inode)); folio_mark_dirty(ifolio); f2fs_clear_page_cache_dirty_tag(folio); set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); folio_clear_f2fs_inline(ifolio); f2fs_folio_put(ifolio, true); return 0; } int f2fs_recover_inline_data(struct inode *inode, struct folio *nfolio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; void *src_addr, *dst_addr; /* * The inline_data recovery policy is as follows. * [prev.] [next] of inline_data flag * o o -> recover inline_data * o x -> remove inline_data, and then recover data blocks * x o -> remove data blocks, and then recover inline_data * x x -> recover data blocks */ if (IS_INODE(nfolio)) ri = F2FS_INODE(nfolio); if (f2fs_has_inline_data(inode) && ri && (ri->i_inline & F2FS_INLINE_DATA)) { struct folio *ifolio; process_inline: ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); f2fs_folio_wait_writeback(ifolio, NODE, true, true); src_addr = inline_data_addr(inode, nfolio); dst_addr = inline_data_addr(inode, ifolio); memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); set_inode_flag(inode, FI_INLINE_DATA); set_inode_flag(inode, FI_DATA_EXIST); folio_mark_dirty(ifolio); f2fs_folio_put(ifolio, true); return 1; } if (f2fs_has_inline_data(inode)) { struct folio *ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); f2fs_truncate_inline_inode(inode, ifolio, 0); stat_dec_inline_inode(inode); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_folio_put(ifolio, true); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { int ret; ret = f2fs_truncate_blocks(inode, 0, false); if (ret) return ret; stat_inc_inline_inode(inode); goto process_inline; } return 0; } struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, struct folio **res_folio, bool use_hash) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; struct folio *ifolio; void *inline_dentry; ifolio = f2fs_get_inode_folio(sbi, dir->i_ino); if (IS_ERR(ifolio)) { *res_folio = ifolio; return NULL; } inline_dentry = inline_data_addr(dir, ifolio); make_dentry_ptr_inline(dir, &d, inline_dentry); de = f2fs_find_target_dentry(&d, fname, NULL, use_hash); folio_unlock(ifolio); if (IS_ERR(de)) { *res_folio = ERR_CAST(de); de = NULL; } if (de) *res_folio = ifolio; else f2fs_folio_put(ifolio, false); return de; } int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct folio *ifolio) { struct f2fs_dentry_ptr d; void *inline_dentry; inline_dentry = inline_data_addr(inode, ifolio); make_dentry_ptr_inline(inode, &d, inline_dentry); f2fs_do_make_empty_dir(inode, parent, &d); folio_mark_dirty(ifolio); /* update i_size to MAX_INLINE_DATA */ if (i_size_read(inode) < MAX_INLINE_DATA(inode)) f2fs_i_size_write(inode, MAX_INLINE_DATA(inode)); return 0; } /* * NOTE: ipage is grabbed by caller, but if any error occurs, we should * release ipage in this function. */ static int f2fs_move_inline_dirents(struct inode *dir, struct folio *ifolio, void *inline_dentry) { struct folio *folio; struct dnode_of_data dn; struct f2fs_dentry_block *dentry_blk; struct f2fs_dentry_ptr src, dst; int err; folio = f2fs_grab_cache_folio(dir->i_mapping, 0, true); if (IS_ERR(folio)) { f2fs_folio_put(ifolio, true); return PTR_ERR(folio); } set_new_dnode(&dn, dir, ifolio, NULL, 0); err = f2fs_reserve_block(&dn, 0); if (err) goto out; if (unlikely(dn.data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(&dn); set_sbi_flag(F2FS_F_SB(folio), SBI_NEED_FSCK); f2fs_warn(F2FS_F_SB(folio), "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", __func__, dir->i_ino, dn.data_blkaddr); f2fs_handle_error(F2FS_F_SB(folio), ERROR_INVALID_BLKADDR); err = -EFSCORRUPTED; goto out; } f2fs_folio_wait_writeback(folio, DATA, true, true); dentry_blk = folio_address(folio); /* * Start by zeroing the full block, to ensure that all unused space is * zeroed and no uninitialized memory is leaked to disk. */ memset(dentry_blk, 0, F2FS_BLKSIZE); make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); /* copy data from inline dentry block to new dentry block */ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); folio_mark_dirty(folio); /* clear inline dir and flag after data writeback */ f2fs_truncate_inline_inode(dir, ifolio, 0); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); /* * should retrieve reserved space which was used to keep * inline_dentry's structure for backward compatibility. */ if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && !f2fs_has_inline_xattr(dir)) F2FS_I(dir)->i_inline_xattr_size = 0; f2fs_i_depth_write(dir, 1); if (i_size_read(dir) < PAGE_SIZE) f2fs_i_size_write(dir, PAGE_SIZE); out: f2fs_folio_put(folio, true); return err; } static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) { struct f2fs_dentry_ptr d; unsigned long bit_pos = 0; int err = 0; make_dentry_ptr_inline(dir, &d, inline_dentry); while (bit_pos < d.max) { struct f2fs_dir_entry *de; struct f2fs_filename fname; nid_t ino; umode_t fake_mode; if (!test_bit_le(bit_pos, d.bitmap)) { bit_pos++; continue; } de = &d.dentry[bit_pos]; if (unlikely(!de->name_len)) { bit_pos++; continue; } /* * We only need the disk_name and hash to move the dentry. * We don't need the original or casefolded filenames. */ memset(&fname, 0, sizeof(fname)); fname.disk_name.name = d.filename[bit_pos]; fname.disk_name.len = le16_to_cpu(de->name_len); fname.hash = de->hash_code; ino = le32_to_cpu(de->ino); fake_mode = fs_ftype_to_dtype(de->file_type) << S_DT_SHIFT; err = f2fs_add_regular_entry(dir, &fname, NULL, ino, fake_mode); if (err) goto punch_dentry_pages; bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); } return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); f2fs_truncate_blocks(dir, 0, false); f2fs_remove_dirty_inode(dir); return err; } static int f2fs_move_rehashed_dirents(struct inode *dir, struct folio *ifolio, void *inline_dentry) { void *backup_dentry; int err; backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir), MAX_INLINE_DATA(dir), GFP_F2FS_ZERO); if (!backup_dentry) { f2fs_folio_put(ifolio, true); return -ENOMEM; } memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir)); f2fs_truncate_inline_inode(dir, ifolio, 0); folio_unlock(ifolio); err = f2fs_add_inline_entries(dir, backup_dentry); if (err) goto recover; folio_lock(ifolio); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); /* * should retrieve reserved space which was used to keep * inline_dentry's structure for backward compatibility. */ if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && !f2fs_has_inline_xattr(dir)) F2FS_I(dir)->i_inline_xattr_size = 0; kfree(backup_dentry); return 0; recover: folio_lock(ifolio); f2fs_folio_wait_writeback(ifolio, NODE, true, true); memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir)); f2fs_i_depth_write(dir, 0); f2fs_i_size_write(dir, MAX_INLINE_DATA(dir)); folio_mark_dirty(ifolio); f2fs_folio_put(ifolio, true); kfree(backup_dentry); return err; } static int do_convert_inline_dir(struct inode *dir, struct folio *ifolio, void *inline_dentry) { if (!F2FS_I(dir)->i_dir_level) return f2fs_move_inline_dirents(dir, ifolio, inline_dentry); else return f2fs_move_rehashed_dirents(dir, ifolio, inline_dentry); } int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct folio *ifolio; struct f2fs_filename fname; void *inline_dentry = NULL; int err = 0; if (!f2fs_has_inline_dentry(dir)) return 0; f2fs_lock_op(sbi); err = f2fs_setup_filename(dir, &dentry->d_name, 0, &fname); if (err) goto out; ifolio = f2fs_get_inode_folio(sbi, dir->i_ino); if (IS_ERR(ifolio)) { err = PTR_ERR(ifolio); goto out_fname; } if (f2fs_has_enough_room(dir, ifolio, &fname)) { f2fs_folio_put(ifolio, true); goto out_fname; } inline_dentry = inline_data_addr(dir, ifolio); err = do_convert_inline_dir(dir, ifolio, inline_dentry); if (!err) f2fs_folio_put(ifolio, true); out_fname: f2fs_free_filename(&fname); out: f2fs_unlock_op(sbi); return err; } int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, struct inode *inode, nid_t ino, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct folio *ifolio; unsigned int bit_pos; void *inline_dentry = NULL; struct f2fs_dentry_ptr d; int slots = GET_DENTRY_SLOTS(fname->disk_name.len); struct folio *folio = NULL; int err = 0; ifolio = f2fs_get_inode_folio(sbi, dir->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); inline_dentry = inline_data_addr(dir, ifolio); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max); if (bit_pos >= d.max) { err = do_convert_inline_dir(dir, ifolio, inline_dentry); if (err) return err; err = -EAGAIN; goto out; } if (inode) { f2fs_down_write_nested(&F2FS_I(inode)->i_sem, SINGLE_DEPTH_NESTING); folio = f2fs_init_inode_metadata(inode, dir, fname, ifolio); if (IS_ERR(folio)) { err = PTR_ERR(folio); goto fail; } } f2fs_folio_wait_writeback(ifolio, NODE, true, true); f2fs_update_dentry(ino, mode, &d, &fname->disk_name, fname->hash, bit_pos); folio_mark_dirty(ifolio); /* we don't need to mark_inode_dirty now */ if (inode) { f2fs_i_pino_write(inode, dir->i_ino); /* synchronize inode page's data from inode cache */ if (is_inode_flag_set(inode, FI_NEW_INODE)) f2fs_update_inode(inode, folio); f2fs_folio_put(folio, true); } f2fs_update_parent_metadata(dir, inode, 0); fail: if (inode) f2fs_up_write(&F2FS_I(inode)->i_sem); out: f2fs_folio_put(ifolio, true); return err; } void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct folio *folio, struct inode *dir, struct inode *inode) { struct f2fs_dentry_ptr d; void *inline_dentry; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); unsigned int bit_pos; int i; folio_lock(folio); f2fs_folio_wait_writeback(folio, NODE, true, true); inline_dentry = inline_data_addr(dir, folio); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = dentry - d.dentry; for (i = 0; i < slots; i++) __clear_bit_le(bit_pos + i, d.bitmap); folio_mark_dirty(folio); f2fs_folio_put(folio, true); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); if (inode) f2fs_drop_nlink(dir, inode); } bool f2fs_empty_inline_dir(struct inode *dir) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct folio *ifolio; unsigned int bit_pos = 2; void *inline_dentry; struct f2fs_dentry_ptr d; ifolio = f2fs_get_inode_folio(sbi, dir->i_ino); if (IS_ERR(ifolio)) return false; inline_dentry = inline_data_addr(dir, ifolio); make_dentry_ptr_inline(dir, &d, inline_dentry); bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos); f2fs_folio_put(ifolio, true); if (bit_pos < d.max) return false; return true; } int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr) { struct inode *inode = file_inode(file); struct folio *ifolio = NULL; struct f2fs_dentry_ptr d; void *inline_dentry = NULL; int err; make_dentry_ptr_inline(inode, &d, inline_dentry); if (ctx->pos == d.max) return 0; ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); /* * f2fs_readdir was protected by inode.i_rwsem, it is safe to access * ipage without page's lock held. */ folio_unlock(ifolio); inline_dentry = inline_data_addr(inode, ifolio); make_dentry_ptr_inline(inode, &d, inline_dentry); err = f2fs_fill_dentries(ctx, &d, 0, fstr); if (!err) ctx->pos = d.max; f2fs_folio_put(ifolio, false); return err < 0 ? err : 0; } int f2fs_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { __u64 byteaddr, ilen; __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | FIEMAP_EXTENT_LAST; struct node_info ni; struct folio *ifolio; int err = 0; ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ifolio)) return PTR_ERR(ifolio); if ((S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) && !f2fs_has_inline_data(inode)) { err = -EAGAIN; goto out; } if (S_ISDIR(inode->i_mode) && !f2fs_has_inline_dentry(inode)) { err = -EAGAIN; goto out; } ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode)); if (start >= ilen) goto out; if (start + len < ilen) ilen = start + len; ilen -= start; err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni, false); if (err) goto out; byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; byteaddr += (char *)inline_data_addr(inode, ifolio) - (char *)F2FS_INODE(ifolio); err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err); out: f2fs_folio_put(ifolio, true); return err; } |
