| 10 6 10 10 10 6 5 4 1 2 2 2 2 2 2 2 1 4 1 3 3 1 1 2 16 1 5 5 5 6 26 18 9 21 6 30 30 29 30 30 30 29 30 30 30 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux I2C core SMBus and SMBus emulation code * * This file contains the SMBus functions which are always included in the I2C * core because they can be emulated via I2C. SMBus specific extensions * (e.g. smbalert) are handled in a separate i2c-smbus module. * * All SMBus-related things are written by Frodo Looijaard <frodol@dds.nl> * SMBus 2.0 support by Mark Studebaker <mdsxyz123@yahoo.com> and * Jean Delvare <jdelvare@suse.de> */ #include <linux/device.h> #include <linux/err.h> #include <linux/i2c.h> #include <linux/i2c-smbus.h> #include <linux/property.h> #include <linux/slab.h> #include "i2c-core.h" #define CREATE_TRACE_POINTS #include <trace/events/smbus.h> /* The SMBus parts */ #define POLY (0x1070U << 3) static u8 crc8(u16 data) { int i; for (i = 0; i < 8; i++) { if (data & 0x8000) data = data ^ POLY; data = data << 1; } return (u8)(data >> 8); } /** * i2c_smbus_pec - Incremental CRC8 over the given input data array * @crc: previous return crc8 value * @p: pointer to data buffer. * @count: number of bytes in data buffer. * * Incremental CRC8 over count bytes in the array pointed to by p */ u8 i2c_smbus_pec(u8 crc, u8 *p, size_t count) { int i; for (i = 0; i < count; i++) crc = crc8((crc ^ p[i]) << 8); return crc; } EXPORT_SYMBOL(i2c_smbus_pec); /* Assume a 7-bit address, which is reasonable for SMBus */ static u8 i2c_smbus_msg_pec(u8 pec, struct i2c_msg *msg) { /* The address will be sent first */ u8 addr = i2c_8bit_addr_from_msg(msg); pec = i2c_smbus_pec(pec, &addr, 1); /* The data buffer follows */ return i2c_smbus_pec(pec, msg->buf, msg->len); } /* Used for write only transactions */ static inline void i2c_smbus_add_pec(struct i2c_msg *msg) { msg->buf[msg->len] = i2c_smbus_msg_pec(0, msg); msg->len++; } /* Return <0 on CRC error If there was a write before this read (most cases) we need to take the partial CRC from the write part into account. Note that this function does modify the message (we need to decrease the message length to hide the CRC byte from the caller). */ static int i2c_smbus_check_pec(u8 cpec, struct i2c_msg *msg) { u8 rpec = msg->buf[--msg->len]; cpec = i2c_smbus_msg_pec(cpec, msg); if (rpec != cpec) { pr_debug("Bad PEC 0x%02x vs. 0x%02x\n", rpec, cpec); return -EBADMSG; } return 0; } /** * i2c_smbus_read_byte - SMBus "receive byte" protocol * @client: Handle to slave device * * This executes the SMBus "receive byte" protocol, returning negative errno * else the byte received from the device. */ s32 i2c_smbus_read_byte(const struct i2c_client *client) { union i2c_smbus_data data; int status; status = i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_READ, 0, I2C_SMBUS_BYTE, &data); return (status < 0) ? status : data.byte; } EXPORT_SYMBOL(i2c_smbus_read_byte); /** * i2c_smbus_write_byte - SMBus "send byte" protocol * @client: Handle to slave device * @value: Byte to be sent * * This executes the SMBus "send byte" protocol, returning negative errno * else zero on success. */ s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value) { return i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_WRITE, value, I2C_SMBUS_BYTE, NULL); } EXPORT_SYMBOL(i2c_smbus_write_byte); /** * i2c_smbus_read_byte_data - SMBus "read byte" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * * This executes the SMBus "read byte" protocol, returning negative errno * else a data byte received from the device. */ s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command) { union i2c_smbus_data data; int status; status = i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_READ, command, I2C_SMBUS_BYTE_DATA, &data); return (status < 0) ? status : data.byte; } EXPORT_SYMBOL(i2c_smbus_read_byte_data); /** * i2c_smbus_write_byte_data - SMBus "write byte" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * @value: Byte being written * * This executes the SMBus "write byte" protocol, returning negative errno * else zero on success. */ s32 i2c_smbus_write_byte_data(const struct i2c_client *client, u8 command, u8 value) { union i2c_smbus_data data; data.byte = value; return i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_WRITE, command, I2C_SMBUS_BYTE_DATA, &data); } EXPORT_SYMBOL(i2c_smbus_write_byte_data); /** * i2c_smbus_read_word_data - SMBus "read word" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * * This executes the SMBus "read word" protocol, returning negative errno * else a 16-bit unsigned "word" received from the device. */ s32 i2c_smbus_read_word_data(const struct i2c_client *client, u8 command) { union i2c_smbus_data data; int status; status = i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_READ, command, I2C_SMBUS_WORD_DATA, &data); return (status < 0) ? status : data.word; } EXPORT_SYMBOL(i2c_smbus_read_word_data); /** * i2c_smbus_write_word_data - SMBus "write word" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * @value: 16-bit "word" being written * * This executes the SMBus "write word" protocol, returning negative errno * else zero on success. */ s32 i2c_smbus_write_word_data(const struct i2c_client *client, u8 command, u16 value) { union i2c_smbus_data data; data.word = value; return i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_WRITE, command, I2C_SMBUS_WORD_DATA, &data); } EXPORT_SYMBOL(i2c_smbus_write_word_data); /** * i2c_smbus_read_block_data - SMBus "block read" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * @values: Byte array into which data will be read; big enough to hold * the data returned by the slave. SMBus allows at most 32 bytes. * * This executes the SMBus "block read" protocol, returning negative errno * else the number of data bytes in the slave's response. * * Note that using this function requires that the client's adapter support * the I2C_FUNC_SMBUS_READ_BLOCK_DATA functionality. Not all adapter drivers * support this; its emulation through I2C messaging relies on a specific * mechanism (I2C_M_RECV_LEN) which may not be implemented. */ s32 i2c_smbus_read_block_data(const struct i2c_client *client, u8 command, u8 *values) { union i2c_smbus_data data; int status; status = i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_READ, command, I2C_SMBUS_BLOCK_DATA, &data); if (status) return status; memcpy(values, &data.block[1], data.block[0]); return data.block[0]; } EXPORT_SYMBOL(i2c_smbus_read_block_data); /** * i2c_smbus_write_block_data - SMBus "block write" protocol * @client: Handle to slave device * @command: Byte interpreted by slave * @length: Size of data block; SMBus allows at most 32 bytes * @values: Byte array which will be written. * * This executes the SMBus "block write" protocol, returning negative errno * else zero on success. */ s32 i2c_smbus_write_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values) { union i2c_smbus_data data; if (length > I2C_SMBUS_BLOCK_MAX) length = I2C_SMBUS_BLOCK_MAX; data.block[0] = length; memcpy(&data.block[1], values, length); return i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_WRITE, command, I2C_SMBUS_BLOCK_DATA, &data); } EXPORT_SYMBOL(i2c_smbus_write_block_data); /* Returns the number of read bytes */ s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, u8 *values) { union i2c_smbus_data data; int status; if (length > I2C_SMBUS_BLOCK_MAX) length = I2C_SMBUS_BLOCK_MAX; data.block[0] = length; status = i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_READ, command, I2C_SMBUS_I2C_BLOCK_DATA, &data); if (status < 0) return status; memcpy(values, &data.block[1], data.block[0]); return data.block[0]; } EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data); s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values) { union i2c_smbus_data data; if (length > I2C_SMBUS_BLOCK_MAX) length = I2C_SMBUS_BLOCK_MAX; data.block[0] = length; memcpy(data.block + 1, values, length); return i2c_smbus_xfer(client->adapter, client->addr, client->flags, I2C_SMBUS_WRITE, command, I2C_SMBUS_I2C_BLOCK_DATA, &data); } EXPORT_SYMBOL(i2c_smbus_write_i2c_block_data); static void i2c_smbus_try_get_dmabuf(struct i2c_msg *msg, u8 init_val) { bool is_read = msg->flags & I2C_M_RD; unsigned char *dma_buf; dma_buf = kzalloc(I2C_SMBUS_BLOCK_MAX + (is_read ? 2 : 3), GFP_KERNEL); if (!dma_buf) return; msg->buf = dma_buf; msg->flags |= I2C_M_DMA_SAFE; if (init_val) msg->buf[0] = init_val; } /* * Simulate a SMBus command using the I2C protocol. * No checking of parameters is done! */ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data) { /* * So we need to generate a series of msgs. In the case of writing, we * need to use only one message; when reading, we need two. We * initialize most things with sane defaults, to keep the code below * somewhat simpler. */ unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3]; unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2]; int nmsgs = read_write == I2C_SMBUS_READ ? 2 : 1; u8 partial_pec = 0; int status; struct i2c_msg msg[2] = { { .addr = addr, .flags = flags, .len = 1, .buf = msgbuf0, }, { .addr = addr, .flags = flags | I2C_M_RD, .len = 0, .buf = msgbuf1, }, }; bool wants_pec = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA); msgbuf0[0] = command; switch (size) { case I2C_SMBUS_QUICK: msg[0].len = 0; /* Special case: The read/write field is used as data */ msg[0].flags = flags | (read_write == I2C_SMBUS_READ ? I2C_M_RD : 0); nmsgs = 1; break; case I2C_SMBUS_BYTE: if (read_write == I2C_SMBUS_READ) { /* Special case: only a read! */ msg[0].flags = I2C_M_RD | flags; nmsgs = 1; } break; case I2C_SMBUS_BYTE_DATA: if (read_write == I2C_SMBUS_READ) msg[1].len = 1; else { msg[0].len = 2; msgbuf0[1] = data->byte; } break; case I2C_SMBUS_WORD_DATA: if (read_write == I2C_SMBUS_READ) msg[1].len = 2; else { msg[0].len = 3; msgbuf0[1] = data->word & 0xff; msgbuf0[2] = data->word >> 8; } break; case I2C_SMBUS_PROC_CALL: nmsgs = 2; /* Special case */ read_write = I2C_SMBUS_READ; msg[0].len = 3; msg[1].len = 2; msgbuf0[1] = data->word & 0xff; msgbuf0[2] = data->word >> 8; break; case I2C_SMBUS_BLOCK_DATA: if (read_write == I2C_SMBUS_READ) { msg[1].flags |= I2C_M_RECV_LEN; msg[1].len = 1; /* block length will be added by the underlying bus driver */ i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 2; if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); return -EINVAL; } i2c_smbus_try_get_dmabuf(&msg[0], command); memcpy(msg[0].buf + 1, data->block, msg[0].len - 1); } break; case I2C_SMBUS_BLOCK_PROC_CALL: nmsgs = 2; /* Another special case */ read_write = I2C_SMBUS_READ; if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); return -EINVAL; } msg[0].len = data->block[0] + 2; i2c_smbus_try_get_dmabuf(&msg[0], command); memcpy(msg[0].buf + 1, data->block, msg[0].len - 1); msg[1].flags |= I2C_M_RECV_LEN; msg[1].len = 1; /* block length will be added by the underlying bus driver */ i2c_smbus_try_get_dmabuf(&msg[1], 0); break; case I2C_SMBUS_I2C_BLOCK_DATA: if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block %s size %d\n", read_write == I2C_SMBUS_READ ? "read" : "write", data->block[0]); return -EINVAL; } if (read_write == I2C_SMBUS_READ) { msg[1].len = data->block[0]; i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 1; i2c_smbus_try_get_dmabuf(&msg[0], command); memcpy(msg[0].buf + 1, data->block + 1, data->block[0]); } break; default: dev_err(&adapter->dev, "Unsupported transaction %d\n", size); return -EOPNOTSUPP; } if (wants_pec) { /* Compute PEC if first message is a write */ if (!(msg[0].flags & I2C_M_RD)) { if (nmsgs == 1) /* Write only */ i2c_smbus_add_pec(&msg[0]); else /* Write followed by read */ partial_pec = i2c_smbus_msg_pec(0, &msg[0]); } /* Ask for PEC if last message is a read */ if (msg[nmsgs - 1].flags & I2C_M_RD) msg[nmsgs - 1].len++; } status = __i2c_transfer(adapter, msg, nmsgs); if (status < 0) goto cleanup; if (status != nmsgs) { status = -EIO; goto cleanup; } status = 0; /* Check PEC if last message is a read */ if (wants_pec && (msg[nmsgs - 1].flags & I2C_M_RD)) { status = i2c_smbus_check_pec(partial_pec, &msg[nmsgs - 1]); if (status < 0) goto cleanup; } if (read_write == I2C_SMBUS_READ) switch (size) { case I2C_SMBUS_BYTE: data->byte = msgbuf0[0]; break; case I2C_SMBUS_BYTE_DATA: data->byte = msgbuf1[0]; break; case I2C_SMBUS_WORD_DATA: case I2C_SMBUS_PROC_CALL: data->word = msgbuf1[0] | (msgbuf1[1] << 8); break; case I2C_SMBUS_I2C_BLOCK_DATA: memcpy(data->block + 1, msg[1].buf, data->block[0]); break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block size returned: %d\n", msg[1].buf[0]); status = -EPROTO; goto cleanup; } memcpy(data->block, msg[1].buf, msg[1].buf[0] + 1); break; } cleanup: if (msg[0].flags & I2C_M_DMA_SAFE) kfree(msg[0].buf); if (msg[1].flags & I2C_M_DMA_SAFE) kfree(msg[1].buf); return status; } /** * i2c_smbus_xfer - execute SMBus protocol operations * @adapter: Handle to I2C bus * @addr: Address of SMBus slave on that bus * @flags: I2C_CLIENT_* flags (usually zero or I2C_CLIENT_PEC) * @read_write: I2C_SMBUS_READ or I2C_SMBUS_WRITE * @command: Byte interpreted by slave, for protocols which use such bytes * @protocol: SMBus protocol operation to execute, such as I2C_SMBUS_PROC_CALL * @data: Data to be read or written * * This executes an SMBus protocol operation, and returns a negative * errno code else zero on success. */ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int protocol, union i2c_smbus_data *data) { s32 res; res = __i2c_lock_bus_helper(adapter); if (res) return res; res = __i2c_smbus_xfer(adapter, addr, flags, read_write, command, protocol, data); i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT); return res; } EXPORT_SYMBOL(i2c_smbus_xfer); s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int protocol, union i2c_smbus_data *data) { int (*xfer_func)(struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data); unsigned long orig_jiffies; int try; s32 res; res = __i2c_check_suspended(adapter); if (res) return res; /* If enabled, the following two tracepoints are conditional on * read_write and protocol. */ trace_smbus_write(adapter, addr, flags, read_write, command, protocol, data); trace_smbus_read(adapter, addr, flags, read_write, command, protocol); flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB; xfer_func = adapter->algo->smbus_xfer; if (i2c_in_atomic_xfer_mode()) { if (adapter->algo->smbus_xfer_atomic) xfer_func = adapter->algo->smbus_xfer_atomic; else if (adapter->algo->master_xfer_atomic) xfer_func = NULL; /* fallback to I2C emulation */ } if (xfer_func) { /* Retry automatically on arbitration loss */ orig_jiffies = jiffies; for (res = 0, try = 0; try <= adapter->retries; try++) { res = xfer_func(adapter, addr, flags, read_write, command, protocol, data); if (res != -EAGAIN) break; if (time_after(jiffies, orig_jiffies + adapter->timeout)) break; } if (res != -EOPNOTSUPP || !adapter->algo->master_xfer) goto trace; /* * Fall back to i2c_smbus_xfer_emulated if the adapter doesn't * implement native support for the SMBus operation. */ } res = i2c_smbus_xfer_emulated(adapter, addr, flags, read_write, command, protocol, data); trace: /* If enabled, the reply tracepoint is conditional on read_write. */ trace_smbus_reply(adapter, addr, flags, read_write, command, protocol, data, res); trace_smbus_result(adapter, addr, flags, read_write, command, protocol, res); return res; } EXPORT_SYMBOL(__i2c_smbus_xfer); /** * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate * @client: Handle to slave device * @command: Byte interpreted by slave * @length: Size of data block; SMBus allows at most I2C_SMBUS_BLOCK_MAX bytes * @values: Byte array into which data will be read; big enough to hold * the data returned by the slave. SMBus allows at most * I2C_SMBUS_BLOCK_MAX bytes. * * This executes the SMBus "block read" protocol if supported by the adapter. * If block read is not supported, it emulates it using either word or byte * read protocols depending on availability. * * The addresses of the I2C slave device that are accessed with this function * must be mapped to a linear region, so that a block read will have the same * effect as a byte read. Before using this function you must double-check * if the I2C slave does support exchanging a block transfer with a byte * transfer. */ s32 i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, u8 command, u8 length, u8 *values) { u8 i = 0; int status; if (length > I2C_SMBUS_BLOCK_MAX) length = I2C_SMBUS_BLOCK_MAX; if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_I2C_BLOCK)) return i2c_smbus_read_i2c_block_data(client, command, length, values); if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_BYTE_DATA)) return -EOPNOTSUPP; if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_WORD_DATA)) { while ((i + 2) <= length) { status = i2c_smbus_read_word_data(client, command + i); if (status < 0) return status; values[i] = status & 0xff; values[i + 1] = status >> 8; i += 2; } } while (i < length) { status = i2c_smbus_read_byte_data(client, command + i); if (status < 0) return status; values[i] = status; i++; } return i; } EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data_or_emulated); /** * i2c_new_smbus_alert_device - get ara client for SMBus alert support * @adapter: the target adapter * @setup: setup data for the SMBus alert handler * Context: can sleep * * Setup handling of the SMBus alert protocol on a given I2C bus segment. * * Handling can be done either through our IRQ handler, or by the * adapter (from its handler, periodic polling, or whatever). * * This returns the ara client, which should be saved for later use with * i2c_handle_smbus_alert() and ultimately i2c_unregister_device(); or an * ERRPTR to indicate an error. */ struct i2c_client *i2c_new_smbus_alert_device(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup) { struct i2c_board_info ara_board_info = { I2C_BOARD_INFO("smbus_alert", 0x0c), .platform_data = setup, }; return i2c_new_client_device(adapter, &ara_board_info); } EXPORT_SYMBOL_GPL(i2c_new_smbus_alert_device); #if IS_ENABLED(CONFIG_I2C_SMBUS) int i2c_setup_smbus_alert(struct i2c_adapter *adapter) { struct device *parent = adapter->dev.parent; int irq; /* Adapter instantiated without parent, skip the SMBus alert setup */ if (!parent) return 0; irq = device_property_match_string(parent, "interrupt-names", "smbus_alert"); if (irq == -EINVAL || irq == -ENODATA) return 0; else if (irq < 0) return irq; return PTR_ERR_OR_ZERO(i2c_new_smbus_alert_device(adapter, NULL)); } #endif |
| 11 3 25 38 25 25 1 9 40 30 11 44 8 10 8 44 58 8 8 58 44 14 59 59 59 32 28 42 18 18 42 18 34 1 43 46 46 22 46 45 46 21 46 9 68 5 54 29 60 17 68 54 29 60 17 68 68 9 9 9 51 7 7 7 9 9 9 9 67 68 39 39 30 30 68 63 5 68 68 5 63 68 68 67 68 68 68 68 1 67 55 27 66 4 4 67 67 59 9 68 68 49 49 49 2 3 3 49 2 2 2 2 57 26 59 9 9 97 97 77 58 58 40 39 68 67 58 51 22 21 19 7 7 58 51 21 58 58 11 1 1 5 1 5 2 2 13 13 40 25 25 25 32 26 4 4 16 58 55 58 58 2 55 45 29 58 5 5 5 33 10 41 3 3 3 3 3 2 2 2 2 30 30 30 41 3 3 3 2 30 41 35 2 31 41 1 37 3 30 11 28 13 37 1 2 38 3 38 2 38 2 39 2 39 2 39 37 35 3 3 35 3 3 38 3 36 5 36 2 3 39 2 38 18 4 39 39 38 38 38 38 17 1 16 17 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 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* COMMON Applications Kept Enhanced (CAKE) discipline * * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com> * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk> * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com> * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de> * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au> * * The CAKE Principles: * (or, how to have your cake and eat it too) * * This is a combination of several shaping, AQM and FQ techniques into one * easy-to-use package: * * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), * eliminating the need for any sort of burst parameter (eg. token bucket * depth). Burst support is limited to that necessary to overcome scheduling * latency. * * - A Diffserv-aware priority queue, giving more priority to certain classes, * up to a specified fraction of bandwidth. Above that bandwidth threshold, * the priority is reduced to avoid starving other tins. * * - Each priority tin has a separate Flow Queue system, to isolate traffic * flows from each other. This prevents a burst on one flow from increasing * the delay to another. Flows are distributed to queues using a * set-associative hash function. * * - Each queue is actively managed by Cobalt, which is a combination of the * Codel and Blue AQM algorithms. This serves flows fairly, and signals * congestion early via ECN (if available) and/or packet drops, to keep * latency low. The codel parameters are auto-tuned based on the bandwidth * setting, as is necessary at low bandwidths. * * The configuration parameters are kept deliberately simple for ease of use. * Everything has sane defaults. Complete generality of configuration is *not* * a goal. * * The priority queue operates according to a weighted DRR scheme, combined with * a bandwidth tracker which reuses the shaper logic to detect which side of the * bandwidth sharing threshold the tin is operating. This determines whether a * priority-based weight (high) or a bandwidth-based weight (low) is used for * that tin in the current pass. * * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly * granted us permission to leverage. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> #include <linux/if_vlan.h> #include <net/gso.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/flow_dissector.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif #define CAKE_SET_WAYS (8) #define CAKE_MAX_TINS (8) #define CAKE_QUEUES (1024) #define CAKE_FLOW_MASK 63 #define CAKE_FLOW_NAT_FLAG 64 /* struct cobalt_params - contains codel and blue parameters * @interval: codel initial drop rate * @target: maximum persistent sojourn time & blue update rate * @mtu_time: serialisation delay of maximum-size packet * @p_inc: increment of blue drop probability (0.32 fxp) * @p_dec: decrement of blue drop probability (0.32 fxp) */ struct cobalt_params { u64 interval; u64 target; u64 mtu_time; u32 p_inc; u32 p_dec; }; /* struct cobalt_vars - contains codel and blue variables * @count: codel dropping frequency * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 * @drop_next: time to drop next packet, or when we dropped last * @blue_timer: Blue time to next drop * @p_drop: BLUE drop probability (0.32 fxp) * @dropping: set if in dropping state * @ecn_marked: set if marked */ struct cobalt_vars { u32 count; u32 rec_inv_sqrt; ktime_t drop_next; ktime_t blue_timer; u32 p_drop; bool dropping; bool ecn_marked; }; enum { CAKE_SET_NONE = 0, CAKE_SET_SPARSE, CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ CAKE_SET_BULK, CAKE_SET_DECAYING }; struct cake_flow { /* this stuff is all needed per-flow at dequeue time */ struct sk_buff *head; struct sk_buff *tail; struct list_head flowchain; s32 deficit; u32 dropped; struct cobalt_vars cvars; u16 srchost; /* index into cake_host table */ u16 dsthost; u8 set; }; /* please try to keep this structure <= 64 bytes */ struct cake_host { u32 srchost_tag; u32 dsthost_tag; u16 srchost_bulk_flow_count; u16 dsthost_bulk_flow_count; }; struct cake_heap_entry { u16 t:3, b:10; }; struct cake_tin_data { struct cake_flow flows[CAKE_QUEUES]; u32 backlogs[CAKE_QUEUES]; u32 tags[CAKE_QUEUES]; /* for set association */ u16 overflow_idx[CAKE_QUEUES]; struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ u16 flow_quantum; struct cobalt_params cparams; u32 drop_overlimit; u16 bulk_flow_count; u16 sparse_flow_count; u16 decaying_flow_count; u16 unresponsive_flow_count; u32 max_skblen; struct list_head new_flows; struct list_head old_flows; struct list_head decaying_flows; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ ktime_t time_next_packet; u64 tin_rate_ns; u64 tin_rate_bps; u16 tin_rate_shft; u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; u32 tin_ecn_mark; u32 packets; u64 bytes; u32 ack_drops; /* moving averages */ u64 avge_delay; u64 peak_delay; u64 base_delay; /* hash function stats */ u32 way_directs; u32 way_hits; u32 way_misses; u32 way_collisions; }; /* number of tins is small, so size of this struct doesn't matter much */ struct cake_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ struct tcf_block *block; struct cake_tin_data *tins; struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; u16 overflow_timeout; u16 tin_cnt; u8 tin_mode; u8 flow_mode; u8 ack_filter; u8 atm_mode; u32 fwmark_mask; u16 fwmark_shft; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ u16 rate_shft; ktime_t time_next_packet; ktime_t failsafe_next_packet; u64 rate_ns; u64 rate_bps; u16 rate_flags; s16 rate_overhead; u16 rate_mpu; u64 interval; u64 target; /* resource tracking */ u32 buffer_used; u32 buffer_max_used; u32 buffer_limit; u32 buffer_config_limit; /* indices for dequeue */ u16 cur_tin; u16 cur_flow; struct qdisc_watchdog watchdog; const u8 *tin_index; const u8 *tin_order; /* bandwidth capacity estimate */ ktime_t last_packet_time; ktime_t avg_window_begin; u64 avg_packet_interval; u64 avg_window_bytes; u64 avg_peak_bandwidth; ktime_t last_reconfig_time; /* packet length stats */ u32 avg_netoff; u16 max_netlen; u16 max_adjlen; u16 min_netlen; u16 min_adjlen; }; enum { CAKE_FLAG_OVERHEAD = BIT(0), CAKE_FLAG_AUTORATE_INGRESS = BIT(1), CAKE_FLAG_INGRESS = BIT(2), CAKE_FLAG_WASH = BIT(3), CAKE_FLAG_SPLIT_GSO = BIT(4) }; /* COBALT operates the Codel and BLUE algorithms in parallel, in order to * obtain the best features of each. Codel is excellent on flows which * respond to congestion signals in a TCP-like way. BLUE is more effective on * unresponsive flows. */ struct cobalt_skb_cb { ktime_t enqueue_time; u32 adjusted_len; }; static u64 us_to_ns(u64 us) { return us * NSEC_PER_USEC; } static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; } static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) { return get_cobalt_cb(skb)->enqueue_time; } static void cobalt_set_enqueue_time(struct sk_buff *skb, ktime_t now) { get_cobalt_cb(skb)->enqueue_time = now; } static u16 quantum_div[CAKE_QUEUES + 1] = {0}; /* Diffserv lookup tables */ static const u8 precedence[] = { 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, }; static const u8 diffserv8[] = { 2, 0, 1, 2, 4, 2, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 5, 2, 4, 2, 4, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 6, 2, 3, 2, 3, 2, 3, 2, 6, 2, 2, 2, 6, 2, 6, 2, 7, 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 2, 2, 2, 2, 2, }; static const u8 diffserv4[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 3, 0, 2, 0, 2, 0, 2, 0, 3, 0, 0, 0, 3, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, }; static const u8 diffserv3[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, }; static const u8 besteffort[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, }; /* tin priority order for stats dumping */ static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7}; static const u8 bulk_order[] = {1, 0, 2, 3}; #define REC_INV_SQRT_CACHE (16) static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0}; /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ static void cobalt_newton_step(struct cobalt_vars *vars) { u32 invsqrt, invsqrt2; u64 val; invsqrt = vars->rec_inv_sqrt; invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; val = (3LL << 32) - ((u64)vars->count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); vars->rec_inv_sqrt = val; } static void cobalt_invsqrt(struct cobalt_vars *vars) { if (vars->count < REC_INV_SQRT_CACHE) vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count]; else cobalt_newton_step(vars); } /* There is a big difference in timing between the accurate values placed in * the cache and the approximations given by a single Newton step for small * count values, particularly when stepping from count 1 to 2 or vice versa. * Above 16, a single Newton step gives sufficient accuracy in either * direction, given the precision stored. * * The magnitude of the error when stepping up to count 2 is such as to give * the value that *should* have been produced at count 4. */ static void cobalt_cache_init(void) { struct cobalt_vars v; memset(&v, 0, sizeof(v)); v.rec_inv_sqrt = ~0U; cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt; for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) { cobalt_newton_step(&v); cobalt_newton_step(&v); cobalt_newton_step(&v); cobalt_newton_step(&v); cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt; } } static void cobalt_vars_init(struct cobalt_vars *vars) { memset(vars, 0, sizeof(*vars)); if (!cobalt_rec_inv_sqrt_cache[0]) { cobalt_cache_init(); cobalt_rec_inv_sqrt_cache[0] = ~0; } } /* CoDel control_law is t + interval/sqrt(count) * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid * both sqrt() and divide operation. */ static ktime_t cobalt_control(ktime_t t, u64 interval, u32 rec_inv_sqrt) { return ktime_add_ns(t, reciprocal_scale(interval, rec_inv_sqrt)); } /* Call this when a packet had to be dropped due to queue overflow. Returns * true if the BLUE state was quiescent before but active after this call. */ static bool cobalt_queue_full(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool up = false; if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { up = !vars->p_drop; vars->p_drop += p->p_inc; if (vars->p_drop < p->p_inc) vars->p_drop = ~0; vars->blue_timer = now; } vars->dropping = true; vars->drop_next = now; if (!vars->count) vars->count = 1; return up; } /* Call this when the queue was serviced but turned out to be empty. Returns * true if the BLUE state was active before but quiescent after this call. */ static bool cobalt_queue_empty(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool down = false; if (vars->p_drop && ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { if (vars->p_drop < p->p_dec) vars->p_drop = 0; else vars->p_drop -= p->p_dec; vars->blue_timer = now; down = !vars->p_drop; } vars->dropping = false; if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); } return down; } /* Call this with a freshly dequeued packet for possible congestion marking. * Returns true as an instruction to drop the packet, false for delivery. */ static bool cobalt_should_drop(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now, struct sk_buff *skb, u32 bulk_flows) { bool next_due, over_target, drop = false; ktime_t schedule; u64 sojourn; /* The 'schedule' variable records, in its sign, whether 'now' is before or * after 'drop_next'. This allows 'drop_next' to be updated before the next * scheduling decision is actually branched, without destroying that * information. Similarly, the first 'schedule' value calculated is preserved * in the boolean 'next_due'. * * As for 'drop_next', we take advantage of the fact that 'interval' is both * the delay between first exceeding 'target' and the first signalling event, * *and* the scaling factor for the signalling frequency. It's therefore very * natural to use a single mechanism for both purposes, and eliminates a * significant amount of reference Codel's spaghetti code. To help with this, * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close * as possible to 1.0 in fixed-point. */ sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); schedule = ktime_sub(now, vars->drop_next); over_target = sojourn > p->target && sojourn > p->mtu_time * bulk_flows * 2 && sojourn > p->mtu_time * 4; next_due = vars->count && ktime_to_ns(schedule) >= 0; vars->ecn_marked = false; if (over_target) { if (!vars->dropping) { vars->dropping = true; vars->drop_next = cobalt_control(now, p->interval, vars->rec_inv_sqrt); } if (!vars->count) vars->count = 1; } else if (vars->dropping) { vars->dropping = false; } if (next_due && vars->dropping) { /* Use ECN mark if possible, otherwise drop */ drop = !(vars->ecn_marked = INET_ECN_set_ce(skb)); vars->count++; if (!vars->count) vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); } else { while (next_due) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); next_due = vars->count && ktime_to_ns(schedule) >= 0; } } /* Simple BLUE implementation. Lack of ECN is deliberate. */ if (vars->p_drop) drop |= (get_random_u32() < vars->p_drop); /* Overload the drop_next field as an activity timeout */ if (!vars->count) vars->drop_next = ktime_add_ns(now, p->interval); else if (ktime_to_ns(schedule) > 0 && !drop) vars->drop_next = now; return drop; } static bool cake_update_flowkeys(struct flow_keys *keys, const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct, upd = false; __be32 ip; if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) return false; ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip; if (ip != keys->addrs.v4addrs.src) { keys->addrs.v4addrs.src = ip; upd = true; } ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip; if (ip != keys->addrs.v4addrs.dst) { keys->addrs.v4addrs.dst = ip; upd = true; } if (keys->ports.ports) { __be16 port; port = rev ? tuple.dst.u.all : tuple.src.u.all; if (port != keys->ports.src) { keys->ports.src = port; upd = true; } port = rev ? tuple.src.u.all : tuple.dst.u.all; if (port != keys->ports.dst) { port = keys->ports.dst; upd = true; } } return upd; #else return false; #endif } /* Cake has several subtle multiple bit settings. In these cases you * would be matching triple isolate mode as well. */ static bool cake_dsrc(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC; } static bool cake_ddst(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode, u16 flow_override, u16 host_override) { bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS)); bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS)); bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG); u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; bool use_skbhash = skb->l4_hash; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; /* If both overrides are set, or we can use the SKB hash and nat mode is * disabled, we can skip packet dissection entirely. If nat mode is * enabled there's another check below after doing the conntrack lookup. */ if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts) goto skip_hash; skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); /* Don't use the SKB hash if we change the lookup keys from conntrack */ if (nat_enabled && cake_update_flowkeys(&keys, skb)) use_skbhash = false; /* If we can still use the SKB hash and don't need the host hash, we can * skip the rest of the hashing procedure */ if (use_skbhash && !hash_hosts) goto skip_hash; /* flow_hash_from_keys() sorts the addresses by value, so we have * to preserve their order in a separate data structure to treat * src and dst host addresses as independently selectable. */ host_keys = keys; host_keys.ports.ports = 0; host_keys.basic.ip_proto = 0; host_keys.keyid.keyid = 0; host_keys.tags.flow_label = 0; switch (host_keys.control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: host_keys.addrs.v4addrs.src = 0; dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; host_keys.addrs.v4addrs.dst = 0; srchost_hash = flow_hash_from_keys(&host_keys); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: memset(&host_keys.addrs.v6addrs.src, 0, sizeof(host_keys.addrs.v6addrs.src)); dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; memset(&host_keys.addrs.v6addrs.dst, 0, sizeof(host_keys.addrs.v6addrs.dst)); srchost_hash = flow_hash_from_keys(&host_keys); break; default: dsthost_hash = 0; srchost_hash = 0; } /* This *must* be after the above switch, since as a * side-effect it sorts the src and dst addresses. */ if (hash_flows && !use_skbhash) flow_hash = flow_hash_from_keys(&keys); skip_hash: if (flow_override) flow_hash = flow_override - 1; else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; srchost_hash = host_override - 1; } if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; if (flow_mode & CAKE_FLOW_DST_IP) flow_hash ^= dsthost_hash; } reduced_hash = flow_hash % CAKE_QUEUES; /* set-associative hashing */ /* fast path if no hash collision (direct lookup succeeds) */ if (likely(q->tags[reduced_hash] == flow_hash && q->flows[reduced_hash].set)) { q->way_directs++; } else { u32 inner_hash = reduced_hash % CAKE_SET_WAYS; u32 outer_hash = reduced_hash - inner_hash; bool allocate_src = false; bool allocate_dst = false; u32 i, k; /* check if any active queue in the set is reserved for * this flow. */ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->tags[outer_hash + k] == flow_hash) { if (i) q->way_hits++; if (!q->flows[outer_hash + k].set) { /* need to increment host refcnts */ allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); } goto found; } } /* no queue is reserved for this flow, look for an * empty one. */ for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->flows[outer_hash + k].set) { q->way_misses++; allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); goto found; } } /* With no empty queues, default to the original * queue, accept the collision, update the host tags. */ q->way_collisions++; if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; } allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); found: /* reserve queue for future packets in same flow */ reduced_hash = outer_hash + k; q->tags[reduced_hash] = flow_hash; if (allocate_src) { srchost_idx = srchost_hash % CAKE_QUEUES; inner_hash = srchost_idx % CAKE_SET_WAYS; outer_hash = srchost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].srchost_tag == srchost_hash) goto found_src; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].srchost_bulk_flow_count) break; } q->hosts[outer_hash + k].srchost_tag = srchost_hash; found_src: srchost_idx = outer_hash + k; if (q->flows[reduced_hash].set == CAKE_SET_BULK) q->hosts[srchost_idx].srchost_bulk_flow_count++; q->flows[reduced_hash].srchost = srchost_idx; } if (allocate_dst) { dsthost_idx = dsthost_hash % CAKE_QUEUES; inner_hash = dsthost_idx % CAKE_SET_WAYS; outer_hash = dsthost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].dsthost_tag == dsthost_hash) goto found_dst; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count) break; } q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; found_dst: dsthost_idx = outer_hash + k; if (q->flows[reduced_hash].set == CAKE_SET_BULK) q->hosts[dsthost_idx].dsthost_bulk_flow_count++; q->flows[reduced_hash].dsthost = dsthost_idx; } } return reduced_hash; } /* helper functions : might be changed when/if skb use a standard list_head */ /* remove one skb from head of slot queue */ static struct sk_buff *dequeue_head(struct cake_flow *flow) { struct sk_buff *skb = flow->head; if (skb) { flow->head = skb->next; skb_mark_not_on_list(skb); } return skb; } /* add skb to flow queue (tail add) */ static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) { if (!flow->head) flow->head = skb; else flow->tail->next = skb; flow->tail = skb; skb->next = NULL; } static struct iphdr *cake_get_iphdr(const struct sk_buff *skb, struct ipv6hdr *buf) { unsigned int offset = skb_network_offset(skb); struct iphdr *iph; iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf); if (!iph) return NULL; if (iph->version == 4 && iph->protocol == IPPROTO_IPV6) return skb_header_pointer(skb, offset + iph->ihl * 4, sizeof(struct ipv6hdr), buf); else if (iph->version == 4) return iph; else if (iph->version == 6) return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr), buf); return NULL; } static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, void *buf, unsigned int bufsize) { unsigned int offset = skb_network_offset(skb); const struct ipv6hdr *ipv6h; const struct tcphdr *tcph; const struct iphdr *iph; struct ipv6hdr _ipv6h; struct tcphdr _tcph; ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h) return NULL; if (ipv6h->version == 4) { iph = (struct iphdr *)ipv6h; offset += iph->ihl * 4; /* special-case 6in4 tunnelling, as that is a common way to get * v6 connectivity in the home */ if (iph->protocol == IPPROTO_IPV6) { ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else if (iph->protocol != IPPROTO_TCP) { return NULL; } } else if (ipv6h->version == 6) { if (ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else { return NULL; } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, min(__tcp_hdrlen(tcph), bufsize), buf); } static const void *cake_get_tcpopt(const struct tcphdr *tcph, int code, int *oplen) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; if (opcode == code) { *oplen = opsize; return ptr; } ptr += opsize - 2; length -= opsize; } return NULL; } /* Compare two SACK sequences. A sequence is considered greater if it SACKs more * bytes than the other. In the case where both sequences ACKs bytes that the * other doesn't, A is considered greater. DSACKs in A also makes A be * considered greater. * * @return -1, 0 or 1 as normal compare functions */ static int cake_tcph_sack_compare(const struct tcphdr *tcph_a, const struct tcphdr *tcph_b) { const struct tcp_sack_block_wire *sack_a, *sack_b; u32 ack_seq_a = ntohl(tcph_a->ack_seq); u32 bytes_a = 0, bytes_b = 0; int oplen_a, oplen_b; bool first = true; sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a); sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b); /* pointers point to option contents */ oplen_a -= TCPOLEN_SACK_BASE; oplen_b -= TCPOLEN_SACK_BASE; if (sack_a && oplen_a >= sizeof(*sack_a) && (!sack_b || oplen_b < sizeof(*sack_b))) return -1; else if (sack_b && oplen_b >= sizeof(*sack_b) && (!sack_a || oplen_a < sizeof(*sack_a))) return 1; else if ((!sack_a || oplen_a < sizeof(*sack_a)) && (!sack_b || oplen_b < sizeof(*sack_b))) return 0; while (oplen_a >= sizeof(*sack_a)) { const struct tcp_sack_block_wire *sack_tmp = sack_b; u32 start_a = get_unaligned_be32(&sack_a->start_seq); u32 end_a = get_unaligned_be32(&sack_a->end_seq); int oplen_tmp = oplen_b; bool found = false; /* DSACK; always considered greater to prevent dropping */ if (before(start_a, ack_seq_a)) return -1; bytes_a += end_a - start_a; while (oplen_tmp >= sizeof(*sack_tmp)) { u32 start_b = get_unaligned_be32(&sack_tmp->start_seq); u32 end_b = get_unaligned_be32(&sack_tmp->end_seq); /* first time through we count the total size */ if (first) bytes_b += end_b - start_b; if (!after(start_b, start_a) && !before(end_b, end_a)) { found = true; if (!first) break; } oplen_tmp -= sizeof(*sack_tmp); sack_tmp++; } if (!found) return -1; oplen_a -= sizeof(*sack_a); sack_a++; first = false; } /* If we made it this far, all ranges SACKed by A are covered by B, so * either the SACKs are equal, or B SACKs more bytes. */ return bytes_b > bytes_a ? 1 : 0; } static void cake_tcph_get_tstamp(const struct tcphdr *tcph, u32 *tsval, u32 *tsecr) { const u8 *ptr; int opsize; ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize); if (ptr && opsize == TCPOLEN_TIMESTAMP) { *tsval = get_unaligned_be32(ptr); *tsecr = get_unaligned_be32(ptr + 4); } } static bool cake_tcph_may_drop(const struct tcphdr *tcph, u32 tstamp_new, u32 tsecr_new) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); u32 tstamp, tsecr; /* 3 reserved flags must be unset to avoid future breakage * ACK must be set * ECE/CWR are handled separately * All other flags URG/PSH/RST/SYN/FIN must be unset * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero) * 0x00C00000 = CWR/ECE (handled separately) * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000 */ if (((tcp_flag_word(tcph) & cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK)) return false; while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; switch (opcode) { case TCPOPT_MD5SIG: /* doesn't influence state */ break; case TCPOPT_SACK: /* stricter checking performed later */ if (opsize % 8 != 2) return false; break; case TCPOPT_TIMESTAMP: /* only drop timestamps lower than new */ if (opsize != TCPOLEN_TIMESTAMP) return false; tstamp = get_unaligned_be32(ptr); tsecr = get_unaligned_be32(ptr + 4); if (after(tstamp, tstamp_new) || after(tsecr, tsecr_new)) return false; break; case TCPOPT_MSS: /* these should only be set on SYN */ case TCPOPT_WINDOW: case TCPOPT_SACK_PERM: case TCPOPT_FASTOPEN: case TCPOPT_EXP: default: /* don't drop if any unknown options are present */ return false; } ptr += opsize - 2; length -= opsize; } return true; } static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, struct cake_flow *flow) { bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE; struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL; struct sk_buff *skb_check, *skb_prev = NULL; const struct ipv6hdr *ipv6h, *ipv6h_check; unsigned char _tcph[64], _tcph_check[64]; const struct tcphdr *tcph, *tcph_check; const struct iphdr *iph, *iph_check; struct ipv6hdr _iph, _iph_check; const struct sk_buff *skb; int seglen, num_found = 0; u32 tstamp = 0, tsecr = 0; __be32 elig_flags = 0; int sack_comp; /* no other possible ACKs to filter */ if (flow->head == flow->tail) return NULL; skb = flow->tail; tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph)); iph = cake_get_iphdr(skb, &_iph); if (!tcph) return NULL; cake_tcph_get_tstamp(tcph, &tstamp, &tsecr); /* the 'triggering' packet need only have the ACK flag set. * also check that SYN is not set, as there won't be any previous ACKs. */ if ((tcp_flag_word(tcph) & (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK) return NULL; /* the 'triggering' ACK is at the tail of the queue, we have already * returned if it is the only packet in the flow. loop through the rest * of the queue looking for pure ACKs with the same 5-tuple as the * triggering one. */ for (skb_check = flow->head; skb_check && skb_check != skb; skb_prev = skb_check, skb_check = skb_check->next) { iph_check = cake_get_iphdr(skb_check, &_iph_check); tcph_check = cake_get_tcphdr(skb_check, &_tcph_check, sizeof(_tcph_check)); /* only TCP packets with matching 5-tuple are eligible, and only * drop safe headers */ if (!tcph_check || iph->version != iph_check->version || tcph_check->source != tcph->source || tcph_check->dest != tcph->dest) continue; if (iph_check->version == 4) { if (iph_check->saddr != iph->saddr || iph_check->daddr != iph->daddr) continue; seglen = iph_totlen(skb, iph_check) - (4 * iph_check->ihl); } else if (iph_check->version == 6) { ipv6h = (struct ipv6hdr *)iph; ipv6h_check = (struct ipv6hdr *)iph_check; if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) || ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr)) continue; seglen = ntohs(ipv6h_check->payload_len); } else { WARN_ON(1); /* shouldn't happen */ continue; } /* If the ECE/CWR flags changed from the previous eligible * packet in the same flow, we should no longer be dropping that * previous packet as this would lose information. */ if (elig_ack && (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) { elig_ack = NULL; elig_ack_prev = NULL; num_found--; } /* Check TCP options and flags, don't drop ACKs with segment * data, and don't drop ACKs with a higher cumulative ACK * counter than the triggering packet. Check ACK seqno here to * avoid parsing SACK options of packets we are going to exclude * anyway. */ if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) || (seglen - __tcp_hdrlen(tcph_check)) != 0 || after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq))) continue; /* Check SACK options. The triggering packet must SACK more data * than the ACK under consideration, or SACK the same range but * have a larger cumulative ACK counter. The latter is a * pathological case, but is contained in the following check * anyway, just to be safe. */ sack_comp = cake_tcph_sack_compare(tcph_check, tcph); if (sack_comp < 0 || (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) && sack_comp == 0)) continue; /* At this point we have found an eligible pure ACK to drop; if * we are in aggressive mode, we are done. Otherwise, keep * searching unless this is the second eligible ACK we * found. * * Since we want to drop ACK closest to the head of the queue, * save the first eligible ACK we find, even if we need to loop * again. */ if (!elig_ack) { elig_ack = skb_check; elig_ack_prev = skb_prev; elig_flags = (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)); } if (num_found++ > 0) goto found; } /* We made it through the queue without finding two eligible ACKs . If * we found a single eligible ACK we can drop it in aggressive mode if * we can guarantee that this does not interfere with ECN flag * information. We ensure this by dropping it only if the enqueued * packet is consecutive with the eligible ACK, and their flags match. */ if (elig_ack && aggressive && elig_ack->next == skb && (elig_flags == (tcp_flag_word(tcph) & (TCP_FLAG_ECE | TCP_FLAG_CWR)))) goto found; return NULL; found: if (elig_ack_prev) elig_ack_prev->next = elig_ack->next; else flow->head = elig_ack->next; skb_mark_not_on_list(elig_ack); return elig_ack; } static u64 cake_ewma(u64 avg, u64 sample, u32 shift) { avg -= avg >> shift; avg += sample >> shift; return avg; } static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off) { if (q->rate_flags & CAKE_FLAG_OVERHEAD) len -= off; if (q->max_netlen < len) q->max_netlen = len; if (q->min_netlen > len) q->min_netlen = len; len += q->rate_overhead; if (len < q->rate_mpu) len = q->rate_mpu; if (q->atm_mode == CAKE_ATM_ATM) { len += 47; len /= 48; len *= 53; } else if (q->atm_mode == CAKE_ATM_PTM) { /* Add one byte per 64 bytes or part thereof. * This is conservative and easier to calculate than the * precise value. */ len += (len + 63) / 64; } if (q->max_adjlen < len) q->max_adjlen = len; if (q->min_adjlen > len) q->min_adjlen = len; return len; } static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int hdr_len, last_len = 0; u32 off = skb_network_offset(skb); u32 len = qdisc_pkt_len(skb); u16 segs = 1; q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); if (!shinfo->gso_size) return cake_calc_overhead(q, len, off); /* borrowed from qdisc_pkt_len_init() */ hdr_len = skb_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) segs = DIV_ROUND_UP(skb->len - hdr_len, shinfo->gso_size); else segs = shinfo->gso_segs; len = shinfo->gso_size + hdr_len; last_len = skb->len - shinfo->gso_size * (segs - 1); return (cake_calc_overhead(q, len, off) * (segs - 1) + cake_calc_overhead(q, last_len, off)); } static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j) { struct cake_heap_entry ii = q->overflow_heap[i]; struct cake_heap_entry jj = q->overflow_heap[j]; q->overflow_heap[i] = jj; q->overflow_heap[j] = ii; q->tins[ii.t].overflow_idx[ii.b] = j; q->tins[jj.t].overflow_idx[jj.b] = i; } static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i) { struct cake_heap_entry ii = q->overflow_heap[i]; return q->tins[ii.t].backlogs[ii.b]; } static void cake_heapify(struct cake_sched_data *q, u16 i) { static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES; u32 mb = cake_heap_get_backlog(q, i); u32 m = i; while (m < a) { u32 l = m + m + 1; u32 r = l + 1; if (l < a) { u32 lb = cake_heap_get_backlog(q, l); if (lb > mb) { m = l; mb = lb; } } if (r < a) { u32 rb = cake_heap_get_backlog(q, r); if (rb > mb) { m = r; mb = rb; } } if (m != i) { cake_heap_swap(q, i, m); i = m; } else { break; } } } static void cake_heapify_up(struct cake_sched_data *q, u16 i) { while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) { u16 p = (i - 1) >> 1; u32 ib = cake_heap_get_backlog(q, i); u32 pb = cake_heap_get_backlog(q, p); if (ib > pb) { cake_heap_swap(q, i, p); i = p; } else { break; } } } static int cake_advance_shaper(struct cake_sched_data *q, struct cake_tin_data *b, struct sk_buff *skb, ktime_t now, bool drop) { u32 len = get_cobalt_cb(skb)->adjusted_len; /* charge packet bandwidth to this tin * and to the global shaper. */ if (q->rate_ns) { u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft; u64 global_dur = (len * q->rate_ns) >> q->rate_shft; u64 failsafe_dur = global_dur + (global_dur >> 1); if (ktime_before(b->time_next_packet, now)) b->time_next_packet = ktime_add_ns(b->time_next_packet, tin_dur); else if (ktime_before(b->time_next_packet, ktime_add_ns(now, tin_dur))) b->time_next_packet = ktime_add_ns(now, tin_dur); q->time_next_packet = ktime_add_ns(q->time_next_packet, global_dur); if (!drop) q->failsafe_next_packet = \ ktime_add_ns(q->failsafe_next_packet, failsafe_dur); } return len; } static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); ktime_t now = ktime_get(); u32 idx = 0, tin = 0, len; struct cake_heap_entry qq; struct cake_tin_data *b; struct cake_flow *flow; struct sk_buff *skb; if (!q->overflow_timeout) { int i; /* Build fresh max-heap */ for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--) cake_heapify(q, i); } q->overflow_timeout = 65535; /* select longest queue for pruning */ qq = q->overflow_heap[0]; tin = qq.t; idx = qq.b; b = &q->tins[tin]; flow = &b->flows[idx]; skb = dequeue_head(flow); if (unlikely(!skb)) { /* heap has gone wrong, rebuild it next time */ q->overflow_timeout = 0; return idx + (tin << 16); } if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count++; len = qdisc_pkt_len(skb); q->buffer_used -= skb->truesize; b->backlogs[idx] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; qdisc_tree_reduce_backlog(sch, 1, len); flow->dropped++; b->tin_dropped++; sch->qstats.drops++; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); __qdisc_drop(skb, to_free); sch->q.qlen--; cake_heapify(q, 0); return idx + (tin << 16); } static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { const int offset = skb_network_offset(skb); u16 *buf, buf_; u8 dscp; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* ToS is in the second byte of iphdr */ dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_IPV6): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* Traffic class is in the first and second bytes of ipv6hdr */ dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_ARP): return 0x38; /* CS7 - Net Control */ default: /* If there is no Diffserv field, treat as best-effort */ return 0; } } static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding * using firewall marks or skb->priority. Call DSCP parsing early if * wash is enabled, otherwise defer to below to skip unneeded parsing. */ mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; wash = !!(q->rate_flags & CAKE_FLAG_WASH); if (wash) dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; else if (mark && mark <= q->tin_cnt) tin = q->tin_order[mark - 1]; else if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && TC_H_MIN(skb->priority) <= q->tin_cnt) tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { if (!wash) dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) tin = 0; } return &q->tins[tin]; } static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct sk_buff *skb, int flow_mode, int *qerr) { struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); if (!filter) goto hash; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return 0; } #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); int len = qdisc_pkt_len(skb); int ret; struct sk_buff *ack = NULL; ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; u32 idx; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); if (idx == 0) { if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return ret; } idx--; flow = &b->flows[idx]; /* ensure shaper state isn't stale */ if (!b->tin_backlog) { if (ktime_before(b->time_next_packet, now)) b->time_next_packet = now; if (!sch->q.qlen) { if (ktime_before(q->time_next_packet, now)) { q->failsafe_next_packet = now; q->time_next_packet = now; } else if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = \ min(ktime_to_ns(q->time_next_packet), ktime_to_ns( q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); } } } if (unlikely(len > b->max_skblen)) b->max_skblen = len; if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); unsigned int slen = 0, numsegs = 0; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, segs); flow_queue_add(flow, segs); sch->q.qlen++; numsegs++; slen += segs->len; q->buffer_used += segs->truesize; b->packets++; } /* stats */ b->bytes += slen; b->backlogs[idx] += slen; b->tin_backlog += slen; sch->qstats.backlog += slen; q->avg_window_bytes += slen; qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); consume_skb(skb); } else { /* not splitting */ cobalt_set_enqueue_time(skb, now); get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb); flow_queue_add(flow, skb); if (q->ack_filter) ack = cake_ack_filter(q, flow); if (ack) { b->ack_drops++; sch->qstats.drops++; b->bytes += qdisc_pkt_len(ack); len -= qdisc_pkt_len(ack); q->buffer_used += skb->truesize - ack->truesize; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, ack, now, true); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack)); consume_skb(ack); } else { sch->q.qlen++; q->buffer_used += skb->truesize; } /* stats */ b->packets++; b->bytes += len; b->backlogs[idx] += len; b->tin_backlog += len; sch->qstats.backlog += len; q->avg_window_bytes += len; } if (q->overflow_timeout) cake_heapify_up(q, b->overflow_idx[idx]); /* incoming bandwidth capacity estimate */ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) { u64 packet_interval = \ ktime_to_ns(ktime_sub(now, q->last_packet_time)); if (packet_interval > NSEC_PER_SEC) packet_interval = NSEC_PER_SEC; /* filter out short-term bursts, eg. wifi aggregation */ q->avg_packet_interval = \ cake_ewma(q->avg_packet_interval, packet_interval, (packet_interval > q->avg_packet_interval ? 2 : 8)); q->last_packet_time = now; if (packet_interval > q->avg_packet_interval) { u64 window_interval = \ ktime_to_ns(ktime_sub(now, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); q->avg_window_bytes = 0; q->avg_window_begin = now; if (ktime_after(now, ktime_add_ms(q->last_reconfig_time, 250))) { q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4; cake_reconfigure(sch); } } } else { q->avg_window_bytes = 0; q->last_packet_time = now; } /* flowchain */ if (!flow->set || flow->set == CAKE_SET_DECAYING) { struct cake_host *srchost = &b->hosts[flow->srchost]; struct cake_host *dsthost = &b->hosts[flow->dsthost]; u16 host_load = 1; if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { b->decaying_flow_count--; list_move_tail(&flow->flowchain, &b->new_flows); } flow->set = CAKE_SET_SPARSE; b->sparse_flow_count++; if (cake_dsrc(q->flow_mode)) host_load = max(host_load, srchost->srchost_bulk_flow_count); if (cake_ddst(q->flow_mode)) host_load = max(host_load, dsthost->dsthost_bulk_flow_count); flow->deficit = (b->flow_quantum * quantum_div[host_load]) >> 16; } else if (flow->set == CAKE_SET_SPARSE_WAIT) { struct cake_host *srchost = &b->hosts[flow->srchost]; struct cake_host *dsthost = &b->hosts[flow->dsthost]; /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ flow->set = CAKE_SET_BULK; b->sparse_flow_count--; b->bulk_flow_count++; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count++; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count++; } if (q->buffer_used > q->buffer_max_used) q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { u32 dropped = 0; while (q->buffer_used > q->buffer_limit) { dropped++; cake_drop(sch, to_free); } b->drop_overlimit += dropped; } return NET_XMIT_SUCCESS; } static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; struct cake_flow *flow = &b->flows[q->cur_flow]; struct sk_buff *skb = NULL; u32 len; if (flow->head) { skb = dequeue_head(flow); len = qdisc_pkt_len(skb); b->backlogs[q->cur_flow] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; q->buffer_used -= skb->truesize; sch->q.qlen--; if (q->overflow_timeout) cake_heapify(q, b->overflow_idx[q->cur_flow]); } return skb; } /* Discard leftover packets from a tin no longer in use. */ static void cake_clear_tin(struct Qdisc *sch, u16 tin) { struct cake_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; q->cur_tin = tin; for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) while (!!(skb = cake_dequeue_one(sch))) kfree_skb(skb); } static struct sk_buff *cake_dequeue(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; struct cake_host *srchost, *dsthost; ktime_t now = ktime_get(); struct cake_flow *flow; struct list_head *head; bool first_flow = true; struct sk_buff *skb; u16 host_load; u64 delay; u32 len; begin: if (!sch->q.qlen) return NULL; /* global hard shaper */ if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); return NULL; } /* Choose a class to work on. */ if (!q->rate_ns) { /* In unlimited mode, can't rely on shaper timings, just balance * with DRR */ bool wrapped = false, empty = true; while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; q->cur_tin++; b++; if (q->cur_tin >= q->tin_cnt) { q->cur_tin = 0; b = q->tins; if (wrapped) { /* It's possible for q->qlen to be * nonzero when we actually have no * packets anywhere. */ if (empty) return NULL; } else { wrapped = true; } } } } else { /* In shaped mode, choose: * - Highest-priority tin with queue and meeting schedule, or * - The earliest-scheduled tin with queue. */ ktime_t best_time = KTIME_MAX; int tin, best_tin = 0; for (tin = 0; tin < q->tin_cnt; tin++) { b = q->tins + tin; if ((b->sparse_flow_count + b->bulk_flow_count) > 0) { ktime_t time_to_pkt = \ ktime_sub(b->time_next_packet, now); if (ktime_to_ns(time_to_pkt) <= 0 || ktime_compare(time_to_pkt, best_time) <= 0) { best_time = time_to_pkt; best_tin = tin; } } } q->cur_tin = best_tin; b = q->tins + best_tin; /* No point in going further if no packets to deliver. */ if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count))) return NULL; } retry: /* service this class */ head = &b->decaying_flows; if (!first_flow || list_empty(head)) { head = &b->new_flows; if (list_empty(head)) { head = &b->old_flows; if (unlikely(list_empty(head))) { head = &b->decaying_flows; if (unlikely(list_empty(head))) goto begin; } } } flow = list_first_entry(head, struct cake_flow, flowchain); q->cur_flow = flow - b->flows; first_flow = false; /* triple isolation (modified DRR++) */ srchost = &b->hosts[flow->srchost]; dsthost = &b->hosts[flow->dsthost]; host_load = 1; /* flow isolation (DRR++) */ if (flow->deficit <= 0) { /* Keep all flows with deficits out of the sparse and decaying * rotations. No non-empty flow can go into the decaying * rotation, so they can't get deficits */ if (flow->set == CAKE_SET_SPARSE) { if (flow->head) { b->sparse_flow_count--; b->bulk_flow_count++; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count++; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count++; flow->set = CAKE_SET_BULK; } else { /* we've moved it to the bulk rotation for * correct deficit accounting but we still want * to count it as a sparse flow, not a bulk one. */ flow->set = CAKE_SET_SPARSE_WAIT; } } if (cake_dsrc(q->flow_mode)) host_load = max(host_load, srchost->srchost_bulk_flow_count); if (cake_ddst(q->flow_mode)) host_load = max(host_load, dsthost->dsthost_bulk_flow_count); WARN_ON(host_load > CAKE_QUEUES); /* The get_random_u16() is a way to apply dithering to avoid * accumulating roundoff errors */ flow->deficit += (b->flow_quantum * quantum_div[host_load] + get_random_u16()) >> 16; list_move_tail(&flow->flowchain, &b->old_flows); goto retry; } /* Retrieve a packet via the AQM */ while (1) { skb = cake_dequeue_one(sch); if (!skb) { /* this queue was actually empty */ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count--; if (flow->cvars.p_drop || flow->cvars.count || ktime_before(now, flow->cvars.drop_next)) { /* keep in the flowchain until the state has * decayed to rest */ list_move_tail(&flow->flowchain, &b->decaying_flows); if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count--; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count--; b->decaying_flow_count++; } else if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) { b->sparse_flow_count--; b->decaying_flow_count++; } flow->set = CAKE_SET_DECAYING; } else { /* remove empty queue from the flowchain */ list_del_init(&flow->flowchain); if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) b->sparse_flow_count--; else if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count--; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count--; } else b->decaying_flow_count--; flow->set = CAKE_SET_NONE; } goto begin; } /* Last packet in queue may be marked, shouldn't be dropped */ if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, (b->bulk_flow_count * !!(q->rate_flags & CAKE_FLAG_INGRESS))) || !flow->head) break; /* drop this packet, get another one */ if (q->rate_flags & CAKE_FLAG_INGRESS) { len = cake_advance_shaper(q, b, skb, now, true); flow->deficit -= len; b->tin_deficit -= len; } flow->dropped++; b->tin_dropped++; qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); kfree_skb(skb); if (q->rate_flags & CAKE_FLAG_INGRESS) goto retry; } b->tin_ecn_mark += !!flow->cvars.ecn_marked; qdisc_bstats_update(sch, skb); /* collect delay stats */ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); b->avge_delay = cake_ewma(b->avge_delay, delay, 8); b->peak_delay = cake_ewma(b->peak_delay, delay, delay > b->peak_delay ? 2 : 8); b->base_delay = cake_ewma(b->base_delay, delay, delay < b->base_delay ? 2 : 8); len = cake_advance_shaper(q, b, skb, now, false); flow->deficit -= len; b->tin_deficit -= len; if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); qdisc_watchdog_schedule_ns(&q->watchdog, next); } else if (!sch->q.qlen) { int i; for (i = 0; i < q->tin_cnt; i++) { if (q->tins[i].decaying_flow_count) { ktime_t next = \ ktime_add_ns(now, q->tins[i].cparams.target); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); break; } } } if (q->overflow_timeout) q->overflow_timeout--; return skb; } static void cake_reset(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); u32 c; if (!q->tins) return; for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 }, [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 }, [TCA_CAKE_ATM] = { .type = NLA_U32 }, [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 }, [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 }, [TCA_CAKE_RTT] = { .type = NLA_U32 }, [TCA_CAKE_TARGET] = { .type = NLA_U32 }, [TCA_CAKE_AUTORATE] = { .type = NLA_U32 }, [TCA_CAKE_MEMORY] = { .type = NLA_U32 }, [TCA_CAKE_NAT] = { .type = NLA_U32 }, [TCA_CAKE_RAW] = { .type = NLA_U32 }, [TCA_CAKE_WASH] = { .type = NLA_U32 }, [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, u64 target_ns, u64 rtt_est_ns) { /* convert byte-rate into time-per-byte * so it will always unwedge in reasonable time. */ static const u64 MIN_RATE = 64; u32 byte_target = mtu; u64 byte_target_ns; u8 rate_shft = 0; u64 rate_ns = 0; b->flow_quantum = 1514; if (rate) { b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); rate_shft = 34; rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); while (!!