| 8 8 8 8 3 8 3 5 5 9 2 6 3 6 6 5 1 5 5 5 1 3 3 5 5 5 3 3 3 2 2 1 1 3 3 3 1 1 1 1 1 1 1 46 46 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | // SPDX-License-Identifier: GPL-2.0 #include <linux/jhash.h> #include <linux/netfilter.h> #include <linux/rcupdate.h> #include <linux/rhashtable.h> #include <linux/vmalloc.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <uapi/linux/genetlink.h> #include "ila.h" struct ila_xlat_params { struct ila_params ip; int ifindex; }; struct ila_map { struct ila_xlat_params xp; struct rhash_head node; struct ila_map __rcu *next; struct rcu_head rcu; }; #define MAX_LOCKS 1024 #define LOCKS_PER_CPU 10 static int alloc_ila_locks(struct ila_net *ilan) { return alloc_bucket_spinlocks(&ilan->xlat.locks, &ilan->xlat.locks_mask, MAX_LOCKS, LOCKS_PER_CPU, GFP_KERNEL); } static u32 hashrnd __read_mostly; static __always_inline void __ila_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static inline u32 ila_locator_hash(struct ila_locator loc) { u32 *v = (u32 *)loc.v32; __ila_hash_secret_init(); return jhash_2words(v[0], v[1], hashrnd); } static inline spinlock_t *ila_get_lock(struct ila_net *ilan, struct ila_locator loc) { return &ilan->xlat.locks[ila_locator_hash(loc) & ilan->xlat.locks_mask]; } static inline int ila_cmp_wildcards(struct ila_map *ila, struct ila_addr *iaddr, int ifindex) { return (ila->xp.ifindex && ila->xp.ifindex != ifindex); } static inline int ila_cmp_params(struct ila_map *ila, struct ila_xlat_params *xp) { return (ila->xp.ifindex != xp->ifindex); } static int ila_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) { const struct ila_map *ila = obj; return (ila->xp.ip.locator_match.v64 != *(__be64 *)arg->key); } static inline int ila_order(struct ila_map *ila) { int score = 0; if (ila->xp.ifindex) score += 1 << 1; return score; } static const struct rhashtable_params rht_params = { .nelem_hint = 1024, .head_offset = offsetof(struct ila_map, node), .key_offset = offsetof(struct ila_map, xp.ip.locator_match), .key_len = sizeof(u64), /* identifier */ .max_size = 1048576, .min_size = 256, .automatic_shrinking = true, .obj_cmpfn = ila_cmpfn, }; static int parse_nl_config(struct genl_info *info, struct ila_xlat_params *xp) { memset(xp, 0, sizeof(*xp)); if (info->attrs[ILA_ATTR_LOCATOR]) xp->ip.locator.v64 = (__force __be64)nla_get_u64( info->attrs[ILA_ATTR_LOCATOR]); if (info->attrs[ILA_ATTR_LOCATOR_MATCH]) xp->ip.locator_match.v64 = (__force __be64)nla_get_u64( info->attrs[ILA_ATTR_LOCATOR_MATCH]); xp->ip.csum_mode = nla_get_u8_default(info->attrs[ILA_ATTR_CSUM_MODE], ILA_CSUM_NO_ACTION); xp->ip.ident_type = nla_get_u8_default(info->attrs[ILA_ATTR_IDENT_TYPE], ILA_ATYPE_USE_FORMAT); if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); return 0; } /* Must be called with rcu readlock */ static inline struct ila_map *ila_lookup_wildcards(struct ila_addr *iaddr, int ifindex, struct ila_net *ilan) { struct ila_map *ila; ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &iaddr->loc, rht_params); while (ila) { if (!ila_cmp_wildcards(ila, iaddr, ifindex)) return ila; ila = rcu_access_pointer(ila->next); } return NULL; } /* Must be called with rcu readlock */ static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *xp, struct ila_net *ilan) { struct ila_map *ila; ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); while (ila) { if (!ila_cmp_params(ila, xp)) return ila; ila = rcu_access_pointer(ila->next); } return NULL; } static inline void ila_release(struct ila_map *ila) { kfree_rcu(ila, rcu); } static void ila_free_node(struct ila_map *ila) { struct ila_map *next; /* Assume rcu_readlock held */ while (ila) { next = rcu_access_pointer(ila->next); ila_release(ila); ila = next; } } static void ila_free_cb(void *ptr, void *arg) { ila_free_node((struct ila_map *)ptr); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int ila_nf_input(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { ila_xlat_addr(skb, false); return NF_ACCEPT; } static const struct nf_hook_ops ila_nf_hook_ops[] = { { .hook = ila_nf_input, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = -1, }, }; static DEFINE_MUTEX(ila_mutex); static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_map *ila, *head; spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; if (!READ_ONCE(ilan->xlat.hooks_registered)) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ mutex_lock(&ila_mutex); if (!ilan->xlat.hooks_registered) { err = nf_register_net_hooks(net, ila_nf_hook_ops, ARRAY_SIZE(ila_nf_hook_ops)); if (!err) WRITE_ONCE(ilan->xlat.hooks_registered, true); } mutex_unlock(&ila_mutex); if (err) return err; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); if (!ila) return -ENOMEM; ila_init_saved_csum(&xp->ip); ila->xp = *xp; order = ila_order(ila); spin_lock(lock); head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); if (!head) { /* New entry for the rhash_table */ err = rhashtable_lookup_insert_fast(&ilan->xlat.rhash_table, &ila->node, rht_params); } else { struct ila_map *tila = head, *prev = NULL; do { if (!ila_cmp_params(tila, xp)) { err = -EEXIST; goto out; } if (order > ila_order(tila)) break; prev = tila; tila = rcu_dereference_protected(tila->next, lockdep_is_held(lock)); } while (tila); if (prev) { /* Insert in sub list of head */ RCU_INIT_POINTER(ila->next, tila); rcu_assign_pointer(prev->next, ila); } else { /* Make this ila new head */ RCU_INIT_POINTER(ila->next, head); err = rhashtable_replace_fast(&ilan->xlat.rhash_table, &head->node, &ila->node, rht_params); if (err) goto out; } } out: spin_unlock(lock); if (err) kfree(ila); return err; } static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_map *ila, *head, *prev; spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = -ENOENT; spin_lock(lock); head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); ila = head; prev = NULL; while (ila) { if (ila_cmp_params(ila, xp)) { prev = ila; ila = rcu_dereference_protected(ila->next, lockdep_is_held(lock)); continue; } err = 0; if (prev) { /* Not head, just delete from list */ rcu_assign_pointer(prev->next, ila->next); } else { /* It is the head. If there is something in the * sublist we need to make a new head. */ head = rcu_dereference_protected(ila->next, lockdep_is_held(lock)); if (head) { /* Put first entry in the sublist into the * table */ err = rhashtable_replace_fast( &ilan->xlat.rhash_table, &ila->node, &head->node, rht_params); if (err) goto out; } else { /* Entry no longer used */ err = rhashtable_remove_fast( &ilan->xlat.rhash_table, &ila->node, rht_params); } } ila_release(ila); break; } out: spin_unlock(lock); return err; } int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params p; int err; err = parse_nl_config(info, &p); if (err) return err; return ila_add_mapping(net, &p); } int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params xp; int err; err = parse_nl_config(info, &xp); if (err) return err; ila_del_mapping(net, &xp); return 0; } static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan, struct ila_map *ila) { return ila_get_lock(ilan, ila->xp.ip.locator_match); } int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_net *ilan = net_generic(net, ila_net_id); struct rhashtable_iter iter; struct ila_map *ila; spinlock_t *lock; int ret = 0; rhashtable_walk_enter(&ilan->xlat.rhash_table, &iter); rhashtable_walk_start(&iter); for (;;) { ila = rhashtable_walk_next(&iter); if (IS_ERR(ila)) { if (PTR_ERR(ila) == -EAGAIN) continue; ret = PTR_ERR(ila); goto done; } else if (!ila) { break; } lock = lock_from_ila_map(ilan, ila); spin_lock(lock); ret = rhashtable_remove_fast(&ilan->xlat.rhash_table, &ila->node, rht_params); if (!ret) ila_free_node(ila); spin_unlock(lock); if (ret) break; } done: rhashtable_walk_stop(&iter); rhashtable_walk_exit(&iter); return ret; } static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) { if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR, (__force