(rate_ns >> 34)) { rate_ns >>= 1; rate_shft--; } } /* else unlimited, ie. zero delay */ b->tin_rate_bps = rate; b->tin_rate_ns = rate_ns; b->tin_rate_shft = rate_shft; byte_target_ns = (byte_target * rate_ns) >> rate_shft; b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); b->cparams.interval = max(rtt_est_ns + b->cparams.target - target_ns, b->cparams.target * 2); b->cparams.mtu_time = byte_target_ns; b->cparams.p_inc = 1 << 24; /* 1/256 */ b->cparams.p_dec = 1 << 20; /* 1/4096 */ } static int cake_config_besteffort(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; q->tin_cnt = 1; q->tin_index = besteffort; q->tin_order = normal_order; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = 65535; return 0; } static int cake_config_precedence(struct Qdisc *sch) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; q->tin_index = precedence; q->tin_order = normal_order; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } /* List of known Diffserv codepoints: * * Default Forwarding (DF/CS0) - Best Effort * Max Throughput (TOS2) * Min Delay (TOS4) * LLT "La" (TOS5) * Assured Forwarding 1 (AF1x) - x3 * Assured Forwarding 2 (AF2x) - x3 * Assured Forwarding 3 (AF3x) - x3 * Assured Forwarding 4 (AF4x) - x3 * Precedence Class 1 (CS1) * Precedence Class 2 (CS2) * Precedence Class 3 (CS3) * Precedence Class 4 (CS4) * Precedence Class 5 (CS5) * Precedence Class 6 (CS6) * Precedence Class 7 (CS7) * Voice Admit (VA) * Expedited Forwarding (EF) * Lower Effort (LE) * * Total 26 codepoints. */ /* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * * Network Control (CS6,CS7) - routing traffic * Telephony (EF,VA) - aka. VoIP streams * Signalling (CS5) - VoIP setup * Multimedia Conferencing (AF4x) - aka. video calls * Realtime Interactive (CS4) - eg. games * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch * Broadcast Video (CS3) * Low-Latency Data (AF2x,TOS4) - eg. database * Ops, Admin, Management (CS2) - eg. ssh * Standard Service (DF & unrecognised codepoints) * High-Throughput Data (AF1x,TOS2) - eg. web traffic * Low-Priority Data (LE,CS1) - eg. BitTorrent * * Total 12 traffic classes. */ static int cake_config_diffserv8(struct Qdisc *sch) { /* Pruned list of traffic classes for typical applications: * * Network Control (CS6, CS7) * Minimum Latency (EF, VA, CS5, CS4) * Interactive Shell (CS2) * Low Latency Transactions (AF2x, TOS4) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (DF etc.) * High Throughput (AF1x, TOS2, CS1) * Background Traffic (LE) * * Total 8 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; /* codepoint to class mapping */ q->tin_index = diffserv8; q->tin_order = normal_order; /* class characteristics */ for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } static int cake_config_diffserv4(struct Qdisc *sch) { /* Further pruned list of traffic classes for four-class system: * * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2) * Best Effort (DF, AF1x, TOS2, and those not specified) * Background Traffic (LE, CS1) * * Total 4 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; /* codepoint to class mapping */ q->tin_index = diffserv4; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 1, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 1; q->tins[3].tin_quantum = quantum >> 2; return 0; } static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) * Best Effort * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; /* codepoint to class mapping */ q->tin_index = diffserv3; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 2; return 0; } static void cake_reconfigure(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: ft = cake_config_besteffort(sch); break; case CAKE_DIFFSERV_PRECEDENCE: ft = cake_config_precedence(sch); break; case CAKE_DIFFSERV_DIFFSERV8: ft = cake_config_diffserv8(sch); break; case CAKE_DIFFSERV_DIFFSERV4: ft = cake_config_diffserv4(sch); break; case CAKE_DIFFSERV_DIFFSERV3: default: ft = cake_config_diffserv3(sch); break; } for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) { cake_clear_tin(sch, c); q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time; } q->rate_ns = q->tins[ft].tin_rate_ns; q->rate_shft = q->tins[ft].tin_rate_shft; if (q->buffer_config_limit) { q->buffer_limit = q->buffer_config_limit; } else if (q->rate_bps) { u64 t = q->rate_bps * q->interval; do_div(t, USEC_PER_SEC / 4); q->buffer_limit = max_t(u32, t, 4U << 20); } else { q->buffer_limit = ~0; } sch->flags &= ~TCQ_F_CAN_BYPASS; q->buffer_limit = min(q->buffer_limit, max(sch->limit * psched_mtu(qdisc_dev(sch)), q->buffer_config_limit)); } static int cake_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CAKE_MAX + 1]; u16 rate_flags; u8 flow_mode; int err; err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy, extack); if (err < 0) return err; flow_mode = q->flow_mode; if (tb[TCA_CAKE_NAT]) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) flow_mode &= ~CAKE_FLOW_NAT_FLAG; flow_mode |= CAKE_FLOW_NAT_FLAG * !!nla_get_u32(tb[TCA_CAKE_NAT]); #else NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT], "No conntrack support in kernel"); return -EOPNOTSUPP; #endif } if (tb[TCA_CAKE_BASE_RATE64]) WRITE_ONCE(q->rate_bps, nla_get_u64(tb[TCA_CAKE_BASE_RATE64])); if (tb[TCA_CAKE_DIFFSERV_MODE]) WRITE_ONCE(q->tin_mode, nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE])); rate_flags = q->rate_flags; if (tb[TCA_CAKE_WASH]) { if (!!nla_get_u32(tb[TCA_CAKE_WASH])) rate_flags |= CAKE_FLAG_WASH; else rate_flags &= ~CAKE_FLAG_WASH; } if (tb[TCA_CAKE_FLOW_MODE]) flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) | (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & CAKE_FLOW_MASK)); if (tb[TCA_CAKE_ATM]) WRITE_ONCE(q->atm_mode, nla_get_u32(tb[TCA_CAKE_ATM])); if (tb[TCA_CAKE_OVERHEAD]) { WRITE_ONCE(q->rate_overhead, nla_get_s32(tb[TCA_CAKE_OVERHEAD])); rate_flags |= CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_RAW]) { rate_flags &= ~CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_MPU]) WRITE_ONCE(q->rate_mpu, nla_get_u32(tb[TCA_CAKE_MPU])); if (tb[TCA_CAKE_RTT]) { u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]); WRITE_ONCE(q->interval, max(interval, 1U)); } if (tb[TCA_CAKE_TARGET]) { u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]); WRITE_ONCE(q->target, max(target, 1U)); } if (tb[TCA_CAKE_AUTORATE]) { if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE])) rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; else rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; } if (tb[TCA_CAKE_INGRESS]) { if (!!nla_get_u32(tb[TCA_CAKE_INGRESS])) rate_flags |= CAKE_FLAG_INGRESS; else rate_flags &= ~CAKE_FLAG_INGRESS; } if (tb[TCA_CAKE_ACK_FILTER]) WRITE_ONCE(q->ack_filter, nla_get_u32(tb[TCA_CAKE_ACK_FILTER])); if (tb[TCA_CAKE_MEMORY]) WRITE_ONCE(q->buffer_config_limit, nla_get_u32(tb[TCA_CAKE_MEMORY])); if (tb[TCA_CAKE_SPLIT_GSO]) { if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) rate_flags |= CAKE_FLAG_SPLIT_GSO; else rate_flags &= ~CAKE_FLAG_SPLIT_GSO; } if (tb[TCA_CAKE_FWMARK]) { WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK])); WRITE_ONCE(q->fwmark_shft, q->fwmark_mask ? __ffs(q->fwmark_mask) : 0); } WRITE_ONCE(q->rate_flags, rate_flags); WRITE_ONCE(q->flow_mode, flow_mode); if (q->tins) { sch_tree_lock(sch); cake_reconfigure(sch); sch_tree_unlock(sch); } return 0; } static void cake_destroy(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); tcf_block_put(q->block); kvfree(q->tins); } static int cake_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); int i, j, err; sch->limit = 10240; q->tin_mode = CAKE_DIFFSERV_DIFFSERV3; q->flow_mode = CAKE_FLOW_TRIPLE; q->rate_bps = 0; /* unlimited by default */ q->interval = 100000; /* 100ms default */ q->target = 5000; /* 5ms: codel RFC argues * for 5 to 10% of interval */ q->rate_flags |= CAKE_FLAG_SPLIT_GSO; q->cur_tin = 0; q->cur_flow = 0; qdisc_watchdog_init(&q->watchdog, sch); if (opt) { err = cake_change(sch, opt, extack); if (err) return err; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; quantum_div[0] = ~0; for (i = 1; i <= CAKE_QUEUES; i++) quantum_div[i] = 65535 / i; q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; INIT_LIST_HEAD(&b->new_flows); INIT_LIST_HEAD(&b->old_flows); INIT_LIST_HEAD(&b->decaying_flows); b->sparse_flow_count = 0; b->bulk_flow_count = 0; b->decaying_flow_count = 0; for (j = 0; j < CAKE_QUEUES; j++) { struct cake_flow *flow = b->flows + j; u32 k = j * CAKE_MAX_TINS + i; INIT_LIST_HEAD(&flow->flowchain); cobalt_vars_init(&flow->cvars); q->overflow_heap[k].t = i; q->overflow_heap[k].b = j; b->overflow_idx[j] = k; } } cake_reconfigure(sch); q->avg_peak_bandwidth = q->rate_bps; q->min_netlen = ~0; q->min_adjlen = ~0; return 0; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *opts; u16 rate_flags; u8 flow_mode; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, READ_ONCE(q->rate_bps), TCA_CAKE_PAD)) goto nla_put_failure; flow_mode = READ_ONCE(q->flow_mode); if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MEMORY, READ_ONCE(q->buffer_config_limit))) goto nla_put_failure; rate_flags = READ_ONCE(q->rate_flags); if (nla_put_u32(skb, TCA_CAKE_AUTORATE, !!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_INGRESS, !!(rate_flags & CAKE_FLAG_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_NAT, !!(flow_mode & CAKE_FLOW_NAT_FLAG))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_WASH, !!(rate_flags & CAKE_FLAG_WASH))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead))) goto nla_put_failure; if (!(rate_flags & CAKE_FLAG_OVERHEAD)) if (nla_put_u32(skb, TCA_CAKE_RAW, 0)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO, !!(rate_flags & CAKE_FLAG_SPLIT_GSO))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: return -1; } static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tstats, *ts; int i; if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \ data, TCA_CAKE_STATS_PAD)) \ goto nla_put_failure; \ } while (0) PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); PUT_STAT_U32(MAX_NETLEN, q->max_netlen); PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); PUT_STAT_U32(MIN_NETLEN, q->min_netlen); PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); #undef PUT_STAT_U32 #undef PUT_STAT_U64 tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS); if (!tstats) goto nla_put_failure; #define PUT_TSTAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_TSTAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \ data, TCA_CAKE_TIN_STATS_PAD)) \ goto nla_put_failure; \ } while (0) for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; ts = nla_nest_start_noflag(d->skb, i + 1); if (!ts) goto nla_put_failure; PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); PUT_TSTAT_U64(SENT_BYTES64, b->bytes); PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); PUT_TSTAT_U32(TARGET_US, ktime_to_us(ns_to_ktime(b->cparams.target))); PUT_TSTAT_U32(INTERVAL_US, ktime_to_us(ns_to_ktime(b->cparams.interval))); PUT_TSTAT_U32(SENT_PACKETS, b->packets); PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); PUT_TSTAT_U32(PEAK_DELAY_US, ktime_to_us(ns_to_ktime(b->peak_delay))); PUT_TSTAT_U32(AVG_DELAY_US, ktime_to_us(ns_to_ktime(b->avge_delay))); PUT_TSTAT_U32(BASE_DELAY_US, ktime_to_us(ns_to_ktime(b->base_delay))); PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); PUT_TSTAT_U32(WAY_MISSES, b->way_misses); PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + b->decaying_flow_count); PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); nla_nest_end(d->skb, ts); } #undef PUT_TSTAT_U32 #undef PUT_TSTAT_U64 nla_nest_end(d->skb, tstats); return nla_nest_end(d->skb, stats); nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; } static unsigned long cake_find(struct Qdisc *sch, u32 classid) { return 0; } static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { return 0; } static void cake_unbind(struct Qdisc *q, unsigned long cl) { } static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static int cake_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { tcm->tcm_handle |= TC_H_MIN(cl); return 0; } static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct cake_sched_data *q = qdisc_priv(sch); const struct cake_flow *flow = NULL; struct gnet_stats_queue qs = { 0 }; struct nlattr *stats; u32 idx = cl - 1; if (idx < CAKE_QUEUES * q->tin_cnt) { const struct cake_tin_data *b = \ &q->tins[q->tin_order[idx / CAKE_QUEUES]]; const struct sk_buff *skb; flow = &b->flows[idx % CAKE_QUEUES]; if (flow->head) { sch_tree_lock(sch); skb = flow->head; while (skb) { qs.qlen++; skb = skb->next; } sch_tree_unlock(sch); } qs.backlog = b->backlogs[idx % CAKE_QUEUES]; qs.drops = flow->dropped; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; if (flow) { ktime_t now = ktime_get(); stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_S32(attr, data) do { \ if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) PUT_STAT_S32(DEFICIT, flow->deficit); PUT_STAT_U32(DROPPING, flow->cvars.dropping); PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); PUT_STAT_U32(P_DROP, flow->cvars.p_drop); if (flow->cvars.p_drop) { PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, ktime_to_us( ktime_sub(now, flow->cvars.drop_next))); } if (nla_nest_end(d->skb, stats) < 0) return -1; } return 0; nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct cake_sched_data *q = qdisc_priv(sch); unsigned int i, j; if (arg->stop) return; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; for (j = 0; j < CAKE_QUEUES; j++) { if (list_empty(&b->flows[j].flowchain)) { arg->count++; continue; } if (!tc_qdisc_stats_dump(sch, i * CAKE_QUEUES + j + 1, arg)) break; } } } static const struct Qdisc_class_ops cake_class_ops = { .leaf = cake_leaf, .find = cake_find, .tcf_block = cake_tcf_block, .bind_tcf = cake_bind, .unbind_tcf = cake_unbind, .dump = cake_dump_class, .dump_stats = cake_dump_class_stats, .walk = cake_walk, }; static struct Qdisc_ops cake_qdisc_ops __read_mostly = { .cl_ops = &cake_class_ops, .id = "cake", .priv_size = sizeof(struct cake_sched_data), .enqueue = cake_enqueue, .dequeue = cake_dequeue, .peek = qdisc_peek_dequeued, .init = cake_init, .reset = cake_reset, .destroy = cake_destroy, .change = cake_change, .dump = cake_dump, .dump_stats = cake_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("cake"); static int __init cake_module_init(void) { return register_qdisc(&cake_qdisc_ops); } static void __exit cake_module_exit(void) { unregister_qdisc(&cake_qdisc_ops); } module_init(cake_module_init) module_exit(cake_module_exit) MODULE_AUTHOR("Jonathan Morton"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("The CAKE shaper."); |
| 8 4 4 4 1 1 1 4 4 4 2 1 2 2 1 2 2 1 1 5 1 1 2 1 19 1 27 4 23 21 3 5 17 5 12 1 1 1 9 6 1 2 1 2 2 4 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 | /* net/tipc/udp_media.c: IP bearer support for TIPC * * Copyright (c) 2015, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/list.h> #include <net/sock.h> #include <net/ip.h> #include <net/udp_tunnel.h> #include <net/ipv6_stubs.h> #include <linux/tipc_netlink.h> #include "core.h" #include "addr.h" #include "net.h" #include "bearer.h" #include "netlink.h" #include "msg.h" #include "udp_media.h" /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 #define UDP_MIN_HEADROOM 48 /** * struct udp_media_addr - IP/UDP addressing information * * This is the bearer level originating address used in neighbor discovery * messages, and all fields should be in network byte order * * @proto: Ethernet protocol in use * @port: port being used * @ipv4: IPv4 address of neighbor * @ipv6: IPv6 address of neighbor */ struct udp_media_addr { __be16 proto; __be16 port; union { struct in_addr ipv4; struct in6_addr ipv6; }; }; /* struct udp_replicast - container for UDP remote addresses */ struct udp_replicast { struct udp_media_addr addr; struct dst_cache dst_cache; struct rcu_head rcu; struct list_head list; }; /** * struct udp_bearer - ip/udp bearer data structure * @bearer: associated generic tipc bearer * @ubsock: bearer associated socket * @ifindex: local address scope * @work: used to schedule deferred work on a bearer * @rcast: associated udp_replicast container */ struct udp_bearer { struct tipc_bearer __rcu *bearer; struct socket *ubsock; u32 ifindex; struct work_struct work; struct udp_replicast rcast; }; static int tipc_udp_is_mcast_addr(struct udp_media_addr *addr) { if (ntohs(addr->proto) == ETH_P_IP) return ipv4_is_multicast(addr->ipv4.s_addr); #if IS_ENABLED(CONFIG_IPV6) else return ipv6_addr_is_multicast(&addr->ipv6); #endif return 0; } /* udp_media_addr_set - convert a ip/udp address to a TIPC media address */ static void tipc_udp_media_addr_set(struct tipc_media_addr *addr, struct udp_media_addr *ua) { memset(addr, 0, sizeof(struct tipc_media_addr)); addr->media_id = TIPC_MEDIA_TYPE_UDP; memcpy(addr->value, ua, sizeof(struct udp_media_addr)); if (tipc_udp_is_mcast_addr(ua)) addr->broadcast = TIPC_BROADCAST_SUPPORT; } /* tipc_udp_addr2str - convert ip/udp address to string */ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size) { struct udp_media_addr *ua = (struct udp_media_addr *)&a->value; if (ntohs(ua->proto) == ETH_P_IP) snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port)); else if (ntohs(ua->proto) == ETH_P_IPV6) snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port)); else pr_err("Invalid UDP media address\n"); return 0; } /* tipc_udp_msg2addr - extract an ip/udp address from a TIPC ndisc message */ static int tipc_udp_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *a, char *msg) { struct udp_media_addr *ua; ua = (struct udp_media_addr *) (msg + TIPC_MEDIA_ADDR_OFFSET); if (msg[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_UDP) return -EINVAL; tipc_udp_media_addr_set(a, ua); return 0; } /* tipc_udp_addr2msg - write an ip/udp address to a TIPC ndisc message */ static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a) { memset(msg, 0, TIPC_MEDIA_INFO_SIZE); msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_UDP; memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, a->value, sizeof(struct udp_media_addr)); return 0; } /* tipc_send_msg - enqueue a send request */ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, struct udp_bearer *ub, struct udp_media_addr *src, struct udp_media_addr *dst, struct dst_cache *cache) { struct dst_entry *ndst; int ttl, err = 0; local_bh_disable(); ndst = dst_cache_get(cache); if (dst->proto == htons(ETH_P_IP)) { struct rtable *rt = dst_rtable(ndst); if (!rt) { struct flowi4 fl = { .daddr = dst->ipv4.s_addr, .saddr = src->ipv4.s_addr, .flowi4_mark = skb->mark, .flowi4_proto = IPPROTO_UDP }; rt = ip_route_output_key(net, &fl); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto tx_error; } dst_cache_set_ip4(cache, &rt->dst, fl.saddr); } ttl = ip4_dst_hoplimit(&rt->dst); udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr, dst->ipv4.s_addr, 0, ttl, 0, src->port, dst->port, false, true); #if IS_ENABLED(CONFIG_IPV6) } else { if (!ndst) { struct flowi6 fl6 = { .flowi6_oif = ub->ifindex, .daddr = dst->ipv6, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; ndst = ipv6_stub->ipv6_dst_lookup_flow(net, ub->ubsock->sk, &fl6, NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); goto tx_error; } dst_cache_set_ip6(cache, ndst, &fl6.saddr); } ttl = ip6_dst_hoplimit(ndst); err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL, &src->ipv6, &dst->ipv6, 0, ttl, 0, src->port, dst->port, false); #endif } local_bh_enable(); return err; tx_error: local_bh_enable(); kfree_skb(skb); return err; } static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, struct tipc_bearer *b, struct tipc_media_addr *addr) { struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; struct udp_media_addr *dst = (struct udp_media_addr *)&addr->value; struct udp_replicast *rcast; struct udp_bearer *ub; int err = 0; if (skb_headroom(skb) < UDP_MIN_HEADROOM) { err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); if (err) goto out; } skb_set_inner_protocol(skb, htons(ETH_P_TIPC)); ub = rcu_dereference(b->media_ptr); if (!ub) { err = -ENODEV; goto out; } if (addr->broadcast != TIPC_REPLICAST_SUPPORT) return tipc_udp_xmit(net, skb, ub, src, dst, &ub->rcast.dst_cache); /* Replicast, send an skb to each configured IP address */ list_for_each_entry_rcu(rcast, &ub->rcast.list, list) { struct sk_buff *_skb; _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) { err = -ENOMEM; goto out; } err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr, &rcast->dst_cache); if (err) goto out; } err = 0; out: kfree_skb(skb); return err; } static bool tipc_udp_is_known_peer(struct tipc_bearer *b, struct udp_media_addr *addr) { struct udp_replicast *rcast, *tmp; struct udp_bearer *ub; ub = rcu_dereference_rtnl(b->media_ptr); if (!ub) { pr_err_ratelimited("UDP bearer instance not found\n"); return false; } list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { if (!memcmp(&rcast->addr, addr, sizeof(struct udp_media_addr))) return true; } return false; } static int tipc_udp_rcast_add(struct tipc_bearer *b, struct udp_media_addr *addr) { struct udp_replicast *rcast; struct udp_bearer *ub; ub = rcu_dereference_rtnl(b->media_ptr); if (!ub) return -ENODEV; rcast = kmalloc(sizeof(*rcast), GFP_ATOMIC); if (!rcast) return -ENOMEM; if (dst_cache_init(&rcast->dst_cache, GFP_ATOMIC)) { kfree(rcast); return -ENOMEM; } memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr)); if (ntohs(addr->proto) == ETH_P_IP) pr_info("New replicast peer: %pI4\n", &rcast->addr.ipv4); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(addr->proto) == ETH_P_IPV6) pr_info("New replicast peer: %pI6\n", &rcast->addr.ipv6); #endif b->bcast_addr.broadcast = TIPC_REPLICAST_SUPPORT; list_add_rcu(&rcast->list, &ub->rcast.list); return 0; } static int tipc_udp_rcast_disc(struct tipc_bearer *b, struct sk_buff *skb) { struct udp_media_addr src = {0}; struct udp_media_addr *dst; dst = (struct udp_media_addr *)&b->bcast_addr.value; if (tipc_udp_is_mcast_addr(dst)) return 0; src.port = udp_hdr(skb)->source; if (ip_hdr(skb)->version == 4) { struct iphdr *iphdr = ip_hdr(skb); src.proto = htons(ETH_P_IP); src.ipv4.s_addr = iphdr->saddr; if (ipv4_is_multicast(iphdr->daddr)) return 0; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_hdr(skb)->version == 6) { struct ipv6hdr *iphdr = ipv6_hdr(skb); src.proto = htons(ETH_P_IPV6); src.ipv6 = iphdr->saddr; if (ipv6_addr_is_multicast(&iphdr->daddr)) return 0; #endif } else { return 0; } if (likely(tipc_udp_is_known_peer(b, &src))) return 0; return tipc_udp_rcast_add(b, &src); } /* tipc_udp_recv - read data from bearer socket */ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) { struct udp_bearer *ub; struct tipc_bearer *b; struct tipc_msg *hdr; int err; ub = rcu_dereference_sk_user_data(sk); if (!ub) { pr_err_ratelimited("Failed to get UDP bearer reference"); goto out; } skb_pull(skb, sizeof(struct udphdr)); hdr = buf_msg(skb); b = rcu_dereference(ub->bearer); if (!b) goto out; if (b && test_bit(0, &b->up)) { TIPC_SKB_CB(skb)->flags = 0; tipc_rcv(sock_net(sk), skb, b); return 0; } if (unlikely(msg_user(hdr) == LINK_CONFIG)) { err = tipc_udp_rcast_disc(b, skb); if (err) goto out; } out: kfree_skb(skb); return 0; } static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) { int err = 0; struct ip_mreqn mreqn; struct sock *sk = ub->ubsock->sk; if (ntohs(remote->proto) == ETH_P_IP) { mreqn.imr_multiaddr = remote->ipv4; mreqn.imr_ifindex = ub->ifindex; err = ip_mc_join_group(sk, &mreqn); #if IS_ENABLED(CONFIG_IPV6) } else { lock_sock(sk); err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex, &remote->ipv6); release_sock(sk); #endif } return err; } static int __tipc_nl_add_udp_addr(struct sk_buff *skb, struct udp_media_addr *addr, int nla_t) { if (ntohs(addr->proto) == ETH_P_IP) { struct sockaddr_in ip4; memset(&ip4, 0, sizeof(ip4)); ip4.sin_family = AF_INET; ip4.sin_port = addr->port; ip4.sin_addr.s_addr = addr->ipv4.s_addr; if (nla_put(skb, nla_t, sizeof(ip4), &ip4)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) } else if (ntohs(addr->proto) == ETH_P_IPV6) { struct sockaddr_in6 ip6; memset(&ip6, 0, sizeof(ip6)); ip6.sin6_family = AF_INET6; ip6.sin6_port = addr->port; memcpy(&ip6.sin6_addr, &addr->ipv6, sizeof(struct in6_addr)); if (nla_put(skb, nla_t, sizeof(ip6), &ip6)) return -EMSGSIZE; #endif } return 0; } int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) { u32 bid = cb->args[0]; u32 skip_cnt = cb->args[1]; u32 portid = NETLINK_CB(cb->skb).portid; struct udp_replicast *rcast, *tmp; struct tipc_bearer *b; struct udp_bearer *ub; void *hdr; int err; int i; if (!bid && !skip_cnt) { struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct net *net = sock_net(skb->sk); struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1]; char *bname; if (!attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(battrs, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, NULL); if (err) return err; if (!battrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; bname = nla_data(battrs[TIPC_NLA_BEARER_NAME]); rtnl_lock(); b = tipc_bearer_find(net, bname); if (!b) { rtnl_unlock(); return -EINVAL; } bid = b->identity; } else { struct net *net = sock_net(skb->sk); struct tipc_net *tn = net_generic(net, tipc_net_id); rtnl_lock(); b = rtnl_dereference(tn->bearer_list[bid]); if (!b) { rtnl_unlock(); return -EINVAL; } } ub = rtnl_dereference(b->media_ptr); if (!ub) { rtnl_unlock(); return -EINVAL; } i = 0; list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { if (i < skip_cnt) goto count; hdr = genlmsg_put(skb, portid, cb->nlh->nlmsg_seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_BEARER_GET); if (!hdr) goto done; err = __tipc_nl_add_udp_addr(skb, &rcast->addr, TIPC_NLA_UDP_REMOTE); if (err) { genlmsg_cancel(skb, hdr); goto done; } genlmsg_end(skb, hdr); count: i++; } done: rtnl_unlock(); cb->args[0] = bid; cb->args[1] = i; return skb->len; } int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b) { struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; struct udp_media_addr *dst; struct udp_bearer *ub; struct nlattr *nest; ub = rtnl_dereference(b->media_ptr); if (!ub) return -ENODEV; nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); if (!nest) goto msg_full; if (__tipc_nl_add_udp_addr(msg->skb, src, TIPC_NLA_UDP_LOCAL)) goto msg_full; dst = (struct udp_media_addr *)&b->bcast_addr.value; if (__tipc_nl_add_udp_addr(msg->skb, dst, TIPC_NLA_UDP_REMOTE)) goto msg_full; if (!list_empty(&ub->rcast.list)) { if (nla_put_flag(msg->skb, TIPC_NLA_UDP_MULTI_REMOTEIP)) goto msg_full; } nla_nest_end(msg->skb, nest); return 0; msg_full: nla_nest_cancel(msg->skb, nest); return -EMSGSIZE; } /** * tipc_parse_udp_addr - build udp media address from netlink data * @nla: netlink attribute containing sockaddr storage aligned address * @addr: tipc media address to fill with address, port and protocol type * @scope_id: IPv6 scope id pointer, not NULL indicates it's required */ static int tipc_parse_udp_addr(struct nlattr *nla, struct udp_media_addr *addr, u32 *scope_id) { struct sockaddr_storage sa; nla_memcpy(&sa, nla, sizeof(sa)); if (sa.ss_family == AF_INET) { struct sockaddr_in *ip4 = (struct sockaddr_in *)&sa; addr->proto = htons(ETH_P_IP); addr->port = ip4->sin_port; addr->ipv4.s_addr = ip4->sin_addr.s_addr; return 0; #if IS_ENABLED(CONFIG_IPV6) } else if (sa.ss_family == AF_INET6) { struct sockaddr_in6 *ip6 = (struct sockaddr_in6 *)&sa; addr->proto = htons(ETH_P_IPV6); addr->port = ip6->sin6_port; memcpy(&addr->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); /* Scope ID is only interesting for local addresses */ if (scope_id) { int atype; atype = ipv6_addr_type(&ip6->sin6_addr); if (__ipv6_addr_needs_scope_id(atype) && !ip6->sin6_scope_id) { return -EINVAL; } *scope_id = ip6->sin6_scope_id ? : 0; } return 0; #endif } return -EADDRNOTAVAIL; } int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr) { int err; struct udp_media_addr addr = {0}; struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; struct udp_media_addr *dst; if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy, NULL)) return -EINVAL; if (!opts[TIPC_NLA_UDP_REMOTE]) return -EINVAL; err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &addr, NULL); if (err) return err; dst = (struct udp_media_addr *)&b->bcast_addr.value; if (tipc_udp_is_mcast_addr(dst)) { pr_err("Can't add remote ip to TIPC UDP multicast bearer\n"); return -EINVAL; } if (tipc_udp_is_known_peer(b, &addr)) return 0; return tipc_udp_rcast_add(b, &addr); } /** * tipc_udp_enable - callback to create a new udp bearer instance * @net: network namespace * @b: pointer to generic tipc_bearer * @attrs: netlink bearer configuration * * validate the bearer parameters and initialize the udp bearer * rtnl_lock should be held */ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]) { int err = -EINVAL; struct udp_bearer *ub; struct udp_media_addr remote = {0}; struct udp_media_addr local = {0}; struct udp_port_cfg udp_conf = {0}; struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; u8 node_id[NODE_ID_LEN] = {0,}; struct net_device *dev; int rmcast = 0; ub = kzalloc(sizeof(*ub), GFP_ATOMIC); if (!ub) return -ENOMEM; INIT_LIST_HEAD(&ub->rcast.list); if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) goto err; if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attrs[TIPC_NLA_BEARER_UDP_OPTS], tipc_nl_udp_policy, NULL)) goto err; if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) { pr_err("Invalid UDP bearer configuration"); err = -EINVAL; goto err; } err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_LOCAL], &local, &ub->ifindex); if (err) goto err; err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &remote, NULL); if (err) goto err; if (remote.proto != local.proto) { err = -EINVAL; goto err; } /* Checking remote ip address */ rmcast = tipc_udp_is_mcast_addr(&remote); /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net)) { memcpy(node_id, local.ipv6.in6_u.u6_addr8, 16); tipc_net_init(net, node_id, 0); } if (!tipc_own_id(net)) { pr_warn("Failed to set node id, please configure manually\n"); err = -EINVAL; goto err; } b->bcast_addr.media_id = TIPC_MEDIA_TYPE_UDP; b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT; rcu_assign_pointer(b->media_ptr, ub); rcu_assign_pointer(ub->bearer, b); tipc_udp_media_addr_set(&b->addr, &local); if (local.proto == htons(ETH_P_IP)) { dev = __ip_dev_find(net, local.ipv4.s_addr, false); if (!dev) { err = -ENODEV; goto err; } udp_conf.family = AF_INET; /* Switch to use ANY to receive packets from group */ if (rmcast) udp_conf.local_ip.s_addr = htonl(INADDR_ANY); else udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL; dev = ipv6_dev_find(net, &local.ipv6, dev); if (!dev) { err = -ENODEV; goto err; } udp_conf.family = AF_INET6; udp_conf.use_udp6_tx_checksums = true; udp_conf.use_udp6_rx_checksums = true; if (rmcast) udp_conf.local_ip6 = in6addr_any; else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { err = -EAFNOSUPPORT; goto err; } udp_conf.local_udp_port = local.port; err = udp_sock_create(net, &udp_conf, &ub->ubsock); if (err) goto err; tuncfg.sk_user_data = ub; tuncfg.encap_type = 1; tuncfg.encap_rcv = tipc_udp_recv; tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); err = dst_cache_init(&ub->rcast.dst_cache, GFP_ATOMIC); if (err) goto free; /* * The bcast media address port is used for all peers and the ip * is used if it's a multicast address. */ memcpy(&b->bcast_addr.value, &remote, sizeof(remote)); if (rmcast) err = enable_mcast(ub, &remote); else err = tipc_udp_rcast_add(b, &remote); if (err) goto free; return 0; free: dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); err: kfree(ub); return err; } /* cleanup_bearer - break the socket/bearer association */ static void cleanup_bearer(struct work_struct *work) { struct udp_bearer *ub = container_of(work, struct udp_bearer, work); struct udp_replicast *rcast, *tmp; list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { dst_cache_destroy(&rcast->dst_cache); list_del_rcu(&rcast->list); kfree_rcu(rcast, rcu); } atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); synchronize_net(); kfree(ub); } /* tipc_udp_disable - detach bearer from socket */ static void tipc_udp_disable(struct tipc_bearer *b) { struct udp_bearer *ub; ub = rtnl_dereference(b->media_ptr); if (!ub) { pr_err("UDP bearer instance not found\n"); return; } sock_set_flag(ub->ubsock->sk, SOCK_DEAD); RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); INIT_WORK(&ub->work, cleanup_bearer); schedule_work(&ub->work); } struct tipc_media udp_media_info = { .send_msg = tipc_udp_send_msg, .enable_media = tipc_udp_enable, .disable_media = tipc_udp_disable, .addr2str = tipc_udp_addr2str, .addr2msg = tipc_udp_addr2msg, .msg2addr = tipc_udp_msg2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .min_win = TIPC_DEF_LINK_WIN, .max_win = TIPC_DEF_LINK_WIN, .mtu = TIPC_DEF_LINK_UDP_MTU, .type_id = TIPC_MEDIA_TYPE_UDP, .hwaddr_len = 0, .name = "udp" }; |
| 5 5 2 767 21 761 21 13 21 14 147 50 20 41 1 28 28 4 33 4 37 26 24 30 | 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 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; #ifndef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) #endif void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { return -EINVAL; } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { BUG(); } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_active_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ unsigned long generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } \ static inline int HPage##uname(struct page *page) \ { return test_bit(HPG_##flname, &(page->private)); } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } \ static inline void SetHPage##uname(struct page *page) \ { set_bit(HPG_##flname, &(page->private)); } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } \ static inline void ClearHPage##uname(struct page *page) \ { clear_bit(HPG_##flname, &(page->private)); } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } \ static inline int HPage##uname(struct page *page) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } \ static inline void SetHPage##uname(struct page *page) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } \ static inline void ClearHPage##uname(struct page *page) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ struct cftype cgroup_files_dfl[8]; struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return huge_page_order(h) > MAX_PAGE_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { if (hugepage_movable_supported(h)) return GFP_HIGHUSER_MOVABLE; else return GFP_HIGHUSER; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { if (huge_page_size(h) == PMD_SIZE) return pmd_lockptr(mm, (pmd_t *) pte); VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); return &mm->page_table_lock; } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { return -ENOMEM; } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PAGE) && \ defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 2 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UDF_SB_H #define __LINUX_UDF_SB_H #include <linux/mutex.h> #include <linux/bitops.h> #include <linux/magic.h> /* * Even UDF 2.6 media should have version <= 0x250 but apparently there are * some broken filesystems with version set to 0x260. Accommodate those. */ #define UDF_MAX_READ_VERSION 0x0260 #define UDF_MAX_WRITE_VERSION 0x0201 #define UDF_FLAG_USE_EXTENDED_FE 0 #define UDF_VERS_USE_EXTENDED_FE 0x0200 #define UDF_FLAG_USE_STREAMS 1 #define UDF_VERS_USE_STREAMS 0x0200 #define UDF_FLAG_USE_SHORT_AD 2 #define UDF_FLAG_USE_AD_IN_ICB 3 #define UDF_FLAG_USE_FILE_CTIME_EA 4 #define UDF_FLAG_STRICT 5 #define UDF_FLAG_UNDELETE 6 #define UDF_FLAG_UNHIDE 7 #define UDF_FLAG_NOVRS 8 #define UDF_FLAG_UID_FORGET 11 /* save -1 for uid to disk */ #define UDF_FLAG_GID_FORGET 12 #define UDF_FLAG_UID_SET 13 #define UDF_FLAG_GID_SET 14 #define UDF_FLAG_SESSION_SET 15 #define UDF_FLAG_LASTBLOCK_SET 16 #define UDF_FLAG_BLOCKSIZE_SET 17 #define UDF_FLAG_INCONSISTENT 18 #define UDF_FLAG_RW_INCOMPAT 19 /* Set when we find RW incompatible * feature */ #define UDF_PART_FLAG_UNALLOC_BITMAP 0x0001 #define UDF_PART_FLAG_UNALLOC_TABLE 0x0002 #define UDF_PART_FLAG_READ_ONLY 0x0010 #define UDF_PART_FLAG_WRITE_ONCE 0x0020 #define UDF_PART_FLAG_REWRITABLE 0x0040 #define UDF_PART_FLAG_OVERWRITABLE 0x0080 #define UDF_MAX_BLOCK_LOADED 8 #define UDF_TYPE1_MAP15 0x1511U #define UDF_VIRTUAL_MAP15 0x1512U #define UDF_VIRTUAL_MAP20 0x2012U #define UDF_SPARABLE_MAP15 0x1522U #define UDF_METADATA_MAP25 0x2511U #define UDF_INVALID_MODE ((umode_t)-1) #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 #define EFSCORRUPTED EUCLEAN struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; __u32 s_bitmap_file_loc; __u32 s_alloc_unit_size; __u16 s_align_unit_size; /* * Partition Reference Number of the associated physical / sparable * partition */ __u16 s_phys_partition_ref; int s_flags; struct inode *s_metadata_fe; struct inode *s_mirror_fe; struct inode *s_bitmap_fe; }; struct udf_sparing_data { __u16 s_packet_len; struct buffer_head *s_spar_map[4]; }; struct udf_virtual_data { __u32 s_num_entries; __u16 s_start_offset; }; struct udf_bitmap { __u32 s_extPosition; int s_nr_groups; struct buffer_head *s_block_bitmap[] __counted_by(s_nr_groups); }; struct udf_part_map { union { struct udf_bitmap *s_bitmap; struct inode *s_table; } s_uspace; __u32 s_partition_root; __u32 s_partition_len; __u16 s_partition_type; __u16 s_partition_num; union { struct udf_sparing_data s_sparing; struct udf_virtual_data s_virtual; struct udf_meta_data s_metadata; } s_type_specific; __u32 (*s_partition_func)(struct super_block *, __u32, __u16, __u32); __u16 s_volumeseqnum; __u16 s_partition_flags; }; #pragma pack() struct udf_sb_info { struct udf_part_map *s_partmaps; __u8 s_volume_ident[32]; /* Overall info */ __u16 s_partitions; __u16 s_partition; /* Sector headers */ __s32 s_session; __u32 s_anchor; __u32 s_last_block; struct buffer_head *s_lvid_bh; /* Default permissions */ umode_t s_umask; kgid_t s_gid; kuid_t s_uid; umode_t s_fmode; umode_t s_dmode; /* Lock protecting consistency of above permission settings */ rwlock_t s_cred_lock; /* Root Info */ struct timespec64 s_record_time; /* Fileset Info */ __u16 s_serial_number; /* highest UDF revision we have recorded to this media */ __u16 s_udfrev; /* Miscellaneous flags */ unsigned long s_flags; /* Encoding info */ struct nls_table *s_nls_map; /* VAT inode */ struct inode *s_vat_inode; struct mutex s_alloc_mutex; /* Protected by s_alloc_mutex */ unsigned int s_lvid_dirty; }; static inline struct udf_sb_info *UDF_SB(struct super_block *sb) { return sb->s_fs_info; } struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb); int udf_compute_nr_groups(struct super_block *sb, u32 partition); static inline int UDF_QUERY_FLAG(struct super_block *sb, int flag) { return test_bit(flag, &UDF_SB(sb)->s_flags); } static inline void UDF_SET_FLAG(struct super_block *sb, int flag) { set_bit(flag, &UDF_SB(sb)->s_flags); } static inline void UDF_CLEAR_FLAG(struct super_block *sb, int flag) { clear_bit(flag, &UDF_SB(sb)->s_flags); } #endif /* __LINUX_UDF_SB_H */ |
| 23 24 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2019 HUAWEI, Inc. * https://www.huawei.com/ */ #ifndef __EROFS_FS_COMPRESS_H #define __EROFS_FS_COMPRESS_H #include "internal.h" struct z_erofs_decompress_req { struct super_block *sb; struct page **in, **out; unsigned short pageofs_in, pageofs_out; unsigned int inputsize, outputsize; unsigned int alg; /* the algorithm for decompression */ bool inplace_io, partial_decoding, fillgaps; gfp_t gfp; /* allocation flags for extra temporary buffers */ }; struct z_erofs_decompressor { int (*config)(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; }; /* some special page->private (unsigned long, see below) */ #define Z_EROFS_SHORTLIVED_PAGE (-1UL << 2) #define Z_EROFS_PREALLOCATED_PAGE (-2UL << 2) /* * For all pages in a pcluster, page->private should be one of * Type Last 2bits page->private * short-lived page 00 Z_EROFS_SHORTLIVED_PAGE * preallocated page (tryalloc) 00 Z_EROFS_PREALLOCATED_PAGE * cached/managed page 00 pointer to z_erofs_pcluster * online page (file-backed, 01/10/11 sub-index << 2 | count * some pages can be used for inplace I/O) * * page->mapping should be one of * Type page->mapping * short-lived page NULL * preallocated page NULL * cached/managed page non-NULL or NULL (invalidated/truncated page) * online page non-NULL * * For all managed pages, PG_private should be set with 1 extra refcount, * which is used for page reclaim / migration. */ /* * short-lived pages are pages directly from buddy system with specific * page->private (no need to set PagePrivate since these are non-LRU / * non-movable pages and bypass reclaim / migration code). */ static inline bool z_erofs_is_shortlived_page(struct page *page) { if (page->private != Z_EROFS_SHORTLIVED_PAGE) return false; DBG_BUGON(page->mapping); return true; } static inline bool z_erofs_put_shortlivedpage(struct page **pagepool, struct page *page) { if (!z_erofs_is_shortlived_page(page)) return false; /* short-lived pages should not be used by others at the same time */ if (page_ref_count(page) > 1) { put_page(page); } else { /* follow the pcluster rule above. */ erofs_pagepool_add(pagepool, page); } return true; } int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, unsigned int padbufsize); extern const struct z_erofs_decompressor erofs_decompressors[]; /* prototypes for specific algorithms */ int z_erofs_load_lzma_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size); int z_erofs_load_deflate_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size); int z_erofs_load_zstd_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, struct page **pgpl); #endif |
| 9 11 5 299 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> * Patrick Schaaf <bof@bof.de> * Martin Josefsson <gandalf@wlug.westbo.se> * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifndef _IP_SET_H #define _IP_SET_H #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/stringify.h> #include <linux/vmalloc.h> #include <net/netlink.h> #include <uapi/linux/netfilter/ipset/ip_set.h> #define _IP_SET_MODULE_DESC(a, b, c) \ MODULE_DESCRIPTION(a " type of IP sets, revisions " b "-" c) #define IP_SET_MODULE_DESC(a, b, c) \ _IP_SET_MODULE_DESC(a, __stringify(b), __stringify(c)) /* Set features */ enum ip_set_feature { IPSET_TYPE_IP_FLAG = 0, IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG), IPSET_TYPE_PORT_FLAG = 1, IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG), IPSET_TYPE_MAC_FLAG = 2, IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG), IPSET_TYPE_IP2_FLAG = 3, IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG), IPSET_TYPE_NAME_FLAG = 4, IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), IPSET_TYPE_IFACE_FLAG = 5, IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG), IPSET_TYPE_MARK_FLAG = 6, IPSET_TYPE_MARK = (1 << IPSET_TYPE_MARK_FLAG), IPSET_TYPE_NOMATCH_FLAG = 7, IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG), /* Strictly speaking not a feature, but a flag for dumping: * this settype must be dumped last */ IPSET_DUMP_LAST_FLAG = 8, IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), }; /* Set extensions */ enum ip_set_extension { IPSET_EXT_BIT_TIMEOUT = 0, IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT), IPSET_EXT_BIT_COUNTER = 1, IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER), IPSET_EXT_BIT_COMMENT = 2, IPSET_EXT_COMMENT = (1 << IPSET_EXT_BIT_COMMENT), IPSET_EXT_BIT_SKBINFO = 3, IPSET_EXT_SKBINFO = (1 << IPSET_EXT_BIT_SKBINFO), /* Mark set with an extension which needs to call destroy */ IPSET_EXT_BIT_DESTROY = 7, IPSET_EXT_DESTROY = (1 << IPSET_EXT_BIT_DESTROY), }; #define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) #define SET_WITH_COUNTER(s) ((s)->extensions & IPSET_EXT_COUNTER) #define SET_WITH_COMMENT(s) ((s)->extensions & IPSET_EXT_COMMENT) #define SET_WITH_SKBINFO(s) ((s)->extensions & IPSET_EXT_SKBINFO) #define SET_WITH_FORCEADD(s) ((s)->flags & IPSET_CREATE_FLAG_FORCEADD) /* Extension id, in size order */ enum ip_set_ext_id { IPSET_EXT_ID_COUNTER = 0, IPSET_EXT_ID_TIMEOUT, IPSET_EXT_ID_SKBINFO, IPSET_EXT_ID_COMMENT, IPSET_EXT_ID_MAX, }; struct ip_set; /* Extension type */ struct ip_set_ext_type { /* Destroy extension private data (can be NULL) */ void (*destroy)(struct ip_set *set, void *ext); enum ip_set_extension type; enum ipset_cadt_flags flag; /* Size and minimal alignment */ u8 len; u8 align; }; extern const struct ip_set_ext_type ip_set_extensions[]; struct ip_set_counter { atomic64_t bytes; atomic64_t packets; }; struct ip_set_comment_rcu { struct rcu_head rcu; char str[]; }; struct ip_set_comment { struct ip_set_comment_rcu __rcu *c; }; struct ip_set_skbinfo { u32 skbmark; u32 skbmarkmask; u32 skbprio; u16 skbqueue; u16 __pad; }; struct ip_set_ext { struct ip_set_skbinfo skbinfo; u64 packets; u64 bytes; char *comment; u32 timeout; u8 packets_op; u8 bytes_op; bool target; }; #define ext_timeout(e, s) \ ((unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])) #define ext_counter(e, s) \ ((struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])) #define ext_comment(e, s) \ ((struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT])) #define ext_skbinfo(e, s) \ ((struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO])) typedef int (*ipset_adtfn)(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 cmdflags); /* Kernel API function options */ struct ip_set_adt_opt { u8 family; /* Actual protocol family */ u8 dim; /* Dimension of match/target */ u8 flags; /* Direction and negation flags */ u32 cmdflags; /* Command-like flags */ struct ip_set_ext ext; /* Extensions */ }; /* Set type, variant-specific part */ struct ip_set_type_variant { /* Kernelspace: test/add/del entries * returns negative error code, * zero for no match/success to add/delete * positive for matching element */ int (*kadt)(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt); /* Userspace: test/add/del entries * returns negative error code, * zero for no match/success to add/delete * positive for matching element */ int (*uadt)(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); /* Low level add/del/test functions */ ipset_adtfn adt[IPSET_ADT_MAX]; /* When adding entries and set is full, try to resize the set */ int (*resize)(struct ip_set *set, bool retried); /* Destroy the set */ void (*destroy)(struct ip_set *set); /* Flush the elements */ void (*flush)(struct ip_set *set); /* Expire entries before listing */ void (*expire)(struct ip_set *set); /* List set header data */ int (*head)(struct ip_set *set, struct sk_buff *skb); /* List elements */ int (*list)(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb); /* Keep listing private when resizing runs parallel */ void (*uref)(struct ip_set *set, struct netlink_callback *cb, bool start); /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); /* Cancel ongoing garbage collectors before destroying the set*/ void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; struct ip_set_region { spinlock_t lock; /* Region lock */ size_t ext_size; /* Size of the dynamic extensions */ u32 elements; /* Number of elements vs timeout */ }; /* Max range where every element is added/deleted in one step */ #define IPSET_MAX_RANGE (1<<14) /* The max revision number supported by any set type + 1 */ #define IPSET_REVISION_MAX 9 /* The core set type structure */ struct ip_set_type { struct list_head list; /* Typename */ char name[IPSET_MAXNAMELEN]; /* Protocol version */ u8 protocol; /* Set type dimension */ u8 dimension; /* * Supported family: may be NFPROTO_UNSPEC for both * NFPROTO_IPV4/NFPROTO_IPV6. */ u8 family; /* Type revisions */ u8 revision_min, revision_max; /* Revision-specific supported (create) flags */ u8 create_flags[IPSET_REVISION_MAX+1]; /* Set features to control swapping */ u16 features; /* Create set */ int (*create)(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags); /* Attribute policies */ const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1]; const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1]; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; }; /* register and unregister set type */ extern int ip_set_type_register(struct ip_set_type *set_type); extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { /* For call_cru in destroy */ struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ spinlock_t lock; /* References to the set */ u32 ref; /* References to the set for netlink events like dump, * ref can be swapped out by ip_set_swap */ u32 ref_netlink; /* The core set type */ struct ip_set_type *type; /* The type variant doing the real job */ const struct ip_set_type_variant *variant; /* The actual INET family of the set */ u8 family; /* The type revision */ u8 revision; /* Extensions */ u8 extensions; /* Create flags */ u8 flags; /* Default timeout value, if enabled */ u32 timeout; /* Number of elements (vs timeout) */ u32 elements; /* Size of the dynamic extensions (vs timeout) */ size_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ size_t offset[IPSET_EXT_ID_MAX]; /* The type specific data */ void *data; }; static inline void ip_set_ext_destroy(struct ip_set *set, void *data) { /* Check that the extension is enabled for the set and * call it's destroy function for its extension part in data. */ if (SET_WITH_COMMENT(set)) { struct ip_set_comment *c = ext_comment(data, set); ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(set, c); } } int ip_set_put_flags(struct sk_buff *skb, struct ip_set *set); /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ IPSET_CB_PROTO, /* ipset protocol */ IPSET_CB_DUMP, /* dump single set/all sets */ IPSET_CB_INDEX, /* set index */ IPSET_CB_PRIVATE, /* set private data */ IPSET_CB_ARG0, /* type specific */ }; /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); /* API for iptables set match, and SET target */ extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt); extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt); extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt); /* Utility functions */ extern void *ip_set_alloc(size_t size); extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, size_t align); extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext); extern int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, const void *e, bool active); extern bool ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags, void *data); static inline int ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) { __be32 ip; int ret = ip_set_get_ipaddr4(nla, &ip); if (ret) return ret; *ipaddr = ntohl(ip); return 0; } /* Ignore IPSET_ERR_EXIST errors if asked to do so? */ static inline bool ip_set_eexist(int ret, u32 flags) { return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); } /* Match elements marked with nomatch */ static inline bool ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && (set->type->features & IPSET_TYPE_NOMATCH) && ((flags >> 16) & IPSET_FLAG_NOMATCH) && (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ static inline bool ip_set_attr_netorder(struct nlattr *tb[], int type) { return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER); } static inline bool ip_set_optattr_netorder(struct nlattr *tb[], int type) { return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER); } /* Useful converters */ static inline u32 ip_set_get_h32(const struct nlattr *attr) { return ntohl(nla_get_be32(attr)); } static inline u16 ip_set_get_h16(const struct nlattr *attr) { return ntohs(nla_get_be16(attr)); } static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) { struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); if (!ret) nla_nest_end(skb, __nested); return ret; } static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, const struct in6_addr *ipaddrptr) { struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr); if (!ret) nla_nest_end(skb, __nested); return ret; } /* Get address from skbuff */ static inline __be32 ip4addr(const struct sk_buff *skb, bool src) { return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; } static inline void ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr) { *addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; } static inline void ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) { memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr, sizeof(*addr)); } /* How often should the gc be run by default */ #define IPSET_GC_TIME (3 * 60) /* Timeout period depending on the timeout value of the given set */ #define IPSET_GC_PERIOD(timeout) \ ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) /* Entry is set with no timeout value */ #define IPSET_ELEM_PERMANENT 0 /* Set is defined with timeout support: timeout value may be 0 */ #define IPSET_NO_TIMEOUT UINT_MAX /* Max timeout value, see msecs_to_jiffies() in jiffies.h */ #define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC #define ip_set_adt_opt_timeout(opt, set) \ ((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) static inline unsigned int ip_set_timeout_uget(struct nlattr *tb) { unsigned int timeout = ip_set_get_h32(tb); /* Normalize to fit into jiffies */ if (timeout > IPSET_MAX_TIMEOUT) timeout = IPSET_MAX_TIMEOUT; return timeout; } static inline bool ip_set_timeout_expired(const unsigned long *t) { return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); } static inline void ip_set_timeout_set(unsigned long *timeout, u32 value) { unsigned long t; if (!value) { *timeout = IPSET_ELEM_PERMANENT; return; } t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; if (t == IPSET_ELEM_PERMANENT) /* Bingo! :-) */ t--; *timeout = t; } void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, const struct ip_set_ext *ext); static inline void ip_set_init_counter(struct ip_set_counter *counter, const struct ip_set_ext *ext) { if (ext->bytes != ULLONG_MAX) atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); if (ext->packets != ULLONG_MAX) atomic64_set(&(counter)->packets, (long long)(ext->packets)); } static inline void ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext) { *skbinfo = ext->skbinfo; } static inline void nf_inet_addr_mask_inplace(union nf_inet_addr *a1, const union nf_inet_addr *mask) { a1->all[0] &= mask->all[0]; a1->all[1] &= mask->all[1]; a1->all[2] &= mask->all[2]; a1->all[3] &= mask->all[3]; } #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ { .bytes = ULLONG_MAX, .packets = ULLONG_MAX, \ .timeout = (set)->timeout } #define IPSET_CONCAT(a, b) a##b #define IPSET_TOKEN(a, b) IPSET_CONCAT(a, b) #endif /*_IP_SET_H */ |
| 51 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Device core Trace Support * Copyright (C) 2021, Intel Corporation * * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM dev #if !defined(__DEV_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define __DEV_TRACE_H #include <linux/device.h> #include <linux/tracepoint.h> #include <linux/types.h> DECLARE_EVENT_CLASS(devres, TP_PROTO(struct device *dev, const char *op, void *node, const char *name, size_t size), TP_ARGS(dev, op, node, name, size), TP_STRUCT__entry( __string(devname, dev_name(dev)) __field(struct device *, dev) __field(const char *, op) __field(void *, node) __field(const char *, name) __field(size_t, size) ), TP_fast_assign( __assign_str(devname); __entry->op = op; __entry->node = node; __entry->name = name; __entry->size = size; ), TP_printk("%s %3s %p %s (%zu bytes)", __get_str(devname), __entry->op, __entry->node, __entry->name, __entry->size) ); DEFINE_EVENT(devres, devres_log, TP_PROTO(struct device *dev, const char *op, void *node, const char *name, size_t size), TP_ARGS(dev, op, node, name, size) ); #endif /* __DEV_TRACE_H */ /* this part has to be here */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 1149 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * ACPI support * * Copyright (C) 2020, Intel Corporation * Author: Mika Westerberg <mika.westerberg@linux.intel.com> */ #include <linux/acpi.h> #include <linux/pm_runtime.h> #include "tb.h" static acpi_status tb_acpi_add_link(acpi_handle handle, u32 level, void *data, void **ret) { struct acpi_device *adev = acpi_fetch_acpi_dev(handle); struct fwnode_handle *fwnode; struct tb_nhi *nhi = data; struct pci_dev *pdev; struct device *dev; if (!adev) return AE_OK; fwnode = fwnode_find_reference(acpi_fwnode_handle(adev), "usb4-host-interface", 0); if (IS_ERR(fwnode)) return AE_OK; /* It needs to reference this NHI */ if (dev_fwnode(&nhi->pdev->dev) != fwnode) goto out_put; /* * Try to find physical device walking upwards to the hierarcy. * We need to do this because the xHCI driver might not yet be * bound so the USB3 SuperSpeed ports are not yet created. */ do { dev = acpi_get_first_physical_node(adev); if (dev) break; adev = acpi_dev_parent(adev); } while (adev); /* * Check that the device is PCIe. This is because USB3 * SuperSpeed ports have this property and they are not power * managed with the xHCI and the SuperSpeed hub so we create the * link from xHCI instead. */ while (dev && !dev_is_pci(dev)) dev = dev->parent; if (!dev) goto out_put; /* * Check that this actually matches the type of device we * expect. It should either be xHCI or PCIe root/downstream * port. */ pdev = to_pci_dev(dev); if (pdev->class == PCI_CLASS_SERIAL_USB_XHCI || (pci_is_pcie(pdev) && (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM))) { const struct device_link *link; /* * Make them both active first to make sure the NHI does * not runtime suspend before the consumer. The * pm_runtime_put() below then allows the consumer to * runtime suspend again (which then allows NHI runtime * suspend too now that the device link is established). */ pm_runtime_get_sync(&pdev->dev); link = device_link_add(&pdev->dev, &nhi->pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER | DL_FLAG_RPM_ACTIVE | DL_FLAG_PM_RUNTIME); if (link) { dev_dbg(&nhi->pdev->dev, "created link from %s\n", dev_name(&pdev->dev)); *(bool *)ret = true; } else { dev_warn(&nhi->pdev->dev, "device link creation from %s failed\n", dev_name(&pdev->dev)); } pm_runtime_put(&pdev->dev); } out_put: fwnode_handle_put(fwnode); return AE_OK; } /** * tb_acpi_add_links() - Add device links based on ACPI description * @nhi: Pointer to NHI * * Goes over ACPI namespace finding tunneled ports that reference to * @nhi ACPI node. For each reference a device link is added. The link * is automatically removed by the driver core. * * Returns %true if at least one link was created. */ bool tb_acpi_add_links(struct tb_nhi *nhi) { acpi_status status; bool ret = false; if (!has_acpi_companion(&nhi->pdev->dev)) return false; /* * Find all devices that have usb4-host-controller interface * property that references to this NHI. */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, 32, tb_acpi_add_link, NULL, nhi, (void **)&ret); if (ACPI_FAILURE(status)) { dev_warn(&nhi->pdev->dev, "failed to enumerate tunneled ports\n"); return false; } return ret; } /** * tb_acpi_is_native() - Did the platform grant native TBT/USB4 control * * Returns %true if the platform granted OS native control over * TBT/USB4. In this case software based connection manager can be used, * otherwise there is firmware based connection manager running. */ bool tb_acpi_is_native(void) { return osc_sb_native_usb4_support_confirmed && osc_sb_native_usb4_control; } /** * tb_acpi_may_tunnel_usb3() - Is USB3 tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native USB3 tunneling. */ bool tb_acpi_may_tunnel_usb3(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_USB3_TUNNELING; return true; } /** * tb_acpi_may_tunnel_dp() - Is DisplayPort tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native DP tunneling. */ bool tb_acpi_may_tunnel_dp(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_DP_TUNNELING; return true; } /** * tb_acpi_may_tunnel_pcie() - Is PCIe tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native PCIe tunneling. */ bool tb_acpi_may_tunnel_pcie(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_PCIE_TUNNELING; return true; } /** * tb_acpi_is_xdomain_allowed() - Are XDomain connections allowed * * When software based connection manager is used, this function * returns %true if platform allows XDomain connections. */ bool tb_acpi_is_xdomain_allowed(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_XDOMAIN; return true; } /* UUID for retimer _DSM: e0053122-795b-4122-8a5e-57be1d26acb3 */ static const guid_t retimer_dsm_guid = GUID_INIT(0xe0053122, 0x795b, 0x4122, 0x8a, 0x5e, 0x57, 0xbe, 0x1d, 0x26, 0xac, 0xb3); #define RETIMER_DSM_QUERY_ONLINE_STATE 1 #define RETIMER_DSM_SET_ONLINE_STATE 2 static int tb_acpi_retimer_set_power(struct tb_port *port, bool power) { struct usb4_port *usb4 = port->usb4; union acpi_object argv4[2]; struct acpi_device *adev; union acpi_object *obj; int ret; if (!usb4->can_offline) return 0; adev = ACPI_COMPANION(&usb4->dev); if (WARN_ON(!adev)) return 0; /* Check if we are already powered on (and in correct mode) */ obj = acpi_evaluate_dsm_typed(adev->handle, &retimer_dsm_guid, 1, RETIMER_DSM_QUERY_ONLINE_STATE, NULL, ACPI_TYPE_INTEGER); if (!obj) { tb_port_warn(port, "ACPI: query online _DSM failed\n"); return -EIO; } ret = obj->integer.value; ACPI_FREE(obj); if (power == ret) return 0; tb_port_dbg(port, "ACPI: calling _DSM to power %s retimers\n", power ? "on" : "off"); argv4[0].type = ACPI_TYPE_PACKAGE; argv4[0].package.count = 1; argv4[0].package.elements = &argv4[1]; argv4[1].integer.type = ACPI_TYPE_INTEGER; argv4[1].integer.value = power; obj = acpi_evaluate_dsm_typed(adev->handle, &retimer_dsm_guid, 1, RETIMER_DSM_SET_ONLINE_STATE, argv4, ACPI_TYPE_INTEGER); if (!obj) { tb_port_warn(port, "ACPI: set online state _DSM evaluation failed\n"); return -EIO; } ret = obj->integer.value; ACPI_FREE(obj); if (ret >= 0) { if (power) return ret == 1 ? 0 : -EBUSY; return 0; } tb_port_warn(port, "ACPI: set online state _DSM failed with error %d\n", ret); return -EIO; } /** * tb_acpi_power_on_retimers() - Call platform to power on retimers * @port: USB4 port * * Calls platform to turn on power to all retimers behind this USB4 * port. After this function returns successfully the caller can * continue with the normal retimer flows (as specified in the USB4 * spec). Note if this returns %-EBUSY it means the type-C port is in * non-USB4/TBT mode (there is non-USB4/TBT device connected). * * This should only be called if the USB4/TBT link is not up. * * Returns %0 on success. */ int tb_acpi_power_on_retimers(struct tb_port *port) { return tb_acpi_retimer_set_power(port, true); } /** * tb_acpi_power_off_retimers() - Call platform to power off retimers * @port: USB4 port * * This is the opposite of tb_acpi_power_on_retimers(). After returning * successfully the normal operations with the @port can continue. * * Returns %0 on success. */ int tb_acpi_power_off_retimers(struct tb_port *port) { return tb_acpi_retimer_set_power(port, false); } static bool tb_acpi_bus_match(struct device *dev) { return tb_is_switch(dev) || tb_is_usb4_port_device(dev); } static struct acpi_device *tb_acpi_switch_find_companion(struct tb_switch *sw) { struct tb_switch *parent_sw = tb_switch_parent(sw); struct acpi_device *adev = NULL; /* * Device routers exists under the downstream facing USB4 port * of the parent router. Their _ADR is always 0. */ if (parent_sw) { struct tb_port *port = tb_switch_downstream_port(sw); struct acpi_device *port_adev; port_adev = acpi_find_child_by_adr(ACPI_COMPANION(&parent_sw->dev), port->port); if (port_adev) adev = acpi_find_child_device(port_adev, 0, false); } else { struct tb_nhi *nhi = sw->tb->nhi; struct acpi_device *parent_adev; parent_adev = ACPI_COMPANION(&nhi->pdev->dev); if (parent_adev) adev = acpi_find_child_device(parent_adev, 0, false); } return adev; } static struct acpi_device *tb_acpi_find_companion(struct device *dev) { /* * The Thunderbolt/USB4 hierarchy looks like following: * * Device (NHI) * Device (HR) // Host router _ADR == 0 * Device (DFP0) // Downstream port _ADR == lane 0 adapter * Device (DR) // Device router _ADR == 0 * Device (UFP) // Upstream port _ADR == lane 0 adapter * Device (DFP1) // Downstream port _ADR == lane 0 adapter number * * At the moment we bind the host router to the corresponding * Linux device. */ if (tb_is_switch(dev)) return tb_acpi_switch_find_companion(tb_to_switch(dev)); if (tb_is_usb4_port_device(dev)) return acpi_find_child_by_adr(ACPI_COMPANION(dev->parent), tb_to_usb4_port_device(dev)->port->port); return NULL; } static void tb_acpi_setup(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); struct usb4_port *usb4 = tb_to_usb4_port_device(dev); if (!adev || !usb4) return; if (acpi_check_dsm(adev->handle, &retimer_dsm_guid, 1, BIT(RETIMER_DSM_QUERY_ONLINE_STATE) | BIT(RETIMER_DSM_SET_ONLINE_STATE))) usb4->can_offline = true; } static struct acpi_bus_type tb_acpi_bus = { .name = "thunderbolt", .match = tb_acpi_bus_match, .find_companion = tb_acpi_find_companion, .setup = tb_acpi_setup, }; int tb_acpi_init(void) { return register_acpi_bus_type(&tb_acpi_bus); } void tb_acpi_exit(void) { unregister_acpi_bus_type(&tb_acpi_bus); } |
| 16 16 11 11 11 11 11 8 8 3 8 8 8 8 8 8 8 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> * * Based on net/ipv4/xfrm4_tunnel.c */ #include <linux/module.h> #include <linux/xfrm.h> #include <linux/slab.h> #include <linux/rculist.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/mutex.h> #include <net/netns/generic.h> #define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256 #define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256 #define XFRM6_TUNNEL_SPI_MIN 1 #define XFRM6_TUNNEL_SPI_MAX 0xffffffff struct xfrm6_tunnel_net { struct hlist_head spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE]; struct hlist_head spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE]; u32 spi; }; static unsigned int xfrm6_tunnel_net_id __read_mostly; static inline struct xfrm6_tunnel_net *xfrm6_tunnel_pernet(struct net *net) { return net_generic(net, xfrm6_tunnel_net_id); } /* * xfrm_tunnel_spi things are for allocating unique id ("spi") * per xfrm_address_t. */ struct xfrm6_tunnel_spi { struct hlist_node list_byaddr; struct hlist_node list_byspi; xfrm_address_t addr; u32 spi; refcount_t refcnt; struct rcu_head rcu_head; }; static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly; static inline unsigned int xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) { unsigned int h; h = ipv6_addr_hash((const struct in6_addr *)addr); h ^= h >> 16; h ^= h >> 8; h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1; return h; } static inline unsigned int xfrm6_tunnel_spi_hash_byspi(u32 spi) { return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE; } static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; hlist_for_each_entry_rcu(x6spi, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr, lockdep_is_held(&xfrm6_tunnel_spi_lock)) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) return x6spi; } return NULL; } __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; rcu_read_lock_bh(); x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); spi = x6spi ? x6spi->spi : 0; rcu_read_unlock_bh(); return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup); static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; int index = xfrm6_tunnel_spi_hash_byspi(spi); hlist_for_each_entry(x6spi, &xfrm6_tn->spi_byspi[index], list_byspi) { if (x6spi->spi == spi) return -1; } return index; } static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); u32 spi; struct xfrm6_tunnel_spi *x6spi; int index; if (xfrm6_tn->spi < XFRM6_TUNNEL_SPI_MIN || xfrm6_tn->spi >= XFRM6_TUNNEL_SPI_MAX) xfrm6_tn->spi = XFRM6_TUNNEL_SPI_MIN; else xfrm6_tn->spi++; for (spi = xfrm6_tn->spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) { index = __xfrm6_tunnel_spi_check(net, spi); if (index >= 0) goto alloc_spi; if (spi == XFRM6_TUNNEL_SPI_MAX) break; } for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) { index = __xfrm6_tunnel_spi_check(net, spi); if (index >= 0) goto alloc_spi; } spi = 0; goto out; alloc_spi: xfrm6_tn->spi = spi; x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, GFP_ATOMIC); if (!x6spi) goto out; memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; refcount_set(&x6spi->refcnt, 1); hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]); index = xfrm6_tunnel_spi_hash_byaddr(saddr); hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tn->spi_byaddr[index]); out: return spi; } __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; spin_lock_bh(&xfrm6_tunnel_spi_lock); x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { refcount_inc(&x6spi->refcnt); spi = x6spi->spi; } else spi = __xfrm6_tunnel_alloc_spi(net, saddr); spin_unlock_bh(&xfrm6_tunnel_spi_lock); return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); static void x6spi_destroy_rcu(struct rcu_head *head) { kmem_cache_free(xfrm6_tunnel_spi_kmem, container_of(head, struct xfrm6_tunnel_spi, rcu_head)); } static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; struct hlist_node *n; spin_lock_bh(&xfrm6_tunnel_spi_lock); hlist_for_each_entry_safe(x6spi, n, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) { if (refcount_dec_and_test(&x6spi->refcnt)) { hlist_del_rcu(&x6spi->list_byaddr); hlist_del_rcu(&x6spi->list_byspi); call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); break; } } } spin_unlock_bh(&xfrm6_tunnel_spi_lock); } static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { skb_push(skb, -skb_network_offset(skb)); return 0; } static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { return skb_network_header(skb)[IP6CB(skb)->nhoff]; } static int xfrm6_tunnel_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = ipv6_hdr(skb); __be32 spi; spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr); return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL); } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { /* xfrm6_tunnel native err handling */ switch (type) { case ICMPV6_DEST_UNREACH: switch (code) { case ICMPV6_NOROUTE: case ICMPV6_ADM_PROHIBITED: case ICMPV6_NOT_NEIGHBOUR: case ICMPV6_ADDR_UNREACH: case ICMPV6_PORT_UNREACH: default: break; } break; case ICMPV6_PKT_TOOBIG: break; case ICMPV6_TIME_EXCEED: switch (code) { case ICMPV6_EXC_HOPLIMIT: break; case ICMPV6_EXC_FRAGTIME: default: break; } break; case ICMPV6_PARAMPROB: switch (code) { case ICMPV6_HDR_FIELD: break; case ICMPV6_UNK_NEXTHDR: break; case ICMPV6_UNK_OPTION: break; } break; default: break; } return 0; } static int xfrm6_tunnel_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { if (x->props.mode != XFRM_MODE_TUNNEL) { NL_SET_ERR_MSG(extack, "IPv6 tunnel can only be used with tunnel mode"); return -EINVAL; } if (x->encap) { NL_SET_ERR_MSG(extack, "IPv6 tunnel is not compatible with encapsulation"); return -EINVAL; } x->props.header_len = sizeof(struct ipv6hdr); return 0; } static void xfrm6_tunnel_destroy(struct xfrm_state *x) { struct net *net = xs_net(x); xfrm6_tunnel_free_spi(net, (xfrm_address_t *)&x->props.saddr); } static const struct xfrm_type xfrm6_tunnel_type = { .owner = THIS_MODULE, .proto = IPPROTO_IPV6, .init_state = xfrm6_tunnel_init_state, .destructor = xfrm6_tunnel_destroy, .input = xfrm6_tunnel_input, .output = xfrm6_tunnel_output, }; static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, .priority = 3, }; static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, .priority = 3, }; static int __net_init xfrm6_tunnel_net_init(struct net *net) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) INIT_HLIST_HEAD(&xfrm6_tn->spi_byaddr[i]); for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) INIT_HLIST_HEAD(&xfrm6_tn->spi_byspi[i]); xfrm6_tn->spi = 0; return 0; } static void __net_exit xfrm6_tunnel_net_exit(struct net *net) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; xfrm_flush_gc(); xfrm_state_flush(net, 0, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byspi[i])); } static struct pernet_operations xfrm6_tunnel_net_ops = { .init = xfrm6_tunnel_net_init, .exit = xfrm6_tunnel_net_exit, .id = &xfrm6_tunnel_net_id, .size = sizeof(struct xfrm6_tunnel_net), }; static int __init xfrm6_tunnel_init(void) { int rv; xfrm6_tunnel_spi_kmem = KMEM_CACHE(xfrm6_tunnel_spi, SLAB_HWCACHE_ALIGN); if (!xfrm6_tunnel_spi_kmem) return -ENOMEM; rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); if (rv < 0) goto out_pernet; rv = xfrm_register_type(&xfrm6_tunnel_type, AF_INET6); if (rv < 0) goto out_type; rv = xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6); if (rv < 0) goto out_xfrm6; rv = xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET); if (rv < 0) goto out_xfrm46; return 0; out_xfrm46: xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); out_xfrm6: xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); out_type: unregister_pernet_subsys(&xfrm6_tunnel_net_ops); out_pernet: kmem_cache_destroy(xfrm6_tunnel_spi_kmem); return rv; } static void __exit xfrm6_tunnel_fini(void) { xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); unregister_pernet_subsys(&xfrm6_tunnel_net_ops); /* Someone maybe has gotten the xfrm6_tunnel_spi. * So need to wait it. */ rcu_barrier(); kmem_cache_destroy(xfrm6_tunnel_spi_kmem); } module_init(xfrm6_tunnel_init); module_exit(xfrm6_tunnel_fini); MODULE_DESCRIPTION("IPv6 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6); |
| 40 40 158 158 158 158 157 157 157 157 2 2 2 2 2 10 11 11 11 11 11 11 11 11 11 2 157 157 4 40 40 40 39 40 40 40 39 40 40 40 40 40 127 56 55 127 61 127 53 52 53 53 53 2 2 271 271 271 270 271 271 270 113 113 113 40 113 53 53 36 53 53 53 53 53 53 53 39 53 53 53 53 53 53 53 51 53 27 27 27 27 27 27 27 197 197 153 147 147 147 147 152 150 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 | // SPDX-License-Identifier: GPL-2.0 /* * Code for manipulating bucket marks for garbage collection. * * Copyright 2014 Datera, Inc. */ #include "bcachefs.h" #include "alloc_background.h" #include "backpointers.h" #include "bset.h" #include "btree_gc.h" #include "btree_update.h" #include "buckets.h" #include "buckets_waiting_for_journal.h" #include "ec.h" #include "error.h" #include "inode.h" #include "movinggc.h" #include "recovery.h" #include "reflink.h" #include "replicas.h" #include "subvolume.h" #include "trace.h" #include <linux/preempt.h> static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage, enum bch_data_type data_type, s64 sectors) { switch (data_type) { case BCH_DATA_btree: fs_usage->btree += sectors; break; case BCH_DATA_user: case BCH_DATA_parity: fs_usage->data += sectors; break; case BCH_DATA_cached: fs_usage->cached += sectors; break; default: break; } } void bch2_fs_usage_initialize(struct bch_fs *c) { percpu_down_write(&c->mark_lock); struct bch_fs_usage *usage = c->usage_base; for (unsigned i = 0; i < ARRAY_SIZE(c->usage); i++) bch2_fs_usage_acc_to_base(c, i); for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++) usage->b.reserved += usage->persistent_reserved[i]; for (unsigned i = 0; i < c->replicas.nr; i++) { struct bch_replicas_entry_v1 *e = cpu_replicas_entry(&c->replicas, i); fs_usage_data_type_to_base(&usage->b, e->data_type, usage->replicas[i]); } for_each_member_device(c, ca) { struct bch_dev_usage dev = bch2_dev_usage_read(ca); usage->b.hidden += (dev.d[BCH_DATA_sb].buckets + dev.d[BCH_DATA_journal].buckets) * ca->mi.bucket_size; } percpu_up_write(&c->mark_lock); } static inline struct bch_dev_usage *dev_usage_ptr(struct bch_dev *ca, unsigned journal_seq, bool gc) { BUG_ON(!gc && !journal_seq); return this_cpu_ptr(gc ? ca->usage_gc : ca->usage[journal_seq & JOURNAL_BUF_MASK]); } void bch2_dev_usage_read_fast(struct bch_dev *ca, struct bch_dev_usage *usage) { struct bch_fs *c = ca->fs; unsigned seq, i, u64s = dev_usage_u64s(); do { seq = read_seqcount_begin(&c->usage_lock); memcpy(usage, ca->usage_base, u64s * sizeof(u64)); for (i = 0; i < ARRAY_SIZE(ca->usage); i++) acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage[i], u64s); } while (read_seqcount_retry(&c->usage_lock, seq)); } u64 bch2_fs_usage_read_one(struct bch_fs *c, u64 *v) { ssize_t offset = v - (u64 *) c->usage_base; unsigned i, seq; u64 ret; BUG_ON(offset < 0 || offset >= fs_usage_u64s(c)); percpu_rwsem_assert_held(&c->mark_lock); do { seq = read_seqcount_begin(&c->usage_lock); ret = *v; for (i = 0; i < ARRAY_SIZE(c->usage); i++) ret += percpu_u64_get((u64 __percpu *) c->usage[i] + offset); } while (read_seqcount_retry(&c->usage_lock, seq)); return ret; } struct bch_fs_usage_online *bch2_fs_usage_read(struct bch_fs *c) { struct bch_fs_usage_online *ret; unsigned nr_replicas = READ_ONCE(c->replicas.nr); unsigned seq, i; retry: ret = kmalloc(__fs_usage_online_u64s(nr_replicas) * sizeof(u64), GFP_KERNEL); if (unlikely(!ret)) return NULL; percpu_down_read(&c->mark_lock); if (nr_replicas != c->replicas.nr) { nr_replicas = c->replicas.nr; percpu_up_read(&c->mark_lock); kfree(ret); goto retry; } ret->online_reserved = percpu_u64_get(c->online_reserved); do { seq = read_seqcount_begin(&c->usage_lock); unsafe_memcpy(&ret->u, c->usage_base, __fs_usage_u64s(nr_replicas) * sizeof(u64), "embedded variable length struct"); for (i = 0; i < ARRAY_SIZE(c->usage); i++) acc_u64s_percpu((u64 *) &ret->u, (u64 __percpu *) c->usage[i], __fs_usage_u64s(nr_replicas)); } while (read_seqcount_retry(&c->usage_lock, seq)); return ret; } void bch2_fs_usage_acc_to_base(struct bch_fs *c, unsigned idx) { unsigned u64s = fs_usage_u64s(c); BUG_ON(idx >= ARRAY_SIZE(c->usage)); preempt_disable(); write_seqcount_begin(&c->usage_lock); acc_u64s_percpu((u64 *) c->usage_base, (u64 __percpu *) c->usage[idx], u64s); percpu_memset(c->usage[idx], 0, u64s * sizeof(u64)); rcu_read_lock(); for_each_member_device_rcu(c, ca, NULL) { u64s = dev_usage_u64s(); acc_u64s_percpu((u64 *) ca->usage_base, (u64 __percpu *) ca->usage[idx], u64s); percpu_memset(ca->usage[idx], 0, u64s * sizeof(u64)); } rcu_read_unlock(); write_seqcount_end(&c->usage_lock); preempt_enable(); } void bch2_fs_usage_to_text(struct printbuf *out, struct bch_fs *c, struct bch_fs_usage_online *fs_usage) { unsigned i; prt_printf(out, "capacity:\t\t\t%llu\n", c->capacity); prt_printf(out, "hidden:\t\t\t\t%llu\n", fs_usage->u.b.hidden); prt_printf(out, "data:\t\t\t\t%llu\n", fs_usage->u.b.data); prt_printf(out, "cached:\t\t\t\t%llu\n", fs_usage->u.b.cached); prt_printf(out, "reserved:\t\t\t%llu\n", fs_usage->u.b.reserved); prt_printf(out, "nr_inodes:\t\t\t%llu\n", fs_usage->u.b.nr_inodes); prt_printf(out, "online reserved:\t\t%llu\n", fs_usage->online_reserved); for (i = 0; i < ARRAY_SIZE(fs_usage->u.persistent_reserved); i++) { prt_printf(out, "%u replicas:\n", i + 1); prt_printf(out, "\treserved:\t\t%llu\n", fs_usage->u.persistent_reserved[i]); } for (i = 0; i < c->replicas.nr; i++) { struct bch_replicas_entry_v1 *e = cpu_replicas_entry(&c->replicas, i); prt_printf(out, "\t"); bch2_replicas_entry_to_text(out, e); prt_printf(out, ":\t%llu\n", fs_usage->u.replicas[i]); } } static u64 reserve_factor(u64 r) { return r + (round_up(r, (1 << RESERVE_FACTOR)) >> RESERVE_FACTOR); } u64 bch2_fs_sectors_used(struct bch_fs *c, struct bch_fs_usage_online *fs_usage) { return min(fs_usage->u.b.hidden + fs_usage->u.b.btree + fs_usage->u.b.data + reserve_factor(fs_usage->u.b.reserved + fs_usage->online_reserved), c->capacity); } static struct bch_fs_usage_short __bch2_fs_usage_read_short(struct bch_fs *c) { struct bch_fs_usage_short ret; u64 data, reserved; ret.capacity = c->capacity - bch2_fs_usage_read_one(c, &c->usage_base->b.hidden); data = bch2_fs_usage_read_one(c, &c->usage_base->b.data) + bch2_fs_usage_read_one(c, &c->usage_base->b.btree); reserved = bch2_fs_usage_read_one(c, &c->usage_base->b.reserved) + percpu_u64_get(c->online_reserved); ret.used = min(ret.capacity, data + reserve_factor(reserved)); ret.free = ret.capacity - ret.used; ret.nr_inodes = bch2_fs_usage_read_one(c, &c->usage_base->b.nr_inodes); return ret; } struct bch_fs_usage_short bch2_fs_usage_read_short(struct bch_fs *c) { struct bch_fs_usage_short ret; percpu_down_read(&c->mark_lock); ret = __bch2_fs_usage_read_short(c); percpu_up_read(&c->mark_lock); return ret; } void bch2_dev_usage_init(struct bch_dev *ca) { ca->usage_base->d[BCH_DATA_free].buckets = ca->mi.nbuckets - ca->mi.first_bucket; } void bch2_dev_usage_to_text(struct printbuf *out, struct bch_dev_usage *usage) { prt_printf(out, "\tbuckets\rsectors\rfragmented\r\n"); for (unsigned i = 0; i < BCH_DATA_NR; i++) { bch2_prt_data_type(out, i); prt_printf(out, "\t%llu\r%llu\r%llu\r\n", usage->d[i].buckets, usage->d[i].sectors, usage->d[i].fragmented); } } void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca, const struct bch_alloc_v4 *old, const struct bch_alloc_v4 *new, u64 journal_seq, bool gc) { struct bch_fs_usage *fs_usage; struct bch_dev_usage *u; preempt_disable(); fs_usage = fs_usage_ptr(c, journal_seq, gc); if (data_type_is_hidden(old->data_type)) fs_usage->b.hidden -= ca->mi.bucket_size; if (data_type_is_hidden(new->data_type)) fs_usage->b.hidden += ca->mi.bucket_size; u = dev_usage_ptr(ca, journal_seq, gc); u->d[old->data_type].buckets--; u->d[new->data_type].buckets++; u->d[old->data_type].sectors -= bch2_bucket_sectors_dirty(*old); u->d[new->data_type].sectors += bch2_bucket_sectors_dirty(*new); u->d[BCH_DATA_cached].sectors += new->cached_sectors; u->d[BCH_DATA_cached].sectors -= old->cached_sectors; u->d[old->data_type].fragmented -= bch2_bucket_sectors_fragmented(ca, *old); u->d[new->data_type].fragmented += bch2_bucket_sectors_fragmented(ca, *new); preempt_enable(); } static inline int __update_replicas(struct bch_fs *c, struct bch_fs_usage *fs_usage, struct bch_replicas_entry_v1 *r, s64 sectors) { int idx = bch2_replicas_entry_idx(c, r); if (idx < 0) return -1; fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors); fs_usage->replicas[idx] += sectors; return 0; } int bch2_update_replicas(struct bch_fs *c, struct bkey_s_c k, struct bch_replicas_entry_v1 *r, s64 sectors, unsigned journal_seq, bool gc) { struct bch_fs_usage *fs_usage; int idx, ret = 0; struct printbuf buf = PRINTBUF; percpu_down_read(&c->mark_lock); idx = bch2_replicas_entry_idx(c, r); if (idx < 0 && fsck_err(c, ptr_to_missing_replicas_entry, "no replicas entry\n while marking %s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { percpu_up_read(&c->mark_lock); ret = bch2_mark_replicas(c, r); percpu_down_read(&c->mark_lock); if (ret) goto err; idx = bch2_replicas_entry_idx(c, r); } if (idx < 0) { ret = -1; goto err; } preempt_disable(); fs_usage = fs_usage_ptr(c, journal_seq, gc); fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors); fs_usage->replicas[idx] += sectors; preempt_enable(); err: fsck_err: percpu_up_read(&c->mark_lock); printbuf_exit(&buf); return ret; } static inline int update_cached_sectors(struct bch_fs *c, struct bkey_s_c k, unsigned dev, s64 sectors, unsigned journal_seq, bool gc) { struct bch_replicas_padded r; bch2_replicas_entry_cached(&r.e, dev); return bch2_update_replicas(c, k, &r.e, sectors, journal_seq, gc); } static int __replicas_deltas_realloc(struct btree_trans *trans, unsigned more, gfp_t gfp) { struct replicas_delta_list *d = trans->fs_usage_deltas; unsigned new_size = d ? (d->size + more) * 2 : 128; unsigned alloc_size = sizeof(*d) + new_size; WARN_ON_ONCE(alloc_size > REPLICAS_DELTA_LIST_MAX); if (!d || d->used + more > d->size) { d = krealloc(d, alloc_size, gfp|__GFP_ZERO); if (unlikely(!d)) { if (alloc_size > REPLICAS_DELTA_LIST_MAX) return -ENOMEM; d = mempool_alloc(&trans->c->replicas_delta_pool, gfp); if (!d) return -ENOMEM; memset(d, 0, REPLICAS_DELTA_LIST_MAX); if (trans->fs_usage_deltas) memcpy(d, trans->fs_usage_deltas, trans->fs_usage_deltas->size + sizeof(*d)); new_size = REPLICAS_DELTA_LIST_MAX - sizeof(*d); kfree(trans->fs_usage_deltas); } d->size = new_size; trans->fs_usage_deltas = d; } return 0; } int bch2_replicas_deltas_realloc(struct btree_trans *trans, unsigned more) { return allocate_dropping_locks_errcode(trans, __replicas_deltas_realloc(trans, more, _gfp)); } int bch2_update_replicas_list(struct btree_trans *trans, struct bch_replicas_entry_v1 *r, s64 sectors) { struct replicas_delta_list *d; struct replicas_delta *n; unsigned b; int ret; if (!sectors) return 0; b = replicas_entry_bytes(r) + 8; ret = bch2_replicas_deltas_realloc(trans, b); if (ret) return ret; d = trans->fs_usage_deltas; n = (void *) d->d + d->used; n->delta = sectors; unsafe_memcpy((void *) n + offsetof(struct replicas_delta, r), r, replicas_entry_bytes(r), "flexible array member embedded in strcuct with padding"); bch2_replicas_entry_sort(&n->r); d->used += b; return 0; } int bch2_update_cached_sectors_list(struct btree_trans *trans, unsigned dev, s64 sectors) { struct bch_replicas_padded r; bch2_replicas_entry_cached(&r.e, dev); return bch2_update_replicas_list(trans, &r.e, sectors); } static int bch2_check_fix_ptr(struct btree_trans *trans, struct bkey_s_c k, struct extent_ptr_decoded p, const union bch_extent_entry *entry, bool *do_update) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (!ca) { if (fsck_err(c, ptr_to_invalid_device, "pointer to missing device %u\n" "while marking %s", p.ptr.dev, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; return 0; } struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); if (!g) { if (fsck_err(c, ptr_to_invalid_device, "pointer to invalid bucket on device %u\n" "while marking %s", p.ptr.dev, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; goto out; } enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry); if (fsck_err_on(!g->gen_valid, c, ptr_to_missing_alloc_key, "bucket %u:%zu data type %s ptr gen %u missing in alloc btree\n" "while marking %s", p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), p.ptr.gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { if (!p.ptr.cached) { g->gen_valid = true; g->gen = p.ptr.gen; } else { *do_update = true; } } if (fsck_err_on(gen_cmp(p.ptr.gen, g->gen) > 0, c, ptr_gen_newer_than_bucket_gen, "bucket %u:%zu data type %s ptr gen in the future: %u > %u\n" "while marking %s", p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), p.ptr.gen, g->gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { if (!p.ptr.cached && (g->data_type != BCH_DATA_btree || data_type == BCH_DATA_btree)) { g->gen_valid = true; g->gen = p.ptr.gen; g->data_type = 0; g->dirty_sectors = 0; g->cached_sectors = 0; } else { *do_update = true; } } if (fsck_err_on(gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX, c, ptr_gen_newer_than_bucket_gen, "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" "while marking %s", p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), p.ptr.gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; if (fsck_err_on(!p.ptr.cached && gen_cmp(p.ptr.gen, g->gen) < 0, c, stale_dirty_ptr, "bucket %u:%zu data type %s stale dirty ptr: %u < %u\n" "while marking %s", p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), p.ptr.gen, g->gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; if (data_type != BCH_DATA_btree && p.ptr.gen != g->gen) goto out; if (fsck_err_on(bucket_data_type_mismatch(g->data_type, data_type), c, ptr_bucket_data_type_mismatch, "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, bch2_data_type_str(g->data_type), bch2_data_type_str(data_type), (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { if (data_type == BCH_DATA_btree) { g->gen_valid = true; g->gen = p.ptr.gen; g->data_type = data_type; g->dirty_sectors = 0; g->cached_sectors = 0; } else { *do_update = true; } } if (p.has_ec) { struct gc_stripe *m = genradix_ptr(&c->gc_stripes, p.ec.idx); if (fsck_err_on(!m || !m->alive, c, ptr_to_missing_stripe, "pointer to nonexistent stripe %llu\n" "while marking %s", (u64) p.ec.idx, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; if (fsck_err_on(m && m->alive && !bch2_ptr_matches_stripe_m(m, p), c, ptr_to_incorrect_stripe, "pointer does not match stripe %llu\n" "while marking %s", (u64) p.ec.idx, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) *do_update = true; } out: fsck_err: bch2_dev_put(ca); printbuf_exit(&buf); return ret; } int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c k, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; struct bkey_ptrs_c ptrs_c = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry_c; struct extent_ptr_decoded p = { 0 }; bool do_update = false; struct printbuf buf = PRINTBUF; int ret = 0; percpu_down_read(&c->mark_lock); bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { ret = bch2_check_fix_ptr(trans, k, p, entry_c, &do_update); if (ret) goto err; } if (do_update) { if (flags & BTREE_TRIGGER_is_root) { bch_err(c, "cannot update btree roots yet"); ret = -EINVAL; goto err; } struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); ret = PTR_ERR_OR_ZERO(new); if (ret) goto err; rcu_read_lock(); bch2_bkey_drop_ptrs(bkey_i_to_s(new), ptr, !bch2_dev_rcu(c, ptr->dev)); rcu_read_unlock(); if (level) { /* * We don't want to drop btree node pointers - if the * btree node isn't there anymore, the read path will * sort it out: */ struct bkey_ptrs ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); rcu_read_lock(); bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); struct bucket *g = PTR_GC_BUCKET(ca, ptr); ptr->gen = g->gen; } rcu_read_unlock(); } else { struct bkey_ptrs ptrs; union bch_extent_entry *entry; rcu_read_lock(); restart_drop_ptrs: ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); bkey_for_each_ptr_decode(bkey_i_to_s(new).k, ptrs, p, entry) { struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); enum bch_data_type data_type = bch2_bkey_ptr_data_type(bkey_i_to_s_c(new), p, entry); if ((p.ptr.cached && (!g->gen_valid || gen_cmp(p.ptr.gen, g->gen) > 0)) || (!p.ptr.cached && gen_cmp(p.ptr.gen, g->gen) < 0) || gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX || (g->data_type && g->data_type != data_type)) { bch2_bkey_drop_ptr(bkey_i_to_s(new), &entry->ptr); goto restart_drop_ptrs; } } rcu_read_unlock(); again: ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); bkey_extent_entry_for_each(ptrs, entry) { if (extent_entry_type(entry) == BCH_EXTENT_ENTRY_stripe_ptr) { struct gc_stripe *m = genradix_ptr(&c->gc_stripes, entry->stripe_ptr.idx); union bch_extent_entry *next_ptr; bkey_extent_entry_for_each_from(ptrs, next_ptr, entry) if (extent_entry_type(next_ptr) == BCH_EXTENT_ENTRY_ptr) goto found; next_ptr = NULL; found: if (!next_ptr) { bch_err(c, "aieee, found stripe ptr with no data ptr"); continue; } if (!m || !m->alive || !__bch2_ptr_matches_stripe(&m->ptrs[entry->stripe_ptr.block], &next_ptr->ptr, m->sectors)) { bch2_bkey_extent_entry_drop(new, entry); goto again; } } } } if (0) { printbuf_reset(&buf); bch2_bkey_val_to_text(&buf, c, k); bch_info(c, "updated %s", buf.buf); printbuf_reset(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(new)); bch_info(c, "new key %s", buf.buf); } percpu_up_read(&c->mark_lock); struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, new->k.p, 0, level, BTREE_ITER_intent|BTREE_ITER_all_snapshots); ret = bch2_btree_iter_traverse(&iter) ?: bch2_trans_update(trans, &iter, new, BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun); bch2_trans_iter_exit(trans, &iter); percpu_down_read(&c->mark_lock); if (ret) goto err; if (level) bch2_btree_node_update_key_early(trans, btree, level - 1, k, new); } err: percpu_up_read(&c->mark_lock); printbuf_exit(&buf); return ret; } int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, const struct bch_extent_ptr *ptr, s64 sectors, enum bch_data_type ptr_data_type, u8 b_gen, u8 bucket_data_type, u32 *bucket_sectors) { struct bch_fs *c = trans->c; size_t bucket_nr = PTR_BUCKET_NR(ca, ptr); struct printbuf buf = PRINTBUF; bool inserting = sectors > 0; int ret = 0; BUG_ON(!sectors); if (gen_after(ptr->gen, b_gen)) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_ptr_gen_newer_than_bucket_gen, "bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n" "while marking %s", ptr->dev, bucket_nr, b_gen, bch2_data_type_str(bucket_data_type ?: ptr_data_type), ptr->gen, (bch2_bkey_val_to_text(&buf, c, k), buf.buf)); if (inserting) goto err; goto out; } if (gen_cmp(b_gen, ptr->gen) > BUCKET_GC_GEN_MAX) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_ptr_too_stale, "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" "while marking %s", ptr->dev, bucket_nr, b_gen, bch2_data_type_str(bucket_data_type ?: ptr_data_type), ptr->gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); if (inserting) goto err; goto out; } if (b_gen != ptr->gen && ptr->cached) { ret = 1; goto out; } if (b_gen != ptr->gen) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_stale_dirty_ptr, "bucket %u:%zu gen %u (mem gen %u) data type %s: stale dirty ptr (gen %u)\n" "while marking %s", ptr->dev, bucket_nr, b_gen, *bucket_gen(ca, bucket_nr), bch2_data_type_str(bucket_data_type ?: ptr_data_type), ptr->gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); if (inserting) goto err; goto out; } if (bucket_data_type_mismatch(bucket_data_type, ptr_data_type)) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_ptr_bucket_data_type_mismatch, "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", ptr->dev, bucket_nr, b_gen, bch2_data_type_str(bucket_data_type), bch2_data_type_str(ptr_data_type), (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); if (inserting) goto err; goto out; } if ((u64) *bucket_sectors + sectors > U32_MAX) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_bucket_sector_count_overflow, "bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n" "while marking %s", ptr->dev, bucket_nr, b_gen, bch2_data_type_str(bucket_data_type ?: ptr_data_type), *bucket_sectors, sectors, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); if (inserting) goto err; sectors = -*bucket_sectors; } *bucket_sectors += sectors; out: printbuf_exit(&buf); return ret; err: bch2_dump_trans_updates(trans); ret = -EIO; goto out; } void bch2_trans_fs_usage_revert(struct btree_trans *trans, struct replicas_delta_list *deltas) { struct bch_fs *c = trans->c; struct bch_fs_usage *dst; struct replicas_delta *d, *top = (void *) deltas->d + deltas->used; s64 added = 0; unsigned i; percpu_down_read(&c->mark_lock); preempt_disable(); dst = fs_usage_ptr(c, trans->journal_res.seq, false); /* revert changes: */ for (d = deltas->d; d != top; d = replicas_delta_next(d)) { switch (d->r.data_type) { case BCH_DATA_btree: case BCH_DATA_user: case BCH_DATA_parity: added += d->delta; } BUG_ON(__update_replicas(c, dst, &d->r, -d->delta)); } dst->b.nr_inodes -= deltas->nr_inodes; for (i = 0; i < BCH_REPLICAS_MAX; i++) { added -= deltas->persistent_reserved[i]; dst->b.reserved -= deltas->persistent_reserved[i]; dst->persistent_reserved[i] -= deltas->persistent_reserved[i]; } if (added > 0) { trans->disk_res->sectors += added; this_cpu_add(*c->online_reserved, added); } preempt_enable(); percpu_up_read(&c->mark_lock); } void bch2_trans_account_disk_usage_change(struct btree_trans *trans) { struct bch_fs *c = trans->c; u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0; static int warned_disk_usage = 0; bool warn = false; percpu_down_read(&c->mark_lock); preempt_disable(); struct bch_fs_usage_base *dst = &fs_usage_ptr(c, trans->journal_res.seq, false)->b; struct bch_fs_usage_base *src = &trans->fs_usage_delta; s64 added = src->btree + src->data + src->reserved; /* * Not allowed to reduce sectors_available except by getting a * reservation: */ s64 should_not_have_added = added - (s64) disk_res_sectors; if (unlikely(should_not_have_added > 0)) { u64 old, new, v = atomic64_read(&c->sectors_available); do { old = v; new = max_t(s64, 0, old - should_not_have_added); } while ((v = atomic64_cmpxchg(&c->sectors_available, old, new)) != old); added -= should_not_have_added; warn = true; } if (added > 0) { trans->disk_res->sectors -= added; this_cpu_sub(*c->online_reserved, added); } dst->hidden += src->hidden; dst->btree += src->btree; dst->data += src->data; dst->cached += src->cached; dst->reserved += src->reserved; dst->nr_inodes += src->nr_inodes; preempt_enable(); percpu_up_read(&c->mark_lock); if (unlikely(warn) && !xchg(&warned_disk_usage, 1)) bch2_trans_inconsistent(trans, "disk usage increased %lli more than %llu sectors reserved)", should_not_have_added, disk_res_sectors); } int bch2_trans_fs_usage_apply(struct btree_trans *trans, struct replicas_delta_list *deltas) { struct bch_fs *c = trans->c; struct replicas_delta *d, *d2; struct replicas_delta *top = (void *) deltas->d + deltas->used; struct bch_fs_usage *dst; unsigned i; percpu_down_read(&c->mark_lock); preempt_disable(); dst = fs_usage_ptr(c, trans->journal_res.seq, false); for (d = deltas->d; d != top; d = replicas_delta_next(d)) if (__update_replicas(c, dst, &d->r, d->delta)) goto need_mark; dst->b.nr_inodes += deltas->nr_inodes; for (i = 0; i < BCH_REPLICAS_MAX; i++) { dst->b.reserved += deltas->persistent_reserved[i]; dst->persistent_reserved[i] += deltas->persistent_reserved[i]; } preempt_enable(); percpu_up_read(&c->mark_lock); return 0; need_mark: /* revert changes: */ for (d2 = deltas->d; d2 != d; d2 = replicas_delta_next(d2)) BUG_ON(__update_replicas(c, dst, &d2->r, -d2->delta)); preempt_enable(); percpu_up_read(&c->mark_lock); return -1; } /* KEY_TYPE_extent: */ static int __mark_pointer(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, const struct bch_extent_ptr *ptr, s64 sectors, enum bch_data_type ptr_data_type, struct bch_alloc_v4 *a) { u32 *dst_sectors = !ptr->cached ? &a->dirty_sectors : &a->cached_sectors; int ret = bch2_bucket_ref_update(trans, ca, k, ptr, sectors, ptr_data_type, a->gen, a->data_type, dst_sectors); if (ret) return ret; alloc_data_type_set(a, ptr_data_type); return 0; } static int bch2_trigger_pointer(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c k, struct extent_ptr_decoded p, const union bch_extent_entry *entry, s64 *sectors, enum btree_iter_update_trigger_flags flags) { bool insert = !(flags & BTREE_TRIGGER_overwrite); struct printbuf buf = PRINTBUF; int ret = 0; struct bch_fs *c = trans->c; struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (unlikely(!ca)) { if (insert) ret = -EIO; goto err; } struct bpos bucket; struct bch_backpointer bp; bch2_extent_ptr_to_bp(trans->c, ca, btree_id, level, k, p, entry, &bucket, &bp); *sectors = insert ? bp.bucket_len : -((s64) bp.bucket_len); if (flags & BTREE_TRIGGER_transactional) { struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, bucket); ret = PTR_ERR_OR_ZERO(a) ?: __mark_pointer(trans, ca, k, &p.ptr, *sectors, bp.data_type, &a->v); if (ret) goto err; if (!p.ptr.cached) { ret = bch2_bucket_backpointer_mod(trans, ca, bucket, bp, k, insert); if (ret) goto err; } } if (flags & BTREE_TRIGGER_gc) { percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", p.ptr.dev, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = -EIO; goto err_unlock; } bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g), new = old; ret = __mark_pointer(trans, ca, k, &p.ptr, *sectors, bp.data_type, &new); if (!ret) { alloc_to_bucket(g, new); bch2_dev_usage_update(c, ca, &old, &new, 0, true); } bucket_unlock(g); err_unlock: percpu_up_read(&c->mark_lock); } err: bch2_dev_put(ca); printbuf_exit(&buf); return ret; } static int bch2_trigger_stripe_ptr(struct btree_trans *trans, struct bkey_s_c k, struct extent_ptr_decoded p, enum bch_data_type data_type, s64 sectors, enum btree_iter_update_trigger_flags flags) { if (flags & BTREE_TRIGGER_transactional) { struct btree_iter iter; struct bkey_i_stripe *s = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_stripes, POS(0, p.ec.idx), BTREE_ITER_with_updates, stripe); int ret = PTR_ERR_OR_ZERO(s); if (unlikely(ret)) { bch2_trans_inconsistent_on(bch2_err_matches(ret, ENOENT), trans, "pointer to nonexistent stripe %llu", (u64) p.ec.idx); goto err; } if (!bch2_ptr_matches_stripe(&s->v, p)) { bch2_trans_inconsistent(trans, "stripe pointer doesn't match stripe %llu", (u64) p.ec.idx); ret = -EIO; goto err; } stripe_blockcount_set(&s->v, p.ec.block, stripe_blockcount_get(&s->v, p.ec.block) + sectors); struct bch_replicas_padded r; bch2_bkey_to_replicas(&r.e, bkey_i_to_s_c(&s->k_i)); r.e.data_type = data_type; ret = bch2_update_replicas_list(trans, &r.e, sectors); err: bch2_trans_iter_exit(trans, &iter); return ret; } if (flags & BTREE_TRIGGER_gc) { struct bch_fs *c = trans->c; BUG_ON(!(flags & BTREE_TRIGGER_gc)); struct gc_stripe *m = genradix_ptr_alloc(&c->gc_stripes, p.ec.idx, GFP_KERNEL); if (!m) { bch_err(c, "error allocating memory for gc_stripes, idx %llu", (u64) p.ec.idx); return -BCH_ERR_ENOMEM_mark_stripe_ptr; } mutex_lock(&c->ec_stripes_heap_lock); if (!m || !m->alive) { mutex_unlock(&c->ec_stripes_heap_lock); struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); bch_err_ratelimited(c, "pointer to nonexistent stripe %llu\n while marking %s", (u64) p.ec.idx, buf.buf); printbuf_exit(&buf); bch2_inconsistent_error(c); return -EIO; } m->block_sectors[p.ec.block] += sectors; struct bch_replicas_padded r = m->r; mutex_unlock(&c->ec_stripes_heap_lock); r.e.data_type = data_type; bch2_update_replicas(c, k, &r.e, sectors, trans->journal_res.seq, true); } return 0; } static int __trigger_extent(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c k, enum btree_iter_update_trigger_flags flags) { bool gc = flags & BTREE_TRIGGER_gc; struct bch_fs *c = trans->c; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; struct bch_replicas_padded r; enum bch_data_type data_type = bkey_is_btree_ptr(k.k) ? BCH_DATA_btree : BCH_DATA_user; s64 replicas_sectors = 0; int ret = 0; r.e.data_type = data_type; r.e.nr_devs = 0; r.e.nr_required = 1; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { s64 disk_sectors = 0; ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags); if (ret < 0) return ret; bool stale = ret > 0; if (p.ptr.cached) { if (!stale) { ret = !gc ? bch2_update_cached_sectors_list(trans, p.ptr.dev, disk_sectors) : update_cached_sectors(c, k, p.ptr.dev, disk_sectors, 0, true); bch2_fs_fatal_err_on(ret && gc, c, "%s: no replicas entry while updating cached sectors", bch2_err_str(ret)); if (ret) return ret; } } else if (!p.has_ec) { replicas_sectors += disk_sectors; r.e.devs[r.e.nr_devs++] = p.ptr.dev; } else { ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags); if (ret) return ret; /* * There may be other dirty pointers in this extent, but * if so they're not required for mounting if we have an * erasure coded pointer in this extent: */ r.e.nr_required = 0; } } if (r.e.nr_devs) { ret = !gc ? bch2_update_replicas_list(trans, &r.e, replicas_sectors) : bch2_update_replicas(c, k, &r.e, replicas_sectors, 0, true); if (unlikely(ret && gc)) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); bch2_fs_fatal_error(c, ": no replicas entry for %s", buf.buf); printbuf_exit(&buf); } if (ret) return ret; } return 0; } int bch2_trigger_extent(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { struct bkey_ptrs_c new_ptrs = bch2_bkey_ptrs_c(new.s_c); struct bkey_ptrs_c old_ptrs = bch2_bkey_ptrs_c(old); unsigned new_ptrs_bytes = (void *) new_ptrs.end - (void *) new_ptrs.start; unsigned old_ptrs_bytes = (void *) old_ptrs.end - (void *) old_ptrs.start; if (unlikely(flags & BTREE_TRIGGER_check_repair)) return bch2_check_fix_ptrs(trans, btree, level, new.s_c, flags); /* if pointers aren't changing - nothing to do: */ if (new_ptrs_bytes == old_ptrs_bytes && !memcmp(new_ptrs.start, old_ptrs.start, new_ptrs_bytes)) return 0; if (flags & BTREE_TRIGGER_transactional) { struct bch_fs *c = trans->c; int mod = (int) bch2_bkey_needs_rebalance(c, new.s_c) - (int) bch2_bkey_needs_rebalance(c, old); if (mod) { int ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_rebalance_work, new.k->p, mod > 0); if (ret) return ret; } } if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) return trigger_run_overwrite_then_insert(__trigger_extent, trans, btree, level, old, new, flags); return 0; } /* KEY_TYPE_reservation */ static int __trigger_reservation(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c k, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; unsigned replicas = bkey_s_c_to_reservation(k).v->nr_replicas; s64 sectors = (s64) k.k->size * replicas; if (flags & BTREE_TRIGGER_overwrite) sectors = -sectors; if (flags & BTREE_TRIGGER_transactional) { int ret = bch2_replicas_deltas_realloc(trans, 0); if (ret) return ret; struct replicas_delta_list *d = trans->fs_usage_deltas; replicas = min(replicas, ARRAY_SIZE(d->persistent_reserved)); d->persistent_reserved[replicas - 1] += sectors; } if (flags & BTREE_TRIGGER_gc) { percpu_down_read(&c->mark_lock); preempt_disable(); struct bch_fs_usage *fs_usage = this_cpu_ptr(c->usage_gc); replicas = min(replicas, ARRAY_SIZE(fs_usage->persistent_reserved)); fs_usage->b.reserved += sectors; fs_usage->persistent_reserved[replicas - 1] += sectors; preempt_enable(); percpu_up_read(&c->mark_lock); } return 0; } int bch2_trigger_reservation(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { return trigger_run_overwrite_then_insert(__trigger_reservation, trans, btree_id, level, old, new, flags); } /* Mark superblocks: */ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev *ca, u64 b, enum bch_data_type type, unsigned sectors) { struct bch_fs *c = trans->c; struct btree_iter iter; int ret = 0; struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update_noupdate(trans, &iter, POS(ca->dev_idx, b)); if (IS_ERR(a)) return PTR_ERR(a); if (a->v.data_type && type && a->v.data_type != type) { bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, BCH_FSCK_ERR_bucket_metadata_type_mismatch, "bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", iter.pos.inode, iter.pos.offset, a->v.gen, bch2_data_type_str(a->v.data_type), bch2_data_type_str(type), bch2_data_type_str(type)); ret = -EIO; goto err; } if (a->v.data_type != type || a->v.dirty_sectors != sectors) { a->v.data_type = type; a->v.dirty_sectors = sectors; ret = bch2_trans_update(trans, &iter, &a->k_i, 0); } err: bch2_trans_iter_exit(trans, &iter); return ret; } static int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, u64 b, enum bch_data_type data_type, unsigned sectors, enum btree_iter_update_trigger_flags flags) { percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, b); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u when marking metadata type %s", ca->dev_idx, bch2_data_type_str(data_type))) goto err_unlock; bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g); if (bch2_fs_inconsistent_on(g->data_type && g->data_type != data_type, c, "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), bch2_data_type_str(data_type))) goto err; if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c, "bucket %u:%llu gen %u data type %s sector count overflow: %u + %u > bucket size", ca->dev_idx, b, g->gen, bch2_data_type_str(g->data_type ?: data_type), g->dirty_sectors, sectors)) goto err; g->data_type = data_type; g->dirty_sectors += sectors; struct bch_alloc_v4 new = bucket_m_to_alloc(*g); bch2_dev_usage_update(c, ca, &old, &new, 0, true); percpu_up_read(&c->mark_lock); return 0; err: bucket_unlock(g); err_unlock: percpu_up_read(&c->mark_lock); return -EIO; } int bch2_trans_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev *ca, u64 b, enum bch_data_type type, unsigned sectors, enum btree_iter_update_trigger_flags flags) { BUG_ON(type != BCH_DATA_free && type != BCH_DATA_sb && type != BCH_DATA_journal); /* * Backup superblock might be past the end of our normal usable space: */ if (b >= ca->mi.nbuckets) return 0; if (flags & BTREE_TRIGGER_gc) return bch2_mark_metadata_bucket(trans->c, ca, b, type, sectors, flags); else if (flags & BTREE_TRIGGER_transactional) return commit_do(trans, NULL, NULL, 0, __bch2_trans_mark_metadata_bucket(trans, ca, b, type, sectors)); else BUG(); } static int bch2_trans_mark_metadata_sectors(struct btree_trans *trans, struct bch_dev *ca, u64 start, u64 end, enum bch_data_type type, u64 *bucket, unsigned *bucket_sectors, enum btree_iter_update_trigger_flags flags) { do { u64 b = sector_to_bucket(ca, start); unsigned sectors = min_t(u64, bucket_to_sector(ca, b + 1), end) - start; if (b != *bucket && *bucket_sectors) { int ret = bch2_trans_mark_metadata_bucket(trans, ca, *bucket, type, *bucket_sectors, flags); if (ret) return ret; *bucket_sectors = 0; } *bucket = b; *bucket_sectors += sectors; start += sectors; } while (start < end); return 0; } static int __bch2_trans_mark_dev_sb(struct btree_trans *trans, struct bch_dev *ca, enum btree_iter_update_trigger_flags flags) { struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; u64 bucket = 0; unsigned i, bucket_sectors = 0; int ret; for (i = 0; i < layout->nr_superblocks; i++) { u64 offset = le64_to_cpu(layout->sb_offset[i]); if (offset == BCH_SB_SECTOR) { ret = bch2_trans_mark_metadata_sectors(trans, ca, 0, BCH_SB_SECTOR, BCH_DATA_sb, &bucket, &bucket_sectors, flags); if (ret) return ret; } ret = bch2_trans_mark_metadata_sectors(trans, ca, offset, offset + (1 << layout->sb_max_size_bits), BCH_DATA_sb, &bucket, &bucket_sectors, flags); if (ret) return ret; } if (bucket_sectors) { ret = bch2_trans_mark_metadata_bucket(trans, ca, bucket, BCH_DATA_sb, bucket_sectors, flags); if (ret) return ret; } for (i = 0; i < ca->journal.nr; i++) { ret = bch2_trans_mark_metadata_bucket(trans, ca, ca->journal.buckets[i], BCH_DATA_journal, ca->mi.bucket_size, flags); if (ret) return ret; } return 0; } int bch2_trans_mark_dev_sb(struct bch_fs *c, struct bch_dev *ca, enum btree_iter_update_trigger_flags flags) { int ret = bch2_trans_run(c, __bch2_trans_mark_dev_sb(trans, ca, flags)); bch_err_fn(c, ret); return ret; } int bch2_trans_mark_dev_sbs_flags(struct bch_fs *c, enum btree_iter_update_trigger_flags flags) { for_each_online_member(c, ca) { int ret = bch2_trans_mark_dev_sb(c, ca, flags); if (ret) { percpu_ref_put(&ca->io_ref); return ret; } } return 0; } int bch2_trans_mark_dev_sbs(struct bch_fs *c) { return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_transactional); } /* Disk reservations: */ #define SECTORS_CACHE 1024 int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res, u64 sectors, int flags) { struct bch_fs_pcpu *pcpu; u64 old, v, get; s64 sectors_available; int ret; percpu_down_read(&c->mark_lock); preempt_disable(); pcpu = this_cpu_ptr(c->pcpu); if (sectors <= pcpu->sectors_available) goto out; v = atomic64_read(&c->sectors_available); do { old = v; get = min((u64) sectors + SECTORS_CACHE, old); if (get < sectors) { preempt_enable(); goto recalculate; } } while ((v = atomic64_cmpxchg(&c->sectors_available, old, old - get)) != old); pcpu->sectors_available += get; out: pcpu->sectors_available -= sectors; this_cpu_add(*c->online_reserved, sectors); res->sectors += sectors; preempt_enable(); percpu_up_read(&c->mark_lock); return 0; recalculate: mutex_lock(&c->sectors_available_lock); percpu_u64_set(&c->pcpu->sectors_available, 0); sectors_available = avail_factor(__bch2_fs_usage_read_short(c).free); if (sectors <= sectors_available || (flags & BCH_DISK_RESERVATION_NOFAIL)) { atomic64_set(&c->sectors_available, max_t(s64, 0, sectors_available - sectors)); this_cpu_add(*c->online_reserved, sectors); res->sectors += sectors; ret = 0; } else { atomic64_set(&c->sectors_available, sectors_available); ret = -BCH_ERR_ENOSPC_disk_reservation; } mutex_unlock(&c->sectors_available_lock); percpu_up_read(&c->mark_lock); return ret; } /* Startup/shutdown: */ void bch2_buckets_nouse_free(struct bch_fs *c) { for_each_member_device(c, ca) { kvfree_rcu_mightsleep(ca->buckets_nouse); ca->buckets_nouse = NULL; } } int bch2_buckets_nouse_alloc(struct bch_fs *c) { for_each_member_device(c, ca) { BUG_ON(ca->buckets_nouse); ca->buckets_nouse = kvmalloc(BITS_TO_LONGS(ca->mi.nbuckets) * sizeof(unsigned long), GFP_KERNEL|__GFP_ZERO); if (!ca->buckets_nouse) { bch2_dev_put(ca); return -BCH_ERR_ENOMEM_buckets_nouse; } } return 0; } static void bucket_gens_free_rcu(struct rcu_head *rcu) { struct bucket_gens *buckets = container_of(rcu, struct bucket_gens, rcu); kvfree(buckets); } int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) { struct bucket_gens *bucket_gens = NULL, *old_bucket_gens = NULL; bool resize = ca->bucket_gens != NULL; int ret; BUG_ON(resize && ca->buckets_nouse); if (!(bucket_gens = kvmalloc(sizeof(struct bucket_gens) + nbuckets, GFP_KERNEL|__GFP_ZERO))) { ret = -BCH_ERR_ENOMEM_bucket_gens; goto err; } bucket_gens->first_bucket = ca->mi.first_bucket; bucket_gens->nbuckets = nbuckets; bucket_gens->nbuckets_minus_first = bucket_gens->nbuckets - bucket_gens->first_bucket; if (resize) { down_write(&c->gc_lock); down_write(&ca->bucket_lock); percpu_down_write(&c->mark_lock); } old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1); if (resize) { size_t n = min(bucket_gens->nbuckets, old_bucket_gens->nbuckets); memcpy(bucket_gens->b, old_bucket_gens->b, n); } rcu_assign_pointer(ca->bucket_gens, bucket_gens); bucket_gens = old_bucket_gens; nbuckets = ca->mi.nbuckets; if (resize) { percpu_up_write(&c->mark_lock); up_write(&ca->bucket_lock); up_write(&c->gc_lock); } ret = 0; err: if (bucket_gens) call_rcu(&bucket_gens->rcu, bucket_gens_free_rcu); return ret; } void bch2_dev_buckets_free(struct bch_dev *ca) { kvfree(ca->buckets_nouse); kvfree(rcu_dereference_protected(ca->bucket_gens, 1)); for (unsigned i = 0; i < ARRAY_SIZE(ca->usage); i++) free_percpu(ca->usage[i]); kfree(ca->usage_base); } int bch2_dev_buckets_alloc(struct bch_fs *c, struct bch_dev *ca) { ca->usage_base = kzalloc(sizeof(struct bch_dev_usage), GFP_KERNEL); if (!ca->usage_base) return -BCH_ERR_ENOMEM_usage_init; for (unsigned i = 0; i < ARRAY_SIZE(ca->usage); i++) { ca->usage[i] = alloc_percpu(struct bch_dev_usage); if (!ca->usage[i]) return -BCH_ERR_ENOMEM_usage_init; } return bch2_dev_buckets_resize(c, ca, ca->mi.nbuckets); } |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/sched.c * * Scheduling for synchronous and asynchronous RPC requests. * * Copyright (C) 1996 Olaf Kirch, <okir@monad.swb.de> * * TCP NFS related read + write fixes * (C) 1999 Dave Airlie, University of Limerick, Ireland <airlied@linux.ie> */ #include <linux/module.h> #include <linux/sched.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/mempool.h> #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/freezer.h> #include <linux/sched/mm.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/metrics.h> #include "sunrpc.h" #define CREATE_TRACE_POINTS #include <trace/events/sunrpc.h> /* * RPC slabs and memory pools */ #define RPC_BUFFER_MAXSIZE (2048) #define RPC_BUFFER_POOLSIZE (8) #define RPC_TASK_POOLSIZE (8) static struct kmem_cache *rpc_task_slabp __read_mostly; static struct kmem_cache *rpc_buffer_slabp __read_mostly; static mempool_t *rpc_task_mempool __read_mostly; static mempool_t *rpc_buffer_mempool __read_mostly; static void rpc_async_schedule(struct work_struct *); static void rpc_release_task(struct rpc_task *task); static void __rpc_queue_timer_fn(struct work_struct *); /* * RPC tasks sit here while waiting for conditions to improve. */ static struct rpc_wait_queue delay_queue; /* * rpciod-related stuff */ struct workqueue_struct *rpciod_workqueue __read_mostly; struct workqueue_struct *xprtiod_workqueue __read_mostly; EXPORT_SYMBOL_GPL(xprtiod_workqueue); gfp_t rpc_task_gfp_mask(void) { if (current->flags & PF_WQ_WORKER) return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; return GFP_KERNEL; } EXPORT_SYMBOL_GPL(rpc_task_gfp_mask); bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status) { if (cmpxchg(&task->tk_rpc_status, 0, rpc_status) == 0) return true; return false; } unsigned long rpc_task_timeout(const struct rpc_task *task) { unsigned long timeout = READ_ONCE(task->tk_timeout); if (timeout != 0) { unsigned long now = jiffies; if (time_before(now, timeout)) return timeout - now; } return 0; } EXPORT_SYMBOL_GPL(rpc_task_timeout); /* * Disable the timer for a given RPC task. Should be called with * queue->lock and bh_disabled in order to avoid races within * rpc_run_timer(). */ static void __rpc_disable_timer(struct rpc_wait_queue *queue, struct rpc_task *task) { if (list_empty(&task->u.tk_wait.timer_list)) return; task->tk_timeout = 0; list_del(&task->u.tk_wait.timer_list); if (list_empty(&queue->timer_list.list)) cancel_delayed_work(&queue->timer_list.dwork); } static void rpc_set_queue_timer(struct rpc_wait_queue *queue, unsigned long expires) { unsigned long now = jiffies; queue->timer_list.expires = expires; if (time_before_eq(expires, now)) expires = 0; else expires -= now; mod_delayed_work(rpciod_workqueue, &queue->timer_list.dwork, expires); } /* * Set up a timer for the current task. */ static void __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned long timeout) { task->tk_timeout = timeout; if (list_empty(&queue->timer_list.list) || time_before(timeout, queue->timer_list.expires)) rpc_set_queue_timer(queue, timeout); list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list); } static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) { if (queue->priority != priority) { queue->priority = priority; queue->nr = 1U << priority; } } static void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue) { rpc_set_waitqueue_priority(queue, queue->maxpriority); } /* * Add a request to a queue list */ static void __rpc_list_enqueue_task(struct list_head *q, struct rpc_task *task) { struct rpc_task *t; list_for_each_entry(t, q, u.tk_wait.list) { if (t->tk_owner == task->tk_owner) { list_add_tail(&task->u.tk_wait.links, &t->u.tk_wait.links); /* Cache the queue head in task->u.tk_wait.list */ task->u.tk_wait.list.next = q; task->u.tk_wait.list.prev = NULL; return; } } INIT_LIST_HEAD(&task->u.tk_wait.links); list_add_tail(&task->u.tk_wait.list, q); } /* * Remove request from a queue list */ static void __rpc_list_dequeue_task(struct rpc_task *task) { struct list_head *q; struct rpc_task *t; if (task->u.tk_wait.list.prev == NULL) { list_del(&task->u.tk_wait.links); return; } if (!list_empty(&task->u.tk_wait.links)) { t = list_first_entry(&task->u.tk_wait.links, struct rpc_task, u.tk_wait.links); /* Assume __rpc_list_enqueue_task() cached the queue head */ q = t->u.tk_wait.list.next; list_add_tail(&t->u.tk_wait.list, q); list_del(&task->u.tk_wait.links); } list_del(&task->u.tk_wait.list); } /* * Add new request to a priority queue. */ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned char queue_priority) { if (unlikely(queue_priority > queue->maxpriority)) queue_priority = queue->maxpriority; __rpc_list_enqueue_task(&queue->tasks[queue_priority], task); } /* * Add new request to wait queue. */ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned char queue_priority) { INIT_LIST_HEAD(&task->u.tk_wait.timer_list); if (RPC_IS_PRIORITY(queue)) __rpc_add_wait_queue_priority(queue, task, queue_priority); else list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]); task->tk_waitqueue = queue; queue->qlen++; /* barrier matches the read in rpc_wake_up_task_queue_locked() */ smp_wmb(); rpc_set_queued(task); } /* * Remove request from a priority queue. */ static void __rpc_remove_wait_queue_priority(struct rpc_task *task) { __rpc_list_dequeue_task(task); } /* * Remove request from queue. * Note: must be called with spin lock held. */ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task) { __rpc_disable_timer(queue, task); if (RPC_IS_PRIORITY(queue)) __rpc_remove_wait_queue_priority(task); else list_del(&task->u.tk_wait.list); queue->qlen--; } static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues) { int i; spin_lock_init(&queue->lock); for (i = 0; i < ARRAY_SIZE(queue->tasks); i++) INIT_LIST_HEAD(&queue->tasks[i]); queue->maxpriority = nr_queues - 1; rpc_reset_waitqueue_priority(queue); queue->qlen = 0; queue->timer_list.expires = 0; INIT_DELAYED_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } void rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname) { __rpc_init_priority_wait_queue(queue, qname, RPC_NR_PRIORITY); } EXPORT_SYMBOL_GPL(rpc_init_priority_wait_queue); void rpc_init_wait_queue(struct rpc_wait_queue *queue, const char *qname) { __rpc_init_priority_wait_queue(queue, qname, 1); } EXPORT_SYMBOL_GPL(rpc_init_wait_queue); void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) { cancel_delayed_work_sync(&queue->timer_list.dwork); } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; /* Might be a task carrying a reverse-direction operation */ if (!clnt) { static atomic_t rpc_pid; task->tk_pid = atomic_inc_return(&rpc_pid); return; } task->tk_pid = atomic_inc_return(&clnt->cl_pid); } #else static inline void rpc_task_set_debuginfo(struct rpc_task *task) { } #endif static void rpc_set_active(struct rpc_task *task) { rpc_task_set_debuginfo(task); set_bit(RPC_TASK_ACTIVE, &task->tk_runstate); trace_rpc_task_begin(task, NULL); } /* * Mark an RPC call as having completed by clearing the 'active' bit * and then waking up all tasks that were sleeping. */ static int rpc_complete_task(struct rpc_task *task) { void *m = &task->tk_runstate; wait_queue_head_t *wq = bit_waitqueue(m, RPC_TASK_ACTIVE); struct wait_bit_key k = __WAIT_BIT_KEY_INITIALIZER(m, RPC_TASK_ACTIVE); unsigned long flags; int ret; trace_rpc_task_complete(task, NULL); spin_lock_irqsave(&wq->lock, flags); clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); ret = atomic_dec_and_test(&task->tk_count); if (waitqueue_active(wq)) __wake_up_locked_key(wq, TASK_NORMAL, &k); spin_unlock_irqrestore(&wq->lock, flags); return ret; } /* * Allow callers to wait for completion of an RPC call * * Note the use of out_of_line_wait_on_bit() rather than wait_on_bit() * to enforce taking of the wq->lock and hence avoid races with * rpc_complete_task(). */ int rpc_wait_for_completion_task(struct rpc_task *task) { return out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE, rpc_wait_bit_killable, TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); } EXPORT_SYMBOL_GPL(rpc_wait_for_completion_task); /* * Make an RPC task runnable. * * Note: If the task is ASYNC, and is being made runnable after sitting on an * rpc_wait_queue, this must be called with the queue spinlock held to protect * the wait queue operation. * Note the ordering of rpc_test_and_set_running() and rpc_clear_queued(), * which is needed to ensure that __rpc_execute() doesn't loop (due to the * lockless RPC_IS_QUEUED() test) before we've had a chance to test * the RPC_TASK_RUNNING flag. */ static void rpc_make_runnable(struct workqueue_struct *wq, struct rpc_task *task) { bool need_wakeup = !rpc_test_and_set_running(task); rpc_clear_queued(task); if (!need_wakeup) return; if (RPC_IS_ASYNC(task)) { INIT_WORK(&task->u.tk_work, rpc_async_schedule); queue_work(wq, &task->u.tk_work); } else wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED); } /* * Prepare for sleeping on a wait queue. * By always appending tasks to the list we ensure FIFO behavior. * NB: An RPC task will only receive interrupt-driven events as long * as it's on a wait queue. */ static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, unsigned char queue_priority) { trace_rpc_task_sleep(task, q); __rpc_add_wait_queue(q, task, queue_priority); } static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, unsigned char queue_priority) { if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) return; __rpc_do_sleep_on_priority(q, task, queue_priority); } static void __rpc_sleep_on_priority_timeout(struct rpc_wait_queue *q, struct rpc_task *task, unsigned long timeout, unsigned char queue_priority) { if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) return; if (time_is_after_jiffies(timeout)) { __rpc_do_sleep_on_priority(q, task, queue_priority); __rpc_add_timer(q, task, timeout); } else task->tk_status = -ETIMEDOUT; } static void rpc_set_tk_callback(struct rpc_task *task, rpc_action action) { if (action && !WARN_ON_ONCE(task->tk_callback != NULL)) task->tk_callback = action; } static bool rpc_sleep_check_activated(struct rpc_task *task) { /* We shouldn't ever put an inactive task to sleep */ if (WARN_ON_ONCE(!RPC_IS_ACTIVATED(task))) { task->tk_status = -EIO; rpc_put_task_async(task); return false; } return true; } void rpc_sleep_on_timeout(struct rpc_wait_queue *q, struct rpc_task *task, rpc_action action, unsigned long timeout) { if (!rpc_sleep_check_activated(task)) return; rpc_set_tk_callback(task, action); /* * Protect the queue operations. */ spin_lock(&q->lock); __rpc_sleep_on_priority_timeout(q, task, timeout, task->tk_priority); spin_unlock(&q->lock); } EXPORT_SYMBOL_GPL(rpc_sleep_on_timeout); void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task, rpc_action action) { if (!rpc_sleep_check_activated(task)) return; rpc_set_tk_callback(task, action); WARN_ON_ONCE(task->tk_timeout != 0); /* * Protect the queue operations. */ spin_lock(&q->lock); __rpc_sleep_on_priority(q, task, task->tk_priority); spin_unlock(&q->lock); } EXPORT_SYMBOL_GPL(rpc_sleep_on); void rpc_sleep_on_priority_timeout(struct rpc_wait_queue *q, struct rpc_task *task, unsigned long timeout, int priority) { if (!rpc_sleep_check_activated(task)) return; priority -= RPC_PRIORITY_LOW; /* * Protect the queue operations. */ spin_lock(&q->lock); __rpc_sleep_on_priority_timeout(q, task, timeout, priority); spin_unlock(&q->lock); } EXPORT_SYMBOL_GPL(rpc_sleep_on_priority_timeout); void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, int priority) { if (!rpc_sleep_check_activated(task)) return; WARN_ON_ONCE(task->tk_timeout != 0); priority -= RPC_PRIORITY_LOW; /* * Protect the queue operations. */ spin_lock(&q->lock); __rpc_sleep_on_priority(q, task, priority); spin_unlock(&q->lock); } EXPORT_SYMBOL_GPL(rpc_sleep_on_priority); /** * __rpc_do_wake_up_task_on_wq - wake up a single rpc_task * @wq: workqueue on which to run task * @queue: wait queue * @task: task to be woken up * * Caller must hold queue->lock, and have cleared the task queued flag. */ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq, struct rpc_wait_queue *queue, struct rpc_task *task) { /* Has the task been executed yet? If not, we cannot wake it up! */ if (!RPC_IS_ACTIVATED(task)) { printk(KERN_ERR "RPC: Inactive task (%p) being woken up!\n", task); return; } trace_rpc_task_wakeup(task, queue); __rpc_remove_wait_queue(queue, task); rpc_make_runnable(wq, task); } /* * Wake up a queued task while the queue lock is being held */ static struct rpc_task * rpc_wake_up_task_on_wq_queue_action_locked(struct workqueue_struct *wq, struct rpc_wait_queue *queue, struct rpc_task *task, bool (*action)(struct rpc_task *, void *), void *data) { if (RPC_IS_QUEUED(task)) { smp_rmb(); if (task->tk_waitqueue == queue) { if (action == NULL || action(task, data)) { __rpc_do_wake_up_task_on_wq(wq, queue, task); return task; } } } return NULL; } /* * Wake up a queued task while the queue lock is being held */ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task) { rpc_wake_up_task_on_wq_queue_action_locked(rpciod_workqueue, queue, task, NULL, NULL); } /* * Wake up a task on a specific queue */ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task) { if (!RPC_IS_QUEUED(task)) return; spin_lock(&queue->lock); rpc_wake_up_task_queue_locked(queue, task); spin_unlock(&queue->lock); } EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task); static bool rpc_task_action_set_status(struct rpc_task *task, void *status) { task->tk_status = *(int *)status; return true; } static void rpc_wake_up_task_queue_set_status_locked(struct rpc_wait_queue *queue, struct rpc_task *task, int status) { rpc_wake_up_task_on_wq_queue_action_locked(rpciod_workqueue, queue, task, rpc_task_action_set_status, &status); } /** * rpc_wake_up_queued_task_set_status - wake up a task and set task->tk_status * @queue: pointer to rpc_wait_queue * @task: pointer to rpc_task * @status: integer error value * * If @task is queued on @queue, then it is woken up, and @task->tk_status is * set to the value of @status. */ void rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *queue, struct rpc_task *task, int status) { if (!RPC_IS_QUEUED(task)) return; spin_lock(&queue->lock); rpc_wake_up_task_queue_set_status_locked(queue, task, status); spin_unlock(&queue->lock); } /* * Wake up the next task on a priority queue. */ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *queue) { struct list_head *q; struct rpc_task *task; /* * Service the privileged queue. */ q = &queue->tasks[RPC_NR_PRIORITY - 1]; if (queue->maxpriority > RPC_PRIORITY_PRIVILEGED && !list_empty(q)) { task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto out; } /* * Service a batch of tasks from a single owner. */ q = &queue->tasks[queue->priority]; if (!list_empty(q) && queue->nr) { queue->nr--; task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto out; } /* * Service the next queue. */ do { if (q == &queue->tasks[0]) q = &queue->tasks[queue->maxpriority]; else q = q - 1; if (!list_empty(q)) { task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto new_queue; } } while (q != &queue->tasks[queue->priority]); rpc_reset_waitqueue_priority(queue); return NULL; new_queue: rpc_set_waitqueue_priority(queue, (unsigned int)(q - &queue->tasks[0])); out: return task; } static struct rpc_task *__rpc_find_next_queued(struct rpc_wait_queue *queue) { if (RPC_IS_PRIORITY(queue)) return __rpc_find_next_queued_priority(queue); if (!list_empty(&queue->tasks[0])) return list_first_entry(&queue->tasks[0], struct rpc_task, u.tk_wait.list); return NULL; } /* * Wake up the first task on the wait queue. */ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, struct rpc_wait_queue *queue, bool (*func)(struct rpc_task *, void *), void *data) { struct rpc_task *task = NULL; spin_lock(&queue->lock); task = __rpc_find_next_queued(queue); if (task != NULL) task = rpc_wake_up_task_on_wq_queue_action_locked(wq, queue, task, func, data); spin_unlock(&queue->lock); return task; } /* * Wake up the first task on the wait queue. */ struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *queue, bool (*func)(struct rpc_task *, void *), void *data) { return rpc_wake_up_first_on_wq(rpciod_workqueue, queue, func, data); } EXPORT_SYMBOL_GPL(rpc_wake_up_first); static bool rpc_wake_up_next_func(struct rpc_task *task, void *data) { return true; } /* * Wake up the next task on the wait queue. */ struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *queue) { return rpc_wake_up_first(queue, rpc_wake_up_next_func, NULL); } EXPORT_SYMBOL_GPL(rpc_wake_up_next); /** * rpc_wake_up_locked - wake up all rpc_tasks * @queue: rpc_wait_queue on which the tasks are sleeping * */ static void rpc_wake_up_locked(struct rpc_wait_queue *queue) { struct rpc_task *task; for (;;) { task = __rpc_find_next_queued(queue); if (task == NULL) break; rpc_wake_up_task_queue_locked(queue, task); } } /** * rpc_wake_up - wake up all rpc_tasks * @queue: rpc_wait_queue on which the tasks are sleeping * * Grabs queue->lock */ void rpc_wake_up(struct rpc_wait_queue *queue) { spin_lock(&queue->lock); rpc_wake_up_locked(queue); spin_unlock(&queue->lock); } EXPORT_SYMBOL_GPL(rpc_wake_up); /** * rpc_wake_up_status_locked - wake up all rpc_tasks and set their status value. * @queue: rpc_wait_queue on which the tasks are sleeping * @status: status value to set */ static void rpc_wake_up_status_locked(struct rpc_wait_queue *queue, int status) { struct rpc_task *task; for (;;) { task = __rpc_find_next_queued(queue); if (task == NULL) break; rpc_wake_up_task_queue_set_status_locked(queue, task, status); } } /** * rpc_wake_up_status - wake up all rpc_tasks and set their status value. * @queue: rpc_wait_queue on which the tasks are sleeping * @status: status value to set * * Grabs queue->lock */ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status) { spin_lock(&queue->lock); rpc_wake_up_status_locked(queue, status); spin_unlock(&queue->lock); } EXPORT_SYMBOL_GPL(rpc_wake_up_status); static void __rpc_queue_timer_fn(struct work_struct *work) { struct rpc_wait_queue *queue = container_of(work, struct rpc_wait_queue, timer_list.dwork.work); struct rpc_task *task, *n; unsigned long expires, now, timeo; spin_lock(&queue->lock); expires = now = jiffies; list_for_each_entry_safe(task, n, &queue->timer_list.list, u.tk_wait.timer_list) { timeo = task->tk_timeout; if (time_after_eq(now, timeo)) { trace_rpc_task_timeout(task, task->tk_action); task->tk_status = -ETIMEDOUT; rpc_wake_up_task_queue_locked(queue, task); continue; } if (expires == now || time_after(expires, timeo)) expires = timeo; } if (!list_empty(&queue->timer_list.list)) rpc_set_queue_timer(queue, expires); spin_unlock(&queue->lock); } static void __rpc_atrun(struct rpc_task *task) { if (task->tk_status == -ETIMEDOUT) task->tk_status = 0; } /* * Run a task at a later time */ void rpc_delay(struct rpc_task *task, unsigned long delay) { rpc_sleep_on_timeout(&delay_queue, task, __rpc_atrun, jiffies + delay); } EXPORT_SYMBOL_GPL(rpc_delay); /* * Helper to call task->tk_ops->rpc_call_prepare */ void rpc_prepare_task(struct rpc_task *task) { task->tk_ops->rpc_call_prepare(task, task->tk_calldata); } static void rpc_init_task_statistics(struct rpc_task *task) { /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; /* starting timestamp */ task->tk_start = ktime_get(); } static void rpc_reset_task_statistics(struct rpc_task *task) { task->tk_timeouts = 0; task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_SENT); rpc_init_task_statistics(task); } /* * Helper that calls task->tk_ops->rpc_call_done if it exists */ void rpc_exit_task(struct rpc_task *task) { trace_rpc_task_end(task, task->tk_action); task->tk_action = NULL; if (task->tk_ops->rpc_count_stats) task->tk_ops->rpc_count_stats(task, task->tk_calldata); else if (task->tk_client) rpc_count_iostats(task, task->tk_client->cl_metrics); if (task->tk_ops->rpc_call_done != NULL) { trace_rpc_task_call_done(task, task->tk_ops->rpc_call_done); task->tk_ops->rpc_call_done(task, task->tk_calldata); if (task->tk_action != NULL) { /* Always release the RPC slot and buffer memory */ xprt_release(task); rpc_reset_task_statistics(task); } } } void rpc_signal_task(struct rpc_task *task) { struct rpc_wait_queue *queue; if (!RPC_IS_ACTIVATED(task)) return; if (!rpc_task_set_rpc_status(task, -ERESTARTSYS)) return; trace_rpc_task_signalled(task, task->tk_action); set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate); smp_mb__after_atomic(); queue = READ_ONCE(task->tk_waitqueue); if (queue) rpc_wake_up_queued_task(queue, task); } void rpc_task_try_cancel(struct rpc_task *task, int error) { struct rpc_wait_queue *queue; if (!rpc_task_set_rpc_status(task, error)) return; queue = READ_ONCE(task->tk_waitqueue); if (queue) rpc_wake_up_queued_task(queue, task); } void rpc_exit(struct rpc_task *task, int status) { task->tk_status = status; task->tk_action = rpc_exit_task; rpc_wake_up_queued_task(task->tk_waitqueue, task); } EXPORT_SYMBOL_GPL(rpc_exit); void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata) { if (ops->rpc_release != NULL) ops->rpc_release(calldata); } static bool xprt_needs_memalloc(struct rpc_xprt *xprt, struct rpc_task *tk) { if (!xprt) return false; if (!atomic_read(&xprt->swapper)) return false; return test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == tk; } /* * This is the RPC `scheduler' (or rather, the finite state machine). */ static void __rpc_execute(struct rpc_task *task) { struct rpc_wait_queue *queue; int task_is_async = RPC_IS_ASYNC(task); int status = 0; unsigned long pflags = current->flags; WARN_ON_ONCE(RPC_IS_QUEUED(task)); if (RPC_IS_QUEUED(task)) return; for (;;) { void (*do_action)(struct rpc_task *); /* * Perform the next FSM step or a pending callback. * * tk_action may be NULL if the task has been killed. */ do_action = task->tk_action; /* Tasks with an RPC error status should exit */ if (do_action && do_action != rpc_exit_task && (status = READ_ONCE(task->tk_rpc_status)) != 0) { task->tk_status = status; do_action = rpc_exit_task; } /* Callbacks override all actions */ if (task->tk_callback) { do_action = task->tk_callback; task->tk_callback = NULL; } if (!do_action) break; if (RPC_IS_SWAPPER(task) || xprt_needs_memalloc(task->tk_xprt, task)) current->flags |= PF_MEMALLOC; trace_rpc_task_run_action(task, do_action); do_action(task); /* * Lockless check for whether task is sleeping or not. */ if (!RPC_IS_QUEUED(task)) { cond_resched(); continue; } /* * The queue->lock protects against races with * rpc_make_runnable(). * * Note that once we clear RPC_TASK_RUNNING on an asynchronous * rpc_task, rpc_make_runnable() can assign it to a * different workqueue. We therefore cannot assume that the * rpc_task pointer may still be dereferenced. */ queue = task->tk_waitqueue; spin_lock(&queue->lock); if (!RPC_IS_QUEUED(task)) { spin_unlock(&queue->lock); continue; } /* Wake up any task that has an exit status */ if (READ_ONCE(task->tk_rpc_status) != 0) { rpc_wake_up_task_queue_locked(queue, task); spin_unlock(&queue->lock); continue; } rpc_clear_running(task); spin_unlock(&queue->lock); if (task_is_async) goto out; /* sync task: sleep here */ trace_rpc_task_sync_sleep(task, task->tk_action); status = out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_QUEUED, rpc_wait_bit_killable, TASK_KILLABLE|TASK_FREEZABLE); if (status < 0) { /* * When a sync task receives a signal, it exits with * -ERESTARTSYS. In order to catch any callbacks that * clean up after sleeping on some queue, we don't * break the loop here, but go around once more. */ rpc_signal_task(task); } trace_rpc_task_sync_wake(task, task->tk_action); } /* Release all resources associated with the task */ rpc_release_task(task); out: current_restore_flags(pflags, PF_MEMALLOC); } /* * User-visible entry point to the scheduler. * * This may be called recursively if e.g. an async NFS task updates * the attributes and finds that dirty pages must be flushed. * NOTE: Upon exit of this function the task is guaranteed to be * released. In particular note that tk_release() will have * been called, so your task memory may have been freed. */ void rpc_execute(struct rpc_task *task) { bool is_async = RPC_IS_ASYNC(task); rpc_set_active(task); rpc_make_runnable(rpciod_workqueue, task); if (!is_async) { unsigned int pflags = memalloc_nofs_save(); __rpc_execute(task); memalloc_nofs_restore(pflags); } } static void rpc_async_schedule(struct work_struct *work) { unsigned int pflags = memalloc_nofs_save(); __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); memalloc_nofs_restore(pflags); } /** * rpc_malloc - allocate RPC buffer resources * @task: RPC task * * A single memory region is allocated, which is split between the * RPC call and RPC reply that this task is being used for. When * this RPC is retired, the memory is released by calling rpc_free. * * To prevent rpciod from hanging, this allocator never sleeps, * returning -ENOMEM and suppressing warning if the request cannot * be serviced immediately. The caller can arrange to sleep in a * way that is safe for rpciod. * * Most requests are 'small' (under 2KiB) and can be serviced from a * mempool, ensuring that NFS reads and writes can always proceed, * and that there is good locality of reference for these buffers. */ int rpc_malloc(struct rpc_task *task) { struct rpc_rqst *rqst = task->tk_rqstp; size_t size = rqst->rq_callsize + rqst->rq_rcvsize; struct rpc_buffer *buf; gfp_t gfp = rpc_task_gfp_mask(); size += sizeof(struct rpc_buffer); if (size <= RPC_BUFFER_MAXSIZE) { buf = kmem_cache_alloc(rpc_buffer_slabp, gfp); /* Reach for the mempool if dynamic allocation fails */ if (!buf && RPC_IS_ASYNC(task)) buf = mempool_alloc(rpc_buffer_mempool, GFP_NOWAIT); } else buf = kmalloc(size, gfp); if (!buf) return -ENOMEM; buf->len = size; rqst->rq_buffer = buf->data; rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize; return 0; } EXPORT_SYMBOL_GPL(rpc_malloc); /** * rpc_free - free RPC buffer resources allocated via rpc_malloc * @task: RPC task * */ void rpc_free(struct rpc_task *task) { void *buffer = task->tk_rqstp->rq_buffer; size_t size; struct rpc_buffer *buf; buf = container_of(buffer, struct rpc_buffer, data); size = buf->len; if (size <= RPC_BUFFER_MAXSIZE) mempool_free(buf, rpc_buffer_mempool); else kfree(buf); } EXPORT_SYMBOL_GPL(rpc_free); /* * Creation and deletion of RPC task structures */ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *task_setup_data) { memset(task, 0, sizeof(*task)); atomic_set(&task->tk_count, 1); task->tk_flags = task_setup_data->flags; task->tk_ops = task_setup_data->callback_ops; task->tk_calldata = task_setup_data->callback_data; INIT_LIST_HEAD(&task->tk_task); task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; /* Initialize workqueue for async tasks */ task->tk_workqueue = task_setup_data->workqueue; task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client, xprt_get(task_setup_data->rpc_xprt)); task->tk_op_cred = get_rpccred(task_setup_data->rpc_op_cred); if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; rpc_init_task_statistics(task); } static struct rpc_task *rpc_alloc_task(void) { struct rpc_task *task; task = kmem_cache_alloc(rpc_task_slabp, rpc_task_gfp_mask()); if (task) return task; return mempool_alloc(rpc_task_mempool, GFP_NOWAIT); } /* * Create a new task for the specified client. */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) { struct rpc_task *task = setup_data->task; unsigned short flags = 0; if (task == NULL) { task = rpc_alloc_task(); if (task == NULL) { rpc_release_calldata(setup_data->callback_ops, setup_data->callback_data); return ERR_PTR(-ENOMEM); } flags = RPC_TASK_DYNAMIC; } rpc_init_task(task, setup_data); task->tk_flags |= flags; return task; } /* * rpc_free_task - release rpc task and perform cleanups * * Note that we free up the rpc_task _after_ rpc_release_calldata() * in order to work around a workqueue dependency issue. * * Tejun Heo states: * "Workqueue currently considers two work items to be the same if they're * on the same address and won't execute them concurrently - ie. it * makes a work item which is queued again while being executed wait * for the previous execution to complete. * * If a work function frees the work item, and then waits for an event * which should be performed by another work item and *that* work item * recycles the freed work item, it can create a false dependency loop. * There really is no reliable way to detect this short of verifying * every memory free." * */ static void rpc_free_task(struct rpc_task *task) { unsigned short tk_flags = task->tk_flags; put_rpccred(task->tk_op_cred); rpc_release_calldata(task->tk_ops, task->tk_calldata); if (tk_flags & RPC_TASK_DYNAMIC) mempool_free(task, rpc_task_mempool); } static void rpc_async_release(struct work_struct *work) { unsigned int pflags = memalloc_nofs_save(); rpc_free_task(container_of(work, struct rpc_task, u.tk_work)); memalloc_nofs_restore(pflags); } static void rpc_release_resources_task(struct rpc_task *task) { xprt_release(task); if (task->tk_msg.rpc_cred) { if (!(task->tk_flags & RPC_TASK_CRED_NOREF)) put_cred(task->tk_msg.rpc_cred); task->tk_msg.rpc_cred = NULL; } rpc_task_release_client(task); } static void rpc_final_put_task(struct rpc_task *task, struct workqueue_struct *q) { if (q != NULL) { INIT_WORK(&task->u.tk_work, rpc_async_release); queue_work(q, &task->u.tk_work); } else rpc_free_task(task); } static void rpc_do_put_task(struct rpc_task *task, struct workqueue_struct *q) { if (atomic_dec_and_test(&task->tk_count)) { rpc_release_resources_task(task); rpc_final_put_task(task, q); } } void rpc_put_task(struct rpc_task *task) { rpc_do_put_task(task, NULL); } EXPORT_SYMBOL_GPL(rpc_put_task); void rpc_put_task_async(struct rpc_task *task) { rpc_do_put_task(task, task->tk_workqueue); } EXPORT_SYMBOL_GPL(rpc_put_task_async); static void rpc_release_task(struct rpc_task *task) { WARN_ON_ONCE(RPC_IS_QUEUED(task)); rpc_release_resources_task(task); /* * Note: at this point we have been removed from rpc_clnt->cl_tasks, * so it should be safe to use task->tk_count as a test for whether * or not any other processes still hold references to our rpc_task. */ if (atomic_read(&task->tk_count) != 1 + !RPC_IS_ASYNC(task)) { /* Wake up anyone who may be waiting for task completion */ if (!rpc_complete_task(task)) return; } else { if (!atomic_dec_and_test(&task->tk_count)) return; } rpc_final_put_task(task, task->tk_workqueue); } int rpciod_up(void) { return try_module_get(THIS_MODULE) ? 0 : -EINVAL; } void rpciod_down(void) { module_put(THIS_MODULE); } /* * Start up the rpciod workqueue. */ static int rpciod_start(void) { struct workqueue_struct *wq; /* * Create the rpciod thread and wait for it to start. */ wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!wq) goto out_failed; rpciod_workqueue = wq; wq = alloc_workqueue("xprtiod", WQ_UNBOUND | WQ_MEM_RECLAIM, 0); if (!wq) goto free_rpciod; xprtiod_workqueue = wq; return 1; free_rpciod: wq = rpciod_workqueue; rpciod_workqueue = NULL; destroy_workqueue(wq); out_failed: return 0; } static void rpciod_stop(void) { struct workqueue_struct *wq = NULL; if (rpciod_workqueue == NULL) return; wq = rpciod_workqueue; rpciod_workqueue = NULL; destroy_workqueue(wq); wq = xprtiod_workqueue; xprtiod_workqueue = NULL; destroy_workqueue(wq); } void rpc_destroy_mempool(void) { rpciod_stop(); mempool_destroy(rpc_buffer_mempool); mempool_destroy(rpc_task_mempool); kmem_cache_destroy(rpc_task_slabp); kmem_cache_destroy(rpc_buffer_slabp); rpc_destroy_wait_queue(&delay_queue); } int rpc_init_mempool(void) { /* * The following is not strictly a mempool initialisation, * but there is no harm in doing it here */ rpc_init_wait_queue(&delay_queue, "delayq"); if (!rpciod_start()) goto err_nomem; rpc_task_slabp = kmem_cache_create("rpc_tasks", sizeof(struct rpc_task), 0, SLAB_HWCACHE_ALIGN, NULL); if (!rpc_task_slabp) goto err_nomem; rpc_buffer_slabp = kmem_cache_create("rpc_buffers", RPC_BUFFER_MAXSIZE, 0, SLAB_HWCACHE_ALIGN, NULL); if (!rpc_buffer_slabp) goto err_nomem; rpc_task_mempool = mempool_create_slab_pool(RPC_TASK_POOLSIZE, rpc_task_slabp); if (!rpc_task_mempool) goto err_nomem; rpc_buffer_mempool = mempool_create_slab_pool(RPC_BUFFER_POOLSIZE, rpc_buffer_slabp); if (!rpc_buffer_mempool) goto err_nomem; return 0; err_nomem: rpc_destroy_mempool(); return -ENOMEM; } |