u64)ila->xp.ip.locator.v64, ILA_ATTR_PAD) || nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR_MATCH, (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode) || nla_put_u8(msg, ILA_ATTR_IDENT_TYPE, ila->xp.ip.ident_type)) return -1; return 0; } static int ila_dump_info(struct ila_map *ila, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &ila_nl_family, flags, cmd); if (!hdr) return -ENOMEM; if (ila_fill_info(ila, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_net *ilan = net_generic(net, ila_net_id); struct sk_buff *msg; struct ila_xlat_params xp; struct ila_map *ila; int ret; ret = parse_nl_config(info, &xp); if (ret) return ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rcu_read_lock(); ret = -ESRCH; ila = ila_lookup_by_params(&xp, ilan); if (ila) { ret = ila_dump_info(ila, info->snd_portid, info->snd_seq, 0, msg, info->genlhdr->cmd); } rcu_read_unlock(); if (ret < 0) goto out_free; return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); return ret; } struct ila_dump_iter { struct rhashtable_iter rhiter; int skip; }; int ila_xlat_nl_dump_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_dump_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; rhashtable_walk_enter(&ilan->xlat.rhash_table, &iter->rhiter); iter->skip = 0; cb->args[0] = (long)iter; return 0; } int ila_xlat_nl_dump_done(struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; rhashtable_walk_exit(&iter->rhiter); kfree(iter); return 0; } int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; struct rhashtable_iter *rhiter = &iter->rhiter; int skip = iter->skip; struct ila_map *ila; int ret; rhashtable_walk_start(rhiter); /* Get first entry */ ila = rhashtable_walk_peek(rhiter); if (ila && !IS_ERR(ila) && skip) { /* Skip over visited entries */ while (ila && skip) { /* Skip over any ila entries in this list that we * have already dumped. */ ila = rcu_access_pointer(ila->next); skip--; } } skip = 0; for (;;) { if (IS_ERR(ila)) { ret = PTR_ERR(ila); if (ret == -EAGAIN) { /* Table has changed and iter has reset. Return * -EAGAIN to the application even if we have * written data to the skb. The application * needs to deal with this. */ goto out_ret; } else { break; } } else if (!ila) { ret = 0; break; } while (ila) { ret = ila_dump_info(ila, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, ILA_CMD_GET); if (ret) goto out; skip++; ila = rcu_access_pointer(ila->next); } skip = 0; ila = rhashtable_walk_next(rhiter); } out: iter->skip = skip; ret = (skb->len ? : ret); out_ret: rhashtable_walk_stop(rhiter); return ret; } int ila_xlat_init_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); int err; err = alloc_ila_locks(ilan); if (err) return err; err = rhashtable_init(&ilan->xlat.rhash_table, &rht_params); if (err) { free_bucket_spinlocks(ilan->xlat.locks); return err; } return 0; } void ila_xlat_pre_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); if (ilan->xlat.hooks_registered) nf_unregister_net_hooks(net, ila_nf_hook_ops, ARRAY_SIZE(ila_nf_hook_ops)); } void ila_xlat_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL); free_bucket_spinlocks(ilan->xlat.locks); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); /* Assumes skb contains a valid IPv6 header that is pulled */ /* No check here that ILA type in the mapping matches what is in the * address. We assume that whatever sender gaves us can be translated. * The checksum mode however is relevant. */ rcu_read_lock(); ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) ila_update_ipv6_locator(skb, &ila->xp.ip, sir2ila); rcu_read_unlock(); return 0; } |