| 15 636 479 177 635 474 173 22 22 22 46 46 41 14 16 16 240 241 2 14 26 3 23 12 17 3 1 16 1 1 3 16 5 10 5 8 1 9 19 3 18 3 8 14 11 46 6 4 1 24 6 7 1 6 9 7 16 23 29 2 6 2 1 4 3 6 35 32 3 35 31 28 1 7 3 13 301 274 149 141 281 274 149 141 281 31 64 59 29 28 60 27 61 64 8 2 6 4 4 4 581 2 554 554 549 553 552 551 553 31 22 9 31 31 6 29 22 9 29 3 38 11 6 5 11 12 1 1 9 1 12 3 4 5 12 33 33 31 31 6 6 6 6 7 2 7 7 7 18 12 1 5 5 3 2 1 8 3 5 4 1 3 2 1 1 2 7 1 3 6 12 1 1 7 1 1 1 9 2 4 6 1 9 7 8 1 7 4 5 2 2 6 2 700 613 207 14 2 11 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_version = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_version = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 48 552 256 255 255 1375 103 442 1 14 182 1 183 182 1 169 98 1 97 98 318 95 160 156 1 2954 13 62 102 33 65 3 4 49 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* 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 call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Speculative Store Bypass */ #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) */ #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 }) /* 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) }) /* 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 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; 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; }; }; struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 kern_flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ /* 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); } /* 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 u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } 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); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } 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); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); 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); void bpf_clear_redirect_map(struct bpf_map *map); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); 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 = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); 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, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, struct bpf_prog *prog); void xdp_do_flush(void); void bpf_warn_invalid_xdp_action(struct net_device *dev, 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_prog *prog, 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); 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=%pK 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 *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 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; 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(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(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 = this_cpu_ptr(&bpf_redirect_info); 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); #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) { } #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ |
| 1340 3 1534 1857 24 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header is used to share core functionality between the * standalone connection tracking module, and the compatibility layer's use * of connection tracking. * * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * - generalize L3 protocol dependent part. * * Derived from include/linux/netfiter_ipv4/ip_conntrack_core.h */ #ifndef _NF_CONNTRACK_CORE_H #define _NF_CONNTRACK_CORE_H #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_l4proto.h> /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); void nf_conntrack_proto_pernet_init(struct net *net); int nf_conntrack_proto_init(void); void nf_conntrack_proto_fini(void); int nf_conntrack_init_start(void); void nf_conntrack_cleanup_start(void); void nf_conntrack_init_end(void); void nf_conntrack_cleanup_end(void); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple); int __nf_conntrack_confirm(struct sk_buff *skb); /* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int nf_conntrack_confirm(struct sk_buff *skb) { struct nf_conn *ct = (struct nf_conn *)skb_nfct(skb); int ret = NF_ACCEPT; if (ct) { if (!nf_ct_is_confirmed(ct)) { ret = __nf_conntrack_confirm(skb); if (ret == NF_ACCEPT) ct = (struct nf_conn *)skb_nfct(skb); } if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } return ret; } unsigned int nf_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *proto); #define CONNTRACK_LOCKS 1024 extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) { if (timeout > INT_MAX) timeout = INT_MAX; if (nf_ct_is_confirmed(ct)) WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); else ct->timeout = (u32)timeout; } int __nf_ct_change_timeout(struct nf_conn *ct, u64 cta_timeout); void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off); int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status); #endif /* _NF_CONNTRACK_CORE_H */ |
| 4 4 4 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 | /* * Copyright (c) 2014 Intel Corporation. All rights reserved. * Copyright (c) 2014 Chelsio, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "iwpm_util.h" static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser"; u16 iwpm_ulib_version = IWPM_UABI_VERSION_MIN; static int iwpm_user_pid = IWPM_PID_UNDEFINED; static atomic_t echo_nlmsg_seq; /** * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid * * Returns true if the pid is greater than zero, otherwise returns false */ int iwpm_valid_pid(void) { return iwpm_user_pid > 0; } /** * iwpm_register_pid - Send a netlink query to userspace * to get the iwarp port mapper pid * @pm_msg: Contains driver info to send to the userspace port mapper * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_REG_PID_SEQ] * [IWPM_NLA_REG_IF_NAME] * [IWPM_NLA_REG_IBDEV_NAME] * [IWPM_NLA_REG_ULIB_NAME] */ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (iwpm_check_registration(nl_client, IWPM_REG_VALID) || iwpm_user_pid == IWPM_PID_UNAVAILABLE) return 0; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto pid_query_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto pid_query_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the pid request message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_REG_PID_SEQ); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IFNAMSIZ, pm_msg->if_name, IWPM_NLA_REG_IF_NAME); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IWPM_DEVNAME_SIZE, pm_msg->dev_name, IWPM_NLA_REG_IBDEV_NAME); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IWPM_ULIBNAME_SIZE, (char *)iwpm_ulib_name, IWPM_NLA_REG_ULIB_NAME); if (ret) goto pid_query_error; nlmsg_end(skb, nlh); pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n", __func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name); ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNAVAILABLE; err_str = "Unable to send a nlmsg"; goto pid_query_error; } nlmsg_request->req_buffer = pm_msg; ret = iwpm_wait_complete_req(nlmsg_request); return ret; pid_query_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_add_mapping - Send a netlink add mapping request to * the userspace port mapper * @pm_msg: Contains the local ip/tcp address info to send * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] * [IWPM_NLA_MANAGE_FLAGS] * * If the request is successful, the pm_msg stores * the port mapper response (mapped address info) */ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto add_mapping_error; } skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto add_mapping_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto add_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the add mapping message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_MANAGE_MAPPING_SEQ); if (ret) goto add_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto add_mapping_error; /* If flags are required and we're not V4, then return a quiet error */ if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { ret = -EINVAL; goto add_mapping_error_nowarn; } if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, IWPM_NLA_MANAGE_FLAGS); if (ret) goto add_mapping_error; } nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; err_str = "Unable to send a nlmsg"; goto add_mapping_error; } ret = iwpm_wait_complete_req(nlmsg_request); return ret; add_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); add_mapping_error_nowarn: dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_add_and_query_mapping - Process the port mapper response to * iwpm_add_and_query_mapping request * @pm_msg: Contains the local ip/tcp address info to send * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_QUERY_MAPPING_SEQ] * [IWPM_NLA_QUERY_LOCAL_ADDR] * [IWPM_NLA_QUERY_REMOTE_ADDR] * [IWPM_NLA_QUERY_FLAGS] */ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto query_mapping_error; } ret = -ENOMEM; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto query_mapping_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto query_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the query message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_QUERY_MAPPING_SEQ); if (ret) goto query_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->loc_addr, IWPM_NLA_QUERY_LOCAL_ADDR); if (ret) goto query_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR); if (ret) goto query_mapping_error; /* If flags are required and we're not V4, then return a quite error */ if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { ret = -EINVAL; goto query_mapping_error_nowarn; } if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, IWPM_NLA_QUERY_FLAGS); if (ret) goto query_mapping_error; } nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ err_str = "Unable to send a nlmsg"; goto query_mapping_error; } ret = iwpm_wait_complete_req(nlmsg_request); return ret; query_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); query_mapping_error_nowarn: dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_remove_mapping - Send a netlink remove mapping request * to the userspace port mapper * * @local_addr: Local ip/tcp address to remove * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] */ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (iwpm_check_registration(nl_client, IWPM_REG_UNDEF)) { err_str = "Unregistered port mapper client"; goto remove_mapping_error; } skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client); if (!skb) { ret = -ENOMEM; err_str = "Unable to create a nlmsg"; goto remove_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_MANAGE_MAPPING_SEQ); if (ret) goto remove_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), local_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto remove_mapping_error; nlmsg_end(skb, nlh); ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; err_str = "Unable to send a nlmsg"; goto remove_mapping_error; } iwpm_print_sockaddr(local_addr, "remove_mapping: Local sockaddr:"); return 0; remove_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); if (skb) dev_kfree_skb_any(skb); return ret; } /* netlink attribute policy for the received response to register pid request */ static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = { [IWPM_NLA_RREG_PID_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RREG_IBDEV_NAME] = { .type = NLA_STRING, .len = IWPM_DEVNAME_SIZE - 1 }, [IWPM_NLA_RREG_ULIB_NAME] = { .type = NLA_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_RREG_ULIB_VER] = { .type = NLA_U16 }, [IWPM_NLA_RREG_PID_ERR] = { .type = NLA_U16 } }; /** * iwpm_register_pid_cb - Process the port mapper response to * iwpm_register_pid query * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * If successful, the function receives the userspace port mapper pid * which is used in future communication with the port mapper */ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RREG_PID_MAX]; struct iwpm_dev_data *pm_msg; char *dev_name, *iwpm_name; u32 msg_seq; u8 nl_client; u16 iwpm_version; const char *msg_type = "Register Pid response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RREG_PID_MAX, resp_reg_policy, nltb, msg_type)) return -EINVAL; msg_seq = nla_get_u32(nltb[IWPM_NLA_RREG_PID_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; nl_client = nlmsg_request->nl_client; dev_name = (char *)nla_data(nltb[IWPM_NLA_RREG_IBDEV_NAME]); iwpm_name = (char *)nla_data(nltb[IWPM_NLA_RREG_ULIB_NAME]); iwpm_version = nla_get_u16(nltb[IWPM_NLA_RREG_ULIB_VER]); /* check device name, ulib name and version */ if (strcmp(pm_msg->dev_name, dev_name) || strcmp(iwpm_ulib_name, iwpm_name) || iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Incorrect info (dev = %s name = %s version = %u)\n", __func__, dev_name, iwpm_name, iwpm_version); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto register_pid_response_exit; } iwpm_user_pid = cb->nlh->nlmsg_pid; iwpm_ulib_version = iwpm_version; if (iwpm_ulib_version < IWPM_UABI_VERSION) pr_warn_once("%s: Down level iwpmd/pid %d. Continuing...", __func__, iwpm_user_pid); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); iwpm_set_registration(nl_client, IWPM_REG_VALID); register_pid_response_exit: nlmsg_request->request_done = 1; /* always for found nlmsg_request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the received response to add mapping request */ static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = { [IWPM_NLA_RMANAGE_MAPPING_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RMANAGE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RMANAGE_MAPPING_ERR] = { .type = NLA_U16 } }; /** * iwpm_add_mapping_cb - Process the port mapper response to * iwpm_add_mapping request * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_sa_data *pm_msg; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RMANAGE_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr; struct sockaddr_storage *mapped_sockaddr; const char *msg_type; u32 msg_seq; msg_type = "Add Mapping response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RMANAGE_MAPPING_MAX, resp_add_policy, nltb, msg_type)) return -EINVAL; atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); msg_seq = nla_get_u32(nltb[IWPM_NLA_RMANAGE_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RMANAGE_ADDR]); mapped_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR]); if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr)) { nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto add_mapping_response_exit; } if (mapped_sockaddr->ss_family != local_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto add_mapping_response_exit; } memcpy(&pm_msg->mapped_loc_addr, mapped_sockaddr, sizeof(*mapped_sockaddr)); iwpm_print_sockaddr(&pm_msg->loc_addr, "add_mapping: Local sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_loc_addr, "add_mapping: Mapped local sockaddr:"); add_mapping_response_exit: nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the response to add and query mapping request * and response with remote address info */ static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = { [IWPM_NLA_RQUERY_MAPPING_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RQUERY_LOCAL_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_REMOTE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPED_REM_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPING_ERR] = { .type = NLA_U16 } }; /** * iwpm_add_and_query_mapping_cb - Process the port mapper response to * iwpm_add_and_query_mapping request * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_sa_data *pm_msg; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr, *remote_sockaddr; struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr; const char *msg_type; u32 msg_seq; u16 err_code; msg_type = "Query Mapping response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX, resp_query_policy, nltb, msg_type)) return -EINVAL; atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); msg_seq = nla_get_u32(nltb[IWPM_NLA_RQUERY_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]); err_code = nla_get_u16(nltb[IWPM_NLA_RQUERY_MAPPING_ERR]); if (err_code == IWPM_REMOTE_QUERY_REJECT) { pr_info("%s: Received a Reject (pid = %u, echo seq = %u)\n", __func__, cb->nlh->nlmsg_pid, msg_seq); nlmsg_request->err_code = IWPM_REMOTE_QUERY_REJECT; } if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr) || iwpm_compare_sockaddr(remote_sockaddr, &pm_msg->rem_addr)) { pr_info("%s: Incorrect local sockaddr\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto query_mapping_response_exit; } if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family || mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto query_mapping_response_exit; } memcpy(&pm_msg->mapped_loc_addr, mapped_loc_sockaddr, sizeof(*mapped_loc_sockaddr)); memcpy(&pm_msg->mapped_rem_addr, mapped_rem_sockaddr, sizeof(*mapped_rem_sockaddr)); iwpm_print_sockaddr(&pm_msg->loc_addr, "query_mapping: Local sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_loc_addr, "query_mapping: Mapped local sockaddr:"); iwpm_print_sockaddr(&pm_msg->rem_addr, "query_mapping: Remote sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_rem_addr, "query_mapping: Mapped remote sockaddr:"); query_mapping_response_exit: nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /** * iwpm_remote_info_cb - Process remote connecting peer address info, which * the port mapper has received from the connecting peer * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Stores the IPv4/IPv6 address info in a hash table */ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr, *remote_sockaddr; struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr; struct iwpm_remote_info *rem_info; const char *msg_type; u8 nl_client; int ret = -EINVAL; msg_type = "Remote Mapping info"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX, resp_query_policy, nltb, msg_type)) return ret; nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]); if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family || mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); return ret; } rem_info = kzalloc(sizeof(struct iwpm_remote_info), GFP_ATOMIC); if (!rem_info) { ret = -ENOMEM; return ret; } memcpy(&rem_info->mapped_loc_sockaddr, mapped_loc_sockaddr, sizeof(struct sockaddr_storage)); memcpy(&rem_info->remote_sockaddr, remote_sockaddr, sizeof(struct sockaddr_storage)); memcpy(&rem_info->mapped_rem_sockaddr, mapped_rem_sockaddr, sizeof(struct sockaddr_storage)); rem_info->nl_client = nl_client; iwpm_add_remote_info(rem_info); iwpm_print_sockaddr(local_sockaddr, "remote_info: Local sockaddr:"); iwpm_print_sockaddr(mapped_loc_sockaddr, "remote_info: Mapped local sockaddr:"); iwpm_print_sockaddr(remote_sockaddr, "remote_info: Remote sockaddr:"); iwpm_print_sockaddr(mapped_rem_sockaddr, "remote_info: Mapped remote sockaddr:"); return ret; } /* netlink attribute policy for the received request for mapping info */ static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = { [IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_MAPINFO_ULIB_VER] = { .type = NLA_U16 } }; /** * iwpm_mapping_info_cb - Process a notification that the userspace * port mapper daemon is started * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Using the received port mapper pid, send all the local mapping * info records to the userspace port mapper */ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX]; const char *msg_type = "Mapping Info response"; u8 nl_client; char *iwpm_name; u16 iwpm_version; int ret = -EINVAL; if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_REQ_MAX, resp_mapinfo_policy, nltb, msg_type)) { pr_info("%s: Unable to parse nlmsg\n", __func__); return ret; } iwpm_name = (char *)nla_data(nltb[IWPM_NLA_MAPINFO_ULIB_NAME]); iwpm_version = nla_get_u16(nltb[IWPM_NLA_MAPINFO_ULIB_VER]); if (strcmp(iwpm_ulib_name, iwpm_name) || iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Invalid port mapper name = %s version = %u\n", __func__, iwpm_name, iwpm_version); return ret; } nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); iwpm_user_pid = cb->nlh->nlmsg_pid; if (iwpm_ulib_version < IWPM_UABI_VERSION) pr_warn_once("%s: Down level iwpmd/pid %d. Continuing...", __func__, iwpm_user_pid); if (!iwpm_mapinfo_available()) return 0; pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid); return ret; } /* netlink attribute policy for the received mapping info ack */ static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = { [IWPM_NLA_MAPINFO_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_MAPINFO_SEND_NUM] = { .type = NLA_U32 }, [IWPM_NLA_MAPINFO_ACK_NUM] = { .type = NLA_U32 } }; /** * iwpm_ack_mapping_info_cb - Process the port mapper ack for * the provided local mapping info records * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_MAPINFO_NUM_MAX]; u32 mapinfo_send, mapinfo_ack; const char *msg_type = "Mapping Info Ack"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_NUM_MAX, ack_mapinfo_policy, nltb, msg_type)) return -EINVAL; mapinfo_send = nla_get_u32(nltb[IWPM_NLA_MAPINFO_SEND_NUM]); mapinfo_ack = nla_get_u32(nltb[IWPM_NLA_MAPINFO_ACK_NUM]); if (mapinfo_ack != mapinfo_send) pr_info("%s: Invalid mapinfo number (sent = %u ack-ed = %u)\n", __func__, mapinfo_send, mapinfo_ack); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); return 0; } /* netlink attribute policy for the received port mapper error message */ static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = { [IWPM_NLA_ERR_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_ERR_CODE] = { .type = NLA_U16 }, }; /** * iwpm_mapping_error_cb - Process port mapper notification for error * * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_nlmsg_request *nlmsg_request = NULL; int nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); struct nlattr *nltb[IWPM_NLA_ERR_MAX]; u32 msg_seq; u16 err_code; const char *msg_type = "Mapping Error Msg"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_ERR_MAX, map_error_policy, nltb, msg_type)) return -EINVAL; msg_seq = nla_get_u32(nltb[IWPM_NLA_ERR_SEQ]); err_code = nla_get_u16(nltb[IWPM_NLA_ERR_CODE]); pr_info("%s: Received msg seq = %u err code = %u client = %d\n", __func__, msg_seq, err_code, nl_client); /* look for nlmsg_request */ nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { /* not all errors have associated requests */ pr_debug("Could not find matching req (seq = %u)\n", msg_seq); return 0; } atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); nlmsg_request->err_code = err_code; nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the received hello request */ static const struct nla_policy hello_policy[IWPM_NLA_HELLO_MAX] = { [IWPM_NLA_HELLO_ABI_VERSION] = { .type = NLA_U16 } }; /** * iwpm_hello_cb - Process a hello message from iwpmd * * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Using the received port mapper pid, send the kernel's abi_version * after adjusting it to support the iwpmd version. */ int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_HELLO_MAX]; const char *msg_type = "Hello request"; u8 nl_client; u16 abi_version; int ret = -EINVAL; if (iwpm_parse_nlmsg(cb, IWPM_NLA_HELLO_MAX, hello_policy, nltb, msg_type)) { pr_info("%s: Unable to parse nlmsg\n", __func__); return ret; } abi_version = nla_get_u16(nltb[IWPM_NLA_HELLO_ABI_VERSION]); nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); iwpm_ulib_version = min_t(u16, IWPM_UABI_VERSION, abi_version); pr_debug("Using ABI version %u\n", iwpm_ulib_version); iwpm_user_pid = cb->nlh->nlmsg_pid; ret = iwpm_send_hello(nl_client, iwpm_user_pid, iwpm_ulib_version); return ret; } |
| 3 3 3 40 2 5 5 1 1 41 28 17 40 3 36 3 3 36 3 17 28 3 3 3 2 3 3 3 3 3 3 38 14 2 24 3 38 38 38 38 4 4 4 4 7 1 2 2 2 1 2 2 2 2 1 1 1 1 1 2 2 1 1 1 2 7 1 3 4 2 7 7 2 18 10 2 6 2 5 13 2 2 11 12 4 6 1 2 7 1 4 4 3 7 2 2 6 4 1 1 2 3 1 1 1 1 1 2 2 1 1 3 3 2 2 3 3 3 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/igmp.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/if_ether.h> #include <net/ip.h> #include <net/netlink.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/addrconf.h> #endif #include "br_private.h" static bool br_ip4_rports_get_timer(struct net_bridge_mcast_port *pmctx, unsigned long *timer) { *timer = br_timer_value(&pmctx->ip4_mc_router_timer); return !hlist_unhashed(&pmctx->ip4_rlist); } static bool br_ip6_rports_get_timer(struct net_bridge_mcast_port *pmctx, unsigned long *timer) { #if IS_ENABLED(CONFIG_IPV6) *timer = br_timer_value(&pmctx->ip6_mc_router_timer); return !hlist_unhashed(&pmctx->ip6_rlist); #else *timer = 0; return false; #endif } static size_t __br_rports_one_size(void) { return nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PORT */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_TIMER */ nla_total_size(sizeof(u8)) + /* MDBA_ROUTER_PATTR_TYPE */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET_TIMER */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET6_TIMER */ nla_total_size(sizeof(u32)); /* MDBA_ROUTER_PATTR_VID */ } size_t br_rports_size(const struct net_bridge_mcast *brmctx) { struct net_bridge_mcast_port *pmctx; size_t size = nla_total_size(0); /* MDBA_ROUTER */ rcu_read_lock(); hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, ip4_rlist) size += __br_rports_one_size(); #if IS_ENABLED(CONFIG_IPV6) hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, ip6_rlist) size += __br_rports_one_size(); #endif rcu_read_unlock(); return size; } int br_rports_fill_info(struct sk_buff *skb, const struct net_bridge_mcast *brmctx) { u16 vid = brmctx->vlan ? brmctx->vlan->vid : 0; bool have_ip4_mc_rtr, have_ip6_mc_rtr; unsigned long ip4_timer, ip6_timer; struct nlattr *nest, *port_nest; struct net_bridge_port *p; if (!brmctx->multicast_router || !br_rports_have_mc_router(brmctx)) return 0; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; list_for_each_entry_rcu(p, &brmctx->br->port_list, list) { struct net_bridge_mcast_port *pmctx; if (vid) { struct net_bridge_vlan *v; v = br_vlan_find(nbp_vlan_group(p), vid); if (!v) continue; pmctx = &v->port_mcast_ctx; } else { pmctx = &p->multicast_ctx; } have_ip4_mc_rtr = br_ip4_rports_get_timer(pmctx, &ip4_timer); have_ip6_mc_rtr = br_ip6_rports_get_timer(pmctx, &ip6_timer); if (!have_ip4_mc_rtr && !have_ip6_mc_rtr) continue; port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto fail; if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, max(ip4_timer, ip6_timer)) || nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, p->multicast_ctx.multicast_router) || (have_ip4_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER, ip4_timer)) || (have_ip6_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER, ip6_timer)) || (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid))) { nla_nest_cancel(skb, port_nest); goto fail; } nla_nest_end(skb, port_nest); } nla_nest_end(skb, nest); return 0; fail: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) { e->state = flags & MDB_PG_FLAGS_PERMANENT; e->flags = 0; if (flags & MDB_PG_FLAGS_OFFLOAD) e->flags |= MDB_FLAGS_OFFLOAD; if (flags & MDB_PG_FLAGS_FAST_LEAVE) e->flags |= MDB_FLAGS_FAST_LEAVE; if (flags & MDB_PG_FLAGS_STAR_EXCL) e->flags |= MDB_FLAGS_STAR_EXCL; if (flags & MDB_PG_FLAGS_BLOCKED) e->flags |= MDB_FLAGS_BLOCKED; } static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, struct nlattr **mdb_attrs) { memset(ip, 0, sizeof(struct br_ip)); ip->vid = entry->vid; ip->proto = entry->addr.proto; switch (ip->proto) { case htons(ETH_P_IP): ip->dst.ip4 = entry->addr.u.ip4; if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip->dst.ip6 = entry->addr.u.ip6; if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #endif default: ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr); } } static int __mdb_fill_srcs(struct sk_buff *skb, struct net_bridge_port_group *p) { struct net_bridge_group_src *ent; struct nlattr *nest, *nest_ent; if (hlist_empty(&p->src_list)) return 0; nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); if (!nest) return -EMSGSIZE; hlist_for_each_entry_rcu(ent, &p->src_list, node, lockdep_is_held(&p->key.port->br->multicast_lock)) { nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); if (!nest_ent) goto out_cancel_err; switch (ent->addr.proto) { case htons(ETH_P_IP): if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, ent->addr.src.ip4)) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, &ent->addr.src.ip6)) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } break; #endif default: nla_nest_cancel(skb, nest_ent); continue; } if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, br_timer_value(&ent->timer))) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } nla_nest_end(skb, nest_ent); } nla_nest_end(skb, nest); return 0; out_cancel_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int __mdb_fill_info(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *p) { bool dump_srcs_mode = false; struct timer_list *mtimer; struct nlattr *nest_ent; struct br_mdb_entry e; u8 flags = 0; int ifindex; memset(&e, 0, sizeof(e)); if (p) { ifindex = p->key.port->dev->ifindex; mtimer = &p->timer; flags = p->flags; } else { ifindex = mp->br->dev->ifindex; mtimer = &mp->timer; } __mdb_entry_fill_flags(&e, flags); e.ifindex = ifindex; e.vid = mp->addr.vid; if (mp->addr.proto == htons(ETH_P_IP)) { e.addr.u.ip4 = mp->addr.dst.ip4; #if IS_ENABLED(CONFIG_IPV6) } else if (mp->addr.proto == htons(ETH_P_IPV6)) { e.addr.u.ip6 = mp->addr.dst.ip6; #endif } else { ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); e.state = MDB_PERMANENT; } e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); if (!nest_ent) return -EMSGSIZE; if (nla_put_nohdr(skb, sizeof(e), &e) || nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, br_timer_value(mtimer))) goto nest_err; switch (mp->addr.proto) { case htons(ETH_P_IP): dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_igmp_version == 3); if (mp->addr.src.ip4) { if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE, mp->addr.src.ip4)) goto nest_err; break; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_mld_version == 2); if (!ipv6_addr_any(&mp->addr.src.ip6)) { if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE, &mp->addr.src.ip6)) goto nest_err; break; } break; #endif default: ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); } if (p) { if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol)) goto nest_err; if (dump_srcs_mode && (__mdb_fill_srcs(skb, p) || nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) goto nest_err; } nla_nest_end(skb, nest_ent); return 0; nest_err: nla_nest_cancel(skb, nest_ent); return -EMSGSIZE; } static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2]; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct nlattr *nest, *nest2; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) return -EMSGSIZE; hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; if (idx < s_idx) goto skip; nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!nest2) { err = -EMSGSIZE; break; } if (!s_pidx && mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) { nla_nest_cancel(skb, nest2); break; } } for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; pp = &p->next) { if (!p->key.port) continue; if (pidx < s_pidx) goto skip_pg; err = __mdb_fill_info(skb, mp, p); if (err) { nla_nest_end(skb, nest2); goto out; } skip_pg: pidx++; } pidx = 0; s_pidx = 0; nla_nest_end(skb, nest2); skip: idx++; } out: cb->args[1] = idx; cb->args[2] = pidx; nla_nest_end(skb, nest); return err; } int br_mdb_dump(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct net_bridge *br = netdev_priv(dev); struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETMDB, sizeof(*bpm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->ifindex = dev->ifindex; rcu_read_lock(); err = br_mdb_fill_info(skb, cb, dev); if (err) goto out; err = br_rports_fill_info(skb, &br->multicast_ctx); if (err) goto out; out: rcu_read_unlock(); nlmsg_end(skb, nlh); return err; } static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { struct nlmsghdr *nlh; struct br_port_msg *bpm; struct nlattr *nest, *nest2; nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) goto cancel; nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (nest2 == NULL) goto end; if (__mdb_fill_info(skb, mp, pg)) goto end; nla_nest_end(skb, nest2); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; end: nla_nest_end(skb, nest); cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t rtnl_mdb_nlmsg_pg_size(const struct net_bridge_port_group *pg) { struct net_bridge_group_src *ent; size_t nlmsg_size, addr_size = 0; /* MDBA_MDB_ENTRY_INFO */ nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) + /* MDBA_MDB_EATTR_TIMER */ nla_total_size(sizeof(u32)); if (!pg) goto out; /* MDBA_MDB_EATTR_RTPROT */ nlmsg_size += nla_total_size(sizeof(u8)); switch (pg->key.addr.proto) { case htons(ETH_P_IP): /* MDBA_MDB_EATTR_SOURCE */ if (pg->key.addr.src.ip4) nlmsg_size += nla_total_size(sizeof(__be32)); if (pg->key.port->br->multicast_ctx.multicast_igmp_version == 2) goto out; addr_size = sizeof(__be32); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): /* MDBA_MDB_EATTR_SOURCE */ if (!ipv6_addr_any(&pg->key.addr.src.ip6)) nlmsg_size += nla_total_size(sizeof(struct in6_addr)); if (pg->key.port->br->multicast_ctx.multicast_mld_version == 1) goto out; addr_size = sizeof(struct in6_addr); break; #endif } /* MDBA_MDB_EATTR_GROUP_MODE */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_SRC_LIST nested attr */ if (!hlist_empty(&pg->src_list)) nlmsg_size += nla_total_size(0); hlist_for_each_entry(ent, &pg->src_list, node) { /* MDBA_MDB_SRCLIST_ENTRY nested attr + * MDBA_MDB_SRCATTR_ADDRESS + MDBA_MDB_SRCATTR_TIMER */ nlmsg_size += nla_total_size(0) + nla_total_size(addr_size) + nla_total_size(sizeof(u32)); } out: return nlmsg_size; } static size_t rtnl_mdb_nlmsg_size(const struct net_bridge_port_group *pg) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0) + /* Port group entry */ rtnl_mdb_nlmsg_pg_size(pg); } void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; br_switchdev_mdb_notify(dev, mp, pg, type); skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC); if (!skb) goto errout; err = nlmsg_populate_mdb_fill(skb, dev, mp, pg, type); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static int nlmsg_populate_rtr_fill(struct sk_buff *skb, struct net_device *dev, int ifindex, u16 vid, u32 pid, u32 seq, int type, unsigned int flags) { struct nlattr *nest, *port_nest; struct br_port_msg *bpm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (!nest) goto cancel; port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto end; if (nla_put_nohdr(skb, sizeof(u32), &ifindex)) { nla_nest_cancel(skb, port_nest); goto end; } if (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid)) { nla_nest_cancel(skb, port_nest); goto end; } nla_nest_end(skb, port_nest); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; end: nla_nest_end(skb, nest); cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t rtnl_rtr_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + nla_total_size(sizeof(__u32)) + nla_total_size(sizeof(u16)); } void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; int ifindex; u16 vid; ifindex = pmctx ? pmctx->port->dev->ifindex : 0; vid = pmctx && br_multicast_port_ctx_is_vlan(pmctx) ? pmctx->vlan->vid : 0; skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = nlmsg_populate_rtr_fill(skb, dev, ifindex, vid, 0, 0, type, NTF_SELF); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static const struct nla_policy br_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static const struct nla_policy br_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(br_mdbe_src_list_entry_pol), }; static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto, struct netlink_ext_ack *extack) { switch (proto) { case htons(ETH_P_IP): if (nla_len(attr) != sizeof(struct in_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); return false; } if (ipv4_is_multicast(nla_get_in_addr(attr))) { NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr src; if (nla_len(attr) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); return false; } src = nla_get_in6_addr(attr); if (ipv6_addr_is_multicast(&src)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } break; } #endif default: NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); return false; } return true; } static struct net_bridge_mcast * __br_mdb_choose_context(struct net_bridge *br, const struct br_mdb_entry *entry, struct netlink_ext_ack *extack) { struct net_bridge_mcast *brmctx = NULL; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { brmctx = &br->multicast_ctx; goto out; } if (!entry->vid) { NL_SET_ERR_MSG_MOD(extack, "Cannot add an entry without a vlan when vlan snooping is enabled"); goto out; } v = br_vlan_find(br_vlan_group(br), entry->vid); if (!v) { NL_SET_ERR_MSG_MOD(extack, "Vlan is not configured"); goto out; } if (br_multicast_ctx_vlan_global_disabled(&v->br_mcast_ctx)) { NL_SET_ERR_MSG_MOD(extack, "Vlan's multicast processing is disabled"); goto out; } brmctx = &v->br_mcast_ctx; out: return brmctx; } static int br_mdb_replace_group_sg(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, unsigned char flags) { unsigned long now = jiffies; pg->flags = flags; pg->rt_protocol = cfg->rt_protocol; if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&pg->timer, now + brmctx->multicast_membership_interval); else del_timer(&pg->timer); br_mdb_notify(cfg->br->dev, mp, pg, RTM_NEWMDB); return 0; } static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; unsigned long now = jiffies; for (pp = &mp->ports; (p = mlock_dereference(*pp, cfg->br)) != NULL; pp = &p->next) { if (p->key.port == cfg->p) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "(S, G) group is already joined by port"); return -EEXIST; } return br_mdb_replace_group_sg(cfg, mp, p, brmctx, flags); } if ((unsigned long)p->key.port < (unsigned long)cfg->p) break; } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, MCAST_INCLUDE, cfg->rt_protocol, extack); if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); br_mdb_notify(cfg->br->dev, mp, p, RTM_NEWMDB); /* All of (*, G) EXCLUDE ports need to be added to the new (S, G) for * proper replication. */ if (br_multicast_should_handle_mode(brmctx, cfg->group.proto)) { struct net_bridge_mdb_entry *star_mp; struct br_ip star_group; star_group = p->key.addr; memset(&star_group.src, 0, sizeof(star_group.src)); star_mp = br_mdb_ip_get(cfg->br, &star_group); if (star_mp) br_multicast_sg_add_exclude_ports(star_mp, p); } return 0; } static int br_mdb_add_group_src_fwd(const struct br_mdb_config *cfg, struct br_ip *src_ip, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { struct net_bridge_mdb_entry *sgmp; struct br_mdb_config sg_cfg; struct br_ip sg_ip; u8 flags = 0; sg_ip = cfg->group; sg_ip.src = src_ip->src; sgmp = br_multicast_new_group(cfg->br, &sg_ip); if (IS_ERR(sgmp)) { NL_SET_ERR_MSG_MOD(extack, "Failed to add (S, G) MDB entry"); return PTR_ERR(sgmp); } if (cfg->entry->state == MDB_PERMANENT) flags |= MDB_PG_FLAGS_PERMANENT; if (cfg->filter_mode == MCAST_EXCLUDE) flags |= MDB_PG_FLAGS_BLOCKED; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.br = cfg->br; sg_cfg.p = cfg->p; sg_cfg.entry = cfg->entry; sg_cfg.group = sg_ip; sg_cfg.src_entry = true; sg_cfg.filter_mode = MCAST_INCLUDE; sg_cfg.rt_protocol = cfg->rt_protocol; sg_cfg.nlflags = cfg->nlflags; return br_mdb_add_group_sg(&sg_cfg, sgmp, brmctx, flags, extack); } static int br_mdb_add_group_src(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct br_mdb_src_entry *src, struct netlink_ext_ack *extack) { struct net_bridge_group_src *ent; unsigned long now = jiffies; int err; ent = br_multicast_find_group_src(pg, &src->addr); if (!ent) { ent = br_multicast_new_group_src(pg, &src->addr); if (!ent) { NL_SET_ERR_MSG_MOD(extack, "Failed to add new source entry"); return -ENOSPC; } } else if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); return -EEXIST; } if (cfg->filter_mode == MCAST_INCLUDE && cfg->entry->state == MDB_TEMPORARY) mod_timer(&ent->timer, now + br_multicast_gmi(brmctx)); else del_timer(&ent->timer); /* Install a (S, G) forwarding entry for the source. */ err = br_mdb_add_group_src_fwd(cfg, &src->addr, brmctx, extack); if (err) goto err_del_sg; ent->flags = BR_SGRP_F_INSTALLED | BR_SGRP_F_USER_ADDED; return 0; err_del_sg: __br_multicast_del_group_src(ent); return err; } static void br_mdb_del_group_src(struct net_bridge_port_group *pg, struct br_mdb_src_entry *src) { struct net_bridge_group_src *ent; ent = br_multicast_find_group_src(pg, &src->addr); if (WARN_ON_ONCE(!ent)) return; br_multicast_del_group_src(ent, false); } static int br_mdb_add_group_srcs(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { int i, err; for (i = 0; i < cfg->num_src_entries; i++) { err = br_mdb_add_group_src(cfg, pg, brmctx, &cfg->src_entries[i], extack); if (err) goto err_del_group_srcs; } return 0; err_del_group_srcs: for (i--; i >= 0; i--) br_mdb_del_group_src(pg, &cfg->src_entries[i]); return err; } static int br_mdb_replace_group_srcs(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { struct net_bridge_group_src *ent; struct hlist_node *tmp; int err; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; err = br_mdb_add_group_srcs(cfg, pg, brmctx, extack); if (err) goto err_clear_delete; hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) { if (ent->flags & BR_SGRP_F_DELETE) br_multicast_del_group_src(ent, false); } return 0; err_clear_delete: hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_DELETE; return err; } static int br_mdb_replace_group_star_g(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { unsigned long now = jiffies; int err; err = br_mdb_replace_group_srcs(cfg, pg, brmctx, extack); if (err) return err; pg->flags = flags; pg->filter_mode = cfg->filter_mode; pg->rt_protocol = cfg->rt_protocol; if (!(flags & MDB_PG_FLAGS_PERMANENT) && cfg->filter_mode == MCAST_EXCLUDE) mod_timer(&pg->timer, now + brmctx->multicast_membership_interval); else del_timer(&pg->timer); br_mdb_notify(cfg->br->dev, mp, pg, RTM_NEWMDB); if (br_multicast_should_handle_mode(brmctx, cfg->group.proto)) br_multicast_star_g_handle_mode(pg, cfg->filter_mode); return 0; } static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; unsigned long now = jiffies; int err; for (pp = &mp->ports; (p = mlock_dereference(*pp, cfg->br)) != NULL; pp = &p->next) { if (p->key.port == cfg->p) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "(*, G) group is already joined by port"); return -EEXIST; } return br_mdb_replace_group_star_g(cfg, mp, p, brmctx, flags, extack); } if ((unsigned long)p->key.port < (unsigned long)cfg->p) break; } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, cfg->filter_mode, cfg->rt_protocol, extack); if (unlikely(!p)) return -ENOMEM; err = br_mdb_add_group_srcs(cfg, p, brmctx, extack); if (err) goto err_del_port_group; rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && cfg->filter_mode == MCAST_EXCLUDE) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); br_mdb_notify(cfg->br->dev, mp, p, RTM_NEWMDB); /* If we are adding a new EXCLUDE port group (*, G), it needs to be * also added to all (S, G) entries for proper replication. */ if (br_multicast_should_handle_mode(brmctx, cfg->group.proto) && cfg->filter_mode == MCAST_EXCLUDE) br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE); return 0; err_del_port_group: br_multicast_del_port_group(p); return err; } static int br_mdb_add_group(const struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = cfg->entry; struct net_bridge_port *port = cfg->p; struct net_bridge_mdb_entry *mp; struct net_bridge *br = cfg->br; struct net_bridge_mcast *brmctx; struct br_ip group = cfg->group; unsigned char flags = 0; brmctx = __br_mdb_choose_context(br, entry, extack); if (!brmctx) return -EINVAL; mp = br_multicast_new_group(br, &group); if (IS_ERR(mp)) return PTR_ERR(mp); /* host join */ if (!port) { if (mp->host_joined) { NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; } br_multicast_host_join(brmctx, mp, false); br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB); return 0; } if (entry->state == MDB_PERMANENT) flags |= MDB_PG_FLAGS_PERMANENT; if (br_multicast_is_star_g(&group)) return br_mdb_add_group_star_g(cfg, mp, brmctx, flags, extack); else return br_mdb_add_group_sg(cfg, mp, brmctx, flags, extack); } static int __br_mdb_add(const struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { int ret; spin_lock_bh(&cfg->br->multicast_lock); ret = br_mdb_add_group(cfg, extack); spin_unlock_bh(&cfg->br->multicast_lock); return ret; } static int br_mdb_config_src_entry_init(struct nlattr *src_entry, struct br_mdb_src_entry *src, __be16 proto, struct netlink_ext_ack *extack) { struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; int err; err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, br_mdbe_src_list_entry_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) return -EINVAL; if (!is_valid_mdb_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) return -EINVAL; src->addr.proto = proto; nla_memcpy(&src->addr.src, tb[MDBE_SRCATTR_ADDRESS], nla_len(tb[MDBE_SRCATTR_ADDRESS])); return 0; } static int br_mdb_config_src_list_init(struct nlattr *src_list, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *src_entry; int rem, err; int i = 0; nla_for_each_nested(src_entry, src_list, rem) cfg->num_src_entries++; if (cfg->num_src_entries >= PG_SRC_ENT_LIMIT) { NL_SET_ERR_MSG_FMT_MOD(extack, "Exceeded maximum number of source entries (%u)", PG_SRC_ENT_LIMIT - 1); return -EINVAL; } cfg->src_entries = kcalloc(cfg->num_src_entries, sizeof(struct br_mdb_src_entry), GFP_KERNEL); if (!cfg->src_entries) return -ENOMEM; nla_for_each_nested(src_entry, src_list, rem) { err = br_mdb_config_src_entry_init(src_entry, &cfg->src_entries[i], cfg->entry->addr.proto, extack); if (err) goto err_src_entry_init; i++; } return 0; err_src_entry_init: kfree(cfg->src_entries); return err; } static void br_mdb_config_src_list_fini(struct br_mdb_config *cfg) { kfree(cfg->src_entries); } static int br_mdb_config_attrs_init(struct nlattr *set_attrs, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1]; int err; err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX, set_attrs, br_mdbe_attrs_pol, extack); if (err) return err; if (mdb_attrs[MDBE_ATTR_SOURCE] && !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE], cfg->entry->addr.proto, extack)) return -EINVAL; __mdb_entry_to_br_ip(cfg->entry, &cfg->group, mdb_attrs); if (mdb_attrs[MDBE_ATTR_GROUP_MODE]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Filter mode cannot be set for host groups"); return -EINVAL; } if (!br_multicast_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); return -EINVAL; } cfg->filter_mode = nla_get_u8(mdb_attrs[MDBE_ATTR_GROUP_MODE]); } else { cfg->filter_mode = MCAST_EXCLUDE; } if (mdb_attrs[MDBE_ATTR_SRC_LIST]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set for host groups"); return -EINVAL; } if (!br_multicast_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); return -EINVAL; } if (!mdb_attrs[MDBE_ATTR_GROUP_MODE]) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); return -EINVAL; } err = br_mdb_config_src_list_init(mdb_attrs[MDBE_ATTR_SRC_LIST], cfg, extack); if (err) return err; } if (!cfg->num_src_entries && cfg->filter_mode == MCAST_INCLUDE) { NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); return -EINVAL; } if (mdb_attrs[MDBE_ATTR_RTPROT]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be set for host groups"); return -EINVAL; } cfg->rt_protocol = nla_get_u8(mdb_attrs[MDBE_ATTR_RTPROT]); } return 0; } static int br_mdb_config_init(struct br_mdb_config *cfg, struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); memset(cfg, 0, sizeof(*cfg)); cfg->filter_mode = MCAST_EXCLUDE; cfg->rt_protocol = RTPROT_STATIC; cfg->nlflags = nlmsg_flags; cfg->br = netdev_priv(dev); if (!netif_running(cfg->br->dev)) { NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running"); return -EINVAL; } if (!br_opt_get(cfg->br, BROPT_MULTICAST_ENABLED)) { NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled"); return -EINVAL; } cfg->entry = nla_data(tb[MDBA_SET_ENTRY]); if (cfg->entry->ifindex != cfg->br->dev->ifindex) { struct net_device *pdev; pdev = __dev_get_by_index(net, cfg->entry->ifindex); if (!pdev) { NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist"); return -ENODEV; } cfg->p = br_port_get_rtnl(pdev); if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port"); return -EINVAL; } if (cfg->p->br != cfg->br) { NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; } } if (cfg->entry->addr.proto == htons(ETH_P_IP) && ipv4_is_zeronet(cfg->entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address 0.0.0.0 is not allowed"); return -EINVAL; } if (tb[MDBA_SET_ENTRY_ATTRS]) return br_mdb_config_attrs_init(tb[MDBA_SET_ENTRY_ATTRS], cfg, extack); else __mdb_entry_to_br_ip(cfg->entry, &cfg->group, NULL); return 0; } static void br_mdb_config_fini(struct br_mdb_config *cfg) { br_mdb_config_src_list_fini(cfg); } int br_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct br_mdb_config cfg; int err; err = br_mdb_config_init(&cfg, dev, tb, nlmsg_flags, extack); if (err) return err; err = -EINVAL; /* host join errors which can happen before creating the group */ if (!cfg.p && !br_group_is_l2(&cfg.group)) { /* don't allow any flags for host-joined IP groups */ if (cfg.entry->state) { NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups"); goto out; } if (!br_multicast_is_star_g(&cfg.group)) { NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined"); goto out; } } if (br_group_is_l2(&cfg.group) && cfg.entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed"); goto out; } if (cfg.p) { if (cfg.p->state == BR_STATE_DISABLED && cfg.entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state and entry is not permanent"); goto out; } vg = nbp_vlan_group(cfg.p); } else { vg = br_vlan_group(cfg.br); } /* If vlan filtering is enabled and VLAN is not specified * install mdb entry on all vlans configured on the port. */ if (br_vlan_enabled(cfg.br->dev) && vg && cfg.entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { cfg.entry->vid = v->vid; cfg.group.vid = v->vid; err = __br_mdb_add(&cfg, extack); if (err) break; } } else { err = __br_mdb_add(&cfg, extack); } out: br_mdb_config_fini(&cfg); return err; } static int __br_mdb_del(const struct br_mdb_config *cfg) { struct br_mdb_entry *entry = cfg->entry; struct net_bridge *br = cfg->br; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip ip = cfg->group; int err = -EINVAL; spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &ip); if (!mp) goto unlock; /* host leave */ if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) { br_multicast_host_leave(mp, false); err = 0; br_mdb_notify(br->dev, mp, NULL, RTM_DELMDB); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); goto unlock; } for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex) continue; br_multicast_del_pg(mp, p, pp); err = 0; break; } unlock: spin_unlock_bh(&br->multicast_lock); return err; } int br_mdb_del(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct br_mdb_config cfg; int err; err = br_mdb_config_init(&cfg, dev, tb, 0, extack); if (err) return err; if (cfg.p) vg = nbp_vlan_group(cfg.p); else vg = br_vlan_group(cfg.br); /* If vlan filtering is enabled and VLAN is not specified * delete mdb entry on all vlans configured on the port. */ if (br_vlan_enabled(cfg.br->dev) && vg && cfg.entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { cfg.entry->vid = v->vid; cfg.group.vid = v->vid; err = __br_mdb_del(&cfg); } } else { err = __br_mdb_del(&cfg); } br_mdb_config_fini(&cfg); return err; } struct br_mdb_flush_desc { u32 port_ifindex; u16 vid; u8 rt_protocol; u8 state; u8 state_mask; }; static const struct nla_policy br_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT), }; static int br_mdb_flush_desc_init(struct br_mdb_flush_desc *desc, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; desc->port_ifindex = entry->ifindex; desc->vid = entry->vid; desc->state = entry->state; if (!tb[MDBA_SET_ENTRY_ATTRS]) return 0; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_SET_ENTRY_ATTRS], br_mdbe_attrs_del_bulk_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) desc->state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]); if (mdbe_attrs[MDBE_ATTR_RTPROT]) desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); return 0; } static void br_mdb_flush_host(struct net_bridge *br, struct net_bridge_mdb_entry *mp, const struct br_mdb_flush_desc *desc) { u8 state; if (desc->port_ifindex && desc->port_ifindex != br->dev->ifindex) return; if (desc->rt_protocol) return; state = br_group_is_l2(&mp->addr) ? MDB_PERMANENT : 0; if (desc->state_mask && (state & desc->state_mask) != desc->state) return; br_multicast_host_leave(mp, true); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } static void br_mdb_flush_pgs(struct net_bridge *br, struct net_bridge_mdb_entry *mp, const struct br_mdb_flush_desc *desc) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;) { u8 state; if (desc->port_ifindex && desc->port_ifindex != p->key.port->dev->ifindex) { pp = &p->next; continue; } if (desc->rt_protocol && desc->rt_protocol != p->rt_protocol) { pp = &p->next; continue; } state = p->flags & MDB_PG_FLAGS_PERMANENT ? MDB_PERMANENT : 0; if (desc->state_mask && (state & desc->state_mask) != desc->state) { pp = &p->next; continue; } br_multicast_del_pg(mp, p, pp); } } static void br_mdb_flush(struct net_bridge *br, const struct br_mdb_flush_desc *desc) { struct net_bridge_mdb_entry *mp; spin_lock_bh(&br->multicast_lock); /* Safe variant is not needed because entries are removed from the list * upon group timer expiration or bridge deletion. */ hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { if (desc->vid && desc->vid != mp->addr.vid) continue; br_mdb_flush_host(br, mp, desc); br_mdb_flush_pgs(br, mp, desc); } spin_unlock_bh(&br->multicast_lock); } int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct br_mdb_flush_desc desc = {}; int err; err = br_mdb_flush_desc_init(&desc, tb, extack); if (err) return err; br_mdb_flush(br, &desc); return 0; } static const struct nla_policy br_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static int br_mdb_get_parse(struct net_device *dev, struct nlattr *tb[], struct br_ip *group, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; if (!tb[MDBA_GET_ENTRY_ATTRS]) { __mdb_entry_to_br_ip(entry, group, NULL); return 0; } err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_GET_ENTRY_ATTRS], br_mdbe_attrs_get_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_SOURCE] && !is_valid_mdb_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; __mdb_entry_to_br_ip(entry, group, mdbe_attrs); return 0; } static struct sk_buff * br_mdb_get_reply_alloc(const struct net_bridge_mdb_entry *mp) { struct net_bridge_port_group *pg; size_t nlmsg_size; nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0); if (mp->host_joined) nlmsg_size += rtnl_mdb_nlmsg_pg_size(NULL); for (pg = mlock_dereference(mp->ports, mp->br); pg; pg = mlock_dereference(pg->next, mp->br)) nlmsg_size += rtnl_mdb_nlmsg_pg_size(pg); return nlmsg_new(nlmsg_size, GFP_ATOMIC); } static int br_mdb_get_reply_fill(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, u32 portid, u32 seq) { struct nlattr *mdb_nest, *mdb_entry_nest; struct net_bridge_port_group *pg; struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = mp->br->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) { err = -EMSGSIZE; goto cancel; } mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) { err = -EMSGSIZE; goto cancel; } if (mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) goto cancel; } for (pg = mlock_dereference(mp->ports, mp->br); pg; pg = mlock_dereference(pg->next, mp->br)) { err = __mdb_fill_info(skb, mp, pg); if (err) goto cancel; } nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return err; } int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct sk_buff *skb; struct br_ip group; int err; err = br_mdb_get_parse(dev, tb, &group, extack); if (err) return err; /* Hold the multicast lock to ensure that the MDB entry does not change * between the time the reply size is determined and when the reply is * filled in. */ spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &group); if (!mp) { NL_SET_ERR_MSG_MOD(extack, "MDB entry not found"); err = -ENOENT; goto unlock; } skb = br_mdb_get_reply_alloc(mp); if (!skb) { err = -ENOMEM; goto unlock; } err = br_mdb_get_reply_fill(skb, mp, portid, seq); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply"); goto free; } spin_unlock_bh(&br->multicast_lock); return rtnl_unicast(skb, dev_net(dev), portid); free: kfree_skb(skb); unlock: spin_unlock_bh(&br->multicast_lock); return err; } |
| 1 1 1482 2 140 1480 1483 1483 1477 1478 1482 1481 1481 1481 1477 1478 197 197 192 191 62 195 195 189 4 6 191 55 71 3 91 110 163 155 5 90 176 85 77 4 2 4 3 10 239 238 237 232 239 7 209 75 70 38 36 44 248 1 242 247 2 240 240 3 3 22 199 78 196 175 167 1 1 2 1 1 1 2 1 1 2 1 1 8 1 1 253 1 1 1 1 220 7 4 1 1 1 1 261 1 255 7 19 1 8 4 6 2 4 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cache.h> #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <net/ip.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); void *ipt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ipt, IPT); } EXPORT_SYMBOL_GPL(ipt_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip_packet_match(const struct iphdr *ip, const char *indev, const char *outdev, const struct ipt_ip *ipinfo, int isfrag) { unsigned long ret; if (NF_INVF(ipinfo, IPT_INV_SRCIP, (ip->saddr & ipinfo->smsk.s_addr) != ipinfo->src.s_addr) || NF_INVF(ipinfo, IPT_INV_DSTIP, (ip->daddr & ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr)) return false; ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_OUT, ret != 0)) return false; /* Check specific protocol */ if (ipinfo->proto && NF_INVF(ipinfo, IPT_INV_PROTO, ip->protocol != ipinfo->proto)) return false; /* If we have a fragment rule but the packet is not a fragment * then we return zero */ if (NF_INVF(ipinfo, IPT_INV_FRAG, (ipinfo->flags & IPT_F_FRAG) && !isfrag)) return false; return true; } static bool ip_checkentry(const struct ipt_ip *ip) { if (ip->flags & ~IPT_F_MASK) return false; if (ip->invflags & ~IPT_INV_MASK) return false; return true; } static unsigned int ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } /* Performance critical */ static inline struct ipt_entry * get_entry(const void *base, unsigned int offset) { return (struct ipt_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; return e->target_offset == sizeof(struct ipt_entry) && memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; } /* for const-correctness */ static inline const struct xt_entry_target * ipt_get_target_c(const struct ipt_entry *e) { return ipt_get_target((struct ipt_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP_TRACE_COMMENT_RULE, NF_IP_TRACE_COMMENT_RETURN, NF_IP_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP_TRACE_COMMENT_RULE] = "rule", [NF_IP_TRACE_COMMENT_RETURN] = "return", [NF_IP_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = 4, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ipt_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] : comments[NF_IP_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ipt_entry *e) { const struct ipt_entry *root; const char *hookname, *chainname, *comment; const struct ipt_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); if (!ip_packet_match(ip, indev, outdev, &e->ip, acpar.fragoff)) { no_match: e = ipt_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ipt_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); } else { e = jumpstack[--stackidx]; e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) { /* Target might have changed stuff. */ ip = ip_hdr(skb); e = ipt_next_entry(e); } else { /* Verdict */ break; } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ipt_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV4; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ip->proto, ip->invflags & IPT_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ipt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV4, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ip.proto, e->ip.invflags & IPT_INV_PROTO); } static int find_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ip; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV4; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ipt_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ipt_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || (unsigned char *)e + sizeof(struct ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ipt_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ipt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ipt_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV4; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ipt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ipt_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ipt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; /* macro does multi eval of i */ } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ipt_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ipt_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ipt_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ipt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ipt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ipt_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ipt_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ipt_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ipt_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET); #endif t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET); #endif return ret; } static int get_entries(struct net *net, struct ipt_get_entries __user *uptr, const int *len) { int ret; struct ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ipt_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ipt_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ipt_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ipt_entry entries[]; }; static int compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ipt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ipt_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ipt_entry); *size -= sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ipt_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ipt_ip *ip, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ipt_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ipt_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ipt_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ip, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ipt_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ipt_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ipt_entry); *size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ipt_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ipt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ipt_entry *iter0; struct ipt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET); ret = xt_compat_init_offsets(AF_INET, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. * entry1/newinfo contains a 64bit ruleset that looks exactly as * generated by 64bit userspace. * * Call standard translate_table() to validate all hook_entrys, * underflows, check for loops, etc. */ xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ipt_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ipt_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ipt_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, int *len) { int ret; struct compat_ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET); return ret; } #endif static int do_ipt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IPT_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IPT_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IPT_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET, rev.name, rev.revision, target, &ret), "ipt_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ipt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ipt_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ipt_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } /* No template? No need to do anything. This is used by 'nat' table, it registers * with the nat core instead of the netfilter core. */ if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ipt_unregister_table(net, new_table); return ret; } void ipt_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ipt_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); } static struct xt_target ipt_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV4, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ipt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, }, }; static struct nf_sockopt_ops ipt_sockopts = { .pf = PF_INET, .set_optmin = IPT_BASE_CTL, .set_optmax = IPT_SO_SET_MAX+1, .set = do_ipt_set_ctl, .get_optmin = IPT_BASE_CTL, .get_optmax = IPT_SO_GET_MAX+1, .get = do_ipt_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV4); } static void __net_exit ip_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV4); } static struct pernet_operations ip_tables_net_ops = { .init = ip_tables_net_init, .exit = ip_tables_net_exit, }; static int __init ip_tables_init(void) { int ret; ret = register_pernet_subsys(&ip_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); err2: unregister_pernet_subsys(&ip_tables_net_ops); err1: return ret; } static void __exit ip_tables_fini(void) { nf_unregister_sockopt(&ipt_sockopts); xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); unregister_pernet_subsys(&ip_tables_net_ops); } EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); module_exit(ip_tables_fini); |
| 20 20 19 717 719 716 6 6 6 6 6 6 6 5 6 6 12 17 4 13 152 151 1990 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 5 2 5 5 5 2 2 1 1 8 8 3 8 3 3 5 4 6 4 2 2 2 6 2 2 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 | /* * VMAC: Message Authentication Code using Universal Hashing * * Reference: https://tools.ietf.org/html/draft-krovetz-vmac-01 * * Copyright (c) 2009, Intel Corporation. * Copyright (c) 2018, Google Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. * * This program is distributed in the hope it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., 59 Temple * Place - Suite 330, Boston, MA 02111-1307 USA. */ /* * Derived from: * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai. * This implementation is herby placed in the public domain. * The authors offers no warranty. Use at your own risk. * Last modified: 17 APR 08, 1700 PDT */ #include <asm/unaligned.h> #include <linux/init.h> #include <linux/types.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <asm/byteorder.h> #include <crypto/scatterwalk.h> #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> /* * User definable settings. */ #define VMAC_TAG_LEN 64 #define VMAC_KEY_SIZE 128/* Must be 128, 192 or 256 */ #define VMAC_KEY_LEN (VMAC_KEY_SIZE/8) #define VMAC_NHBYTES 128/* Must 2^i for any 3 < i < 13 Standard = 128*/ #define VMAC_NONCEBYTES 16 /* per-transform (per-key) context */ struct vmac_tfm_ctx { struct crypto_cipher *cipher; u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)]; u64 polykey[2*VMAC_TAG_LEN/64]; u64 l3key[2*VMAC_TAG_LEN/64]; }; /* per-request context */ struct vmac_desc_ctx { union { u8 partial[VMAC_NHBYTES]; /* partial block */ __le64 partial_words[VMAC_NHBYTES / 8]; }; unsigned int partial_size; /* size of the partial block */ bool first_block_processed; u64 polytmp[2*VMAC_TAG_LEN/64]; /* running total of L2-hash */ union { u8 bytes[VMAC_NONCEBYTES]; __be64 pads[VMAC_NONCEBYTES / 8]; } nonce; unsigned int nonce_size; /* nonce bytes filled so far */ }; /* * Constants and masks */ #define UINT64_C(x) x##ULL static const u64 p64 = UINT64_C(0xfffffffffffffeff); /* 2^64 - 257 prime */ static const u64 m62 = UINT64_C(0x3fffffffffffffff); /* 62-bit mask */ static const u64 m63 = UINT64_C(0x7fffffffffffffff); /* 63-bit mask */ static const u64 m64 = UINT64_C(0xffffffffffffffff); /* 64-bit mask */ static const u64 mpoly = UINT64_C(0x1fffffff1fffffff); /* Poly key mask */ #define pe64_to_cpup le64_to_cpup /* Prefer little endian */ #ifdef __LITTLE_ENDIAN #define INDEX_HIGH 1 #define INDEX_LOW 0 #else #define INDEX_HIGH 0 #define INDEX_LOW 1 #endif /* * The following routines are used in this implementation. They are * written via macros to simulate zero-overhead call-by-reference. * * MUL64: 64x64->128-bit multiplication * PMUL64: assumes top bits cleared on inputs * ADD128: 128x128->128-bit addition */ #define ADD128(rh, rl, ih, il) \ do { \ u64 _il = (il); \ (rl) += (_il); \ if ((rl) < (_il)) \ (rh)++; \ (rh) += (ih); \ } while (0) #define MUL32(i1, i2) ((u64)(u32)(i1)*(u32)(i2)) #define PMUL64(rh, rl, i1, i2) /* Assumes m doesn't overflow */ \ do { \ u64 _i1 = (i1), _i2 = (i2); \ u64 m = MUL32(_i1, _i2>>32) + MUL32(_i1>>32, _i2); \ rh = MUL32(_i1>>32, _i2>>32); \ rl = MUL32(_i1, _i2); \ ADD128(rh, rl, (m >> 32), (m << 32)); \ } while (0) #define MUL64(rh, rl, i1, i2) \ do { \ u64 _i1 = (i1), _i2 = (i2); \ u64 m1 = MUL32(_i1, _i2>>32); \ u64 m2 = MUL32(_i1>>32, _i2); \ rh = MUL32(_i1>>32, _i2>>32); \ rl = MUL32(_i1, _i2); \ ADD128(rh, rl, (m1 >> 32), (m1 << 32)); \ ADD128(rh, rl, (m2 >> 32), (m2 << 32)); \ } while (0) /* * For highest performance the L1 NH and L2 polynomial hashes should be * carefully implemented to take advantage of one's target architecture. * Here these two hash functions are defined multiple time; once for * 64-bit architectures, once for 32-bit SSE2 architectures, and once * for the rest (32-bit) architectures. * For each, nh_16 *must* be defined (works on multiples of 16 bytes). * Optionally, nh_vmac_nhbytes can be defined (for multiples of * VMAC_NHBYTES), and nh_16_2 and nh_vmac_nhbytes_2 (versions that do two * NH computations at once). */ #ifdef CONFIG_64BIT #define nh_16(mp, kp, nw, rh, rl) \ do { \ int i; u64 th, tl; \ rh = rl = 0; \ for (i = 0; i < nw; i += 2) { \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ ADD128(rh, rl, th, tl); \ } \ } while (0) #define nh_16_2(mp, kp, nw, rh, rl, rh1, rl1) \ do { \ int i; u64 th, tl; \ rh1 = rl1 = rh = rl = 0; \ for (i = 0; i < nw; i += 2) { \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i+2], \ pe64_to_cpup((mp)+i+1)+(kp)[i+3]); \ ADD128(rh1, rl1, th, tl); \ } \ } while (0) #if (VMAC_NHBYTES >= 64) /* These versions do 64-bytes of message at a time */ #define nh_vmac_nhbytes(mp, kp, nw, rh, rl) \ do { \ int i; u64 th, tl; \ rh = rl = 0; \ for (i = 0; i < nw; i += 8) { \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+2], \ pe64_to_cpup((mp)+i+3)+(kp)[i+3]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+4], \ pe64_to_cpup((mp)+i+5)+(kp)[i+5]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+6], \ pe64_to_cpup((mp)+i+7)+(kp)[i+7]); \ ADD128(rh, rl, th, tl); \ } \ } while (0) #define nh_vmac_nhbytes_2(mp, kp, nw, rh, rl, rh1, rl1) \ do { \ int i; u64 th, tl; \ rh1 = rl1 = rh = rl = 0; \ for (i = 0; i < nw; i += 8) { \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i+2], \ pe64_to_cpup((mp)+i+1)+(kp)[i+3]); \ ADD128(rh1, rl1, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+2], \ pe64_to_cpup((mp)+i+3)+(kp)[i+3]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+4], \ pe64_to_cpup((mp)+i+3)+(kp)[i+5]); \ ADD128(rh1, rl1, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+4], \ pe64_to_cpup((mp)+i+5)+(kp)[i+5]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+6], \ pe64_to_cpup((mp)+i+5)+(kp)[i+7]); \ ADD128(rh1, rl1, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+6], \ pe64_to_cpup((mp)+i+7)+(kp)[i+7]); \ ADD128(rh, rl, th, tl); \ MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+8], \ pe64_to_cpup((mp)+i+7)+(kp)[i+9]); \ ADD128(rh1, rl1, th, tl); \ } \ } while (0) #endif #define poly_step(ah, al, kh, kl, mh, ml) \ do { \ u64 t1h, t1l, t2h, t2l, t3h, t3l, z = 0; \ /* compute ab*cd, put bd into result registers */ \ PMUL64(t3h, t3l, al, kh); \ PMUL64(t2h, t2l, ah, kl); \ PMUL64(t1h, t1l, ah, 2*kh); \ PMUL64(ah, al, al, kl); \ /* add 2 * ac to result */ \ ADD128(ah, al, t1h, t1l); \ /* add together ad + bc */ \ ADD128(t2h, t2l, t3h, t3l); \ /* now (ah,al), (t2l,2*t2h) need summing */ \ /* first add the high registers, carrying into t2h */ \ ADD128(t2h, ah, z, t2l); \ /* double t2h and add top bit of ah */ \ t2h = 2 * t2h + (ah >> 63); \ ah &= m63; \ /* now add the low registers */ \ ADD128(ah, al, mh, ml); \ ADD128(ah, al, z, t2h); \ } while (0) #else /* ! CONFIG_64BIT */ #ifndef nh_16 #define nh_16(mp, kp, nw, rh, rl) \ do { \ u64 t1, t2, m1, m2, t; \ int i; \ rh = rl = t = 0; \ for (i = 0; i < nw; i += 2) { \ t1 = pe64_to_cpup(mp+i) + kp[i]; \ t2 = pe64_to_cpup(mp+i+1) + kp[i+1]; \ m2 = MUL32(t1 >> 32, t2); \ m1 = MUL32(t1, t2 >> 32); \ ADD128(rh, rl, MUL32(t1 >> 32, t2 >> 32), \ MUL32(t1, t2)); \ rh += (u64)(u32)(m1 >> 32) \ + (u32)(m2 >> 32); \ t += (u64)(u32)m1 + (u32)m2; \ } \ ADD128(rh, rl, (t >> 32), (t << 32)); \ } while (0) #endif static void poly_step_func(u64 *ahi, u64 *alo, const u64 *kh, const u64 *kl, const u64 *mh, const u64 *ml) { #define a0 (*(((u32 *)alo)+INDEX_LOW)) #define a1 (*(((u32 *)alo)+INDEX_HIGH)) #define a2 (*(((u32 *)ahi)+INDEX_LOW)) #define a3 (*(((u32 *)ahi)+INDEX_HIGH)) #define k0 (*(((u32 *)kl)+INDEX_LOW)) #define k1 (*(((u32 *)kl)+INDEX_HIGH)) #define k2 (*(((u32 *)kh)+INDEX_LOW)) #define k3 (*(((u32 *)kh)+INDEX_HIGH)) u64 p, q, t; u32 t2; p = MUL32(a3, k3); p += p; p += *(u64 *)mh; p += MUL32(a0, k2); p += MUL32(a1, k1); p += MUL32(a2, k0); t = (u32)(p); p >>= 32; p += MUL32(a0, k3); p += MUL32(a1, k2); p += MUL32(a2, k1); p += MUL32(a3, k0); t |= ((u64)((u32)p & 0x7fffffff)) << 32; p >>= 31; p += (u64)(((u32 *)ml)[INDEX_LOW]); p += MUL32(a0, k0); q = MUL32(a1, k3); q += MUL32(a2, k2); q += MUL32(a3, k1); q += q; p += q; t2 = (u32)(p); p >>= 32; p += (u64)(((u32 *)ml)[INDEX_HIGH]); p += MUL32(a0, k1); p += MUL32(a1, k0); q = MUL32(a2, k3); q += MUL32(a3, k2); q += q; p += q; *(u64 *)(alo) = (p << 32) | t2; p >>= 32; *(u64 *)(ahi) = p + t; #undef a0 #undef a1 #undef a2 #undef a3 #undef k0 #undef k1 #undef k2 #undef k3 } #define poly_step(ah, al, kh, kl, mh, ml) \ poly_step_func(&(ah), &(al), &(kh), &(kl), &(mh), &(ml)) #endif /* end of specialized NH and poly definitions */ /* At least nh_16 is defined. Defined others as needed here */ #ifndef nh_16_2 #define nh_16_2(mp, kp, nw, rh, rl, rh2, rl2) \ do { \ nh_16(mp, kp, nw, rh, rl); \ nh_16(mp, ((kp)+2), nw, rh2, rl2); \ } while (0) #endif #ifndef nh_vmac_nhbytes #define nh_vmac_nhbytes(mp, kp, nw, rh, rl) \ nh_16(mp, kp, nw, rh, rl) #endif #ifndef nh_vmac_nhbytes_2 #define nh_vmac_nhbytes_2(mp, kp, nw, rh, rl, rh2, rl2) \ do { \ nh_vmac_nhbytes(mp, kp, nw, rh, rl); \ nh_vmac_nhbytes(mp, ((kp)+2), nw, rh2, rl2); \ } while (0) #endif static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len) { u64 rh, rl, t, z = 0; /* fully reduce (p1,p2)+(len,0) mod p127 */ t = p1 >> 63; p1 &= m63; ADD128(p1, p2, len, t); /* At this point, (p1,p2) is at most 2^127+(len<<64) */ t = (p1 > m63) + ((p1 == m63) && (p2 == m64)); ADD128(p1, p2, z, t); p1 &= m63; /* compute (p1,p2)/(2^64-2^32) and (p1,p2)%(2^64-2^32) */ t = p1 + (p2 >> 32); t += (t >> 32); t += (u32)t > 0xfffffffeu; p1 += (t >> 32); p2 += (p1 << 32); /* compute (p1+k1)%p64 and (p2+k2)%p64 */ p1 += k1; p1 += (0 - (p1 < k1)) & 257; p2 += k2; p2 += (0 - (p2 < k2)) & 257; /* compute (p1+k1)*(p2+k2)%p64 */ MUL64(rh, rl, p1, p2); t = rh >> 56; ADD128(t, rl, z, rh); rh <<= 8; ADD128(t, rl, z, rh); t += t << 8; rl += t; rl += (0 - (rl < t)) & 257; rl += (0 - (rl > p64-1)) & 257; return rl; } /* L1 and L2-hash one or more VMAC_NHBYTES-byte blocks */ static void vhash_blocks(const struct vmac_tfm_ctx *tctx, struct vmac_desc_ctx *dctx, const __le64 *mptr, unsigned int blocks) { const u64 *kptr = tctx->nhkey; const u64 pkh = tctx->polykey[0]; const u64 pkl = tctx->polykey[1]; u64 ch = dctx->polytmp[0]; u64 cl = dctx->polytmp[1]; u64 rh, rl; if (!dctx->first_block_processed) { dctx->first_block_processed = true; nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); rh &= m62; ADD128(ch, cl, rh, rl); mptr += (VMAC_NHBYTES/sizeof(u64)); blocks--; } while (blocks--) { nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); rh &= m62; poly_step(ch, cl, pkh, pkl, rh, rl); mptr += (VMAC_NHBYTES/sizeof(u64)); } dctx->polytmp[0] = ch; dctx->polytmp[1] = cl; } static int vmac_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct vmac_tfm_ctx *tctx = crypto_shash_ctx(tfm); __be64 out[2]; u8 in[16] = { 0 }; unsigned int i; int err; if (keylen != VMAC_KEY_LEN) return -EINVAL; err = crypto_cipher_setkey(tctx->cipher, key, keylen); if (err) return err; /* Fill nh key */ in[0] = 0x80; for (i = 0; i < ARRAY_SIZE(tctx->nhkey); i += 2) { crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); tctx->nhkey[i] = be64_to_cpu(out[0]); tctx->nhkey[i+1] = be64_to_cpu(out[1]); in[15]++; } /* Fill poly key */ in[0] = 0xC0; in[15] = 0; for (i = 0; i < ARRAY_SIZE(tctx->polykey); i += 2) { crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); tctx->polykey[i] = be64_to_cpu(out[0]) & mpoly; tctx->polykey[i+1] = be64_to_cpu(out[1]) & mpoly; in[15]++; } /* Fill ip key */ in[0] = 0xE0; in[15] = 0; for (i = 0; i < ARRAY_SIZE(tctx->l3key); i += 2) { do { crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); tctx->l3key[i] = be64_to_cpu(out[0]); tctx->l3key[i+1] = be64_to_cpu(out[1]); in[15]++; } while (tctx->l3key[i] >= p64 || tctx->l3key[i+1] >= p64); } return 0; } static int vmac_init(struct shash_desc *desc) { const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); dctx->partial_size = 0; dctx->first_block_processed = false; memcpy(dctx->polytmp, tctx->polykey, sizeof(dctx->polytmp)); dctx->nonce_size = 0; return 0; } static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len) { const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); unsigned int n; /* Nonce is passed as first VMAC_NONCEBYTES bytes of data */ if (dctx->nonce_size < VMAC_NONCEBYTES) { n = min(len, VMAC_NONCEBYTES - dctx->nonce_size); memcpy(&dctx->nonce.bytes[dctx->nonce_size], p, n); dctx->nonce_size += n; p += n; len -= n; } if (dctx->partial_size) { n = min(len, VMAC_NHBYTES - dctx->partial_size); memcpy(&dctx->partial[dctx->partial_size], p, n); dctx->partial_size += n; p += n; len -= n; if (dctx->partial_size == VMAC_NHBYTES) { vhash_blocks(tctx, dctx, dctx->partial_words, 1); dctx->partial_size = 0; } } if (len >= VMAC_NHBYTES) { n = round_down(len, VMAC_NHBYTES); /* TODO: 'p' may be misaligned here */ vhash_blocks(tctx, dctx, (const __le64 *)p, n / VMAC_NHBYTES); p += n; len -= n; } if (len) { memcpy(dctx->partial, p, len); dctx->partial_size = len; } return 0; } static u64 vhash_final(const struct vmac_tfm_ctx *tctx, struct vmac_desc_ctx *dctx) { unsigned int partial = dctx->partial_size; u64 ch = dctx->polytmp[0]; u64 cl = dctx->polytmp[1]; /* L1 and L2-hash the final block if needed */ if (partial) { /* Zero-pad to next 128-bit boundary */ unsigned int n = round_up(partial, 16); u64 rh, rl; memset(&dctx->partial[partial], 0, n - partial); nh_16(dctx->partial_words, tctx->nhkey, n / 8, rh, rl); rh &= m62; if (dctx->first_block_processed) poly_step(ch, cl, tctx->polykey[0], tctx->polykey[1], rh, rl); else ADD128(ch, cl, rh, rl); } /* L3-hash the 128-bit output of L2-hash */ return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8); } static int vmac_final(struct shash_desc *desc, u8 *out) { const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); int index; u64 hash, pad; if (dctx->nonce_size != VMAC_NONCEBYTES) return -EINVAL; /* * The VMAC specification requires a nonce at least 1 bit shorter than * the block cipher's block length, so we actually only accept a 127-bit * nonce. We define the unused bit to be the first one and require that * it be 0, so the needed prepending of a 0 bit is implicit. */ if (dctx->nonce.bytes[0] & 0x80) return -EINVAL; /* Finish calculating the VHASH of the message */ hash = vhash_final(tctx, dctx); /* Generate pseudorandom pad by encrypting the nonce */ BUILD_BUG_ON(VMAC_NONCEBYTES != 2 * (VMAC_TAG_LEN / 8)); index = dctx->nonce.bytes[VMAC_NONCEBYTES - 1] & 1; dctx->nonce.bytes[VMAC_NONCEBYTES - 1] &= ~1; crypto_cipher_encrypt_one(tctx->cipher, dctx->nonce.bytes, dctx->nonce.bytes); pad = be64_to_cpu(dctx->nonce.pads[index]); /* The VMAC is the sum of VHASH and the pseudorandom pad */ put_unaligned_be64(hash + pad, out); return 0; } static int vmac_init_tfm(struct crypto_tfm *tfm) { struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst); struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); struct crypto_cipher *cipher; cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); tctx->cipher = cipher; return 0; } static void vmac_exit_tfm(struct crypto_tfm *tfm) { struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); crypto_free_cipher(tctx->cipher); } static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); err = -EINVAL; if (alg->cra_blocksize != VMAC_NONCEBYTES) goto err_free_inst; err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct vmac_tfm_ctx); inst->alg.base.cra_init = vmac_init_tfm; inst->alg.base.cra_exit = vmac_exit_tfm; inst->alg.descsize = sizeof(struct vmac_desc_ctx); inst->alg.digestsize = VMAC_TAG_LEN / 8; inst->alg.init = vmac_init; inst->alg.update = vmac_update; inst->alg.final = vmac_final; inst->alg.setkey = vmac_setkey; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template vmac64_tmpl = { .name = "vmac64", .create = vmac_create, .module = THIS_MODULE, }; static int __init vmac_module_init(void) { return crypto_register_template(&vmac64_tmpl); } static void __exit vmac_module_exit(void) { crypto_unregister_template(&vmac64_tmpl); } subsys_initcall(vmac_module_init); module_exit(vmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMAC hash algorithm"); MODULE_ALIAS_CRYPTO("vmac64"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); |
| 2 2 3 2 1 5 5 4 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - operations for initializing and mounting sysfs * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/fs.h> #include <linux/magic.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <net/net_namespace.h> #include "sysfs.h" static struct kernfs_root *sysfs_root; struct kernfs_node *sysfs_root_kn; static int sysfs_get_tree(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; int ret; ret = kernfs_get_tree(fc); if (ret) return ret; if (kfc->new_sb_created) fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE; return 0; } static void sysfs_fs_context_free(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; if (kfc->ns_tag) kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag); kernfs_free_fs_context(fc); kfree(kfc); } static const struct fs_context_operations sysfs_fs_context_ops = { .free = sysfs_fs_context_free, .get_tree = sysfs_get_tree, }; static int sysfs_init_fs_context(struct fs_context *fc) { struct kernfs_fs_context *kfc; struct net *netns; if (!(fc->sb_flags & SB_KERNMOUNT)) { if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return -EPERM; } kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL); if (!kfc) return -ENOMEM; kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); kfc->root = sysfs_root; kfc->magic = SYSFS_MAGIC; fc->fs_private = kfc; fc->ops = &sysfs_fs_context_ops; if (netns) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(netns->user_ns); } fc->global = true; return 0; } static void sysfs_kill_sb(struct super_block *sb) { void *ns = (void *)kernfs_super_ns(sb); kernfs_kill_sb(sb); kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); } static struct file_system_type sysfs_fs_type = { .name = "sysfs", .init_fs_context = sysfs_init_fs_context, .kill_sb = sysfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; int __init sysfs_init(void) { int err; sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, NULL); if (IS_ERR(sysfs_root)) return PTR_ERR(sysfs_root); sysfs_root_kn = kernfs_root_to_node(sysfs_root); err = register_filesystem(&sysfs_fs_type); if (err) { kernfs_destroy_root(sysfs_root); return err; } return 0; } |
| 463 310 1 6 133 17 327 15 238 216 26 239 239 1 238 238 238 10 113 49 59 11 172 58 1 1 60 61 58 59 58 3 55 59 56 3 59 53 6 2 2 4 4 69 69 69 69 10 59 61 1 1 21 20 1 18 3 18 16 14 10 10 1 3 1 3 1 1 1 4 4 4 1 27 1 1 25 26 4 21 4 5 18 23 32 20 5 1 6 3 1 2 2 5 2 4 2 22 3 7 12 9 5 4 9 8 1 7 4 1 76 75 1 1 3 1 10 2 4 4 47 47 38 44 2 1 1 31 10 10 22 7 8 1239 1094 74 216 80 285 4 285 24 409 1 3 8 8 3 1 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* linux/net/ipv4/arp.c * * Copyright (C) 1994 by Florian La Roche * * This module implements the Address Resolution Protocol ARP (RFC 826), * which is used to convert IP addresses (or in the future maybe other * high-level addresses) into a low-level hardware address (like an Ethernet * address). * * Fixes: * Alan Cox : Removed the Ethernet assumptions in * Florian's code * Alan Cox : Fixed some small errors in the ARP * logic * Alan Cox : Allow >4K in /proc * Alan Cox : Make ARP add its own protocol entry * Ross Martin : Rewrote arp_rcv() and arp_get_info() * Stephen Henson : Add AX25 support to arp_get_info() * Alan Cox : Drop data when a device is downed. * Alan Cox : Use init_timer(). * Alan Cox : Double lock fixes. * Martin Seine : Move the arphdr structure * to if_arp.h for compatibility. * with BSD based programs. * Andrew Tridgell : Added ARP netmask code and * re-arranged proxy handling. * Alan Cox : Changed to use notifiers. * Niibe Yutaka : Reply for this device or proxies only. * Alan Cox : Don't proxy across hardware types! * Jonathan Naylor : Added support for NET/ROM. * Mike Shaver : RFC1122 checks. * Jonathan Naylor : Only lookup the hardware address for * the correct hardware type. * Germano Caronni : Assorted subtle races. * Craig Schlenter : Don't modify permanent entry * during arp_rcv. * Russ Nelson : Tidied up a few bits. * Alexey Kuznetsov: Major changes to caching and behaviour, * eg intelligent arp probing and * generation * of host down events. * Alan Cox : Missing unlock in device events. * Eckes : ARP ioctl control errors. * Alexey Kuznetsov: Arp free fix. * Manuel Rodriguez: Gratuitous ARP. * Jonathan Layes : Added arpd support through kerneld * message queue (960314) * Mike Shaver : /proc/sys/net/ipv4/arp_* support * Mike McLagan : Routing by source * Stuart Cheshire : Metricom and grat arp fixes * *** FOR 2.1 clean this up *** * Lawrence V. Stefani: (08/12/96) Added FDDI support. * Alan Cox : Took the AP1000 nasty FDDI hack and * folded into the mainstream FDDI code. * Ack spit, Linus how did you allow that * one in... * Jes Sorensen : Make FDDI work again in 2.1.x and * clean up the APFDDI & gen. FDDI bits. * Alexey Kuznetsov: new arp state machine; * now it is in net/core/neighbour.c. * Krzysztof Halasa: Added Frame Relay ARP support. * Arnaldo C. Melo : convert /proc/net/arp to seq_file * Shmulik Hen: Split arp_send to arp_create and * arp_xmit so intermediate drivers like * bonding can change the skb before * sending (e.g. insert 8021q tag). * Harald Welte : convert to make use of jenkins hash * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/capability.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/fddidevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/net_namespace.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ax25.h> #include <net/netrom.h> #include <net/dst_metadata.h> #include <net/ip_tunnels.h> #include <linux/uaccess.h> #include <linux/netfilter_arp.h> /* * Interface to generic neighbour cache. */ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool arp_key_eq(const struct neighbour *n, const void *pkey); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops arp_hh_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops arp_direct_ops = { .family = AF_INET, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table arp_tbl = { .family = AF_INET, .key_len = 4, .protocol = cpu_to_be16(ETH_P_IP), .hash = arp_hash, .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, .reachable_time = 30 * HZ, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, [NEIGH_VAR_LOCKTIME] = 1 * HZ, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL(arp_tbl); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: ip_eth_mc_map(addr, haddr); return 0; case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; case ARPHRD_IPGRE: ip_ipgre_mc_map(addr, dev->broadcast, haddr); return 0; default: if (dir) { memcpy(haddr, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return arp_hashfn(pkey, dev, hash_rnd); } static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) { return neigh_key_eq32(neigh, pkey); } static int arp_constructor(struct neighbour *neigh) { __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; u32 inaddr_any = INADDR_ANY; if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return -EINVAL; } neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); rcu_read_unlock(); if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) ARPHRD_ETHER: (ethernet, apfddi) ARPHRD_FDDI: (fddi) ARPHRD_IEEE802: (tr) ARPHRD_METRICOM: (strip) ARPHRD_ARCNET: etc. etc. etc. ARPHRD_IPDDP will also work, if author repairs it. I did not it, because this driver does not work even in old paradigm. */ if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); } else if (neigh->type == RTN_BROADCAST || (dev->flags & IFF_POINTOPOINT)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &arp_hh_ops; else neigh->ops = &arp_generic_ops; if (neigh->nud_state & NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } return 0; } static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) { dst_link_failure(skb); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_FAILED); } /* Create and send an arp packet. */ static void arp_send_dst(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw, struct dst_entry *dst) { struct sk_buff *skb; /* arp on this interface. */ if (dev->flags & IFF_NOARP) return; skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); if (!skb) return; skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw, NULL); } EXPORT_SYMBOL(arp_send); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return; } switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ if (!skb) break; saddr = ip_hdr(skb)->saddr; if (inet_addr_type_dev_table(dev_net(dev), dev, saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; } saddr = 0; break; case 2: /* Avoid secondary IPs, get a primary/preferred one */ break; } rcu_read_unlock(); if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); neigh_ha_snapshot(dst_ha, neigh, dev); dst_hw = dst_ha; } else { probes -= NEIGH_VAR(neigh->parms, APP_PROBES); if (probes < 0) { neigh_app_ns(neigh); return; } } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) { struct net *net = dev_net(in_dev->dev); int scope; switch (IN_DEV_ARP_IGNORE(in_dev)) { case 0: /* Reply, the tip is already validated */ return 0; case 1: /* Reply only if tip is configured on the incoming interface */ sip = 0; scope = RT_SCOPE_HOST; break; case 2: /* * Reply only if tip is configured on the incoming interface * and is in same subnet as sip */ scope = RT_SCOPE_HOST; break; case 3: /* Do not reply for scope host addresses */ sip = 0; scope = RT_SCOPE_LINK; in_dev = NULL; break; case 4: /* Reserved */ case 5: case 6: case 7: return 0; case 8: /* Do not reply */ return 1; default: return 0; } return !inet_confirm_addr(net, in_dev, sip, tip, scope); } static int arp_accept(struct in_device *in_dev, __be32 sip) { struct net *net = dev_net(in_dev->dev); int scope = RT_SCOPE_LINK; switch (IN_DEV_ARP_ACCEPT(in_dev)) { case 0: /* Don't create new entries from garp */ return 0; case 1: /* Create new entries from garp */ return 1; case 2: /* Create a neighbor in the arp table only if sip * is in the same subnet as an address configured * on the interface that received the garp message */ return !!inet_confirm_addr(net, in_dev, sip, 0, scope); default: return 0; } } static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) { struct rtable *rt; int flag = 0; /*unsigned long now; */ struct net *net = dev_net(dev); rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev), RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { __NET_INC_STATS(net, LINUX_MIB_ARPFILTER); flag = 1; } ip_rt_put(rt); return flag; } /* * Check if we can use proxy ARP for this path */ static inline int arp_fwd_proxy(struct in_device *in_dev, struct net_device *dev, struct rtable *rt) { struct in_device *out_dev; int imi, omi = -1; if (rt->dst.dev == dev) return 0; if (!IN_DEV_PROXY_ARP(in_dev)) return 0; imi = IN_DEV_MEDIUM_ID(in_dev); if (imi == 0) return 1; if (imi == -1) return 0; /* place to check for proxy_arp for routes */ out_dev = __in_dev_get_rcu(rt->dst.dev); if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); return omi != imi && omi != -1; } /* * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev) * * RFC3069 supports proxy arp replies back to the same interface. This * is done to support (ethernet) switch features, like RFC 3069, where * the individual ports are not allowed to communicate with each * other, BUT they are allowed to talk to the upstream router. As * described in RFC 3069, it is possible to allow these hosts to * communicate through the upstream router, by proxy_arp'ing. * * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation" * * This technology is known by different names: * In RFC 3069 it is called VLAN Aggregation. * Cisco and Allied Telesyn call it Private VLAN. * Hewlett-Packard call it Source-Port filtering or port-isolation. * Ericsson call it MAC-Forced Forwarding (RFC Draft). * */ static inline int arp_fwd_pvlan(struct in_device *in_dev, struct net_device *dev, struct rtable *rt, __be32 sip, __be32 tip) { /* Private VLAN is only concerned about the same ethernet segment */ if (rt->dst.dev != dev) return 0; /* Don't reply on self probes (often done by windowz boxes)*/ if (sip == tip) return 0; if (IN_DEV_PROXY_ARP_PVLAN(in_dev)) return 1; else return 0; } /* * Interface to link layer: send routine and receive handler. */ /* * Create an arp packet. If dest_hw is not set, we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; /* * Allocate a buffer */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (!skb) return NULL; skb_reserve(skb, hlen); skb_reset_network_header(skb); arp = skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) src_hw = dev->dev_addr; if (!dest_hw) dest_hw = dev->broadcast; /* * Fill the device header for the ARP frame */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; /* * Fill out the arp protocol part. * * The arp hardware type should match the device type, except for FDDI, * which (according to RFC 1390) should always equal 1 (Ethernet). */ /* * Exceptions everywhere. AX.25 uses the AX.25 PID value not the * DIX code for the protocol. Make these device structure fields. */ switch (dev->type) { default: arp->ar_hrd = htons(dev->type); arp->ar_pro = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; #if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); break; #endif #endif #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif } arp->ar_hln = dev->addr_len; arp->ar_pln = 4; arp->ar_op = htons(type); arp_ptr = (unsigned char *)(arp + 1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr += dev->addr_len; memcpy(arp_ptr, &src_ip, 4); arp_ptr += 4; switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: if (target_hw) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); arp_ptr += dev->addr_len; } memcpy(arp_ptr, &dest_ip, 4); return skb; out: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(arp_create); static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } /* * Send an arp packet. */ void arp_xmit(struct sk_buff *skb) { /* Send it off, maybe filter it using firewalling first. */ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, dev_net(skb->dev), NULL, skb, NULL, skb->dev, arp_xmit_finish); } EXPORT_SYMBOL(arp_xmit); static bool arp_is_garp(struct net *net, struct net_device *dev, int *addr_type, __be16 ar_op, __be32 sip, __be32 tip, unsigned char *sha, unsigned char *tha) { bool is_garp = tip == sip; /* Gratuitous ARP _replies_ also require target hwaddr to be * the same as source. */ if (is_garp && ar_op == htons(ARPOP_REPLY)) is_garp = /* IPv4 over IEEE 1394 doesn't provide target * hardware address field in its ARP payload. */ tha && !memcmp(tha, sha, dev->addr_len); if (is_garp) { *addr_type = inet_addr_type_dev_table(net, dev, sip); if (*addr_type != RTN_UNICAST) is_garp = false; } return is_garp; } /* * Process an arp request. */ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); struct arphdr *arp; unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; unsigned char *tha = NULL; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; struct neighbour *n; struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. */ if (!in_dev) goto out_free_skb; arp = arp_hdr(skb); switch (dev_type) { default: if (arp->ar_pro != htons(ETH_P_IP) || htons(dev_type) != arp->ar_hrd) goto out_free_skb; break; case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* * ETHERNET, and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that * FDDI devices should accept ARP hardware of (1) Ethernet, * however, to be more robust, we'll accept both 1 (Ethernet) * or 6 (IEEE 802.2) */ if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || arp->ar_pro != htons(ETH_P_IP)) goto out_free_skb; break; case ARPHRD_AX25: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_AX25)) goto out_free_skb; break; case ARPHRD_NETROM: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_NETROM)) goto out_free_skb; break; } /* Understand only these message types */ if (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST)) goto out_free_skb; /* * Extract fields */ arp_ptr = (unsigned char *)(arp + 1); sha = arp_ptr; arp_ptr += dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; switch (dev_type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: tha = arp_ptr; arp_ptr += dev->addr_len; } memcpy(&tip, arp_ptr, 4); /* * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ if (ipv4_is_multicast(tip) || (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) goto out_free_skb; /* * For some 802.11 wireless deployments (and possibly other networks), * there will be an ARP proxy and gratuitous ARP frames are attacks * and thus should not be accepted. */ if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP)) goto out_free_skb; /* * Special case: We must set Frame Relay source Q.922 address */ if (dev_type == ARPHRD_DLCI) sha = dev->broadcast; /* * Process entry. The idea here is we want to send a reply if it is a * request for us or if it is a request for someone else that we hold * a proxy for. We want to add an entry to our cache if it is a reply * to us or if it is a request for our address. * (The assumption for this last is that if someone is requesting our * address, they are probably intending to talk to us, so it saves time * if we cache their address. Their address is also probably not in * our cache, since ours is not in their cache.) * * Putting this another way, we only care about replies if they are to * us, in which case we add them to the cache. For requests, we care * about those for us and those for our proxies. We reply to both, * and in the case of requests for us we add the requester to the arp * cache. */ if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) reply_dst = (struct dst_entry *) iptunnel_metadata_reply(skb_metadata_dst(skb), GFP_ATOMIC); /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); goto out_consume_skb; } if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { int dont_send; dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); neigh_release(n); } } goto out_consume_skb; } else if (IN_DEV_FORWARD(in_dev)) { if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); goto out_free_dst; } goto out_consume_skb; } } } /* Update our ARP tables */ n = __neigh_lookup(&arp_tbl, &sip, dev, 0); addr_type = -1; if (n || arp_accept(in_dev, sip)) { is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op, sip, tip, sha, tha); } if (arp_accept(in_dev, sip)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ if (!n && (is_garp || (arp->ar_op == htons(ARPOP_REPLY) && (addr_type == RTN_UNICAST || (addr_type < 0 && /* postpone calculation to as late as possible */ inet_addr_type_dev_table(net, dev, sip) == RTN_UNICAST))))) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { int state = NUD_REACHABLE; int override; /* If several different ARP replies follows back-to-back, use the FIRST one. It is possible, if several proxy agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ override = time_after(jiffies, n->updated + NEIGH_VAR(n->parms, LOCKTIME)) || is_garp; /* Broadcast replies and request packets do not assert neighbour reachability. */ if (arp->ar_op != htons(ARPOP_REPLY) || skb->pkt_type != PACKET_HOST) state = NUD_STALE; neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0); neigh_release(n); } out_consume_skb: consume_skb(skb); out_free_dst: dst_release(reply_dst); return NET_RX_SUCCESS; out_free_skb: kfree_skb(skb); return NET_RX_DROP; } static void parp_redo(struct sk_buff *skb) { arp_process(dev_net(skb->dev), NULL, skb); } static int arp_is_multicast(const void *pkey) { return ipv4_is_multicast(*((__be32 *)pkey)); } /* * Receive an arp request from the device layer. */ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { const struct arphdr *arp; /* do not tweak dropwatch on an ARP we will ignore */ if (dev->flags & IFF_NOARP || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto consumeskb; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto freeskb; arp = arp_hdr(skb); if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) goto freeskb; memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, dev_net(dev), NULL, skb, dev, NULL, arp_process); consumeskb: consume_skb(skb); return NET_RX_SUCCESS; freeskb: kfree_skb(skb); out_of_mem: return NET_RX_DROP; } /* * User level interface (ioctl) */ static struct net_device *arp_req_dev_by_name(struct net *net, struct arpreq *r, bool getarp) { struct net_device *dev; if (getarp) dev = dev_get_by_name_rcu(net, r->arp_dev); else dev = __dev_get_by_name(net, r->arp_dev); if (!dev) return ERR_PTR(-ENODEV); /* Mmmm... It is wrong... ARPHRD_NETROM == 0 */ if (!r->arp_ha.sa_family) r->arp_ha.sa_family = dev->type; if ((r->arp_flags & ATF_COM) && r->arp_ha.sa_family != dev->type) return ERR_PTR(-EINVAL); return dev; } static struct net_device *arp_req_dev(struct net *net, struct arpreq *r) { struct net_device *dev; struct rtable *rt; __be32 ip; if (r->arp_dev[0]) return arp_req_dev_by_name(net, r, false); if (r->arp_flags & ATF_PUBL) return NULL; ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; rt = ip_route_output(net, ip, 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; ip_rt_put(rt); if (!dev) return ERR_PTR(-EINVAL); return dev; } /* * Set (create) an ARP cache entry. */ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) { if (!dev) { IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } if (__in_dev_get_rtnl(dev)) { IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); return 0; } return -ENXIO; } static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; } if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) return -ENOBUFS; return 0; } return arp_req_set_proxy(net, dev, 1); } static int arp_req_set(struct net *net, struct arpreq *r) { struct neighbour *neigh; struct net_device *dev; __be32 ip; int err; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_set_public(net, r, dev); switch (dev->type) { #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP * hardware types of 1 (Ethernet). However, to be more * robust, we'll accept hardware types of either 1 (Ethernet) * or 6 (IEEE 802.2). */ if (r->arp_ha.sa_family != ARPHRD_FDDI && r->arp_ha.sa_family != ARPHRD_ETHER && r->arp_ha.sa_family != ARPHRD_IEEE802) return -EINVAL; break; #endif default: if (r->arp_ha.sa_family != dev->type) return -EINVAL; break; } ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { unsigned int state = NUD_STALE; if (r->arp_flags & ATF_PERM) { r->arp_flags |= ATF_COM; state = NUD_PERMANENT; } err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); } return err; } static unsigned int arp_state_to_flags(struct neighbour *neigh) { if (neigh->nud_state&NUD_PERMANENT) return ATF_PERM | ATF_COM; else if (neigh->nud_state&NUD_VALID) return ATF_COM; else return 0; } /* * Get an ARP cache entry. */ static int arp_req_get(struct net *net, struct arpreq *r) { __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; struct net_device *dev; if (!r->arp_dev[0]) return -ENODEV; dev = arp_req_dev_by_name(net, r, true); if (IS_ERR(dev)) return PTR_ERR(dev); neigh = neigh_lookup(&arp_tbl, &ip, dev); if (!neigh) return -ENXIO; if (READ_ONCE(neigh->nud_state) & NUD_NOARP) { neigh_release(neigh); return -ENXIO; } read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); neigh_release(neigh); r->arp_ha.sa_family = dev->type; netdev_copy_name(dev, r->arp_dev); return 0; } int arp_invalidate(struct net_device *dev, __be32 ip, bool force) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; struct neigh_table *tbl = &arp_tbl; if (neigh) { if ((READ_ONCE(neigh->nud_state) & NUD_VALID) && !force) { neigh_release(neigh); return 0; } if (READ_ONCE(neigh->nud_state) & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); write_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh, tbl); write_unlock_bh(&tbl->lock); } return err; } static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return pneigh_delete(&arp_tbl, net, &ip, dev); } return arp_req_set_proxy(net, dev, 0); } static int arp_req_delete(struct net *net, struct arpreq *r) { struct net_device *dev; __be32 ip; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return arp_invalidate(dev, ip, true); } /* * Handle an ARP layer I/O control request. */ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct arpreq r; __be32 *netmask; int err; switch (cmd) { case SIOCDARP: case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; fallthrough; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) return -EFAULT; break; default: return -EINVAL; } if (r.arp_pa.sa_family != AF_INET) return -EPFNOSUPPORT; if (!(r.arp_flags & ATF_PUBL) && (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; netmask = &((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr; if (!(r.arp_flags & ATF_NETMASK)) *netmask = htonl(0xFFFFFFFFUL); else if (*netmask && *netmask != htonl(0xFFFFFFFFUL)) return -EINVAL; switch (cmd) { case SIOCDARP: rtnl_lock(); err = arp_req_delete(net, &r); rtnl_unlock(); break; case SIOCSARP: rtnl_lock(); err = arp_req_set(net, &r); rtnl_unlock(); break; case SIOCGARP: rcu_read_lock(); err = arp_req_get(net, &r); rcu_read_unlock(); if (!err && copy_to_user(arg, &r, sizeof(r))) err = -EFAULT; break; } return err; } static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct in_device *in_dev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); rt_cache_flush(dev_net(dev)); break; case NETDEV_CHANGE: change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) evict_nocarrier = true; else evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block arp_netdev_notifier = { .notifier_call = arp_netdev_event, }; /* Note, that it is not on notifier chain. It is necessary, that this routine was called after route cache will be flushed. */ void arp_ifdown(struct net_device *dev) { neigh_ifdown(&arp_tbl, dev); } /* * Called once on startup. */ static struct packet_type arp_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_ARP), .func = arp_rcv, }; #ifdef CONFIG_PROC_FS #if IS_ENABLED(CONFIG_AX25) /* * ax25 -> ASCII conversion */ static void ax2asc2(ax25_address *a, char *buf) { char c, *s; int n; for (n = 0, s = buf; n < 6; n++) { c = (a->ax25_call[n] >> 1) & 0x7F; if (c != ' ') *s++ = c; } *s++ = '-'; n = (a->ax25_call[6] >> 1) & 0x0F; if (n > 9) { *s++ = '1'; n -= 10; } *s++ = n + '0'; *s++ = '\0'; if (*buf == '\0' || *buf == '-') { buf[0] = '*'; buf[1] = '\0'; } } #endif /* CONFIG_AX25 */ #define HBUFFERLEN 30 static void arp_format_neigh_entry(struct seq_file *seq, struct neighbour *n) { char hbuffer[HBUFFERLEN]; int k, j; char tbuf[16]; struct net_device *dev = n->dev; int hatype = dev->type; read_lock(&n->lock); /* Convert hardware address to XX:XX:XX:XX ... form. */ #if IS_ENABLED(CONFIG_AX25) if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM) ax2asc2((ax25_address *)n->ha, hbuffer); else { #endif for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) { hbuffer[k++] = hex_asc_hi(n->ha[j]); hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } if (k != 0) --k; hbuffer[k] = 0; #if IS_ENABLED(CONFIG_AX25) } #endif sprintf(tbuf, "%pI4", n->primary_key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); } static void arp_format_pneigh_entry(struct seq_file *seq, struct pneigh_entry *n) { struct net_device *dev = n->dev; int hatype = dev ? dev->type : 0; char tbuf[16]; sprintf(tbuf, "%pI4", n->key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", tbuf, hatype, ATF_PUBL | ATF_PERM, "00:00:00:00:00:00", dev ? dev->name : "*"); } static int arp_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "IP address HW type Flags " "HW address Mask Device\n"); } else { struct neigh_seq_state *state = seq->private; if (state->flags & NEIGH_SEQ_IS_PNEIGH) arp_format_pneigh_entry(seq, v); else arp_format_neigh_entry(seq, v); } return 0; } static void *arp_seq_start(struct seq_file *seq, loff_t *pos) { /* Don't want to confuse "arp -a" w/ magic entries, * so we tell the generic iterator to skip NUD_NOARP. */ return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_SKIP_NOARP); } static const struct seq_operations arp_seq_ops = { .start = arp_seq_start, .next = neigh_seq_next, .stop = neigh_seq_stop, .show = arp_seq_show, }; #endif /* CONFIG_PROC_FS */ static int __net_init arp_net_init(struct net *net) { if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops, sizeof(struct neigh_seq_state))) return -ENOMEM; return 0; } static void __net_exit arp_net_exit(struct net *net) { remove_proc_entry("arp", net->proc_net); } static struct pernet_operations arp_net_ops = { .init = arp_net_init, .exit = arp_net_exit, }; void __init arp_init(void) { neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); dev_add_pack(&arp_packet_type); register_pernet_subsys(&arp_net_ops); #ifdef CONFIG_SYSCTL neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); #endif register_netdevice_notifier(&arp_netdev_notifier); } |
| 287 287 286 285 19 286 254 1 286 73 100 285 286 287 287 | 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 | // SPDX-License-Identifier: BSD-3-Clause /* $OpenBSD: siphash.c,v 1.3 2015/02/20 11:51:03 tedu Exp $ */ /*- * Copyright (c) 2013 Andre Oppermann <andre@FreeBSD.org> * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The name of the author may not be used to endorse or promote * products derived from this software without specific prior written * permission. * * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ /* * SipHash is a family of PRFs SipHash-c-d where the integer parameters c and d * are the number of compression rounds and the number of finalization rounds. * A compression round is identical to a finalization round and this round * function is called SipRound. Given a 128-bit key k and a (possibly empty) * byte string m, SipHash-c-d returns a 64-bit value SipHash-c-d(k; m). * * Implemented from the paper "SipHash: a fast short-input PRF", 2012.09.18, * by Jean-Philippe Aumasson and Daniel J. Bernstein, * Permanent Document ID b9a943a805fbfc6fde808af9fc0ecdfa * https://131002.net/siphash/siphash.pdf * https://131002.net/siphash/ */ #include <asm/byteorder.h> #include <asm/unaligned.h> #include <linux/bitops.h> #include <linux/string.h> #include "siphash.h" static void SipHash_Rounds(SIPHASH_CTX *ctx, int rounds) { while (rounds--) { ctx->v[0] += ctx->v[1]; ctx->v[2] += ctx->v[3]; ctx->v[1] = rol64(ctx->v[1], 13); ctx->v[3] = rol64(ctx->v[3], 16); ctx->v[1] ^= ctx->v[0]; ctx->v[3] ^= ctx->v[2]; ctx->v[0] = rol64(ctx->v[0], 32); ctx->v[2] += ctx->v[1]; ctx->v[0] += ctx->v[3]; ctx->v[1] = rol64(ctx->v[1], 17); ctx->v[3] = rol64(ctx->v[3], 21); ctx->v[1] ^= ctx->v[2]; ctx->v[3] ^= ctx->v[0]; ctx->v[2] = rol64(ctx->v[2], 32); } } static void SipHash_CRounds(SIPHASH_CTX *ctx, const void *ptr, int rounds) { u64 m = get_unaligned_le64(ptr); ctx->v[3] ^= m; SipHash_Rounds(ctx, rounds); ctx->v[0] ^= m; } void SipHash_Init(SIPHASH_CTX *ctx, const SIPHASH_KEY *key) { u64 k0, k1; k0 = le64_to_cpu(key->k0); k1 = le64_to_cpu(key->k1); ctx->v[0] = 0x736f6d6570736575ULL ^ k0; ctx->v[1] = 0x646f72616e646f6dULL ^ k1; ctx->v[2] = 0x6c7967656e657261ULL ^ k0; ctx->v[3] = 0x7465646279746573ULL ^ k1; memset(ctx->buf, 0, sizeof(ctx->buf)); ctx->bytes = 0; } void SipHash_Update(SIPHASH_CTX *ctx, int rc, int rf, const void *src, size_t len) { const u8 *ptr = src; size_t left, used; if (len == 0) return; used = ctx->bytes % sizeof(ctx->buf); ctx->bytes += len; if (used > 0) { left = sizeof(ctx->buf) - used; if (len >= left) { memcpy(&ctx->buf[used], ptr, left); SipHash_CRounds(ctx, ctx->buf, rc); len -= left; ptr += left; } else { memcpy(&ctx->buf[used], ptr, len); return; } } while (len >= sizeof(ctx->buf)) { SipHash_CRounds(ctx, ptr, rc); len -= sizeof(ctx->buf); ptr += sizeof(ctx->buf); } if (len > 0) memcpy(&ctx->buf[used], ptr, len); } void SipHash_Final(void *dst, SIPHASH_CTX *ctx, int rc, int rf) { u64 r; r = SipHash_End(ctx, rc, rf); *((__le64 *) dst) = cpu_to_le64(r); } u64 SipHash_End(SIPHASH_CTX *ctx, int rc, int rf) { u64 r; size_t left, used; used = ctx->bytes % sizeof(ctx->buf); left = sizeof(ctx->buf) - used; memset(&ctx->buf[used], 0, left - 1); ctx->buf[7] = ctx->bytes; SipHash_CRounds(ctx, ctx->buf, rc); ctx->v[2] ^= 0xff; SipHash_Rounds(ctx, rf); r = (ctx->v[0] ^ ctx->v[1]) ^ (ctx->v[2] ^ ctx->v[3]); memset(ctx, 0, sizeof(*ctx)); return r; } u64 SipHash(const SIPHASH_KEY *key, int rc, int rf, const void *src, size_t len) { SIPHASH_CTX ctx; SipHash_Init(&ctx, key); SipHash_Update(&ctx, rc, rf, src, len); return SipHash_End(&ctx, rc, rf); } |
| 25 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Sysfs attributes of bond slaves * * Copyright (c) 2014 Scott Feldman <sfeldma@cumulusnetworks.com> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/bonding.h> struct slave_attribute { struct attribute attr; ssize_t (*show)(struct slave *, char *); }; #define SLAVE_ATTR_RO(_name) \ const struct slave_attribute slave_attr_##_name = __ATTR_RO(_name) static ssize_t state_show(struct slave *slave, char *buf) { switch (bond_slave_state(slave)) { case BOND_STATE_ACTIVE: return sysfs_emit(buf, "active\n"); case BOND_STATE_BACKUP: return sysfs_emit(buf, "backup\n"); default: return sysfs_emit(buf, "UNKNOWN\n"); } } static SLAVE_ATTR_RO(state); static ssize_t mii_status_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%s\n", bond_slave_link_status(slave->link)); } static SLAVE_ATTR_RO(mii_status); static ssize_t link_failure_count_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%d\n", slave->link_failure_count); } static SLAVE_ATTR_RO(link_failure_count); static ssize_t perm_hwaddr_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%*phC\n", slave->dev->addr_len, slave->perm_hwaddr); } static SLAVE_ATTR_RO(perm_hwaddr); static ssize_t queue_id_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%d\n", READ_ONCE(slave->queue_id)); } static SLAVE_ATTR_RO(queue_id); static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) { const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg) return sysfs_emit(buf, "%d\n", agg->aggregator_identifier); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_aggregator_id); static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) { const struct port *ad_port; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; if (ad_port->aggregator) return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_actor_oper_port_state); static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) { const struct port *ad_port; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; if (ad_port->aggregator) return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_partner_oper_port_state); static const struct attribute *slave_attrs[] = { &slave_attr_state.attr, &slave_attr_mii_status.attr, &slave_attr_link_failure_count.attr, &slave_attr_perm_hwaddr.attr, &slave_attr_queue_id.attr, &slave_attr_ad_aggregator_id.attr, &slave_attr_ad_actor_oper_port_state.attr, &slave_attr_ad_partner_oper_port_state.attr, NULL }; #define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) static ssize_t slave_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct slave_attribute *slave_attr = to_slave_attr(attr); struct slave *slave = to_slave(kobj); return slave_attr->show(slave, buf); } const struct sysfs_ops slave_sysfs_ops = { .show = slave_show, }; int bond_sysfs_slave_add(struct slave *slave) { return sysfs_create_files(&slave->kobj, slave_attrs); } void bond_sysfs_slave_del(struct slave *slave) { sysfs_remove_files(&slave->kobj, slave_attrs); } |
| 3 76 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* AF_RXRPC internal definitions * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/atomic.h> #include <linux/seqlock.h> #include <linux/win_minmax.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include "protocol.h" #define FCRYPT_BSIZE 8 struct rxrpc_crypt { union { u8 x[FCRYPT_BSIZE]; __be32 n[2]; }; } __attribute__((aligned(8))); #define rxrpc_queue_work(WS) queue_work(rxrpc_workqueue, (WS)) #define rxrpc_queue_delayed_work(WS,D) \ queue_delayed_work(rxrpc_workqueue, (WS), (D)) struct key_preparsed_payload; struct rxrpc_connection; struct rxrpc_txbuf; /* * Mark applied to socket buffers in skb->mark. skb->priority is used * to pass supplementary information. */ enum rxrpc_skb_mark { RXRPC_SKB_MARK_PACKET, /* Received packet */ RXRPC_SKB_MARK_ERROR, /* Error notification */ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; /* * sk_state for RxRPC sockets */ enum { RXRPC_UNBOUND = 0, RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ RXRPC_SERVER_BOUND, /* server local address bound */ RXRPC_SERVER_BOUND2, /* second server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_SERVER_LISTEN_DISABLED, /* server listening disabled */ RXRPC_CLOSE, /* socket is being closed */ }; /* * Per-network namespace data. */ struct rxrpc_net { struct proc_dir_entry *proc_net; /* Subdir in /proc/net */ u32 epoch; /* Local epoch for detecting local-end reset */ struct list_head calls; /* List of calls active in this namespace */ spinlock_t call_lock; /* Lock for ->calls */ atomic_t nr_calls; /* Count of allocated calls */ atomic_t nr_conns; struct list_head bundle_proc_list; /* List of bundles for proc */ struct list_head conn_proc_list; /* List of conns in this namespace for proc */ struct list_head service_conns; /* Service conns in this namespace */ rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ struct work_struct service_conn_reaper; struct timer_list service_conn_reap_timer; bool live; atomic_t nr_client_conns; struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ DECLARE_HASHTABLE (peer_hash, 10); spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ u8 peer_keepalive_cursor; time64_t peer_keepalive_base; struct list_head peer_keepalive[32]; struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; atomic_t stat_tx_data; atomic_t stat_tx_data_retrans; atomic_t stat_tx_data_send; atomic_t stat_tx_data_send_frag; atomic_t stat_tx_data_send_fail; atomic_t stat_tx_data_underflow; atomic_t stat_tx_data_cwnd_reset; atomic_t stat_rx_data; atomic_t stat_rx_data_reqack; atomic_t stat_rx_data_jumbo; atomic_t stat_tx_ack_fill; atomic_t stat_tx_ack_send; atomic_t stat_tx_ack_skip; atomic_t stat_tx_acks[256]; atomic_t stat_rx_acks[256]; atomic_t stat_why_req_ack[8]; atomic_t stat_io_loop; }; /* * Service backlog preallocation. * * This contains circular buffers of preallocated peers, connections and calls * for incoming service calls and their head and tail pointers. This allows * calls to be set up in the data_ready handler, thereby avoiding the need to * shuffle packets around so much. */ struct rxrpc_backlog { unsigned short peer_backlog_head; unsigned short peer_backlog_tail; unsigned short conn_backlog_head; unsigned short conn_backlog_tail; unsigned short call_backlog_head; unsigned short call_backlog_tail; #define RXRPC_BACKLOG_MAX 32 struct rxrpc_peer *peer_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_connection *conn_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_call *call_backlog[RXRPC_BACKLOG_MAX]; }; /* * RxRPC socket definition */ struct rxrpc_sock { /* WARNING: sk has to be the first member */ struct sock sk; rxrpc_notify_new_call_t notify_new_call; /* Func to notify of new call */ rxrpc_discard_new_call_t discard_new_call; /* Func to discard a new call */ struct rxrpc_local *local; /* local endpoint */ struct rxrpc_backlog *backlog; /* Preallocation for services */ spinlock_t incoming_lock; /* Incoming call vs service shutdown lock */ struct list_head sock_calls; /* List of calls owned by this socket */ struct list_head to_be_accepted; /* calls awaiting acceptance */ struct list_head recvmsg_q; /* Calls awaiting recvmsg's attention */ spinlock_t recvmsg_lock; /* Lock for recvmsg_q */ struct key *key; /* security for this socket */ struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* User ID -> call mapping */ unsigned long flags; #define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT bool exclusive; /* Exclusive connection for a client socket */ u16 second_service; /* Additional service bound to the endpoint */ struct { /* Service upgrade information */ u16 from; /* Service ID to upgrade (if not 0) */ u16 to; /* service ID to upgrade to */ } service_upgrade; sa_family_t family; /* Protocol family created with */ struct sockaddr_rxrpc srx; /* Primary Service/local addresses */ struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ }; #define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk) /* * CPU-byteorder normalised Rx packet header. */ struct rxrpc_host_header { u32 epoch; /* client boot timestamp */ u32 cid; /* connection and channel ID */ u32 callNumber; /* call ID (0 for connection-level packets) */ u32 seq; /* sequence number of pkt in call stream */ u32 serial; /* serial number of pkt sent to network */ u8 type; /* packet type */ u8 flags; /* packet flags */ u8 userStatus; /* app-layer defined status */ u8 securityIndex; /* security protocol ID */ union { u16 _rsvd; /* reserved */ u16 cksum; /* kerberos security checksum */ }; u16 serviceId; /* service ID */ } __packed; /* * RxRPC socket buffer private variables * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { union { struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ u8 flags; #define RXRPC_RX_VERIFIED 0x01 }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ rxrpc_seq_t prev_ack; /* Highest seq seen */ rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ u8 reason; /* Reason for ack */ u8 nr_acks; /* Number of acks+nacks */ u8 nr_nacks; /* Number of nacks */ } ack; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) /* * RxRPC security module interface */ struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); /* Clean up a security service */ void (*exit)(void); /* Parse the information from a server key */ int (*preparse_server_key)(struct key_preparsed_payload *); /* Clean up the preparse buffer after parsing a server key */ void (*free_preparse_server_key)(struct key_preparsed_payload *); /* Destroy the payload of a server key */ void (*destroy_server_key)(struct key *); /* Describe a server key */ void (*describe_server_key)(const struct key *, struct seq_file *); /* initialise a connection's security */ int (*init_connection_security)(struct rxrpc_connection *, struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate * of the amount of data remaining and allocate a data buffer. */ struct rxrpc_txbuf *(*alloc_txbuf)(struct rxrpc_call *call, size_t remaining, gfp_t gfp); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); /* respond to a challenge */ int (*respond_to_challenge)(struct rxrpc_connection *, struct sk_buff *); /* verify a response */ int (*verify_response)(struct rxrpc_connection *, struct sk_buff *); /* clear connection security */ void (*clear)(struct rxrpc_connection *); }; /* * RxRPC local transport endpoint description * - owned by a single AF_RXRPC socket * - pointed to by transport socket struct sk_user_data */ struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ refcount_t ref; /* Number of references to the structure */ struct net *net; /* The network namespace */ struct rxrpc_net *rxnet; /* Our bits in the network namespace */ struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ struct page_frag_cache tx_alloc; /* Tx control packet allocation (I/O thread only) */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY struct sk_buff_head rx_delay_queue; /* Delay injection queue */ #endif struct sk_buff_head rx_queue; /* Received packets */ struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ bool kill_all_client_conns; struct list_head idle_client_conns; struct timer_list client_conn_reap_timer; unsigned long client_conn_flags; #define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ bool dead; bool service_closed; /* Service socket closed */ struct idr conn_ids; /* List of connection IDs */ struct list_head new_client_calls; /* Newly created client calls need connection */ spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ }; /* * RxRPC remote transport endpoint definition * - matched by local endpoint, remote port, address and protocol type */ struct rxrpc_peer { struct rcu_head rcu; /* This must be first */ refcount_t ref; unsigned long hash_key; struct hlist_node hash_link; struct rxrpc_local *local; struct hlist_head error_targets; /* targets for net error distribution */ struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ unsigned int if_mtu; /* interface MTU for this peer */ unsigned int mtu; /* network MTU for this peer */ unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ struct sockaddr_rxrpc srx; /* remote address */ /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 spinlock_t rtt_input_lock; /* RTT lock for input routine */ ktime_t rtt_last_req; /* Time of last RTT request */ unsigned int rtt_count; /* Number of samples we've got */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rto_us; /* Retransmission timeout in usec */ u8 backoff; /* Backoff timeout (as shift) */ u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* * Keys for matching a connection. */ struct rxrpc_conn_proto { union { struct { u32 epoch; /* epoch of this connection */ u32 cid; /* connection ID */ }; u64 index_key; }; }; struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Representation of remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ u16 service_id; /* Service ID for this connection */ u32 security_level; /* Security level selected */ }; /* * Call completion condition (state == RXRPC_CALL_COMPLETE). */ enum rxrpc_call_completion { RXRPC_CALL_SUCCEEDED, /* - Normal termination */ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ NR__RXRPC_CALL_COMPLETIONS }; /* * Bits in the connection flags. */ enum rxrpc_conn_flag { RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */ RXRPC_CONN_FINAL_ACK_2, /* Need final ACK for channel 2 */ RXRPC_CONN_FINAL_ACK_3, /* Need final ACK for channel 3 */ }; #define RXRPC_CONN_FINAL_ACK_MASK ((1UL << RXRPC_CONN_FINAL_ACK_0) | \ (1UL << RXRPC_CONN_FINAL_ACK_1) | \ (1UL << RXRPC_CONN_FINAL_ACK_2) | \ (1UL << RXRPC_CONN_FINAL_ACK_3)) /* * Events that can be raised upon a connection. */ enum rxrpc_conn_event { RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */ }; /* * The connection protocol state. */ enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */ RXRPC_CONN_CLIENT, /* Client connection */ RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ RXRPC_CONN_ABORTED, /* Conn aborted */ RXRPC_CONN__NR_STATES }; /* * RxRPC client connection bundle. */ struct rxrpc_bundle { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ struct list_head proc_link; /* Link in net->bundle_proc_list */ const struct rxrpc_security *security; /* applied security module */ refcount_t ref; atomic_t active; /* Number of active users */ unsigned int debug_id; u32 security_level; /* Security level selected */ u16 service_id; /* Service ID for this connection */ bool try_upgrade; /* True if the bundle is attempting upgrade */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ unsigned short alloc_error; /* Error from last conn allocation */ struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ unsigned int conn_ids[4]; /* Connection IDs. */ struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ }; /* * RxRPC connection definition * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls */ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ struct list_head attend_link; /* Link in local->conn_attend_q */ refcount_t ref; atomic_t active; /* Active count for service conns */ struct rcu_head rcu; struct list_head cache_link; unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call *call; /* Active call */ unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ u8 last_type; /* Type of last packet */ union { u32 last_seq; u32 last_abort; }; } channels[RXRPC_MAXCALLS]; struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ struct work_struct destructor; /* In-process-context destroyer */ struct rxrpc_bundle *bundle; /* Client connection bundle */ struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ struct page_frag_cache tx_data_alloc; /* Tx DATA packet allocation */ struct mutex tx_data_alloc_lock; struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ union { struct { struct crypto_sync_skcipher *cipher; /* encryption handle */ struct rxrpc_crypt csum_iv; /* packet checksum base */ u32 nonce; /* response re-use preventer */ } rxkad; }; unsigned long flags; unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_proto_state state; /* current state of connection */ enum rxrpc_call_completion completion; /* Completion condition */ s32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ rxrpc_serial_t tx_serial; /* Outgoing packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 service_id; /* Service ID, possibly upgraded */ u32 security_level; /* Security level selected */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ u8 bundle_shift; /* Index into bundle->avail_chans */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ u16 orig_service_id; /* Originally requested service ID */ short error; /* Local error code */ }; static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) { return sp->hdr.flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp) { return !rxrpc_to_server(sp); } /* * Flags in call->flags. */ enum rxrpc_call_flag { RXRPC_CALL_RELEASED, /* call has been released - no more message to userspace */ RXRPC_CALL_HAS_USERID, /* has a user ID attached */ RXRPC_CALL_IS_SERVICE, /* Call is service call */ RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ RXRPC_CALL_EV_INITIAL_PING, /* Send initial ping for a new service call */ }; /* * The states that a call can be in. */ enum rxrpc_call_state { RXRPC_CALL_UNINITIALISED, RXRPC_CALL_CLIENT_AWAIT_CONN, /* - client waiting for connection to become available */ RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */ RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ RXRPC_CALL_COMPLETE, /* - call complete */ NR__RXRPC_CALL_STATES }; /* * Call Tx congestion management modes. */ enum rxrpc_congest_mode { RXRPC_CALL_SLOW_START, RXRPC_CALL_CONGEST_AVOIDANCE, RXRPC_CALL_PACKET_LOSS, RXRPC_CALL_FAST_RETRANSMIT, NR__RXRPC_CONGEST_MODES }; /* * RxRPC call definition * - matched by { connection, call_id } */ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_bundle *bundle; /* Connection bundle to use */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ ktime_t ack_lost_at; /* When ACK is figured as lost */ ktime_t resend_at; /* When next resend needs to happen */ ktime_t ping_at; /* When next to send a ping */ ktime_t keepalive_at; /* When next to send a keepalive ping */ ktime_t expect_rx_by; /* When we expect to get a packet by */ ktime_t expect_req_by; /* When we expect to get a request DATA packet by */ ktime_t expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (ms) */ u32 next_req_timo; /* Timeout for next Rx request packet (ms) */ u32 hard_timo; /* Maximum lifetime or 0 (s) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head wait_link; /* Link in local->new_client_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ struct list_head attend_link; /* Link in local->call_attend_q */ struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */ s32 send_abort; /* Abort code to be sent */ short send_abort_err; /* Error to be associated with the abort */ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */ s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ enum rxrpc_call_state _state; /* Current state of call (needs barrier) */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ u32 security_level; /* Security level selected */ int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ /* Transmitted data tracking. */ spinlock_t tx_lock; /* Transmit queue lock */ struct list_head tx_sendmsg; /* Sendmsg prepared packets */ struct list_head tx_buffer; /* Buffer of transmissible packets */ rxrpc_seq_t tx_bottom; /* First packet in buffer */ rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 ktime_t tx_last_sent; /* Last time a transmission occurred */ /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ rxrpc_seq_t rx_consumed; /* Highest packet consumed */ rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA * packets) rather than bytes. */ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN #define RXRPC_MIN_CWND 4 u8 cong_cwnd; /* Congestion window size */ u8 cong_extra; /* Extra to send for congestion management */ u8 cong_ssthresh; /* Slow-start threshold */ enum rxrpc_congest_mode cong_mode:8; /* Congestion management mode */ u8 cong_dup_acks; /* Count of ACKs showing missing packets */ u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ struct sk_buff *cong_last_nack; /* Last ACK with nacks received */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ u16 ackr_sack_base; /* Starting slot in SACK table ring */ rxrpc_seq_t ackr_window; /* Base of SACK window */ rxrpc_seq_t ackr_wtop; /* Base of SACK window */ unsigned int ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ struct { #define RXRPC_SACK_SIZE 256 /* SACK table for soft-acked packets */ u8 ackr_sack_table[RXRPC_SACK_SIZE]; } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ ktime_t rtt_sent_at[4]; /* Time packet sent */ unsigned long rtt_avail; /* Mask of available slots in bits 0-3, * Mask of pending samples in 8-11 */ #define RXRPC_CALL_RTT_AVAIL_MASK 0xf #define RXRPC_CALL_RTT_PEND_SHIFT 8 /* Transmission-phase ACK management (ACKs we've received). */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { u16 nr_acks; /* Number of ACKs in packet */ u16 nr_new_acks; /* Number of new ACKs in packet */ u16 nr_new_nacks; /* Number of new nacks in packet */ u16 nr_retained_nacks; /* Number of nacks retained between ACKs */ u8 ack_reason; bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ /* Place to stash values for tracing */ enum rxrpc_congest_mode mode:8; u8 cwnd; u8 ssthresh; u8 dup_acks; u8 cumulative_acks; }; /* * sendmsg() cmsg-specified parameters. */ enum rxrpc_command { RXRPC_CMD_SEND_DATA, /* send data message */ RXRPC_CMD_SEND_ABORT, /* request abort generation */ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */ }; struct rxrpc_call_params { s64 tx_total_len; /* Total Tx data length (if send data) */ unsigned long user_call_ID; /* User's call ID */ struct { u32 hard; /* Maximum lifetime (sec) */ u32 idle; /* Max time since last data packet (msec) */ u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ bool kernel; /* T if kernel is making the call */ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; struct rxrpc_send_params { struct rxrpc_call_params call; u32 abort_code; /* Abort code to Tx (if abort) */ enum rxrpc_command command : 8; /* The command to implement */ bool exclusive; /* Shared or exclusive call */ bool upgrade; /* If the connection is upgradeable */ }; /* * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; unsigned int len; /* Amount of data in buffer */ unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ unsigned int flags; #define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ #define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ __be16 cksum; /* Checksum to go in header */ unsigned short ack_rwind; /* ACK receive window */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ u8 nr_kvec; /* Amount of kvec[] used */ struct kvec kvec[3]; }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) { return txb->flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) { return !rxrpc_sending_to_server(txb); } #include <trace/events/rxrpc.h> /* * Allocate the next serial number on a connection. 