| 251 249 187 187 15 15 15 15 15 15 19 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/pagemap.h> #include "squashfs_fs_sb.h" #include "decompressor.h" #include "page_actor.h" /* * This file contains implementations of page_actor for decompressing into * an intermediate buffer, and for decompressing directly into the * page cache. * * Calling code should avoid sleeping between calls to squashfs_first_page() * and squashfs_finish_page(). */ /* Implementation of page_actor for decompressing into intermediate buffer */ static void *cache_first_page(struct squashfs_page_actor *actor) { actor->next_page = 1; return actor->buffer[0]; } static void *cache_next_page(struct squashfs_page_actor *actor) { if (actor->next_page == actor->pages) return NULL; return actor->buffer[actor->next_page++]; } static void cache_finish_page(struct squashfs_page_actor *actor) { /* empty */ } struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, int pages, int length) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; actor->length = length ? : pages * PAGE_SIZE; actor->buffer = buffer; actor->pages = pages; actor->next_page = 0; actor->tmp_buffer = NULL; actor->squashfs_first_page = cache_first_page; actor->squashfs_next_page = cache_next_page; actor->squashfs_finish_page = cache_finish_page; return actor; } /* Implementation of page_actor for decompressing directly into page cache. */ static loff_t page_next_index(struct squashfs_page_actor *actor) { return page_folio(actor->page[actor->next_page])->index; } static void *handle_next_page(struct squashfs_page_actor *actor) { int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT; if (actor->returned_pages == max_pages) return NULL; if ((actor->next_page == actor->pages) || (actor->next_index != page_next_index(actor))) { actor->next_index++; actor->returned_pages++; actor->last_page = NULL; return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM); } actor->next_index++; actor->returned_pages++; actor->last_page = actor->page[actor->next_page]; return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]); } static void *direct_first_page(struct squashfs_page_actor *actor) { return handle_next_page(actor); } static void *direct_next_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) { kunmap_local(actor->pageaddr); actor->pageaddr = NULL; } return handle_next_page(actor); } static void direct_finish_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) kunmap_local(actor->pageaddr); } struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, struct page **page, int pages, int length, loff_t start_index) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; if (msblk->decompressor->alloc_buffer) { actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (actor->tmp_buffer == NULL) { kfree(actor); return NULL; } } else actor->tmp_buffer = NULL; actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; actor->returned_pages = 0; actor->next_index = start_index >> PAGE_SHIFT; actor->pageaddr = NULL; actor->last_page = NULL; actor->alloc_buffer = msblk->decompressor->alloc_buffer; actor->squashfs_first_page = direct_first_page; actor->squashfs_next_page = direct_next_page; actor->squashfs_finish_page = direct_finish_page; return actor; } |
| 16 175 2 11 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct skb_array' datastructure. * * Author: * Michael S. Tsirkin <mst@redhat.com> * * Copyright (C) 2016 Red Hat, Inc. * * Limited-size FIFO of skbs. Can be used more or less whenever * sk_buff_head can be used, except you need to know the queue size in * advance. * Implemented as a type-safe wrapper around ptr_ring. */ #ifndef _LINUX_SKB_ARRAY_H #define _LINUX_SKB_ARRAY_H 1 #ifdef __KERNEL__ #include <linux/ptr_ring.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #endif struct skb_array { struct ptr_ring ring; }; /* Might be slightly faster than skb_array_full below, but callers invoking * this in a loop must use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_full(struct skb_array *a) { return __ptr_ring_full(&a->ring); } static inline bool skb_array_full(struct skb_array *a) { return ptr_ring_full(&a->ring); } static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce(&a->ring, skb); } static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_irq(&a->ring, skb); } static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_bh(&a->ring, skb); } static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_any(&a->ring, skb); } /* Might