0 must be skipped. */ static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn) { rxrpc_serial_t serial; serial = conn->tx_serial; if (serial == 0) serial = 1; conn->tx_serial = serial + 1; return serial; } /* * af_rxrpc.c */ extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* * call_accept.c */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* * call_object.c */ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern struct kmem_cache *rxrpc_call_jar; void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what); struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct rxrpc_call_params *, gfp_t, unsigned int); void rxrpc_start_call_timer(struct rxrpc_call *call); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); void rxrpc_destroy_all_calls(struct rxrpc_net *); static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) { return test_bit(RXRPC_CALL_IS_SERVICE, &call->flags); } static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) { return !rxrpc_is_service_call(call); } /* * call_state.c */ bool rxrpc_set_call_completion(struct rxrpc_call *call, enum rxrpc_call_completion compl, u32 abort_code, int error); bool rxrpc_call_completed(struct rxrpc_call *call); bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, u32 abort_code, int error, enum rxrpc_abort_reason why); void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, int error); static inline void rxrpc_set_call_state(struct rxrpc_call *call, enum rxrpc_call_state state) { /* Order write of completion info before write of ->state. */ smp_store_release(&call->_state, state); wake_up(&call->waitq); } static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call) { return call->_state; /* Only inside I/O thread */ } static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call) { return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; } static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call) { /* Order read ->state before read of completion info. */ return smp_load_acquire(&call->_state); } static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call) { return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; } static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call) { return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED; } /* * conn_client.c */ extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; void rxrpc_purge_client_connections(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp); void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c */ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, unsigned int channel); int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, s32 abort_code, int err, enum rxrpc_abort_reason why); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn) { /* Order reading the abort info after the state check. */ return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED; } /* * conn_object.c */ extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why); struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, struct sockaddr_rxrpc *, struct sk_buff *); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_client_conn(struct rxrpc_connection *); void rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_put_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) { return conn->out_clientflag; } static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) { return !rxrpc_conn_is_client(conn); } static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, unsigned long expire_at) { timer_reduce(&conn->timer, expire_at); } /* * conn_service.c */ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, const struct rxrpc_security *, struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ void rxrpc_congestion_degrade(struct rxrpc_call *); void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); /* * io_thread.c */ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); int rxrpc_io_thread(void *data); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { wake_up_process(local->io_thread); } static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why) { return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO); } /* * insecure.c */ extern const struct rxrpc_security rxrpc_no_security; /* * key.c */ extern struct key_type key_type_rxrpc; int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int); int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, u32); /* * local_event.c */ void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); /* * local_object.c */ void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set); struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_destroy_local(struct rxrpc_local *local); void rxrpc_destroy_all_locals(struct rxrpc_net *); static inline bool __rxrpc_use_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { int r, u; r = refcount_read(&local->ref); u = atomic_fetch_add_unless(&local->active_users, 1, 0); trace_rxrpc_local(local->debug_id, why, r, u); return u != 0; } static inline void rxrpc_see_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { int r, u; r = refcount_read(&local->ref); u = atomic_read(&local->active_users); trace_rxrpc_local(local->debug_id, why, r, u); } /* * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY extern unsigned long rxrpc_inject_rx_delay; #endif /* * net_ns.c */ extern unsigned int rxrpc_net_id; extern struct pernet_operations rxrpc_net_ops; static inline struct rxrpc_net *rxrpc_net(struct net *net) { return net_generic(net, rxrpc_net_id); } /* * output.c */ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); int rxrpc_send_abort_packet(struct rxrpc_call *); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); /* * peer_event.c */ void rxrpc_input_error(struct rxrpc_local *, struct sk_buff *); void rxrpc_peer_keepalive_worker(struct work_struct *); /* * peer_object.c */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); /* * proc.c */ extern const struct seq_operations rxrpc_call_seq_ops; extern const struct seq_operations rxrpc_connection_seq_ops; extern const struct seq_operations rxrpc_bundle_seq_ops; extern const struct seq_operations rxrpc_peer_seq_ops; extern const struct seq_operations rxrpc_local_seq_ops; /* * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * Abort a call due to a protocol error. */ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, struct sk_buff *skb, s32 abort_code, enum rxrpc_abort_reason why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why); return -EPROTO; } /* * rtt.c */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans); void rxrpc_peer_init_rtt(struct rxrpc_peer *); /* * rxkad.c */ #ifdef CONFIG_RXKAD extern const struct rxrpc_security rxkad; #endif /* * security.c */ int __init rxrpc_init_security(void); const struct rxrpc_security *rxrpc_security_lookup(u8); void rxrpc_exit_security(void); int rxrpc_init_client_call_security(struct rxrpc_call *); int rxrpc_init_client_conn_security(struct rxrpc_connection *); const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *, struct sk_buff *); struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, struct sk_buff *, u32, u32); /* * sendmsg.c */ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, enum rxrpc_abort_reason why); int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* * server_key.c */ extern struct key_type key_type_rxrpc_s; int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int); /* * skbuff.c */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* * stats.c */ int rxrpc_stats_show(struct seq_file *seq, void *v); int rxrpc_stats_clear(struct file *file, char *buf, size_t size); #define rxrpc_inc_stat(rxnet, s) atomic_inc(&(rxnet)->s) #define rxrpc_dec_stat(rxnet, s) atomic_dec(&(rxnet)->s) /* * sysctl.c */ #ifdef CONFIG_SYSCTL extern int __init rxrpc_sysctl_init(void); extern void rxrpc_sysctl_exit(void); #else static inline int __init rxrpc_sysctl_init(void) { return 0; } static inline void rxrpc_sysctl_exit(void) {} #endif /* * txbuf.c */ extern atomic_t rxrpc_nr_txbuf; struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, size_t data_align, gfp_t gfp); struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size); void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); /* * utils.c */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); static inline bool before(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) < 0; } static inline bool before_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) <= 0; } static inline bool after(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) > 0; } static inline bool after_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) >= 0; } /* * debug tracing */ extern unsigned int rxrpc_debug; #define dbgprintk(FMT,...) \ printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__) #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) #if defined(__KDEBUG) #define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) #define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) #define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) #elif defined(CONFIG_AF_RXRPC_DEBUG) #define RXRPC_DEBUG_KENTER 0x01 #define RXRPC_DEBUG_KLEAVE 0x02 #define RXRPC_DEBUG_KDEBUG 0x04 #define _enter(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KENTER)) \ kenter(FMT,##__VA_ARGS__); \ } while (0) #define _leave(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KLEAVE)) \ kleave(FMT,##__VA_ARGS__); \ } while (0) #define _debug(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KDEBUG)) \ kdebug(FMT,##__VA_ARGS__); \ } while (0) #else #define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__) #endif /* * debug assertion checking */ #if 1 // defined(__KDEBUGALL) #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely(!(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely((C) && !(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #else #define ASSERT(X) \ do { \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ } while (0) #define ASSERTIF(C, X) \ do { \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ } while (0) #endif /* __KDEBUGALL */ |
| 14 2 12 2 2 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "btree_iter.h" #include "btree_update.h" #include "btree_write_buffer.h" #include "buckets.h" #include "clock.h" #include "compress.h" #include "disk_groups.h" #include "errcode.h" #include "error.h" #include "inode.h" #include "move.h" #include "rebalance.h" #include "subvolume.h" #include "super-io.h" #include "trace.h" #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/sched/cputime.h> #define REBALANCE_WORK_SCAN_OFFSET (U64_MAX - 1) static const char * const bch2_rebalance_state_strs[] = { #define x(t) #t, BCH_REBALANCE_STATES() NULL #undef x }; static int __bch2_set_rebalance_needs_scan(struct btree_trans *trans, u64 inum) { struct btree_iter iter; struct bkey_s_c k; struct bkey_i_cookie *cookie; u64 v; int ret; bch2_trans_iter_init(trans, &iter, BTREE_ID_rebalance_work, SPOS(inum, REBALANCE_WORK_SCAN_OFFSET, U32_MAX), BTREE_ITER_intent); k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); if (ret) goto err; v = k.k->type == KEY_TYPE_cookie ? le64_to_cpu(bkey_s_c_to_cookie(k).v->cookie) : 0; cookie = bch2_trans_kmalloc(trans, sizeof(*cookie)); ret = PTR_ERR_OR_ZERO(cookie); if (ret) goto err; bkey_cookie_init(&cookie->k_i); cookie->k.p = iter.pos; cookie->v.cookie = cpu_to_le64(v + 1); ret = bch2_trans_update(trans, &iter, &cookie->k_i, 0); err: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum) { int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw, __bch2_set_rebalance_needs_scan(trans, inum)); rebalance_wakeup(c); return ret; } int bch2_set_fs_needs_rebalance(struct bch_fs *c) { return bch2_set_rebalance_needs_scan(c, 0); } static int bch2_clear_rebalance_needs_scan(struct btree_trans *trans, u64 inum, u64 cookie) { struct btree_iter iter; struct bkey_s_c k; u64 v; int ret; bch2_trans_iter_init(trans, &iter, BTREE_ID_rebalance_work, SPOS(inum, REBALANCE_WORK_SCAN_OFFSET, U32_MAX), BTREE_ITER_intent); k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); if (ret) goto err; v = k.k->type == KEY_TYPE_cookie ? le64_to_cpu(bkey_s_c_to_cookie(k).v->cookie) : 0; if (v == cookie) ret = bch2_btree_delete_at(trans, &iter, 0); err: bch2_trans_iter_exit(trans, &iter); return ret; } static struct bkey_s_c next_rebalance_entry(struct btree_trans *trans, struct btree_iter *work_iter) { return !kthread_should_stop() ? bch2_btree_iter_peek(work_iter) : bkey_s_c_null; } static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0); int ret = PTR_ERR_OR_ZERO(n); if (ret) return ret; extent_entry_drop(bkey_i_to_s(n), (void *) bch2_bkey_rebalance_opts(bkey_i_to_s_c(n))); return bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); } static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans, struct bpos work_pos, struct btree_iter *extent_iter, struct data_update_opts *data_opts) { struct bch_fs *c = trans->c; struct bkey_s_c k; bch2_trans_iter_exit(trans, extent_iter); bch2_trans_iter_init(trans, extent_iter, work_pos.inode ? BTREE_ID_extents : BTREE_ID_reflink, work_pos, BTREE_ITER_all_snapshots); k = bch2_btree_iter_peek_slot(extent_iter); if (bkey_err(k)) return k; const struct bch_extent_rebalance *r = k.k ? bch2_bkey_rebalance_opts(k) : NULL; if (!r) { /* raced due to btree write buffer, nothing to do */ return bkey_s_c_null; } memset(data_opts, 0, sizeof(*data_opts)); data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, k, r->target, r->compression); data_opts->target = r->target; if (!data_opts->rewrite_ptrs) { /* * device we would want to write to offline? devices in target * changed? * * We'll now need a full scan before this extent is picked up * again: */ int ret = bch2_bkey_clear_needs_rebalance(trans, extent_iter, k); if (ret) return bkey_s_c_err(ret); return bkey_s_c_null; } if (trace_rebalance_extent_enabled()) { struct printbuf buf = PRINTBUF; prt_str(&buf, "target="); bch2_target_to_text(&buf, c, r->target); prt_str(&buf, " compression="); bch2_compression_opt_to_text(&buf, r->compression); prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, k); trace_rebalance_extent(c, buf.buf); printbuf_exit(&buf); } return k; } noinline_for_stack static int do_rebalance_extent(struct moving_context *ctxt, struct bpos work_pos, struct btree_iter *extent_iter) { struct btree_trans *trans = ctxt->trans; struct bch_fs *c = trans->c; struct bch_fs_rebalance *r = &trans->c->rebalance; struct data_update_opts data_opts; struct bch_io_opts io_opts; struct bkey_s_c k; struct bkey_buf sk; int ret; ctxt->stats = &r->work_stats; r->state = BCH_REBALANCE_working; bch2_bkey_buf_init(&sk); ret = bkey_err(k = next_rebalance_extent(trans, work_pos, extent_iter, &data_opts)); if (ret || !k.k) goto out; ret = bch2_move_get_io_opts_one(trans, &io_opts, k); if (ret) goto out; atomic64_add(k.k->size, &ctxt->stats->sectors_seen); /* * The iterator gets unlocked by __bch2_read_extent - need to * save a copy of @k elsewhere: */ bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); ret = bch2_move_extent(ctxt, NULL, extent_iter, k, io_opts, data_opts); if (ret) { if (bch2_err_matches(ret, ENOMEM)) { /* memory allocation failure, wait for some IO to finish */ bch2_move_ctxt_wait_for_io(ctxt); ret = -BCH_ERR_transaction_restart_nested; } if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto out; /* skip it and continue, XXX signal failure */ ret = 0; } out: bch2_bkey_buf_exit(&sk, c); return ret; } static bool rebalance_pred(struct bch_fs *c, void *arg, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { unsigned target, compression; if (k.k->p.inode) { target = io_opts->background_target; compression = background_compression(*io_opts); } else { const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); target = r ? r->target : io_opts->background_target; compression = r ? r->compression : background_compression(*io_opts); } data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, k, target, compression); data_opts->target = target; return data_opts->rewrite_ptrs != 0; } static int do_rebalance_scan(struct moving_context *ctxt, u64 inum, u64 cookie) { struct btree_trans *trans = ctxt->trans; struct bch_fs_rebalance *r = &trans->c->rebalance; int ret; bch2_move_stats_init(&r->scan_stats, "rebalance_scan"); ctxt->stats = &r->scan_stats; if (!inum) { r->scan_start = BBPOS_MIN; r->scan_end = BBPOS_MAX; } else { r->scan_start = BBPOS(BTREE_ID_extents, POS(inum, 0)); r->scan_end = BBPOS(BTREE_ID_extents, POS(inum, U64_MAX)); } r->state = BCH_REBALANCE_scanning; ret = __bch2_move_data(ctxt, r->scan_start, r->scan_end, rebalance_pred, NULL) ?: commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_clear_rebalance_needs_scan(trans, inum, cookie)); bch2_move_stats_exit(&r->scan_stats, trans->c); return ret; } static void rebalance_wait(struct bch_fs *c) { struct bch_fs_rebalance *r = &c->rebalance; struct io_clock *clock = &c->io_clock[WRITE]; u64 now = atomic64_read(&clock->now); u64 min_member_capacity = bch2_min_rw_member_capacity(c); if (min_member_capacity == U64_MAX) min_member_capacity = 128 * 2048; r->wait_iotime_end = now + (min_member_capacity >> 6); if (r->state != BCH_REBALANCE_waiting) { r->wait_iotime_start = now; r->wait_wallclock_start = ktime_get_real_ns(); r->state = BCH_REBALANCE_waiting; } bch2_kthread_io_clock_wait(clock, r->wait_iotime_end, MAX_SCHEDULE_TIMEOUT); } static int do_rebalance(struct moving_context *ctxt) { struct btree_trans *trans = ctxt->trans; struct bch_fs *c = trans->c; struct bch_fs_rebalance *r = &c->rebalance; struct btree_iter rebalance_work_iter, extent_iter = { NULL }; struct bkey_s_c k; int ret = 0; bch2_trans_begin(trans); bch2_move_stats_init(&r->work_stats, "rebalance_work"); bch2_move_stats_init(&r->scan_stats, "rebalance_scan"); bch2_trans_iter_init(trans, &rebalance_work_iter, BTREE_ID_rebalance_work, POS_MIN, BTREE_ITER_all_snapshots); while (!bch2_move_ratelimit(ctxt)) { if (!r->enabled) { bch2_moving_ctxt_flush_all(ctxt); kthread_wait_freezable(r->enabled || kthread_should_stop()); } if (kthread_should_stop()) break; bch2_trans_begin(trans); ret = bkey_err(k = next_rebalance_entry(trans, &rebalance_work_iter)); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret || !k.k) break; ret = k.k->type == KEY_TYPE_cookie ? do_rebalance_scan(ctxt, k.k->p.inode, le64_to_cpu(bkey_s_c_to_cookie(k).v->cookie)) : do_rebalance_extent(ctxt, k.k->p, &extent_iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; bch2_btree_iter_advance(&rebalance_work_iter); } bch2_trans_iter_exit(trans, &extent_iter); bch2_trans_iter_exit(trans, &rebalance_work_iter); bch2_move_stats_exit(&r->scan_stats, c); if (!ret && !kthread_should_stop() && !atomic64_read(&r->work_stats.sectors_seen) && !atomic64_read(&r->scan_stats.sectors_seen)) { bch2_moving_ctxt_flush_all(ctxt); bch2_trans_unlock_long(trans); rebalance_wait(c); } if (!bch2_err_matches(ret, EROFS)) bch_err_fn(c, ret); return ret; } static int bch2_rebalance_thread(void *arg) { struct bch_fs *c = arg; struct bch_fs_rebalance *r = &c->rebalance; struct moving_context ctxt; set_freezable(); bch2_moving_ctxt_init(&ctxt, c, NULL, &r->work_stats, writepoint_ptr(&c->rebalance_write_point), true); while (!kthread_should_stop() && !do_rebalance(&ctxt)) ; bch2_moving_ctxt_exit(&ctxt); return 0; } void bch2_rebalance_status_to_text(struct printbuf *out, struct bch_fs *c) { struct bch_fs_rebalance *r = &c->rebalance; prt_str(out, bch2_rebalance_state_strs[r->state]); prt_newline(out); printbuf_indent_add(out, 2); switch (r->state) { case BCH_REBALANCE_waiting: { u64 now = atomic64_read(&c->io_clock[WRITE].now); prt_str(out, "io wait duration: "); bch2_prt_human_readable_s64(out, (r->wait_iotime_end - r->wait_iotime_start) << 9); prt_newline(out); prt_str(out, "io wait remaining: "); bch2_prt_human_readable_s64(out, (r->wait_iotime_end - now) << 9); prt_newline(out); prt_str(out, "duration waited: "); bch2_pr_time_units(out, ktime_get_real_ns() - r->wait_wallclock_start); prt_newline(out); break; } case BCH_REBALANCE_working: bch2_move_stats_to_text(out, &r->work_stats); break; case BCH_REBALANCE_scanning: bch2_move_stats_to_text(out, &r->scan_stats); break; } prt_newline(out); printbuf_indent_sub(out, 2); } void bch2_rebalance_stop(struct bch_fs *c) { struct task_struct *p; c->rebalance.pd.rate.rate = UINT_MAX; bch2_ratelimit_reset(&c->rebalance.pd.rate); p = rcu_dereference_protected(c->rebalance.thread, 1); c->rebalance.thread = NULL; if (p) { /* for sychronizing with rebalance_wakeup() */ synchronize_rcu(); kthread_stop(p); put_task_struct(p); } } int bch2_rebalance_start(struct bch_fs *c) { struct task_struct *p; int ret; if (c->rebalance.thread) return 0; if (c->opts.nochanges) return 0; p = kthread_create(bch2_rebalance_thread, c, "bch-rebalance/%s", c->name); ret = PTR_ERR_OR_ZERO(p); bch_err_msg(c, ret, "creating rebalance thread"); if (ret) return ret; get_task_struct(p); rcu_assign_pointer(c->rebalance.thread, p); wake_up_process(p); return 0; } void bch2_fs_rebalance_init(struct bch_fs *c) { bch2_pd_controller_init(&c->rebalance.pd); } |
| 2 2 1 3 9 9 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. */ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> #include "gfs2.h" #include "incore.h" #include "dir.h" #include "glock.h" #include "glops.h" #include "inode.h" #include "super.h" #include "rgrp.h" #include "util.h" #define GFS2_SMALL_FH_SIZE 4 #define GFS2_LARGE_FH_SIZE 8 #define GFS2_OLD_FH_SIZE 10 static int gfs2_encode_fh(struct inode *inode, __u32 *p, int *len, struct inode *parent) { __be32 *fh = (__force __be32 *)p; struct super_block *sb = inode->i_sb; struct gfs2_inode *ip = GFS2_I(inode); if (parent && (*len < GFS2_LARGE_FH_SIZE)) { *len = GFS2_LARGE_FH_SIZE; return FILEID_INVALID; } else if (*len < GFS2_SMALL_FH_SIZE) { *len = GFS2_SMALL_FH_SIZE; return FILEID_INVALID; } fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32); fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); fh[2] = cpu_to_be32(ip->i_no_addr >> 32); fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_SMALL_FH_SIZE; if (!parent || inode == d_inode(sb->s_root)) return *len; ip = GFS2_I(parent); fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32); fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); fh[6] = cpu_to_be32(ip->i_no_addr >> 32); fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_LARGE_FH_SIZE; return *len; } struct get_name_filldir { struct dir_context ctx; struct gfs2_inum_host inum; char *name; }; static bool get_name_filldir(struct dir_context *ctx, const char *name, int length, loff_t offset, u64 inum, unsigned int type) { struct get_name_filldir *gnfd = container_of(ctx, struct get_name_filldir, ctx); if (inum != gnfd->inum.no_addr) return true; memcpy(gnfd->name, name, length); gnfd->name[length] = 0; return false; } static int gfs2_get_name(struct dentry *parent, char *name, struct dentry *child) { struct inode *dir = d_inode(parent); struct inode *inode = d_inode(child); struct gfs2_inode *dip, *ip; struct get_name_filldir gnfd = { .ctx.actor = get_name_filldir, .name = name }; struct gfs2_holder gh; int error; struct file_ra_state f_ra = { .start = 0 }; if (!dir) return -EINVAL; if (!S_ISDIR(dir->i_mode) || !inode) return -EINVAL; dip = GFS2_I(dir); ip = GFS2_I(inode); *name = 0; gnfd.inum.no_addr = ip->i_no_addr; gnfd.inum.no_formal_ino = ip->i_no_formal_ino; error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh); if (error) return error; error = gfs2_dir_read(dir, &gnfd.ctx, &f_ra); gfs2_glock_dq_uninit(&gh); if (!error && !*name) error = -ENOENT; return error; } static struct dentry *gfs2_get_parent(struct dentry *child) { return d_obtain_alias(gfs2_lookupi(d_inode(child), &gfs2_qdotdot, 1)); } static struct dentry *gfs2_get_dentry(struct super_block *sb, struct gfs2_inum_host *inum) { struct gfs2_sbd *sdp = sb->s_fs_info; struct inode *inode; if (!inum->no_formal_ino) return ERR_PTR(-ESTALE); inode = gfs2_lookup_by_inum(sdp, inum->no_addr, inum->no_formal_ino, GFS2_BLKST_DINODE); return d_obtain_alias(inode); } static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct gfs2_inum_host this; __be32 *fh = (__force __be32 *)fid->raw; switch (fh_type) { case GFS2_SMALL_FH_SIZE: case GFS2_LARGE_FH_SIZE: case GFS2_OLD_FH_SIZE: if (fh_len < GFS2_SMALL_FH_SIZE) return NULL; this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32; this.no_formal_ino |= be32_to_cpu(fh[1]); this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32; this.no_addr |= be32_to_cpu(fh[3]); return gfs2_get_dentry(sb, &this); default: return NULL; } } static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct gfs2_inum_host parent; __be32 *fh = (__force __be32 *)fid->raw; switch (fh_type) { case GFS2_LARGE_FH_SIZE: case GFS2_OLD_FH_SIZE: if (fh_len < GFS2_LARGE_FH_SIZE) return NULL; parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32; parent.no_formal_ino |= be32_to_cpu(fh[5]); parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32; parent.no_addr |= be32_to_cpu(fh[7]); return gfs2_get_dentry(sb, &parent); default: return NULL; } } const struct export_operations gfs2_export_ops = { .encode_fh = gfs2_encode_fh, .fh_to_dentry = gfs2_fh_to_dentry, .fh_to_parent = gfs2_fh_to_parent, .get_name = gfs2_get_name, .get_parent = gfs2_get_parent, .flags = EXPORT_OP_ASYNC_LOCK, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:ip,port type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ /* 6 bucketsize, initval support added */ #define IPSET_TYPE_REV_MAX 7 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:ip,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:ip,port"); /* Type specific function prefix */ #define HTYPE hash_ipport #define IP_SET_HASH_WITH_NETMASK #define IP_SET_HASH_WITH_BITMASK /* IPv4 variant */ /* Member elements */ struct hash_ipport4_elem { __be32 ip; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static bool hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1, const struct hash_ipport4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipport4_data_list(struct sk_buff *skb, const struct hash_ipport4_elem *data) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipport4_data_next(struct hash_ipport4_elem *next, const struct hash_ipport4_elem *d) { next->ip = d->ip; next->port = d->port; } #define MTYPE hash_ipport4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); const struct MTYPE *h = set->data; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= h->bitmask.ip; if (e.ip == 0) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_ipport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; e.ip &= h->bitmask.ip; if (e.ip == 0) return -EINVAL; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip = ntohl(e.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip > ip_to) swap(ip, ip_to); } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } port_to = port = ntohs(e.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_ipport4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } } return ret; } /* IPv6 variant */ struct hash_ipport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static bool hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, const struct hash_ipport6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipport6_data_list(struct sk_buff *skb, const struct hash_ipport6_elem *data) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipport6_data_next(struct hash_ipport6_elem *next, const struct hash_ipport6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_ipport6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); const struct MTYPE *h = set->data; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_ipport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (unlikely(tb[IPSET_ATTR_CIDR])) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (cidr != HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -EINVAL; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_ipport_type __read_mostly = { .name = "hash:ip,port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_ipport_init(void) { return ip_set_type_register(&hash_ipport_type); } static void __exit hash_ipport_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_ipport_type); } module_init(hash_ipport_init); module_exit(hash_ipport_fini); |
| 43 45 45 43 45 45 1 1 4 45 46 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 43 43 43 1 1 1 45 45 45 44 4 4 4 4 45 45 45 44 45 45 45 45 45 45 2 2 12 2 12 6 6 4 2 8 8 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/bug.h> #include <linux/list.h> #include <crypto/hash.h> #include "messages.h" #include "ctree.h" #include "discard.h" #include "disk-io.h" #include "send.h" #include "transaction.h" #include "sysfs.h" #include "volumes.h" #include "space-info.h" #include "block-group.h" #include "qgroup.h" #include "misc.h" #include "fs.h" #include "accessors.h" /* * Structure name Path * -------------------------------------------------------------------------- * btrfs_supported_static_feature_attrs /sys/fs/btrfs/features * btrfs_supported_feature_attrs /sys/fs/btrfs/features and * /sys/fs/btrfs/<uuid>/features * btrfs_attrs /sys/fs/btrfs/<uuid> * devid_attrs /sys/fs/btrfs/<uuid>/devinfo/<devid> * allocation_attrs /sys/fs/btrfs/<uuid>/allocation * qgroup_attrs /sys/fs/btrfs/<uuid>/qgroups/<level>_<qgroupid> * space_info_attrs /sys/fs/btrfs/<uuid>/allocation/<bg-type> * raid_attrs /sys/fs/btrfs/<uuid>/allocation/<bg-type>/<bg-profile> * discard_attrs /sys/fs/btrfs/<uuid>/discard * * When built with BTRFS_CONFIG_DEBUG: * * btrfs_debug_feature_attrs /sys/fs/btrfs/debug * btrfs_debug_mount_attrs /sys/fs/btrfs/<uuid>/debug */ struct btrfs_feature_attr { struct kobj_attribute kobj_attr; enum btrfs_feature_set feature_set; u64 feature_bit; }; /* For raid type sysfs entries */ struct raid_kobject { u64 flags; struct kobject kobj; }; #define __INIT_KOBJ_ATTR(_name, _mode, _show, _store) \ { \ .attr = { .name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ } #define BTRFS_ATTR_W(_prefix, _name, _store) \ static struct kobj_attribute btrfs_attr_##_prefix##_##_name = \ __INIT_KOBJ_ATTR(_name, 0200, NULL, _store) #define BTRFS_ATTR_RW(_prefix, _name, _show, _store) \ static struct kobj_attribute btrfs_attr_##_prefix##_##_name = \ __INIT_KOBJ_ATTR(_name, 0644, _show, _store) #define BTRFS_ATTR(_prefix, _name, _show) \ static struct kobj_attribute btrfs_attr_##_prefix##_##_name = \ __INIT_KOBJ_ATTR(_name, 0444, _show, NULL) #define BTRFS_ATTR_PTR(_prefix, _name) \ (&btrfs_attr_##_prefix##_##_name.attr) #define BTRFS_FEAT_ATTR(_name, _feature_set, _feature_prefix, _feature_bit) \ static struct btrfs_feature_attr btrfs_attr_features_##_name = { \ .kobj_attr = __INIT_KOBJ_ATTR(_name, S_IRUGO, \ btrfs_feature_attr_show, \ btrfs_feature_attr_store), \ .feature_set = _feature_set, \ .feature_bit = _feature_prefix ##_## _feature_bit, \ } #define BTRFS_FEAT_ATTR_PTR(_name) \ (&btrfs_attr_features_##_name.kobj_attr.attr) #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature) #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature) #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature) static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj); static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj); static struct kobject *get_btrfs_kobj(struct kobject *kobj); static struct btrfs_feature_attr *to_btrfs_feature_attr(struct kobj_attribute *a) { return container_of(a, struct btrfs_feature_attr, kobj_attr); } static struct kobj_attribute *attr_to_btrfs_attr(struct attribute *attr) { return container_of(attr, struct kobj_attribute, attr); } static struct btrfs_feature_attr *attr_to_btrfs_feature_attr( struct attribute *attr) { return to_btrfs_feature_attr(attr_to_btrfs_attr(attr)); } static u64 get_features(struct btrfs_fs_info *fs_info, enum btrfs_feature_set set) { struct btrfs_super_block *disk_super = fs_info->super_copy; if (set == FEAT_COMPAT) return btrfs_super_compat_flags(disk_super); else if (set == FEAT_COMPAT_RO) return btrfs_super_compat_ro_flags(disk_super); else return btrfs_super_incompat_flags(disk_super); } static void set_features(struct btrfs_fs_info *fs_info, enum btrfs_feature_set set, u64 features) { struct btrfs_super_block *disk_super = fs_info->super_copy; if (set == FEAT_COMPAT) btrfs_set_super_compat_flags(disk_super, features); else if (set == FEAT_COMPAT_RO) btrfs_set_super_compat_ro_flags(disk_super, features); else btrfs_set_super_incompat_flags(disk_super, features); } static int can_modify_feature(struct btrfs_feature_attr *fa) { int val = 0; u64 set, clear; switch (fa->feature_set) { case FEAT_COMPAT: set = BTRFS_FEATURE_COMPAT_SAFE_SET; clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR; break; case FEAT_COMPAT_RO: set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET; clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR; break; case FEAT_INCOMPAT: set = BTRFS_FEATURE_INCOMPAT_SAFE_SET; clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR; break; default: pr_warn("btrfs: sysfs: unknown feature set %d\n", fa->feature_set); return 0; } if (set & fa->feature_bit) val |= 1; if (clear & fa->feature_bit) val |= 2; return val; } static ssize_t btrfs_feature_attr_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { int val = 0; struct btrfs_fs_info *fs_info = to_fs_info(kobj); struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a); if (fs_info) { u64 features = get_features(fs_info, fa->feature_set); if (features & fa->feature_bit) val = 1; } else val = can_modify_feature(fa); return sysfs_emit(buf, "%d\n", val); } static ssize_t btrfs_feature_attr_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t count) { struct btrfs_fs_info *fs_info; struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a); u64 features, set, clear; unsigned long val; int ret; fs_info = to_fs_info(kobj); if (!fs_info) return -EPERM; if (sb_rdonly(fs_info->sb)) return -EROFS; ret = kstrtoul(skip_spaces(buf), 0, &val); if (ret) return ret; if (fa->feature_set == FEAT_COMPAT) { set = BTRFS_FEATURE_COMPAT_SAFE_SET; clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR; } else if (fa->feature_set == FEAT_COMPAT_RO) { set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET; clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR; } else { set = BTRFS_FEATURE_INCOMPAT_SAFE_SET; clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR; } features = get_features(fs_info, fa->feature_set); /* Nothing to do */ if ((val && (features & fa->feature_bit)) || (!val && !(features & fa->feature_bit))) return count; if ((val && !(set & fa->feature_bit)) || (!val && !(clear & fa->feature_bit))) { btrfs_info(fs_info, "%sabling feature %s on mounted fs is not supported.", val ? "En" : "Dis", fa->kobj_attr.attr.name); return -EPERM; } btrfs_info(fs_info, "%s %s feature flag", val ? "Setting" : "Clearing", fa->kobj_attr.attr.name); spin_lock(&fs_info->super_lock); features = get_features(fs_info, fa->feature_set); if (val) features |= fa->feature_bit; else features &= ~fa->feature_bit; set_features(fs_info, fa->feature_set, features); spin_unlock(&fs_info->super_lock); /* * We don't want to do full transaction commit from inside sysfs */ set_bit(BTRFS_FS_NEED_TRANS_COMMIT, &fs_info->flags); wake_up_process(fs_info->transaction_kthread); return count; } static umode_t btrfs_feature_visible(struct kobject *kobj, struct attribute *attr, int unused) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); umode_t mode = attr->mode; if (fs_info) { struct btrfs_feature_attr *fa; u64 features; fa = attr_to_btrfs_feature_attr(attr); features = get_features(fs_info, fa->feature_set); if (can_modify_feature(fa)) mode |= S_IWUSR; else if (!(features & fa->feature_bit)) mode = 0; } return mode; } BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL); BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS); BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO); BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD); BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID); BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); BTRFS_FEAT_ATTR_COMPAT_RO(block_group_tree, BLOCK_GROUP_TREE); BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34); BTRFS_FEAT_ATTR_INCOMPAT(simple_quota, SIMPLE_QUOTA); #ifdef CONFIG_BLK_DEV_ZONED BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED); #endif #ifdef CONFIG_BTRFS_DEBUG /* Remove once support for extent tree v2 is feature complete */ BTRFS_FEAT_ATTR_INCOMPAT(extent_tree_v2, EXTENT_TREE_V2); /* Remove once support for raid stripe tree is feature complete. */ BTRFS_FEAT_ATTR_INCOMPAT(raid_stripe_tree, RAID_STRIPE_TREE); #endif #ifdef CONFIG_FS_VERITY BTRFS_FEAT_ATTR_COMPAT_RO(verity, VERITY); #endif /* * Features which depend on feature bits and may differ between each fs. * * /sys/fs/btrfs/features - all available features implemented by this version * /sys/fs/btrfs/UUID/features - features of the fs which are enabled or * can be changed on a mounted filesystem. */ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(default_subvol), BTRFS_FEAT_ATTR_PTR(mixed_groups), BTRFS_FEAT_ATTR_PTR(compress_lzo), BTRFS_FEAT_ATTR_PTR(compress_zstd), BTRFS_FEAT_ATTR_PTR(extended_iref), BTRFS_FEAT_ATTR_PTR(raid56), BTRFS_FEAT_ATTR_PTR(skinny_metadata), BTRFS_FEAT_ATTR_PTR(no_holes), BTRFS_FEAT_ATTR_PTR(metadata_uuid), BTRFS_FEAT_ATTR_PTR(free_space_tree), BTRFS_FEAT_ATTR_PTR(raid1c34), BTRFS_FEAT_ATTR_PTR(block_group_tree), BTRFS_FEAT_ATTR_PTR(simple_quota), #ifdef CONFIG_BLK_DEV_ZONED BTRFS_FEAT_ATTR_PTR(zoned), #endif #ifdef CONFIG_BTRFS_DEBUG BTRFS_FEAT_ATTR_PTR(extent_tree_v2), BTRFS_FEAT_ATTR_PTR(raid_stripe_tree), #endif #ifdef CONFIG_FS_VERITY BTRFS_FEAT_ATTR_PTR(verity), #endif NULL }; static const struct attribute_group btrfs_feature_attr_group = { .name = "features", .is_visible = btrfs_feature_visible, .attrs = btrfs_supported_feature_attrs, }; static ssize_t rmdir_subvol_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { return sysfs_emit(buf, "0\n"); } BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show); static ssize_t supported_checksums_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { ssize_t ret = 0; int i; for (i = 0; i < btrfs_get_num_csums(); i++) { /* * This "trick" only works as long as 'enum btrfs_csum_type' has * no holes in it */ ret += sysfs_emit_at(buf, ret, "%s%s", (i == 0 ? "" : " "), btrfs_super_csum_name(i)); } ret += sysfs_emit_at(buf, ret, "\n"); return ret; } BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show); static ssize_t send_stream_version_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { return sysfs_emit(buf, "%d\n", BTRFS_SEND_STREAM_VERSION); } BTRFS_ATTR(static_feature, send_stream_version, send_stream_version_show); static const char *rescue_opts[] = { "usebackuproot", "nologreplay", "ignorebadroots", "ignoredatacsums", "all", }; static ssize_t supported_rescue_options_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { ssize_t ret = 0; int i; for (i = 0; i < ARRAY_SIZE(rescue_opts); i++) ret += sysfs_emit_at(buf, ret, "%s%s", (i ? " " : ""), rescue_opts[i]); ret += sysfs_emit_at(buf, ret, "\n"); return ret; } BTRFS_ATTR(static_feature, supported_rescue_options, supported_rescue_options_show); static ssize_t supported_sectorsizes_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { ssize_t ret = 0; /* An artificial limit to only support 4K and PAGE_SIZE */ if (PAGE_SIZE > SZ_4K) ret += sysfs_emit_at(buf, ret, "%u ", SZ_4K); ret += sysfs_emit_at(buf, ret, "%lu\n", PAGE_SIZE); return ret; } BTRFS_ATTR(static_feature, supported_sectorsizes, supported_sectorsizes_show); static ssize_t acl_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { return sysfs_emit(buf, "%d\n", IS_ENABLED(CONFIG_BTRFS_FS_POSIX_ACL)); } BTRFS_ATTR(static_feature, acl, acl_show); static ssize_t temp_fsid_supported_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { return sysfs_emit(buf, "0\n"); } BTRFS_ATTR(static_feature, temp_fsid, temp_fsid_supported_show); /* * Features which only depend on kernel version. * * These are listed in /sys/fs/btrfs/features along with * btrfs_supported_feature_attrs. */ static struct attribute *btrfs_supported_static_feature_attrs[] = { BTRFS_ATTR_PTR(static_feature, acl), BTRFS_ATTR_PTR(static_feature, rmdir_subvol), BTRFS_ATTR_PTR(static_feature, supported_checksums), BTRFS_ATTR_PTR(static_feature, send_stream_version), BTRFS_ATTR_PTR(static_feature, supported_rescue_options), BTRFS_ATTR_PTR(static_feature, supported_sectorsizes), BTRFS_ATTR_PTR(static_feature, temp_fsid), NULL }; static const struct attribute_group btrfs_static_feature_attr_group = { .name = "features", .attrs = btrfs_supported_static_feature_attrs, }; /* * Discard statistics and tunables */ #define discard_to_fs_info(_kobj) to_fs_info(get_btrfs_kobj(_kobj)) static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%lld\n", atomic64_read(&fs_info->discard_ctl.discardable_bytes)); } BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show); static ssize_t btrfs_discardable_extents_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%d\n", atomic_read(&fs_info->discard_ctl.discardable_extents)); } BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show); static ssize_t btrfs_discard_bitmap_bytes_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%llu\n", fs_info->discard_ctl.discard_bitmap_bytes); } BTRFS_ATTR(discard, discard_bitmap_bytes, btrfs_discard_bitmap_bytes_show); static ssize_t btrfs_discard_bytes_saved_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%lld\n", atomic64_read(&fs_info->discard_ctl.discard_bytes_saved)); } BTRFS_ATTR(discard, discard_bytes_saved, btrfs_discard_bytes_saved_show); static ssize_t btrfs_discard_extent_bytes_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%llu\n", fs_info->discard_ctl.discard_extent_bytes); } BTRFS_ATTR(discard, discard_extent_bytes, btrfs_discard_extent_bytes_show); static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%u\n", READ_ONCE(fs_info->discard_ctl.iops_limit)); } static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl; u32 iops_limit; int ret; ret = kstrtou32(buf, 10, &iops_limit); if (ret) return -EINVAL; WRITE_ONCE(discard_ctl->iops_limit, iops_limit); btrfs_discard_calc_delay(discard_ctl); btrfs_discard_schedule_work(discard_ctl, true); return len; } BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show, btrfs_discard_iops_limit_store); static ssize_t btrfs_discard_kbps_limit_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%u\n", READ_ONCE(fs_info->discard_ctl.kbps_limit)); } static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl; u32 kbps_limit; int ret; ret = kstrtou32(buf, 10, &kbps_limit); if (ret) return -EINVAL; WRITE_ONCE(discard_ctl->kbps_limit, kbps_limit); btrfs_discard_schedule_work(discard_ctl, true); return len; } BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show, btrfs_discard_kbps_limit_store); static ssize_t btrfs_discard_max_discard_size_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); return sysfs_emit(buf, "%llu\n", READ_ONCE(fs_info->discard_ctl.max_discard_size)); } static ssize_t btrfs_discard_max_discard_size_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl; u64 max_discard_size; int ret; ret = kstrtou64(buf, 10, &max_discard_size); if (ret) return -EINVAL; WRITE_ONCE(discard_ctl->max_discard_size, max_discard_size); return len; } BTRFS_ATTR_RW(discard, max_discard_size, btrfs_discard_max_discard_size_show, btrfs_discard_max_discard_size_store); /* * Per-filesystem stats for discard (when mounted with discard=async). * * Path: /sys/fs/btrfs/<uuid>/discard/ */ static const struct attribute *discard_attrs[] = { BTRFS_ATTR_PTR(discard, discardable_bytes), BTRFS_ATTR_PTR(discard, discardable_extents), BTRFS_ATTR_PTR(discard, discard_bitmap_bytes), BTRFS_ATTR_PTR(discard, discard_bytes_saved), BTRFS_ATTR_PTR(discard, discard_extent_bytes), BTRFS_ATTR_PTR(discard, iops_limit), BTRFS_ATTR_PTR(discard, kbps_limit), BTRFS_ATTR_PTR(discard, max_discard_size), NULL, }; #ifdef CONFIG_BTRFS_DEBUG /* * Per-filesystem runtime debugging exported via sysfs. * * Path: /sys/fs/btrfs/UUID/debug/ */ static const struct attribute *btrfs_debug_mount_attrs[] = { NULL, }; /* * Runtime debugging exported via sysfs, applies to all mounted filesystems. * * Path: /sys/fs/btrfs/debug */ static struct attribute *btrfs_debug_feature_attrs[] = { NULL }; static const struct attribute_group btrfs_debug_feature_attr_group = { .name = "debug", .attrs = btrfs_debug_feature_attrs, }; #endif static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf) { u64 val; if (lock) spin_lock(lock); val = *value_ptr; if (lock) spin_unlock(lock); return sysfs_emit(buf, "%llu\n", val); } static ssize_t global_rsv_size_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent); struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; return btrfs_show_u64(&block_rsv->size, &block_rsv->lock, buf); } BTRFS_ATTR(allocation, global_rsv_size, global_rsv_size_show); static ssize_t global_rsv_reserved_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent); struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; return btrfs_show_u64(&block_rsv->reserved, &block_rsv->lock, buf); } BTRFS_ATTR(allocation, global_rsv_reserved, global_rsv_reserved_show); #define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj) #define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj) static ssize_t raid_bytes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf); BTRFS_ATTR(raid, total_bytes, raid_bytes_show); BTRFS_ATTR(raid, used_bytes, raid_bytes_show); static ssize_t raid_bytes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct btrfs_space_info *sinfo = to_space_info(kobj->parent); struct btrfs_block_group *block_group; int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags); u64 val = 0; down_read(&sinfo->groups_sem); list_for_each_entry(block_group, &sinfo->block_groups[index], list) { if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes)) val += block_group->length; else val += block_group->used; } up_read(&sinfo->groups_sem); return sysfs_emit(buf, "%llu\n", val); } /* * Allocation information about block group profiles. * * Path: /sys/fs/btrfs/<uuid>/allocation/<bg-type>/<bg-profile>/ */ static struct attribute *raid_attrs[] = { BTRFS_ATTR_PTR(raid, total_bytes), BTRFS_ATTR_PTR(raid, used_bytes), NULL }; ATTRIBUTE_GROUPS(raid); static void release_raid_kobj(struct kobject *kobj) { kfree(to_raid_kobj(kobj)); } static const struct kobj_type btrfs_raid_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = release_raid_kobj, .default_groups = raid_groups, }; #define SPACE_INFO_ATTR(field) \ static ssize_t btrfs_space_info_show_##field(struct kobject *kobj, \ struct kobj_attribute *a, \ char *buf) \ { \ struct btrfs_space_info *sinfo = to_space_info(kobj); \ return btrfs_show_u64(&sinfo->field, &sinfo->lock, buf); \ } \ BTRFS_ATTR(space_info, field, btrfs_space_info_show_##field) static ssize_t btrfs_chunk_size_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_space_info *sinfo = to_space_info(kobj); return sysfs_emit(buf, "%llu\n", READ_ONCE(sinfo->chunk_size)); } /* * Store new chunk size in space info. Can be called on a read-only filesystem. * * If the new chunk size value is larger than 10% of free space it is reduced * to match that limit. Alignment must be to 256M and the system chunk size * cannot be set. */ static ssize_t btrfs_chunk_size_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_space_info *space_info = to_space_info(kobj); struct btrfs_fs_info *fs_info = to_fs_info(get_btrfs_kobj(kobj)); char *retptr; u64 val; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!fs_info->fs_devices) return -EINVAL; if (btrfs_is_zoned(fs_info)) return -EINVAL; /* System block type must not be changed. */ if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM) return -EPERM; val = memparse(buf, &retptr); /* There could be trailing '\n', also catch any typos after the value */ retptr = skip_spaces(retptr); if (*retptr != 0 || val == 0) return -EINVAL; val = min(val, BTRFS_MAX_DATA_CHUNK_SIZE); /* Limit stripe size to 10% of available space. */ val = min(mult_perc(fs_info->fs_devices->total_rw_bytes, 10), val); /* Must be multiple of 256M. */ val &= ~((u64)SZ_256M - 1); /* Must be at least 256M. */ if (val < SZ_256M) return -EINVAL; btrfs_update_space_info_chunk_size(space_info, val); return len; } static ssize_t btrfs_size_classes_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_space_info *sinfo = to_space_info(kobj); struct btrfs_block_group *bg; u32 none = 0; u32 small = 0; u32 medium = 0; u32 large = 0; for (int i = 0; i < BTRFS_NR_RAID_TYPES; ++i) { down_read(&sinfo->groups_sem); list_for_each_entry(bg, &sinfo->block_groups[i], list) { if (!btrfs_block_group_should_use_size_class(bg)) continue; switch (bg->size_class) { case BTRFS_BG_SZ_NONE: none++; break; case BTRFS_BG_SZ_SMALL: small++; break; case BTRFS_BG_SZ_MEDIUM: medium++; break; case BTRFS_BG_SZ_LARGE: large++; break; } } up_read(&sinfo->groups_sem); } return sysfs_emit(buf, "none %u\n" "small %u\n" "medium %u\n" "large %u\n", none, small, medium, large); } #ifdef CONFIG_BTRFS_DEBUG /* * Request chunk allocation with current chunk size. */ static ssize_t btrfs_force_chunk_alloc_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_space_info *space_info = to_space_info(kobj); struct btrfs_fs_info *fs_info = to_fs_info(get_btrfs_kobj(kobj)); struct btrfs_trans_handle *trans; bool val; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (sb_rdonly(fs_info->sb)) return -EROFS; ret = kstrtobool(buf, &val); if (ret) return ret; if (!val) return -EINVAL; /* * This is unsafe to be called from sysfs context and may cause * unexpected problems. */ trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); ret = btrfs_force_chunk_alloc(trans, space_info->flags); btrfs_end_transaction(trans); if (ret == 1) return len; return -ENOSPC; } BTRFS_ATTR_W(space_info, force_chunk_alloc, btrfs_force_chunk_alloc_store); #endif SPACE_INFO_ATTR(flags); SPACE_INFO_ATTR(total_bytes); SPACE_INFO_ATTR(bytes_used); SPACE_INFO_ATTR(bytes_pinned); SPACE_INFO_ATTR(bytes_reserved); SPACE_INFO_ATTR(bytes_may_use); SPACE_INFO_ATTR(bytes_readonly); SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR_RW(space_info, chunk_size, btrfs_chunk_size_show, btrfs_chunk_size_store); BTRFS_ATTR(space_info, size_classes, btrfs_size_classes_show); static ssize_t btrfs_sinfo_bg_reclaim_threshold_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_space_info *space_info = to_space_info(kobj); return sysfs_emit(buf, "%d\n", READ_ONCE(space_info->bg_reclaim_threshold)); } static ssize_t btrfs_sinfo_bg_reclaim_threshold_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_space_info *space_info = to_space_info(kobj); int thresh; int ret; ret = kstrtoint(buf, 10, &thresh); if (ret) return ret; if (thresh < 0 || thresh > 100) return -EINVAL; WRITE_ONCE(space_info->bg_reclaim_threshold, thresh); return len; } BTRFS_ATTR_RW(space_info, bg_reclaim_threshold, btrfs_sinfo_bg_reclaim_threshold_show, btrfs_sinfo_bg_reclaim_threshold_store); /* * Allocation information about block group types. * * Path: /sys/fs/btrfs/<uuid>/allocation/<bg-type>/ */ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, flags), BTRFS_ATTR_PTR(space_info, total_bytes), BTRFS_ATTR_PTR(space_info, bytes_used), BTRFS_ATTR_PTR(space_info, bytes_pinned), BTRFS_ATTR_PTR(space_info, bytes_reserved), BTRFS_ATTR_PTR(space_info, bytes_may_use), BTRFS_ATTR_PTR(space_info, bytes_readonly), BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, bg_reclaim_threshold), BTRFS_ATTR_PTR(space_info, chunk_size), BTRFS_ATTR_PTR(space_info, size_classes), #ifdef CONFIG_BTRFS_DEBUG BTRFS_ATTR_PTR(space_info, force_chunk_alloc), #endif NULL, }; ATTRIBUTE_GROUPS(space_info); static void space_info_release(struct kobject *kobj) { struct btrfs_space_info *sinfo = to_space_info(kobj); kfree(sinfo); } static const struct kobj_type space_info_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = space_info_release, .default_groups = space_info_groups, }; /* * Allocation information about block groups. * * Path: /sys/fs/btrfs/<uuid>/allocation/ */ static const struct attribute *allocation_attrs[] = { BTRFS_ATTR_PTR(allocation, global_rsv_reserved), BTRFS_ATTR_PTR(allocation, global_rsv_size), NULL, }; static ssize_t btrfs_label_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); char *label = fs_info->super_copy->label; ssize_t ret; spin_lock(&fs_info->super_lock); ret = sysfs_emit(buf, label[0] ? "%s\n" : "%s", label); spin_unlock(&fs_info->super_lock); return ret; } static ssize_t btrfs_label_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); size_t p_len; if (!fs_info) return -EPERM; if (sb_rdonly(fs_info->sb)) return -EROFS; /* * p_len is the len until the first occurrence of either * '\n' or '\0' */ p_len = strcspn(buf, "\n"); if (p_len >= BTRFS_LABEL_SIZE) return -EINVAL; spin_lock(&fs_info->super_lock); memset(fs_info->super_copy->label, 0, BTRFS_LABEL_SIZE); memcpy(fs_info->super_copy->label, buf, p_len); spin_unlock(&fs_info->super_lock); /* * We don't want to do full transaction commit from inside sysfs */ set_bit(BTRFS_FS_NEED_TRANS_COMMIT, &fs_info->flags); wake_up_process(fs_info->transaction_kthread); return len; } BTRFS_ATTR_RW(, label, btrfs_label_show, btrfs_label_store); static ssize_t btrfs_nodesize_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); static ssize_t btrfs_sectorsize_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); static ssize_t btrfs_commit_stats_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "commits %llu\n" "last_commit_ms %llu\n" "max_commit_ms %llu\n" "total_commit_ms %llu\n", fs_info->commit_stats.commit_count, div_u64(fs_info->commit_stats.last_commit_dur, NSEC_PER_MSEC), div_u64(fs_info->commit_stats.max_commit_dur, NSEC_PER_MSEC), div_u64(fs_info->commit_stats.total_commit_dur, NSEC_PER_MSEC)); } static ssize_t btrfs_commit_stats_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); unsigned long val; int ret; if (!fs_info) return -EPERM; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; ret = kstrtoul(buf, 10, &val); if (ret) return ret; if (val) return -EINVAL; WRITE_ONCE(fs_info->commit_stats.max_commit_dur, 0); return len; } BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store); static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); static ssize_t quota_override_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); int quota_override; quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); return sysfs_emit(buf, "%d\n", quota_override); } static ssize_t quota_override_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); unsigned long knob; int err; if (!fs_info) return -EPERM; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; err = kstrtoul(buf, 10, &knob); if (err) return err; if (knob > 1) return -EINVAL; if (knob) set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); else clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); return len; } BTRFS_ATTR_RW(, quota_override, quota_override_show, quota_override_store); static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%pU\n", fs_info->fs_devices->metadata_uuid); } BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show); static ssize_t btrfs_checksum_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); u16 csum_type = btrfs_super_csum_type(fs_info->super_copy); return sysfs_emit(buf, "%s (%s)\n", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(fs_info->csum_shash)); } BTRFS_ATTR(, checksum, btrfs_checksum_show); static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); const char *str; switch (READ_ONCE(fs_info->exclusive_operation)) { case BTRFS_EXCLOP_NONE: str = "none\n"; break; case BTRFS_EXCLOP_BALANCE: str = "balance\n"; break; case BTRFS_EXCLOP_BALANCE_PAUSED: str = "balance paused\n"; break; case BTRFS_EXCLOP_DEV_ADD: str = "device add\n"; break; case BTRFS_EXCLOP_DEV_REMOVE: str = "device remove\n"; break; case BTRFS_EXCLOP_DEV_REPLACE: str = "device replace\n"; break; case BTRFS_EXCLOP_RESIZE: str = "resize\n"; break; case BTRFS_EXCLOP_SWAP_ACTIVATE: str = "swap activate\n"; break; default: str = "UNKNOWN\n"; break; } return sysfs_emit(buf, "%s", str); } BTRFS_ATTR(, exclusive_operation, btrfs_exclusive_operation_show); static ssize_t btrfs_generation_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%llu\n", btrfs_get_fs_generation(fs_info)); } BTRFS_ATTR(, generation, btrfs_generation_show); static ssize_t btrfs_temp_fsid_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%d\n", fs_info->fs_devices->temp_fsid); } BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show); static const char * const btrfs_read_policy_name[] = { "pid" }; static ssize_t btrfs_read_policy_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); const enum btrfs_read_policy policy = READ_ONCE(fs_devices->read_policy); ssize_t ret = 0; int i; for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { if (policy == i) ret += sysfs_emit_at(buf, ret, "%s[%s]", (ret == 0 ? "" : " "), btrfs_read_policy_name[i]); else ret += sysfs_emit_at(buf, ret, "%s%s", (ret == 0 ? "" : " "), btrfs_read_policy_name[i]); } ret += sysfs_emit_at(buf, ret, "\n"); return ret; } static ssize_t btrfs_read_policy_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); int i; for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { if (sysfs_streq(buf, btrfs_read_policy_name[i])) { if (i != READ_ONCE(fs_devices->read_policy)) { WRITE_ONCE(fs_devices->read_policy, i); btrfs_info(fs_devices->fs_info, "read policy set to '%s'", btrfs_read_policy_name[i]); } return len; } } return -EINVAL; } BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store); static ssize_t btrfs_bg_reclaim_threshold_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); return sysfs_emit(buf, "%d\n", READ_ONCE(fs_info->bg_reclaim_threshold)); } static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = to_fs_info(kobj); int thresh; int ret; ret = kstrtoint(buf, 10, &thresh); if (ret) return ret; #ifdef CONFIG_BTRFS_DEBUG if (thresh != 0 && (thresh > 100)) return -EINVAL; #else if (thresh != 0 && (thresh <= 50 || thresh > 100)) return -EINVAL; #endif WRITE_ONCE(fs_info->bg_reclaim_threshold, thresh); return len; } BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show, btrfs_bg_reclaim_threshold_store); #ifdef CONFIG_BTRFS_DEBUG static ssize_t btrfs_offload_csum_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); switch (READ_ONCE(fs_devices->offload_csum_mode)) { case BTRFS_OFFLOAD_CSUM_AUTO: return sysfs_emit(buf, "auto\n"); case BTRFS_OFFLOAD_CSUM_FORCE_ON: return sysfs_emit(buf, "1\n"); case BTRFS_OFFLOAD_CSUM_FORCE_OFF: return sysfs_emit(buf, "0\n"); default: WARN_ON(1); return -EINVAL; } } static ssize_t btrfs_offload_csum_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); int ret; bool val; ret = kstrtobool(buf, &val); if (ret == 0) WRITE_ONCE(fs_devices->offload_csum_mode, val ? BTRFS_OFFLOAD_CSUM_FORCE_ON : BTRFS_OFFLOAD_CSUM_FORCE_OFF); else if (ret == -EINVAL && sysfs_streq(buf, "auto")) WRITE_ONCE(fs_devices->offload_csum_mode, BTRFS_OFFLOAD_CSUM_AUTO); else return -EINVAL; return len; } BTRFS_ATTR_RW(, offload_csum, btrfs_offload_csum_show, btrfs_offload_csum_store); #endif /* * Per-filesystem information and stats. * * Path: /sys/fs/btrfs/<uuid>/ */ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, label), BTRFS_ATTR_PTR(, nodesize), BTRFS_ATTR_PTR(, sectorsize), BTRFS_ATTR_PTR(, clone_alignment), BTRFS_ATTR_PTR(, quota_override), BTRFS_ATTR_PTR(, metadata_uuid), BTRFS_ATTR_PTR(, checksum), BTRFS_ATTR_PTR(, exclusive_operation), BTRFS_ATTR_PTR(, generation), BTRFS_ATTR_PTR(, read_policy), BTRFS_ATTR_PTR(, bg_reclaim_threshold), BTRFS_ATTR_PTR(, commit_stats), BTRFS_ATTR_PTR(, temp_fsid), #ifdef CONFIG_BTRFS_DEBUG BTRFS_ATTR_PTR(, offload_csum), #endif NULL, }; static void btrfs_release_fsid_kobj(struct kobject *kobj) { struct btrfs_fs_devices *fs_devs = to_fs_devs(kobj); memset(&fs_devs->fsid_kobj, 0, sizeof(struct kobject)); complete(&fs_devs->kobj_unregister); } static const struct kobj_type btrfs_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = btrfs_release_fsid_kobj, }; static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj) { if (kobj->ktype != &btrfs_ktype) return NULL; return container_of(kobj, struct btrfs_fs_devices, fsid_kobj); } static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj) { if (kobj->ktype != &btrfs_ktype) return NULL; return to_fs_devs(kobj)->fs_info; } static struct kobject *get_btrfs_kobj(struct kobject *kobj) { while (kobj) { if (kobj->ktype == &btrfs_ktype) return kobj; kobj = kobj->parent; } return NULL; } #define NUM_FEATURE_BITS 64 #define BTRFS_FEATURE_NAME_MAX 13 static char btrfs_unknown_feature_names[FEAT_MAX][NUM_FEATURE_BITS][BTRFS_FEATURE_NAME_MAX]; static struct btrfs_feature_attr btrfs_feature_attrs[FEAT_MAX][NUM_FEATURE_BITS]; static_assert(ARRAY_SIZE(btrfs_unknown_feature_names) == ARRAY_SIZE(btrfs_feature_attrs)); static_assert(ARRAY_SIZE(btrfs_unknown_feature_names[0]) == ARRAY_SIZE(btrfs_feature_attrs[0])); static const u64 supported_feature_masks[FEAT_MAX] = { [FEAT_COMPAT] = BTRFS_FEATURE_COMPAT_SUPP, [FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP, [FEAT_INCOMPAT] = BTRFS_FEATURE_INCOMPAT_SUPP, }; static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add) { int set; for (set = 0; set < FEAT_MAX; set++) { int i; struct attribute *attrs[2]; struct attribute_group agroup = { .name = "features", .attrs = attrs, }; u64 features = get_features(fs_info, set); features &= ~supported_feature_masks[set]; if (!features) continue; attrs[1] = NULL; for (i = 0; i < NUM_FEATURE_BITS; i++) { struct btrfs_feature_attr *fa; if (!(features & (1ULL << i))) continue; fa = &btrfs_feature_attrs[set][i]; attrs[0] = &fa->kobj_attr.attr; if (add) { int ret; ret = sysfs_merge_group(&fs_info->fs_devices->fsid_kobj, &agroup); if (ret) return ret; } else sysfs_unmerge_group(&fs_info->fs_devices->fsid_kobj, &agroup); } } return 0; } static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) { if (fs_devs->devinfo_kobj) { kobject_del(fs_devs->devinfo_kobj); kobject_put(fs_devs->devinfo_kobj); fs_devs->devinfo_kobj = NULL; } if (fs_devs->devices_kobj) { kobject_del(fs_devs->devices_kobj); kobject_put(fs_devs->devices_kobj); fs_devs->devices_kobj = NULL; } if (fs_devs->fsid_kobj.state_initialized) { kobject_del(&fs_devs->fsid_kobj); kobject_put(&fs_devs->fsid_kobj); wait_for_completion(&fs_devs->kobj_unregister); } } /* when fs_devs is NULL it will remove all fsid kobject */ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) { struct list_head *fs_uuids = btrfs_get_fs_uuids(); if (fs_devs) { __btrfs_sysfs_remove_fsid(fs_devs); return; } list_for_each_entry(fs_devs, fs_uuids, fs_list) { __btrfs_sysfs_remove_fsid(fs_devs); } } static void btrfs_sysfs_remove_fs_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device; struct btrfs_fs_devices *seed; list_for_each_entry(device, &fs_devices->devices, dev_list) btrfs_sysfs_remove_device(device); list_for_each_entry(seed, &fs_devices->seed_list, seed_list) { list_for_each_entry(device, &seed->devices, dev_list) btrfs_sysfs_remove_device(device); } } void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info) { struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj; sysfs_remove_link(fsid_kobj, "bdi"); if (fs_info->space_info_kobj) { sysfs_remove_files(fs_info->space_info_kobj, allocation_attrs); kobject_del(fs_info->space_info_kobj); kobject_put(fs_info->space_info_kobj); } if (fs_info->discard_kobj) { sysfs_remove_files(fs_info->discard_kobj, discard_attrs); kobject_del(fs_info->discard_kobj); kobject_put(fs_info->discard_kobj); } #ifdef CONFIG_BTRFS_DEBUG if (fs_info->debug_kobj) { sysfs_remove_files(fs_info->debug_kobj, btrfs_debug_mount_attrs); kobject_del(fs_info->debug_kobj); kobject_put(fs_info->debug_kobj); } #endif addrm_unknown_feature_attrs(fs_info, false); sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group); sysfs_remove_files(fsid_kobj, btrfs_attrs); btrfs_sysfs_remove_fs_devices(fs_info->fs_devices); } static const char * const btrfs_feature_set_names[FEAT_MAX] = { [FEAT_COMPAT] = "compat", [FEAT_COMPAT_RO] = "compat_ro", [FEAT_INCOMPAT] = "incompat", }; const char *btrfs_feature_set_name(enum btrfs_feature_set set) { return btrfs_feature_set_names[set]; } char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags) { size_t bufsize = 4096; /* safe max, 64 names * 64 bytes */ int len = 0; int i; char *str; str = kmalloc(bufsize, GFP_KERNEL); if (!str) return str; for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) { const char *name; if (!(flags & (1ULL << i))) continue; name = btrfs_feature_attrs[set][i].kobj_attr.attr.name; len += scnprintf(str + len, bufsize - len, "%s%s", len ? "," : "", name); } return str; } static void init_feature_attrs(void) { struct btrfs_feature_attr *fa; int set, i; memset(btrfs_feature_attrs, 0, sizeof(btrfs_feature_attrs)); memset(btrfs_unknown_feature_names, 0, sizeof(btrfs_unknown_feature_names)); for (i = 0; btrfs_supported_feature_attrs[i]; i++) { struct btrfs_feature_attr *sfa; struct attribute *a = btrfs_supported_feature_attrs[i]; int bit; sfa = attr_to_btrfs_feature_attr(a); bit = ilog2(sfa->feature_bit); fa = &btrfs_feature_attrs[sfa->feature_set][bit]; fa->kobj_attr.attr.name = sfa->kobj_attr.attr.name; } for (set = 0; set < FEAT_MAX; set++) { for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) { char *name = btrfs_unknown_feature_names[set][i]; fa = &btrfs_feature_attrs[set][i]; if (fa->kobj_attr.attr.name) continue; snprintf(name, BTRFS_FEATURE_NAME_MAX, "%s:%u", btrfs_feature_set_names[set], i); fa->kobj_attr.attr.name = name; fa->kobj_attr.attr.mode = S_IRUGO; fa->feature_set = set; fa->feature_bit = 1ULL << i; } } } /* * Create a sysfs entry for a given block group type at path * /sys/fs/btrfs/UUID/allocation/data/TYPE */ void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_space_info *space_info = cache->space_info; struct raid_kobject *rkobj; const int index = btrfs_bg_flags_to_raid_index(cache->flags); unsigned int nofs_flag; int ret; /* * Setup a NOFS context because kobject_add(), deep in its call chain, * does GFP_KERNEL allocations, and we are often called in a context * where if reclaim is triggered we can deadlock (we are either holding * a transaction handle or some lock required for a transaction * commit). */ nofs_flag = memalloc_nofs_save(); rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS); if (!rkobj) { memalloc_nofs_restore(nofs_flag); btrfs_warn(cache->fs_info, "couldn't alloc memory for raid level kobject"); return; } rkobj->flags = cache->flags; kobject_init(&rkobj->kobj, &btrfs_raid_ktype); /* * We call this either on mount, or if we've created a block group for a * new index type while running (i.e. when restriping). The running * case is tricky because we could race with other threads, so we need * to have this check to make sure we didn't already init the kobject. * * We don't have to protect on the free side because it only happens on * unmount. */ spin_lock(&space_info->lock); if (space_info->block_group_kobjs[index]) { spin_unlock(&space_info->lock); kobject_put(&rkobj->kobj); return; } else { space_info->block_group_kobjs[index] = &rkobj->kobj; } spin_unlock(&space_info->lock); ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s", btrfs_bg_type_to_raid_name(rkobj->flags)); memalloc_nofs_restore(nofs_flag); if (ret) { spin_lock(&space_info->lock); space_info->block_group_kobjs[index] = NULL; spin_unlock(&space_info->lock); kobject_put(&rkobj->kobj); btrfs_warn(fs_info, "failed to add kobject for block cache, ignoring"); return; } } /* * Remove sysfs directories for all block group types of a given space info and * the space info as well */ void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info) { int i; for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { struct kobject *kobj; kobj = space_info->block_group_kobjs[i]; space_info->block_group_kobjs[i] = NULL; if (kobj) { kobject_del(kobj); kobject_put(kobj); } } kobject_del(&space_info->kobj); kobject_put(&space_info->kobj); } static const char *alloc_name(u64 flags) { switch (flags) { case BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA: return "mixed"; case BTRFS_BLOCK_GROUP_METADATA: return "metadata"; case BTRFS_BLOCK_GROUP_DATA: return "data"; case BTRFS_BLOCK_GROUP_SYSTEM: return "system"; default: WARN_ON(1); return "invalid-combination"; } } /* * Create a sysfs entry for a space info type at path * /sys/fs/btrfs/UUID/allocation/TYPE */ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info) { int ret; ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype, fs_info->space_info_kobj, "%s", alloc_name(space_info->flags)); if (ret) { kobject_put(&space_info->kobj); return ret; } return 0; } void btrfs_sysfs_remove_device(struct btrfs_device *device) { struct kobject *devices_kobj; /* * Seed fs_devices devices_kobj aren't used, fetch kobject from the * fs_info::fs_devices. */ devices_kobj = device->fs_info->fs_devices->devices_kobj; ASSERT(devices_kobj); if (device->bdev) sysfs_remove_link(devices_kobj, bdev_kobj(device->bdev)->name); if (device->devid_kobj.state_initialized) { kobject_del(&device->devid_kobj); kobject_put(&device->devid_kobj); wait_for_completion(&device->kobj_unregister); } } static ssize_t btrfs_devinfo_in_fs_metadata_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { int val; struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); val = !!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); return sysfs_emit(buf, "%d\n", val); } BTRFS_ATTR(devid, in_fs_metadata, btrfs_devinfo_in_fs_metadata_show); static ssize_t btrfs_devinfo_missing_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { int val; struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); val = !!test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state); return sysfs_emit(buf, "%d\n", val); } BTRFS_ATTR(devid, missing, btrfs_devinfo_missing_show); static ssize_t btrfs_devinfo_replace_target_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { int val; struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); val = !!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); return sysfs_emit(buf, "%d\n", val); } BTRFS_ATTR(devid, replace_target, btrfs_devinfo_replace_target_show); static ssize_t btrfs_devinfo_scrub_speed_max_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); return sysfs_emit(buf, "%llu\n", READ_ONCE(device->scrub_speed_max)); } static ssize_t btrfs_devinfo_scrub_speed_max_store(struct kobject *kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); char *endptr; unsigned long long limit; limit = memparse(buf, &endptr); /* There could be trailing '\n', also catch any typos after the value. */ endptr = skip_spaces(endptr); if (*endptr != 0) return -EINVAL; WRITE_ONCE(device->scrub_speed_max, limit); return len; } BTRFS_ATTR_RW(devid, scrub_speed_max, btrfs_devinfo_scrub_speed_max_show, btrfs_devinfo_scrub_speed_max_store); static ssize_t btrfs_devinfo_writeable_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { int val; struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); val = !!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); return sysfs_emit(buf, "%d\n", val); } BTRFS_ATTR(devid, writeable, btrfs_devinfo_writeable_show); static ssize_t btrfs_devinfo_fsid_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); return sysfs_emit(buf, "%pU\n", device->fs_devices->fsid); } BTRFS_ATTR(devid, fsid, btrfs_devinfo_fsid_show); static ssize_t btrfs_devinfo_error_stats_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); if (!device->dev_stats_valid) return sysfs_emit(buf, "invalid\n"); /* * Print all at once so we get a snapshot of all values from the same * time. Keep them in sync and in order of definition of * btrfs_dev_stat_values. */ return sysfs_emit(buf, "write_errs %d\n" "read_errs %d\n" "flush_errs %d\n" "corruption_errs %d\n" "generation_errs %d\n", btrfs_dev_stat_read(device, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(device, BTRFS_DEV_STAT_READ_ERRS), btrfs_dev_stat_read(device, BTRFS_DEV_STAT_FLUSH_ERRS), btrfs_dev_stat_read(device, BTRFS_DEV_STAT_CORRUPTION_ERRS), btrfs_dev_stat_read(device, BTRFS_DEV_STAT_GENERATION_ERRS)); } BTRFS_ATTR(devid, error_stats, btrfs_devinfo_error_stats_show); /* * Information about one device. * * Path: /sys/fs/btrfs/<uuid>/devinfo/<devid>/ */ static struct attribute *devid_attrs[] = { BTRFS_ATTR_PTR(devid, error_stats), BTRFS_ATTR_PTR(devid, fsid), BTRFS_ATTR_PTR(devid, in_fs_metadata), BTRFS_ATTR_PTR(devid, missing), BTRFS_ATTR_PTR(devid, replace_target), BTRFS_ATTR_PTR(devid, scrub_speed_max), BTRFS_ATTR_PTR(devid, writeable), NULL }; ATTRIBUTE_GROUPS(devid); static void btrfs_release_devid_kobj(struct kobject *kobj) { struct btrfs_device *device = container_of(kobj, struct btrfs_device, devid_kobj); memset(&device->devid_kobj, 0, sizeof(struct kobject)); complete(&device->kobj_unregister); } static const struct kobj_type devid_ktype = { .sysfs_ops = &kobj_sysfs_ops, .default_groups = devid_groups, .release = btrfs_release_devid_kobj, }; int btrfs_sysfs_add_device(struct btrfs_device *device) { int ret; unsigned int nofs_flag; struct kobject *devices_kobj; struct kobject *devinfo_kobj; /* * Make sure we use the fs_info::fs_devices to fetch the kobjects even * for the seed fs_devices */ devices_kobj = device->fs_info->fs_devices->devices_kobj; devinfo_kobj = device->fs_info->fs_devices->devinfo_kobj; ASSERT(devices_kobj); ASSERT(devinfo_kobj); nofs_flag = memalloc_nofs_save(); if (device->bdev) { struct kobject *disk_kobj = bdev_kobj(device->bdev); ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name); if (ret) { btrfs_warn(device->fs_info, "creating sysfs device link for devid %llu failed: %d", device->devid, ret); goto out; } } init_completion(&device->kobj_unregister); ret = kobject_init_and_add(&device->devid_kobj, &devid_ktype, devinfo_kobj, "%llu", device->devid); if (ret) { kobject_put(&device->devid_kobj); btrfs_warn(device->fs_info, "devinfo init for devid %llu failed: %d", device->devid, ret); } out: memalloc_nofs_restore(nofs_flag); return ret; } static int btrfs_sysfs_add_fs_devices(struct btrfs_fs_devices *fs_devices) { int ret; struct btrfs_device *device; struct btrfs_fs_devices *seed; list_for_each_entry(device, &fs_devices->devices, dev_list) { ret = btrfs_sysfs_add_device(device); if (ret) goto fail; } list_for_each_entry(seed, &fs_devices->seed_list, seed_list) { list_for_each_entry(device, &seed->devices, dev_list) { ret = btrfs_sysfs_add_device(device); if (ret) goto fail; } } return 0; fail: btrfs_sysfs_remove_fs_devices(fs_devices); return ret; } void btrfs_kobject_uevent(struct block_device *bdev, enum kobject_action action) { int ret; ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action); if (ret) pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n", action, kobject_name(&disk_to_dev(bdev->bd_disk)->kobj), &disk_to_dev(bdev->bd_disk)->kobj); } void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices) { char fsid_buf[BTRFS_UUID_UNPARSED_SIZE]; /* * Sprouting changes fsid of the mounted filesystem, rename the fsid * directory */ snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU", fs_devices->fsid); if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf)) btrfs_warn(fs_devices->fs_info, "sysfs: failed to create fsid for sprout"); } void btrfs_sysfs_update_devid(struct btrfs_device *device) { char tmp[24]; snprintf(tmp, sizeof(tmp), "%llu", device->devid); if (kobject_rename(&device->devid_kobj, tmp)) btrfs_warn(device->fs_devices->fs_info, "sysfs: failed to update devid for %llu", device->devid); } /* /sys/fs/btrfs/ entry */ static struct kset *btrfs_kset; /* * Creates: * /sys/fs/btrfs/UUID * * Can be called by the device discovery thread. */ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs) { int error; init_completion(&fs_devs->kobj_unregister); fs_devs->fsid_kobj.kset = btrfs_kset; error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, NULL, "%pU", fs_devs->fsid); if (error) { kobject_put(&fs_devs->fsid_kobj); return error; } fs_devs->devices_kobj = kobject_create_and_add("devices", &fs_devs->fsid_kobj); if (!fs_devs->devices_kobj) { btrfs_err(fs_devs->fs_info, "failed to init sysfs device interface"); btrfs_sysfs_remove_fsid(fs_devs); return -ENOMEM; } fs_devs->devinfo_kobj = kobject_create_and_add("devinfo", &fs_devs->fsid_kobj); if (!fs_devs->devinfo_kobj) { btrfs_err(fs_devs->fs_info, "failed to init sysfs devinfo kobject"); btrfs_sysfs_remove_fsid(fs_devs); return -ENOMEM; } return 0; } int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) { int error; struct btrfs_fs_devices *fs_devs = fs_info->fs_devices; struct kobject *fsid_kobj = &fs_devs->fsid_kobj; error = btrfs_sysfs_add_fs_devices(fs_devs); if (error) return error; error = sysfs_create_files(fsid_kobj, btrfs_attrs); if (error) { btrfs_sysfs_remove_fs_devices(fs_devs); return error; } error = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); if (error) goto failure; #ifdef CONFIG_BTRFS_DEBUG fs_info->debug_kobj = kobject_create_and_add("debug", fsid_kobj); if (!fs_info->debug_kobj) { error = -ENOMEM; goto failure; } error = sysfs_create_files(fs_info->debug_kobj, btrfs_debug_mount_attrs); if (error) goto failure; #endif /* Discard directory */ fs_info->discard_kobj = kobject_create_and_add("discard", fsid_kobj); if (!fs_info->discard_kobj) { error = -ENOMEM; goto failure; } error = sysfs_create_files(fs_info->discard_kobj, discard_attrs); if (error) goto failure; error = addrm_unknown_feature_attrs(fs_info, true); if (error) goto failure; error = sysfs_create_link(fsid_kobj, &fs_info->sb->s_bdi->dev->kobj, "bdi"); if (error) goto failure; fs_info->space_info_kobj = kobject_create_and_add("allocation", fsid_kobj); if (!fs_info->space_info_kobj) { error = -ENOMEM; goto failure; } error = sysfs_create_files(fs_info->space_info_kobj, allocation_attrs); if (error) goto failure; return 0; failure: btrfs_sysfs_remove_mounted(fs_info); return error; } static ssize_t qgroup_enabled_show(struct kobject *qgroups_kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(qgroups_kobj->parent); bool enabled; spin_lock(&fs_info->qgroup_lock); enabled = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON; spin_unlock(&fs_info->qgroup_lock); return sysfs_emit(buf, "%d\n", enabled); } BTRFS_ATTR(qgroups, enabled, qgroup_enabled_show); static ssize_t qgroup_mode_show(struct kobject *qgroups_kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(qgroups_kobj->parent); ssize_t ret = 0; spin_lock(&fs_info->qgroup_lock); ASSERT(btrfs_qgroup_enabled(fs_info)); switch (btrfs_qgroup_mode(fs_info)) { case BTRFS_QGROUP_MODE_FULL: ret = sysfs_emit(buf, "qgroup\n"); break; case BTRFS_QGROUP_MODE_SIMPLE: ret = sysfs_emit(buf, "squota\n"); break; default: btrfs_warn(fs_info, "unexpected qgroup mode %d\n", btrfs_qgroup_mode(fs_info)); break; } spin_unlock(&fs_info->qgroup_lock); return ret; } BTRFS_ATTR(qgroups, mode, qgroup_mode_show); static ssize_t qgroup_inconsistent_show(struct kobject *qgroups_kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(qgroups_kobj->parent); bool inconsistent; spin_lock(&fs_info->qgroup_lock); inconsistent = (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT); spin_unlock(&fs_info->qgroup_lock); return sysfs_emit(buf, "%d\n", inconsistent); } BTRFS_ATTR(qgroups, inconsistent, qgroup_inconsistent_show); static ssize_t qgroup_drop_subtree_thres_show(struct kobject *qgroups_kobj, struct kobj_attribute *a, char *buf) { struct btrfs_fs_info *fs_info = to_fs_info(qgroups_kobj->parent); u8 result; spin_lock(&fs_info->qgroup_lock); result = fs_info->qgroup_drop_subtree_thres; spin_unlock(&fs_info->qgroup_lock); return sysfs_emit(buf, "%d\n", result); } static ssize_t qgroup_drop_subtree_thres_store(struct kobject *qgroups_kobj, struct kobj_attribute *a, const char *buf, size_t len) { struct btrfs_fs_info *fs_info = to_fs_info(qgroups_kobj->parent); u8 new_thres; int ret; ret = kstrtou8(buf, 10, &new_thres); if (ret) return -EINVAL; if (new_thres > BTRFS_MAX_LEVEL) return -EINVAL; spin_lock(&fs_info->qgroup_lock); fs_info->qgroup_drop_subtree_thres = new_thres; spin_unlock(&fs_info->qgroup_lock); return len; } BTRFS_ATTR_RW(qgroups, drop_subtree_threshold, qgroup_drop_subtree_thres_show, qgroup_drop_subtree_thres_store); /* * Qgroups global info * * Path: /sys/fs/btrfs/<uuid>/qgroups/ */ static struct attribute *qgroups_attrs[] = { BTRFS_ATTR_PTR(qgroups, enabled), BTRFS_ATTR_PTR(qgroups, inconsistent), BTRFS_ATTR_PTR(qgroups, drop_subtree_threshold), BTRFS_ATTR_PTR(qgroups, mode), NULL }; ATTRIBUTE_GROUPS(qgroups); static void qgroups_release(struct kobject *kobj) { kfree(kobj); } static const struct kobj_type qgroups_ktype = { .sysfs_ops = &kobj_sysfs_ops, .default_groups = qgroups_groups, .release = qgroups_release, }; static inline struct btrfs_fs_info *qgroup_kobj_to_fs_info(struct kobject *kobj) { return to_fs_info(kobj->parent->parent); } #define QGROUP_ATTR(_member, _show_name) \ static ssize_t btrfs_qgroup_show_##_member(struct kobject *qgroup_kobj, \ struct kobj_attribute *a, \ char *buf) \ { \ struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \ struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \ struct btrfs_qgroup, kobj); \ return btrfs_show_u64(&qgroup->_member, &fs_info->qgroup_lock, buf); \ } \ BTRFS_ATTR(qgroup, _show_name, btrfs_qgroup_show_##_member) #define QGROUP_RSV_ATTR(_name, _type) \ static ssize_t btrfs_qgroup_rsv_show_##_name(struct kobject *qgroup_kobj, \ struct kobj_attribute *a, \ char *buf) \ { \ struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \ struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \ struct btrfs_qgroup, kobj); \ return btrfs_show_u64(&qgroup->rsv.values[_type], \ &fs_info->qgroup_lock, buf); \ } \ BTRFS_ATTR(qgroup, rsv_##_name, btrfs_qgroup_rsv_show_##_name) QGROUP_ATTR(rfer, referenced); QGROUP_ATTR(excl, exclusive); QGROUP_ATTR(max_rfer, max_referenced); QGROUP_ATTR(max_excl, max_exclusive); QGROUP_ATTR(lim_flags, limit_flags); QGROUP_RSV_ATTR(data, BTRFS_QGROUP_RSV_DATA); QGROUP_RSV_ATTR(meta_pertrans, BTRFS_QGROUP_RSV_META_PERTRANS); QGROUP_RSV_ATTR(meta_prealloc, BTRFS_QGROUP_RSV_META_PREALLOC); /* * Qgroup information. * * Path: /sys/fs/btrfs/<uuid>/qgroups/<level>_<qgroupid>/ */ static struct attribute *qgroup_attrs[] = { BTRFS_ATTR_PTR(qgroup, referenced), BTRFS_ATTR_PTR(qgroup, exclusive), BTRFS_ATTR_PTR(qgroup, max_referenced), BTRFS_ATTR_PTR(qgroup, max_exclusive), BTRFS_ATTR_PTR(qgroup, limit_flags), BTRFS_ATTR_PTR(qgroup, rsv_data), BTRFS_ATTR_PTR(qgroup, rsv_meta_pertrans), BTRFS_ATTR_PTR(qgroup, rsv_meta_prealloc), NULL }; ATTRIBUTE_GROUPS(qgroup); static void qgroup_release(struct kobject *kobj) { struct btrfs_qgroup *qgroup = container_of(kobj, struct btrfs_qgroup, kobj); memset(&qgroup->kobj, 0, sizeof(*kobj)); } static const struct kobj_type qgroup_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = qgroup_release, .default_groups = qgroup_groups, }; int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { struct kobject *qgroups_kobj = fs_info->qgroups_kobj; int ret; if (btrfs_is_testing(fs_info)) return 0; if (qgroup->kobj.state_initialized) return 0; if (!qgroups_kobj) return -EINVAL; ret = kobject_init_and_add(&qgroup->kobj, &qgroup_ktype, qgroups_kobj, "%hu_%llu", btrfs_qgroup_level(qgroup->qgroupid), btrfs_qgroup_subvolid(qgroup->qgroupid)); if (ret < 0) kobject_put(&qgroup->kobj); return ret; } void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info) { struct btrfs_qgroup *qgroup; struct btrfs_qgroup *next; if (btrfs_is_testing(fs_info)) return; rbtree_postorder_for_each_entry_safe(qgroup, next, &fs_info->qgroup_tree, node) btrfs_sysfs_del_one_qgroup(fs_info, qgroup); if (fs_info->qgroups_kobj) { kobject_del(fs_info->qgroups_kobj); kobject_put(fs_info->qgroups_kobj); fs_info->qgroups_kobj = NULL; } } /* Called when qgroups get initialized, thus there is no need for locking */ int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info) { struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj; struct btrfs_qgroup *qgroup; struct btrfs_qgroup *next; int ret = 0; if (btrfs_is_testing(fs_info)) return 0; ASSERT(fsid_kobj); if (fs_info->qgroups_kobj) return 0; fs_info->qgroups_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!fs_info->qgroups_kobj) return -ENOMEM; ret = kobject_init_and_add(fs_info->qgroups_kobj, &qgroups_ktype, fsid_kobj, "qgroups"); if (ret < 0) goto out; rbtree_postorder_for_each_entry_safe(qgroup, next, &fs_info->qgroup_tree, node) { ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (ret < 0) goto out; } out: if (ret < 0) btrfs_sysfs_del_qgroups(fs_info); return ret; } void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { if (btrfs_is_testing(fs_info)) return; if (qgroup->kobj.state_initialized) { kobject_del(&qgroup->kobj); kobject_put(&qgroup->kobj); } } /* * Change per-fs features in /sys/fs/btrfs/UUID/features to match current * values in superblock. Call after any changes to incompat/compat_ro flags */ void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info) { struct kobject *fsid_kobj; int ret; if (!fs_info) return; fsid_kobj = &fs_info->fs_devices->fsid_kobj; if (!fsid_kobj->state_initialized) return; ret = sysfs_update_group(fsid_kobj, &btrfs_feature_attr_group); if (ret < 0) btrfs_warn(fs_info, "failed to update /sys/fs/btrfs/%pU/features: %d", fs_info->fs_devices->fsid, ret); } int __init btrfs_init_sysfs(void) { int ret; btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj); if (!btrfs_kset) return -ENOMEM; init_feature_attrs(); ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group); if (ret) goto out2; ret = sysfs_merge_group(&btrfs_kset->kobj, &btrfs_static_feature_attr_group); if (ret) goto out_remove_group; #ifdef CONFIG_BTRFS_DEBUG ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group); if (ret) { sysfs_unmerge_group(&btrfs_kset->kobj, &btrfs_static_feature_attr_group); goto out_remove_group; } #endif return 0; out_remove_group: sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group); out2: kset_unregister(btrfs_kset); return ret; } void __cold btrfs_exit_sysfs(void) { sysfs_unmerge_group(&btrfs_kset->kobj, &btrfs_static_feature_attr_group); sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group); #ifdef CONFIG_BTRFS_DEBUG sysfs_remove_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group); #endif kset_unregister(btrfs_kset); } |
| 4 279 279 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Checksumming functions for IPv6 * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Borrows very liberally from tcp.c and ip.c, see those * files for more names. */ /* * Fixes: * * Ralf Baechle : generic ipv6 checksum * <ralf@waldorf-gmbh.de> */ #ifndef _CHECKSUM_IPV6_H #define _CHECKSUM_IPV6_H #include <asm/types.h> #include <asm/byteorder.h> #include <net/ip.h> #include <asm/checksum.h> #include <linux/in6.h> #include <linux/tcp.h> #include <linux/ipv6.h> #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum csum); #endif static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) { return ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, proto, 0)); } static __inline__ __sum16 tcp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, __wsum base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline void __tcp_v6_send_check(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } static inline void tcp_v6_gso_csum_prep(struct sk_buff *skb) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); ipv6h->payload_len = 0; th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0); } static inline __sum16 udp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, __wsum base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, base); } void udp6_set_csum(bool nocheck, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int len); int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto); #endif |
| 12 2 10 3 7 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6t_NPT.h> #include <linux/netfilter/x_tables.h> static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) { struct ip6t_npt_tginfo *npt = par->targinfo; struct in6_addr pfx; __wsum src_sum, dst_sum; if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) return -EINVAL; /* Ensure that LSB of prefix is zero */ ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len); if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6)) return -EINVAL; ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len); if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6)) return -EINVAL; src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0); dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0); npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum)); return 0; } static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, struct in6_addr *addr) { unsigned int pfx_len; unsigned int i, idx; __be32 mask; __sum16 sum; pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len); for (i = 0; i < pfx_len; i += 32) { if (pfx_len - i >= 32) mask = 0; else mask = htonl((1 << (i - pfx_len + 32)) - 1); idx = i / 32; addr->s6_addr32[idx] &= mask; addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx]; } if (pfx_len <= 48) idx = 3; else { for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) { if ((__force __sum16)addr->s6_addr16[idx] != CSUM_MANGLED_0) break; } if (idx == ARRAY_SIZE(addr->s6_addr16)) return false; } sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]), csum_unfold(npt->adjustment))); if (sum == CSUM_MANGLED_0) sum = 0; *(__force __sum16 *)&addr->s6_addr16[idx] = sum; return true; } static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb, struct ipv6hdr *_bounced_hdr) { if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NULL; if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type)) return NULL; return skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(struct icmp6hdr), sizeof(struct ipv6hdr), _bounced_hdr); } static unsigned int ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; struct ipv6hdr _bounced_hdr; struct ipv6hdr *bounced_hdr; struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, saddr)); return NF_DROP; } /* rewrite dst addr of bounced packet which was sent to dst range */ bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); if (bounced_hdr) { ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len); if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) ip6t_npt_map_pfx(npt, &bounced_hdr->daddr); } return XT_CONTINUE; } static unsigned int ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; struct ipv6hdr _bounced_hdr; struct ipv6hdr *bounced_hdr; struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, daddr)); return NF_DROP; } /* rewrite src addr of bounced packet which was sent from dst range */ bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); if (bounced_hdr) { ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len); if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) ip6t_npt_map_pfx(npt, &bounced_hdr->saddr); } return XT_CONTINUE; } static struct xt_target ip6t_npt_target_reg[] __read_mostly = { { .name = "SNPT", .table = "mangle", .target = ip6t_snpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .usersize = offsetof(struct ip6t_npt_tginfo, adjustment), .checkentry = ip6t_npt_checkentry, .family = NFPROTO_IPV6, .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_POST_ROUTING), .me = THIS_MODULE, }, { .name = "DNPT", .table = "mangle", .target = ip6t_dnpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .usersize = offsetof(struct ip6t_npt_tginfo, adjustment), .checkentry = ip6t_npt_checkentry, .family = NFPROTO_IPV6, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, }; static int __init ip6t_npt_init(void) { return xt_register_targets(ip6t_npt_target_reg, ARRAY_SIZE(ip6t_npt_target_reg)); } static void __exit ip6t_npt_exit(void) { xt_unregister_targets(ip6t_npt_target_reg, ARRAY_SIZE(ip6t_npt_target_reg)); } module_init(ip6t_npt_init); module_exit(ip6t_npt_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS("ip6t_SNPT"); MODULE_ALIAS("ip6t_DNPT"); |
| 19 19 19 19 9 11 16 16 16 1 11 9 15 2 16 11 11 11 6 8 5 3 3 3 1 3 16 16 11 11 12 12 12 2 16 14 11 2 1 9 3 3 9 9 9 9 1 1 1 11 15 15 4 2 9 11 11 9 11 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * Copyright (c) 2013 Red Hat, 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_bmap.h" #include "xfs_buf_item.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_health.h" /* * Local function prototypes. */ static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp, int first, int last); static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp); static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp, int *entno); static int xfs_dir2_block_sort(const void *a, const void *b); static xfs_dahash_t xfs_dir_hash_dot, xfs_dir_hash_dotdot; /* * One-time startup routine called from xfs_init(). */ void xfs_dir_startup(void) { xfs_dir_hash_dot = xfs_da_hashname((unsigned char *)".", 1); xfs_dir_hash_dotdot = xfs_da_hashname((unsigned char *)"..", 2); } static xfs_failaddr_t xfs_dir3_block_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; if (!xfs_verify_magic(bp, hdr3->magic)) return __this_address; if (xfs_has_crc(mp)) { if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (be64_to_cpu(hdr3->blkno) != xfs_buf_daddr(bp)) return __this_address; if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn))) return __this_address; } return __xfs_dir3_data_check(NULL, bp); } static void xfs_dir3_block_read_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_has_crc(mp) && !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_dir3_block_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } } static void xfs_dir3_block_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; fa = xfs_dir3_block_verify(bp); if (fa) { xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } if (!xfs_has_crc(mp)) return; if (bip) hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF); } const struct xfs_buf_ops xfs_dir3_block_buf_ops = { .name = "xfs_dir3_block", .magic = { cpu_to_be32(XFS_DIR2_BLOCK_MAGIC), cpu_to_be32(XFS_DIR3_BLOCK_MAGIC) }, .verify_read = xfs_dir3_block_read_verify, .verify_write = xfs_dir3_block_write_verify, .verify_struct = xfs_dir3_block_verify, }; xfs_failaddr_t xfs_dir3_block_header_check( struct xfs_buf *bp, xfs_ino_t owner) { struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; if (hdr3->magic != cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) return __this_address; if (be64_to_cpu(hdr3->owner) != owner) return __this_address; } return NULL; } int xfs_dir3_block_read( struct xfs_trans *tp, struct xfs_inode *dp, xfs_ino_t owner, struct xfs_buf **bpp) { struct xfs_mount *mp = dp->i_mount; xfs_failaddr_t fa; int err; err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, 0, bpp, XFS_DATA_FORK, &xfs_dir3_block_buf_ops); if (err || !*bpp) return err; /* Check things that we can't do in the verifier. */ fa = xfs_dir3_block_header_check(*bpp, owner); if (fa) { __xfs_buf_mark_corrupt(*bpp, fa); xfs_trans_brelse(tp, *bpp); *bpp = NULL; xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); return -EFSCORRUPTED; } xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF); return err; } static void xfs_dir3_block_init( struct xfs_da_args *args, struct xfs_buf *bp) { struct xfs_trans *tp = args->trans; struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; bp->b_ops = &xfs_dir3_block_buf_ops; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF); if (xfs_has_crc(mp)) { memset(hdr3, 0, sizeof(*hdr3)); hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC); hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); hdr3->owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid); return; } hdr3->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC); } static void xfs_dir2_block_need_space( struct xfs_inode *dp, struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_block_tail *btp, struct xfs_dir2_leaf_entry *blp, __be16 **tagpp, struct xfs_dir2_data_unused **dupp, struct xfs_dir2_data_unused **enddupp, int *compact, int len) { struct xfs_dir2_data_free *bf; __be16 *tagp = NULL; struct xfs_dir2_data_unused *dup = NULL; struct xfs_dir2_data_unused *enddup = NULL; *compact = 0; bf = xfs_dir2_data_bestfree_p(dp->i_mount, hdr); /* * If there are stale entries we'll use one for the leaf. */ if (btp->stale) { if (be16_to_cpu(bf[0].length) >= len) { /* * The biggest entry enough to avoid compaction. */ dup = (xfs_dir2_data_unused_t *) ((char *)hdr + be16_to_cpu(bf[0].offset)); goto out; } /* * Will need to compact to make this work. * Tag just before the first leaf entry. */ *compact = 1; tagp = (__be16 *)blp - 1; /* Data object just before the first leaf entry. */ dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free then the data will go where the * leaf data starts now, if it works at all. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { if (be16_to_cpu(dup->length) + (be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len) dup = NULL; } else if ((be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len) dup = NULL; else dup = (xfs_dir2_data_unused_t *)blp; goto out; } /* * no stale entries, so just use free space. * Tag just before the first leaf entry. */ tagp = (__be16 *)blp - 1; /* Data object just before the first leaf entry. */ enddup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free then can't do this add without cleaning up: * the space before the first leaf entry needs to be free so it * can be expanded to hold the pointer to the new entry. */ if (be16_to_cpu(enddup->freetag) == XFS_DIR2_DATA_FREE_TAG) { /* * Check out the biggest freespace and see if it's the same one. */ dup = (xfs_dir2_data_unused_t *) ((char *)hdr + be16_to_cpu(bf[0].offset)); if (dup != enddup) { /* * Not the same free entry, just check its length. */ if (be16_to_cpu(dup->length) < len) dup = NULL; goto out; } /* * It is the biggest freespace, can it hold the leaf too? */ if (be16_to_cpu(dup->length) < len + (uint)sizeof(*blp)) { /* * Yes, use the second-largest entry instead if it works. */ if (be16_to_cpu(bf[1].length) >= len) dup = (xfs_dir2_data_unused_t *) ((char *)hdr + be16_to_cpu(bf[1].offset)); else dup = NULL; } } out: *tagpp = tagp; *dupp = dup; *enddupp = enddup; } /* * compact the leaf entries. * Leave the highest-numbered stale entry stale. * XXX should be the one closest to mid but mid is not yet computed. */ static void xfs_dir2_block_compact( struct xfs_da_args *args, struct xfs_buf *bp, struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_block_tail *btp, struct xfs_dir2_leaf_entry *blp, int *needlog, int *lfloghigh, int *lfloglow) { int fromidx; /* source leaf index */ int toidx; /* target leaf index */ int needscan = 0; int highstale; /* high stale index */ fromidx = toidx = be32_to_cpu(btp->count) - 1; highstale = *lfloghigh = -1; for (; fromidx >= 0; fromidx--) { if (blp[fromidx].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) { if (highstale == -1) highstale = toidx; else { if (*lfloghigh == -1) *lfloghigh = toidx; continue; } } if (fromidx < toidx) blp[toidx] = blp[fromidx]; toidx--; } *lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1); *lfloghigh -= be32_to_cpu(btp->stale) - 1; be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1)); xfs_dir2_data_make_free(args, bp, (xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr), (xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)), needlog, &needscan); btp->stale = cpu_to_be32(1); /* * If we now need to rebuild the bestfree map, do so. * This needs to happen before the next call to use_free. */ if (needscan) xfs_dir2_data_freescan(args->dp->i_mount, hdr, needlog); } /* * Add an entry to a block directory. */ int /* error */ xfs_dir2_block_addname( xfs_da_args_t *args) /* directory op arguments */ { xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ struct xfs_buf *bp; /* buffer for block */ xfs_dir2_block_tail_t *btp; /* block tail */ int compact; /* need to compact leaf ents */ xfs_dir2_data_entry_t *dep; /* block data entry */ xfs_inode_t *dp; /* directory inode */ xfs_dir2_data_unused_t *dup; /* block unused entry */ int error; /* error return value */ xfs_dir2_data_unused_t *enddup=NULL; /* unused at end of data */ xfs_dahash_t hash; /* hash value of found entry */ int high; /* high index for binary srch */ int highstale; /* high stale index */ int lfloghigh=0; /* last final leaf to log */ int lfloglow=0; /* first final leaf to log */ int len; /* length of the new entry */ int low; /* low index for binary srch */ int lowstale; /* low stale index */ int mid=0; /* midpoint for binary srch */ int needlog; /* need to log header */ int needscan; /* need to rescan freespace */ __be16 *tagp; /* pointer to tag value */ xfs_trans_t *tp; /* transaction structure */ trace_xfs_dir2_block_addname(args); dp = args->dp; tp = args->trans; /* Read the (one and only) directory block into bp. */ error = xfs_dir3_block_read(tp, dp, args->owner, &bp); if (error) return error; len = xfs_dir2_data_entsize(dp->i_mount, args->namelen); /* * Set up pointers to parts of the block. */ hdr = bp->b_addr; btp = xfs_dir2_block_tail_p(args->geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Find out if we can reuse stale entries or whether we need extra * space for entry and new leaf. */ xfs_dir2_block_need_space(dp, hdr, btp, blp, &tagp, &dup, &enddup, &compact, len); /* * Done everything we need for a space check now. */ if (args->op_flags & XFS_DA_OP_JUSTCHECK) { xfs_trans_brelse(tp, bp); if (!dup) return -ENOSPC; return 0; } /* * If we don't have space for the new entry & leaf ... */ if (!dup) { /* Don't have a space reservation: return no-space. */ if (args->total == 0) return -ENOSPC; /* * Convert to the next larger format. * Then add the new entry in that format. */ error = xfs_dir2_block_to_leaf(args, bp); if (error) return error; return xfs_dir2_leaf_addname(args); } needlog = needscan = 0; /* * If need to compact the leaf entries, do it now. */ if (compact) { xfs_dir2_block_compact(args, bp, hdr, btp, blp, &needlog, &lfloghigh, &lfloglow); /* recalculate blp post-compaction */ blp = xfs_dir2_block_leaf_p(btp); } else if (btp->stale) { /* * Set leaf logging boundaries to impossible state. * For the no-stale case they're set explicitly. */ lfloglow = be32_to_cpu(btp->count); lfloghigh = -1; } /* * Find the slot that's first lower than our hash value, -1 if none. */ for (low = 0, high = be32_to_cpu(btp->count) - 1; low <= high; ) { mid = (low + high) >> 1; if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval) break; if (hash < args->hashval) low = mid + 1; else high = mid - 1; } while (mid >= 0 && be32_to_cpu(blp[mid].hashval) >= args->hashval) { mid--; } /* * No stale entries, will use enddup space to hold new leaf. */ if (!btp->stale) { xfs_dir2_data_aoff_t aoff; /* * Mark the space needed for the new leaf entry, now in use. */ aoff = (xfs_dir2_data_aoff_t)((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) - sizeof(*blp)); error = xfs_dir2_data_use_free(args, bp, enddup, aoff, (xfs_dir2_data_aoff_t)sizeof(*blp), &needlog, &needscan); if (error) return error; /* * Update the tail (entry count). */ be32_add_cpu(&btp->count, 1); /* * If we now need to rebuild the bestfree map, do so. * This needs to happen before the next call to use_free. */ if (needscan) { xfs_dir2_data_freescan(dp->i_mount, hdr, &needlog); needscan = 0; } /* * Adjust pointer to the first leaf entry, we're about to move * the table up one to open up space for the new leaf entry. * Then adjust our index to match. */ blp--; mid++; if (mid) memmove(blp, &blp[1], mid * sizeof(*blp)); lfloglow = 0; lfloghigh = mid; } /* * Use a stale leaf for our new entry. */ else { for (lowstale = mid; lowstale >= 0 && blp[lowstale].address != cpu_to_be32(XFS_DIR2_NULL_DATAPTR); lowstale--) continue; for (highstale = mid + 1; highstale < be32_to_cpu(btp->count) && blp[highstale].address != cpu_to_be32(XFS_DIR2_NULL_DATAPTR) && (lowstale < 0 || mid - lowstale > highstale - mid); highstale++) continue; /* * Move entries toward the low-numbered stale entry. */ if (lowstale >= 0 && (highstale == be32_to_cpu(btp->count) || mid - lowstale <= highstale - mid)) { if (mid - lowstale) memmove(&blp[lowstale], &blp[lowstale + 1], (mid - lowstale) * sizeof(*blp)); lfloglow = min(lowstale, lfloglow); lfloghigh = max(mid, lfloghigh); } /* * Move entries toward the high-numbered stale entry. */ else { ASSERT(highstale < be32_to_cpu(btp->count)); mid++; if (highstale - mid) memmove(&blp[mid + 1], &blp[mid], (highstale - mid) * sizeof(*blp)); lfloglow = min(mid, lfloglow); lfloghigh = max(highstale, lfloghigh); } be32_add_cpu(&btp->stale, -1); } /* * Point to the new data entry. */ dep = (xfs_dir2_data_entry_t *)dup; /* * Fill in the leaf entry. */ blp[mid].hashval = cpu_to_be32(args->hashval); blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr( (char *)dep - (char *)hdr)); xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh); /* * Mark space for the data entry used. */ error = xfs_dir2_data_use_free(args, bp, dup, (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), (xfs_dir2_data_aoff_t)len, &needlog, &needscan); if (error) return error; /* * Create the new data entry. */ dep->inumber = cpu_to_be64(args->inumber); dep->namelen = args->namelen; memcpy(dep->name, args->name, args->namelen); xfs_dir2_data_put_ftype(dp->i_mount, dep, args->filetype); tagp = xfs_dir2_data_entry_tag_p(dp->i_mount, dep); *tagp = cpu_to_be16((char *)dep - (char *)hdr); /* * Clean up the bestfree array and log the header, tail, and entry. */ if (needscan) xfs_dir2_data_freescan(dp->i_mount, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(args, bp); xfs_dir2_block_log_tail(tp, bp); xfs_dir2_data_log_entry(args, bp, dep); xfs_dir3_data_check(dp, bp); return 0; } /* * Log leaf entries from the block. */ static void xfs_dir2_block_log_leaf( xfs_trans_t *tp, /* transaction structure */ struct xfs_buf *bp, /* block buffer */ int first, /* index of first logged leaf */ int last) /* index of last logged leaf */ { xfs_dir2_data_hdr_t *hdr = bp->b_addr; xfs_dir2_leaf_entry_t *blp; xfs_dir2_block_tail_t *btp; btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr); blp = xfs_dir2_block_leaf_p(btp); xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr), (uint)((char *)&blp[last + 1] - (char *)hdr - 1)); } /* * Log the block tail. */ static void xfs_dir2_block_log_tail( xfs_trans_t *tp, /* transaction structure */ struct xfs_buf *bp) /* block buffer */ { xfs_dir2_data_hdr_t *hdr = bp->b_addr; xfs_dir2_block_tail_t *btp; btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr); xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr), (uint)((char *)(btp + 1) - (char *)hdr - 1)); } /* * Look up an entry in the block. This is the external routine, * xfs_dir2_block_lookup_int does the real work. */ int /* error */ xfs_dir2_block_lookup( xfs_da_args_t *args) /* dir lookup arguments */ { xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ struct xfs_buf *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_dir2_data_entry_t *dep; /* block data entry */ xfs_inode_t *dp; /* incore inode */ int ent; /* entry index */ int error; /* error return value */ trace_xfs_dir2_block_lookup(args); /* * Get the buffer, look up the entry. * If not found (ENOENT) then return, have no buffer. */ if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent))) return error; dp = args->dp; hdr = bp->b_addr; xfs_dir3_data_check(dp, bp); btp = xfs_dir2_block_tail_p(args->geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Get the offset from the leaf entry, to point to the data. */ dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(blp[ent].address))); /* * Fill in inode number, CI name if appropriate, release the block. */ args->inumber = be64_to_cpu(dep->inumber); args->filetype = xfs_dir2_data_get_ftype(dp->i_mount, dep); error = xfs_dir_cilookup_result(args, dep->name, dep->namelen); xfs_trans_brelse(args->trans, bp); return error; } /* * Internal block lookup routine. */ static int /* error */ xfs_dir2_block_lookup_int( xfs_da_args_t *args, /* dir lookup arguments */ struct xfs_buf **bpp, /* returned block buffer */ int *entno) /* returned entry number */ { xfs_dir2_dataptr_t addr; /* data entry address */ xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ struct xfs_buf *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_dir2_data_entry_t *dep; /* block data entry */ xfs_inode_t *dp; /* incore inode */ int error; /* error return value */ xfs_dahash_t hash; /* found hash value */ int high; /* binary search high index */ int low; /* binary search low index */ int mid; /* binary search current idx */ xfs_trans_t *tp; /* transaction pointer */ enum xfs_dacmp cmp; /* comparison result */ dp = args->dp; tp = args->trans; error = xfs_dir3_block_read(tp, dp, args->owner, &bp); if (error) return error; hdr = bp->b_addr; xfs_dir3_data_check(dp, bp); btp = xfs_dir2_block_tail_p(args->geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Loop doing a binary search for our hash value. * Find our entry, ENOENT if it's not there. */ for (low = 0, high = be32_to_cpu(btp->count) - 1; ; ) { ASSERT(low <= high); mid = (low + high) >> 1; if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval) break; if (hash < args->hashval) low = mid + 1; else high = mid - 1; if (low > high) { ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); xfs_trans_brelse(tp, bp); return -ENOENT; } } /* * Back up to the first one with the right hash value. */ while (mid > 0 && be32_to_cpu(blp[mid - 1].hashval) == args->hashval) { mid--; } /* * Now loop forward through all the entries with the * right hash value looking for our name. */ do { if ((addr = be32_to_cpu(blp[mid].address)) == XFS_DIR2_NULL_DATAPTR) continue; /* * Get pointer to the entry from the leaf. */ dep = (xfs_dir2_data_entry_t *) ((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, addr)); /* * Compare name and if it's an exact match, return the index * and buffer. If it's the first case-insensitive match, store * the index and buffer and continue looking for an exact match. */ cmp = xfs_dir2_compname(args, dep->name, dep->namelen); if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { args->cmpresult = cmp; *bpp = bp; *entno = mid; if (cmp == XFS_CMP_EXACT) return 0; } } while (++mid < be32_to_cpu(btp->count) && be32_to_cpu(blp[mid].hashval) == hash); ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); /* * Here, we can only be doing a lookup (not a rename or replace). * If a case-insensitive match was found earlier, return success. */ if (args->cmpresult == XFS_CMP_CASE) return 0; /* * No match, release the buffer and return ENOENT. */ xfs_trans_brelse(tp, bp); return -ENOENT; } /* * Remove an entry from a block format directory. * If that makes the block small enough to fit in shortform, transform it. */ int /* error */ xfs_dir2_block_removename( xfs_da_args_t *args) /* directory operation args */ { xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf pointer */ struct xfs_buf *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_dir2_data_entry_t *dep; /* block data entry */ xfs_inode_t *dp; /* incore inode */ int ent; /* block leaf entry index */ int error; /* error return value */ int needlog; /* need to log block header */ int needscan; /* need to fixup bestfree */ xfs_dir2_sf_hdr_t sfh; /* shortform header */ int size; /* shortform size */ xfs_trans_t *tp; /* transaction pointer */ trace_xfs_dir2_block_removename(args); /* * Look up the entry in the block. Gets the buffer and entry index. * It will always be there, the vnodeops level does a lookup first. */ if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent))) { return error; } dp = args->dp; tp = args->trans; hdr = bp->b_addr; btp = xfs_dir2_block_tail_p(args->geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Point to the data entry using the leaf entry. */ dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(blp[ent].address))); /* * Mark the data entry's space free. */ needlog = needscan = 0; xfs_dir2_data_make_free(args, bp, (xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr), xfs_dir2_data_entsize(dp->i_mount, dep->namelen), &needlog, &needscan); /* * Fix up the block tail. */ be32_add_cpu(&btp->stale, 1); xfs_dir2_block_log_tail(tp, bp); /* * Remove the leaf entry by marking it stale. */ blp[ent].address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR); xfs_dir2_block_log_leaf(tp, bp, ent, ent); /* * Fix up bestfree, log the header if necessary. */ if (needscan) xfs_dir2_data_freescan(dp->i_mount, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(args, bp); xfs_dir3_data_check(dp, bp); /* * See if the size as a shortform is good enough. */ size = xfs_dir2_block_sfsize(dp, hdr, &sfh); if (size > xfs_inode_data_fork_size(dp)) return 0; /* * If it works, do the conversion. */ return xfs_dir2_block_to_sf(args, bp, size, &sfh); } /* * Replace an entry in a V2 block directory. * Change the inode number to the new value. */ int /* error */ xfs_dir2_block_replace( xfs_da_args_t *args) /* directory operation args */ { xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ struct xfs_buf *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_dir2_data_entry_t *dep; /* block data entry */ xfs_inode_t *dp; /* incore inode */ int ent; /* leaf entry index */ int error; /* error return value */ trace_xfs_dir2_block_replace(args); /* * Lookup the entry in the directory. Get buffer and entry index. * This will always succeed since the caller has already done a lookup. */ if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent))) { return error; } dp = args->dp; hdr = bp->b_addr; btp = xfs_dir2_block_tail_p(args->geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Point to the data entry we need to change. */ dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(blp[ent].address))); ASSERT(be64_to_cpu(dep->inumber) != args->inumber); /* * Change the inode number to the new value. */ dep->inumber = cpu_to_be64(args->inumber); xfs_dir2_data_put_ftype(dp->i_mount, dep, args->filetype); xfs_dir2_data_log_entry(args, bp, dep); xfs_dir3_data_check(dp, bp); return 0; } /* * Qsort comparison routine for the block leaf entries. */ static int /* sort order */ xfs_dir2_block_sort( const void *a, /* first leaf entry */ const void *b) /* second leaf entry */ { const xfs_dir2_leaf_entry_t *la; /* first leaf entry */ const xfs_dir2_leaf_entry_t *lb; /* second leaf entry */ la = a; lb = b; return be32_to_cpu(la->hashval) < be32_to_cpu(lb->hashval) ? -1 : (be32_to_cpu(la->hashval) > be32_to_cpu(lb->hashval) ? 1 : 0); } /* * Convert a V2 leaf directory to a V2 block directory if possible. */ int /* error */ xfs_dir2_leaf_to_block( xfs_da_args_t *args, /* operation arguments */ struct xfs_buf *lbp, /* leaf buffer */ struct xfs_buf *dbp) /* data buffer */ { __be16 *bestsp; /* leaf bests table */ xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_inode_t *dp; /* incore directory inode */ xfs_dir2_data_unused_t *dup; /* unused data entry */ int error; /* error return value */ int from; /* leaf from index */ xfs_dir2_leaf_t *leaf; /* leaf structure */ xfs_dir2_leaf_entry_t *lep; /* leaf entry */ xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */ xfs_mount_t *mp; /* file system mount point */ int needlog; /* need to log data header */ int needscan; /* need to scan for bestfree */ xfs_dir2_sf_hdr_t sfh; /* shortform header */ int size; /* bytes used */ __be16 *tagp; /* end of entry (tag) */ int to; /* block/leaf to index */ xfs_trans_t *tp; /* transaction pointer */ struct xfs_dir3_icleaf_hdr leafhdr; trace_xfs_dir2_leaf_to_block(args); dp = args->dp; tp = args->trans; mp = dp->i_mount; leaf = lbp->b_addr; xfs_dir2_leaf_hdr_from_disk(mp, &leafhdr, leaf); ltp = xfs_dir2_leaf_tail_p(args->geo, leaf); ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC || leafhdr.magic == XFS_DIR3_LEAF1_MAGIC); /* * If there are data blocks other than the first one, take this * opportunity to remove trailing empty data blocks that may have * been left behind during no-space-reservation operations. * These will show up in the leaf bests table. */ while (dp->i_disk_size > args->geo->blksize) { int hdrsz; hdrsz = args->geo->data_entry_offset; bestsp = xfs_dir2_leaf_bests_p(ltp); if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) == args->geo->blksize - hdrsz) { if ((error = xfs_dir2_leaf_trim_data(args, lbp, (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1)))) return error; } else return 0; } /* * Read the data block if we don't already have it, give up if it fails. */ if (!dbp) { error = xfs_dir3_data_read(tp, dp, args->owner, args->geo->datablk, 0, &dbp); if (error) return error; } hdr = dbp->b_addr; ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC)); /* * Size of the "leaf" area in the block. */ size = (uint)sizeof(xfs_dir2_block_tail_t) + (uint)sizeof(*lep) * (leafhdr.count - leafhdr.stale); /* * Look at the last data entry. */ tagp = (__be16 *)((char *)hdr + args->geo->blksize) - 1; dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free or is too short we can't do it. */ if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG || be16_to_cpu(dup->length) < size) return 0; /* * Start converting it to block form. */ xfs_dir3_block_init(args, dbp); needlog = 1; needscan = 0; /* * Use up the space at the end of the block (blp/btp). */ error = xfs_dir2_data_use_free(args, dbp, dup, args->geo->blksize - size, size, &needlog, &needscan); if (error) return error; /* * Initialize the block tail. */ btp = xfs_dir2_block_tail_p(args->geo, hdr); btp->count = cpu_to_be32(leafhdr.count - leafhdr.stale); btp->stale = 0; xfs_dir2_block_log_tail(tp, dbp); /* * Initialize the block leaf area. We compact out stale entries. */ lep = xfs_dir2_block_leaf_p(btp); for (from = to = 0; from < leafhdr.count; from++) { if (leafhdr.ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) continue; lep[to++] = leafhdr.ents[from]; } ASSERT(to == be32_to_cpu(btp->count)); xfs_dir2_block_log_leaf(tp, dbp, 0, be32_to_cpu(btp->count) - 1); /* * Scan the bestfree if we need it and log the data block header. */ if (needscan) xfs_dir2_data_freescan(dp->i_mount, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(args, dbp); /* * Pitch the old leaf block. */ error = xfs_da_shrink_inode(args, args->geo->leafblk, lbp); if (error) return error; /* * Now see if the resulting block can be shrunken to shortform. */ size = xfs_dir2_block_sfsize(dp, hdr, &sfh); if (size > xfs_inode_data_fork_size(dp)) return 0; return xfs_dir2_block_to_sf(args, dbp, size, &sfh); } /* * Convert the shortform directory to block form. */ int /* error */ xfs_dir2_sf_to_block( struct xfs_da_args *args) { struct xfs_trans *tp = args->trans; struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); struct xfs_da_geometry *geo = args->geo; xfs_dir2_db_t blkno; /* dir-relative block # (0) */ xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ struct xfs_buf *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail pointer */ xfs_dir2_data_entry_t *dep; /* data entry pointer */ int dummy; /* trash */ xfs_dir2_data_unused_t *dup; /* unused entry pointer */ int endoffset; /* end of data objects */ int error; /* error return value */ int i; /* index */ int needlog; /* need to log block header */ int needscan; /* need to scan block freespc */ int newoffset; /* offset from current entry */ unsigned int offset = geo->data_entry_offset; xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */ struct xfs_dir2_sf_hdr *oldsfp = ifp->if_data; xfs_dir2_sf_hdr_t *sfp; /* shortform header */ __be16 *tagp; /* end of data entry */ struct xfs_name name; trace_xfs_dir2_sf_to_block(args); ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(ifp->if_bytes == dp->i_disk_size); ASSERT(oldsfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count)); ASSERT(dp->i_df.if_nextents == 0); /* * Copy the directory into a temporary buffer. * Then pitch the incore inode data so we can make extents. */ sfp = kmalloc(ifp->if_bytes, GFP_KERNEL | __GFP_NOFAIL); memcpy(sfp, oldsfp, ifp->if_bytes); xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK); xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK); dp->i_disk_size = 0; /* * Add block 0 to the inode. */ error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno); if (error) goto out_free; /* * Initialize the data block, then convert it to block format. */ error = xfs_dir3_data_init(args, blkno, &bp); if (error) goto out_free; xfs_dir3_block_init(args, bp); hdr = bp->b_addr; /* * Compute size of block "tail" area. */ i = (uint)sizeof(*btp) + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t); /* * The whole thing is initialized to free by the init routine. * Say we're using the leaf and tail area. */ dup = bp->b_addr + offset; needlog = needscan = 0; error = xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i, i, &needlog, &needscan); if (error) goto out_free; ASSERT(needscan == 0); /* * Fill in the tail. */ btp = xfs_dir2_block_tail_p(args->geo, hdr); btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */ btp->stale = 0; blp = xfs_dir2_block_leaf_p(btp); endoffset = (uint)((char *)blp - (char *)hdr); /* * Remove the freespace, we'll manage it. */ error = xfs_dir2_data_use_free(args, bp, dup, (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), be16_to_cpu(dup->length), &needlog, &needscan); if (error) goto out_free; /* * Create entry for . */ dep = bp->b_addr + offset; dep->inumber = cpu_to_be64(args->owner); dep->namelen = 1; dep->name[0] = '.'; xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR); tagp = xfs_dir2_data_entry_tag_p(mp, dep); *tagp = cpu_to_be16(offset); xfs_dir2_data_log_entry(args, bp, dep); blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot); blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(offset)); offset += xfs_dir2_data_entsize(mp, dep->namelen); /* * Create entry for .. */ dep = bp->b_addr + offset; dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp)); dep->namelen = 2; dep->name[0] = dep->name[1] = '.'; xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR); tagp = xfs_dir2_data_entry_tag_p(mp, dep); *tagp = cpu_to_be16(offset); xfs_dir2_data_log_entry(args, bp, dep); blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot); blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(offset)); offset += xfs_dir2_data_entsize(mp, dep->namelen); /* * Loop over existing entries, stuff them in. */ i = 0; if (!sfp->count) sfep = NULL; else sfep = xfs_dir2_sf_firstentry(sfp); /* * Need to preserve the existing offset values in the sf directory. * Insert holes (unused entries) where necessary. */ while (offset < endoffset) { /* * sfep is null when we reach the end of the list. */ if (sfep == NULL) newoffset = endoffset; else newoffset = xfs_dir2_sf_get_offset(sfep); /* * There should be a hole here, make one. */ if (offset < newoffset) { dup = bp->b_addr + offset; dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); dup->length = cpu_to_be16(newoffset - offset); *xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(offset); xfs_dir2_data_log_unused(args, bp, dup); xfs_dir2_data_freeinsert(hdr, xfs_dir2_data_bestfree_p(mp, hdr), dup, &dummy); offset += be16_to_cpu(dup->length); continue; } /* * Copy a real entry. */ dep = bp->b_addr + newoffset; dep->inumber = cpu_to_be64(xfs_dir2_sf_get_ino(mp, sfp, sfep)); dep->namelen = sfep->namelen; xfs_dir2_data_put_ftype(mp, dep, xfs_dir2_sf_get_ftype(mp, sfep)); memcpy(dep->name, sfep->name, dep->namelen); tagp = xfs_dir2_data_entry_tag_p(mp, dep); *tagp = cpu_to_be16(newoffset); xfs_dir2_data_log_entry(args, bp, dep); name.name = sfep->name; name.len = sfep->namelen; blp[2 + i].hashval = cpu_to_be32(xfs_dir2_hashname(mp, &name)); blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(newoffset)); offset = (int)((char *)(tagp + 1) - (char *)hdr); if (++i == sfp->count) sfep = NULL; else sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); } /* Done with the temporary buffer */ kfree(sfp); /* * Sort the leaf entries by hash value. */ xfs_sort(blp, be32_to_cpu(btp->count), sizeof(*blp), xfs_dir2_block_sort); /* * Log the leaf entry area and tail. * Already logged the header in data_init, ignore needlog. */ ASSERT(needscan == 0); xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1); xfs_dir2_block_log_tail(tp, bp); xfs_dir3_data_check(dp, bp); return 0; out_free: kfree(sfp); return error; } |