be slightly faster than skb_array_empty below, but only safe if the * array is never resized. Also, callers invoking this in a loop must take care * to use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_empty(struct skb_array *a) { return __ptr_ring_empty(&a->ring); } static inline struct sk_buff *__skb_array_peek(struct skb_array *a) { return __ptr_ring_peek(&a->ring); } static inline bool skb_array_empty(struct skb_array *a) { return ptr_ring_empty(&a->ring); } static inline bool skb_array_empty_bh(struct skb_array *a) { return ptr_ring_empty_bh(&a->ring); } static inline bool skb_array_empty_irq(struct skb_array *a) { return ptr_ring_empty_irq(&a->ring); } static inline bool skb_array_empty_any(struct skb_array *a) { return ptr_ring_empty_any(&a->ring); } static inline struct sk_buff *__skb_array_consume(struct skb_array *a) { return __ptr_ring_consume(&a->ring); } static inline struct sk_buff *skb_array_consume(struct skb_array *a) { return ptr_ring_consume(&a->ring); } static inline int skb_array_consume_batched(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) { return ptr_ring_consume_irq(&a->ring); } static inline int skb_array_consume_batched_irq(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_irq(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) { return ptr_ring_consume_any(&a->ring); } static inline int skb_array_consume_batched_any(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_any(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) { return ptr_ring_consume_bh(&a->ring); } static inline int skb_array_consume_batched_bh(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_bh(&a->ring, (void **)array, n); } static inline int __skb_array_len_with_tag(struct sk_buff *skb) { if (likely(skb)) { int len = skb->len; if (skb_vlan_tag_present(skb)) len += VLAN_HLEN; return len; } else { return 0; } } static inline int skb_array_peek_len(struct skb_array *a) { return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_irq(struct skb_array *a) { return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_bh(struct skb_array *a) { return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_any(struct skb_array *a) { return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_init_noprof(&a->ring, size, gfp); } #define skb_array_init(...) alloc_hooks(skb_array_init_noprof(__VA_ARGS__)) static void __skb_array_destroy_skb(void *ptr) { kfree_skb(ptr); } static inline void skb_array_unconsume(struct skb_array *a, struct sk_buff **skbs, int n) { ptr_ring_unconsume(&a->ring, (void **)skbs, n, __skb_array_destroy_skb); } static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } static inline int skb_array_resize_multiple_bh_noprof(struct skb_array **rings, int nrings, unsigned int size, gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple_bh_noprof((struct ptr_ring **)rings, nrings, size, gfp, __skb_array_destroy_skb); } #define skb_array_resize_multiple_bh(...) \ alloc_hooks(skb_array_resize_multiple_bh_noprof(__VA_ARGS__)) static inline void skb_array_cleanup(struct skb_array *a) { ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb); } #endif /* _LINUX_SKB_ARRAY_H */ |
| 48 48 47 48 48 48 43 43 45 45 45 45 45 45 45 45 46 2 45 44 45 30 30 30 30 30 30 30 30 30 47 47 51 47 39 52 52 51 52 51 1 52 8 47 8 3 5 8 47 47 47 47 47 46 47 47 47 47 8 8 8 8 8 39 39 39 39 39 39 39 39 39 39 39 39 39 39 56 1 3 52 46 8 10 38 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006 Thomas Gleixner * * This file contains driver APIs to the irq subsystem. */ #define pr_fmt(fmt) "genirq: " fmt #include <linux/irq.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/random.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> #include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> #include "internals.h" #if defined(CONFIG_IRQ_FORCED_THREADING) && !defin |