| 6 7800 7808 483 4534 4572 482 484 484 484 484 484 482 484 9 477 8 1 475 484 483 483 484 5067 5075 477 1 1 474 4 4 4 4 4 4 4 4 4 4 1 1 9 9 9 9 6 3 3 3 3 3 3 3 6 6 6 6 6 6 6 6 6 9 9 9 4 4 6183 6195 5062 5075 477 5071 5063 5065 5066 393 7 5075 5067 5068 205 5071 5065 181 180 4886 4888 3340 3347 3351 3343 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit_queue: blk_queue_exit(q); fail: /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, cgroup_rstat_lock is always held, so * this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; int ret; new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); ret = blk_ioprio_init(disk); if (ret) goto err_destroy_all; return 0; err_destroy_all: blkg_destroy_all(disk); return ret; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); cgroup_rstat_updated(blkcg->css.cgroup, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct cgroup_subsys_state *css; bool ret = false; rcu_read_lock(); for (css = blkcg_css(); css; css = css->parent) { if (atomic_read(&css->cgroup->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 596 595 179 596 595 15355 15357 13266 5580 5581 14343 14357 13132 2587 593 2076 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #define pr_fmt(fmt) "ref_tracker: " fmt #include <linux/export.h> #include <linux/list_sort.h> #include <linux/ref_tracker.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #define REF_TRACKER_STACK_ENTRIES 16 #define STACK_BUF_SIZE 1024 struct ref_tracker { struct list_head head; /* anchor into dir->list or dir->quarantine */ bool dead; depot_stack_handle_t alloc_stack_handle; depot_stack_handle_t free_stack_handle; }; struct ref_tracker_dir_stats { int total; int count; struct { depot_stack_handle_t stack_handle; unsigned int count; } stacks[]; }; static struct ref_tracker_dir_stats * ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit) { struct ref_tracker_dir_stats *stats; struct ref_tracker *tracker; stats = kmalloc(struct_size(stats, stacks, limit), GFP_NOWAIT | __GFP_NOWARN); if (!stats) return ERR_PTR(-ENOMEM); stats->total = 0; stats->count = 0; list_for_each_entry(tracker, &dir->list, head) { depot_stack_handle_t stack = tracker->alloc_stack_handle; int i; ++stats->total; for (i = 0; i < stats->count; ++i) if (stats->stacks[i].stack_handle == stack) break; if (i >= limit) continue; if (i >= stats->count) { stats->stacks[i].stack_handle = stack; stats->stacks[i].count = 0; ++stats->count; } ++stats->stacks[i].count; } return stats; } struct ostream { char *buf; int size, used; }; #define pr_ostream(stream, fmt, args...) \ ({ \ struct ostream *_s = (stream); \ \ if (!_s->buf) { \ pr_err(fmt, ##args); \ } else { \ int ret, len = _s->size - _s->used; \ ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \ _s->used += min(ret, len); \ } \ }) static void __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir, unsigned int display_limit, struct ostream *s) { struct ref_tracker_dir_stats *stats; unsigned int i = 0, skipped; depot_stack_handle_t stack; char *sbuf; lockdep_assert_held(&dir->lock); if (list_empty(&dir->list)) return; stats = ref_tracker_get_stats(dir, display_limit); if (IS_ERR(stats)) { pr_ostream(s, "%s@%pK: couldn't get stats, error %pe\n", dir->name, dir, stats); return; } sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT | __GFP_NOWARN); for (i = 0, skipped = stats->total; i < stats->count; ++i) { stack = stats->stacks[i].stack_handle; if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4)) sbuf[0] = 0; pr_ostream(s, "%s@%pK has %d/%d users at\n%s\n", dir->name, dir, stats->stacks[i].count, stats->total, sbuf); skipped -= stats->stacks[i].count; } if (skipped) pr_ostream(s, "%s@%pK skipped reports about %d/%d users.\n", dir->name, dir, skipped, stats->total); kfree(sbuf); kfree(stats); } void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, unsigned int display_limit) { struct ostream os = {}; __ref_tracker_dir_pr_ostream(dir, display_limit, &os); } EXPORT_SYMBOL(ref_tracker_dir_print_locked); void ref_tracker_dir_print(struct ref_tracker_dir *dir, unsigned int display_limit) { unsigned long flags; spin_lock_irqsave(&dir->lock, flags); ref_tracker_dir_print_locked(dir, display_limit); spin_unlock_irqrestore(&dir->lock, flags); } EXPORT_SYMBOL(ref_tracker_dir_print); int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size) { struct ostream os = { .buf = buf, .size = size }; unsigned long flags; spin_lock_irqsave(&dir->lock, flags); __ref_tracker_dir_pr_ostream(dir, 16, &os); spin_unlock_irqrestore(&dir->lock, flags); return os.used; } EXPORT_SYMBOL(ref_tracker_dir_snprint); void ref_tracker_dir_exit(struct ref_tracker_dir *dir) { struct ref_tracker *tracker, *n; unsigned long flags; bool leak = false; dir->dead = true; spin_lock_irqsave(&dir->lock, flags); list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { list_del(&tracker->head); kfree(tracker); dir->quarantine_avail++; } if (!list_empty(&dir->list)) { ref_tracker_dir_print_locked(dir, 16); leak = true; list_for_each_entry_safe(tracker, n, &dir->list, head) { list_del(&tracker->head); kfree(tracker); } } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1); } EXPORT_SYMBOL(ref_tracker_dir_exit); int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; struct ref_tracker *tracker; unsigned int nr_entries; gfp_t gfp_mask = gfp | __GFP_NOWARN; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_inc(&dir->no_tracker); return 0; } if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); if (unlikely(!tracker)) { pr_err_once("memory allocation failure, unreliable refcount tracker.\n"); refcount_inc(&dir->untracked); return -ENOMEM; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); spin_lock_irqsave(&dir->lock, flags); list_add(&tracker->head, &dir->list); spin_unlock_irqrestore(&dir->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_alloc); int ref_tracker_free(struct ref_tracker_dir *dir, struct ref_tracker **trackerp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; depot_stack_handle_t stack_handle; struct ref_tracker *tracker; unsigned int nr_entries; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_dec(&dir->no_tracker); return 0; } tracker = *trackerp; if (!tracker) { refcount_dec(&dir->untracked); return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); stack_handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT | __GFP_NOWARN); spin_lock_irqsave(&dir->lock, flags); if (tracker->dead) { pr_err("reference already released.\n"); if (tracker->alloc_stack_handle) { pr_err("allocated in:\n"); stack_depot_print(tracker->alloc_stack_handle); } if (tracker->free_stack_handle) { pr_err("freed in:\n"); stack_depot_print(tracker->free_stack_handle); } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(1); return -EINVAL; } tracker->dead = true; tracker->free_stack_handle = stack_handle; list_move_tail(&tracker->head, &dir->quarantine); if (!dir->quarantine_avail) { tracker = list_first_entry(&dir->quarantine, struct ref_tracker, head); list_del(&tracker->head); } else { dir->quarantine_avail--; tracker = NULL; } spin_unlock_irqrestore(&dir->lock, flags); kfree(tracker); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_free); |
| 45 6 6 27 22 202 228 276 274 4 4 4 83 71 128 276 3 133 191 373 128 276 360 452 452 55 373 15 15 15 5 15 15 1 1 15 15 1 4 16 15 4 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 | /* * Copyright (c) 2018 Cumulus Networks. All rights reserved. * Copyright (c) 2018 David Ahern <dsa@cumulusnetworks.com> * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this * source tree. * * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ #include <linux/bitmap.h> #include <linux/in6.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rhashtable.h> #include <linux/spinlock_types.h> #include <linux/types.h> #include <net/fib_notifier.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/fib_rules.h> #include <net/net_namespace.h> #include <net/nexthop.h> #include <linux/debugfs.h> #include "netdevsim.h" struct nsim_fib_entry { u64 max; atomic64_t num; }; struct nsim_per_fib_data { struct nsim_fib_entry fib; struct nsim_fib_entry rules; }; struct nsim_fib_data { struct notifier_block fib_nb; struct nsim_per_fib_data ipv4; struct nsim_per_fib_data ipv6; struct nsim_fib_entry nexthops; struct rhashtable fib_rt_ht; struct list_head fib_rt_list; struct mutex fib_lock; /* Protects FIB HT and list */ struct notifier_block nexthop_nb; struct rhashtable nexthop_ht; struct devlink *devlink; struct work_struct fib_event_work; struct work_struct fib_flush_work; struct list_head fib_event_queue; spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ struct mutex nh_lock; /* Protects NH HT */ struct dentry *ddir; bool fail_route_offload; bool fail_res_nexthop_group_replace; bool fail_nexthop_bucket_replace; bool fail_route_delete; }; struct nsim_fib_rt_key { unsigned char addr[sizeof(struct in6_addr)]; unsigned char prefix_len; int family; u32 tb_id; }; struct nsim_fib_rt { struct nsim_fib_rt_key key; struct rhash_head ht_node; struct list_head list; /* Member of fib_rt_list */ }; struct nsim_fib4_rt { struct nsim_fib_rt common; struct fib_info *fi; dscp_t dscp; u8 type; }; struct nsim_fib6_rt { struct nsim_fib_rt common; struct list_head nh_list; unsigned int nhs; }; struct nsim_fib6_rt_nh { struct list_head list; /* Member of nh_list */ struct fib6_info *rt; }; struct nsim_fib6_event { struct fib6_info **rt_arr; unsigned int nrt6; }; struct nsim_fib_event { struct list_head list; /* node in fib queue */ union { struct fib_entry_notifier_info fen_info; struct nsim_fib6_event fib6_event; }; struct nsim_fib_data *data; unsigned long event; int family; }; static const struct rhashtable_params nsim_fib_rt_ht_params = { .key_offset = offsetof(struct nsim_fib_rt, key), .head_offset = offsetof(struct nsim_fib_rt, ht_node), .key_len = sizeof(struct nsim_fib_rt_key), .automatic_shrinking = true, }; struct nsim_nexthop { struct rhash_head ht_node; u64 occ; u32 id; bool is_resilient; }; static const struct rhashtable_params nsim_nexthop_ht_params = { .key_offset = offsetof(struct nsim_nexthop, id), .head_offset = offsetof(struct nsim_nexthop, ht_node), .key_len = sizeof(u32), .automatic_shrinking = true, }; u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max) { struct nsim_fib_entry *entry; switch (res_id) { case NSIM_RESOURCE_IPV4_FIB: entry = &fib_data->ipv4.fib; break; case NSIM_RESOURCE_IPV4_FIB_RULES: entry = &fib_data->ipv4.rules; break; case NSIM_RESOURCE_IPV6_FIB: entry = &fib_data->ipv6.fib; break; case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; case NSIM_RESOURCE_NEXTHOPS: entry = &fib_data->nexthops; break; default: return 0; } return max ? entry->max : atomic64_read(&entry->num); } static void nsim_fib_set_max(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, u64 val) { struct nsim_fib_entry *entry; switch (res_id) { case NSIM_RESOURCE_IPV4_FIB: entry = &fib_data->ipv4.fib; break; case NSIM_RESOURCE_IPV4_FIB_RULES: entry = &fib_data->ipv4.rules; break; case NSIM_RESOURCE_IPV6_FIB: entry = &fib_data->ipv6.fib; break; case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; case NSIM_RESOURCE_NEXTHOPS: entry = &fib_data->nexthops; break; default: WARN_ON(1); return; } entry->max = val; } static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, struct netlink_ext_ack *extack) { int err = 0; if (add) { if (!atomic64_add_unless(&entry->num, 1, entry->max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries"); } } else { atomic64_dec_if_positive(&entry->num); } return err; } static int nsim_fib_rule_event(struct nsim_fib_data *data, struct fib_notifier_info *info, bool add) { struct netlink_ext_ack *extack = info->extack; int err = 0; switch (info->family) { case AF_INET: err = nsim_fib_rule_account(&data->ipv4.rules, add, extack); break; case AF_INET6: err = nsim_fib_rule_account(&data->ipv6.rules, add, extack); break; } return err; } static int nsim_fib_account(struct nsim_fib_entry *entry, bool add) { int err = 0; if (add) { if (!atomic64_add_unless(&entry->num, 1, entry->max)) err = -ENOSPC; } else { atomic64_dec_if_positive(&entry->num); } return err; } static void nsim_fib_rt_init(struct nsim_fib_data *data, struct nsim_fib_rt *fib_rt, const void *addr, size_t addr_len, unsigned int prefix_len, int family, u32 tb_id) { memcpy(fib_rt->key.addr, addr, addr_len); fib_rt->key.prefix_len = prefix_len; fib_rt->key.family = family; fib_rt->key.tb_id = tb_id; list_add(&fib_rt->list, &data->fib_rt_list); } static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt) { list_del(&fib_rt->list); } static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht, const void *addr, size_t addr_len, unsigned int prefix_len, int family, u32 tb_id) { struct nsim_fib_rt_key key; memset(&key, 0, sizeof(key)); memcpy(key.addr, addr, addr_len); key.prefix_len = prefix_len; key.family = family; key.tb_id = tb_id; return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params); } static struct nsim_fib4_rt * nsim_fib4_rt_create(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt; fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_KERNEL); if (!fib4_rt) return NULL; nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32), fen_info->dst_len, AF_INET, fen_info->tb_id); fib4_rt->fi = fen_info->fi; fib_info_hold(fib4_rt->fi); fib4_rt->dscp = fen_info->dscp; fib4_rt->type = fen_info->type; return fib4_rt; } static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt) { fib_info_put(fib4_rt->fi); nsim_fib_rt_fini(&fib4_rt->common); kfree(fib4_rt); } static struct nsim_fib4_rt * nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib_entry_notifier_info *fen_info) { struct nsim_fib_rt *fib_rt; fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32), fen_info->dst_len, AF_INET, fen_info->tb_id); if (!fib_rt) return NULL; return container_of(fib_rt, struct nsim_fib4_rt, common); } static void nsim_fib4_rt_offload_failed_flag_set(struct net *net, struct fib_entry_notifier_info *fen_info) { u32 *p_dst = (u32 *)&fen_info->dst; struct fib_rt_info fri; fri.fi = fen_info->fi; fri.tb_id = fen_info->tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = fen_info->dst_len; fri.dscp = fen_info->dscp; fri.type = fen_info->type; fri.offload = false; fri.trap = false; fri.offload_failed = true; fib_alias_hw_flags_set(net, &fri); } static void nsim_fib4_rt_hw_flags_set(struct net *net, const struct nsim_fib4_rt *fib4_rt, bool trap) { u32 *p_dst = (u32 *) fib4_rt->common.key.addr; int dst_len = fib4_rt->common.key.prefix_len; struct fib_rt_info fri; fri.fi = fib4_rt->fi; fri.tb_id = fib4_rt->common.key.tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = dst_len; fri.dscp = fib4_rt->dscp; fri.type = fib4_rt->type; fri.offload = false; fri.trap = trap; fri.offload_failed = false; fib_alias_hw_flags_set(net, &fri); } static int nsim_fib4_rt_add(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt) { struct net *net = devlink_net(data->devlink); int err; err = rhashtable_insert_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) goto err_fib_dismiss; /* Simulate hardware programming latency. */ msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); return 0; err_fib_dismiss: /* Drop the accounting that was increased from the notification * context when FIB_EVENT_ENTRY_REPLACE was triggered. */ nsim_fib_account(&data->ipv4.fib, false); return err; } static int nsim_fib4_rt_replace(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt, struct nsim_fib4_rt *fib4_rt_old) { struct net *net = devlink_net(data->devlink); int err; /* We are replacing a route, so need to remove the accounting which * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. */ err = nsim_fib_account(&data->ipv4.fib, false); if (err) return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib4_rt_old->common.ht_node, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) return err; msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false); nsim_fib4_rt_destroy(fib4_rt_old); return 0; } static int nsim_fib4_rt_insert(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt, *fib4_rt_old; int err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib4_rt = nsim_fib4_rt_create(data, fen_info); if (!fib4_rt) return -ENOMEM; fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt_old) err = nsim_fib4_rt_add(data, fib4_rt); else err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old); if (err) nsim_fib4_rt_destroy(fib4_rt); return err; } static void nsim_fib4_rt_remove(struct nsim_fib_data *data, const struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt; fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt) return; rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); nsim_fib4_rt_destroy(fib4_rt); } static int nsim_fib4_event(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info, unsigned long event) { int err = 0; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib4_rt_insert(data, fen_info); if (err) { struct net *net = devlink_net(data->devlink); nsim_fib4_rt_offload_failed_flag_set(net, fen_info); } break; case FIB_EVENT_ENTRY_DEL: nsim_fib4_rt_remove(data, fen_info); break; default: break; } return err; } static struct nsim_fib6_rt_nh * nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) { if (fib6_rt_nh->rt == rt) return fib6_rt_nh; } return NULL; } static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_KERNEL); if (!fib6_rt_nh) return -ENOMEM; fib6_info_hold(rt); fib6_rt_nh->rt = rt; list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list); fib6_rt->nhs++; return 0; } #if IS_ENABLED(CONFIG_IPV6) static void nsim_rt6_release(struct fib6_info *rt) { fib6_info_release(rt); } #else static void nsim_rt6_release(struct fib6_info *rt) { } #endif static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt); if (!fib6_rt_nh) return; fib6_rt->nhs--; list_del(&fib6_rt_nh->list); nsim_rt6_release(fib6_rt_nh->rt); kfree(fib6_rt_nh); } static struct nsim_fib6_rt * nsim_fib6_rt_create(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { struct fib6_info *rt = rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i = 0; int err; fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_KERNEL); if (!fib6_rt) return ERR_PTR(-ENOMEM); nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr, sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6, rt->fib6_table->tb6_id); /* We consider a multipath IPv6 route as one entry, but it can be made * up from several fib6_info structs (one for each nexthop), so we * add them all to the same list under the entry. */ INIT_LIST_HEAD(&fib6_rt->nh_list); for (i = 0; i < nrt6; i++) { err = nsim_fib6_rt_nh_add(fib6_rt, rt_arr[i]); if (err) goto err_fib6_rt_nh_del; } return fib6_rt; err_fib6_rt_nh_del: for (i--; i >= 0; i--) { nsim_fib6_rt_nh_del(fib6_rt, rt_arr[i]); } nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); return ERR_PTR(err); } static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt) { struct nsim_fib6_rt_nh *iter, *tmp; list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list) nsim_fib6_rt_nh_del(fib6_rt, iter->rt); WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list)); nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); } static struct nsim_fib6_rt * nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt) { struct nsim_fib_rt *fib_rt; fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr, sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6, rt->fib6_table->tb6_id); if (!fib_rt) return NULL; return container_of(fib_rt, struct nsim_fib6_rt, common); } static int nsim_fib6_rt_append(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i, err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return -EINVAL; for (i = 0; i < fib6_event->nrt6; i++) { err = nsim_fib6_rt_nh_add(fib6_rt, fib6_event->rt_arr[i]); if (err) goto err_fib6_rt_nh_del; WRITE_ONCE(fib6_event->rt_arr[i]->trap, true); } return 0; err_fib6_rt_nh_del: for (i--; i >= 0; i--) { WRITE_ONCE(fib6_event->rt_arr[i]->trap, false); nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); } return err; } #if IS_ENABLED(CONFIG_IPV6) static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { struct net *net = devlink_net(data->devlink); int i; for (i = 0; i < nrt6; i++) fib6_info_hw_flags_set(net, rt_arr[i], false, false, true); } #else static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { } #endif #if IS_ENABLED(CONFIG_IPV6) static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, const struct nsim_fib6_rt *fib6_rt, bool trap) { struct net *net = devlink_net(data->devlink); struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap, false); } #else static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, const struct nsim_fib6_rt *fib6_rt, bool trap) { } #endif static int nsim_fib6_rt_add(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt) { int err; err = rhashtable_insert_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) goto err_fib_dismiss; msleep(1); nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); return 0; err_fib_dismiss: /* Drop the accounting that was increased from the notification * context when FIB_EVENT_ENTRY_REPLACE was triggered. */ nsim_fib_account(&data->ipv6.fib, false); return err; } static int nsim_fib6_rt_replace(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt, struct nsim_fib6_rt *fib6_rt_old) { int err; /* We are replacing a route, so need to remove the accounting which * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. */ err = nsim_fib_account(&data->ipv6.fib, false); if (err) return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib6_rt_old->common.ht_node, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) return err; msleep(1); nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); nsim_fib6_rt_hw_flags_set(data, fib6_rt_old, false); nsim_fib6_rt_destroy(fib6_rt_old); return 0; } static int nsim_fib6_rt_insert(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt, *fib6_rt_old; int err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib6_rt = nsim_fib6_rt_create(data, fib6_event->rt_arr, fib6_event->nrt6); if (IS_ERR(fib6_rt)) return PTR_ERR(fib6_rt); fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt_old) err = nsim_fib6_rt_add(data, fib6_rt); else err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old); if (err) nsim_fib6_rt_destroy(fib6_rt); return err; } static void nsim_fib6_rt_remove(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete * notification for a route we do not have. Therefore, do not warn if * route was not found. */ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ if (fib6_event->nrt6 != fib6_rt->nhs) { for (i = 0; i < fib6_event->nrt6; i++) nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); return; } rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); nsim_fib6_rt_destroy(fib6_rt); } static int nsim_fib6_event_init(struct nsim_fib6_event *fib6_event, struct fib6_entry_notifier_info *fen6_info) { struct fib6_info *rt = fen6_info->rt; struct fib6_info **rt_arr; struct fib6_info *iter; unsigned int nrt6; int i = 0; nrt6 = fen6_info->nsiblings + 1; rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC); if (!rt_arr) return -ENOMEM; fib6_event->rt_arr = rt_arr; fib6_event->nrt6 = nrt6; rt_arr[0] = rt; fib6_info_hold(rt); if (!fen6_info->nsiblings) return 0; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (i == fen6_info->nsiblings) break; rt_arr[i + 1] = iter; fib6_info_hold(iter); i++; } WARN_ON_ONCE(i != fen6_info->nsiblings); return 0; } static void nsim_fib6_event_fini(struct nsim_fib6_event *fib6_event) { int i; for (i = 0; i < fib6_event->nrt6; i++) nsim_rt6_release(fib6_event->rt_arr[i]); kfree(fib6_event->rt_arr); } static int nsim_fib6_event(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event, unsigned long event) { int err; if (fib6_event->rt_arr[0]->fib6_src.plen) return 0; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib6_rt_insert(data, fib6_event); if (err) goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_APPEND: err = nsim_fib6_rt_append(data, fib6_event); if (err) goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_DEL: nsim_fib6_rt_remove(data, fib6_event); break; default: break; } return 0; err_rt_offload_failed_flag_set: nsim_fib6_rt_offload_failed_flag_set(data, fib6_event->rt_arr, fib6_event->nrt6); return err; } static void nsim_fib_event(struct nsim_fib_event *fib_event) { switch (fib_event->family) { case AF_INET: nsim_fib4_event(fib_event->data, &fib_event->fen_info, fib_event->event); fib_info_put(fib_event->fen_info.fi); break; case AF_INET6: nsim_fib6_event(fib_event->data, &fib_event->fib6_event, fib_event->event); nsim_fib6_event_fini(&fib_event->fib6_event); break; } } static int nsim_fib4_prepare_event(struct fib_notifier_info *info, struct nsim_fib_event *fib_event, unsigned long event) { struct nsim_fib_data *data = fib_event->data; struct fib_entry_notifier_info *fen_info; struct netlink_ext_ack *extack; int err = 0; fen_info = container_of(info, struct fib_entry_notifier_info, info); fib_event->fen_info = *fen_info; extack = info->extack; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib_account(&data->ipv4.fib, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); return err; } break; case FIB_EVENT_ENTRY_DEL: if (data->fail_route_delete) { NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); return -EINVAL; } nsim_fib_account(&data->ipv4.fib, false); break; } /* Take reference on fib_info to prevent it from being * freed while event is queued. Release it afterwards. */ fib_info_hold(fib_event->fen_info.fi); return 0; } static int nsim_fib6_prepare_event(struct fib_notifier_info *info, struct nsim_fib_event *fib_event, unsigned long event) { struct nsim_fib_data *data = fib_event->data; struct fib6_entry_notifier_info *fen6_info; struct netlink_ext_ack *extack; int err = 0; fen6_info = container_of(info, struct fib6_entry_notifier_info, info); err = nsim_fib6_event_init(&fib_event->fib6_event, fen6_info); if (err) return err; extack = info->extack; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib_account(&data->ipv6.fib, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); goto err_fib6_event_fini; } break; case FIB_EVENT_ENTRY_DEL: if (data->fail_route_delete) { err = -EINVAL; NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); goto err_fib6_event_fini; } nsim_fib_account(&data->ipv6.fib, false); break; } return 0; err_fib6_event_fini: nsim_fib6_event_fini(&fib_event->fib6_event); return err; } static int nsim_fib_event_schedule_work(struct nsim_fib_data *data, struct fib_notifier_info *info, unsigned long event) { struct nsim_fib_event *fib_event; int err; if (info->family != AF_INET && info->family != AF_INET6) /* netdevsim does not support 'RTNL_FAMILY_IP6MR' and * 'RTNL_FAMILY_IPMR' and should ignore them. */ return NOTIFY_DONE; fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); if (!fib_event) goto err_fib_event_alloc; fib_event->data = data; fib_event->event = event; fib_event->family = info->family; switch (info->family) { case AF_INET: err = nsim_fib4_prepare_event(info, fib_event, event); break; case AF_INET6: err = nsim_fib6_prepare_event(info, fib_event, event); break; } if (err) goto err_fib_prepare_event; /* Enqueue the event and trigger the work */ spin_lock_bh(&data->fib_event_queue_lock); list_add_tail(&fib_event->list, &data->fib_event_queue); spin_unlock_bh(&data->fib_event_queue_lock); schedule_work(&data->fib_event_work); return NOTIFY_DONE; err_fib_prepare_event: kfree(fib_event); err_fib_event_alloc: if (event == FIB_EVENT_ENTRY_DEL) schedule_work(&data->fib_flush_work); return NOTIFY_BAD; } static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct fib_notifier_info *info = ptr; int err; switch (event) { case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = nsim_fib_rule_event(data, info, event == FIB_EVENT_RULE_ADD); return notifier_from_errno(err); case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: return nsim_fib_event_schedule_work(data, info, event); } return NOTIFY_DONE; } static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib_data *data) { struct devlink *devlink = data->devlink; struct nsim_fib4_rt *fib4_rt; fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common); nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false); nsim_fib_account(&data->ipv4.fib, false); nsim_fib4_rt_destroy(fib4_rt); } static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib_data *data) { struct nsim_fib6_rt *fib6_rt; fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common); nsim_fib6_rt_hw_flags_set(data, fib6_rt, false); nsim_fib_account(&data->ipv6.fib, false); nsim_fib6_rt_destroy(fib6_rt); } static void nsim_fib_rt_free(void *ptr, void *arg) { struct nsim_fib_rt *fib_rt = ptr; struct nsim_fib_data *data = arg; switch (fib_rt->key.family) { case AF_INET: nsim_fib4_rt_free(fib_rt, data); break; case AF_INET6: nsim_fib6_rt_free(fib_rt, data); break; default: WARN_ON_ONCE(1); } } /* inconsistent dump, trying again */ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; /* Flush the work to make sure there is no race with notifications. */ flush_work(&data->fib_event_work); /* The notifier block is still not registered, so we do not need to * take any locks here. */ list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) { rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node, nsim_fib_rt_ht_params); nsim_fib_rt_free(fib_rt, data); } atomic64_set(&data->ipv4.rules.num, 0ULL); atomic64_set(&data->ipv6.rules.num, 0ULL); } static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop; u64 occ = 0; int i; nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL); if (!nexthop) return ERR_PTR(-ENOMEM); nexthop->id = info->id; /* Determine the number of nexthop entries the new nexthop will * occupy. */ switch (info->type) { case NH_NOTIFIER_INFO_TYPE_SINGLE: occ = 1; break; case NH_NOTIFIER_INFO_TYPE_GRP: for (i = 0; i < info->nh_grp->num_nh; i++) occ += info->nh_grp->nh_entries[i].weight; break; case NH_NOTIFIER_INFO_TYPE_RES_TABLE: occ = info->nh_res_table->num_nh_buckets; nexthop->is_resilient = true; break; default: NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type"); kfree(nexthop); return ERR_PTR(-EOPNOTSUPP); } nexthop->occ = occ; return nexthop; } static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop) { kfree(nexthop); } static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ, bool add, struct netlink_ext_ack *extack) { int i, err = 0; if (add) { for (i = 0; i < occ; i++) if (!atomic64_add_unless(&data->nexthops.num, 1, data->nexthops.max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); goto err_num_decrease; } } else { if (WARN_ON(occ > atomic64_read(&data->nexthops.num))) return -EINVAL; atomic64_sub(occ, &data->nexthops.num); } return err; err_num_decrease: atomic64_sub(i, &data->nexthops.num); return err; } static void nsim_nexthop_hw_flags_set(struct net *net, const struct nsim_nexthop *nexthop, bool trap) { int i; nexthop_set_hw_flags(net, nexthop->id, false, trap); if (!nexthop->is_resilient) return; for (i = 0; i < nexthop->occ; i++) nexthop_bucket_set_hw_flags(net, nexthop->id, i, false, trap); } static int nsim_nexthop_add(struct nsim_fib_data *data, struct nsim_nexthop *nexthop, struct netlink_ext_ack *extack) { struct net *net = devlink_net(data->devlink); int err; err = nsim_nexthop_account(data, nexthop->occ, true, extack); if (err) return err; err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node, nsim_nexthop_ht_params); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop"); goto err_nexthop_dismiss; } nsim_nexthop_hw_flags_set(net, nexthop, true); return 0; err_nexthop_dismiss: nsim_nexthop_account(data, nexthop->occ, false, extack); return err; } static int nsim_nexthop_replace(struct nsim_fib_data *data, struct nsim_nexthop *nexthop, struct nsim_nexthop *nexthop_old, struct netlink_ext_ack *extack) { struct net *net = devlink_net(data->devlink); int err; err = nsim_nexthop_account(data, nexthop->occ, true, extack); if (err) return err; err = rhashtable_replace_fast(&data->nexthop_ht, &nexthop_old->ht_node, &nexthop->ht_node, nsim_nexthop_ht_params); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop"); goto err_nexthop_dismiss; } nsim_nexthop_hw_flags_set(net, nexthop, true); nsim_nexthop_account(data, nexthop_old->occ, false, extack); nsim_nexthop_destroy(nexthop_old); return 0; err_nexthop_dismiss: nsim_nexthop_account(data, nexthop->occ, false, extack); return err; } static int nsim_nexthop_insert(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop, *nexthop_old; int err; nexthop = nsim_nexthop_create(data, info); if (IS_ERR(nexthop)) return PTR_ERR(nexthop); nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, nsim_nexthop_ht_params); if (!nexthop_old) err = nsim_nexthop_add(data, nexthop, info->extack); else err = nsim_nexthop_replace(data, nexthop, nexthop_old, info->extack); if (err) nsim_nexthop_destroy(nexthop); return err; } static void nsim_nexthop_remove(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop; nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, nsim_nexthop_ht_params); if (!nexthop) return; rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node, nsim_nexthop_ht_params); nsim_nexthop_account(data, nexthop->occ, false, info->extack); nsim_nexthop_destroy(nexthop); } static int nsim_nexthop_res_table_pre_replace(struct nsim_fib_data *data, struct nh_notifier_info *info) { if (data->fail_res_nexthop_group_replace) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace a resilient nexthop group"); return -EINVAL; } return 0; } static int nsim_nexthop_bucket_replace(struct nsim_fib_data *data, struct nh_notifier_info *info) { if (data->fail_nexthop_bucket_replace) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace nexthop bucket"); return -EINVAL; } nexthop_bucket_set_hw_flags(info->net, info->id, info->nh_res_bucket->bucket_index, false, true); return 0; } static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, nexthop_nb); struct nh_notifier_info *info = ptr; int err = 0; mutex_lock(&data->nh_lock); switch (event) { case NEXTHOP_EVENT_REPLACE: err = nsim_nexthop_insert(data, info); break; case NEXTHOP_EVENT_DEL: nsim_nexthop_remove(data, info); break; case NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE: err = nsim_nexthop_res_table_pre_replace(data, info); break; case NEXTHOP_EVENT_BUCKET_REPLACE: err = nsim_nexthop_bucket_replace(data, info); break; default: break; } mutex_unlock(&data->nh_lock); return notifier_from_errno(err); } static void nsim_nexthop_free(void *ptr, void *arg) { struct nsim_nexthop *nexthop = ptr; struct nsim_fib_data *data = arg; struct net *net; net = devlink_net(data->devlink); nsim_nexthop_hw_flags_set(net, nexthop, false); nsim_nexthop_account(data, nexthop->occ, false, NULL); nsim_nexthop_destroy(nexthop); } static ssize_t nsim_nexthop_bucket_activity_write(struct file *file, const char __user *user_buf, size_t size, loff_t *ppos) { struct nsim_fib_data *data = file->private_data; struct net *net = devlink_net(data->devlink); struct nsim_nexthop *nexthop; unsigned long *activity; loff_t pos = *ppos; u16 bucket_index; char buf[128]; int err = 0; u32 nhid; if (pos != 0) return -EINVAL; if (size > sizeof(buf)) return -EINVAL; if (copy_from_user(buf, user_buf, size)) return -EFAULT; if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2) return -EINVAL; rtnl_lock(); nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &nhid, nsim_nexthop_ht_params); if (!nexthop || !nexthop->is_resilient || bucket_index >= nexthop->occ) { err = -EINVAL; goto out; } activity = bitmap_zalloc(nexthop->occ, GFP_KERNEL); if (!activity) { err = -ENOMEM; goto out; } bitmap_set(activity, bucket_index, 1); nexthop_res_grp_activity_update(net, nhid, nexthop->occ, activity); bitmap_free(activity); out: rtnl_unlock(); *ppos = size; return err ?: size; } static const struct file_operations nsim_nexthop_bucket_activity_fops = { .open = simple_open, .write = nsim_nexthop_bucket_activity_write, .llseek = no_llseek, .owner = THIS_MODULE, }; static u64 nsim_fib_ipv4_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB, false); } static u64 nsim_fib_ipv4_rules_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB_RULES, false); } static u64 nsim_fib_ipv6_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB, false); } static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false); } static u64 nsim_fib_nexthops_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false); } static void nsim_fib_set_max_all(struct nsim_fib_data *data, struct devlink *devlink) { static const enum nsim_resource_id res_ids[] = { NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, NSIM_RESOURCE_NEXTHOPS, }; int i; for (i = 0; i < ARRAY_SIZE(res_ids); i++) { int err; u64 val; err = devl_resource_size_get(devlink, res_ids[i], &val); if (err) val = (u64) -1; nsim_fib_set_max(data, res_ids[i], val); } } static void nsim_fib_event_work(struct work_struct *work) { struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, fib_event_work); struct nsim_fib_event *fib_event, *next_fib_event; LIST_HEAD(fib_event_queue); spin_lock_bh(&data->fib_event_queue_lock); list_splice_init(&data->fib_event_queue, &fib_event_queue); spin_unlock_bh(&data->fib_event_queue_lock); mutex_lock(&data->fib_lock); list_for_each_entry_safe(fib_event, next_fib_event, &fib_event_queue, list) { nsim_fib_event(fib_event); list_del(&fib_event->list); kfree(fib_event); cond_resched(); } mutex_unlock(&data->fib_lock); } static void nsim_fib_flush_work(struct work_struct *work) { struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, fib_flush_work); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; /* Process pending work. */ flush_work(&data->fib_event_work); mutex_lock(&data->fib_lock); list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) { rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node, nsim_fib_rt_ht_params); nsim_fib_rt_free(fib_rt, data); } mutex_unlock(&data->fib_lock); } static int nsim_fib_debugfs_init(struct nsim_fib_data *data, struct nsim_dev *nsim_dev) { data->ddir = debugfs_create_dir("fib", nsim_dev->ddir); if (IS_ERR(data->ddir)) return PTR_ERR(data->ddir); data->fail_route_offload = false; debugfs_create_bool("fail_route_offload", 0600, data->ddir, &data->fail_route_offload); data->fail_res_nexthop_group_replace = false; debugfs_create_bool("fail_res_nexthop_group_replace", 0600, data->ddir, &data->fail_res_nexthop_group_replace); data->fail_nexthop_bucket_replace = false; debugfs_create_bool("fail_nexthop_bucket_replace", 0600, data->ddir, &data->fail_nexthop_bucket_replace); debugfs_create_file("nexthop_bucket_activity", 0200, data->ddir, data, &nsim_nexthop_bucket_activity_fops); data->fail_route_delete = false; debugfs_create_bool("fail_route_delete", 0600, data->ddir, &data->fail_route_delete); return 0; } static void nsim_fib_debugfs_exit(struct nsim_fib_data *data) { debugfs_remove_recursive(data->ddir); } struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, struct netlink_ext_ack *extack) { struct nsim_fib_data *data; struct nsim_dev *nsim_dev; int err; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); data->devlink = devlink; nsim_dev = devlink_priv(devlink); err = nsim_fib_debugfs_init(data, nsim_dev); if (err) goto err_data_free; mutex_init(&data->nh_lock); err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params); if (err) goto err_debugfs_exit; mutex_init(&data->fib_lock); INIT_LIST_HEAD(&data->fib_rt_list); err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params); if (err) goto err_rhashtable_nexthop_destroy; INIT_WORK(&data->fib_event_work, nsim_fib_event_work); INIT_WORK(&data->fib_flush_work, nsim_fib_flush_work); INIT_LIST_HEAD(&data->fib_event_queue); spin_lock_init(&data->fib_event_queue_lock); nsim_fib_set_max_all(data, devlink); data->nexthop_nb.notifier_call = nsim_nexthop_event_nb; err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb, extack); if (err) { pr_err("Failed to register nexthop notifier\n"); goto err_rhashtable_fib_destroy; } data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(devlink_net(devlink), &data->fib_nb, nsim_fib_dump_inconsistent, extack); if (err) { pr_err("Failed to register fib notifier\n"); goto err_nexthop_nb_unregister; } devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV4_FIB, nsim_fib_ipv4_resource_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV4_FIB_RULES, nsim_fib_ipv4_rules_res_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV6_FIB, nsim_fib_ipv6_resource_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV6_FIB_RULES, nsim_fib_ipv6_rules_res_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_NEXTHOPS, nsim_fib_nexthops_res_occ_get, data); return data; err_nexthop_nb_unregister: unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); err_rhashtable_fib_destroy: cancel_work_sync(&data->fib_flush_work); flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); err_rhashtable_nexthop_destroy: rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); mutex_destroy(&data->fib_lock); err_debugfs_exit: mutex_destroy(&data->nh_lock); nsim_fib_debugfs_exit(data); err_data_free: kfree(data); return ERR_PTR(err); } void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) { devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_NEXTHOPS); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB_RULES); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB_RULES); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB); unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); cancel_work_sync(&data->fib_flush_work); flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); WARN_ON_ONCE(!list_empty(&data->fib_event_queue)); WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); mutex_destroy(&data->fib_lock); mutex_destroy(&data->nh_lock); nsim_fib_debugfs_exit(data); kfree(data); } |
| 1 1 1 1 1 1 1 3 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 | // SPDX-License-Identifier: GPL-2.0+ /* * inode.c -- user mode filesystem api for usb gadget controllers * * Copyright (C) 2003-2004 David Brownell * Copyright (C) 2003 Agilent Technologies */ /* #define VERBOSE_DEBUG */ #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/uts.h> #include <linux/wait.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/kthread.h> #include <linux/aio.h> #include <linux/uio.h> #include <linux/refcount.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/moduleparam.h> #include <linux/usb/gadgetfs.h> #include <linux/usb/gadget.h> #include <linux/usb/composite.h> /* for USB_GADGET_DELAYED_STATUS */ /* Undef helpers from linux/usb/composite.h as gadgetfs redefines them */ #undef DBG #undef ERROR #undef INFO /* * The gadgetfs API maps each endpoint to a file descriptor so that you * can use standard synchronous read/write calls for I/O. There's some * O_NONBLOCK and O_ASYNC/FASYNC style i/o support. Example usermode * drivers show how this works in practice. You can also use AIO to * eliminate I/O gaps between requests, to help when streaming data. * * Key parts that must be USB-specific are protocols defining how the * read/write operations relate to the hardware state machines. There * are two types of files. One type is for the device, implementing ep0. * The other type is for each IN or OUT endpoint. In both cases, the * user mode driver must configure the hardware before using it. * * - First, dev_config() is called when /dev/gadget/$CHIP is configured * (by writing configuration and device descriptors). Afterwards it * may serve as a source of device events, used to handle all control * requests other than basic enumeration. * * - Then, after a SET_CONFIGURATION control request, ep_config() is * called when each /dev/gadget/ep* file is configured (by writing * endpoint descriptors). Afterwards these files are used to write() * IN data or to read() OUT data. To halt the endpoint, a "wrong * direction" request is issued (like reading an IN endpoint). * * Unlike "usbfs" the only ioctl()s are for things that are rare, and maybe * not possible on all hardware. For example, precise fault handling with * respect to data left in endpoint fifos after aborted operations; or * selective clearing of endpoint halts, to implement SET_INTERFACE. */ #define DRIVER_DESC "USB Gadget filesystem" #define DRIVER_VERSION "24 Aug 2004" static const char driver_desc [] = DRIVER_DESC; static const char shortname [] = "gadgetfs"; MODULE_DESCRIPTION (DRIVER_DESC); MODULE_AUTHOR ("David Brownell"); MODULE_LICENSE ("GPL"); static int ep_open(struct inode *, struct file *); /*----------------------------------------------------------------------*/ #define GADGETFS_MAGIC 0xaee71ee7 /* /dev/gadget/$CHIP represents ep0 and the whole device */ enum ep0_state { /* DISABLED is the initial state. */ STATE_DEV_DISABLED = 0, /* Only one open() of /dev/gadget/$CHIP; only one file tracks * ep0/device i/o modes and binding to the controller. Driver * must always write descriptors to initialize the device, then * the device becomes UNCONNECTED until enumeration. */ STATE_DEV_OPENED, /* From then on, ep0 fd is in either of two basic modes: * - (UN)CONNECTED: read usb_gadgetfs_event(s) from it * - SETUP: read/write will transfer control data and succeed; * or if "wrong direction", performs protocol stall */ STATE_DEV_UNCONNECTED, STATE_DEV_CONNECTED, STATE_DEV_SETUP, /* UNBOUND means the driver closed ep0, so the device won't be * accessible again (DEV_DISABLED) until all fds are closed. */ STATE_DEV_UNBOUND, }; /* enough for the whole queue: most events invalidate others */ #define N_EVENT 5 #define RBUF_SIZE 256 struct dev_data { spinlock_t lock; refcount_t count; int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; struct fasync_struct *fasync; u8 current_config; /* drivers reading ep0 MUST handle control requests (SETUP) * reported that way; else the host will time out. */ unsigned usermode_setup : 1, setup_in : 1, setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, setup_abort : 1, gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ struct usb_config_descriptor *config, *hs_config; struct usb_device_descriptor *dev; struct usb_request *req; struct usb_gadget *gadget; struct list_head epfiles; void *buf; wait_queue_head_t wait; struct super_block *sb; struct dentry *dentry; /* except this scratch i/o buffer for ep0 */ u8 rbuf[RBUF_SIZE]; }; static inline void get_dev (struct dev_data *data) { refcount_inc (&data->count); } static void put_dev (struct dev_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; /* needs no more cleanup */ BUG_ON (waitqueue_active (&data->wait)); kfree (data); } static struct dev_data *dev_new (void) { struct dev_data *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; dev->state = STATE_DEV_DISABLED; refcount_set (&dev->count, 1); spin_lock_init (&dev->lock); INIT_LIST_HEAD (&dev->epfiles); init_waitqueue_head (&dev->wait); return dev; } /*----------------------------------------------------------------------*/ /* other /dev/gadget/$ENDPOINT files represent endpoints */ enum ep_state { STATE_EP_DISABLED = 0, STATE_EP_READY, STATE_EP_ENABLED, STATE_EP_UNBOUND, }; struct ep_data { struct mutex lock; enum ep_state state; refcount_t count; struct dev_data *dev; /* must hold dev->lock before accessing ep or req */ struct usb_ep *ep; struct usb_request *req; ssize_t status; char name [16]; struct usb_endpoint_descriptor desc, hs_desc; struct list_head epfiles; wait_queue_head_t wait; struct dentry *dentry; }; static inline void get_ep (struct ep_data *data) { refcount_inc (&data->count); } static void put_ep (struct ep_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; put_dev (data->dev); /* needs no more cleanup */ BUG_ON (!list_empty (&data->epfiles)); BUG_ON (waitqueue_active (&data->wait)); kfree (data); } /*----------------------------------------------------------------------*/ /* most "how to use the hardware" policy choices are in userspace: * mapping endpoint roles (which the driver needs) to the capabilities * which the usb controller has. most of those capabilities are exposed * implicitly, starting with the driver name and then endpoint names. */ static const char *CHIP; static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */ /*----------------------------------------------------------------------*/ /* NOTE: don't use dev_printk calls before binding to the gadget * at the end of ep0 configuration, or after unbind. */ /* too wordy: dev_printk(level , &(d)->gadget->dev , fmt , ## args) */ #define xprintk(d,level,fmt,args...) \ printk(level "%s: " fmt , shortname , ## args) #ifdef DEBUG #define DBG(dev,fmt,args...) \ xprintk(dev , KERN_DEBUG , fmt , ## args) #else #define DBG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #ifdef VERBOSE_DEBUG #define VDEBUG DBG #else #define VDEBUG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #define ERROR(dev,fmt,args...) \ xprintk(dev , KERN_ERR , fmt , ## args) #define INFO(dev,fmt,args...) \ xprintk(dev , KERN_INFO , fmt , ## args) /*----------------------------------------------------------------------*/ /* SYNCHRONOUS ENDPOINT OPERATIONS (bulk/intr/iso) * * After opening, configure non-control endpoints. Then use normal * stream read() and write() requests; and maybe ioctl() to get more * precise FIFO status when recovering from cancellation. */ static void epio_complete (struct usb_ep *ep, struct usb_request *req) { struct ep_data *epdata = ep->driver_data; if (!req->context) return; if (req->status) epdata->status = req->status; else epdata->status = req->actual; complete ((struct completion *)req->context); } /* tasklock endpoint, returning when it's connected. * still need dev->lock to use epdata->ep. */ static int get_ready_ep (unsigned f_flags, struct ep_data *epdata, bool is_write) { int val; if (f_flags & O_NONBLOCK) { if (!mutex_trylock(&epdata->lock)) goto nonblock; if (epdata->state != STATE_EP_ENABLED && (!is_write || epdata->state != STATE_EP_READY)) { mutex_unlock(&epdata->lock); nonblock: val = -EAGAIN; } else val = 0; return val; } val = mutex_lock_interruptible(&epdata->lock); if (val < 0) return val; switch (epdata->state) { case STATE_EP_ENABLED: return 0; case STATE_EP_READY: /* not configured yet */ if (is_write) return 0; fallthrough; case STATE_EP_UNBOUND: /* clean disconnect */ break; // case STATE_EP_DISABLED: /* "can't happen" */ default: /* error! */ pr_debug ("%s: ep %p not available, state %d\n", shortname, epdata, epdata->state); } mutex_unlock(&epdata->lock); return -ENODEV; } static ssize_t ep_io (struct ep_data *epdata, void *buf, unsigned len) { DECLARE_COMPLETION_ONSTACK (done); int value; spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { struct usb_request *req = epdata->req; req->context = &done; req->complete = epio_complete; req->buf = buf; req->length = len; value = usb_ep_queue (epdata->ep, req, GFP_ATOMIC); } else value = -ENODEV; spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { value = wait_for_completion_interruptible(&done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { DBG (epdata->dev, "%s i/o interrupted\n", epdata->name); usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); wait_for_completion(&done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { spin_unlock_irq (&epdata->dev->lock); DBG (epdata->dev, "endpoint gone\n"); wait_for_completion(&done); epdata->status = -ENODEV; } } return epdata->status; } return value; } static int ep_release (struct inode *inode, struct file *fd) { struct ep_data *data = fd->private_data; int value; value = mutex_lock_interruptible(&data->lock); if (value < 0) return value; /* clean up if this can be reopened */ if (data->state != STATE_EP_UNBOUND) { data->state = STATE_EP_DISABLED; data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; usb_ep_disable(data->ep); } mutex_unlock(&data->lock); put_ep (data); return 0; } static long ep_ioctl(struct file *fd, unsigned code, unsigned long value) { struct ep_data *data = fd->private_data; int status; if ((status = get_ready_ep (fd->f_flags, data, false)) < 0) return status; spin_lock_irq (&data->dev->lock); if (likely (data->ep != NULL)) { switch (code) { case GADGETFS_FIFO_STATUS: status = usb_ep_fifo_status (data->ep); break; case GADGETFS_FIFO_FLUSH: usb_ep_fifo_flush (data->ep); break; case GADGETFS_CLEAR_HALT: status = usb_ep_clear_halt (data->ep); break; default: status = -ENOTTY; } } else status = -ENODEV; spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return status; } /*----------------------------------------------------------------------*/ /* ASYNCHRONOUS ENDPOINT I/O OPERATIONS (bulk/intr/iso) */ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; struct kiocb *iocb; struct mm_struct *mm; struct work_struct work; void *buf; struct iov_iter to; const void *to_free; unsigned actual; }; static int ep_aio_cancel(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; struct ep_data *epdata; int value; local_irq_disable(); epdata = priv->epdata; // spin_lock(&epdata->dev->lock); if (likely(epdata && epdata->ep && priv->req)) value = usb_ep_dequeue (epdata->ep, priv->req); else value = -EINVAL; // spin_unlock(&epdata->dev->lock); local_irq_enable(); return value; } static void ep_user_copy_worker(struct work_struct *work) { struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); struct mm_struct *mm = priv->mm; struct kiocb *iocb = priv->iocb; size_t ret; kthread_use_mm(mm); ret = copy_to_iter(priv->buf, priv->actual, &priv->to); kthread_unuse_mm(mm); if (!ret) ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ iocb->ki_complete(iocb, ret); kfree(priv->buf); kfree(priv->to_free); kfree(priv); } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) { struct kiocb *iocb = req->context; struct kiocb_priv *priv = iocb->private; struct ep_data *epdata = priv->epdata; /* lock against disconnect (and ideally, cancel) */ spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; /* if this was a write or a read returning no data then we * don't need to copy anything to userspace, so we can * complete the aio request immediately. */ if (priv->to_free == NULL || unlikely(req->actual == 0)) { kfree(req->buf); kfree(priv->to_free); kfree(priv); iocb->private = NULL; iocb->ki_complete(iocb, req->actual ? req->actual : (long)req->status); } else { /* ep_copy_to_user() won't report both; we hide some faults */ if (unlikely(0 != req->status)) DBG(epdata->dev, "%s fault %d len %d\n", ep->name, req->status, req->actual); priv->buf = req->buf; priv->actual = req->actual; INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } usb_ep_free_request(ep, req); spin_unlock(&epdata->dev->lock); put_ep(epdata); } static ssize_t ep_aio(struct kiocb *iocb, struct kiocb_priv *priv, struct ep_data *epdata, char *buf, size_t len) { struct usb_request *req; ssize_t value; iocb->private = priv; priv->iocb = iocb; kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); priv->epdata = epdata; priv->actual = 0; priv->mm = current->mm; /* mm teardown waits for iocbs in exit_aio() */ /* each kiocb is coupled to one usb_request, but we can't * allocate or submit those if the host disconnected. */ spin_lock_irq(&epdata->dev->lock); value = -ENODEV; if (unlikely(epdata->ep == NULL)) goto fail; req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); value = -ENOMEM; if (unlikely(!req)) goto fail; priv->req = req; req->buf = buf; req->length = len; req->complete = ep_aio_complete; req->context = iocb; value = usb_ep_queue(epdata->ep, req, GFP_ATOMIC); if (unlikely(0 != value)) { usb_ep_free_request(epdata->ep, req); goto fail; } spin_unlock_irq(&epdata->dev->lock); return -EIOCBQUEUED; fail: spin_unlock_irq(&epdata->dev->lock); kfree(priv->to_free); kfree(priv); put_ep(epdata); return value; } static ssize_t ep_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(to); ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, false)) < 0) return value; /* halt any endpoint by doing a "wrong direction" i/o call */ if (usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); if (value >= 0 && (copy_to_iter(buf, value, to) != value)) value = -EFAULT; } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); value = -ENOMEM; if (!priv) goto fail; priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); if (!iter_is_ubuf(&priv->to) && !priv->to_free) { kfree(priv); goto fail; } value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } fail: kfree(buf); mutex_unlock(&epdata->lock); return value; } static ssize_t ep_config(struct ep_data *, const char *, size_t); static ssize_t ep_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(from); bool configured; ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, true)) < 0) return value; configured = epdata->state == STATE_EP_ENABLED; /* halt any endpoint by doing a "wrong direction" i/o call */ if (configured && !usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (unlikely(!copy_from_iter_full(buf, len, from))) { value = -EFAULT; goto out; } if (unlikely(!configured)) { value = ep_config(epdata, buf, len); } else if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); value = -ENOMEM; if (priv) { value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } } out: kfree(buf); mutex_unlock(&epdata->lock); return value; } /*----------------------------------------------------------------------*/ /* used after endpoint configuration */ static const struct file_operations ep_io_operations = { .owner = THIS_MODULE, .open = ep_open, .release = ep_release, .llseek = no_llseek, .unlocked_ioctl = ep_ioctl, .read_iter = ep_read_iter, .write_iter = ep_write_iter, }; /* ENDPOINT INITIALIZATION * * fd = open ("/dev/gadget/$ENDPOINT", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the endpoint configuration, configuring * the controller to process bulk, interrupt, or isochronous transfers * at the right maxpacket size, and so on. * * The descriptors are message type 1, identified by a host order u32 * at the beginning of what's written. Descriptor order is: full/low * speed descriptor, then optional high speed descriptor. */ static ssize_t ep_config (struct ep_data *data, const char *buf, size_t len) { struct usb_ep *ep; u32 tag; int value, length = len; if (data->state != STATE_EP_READY) { value = -EL2HLT; goto fail; } value = len; if (len < USB_DT_ENDPOINT_SIZE + 4) goto fail0; /* we might need to change message format someday */ memcpy(&tag, buf, 4); if (tag != 1) { DBG(data->dev, "config %s, bad tag %d\n", data->name, tag); goto fail0; } buf += 4; len -= 4; /* NOTE: audio endpoint extensions not accepted here; * just don't include the extra bytes. */ /* full/low speed descriptor, then high speed */ memcpy(&data->desc, buf, USB_DT_ENDPOINT_SIZE); if (data->desc.bLength != USB_DT_ENDPOINT_SIZE || data->desc.bDescriptorType != USB_DT_ENDPOINT) goto fail0; if (len != USB_DT_ENDPOINT_SIZE) { if (len != 2 * USB_DT_ENDPOINT_SIZE) goto fail0; memcpy(&data->hs_desc, buf + USB_DT_ENDPOINT_SIZE, USB_DT_ENDPOINT_SIZE); if (data->hs_desc.bLength != USB_DT_ENDPOINT_SIZE || data->hs_desc.bDescriptorType != USB_DT_ENDPOINT) { DBG(data->dev, "config %s, bad hs length or type\n", data->name); goto fail0; } } spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) { value = -ENOENT; goto gone; } else { ep = data->ep; if (ep == NULL) { value = -ENODEV; goto gone; } } switch (data->dev->gadget->speed) { case USB_SPEED_LOW: case USB_SPEED_FULL: ep->desc = &data->desc; break; case USB_SPEED_HIGH: /* fails if caller didn't provide that descriptor... */ ep->desc = &data->hs_desc; break; default: DBG(data->dev, "unconnected, %s init abandoned\n", data->name); value = -EINVAL; goto gone; } value = usb_ep_enable(ep); if (value == 0) { data->state = STATE_EP_ENABLED; value = length; } gone: spin_unlock_irq (&data->dev->lock); if (value < 0) { fail: data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; } return value; fail0: value = -EINVAL; goto fail; } static int ep_open (struct inode *inode, struct file *fd) { struct ep_data *data = inode->i_private; int value = -EBUSY; if (mutex_lock_interruptible(&data->lock) != 0) return -EINTR; spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) value = -ENOENT; else if (data->state == STATE_EP_DISABLED) { value = 0; data->state = STATE_EP_READY; get_ep (data); fd->private_data = data; VDEBUG (data->dev, "%s ready\n", data->name); } else DBG (data->dev, "%s state %d\n", data->name, data->state); spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return value; } /*----------------------------------------------------------------------*/ /* EP0 IMPLEMENTATION can be partly in userspace. * * Drivers that use this facility receive various events, including * control requests the kernel doesn't handle. Drivers that don't * use this facility may be too simple-minded for real applications. */ static inline void ep0_readable (struct dev_data *dev) { wake_up (&dev->wait); kill_fasync (&dev->fasync, SIGIO, POLL_IN); } static void clean_req (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; if (req->buf != dev->rbuf) { kfree(req->buf); req->buf = dev->rbuf; } req->complete = epio_complete; dev->setup_out_ready = 0; } static void ep0_complete (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; unsigned long flags; int free = 1; /* for control OUT, data must still get to userspace */ spin_lock_irqsave(&dev->lock, flags); if (!dev->setup_in) { dev->setup_out_error = (req->status != 0); if (!dev->setup_out_error) free = 0; dev->setup_out_ready = 1; ep0_readable (dev); } /* clean up as appropriate */ if (free && req->buf != &dev->rbuf) clean_req (ep, req); req->complete = epio_complete; spin_unlock_irqrestore(&dev->lock, flags); } static int setup_req (struct usb_ep *ep, struct usb_request *req, u16 len) { struct dev_data *dev = ep->driver_data; if (dev->setup_out_ready) { DBG (dev, "ep0 request busy!\n"); return -EBUSY; } if (len > sizeof (dev->rbuf)) req->buf = kmalloc(len, GFP_ATOMIC); if (req->buf == NULL) { req->buf = dev->rbuf; return -ENOMEM; } req->complete = ep0_complete; req->length = len; req->zero = 0; return 0; } static ssize_t ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval; enum ep0_state state; spin_lock_irq (&dev->lock); if (dev->state <= STATE_DEV_OPENED) { retval = -EINVAL; goto done; } /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; goto done; } /* control DATA stage */ if ((state = dev->state) == STATE_DEV_SETUP) { if (dev->setup_in) { /* stall IN */ VDEBUG(dev, "ep0in stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else if (len == 0) { /* ack SET_CONFIGURATION etc */ struct usb_ep *ep = dev->gadget->ep0; struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; /* assume that was SET_CONFIGURATION */ if (dev->current_config) { unsigned power; if (gadget_is_dualspeed(dev->gadget) && (dev->gadget->speed == USB_SPEED_HIGH)) power = dev->hs_config->bMaxPower; else power = dev->config->bMaxPower; usb_gadget_vbus_draw(dev->gadget, 2 * power); } } else { /* collect OUT data */ if ((fd->f_flags & O_NONBLOCK) != 0 && !dev->setup_out_ready) { retval = -EAGAIN; goto done; } spin_unlock_irq (&dev->lock); retval = wait_event_interruptible (dev->wait, dev->setup_out_ready != 0); /* FIXME state could change from under us */ spin_lock_irq (&dev->lock); if (retval) goto done; if (dev->state != STATE_DEV_SETUP) { retval = -ECANCELED; goto done; } dev->state = STATE_DEV_CONNECTED; if (dev->setup_out_error) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); ++dev->udc_usage; spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; spin_lock_irq(&dev->lock); --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } } goto done; } /* else normal: return event data */ if (len < sizeof dev->event [0]) { retval = -EINVAL; goto done; } len -= len % sizeof (struct usb_gadgetfs_event); dev->usermode_setup = 1; scan: /* return queued events right away */ if (dev->ev_next != 0) { unsigned i, n; n = len / sizeof (struct usb_gadgetfs_event); if (dev->ev_next < n) n = dev->ev_next; /* ep0 i/o has special semantics during STATE_DEV_SETUP */ for (i = 0; i < n; i++) { if (dev->event [i].type == GADGETFS_SETUP) { dev->state = STATE_DEV_SETUP; n = i + 1; break; } } spin_unlock_irq (&dev->lock); len = n * sizeof (struct usb_gadgetfs_event); if (copy_to_user (buf, &dev->event, len)) retval = -EFAULT; else retval = len; if (len > 0) { /* NOTE this doesn't guard against broken drivers; * concurrent ep0 readers may lose events. */ spin_lock_irq (&dev->lock); if (dev->ev_next > n) { memmove(&dev->event[0], &dev->event[n], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - n)); } dev->ev_next -= n; spin_unlock_irq (&dev->lock); } return retval; } if (fd->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto done; } switch (state) { default: DBG (dev, "fail %s, state %d\n", __func__, state); retval = -ESRCH; break; case STATE_DEV_UNCONNECTED: case STATE_DEV_CONNECTED: spin_unlock_irq (&dev->lock); DBG (dev, "%s wait\n", __func__); /* wait for events */ retval = wait_event_interruptible (dev->wait, dev->ev_next != 0); if (retval < 0) return retval; spin_lock_irq (&dev->lock); goto scan; } done: spin_unlock_irq (&dev->lock); return retval; } static struct usb_gadgetfs_event * next_event (struct dev_data *dev, enum usb_gadgetfs_event_type type) { struct usb_gadgetfs_event *event; unsigned i; switch (type) { /* these events purge the queue */ case GADGETFS_DISCONNECT: if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; fallthrough; case GADGETFS_CONNECT: dev->ev_next = 0; break; case GADGETFS_SETUP: /* previous request timed out */ case GADGETFS_SUSPEND: /* same effect */ /* these events can't be repeated */ for (i = 0; i != dev->ev_next; i++) { if (dev->event [i].type != type) continue; DBG(dev, "discard old event[%d] %d\n", i, type); dev->ev_next--; if (i == dev->ev_next) break; /* indices start at zero, for simplicity */ memmove (&dev->event [i], &dev->event [i + 1], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - i)); } break; default: BUG (); } VDEBUG(dev, "event[%d] = %d\n", dev->ev_next, type); event = &dev->event [dev->ev_next++]; BUG_ON (dev->ev_next > N_EVENT); memset (event, 0, sizeof *event); event->type = type; return event; } static ssize_t ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval = -ESRCH; /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; /* data and/or status stage for control request */ } else if (dev->state == STATE_DEV_SETUP) { len = min_t(size_t, len, dev->setup_wLength); if (dev->setup_in) { retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; else { if (len < dev->setup_wLength) dev->req->zero = 1; retval = usb_ep_queue ( dev->gadget->ep0, dev->req, GFP_KERNEL); } spin_lock_irq(&dev->lock); --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else retval = len; return retval; } /* can stall some OUT transfers */ } else if (dev->setup_can_stall) { VDEBUG(dev, "ep0out stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else { DBG(dev, "bogus ep0out stall!\n"); } } else DBG (dev, "fail %s, state %d\n", __func__, dev->state); return retval; } static int ep0_fasync (int f, struct file *fd, int on) { struct dev_data *dev = fd->private_data; // caller must F_SETOWN before signal delivery happens VDEBUG (dev, "%s %s\n", __func__, on ? "on" : "off"); return fasync_helper (f, fd, on, &dev->fasync); } static struct usb_gadget_driver gadgetfs_driver; static int dev_release (struct inode *inode, struct file *fd) { struct dev_data *dev = fd->private_data; /* closing ep0 === shutdown all */ if (dev->gadget_registered) { usb_gadget_unregister_driver (&gadgetfs_driver); dev->gadget_registered = false; } /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. * alternatively, all host requests will time out. */ kfree (dev->buf); dev->buf = NULL; /* other endpoints were all decoupled from this device */ spin_lock_irq(&dev->lock); dev->state = STATE_DEV_DISABLED; spin_unlock_irq(&dev->lock); put_dev (dev); return 0; } static __poll_t ep0_poll (struct file *fd, poll_table *wait) { struct dev_data *dev = fd->private_data; __poll_t mask = 0; if (dev->state <= STATE_DEV_OPENED) return DEFAULT_POLLMASK; poll_wait(fd, &dev->wait, wait); spin_lock_irq(&dev->lock); /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; mask = EPOLLHUP; goto out; } if (dev->state == STATE_DEV_SETUP) { if (dev->setup_in || dev->setup_can_stall) mask = EPOLLOUT; } else { if (dev->ev_next != 0) mask = EPOLLIN; } out: spin_unlock_irq(&dev->lock); return mask; } static long gadget_dev_ioctl (struct file *fd, unsigned code, unsigned long value) { struct dev_data *dev = fd->private_data; struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_OPENED || dev->state == STATE_DEV_UNBOUND) { /* Not bound to a UDC */ } else if (gadget->ops->ioctl) { ++dev->udc_usage; spin_unlock_irq(&dev->lock); ret = gadget->ops->ioctl (gadget, code, value); spin_lock_irq(&dev->lock); --dev->udc_usage; } spin_unlock_irq(&dev->lock); return ret; } /*----------------------------------------------------------------------*/ /* The in-kernel gadget driver handles most ep0 issues, in particular * enumerating the single configuration (as provided from user space). * * Unrecognized ep0 requests may be handled in user space. */ static void make_qualifier (struct dev_data *dev) { struct usb_qualifier_descriptor qual; struct usb_device_descriptor *desc; qual.bLength = sizeof qual; qual.bDescriptorType = USB_DT_DEVICE_QUALIFIER; qual.bcdUSB = cpu_to_le16 (0x0200); desc = dev->dev; qual.bDeviceClass = desc->bDeviceClass; qual.bDeviceSubClass = desc->bDeviceSubClass; qual.bDeviceProtocol = desc->bDeviceProtocol; /* assumes ep0 uses the same value for both speeds ... */ qual.bMaxPacketSize0 = dev->gadget->ep0->maxpacket; qual.bNumConfigurations = 1; qual.bRESERVED = 0; memcpy (dev->rbuf, &qual, sizeof qual); } static int config_buf (struct dev_data *dev, u8 type, unsigned index) { int len; int hs = 0; /* only one configuration */ if (index > 0) return -EINVAL; if (gadget_is_dualspeed(dev->gadget)) { hs = (dev->gadget->speed == USB_SPEED_HIGH); if (type == USB_DT_OTHER_SPEED_CONFIG) hs = !hs; } if (hs) { dev->req->buf = dev->hs_config; len = le16_to_cpu(dev->hs_config->wTotalLength); } else { dev->req->buf = dev->config; len = le16_to_cpu(dev->config->wTotalLength); } ((u8 *)dev->req->buf) [1] = type; return len; } static int gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) { struct dev_data *dev = get_gadget_data (gadget); struct usb_request *req = dev->req; int value = -EOPNOTSUPP; struct usb_gadgetfs_event *event; u16 w_value = le16_to_cpu(ctrl->wValue); u16 w_length = le16_to_cpu(ctrl->wLength); if (w_length > RBUF_SIZE) { if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; } else { return value; } } spin_lock (&dev->lock); dev->setup_abort = 0; if (dev->state == STATE_DEV_UNCONNECTED) { if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH && dev->hs_config == NULL) { spin_unlock(&dev->lock); ERROR (dev, "no high speed config??\n"); return -EINVAL; } dev->state = STATE_DEV_CONNECTED; INFO (dev, "connected\n"); event = next_event (dev, GADGETFS_CONNECT); event->u.speed = gadget->speed; ep0_readable (dev); /* host may have given up waiting for response. we can miss control * requests handled lower down (device/endpoint status and features); * then ep0_{read,write} will report the wrong status. controller * driver will have aborted pending i/o. */ } else if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; req->buf = dev->rbuf; req->context = NULL; switch (ctrl->bRequest) { case USB_REQ_GET_DESCRIPTOR: if (ctrl->bRequestType != USB_DIR_IN) goto unrecognized; switch (w_value >> 8) { case USB_DT_DEVICE: value = min (w_length, (u16) sizeof *dev->dev); dev->dev->bMaxPacketSize0 = dev->gadget->ep0->maxpacket; req->buf = dev->dev; break; case USB_DT_DEVICE_QUALIFIER: if (!dev->hs_config) break; value = min (w_length, (u16) sizeof (struct usb_qualifier_descriptor)); make_qualifier (dev); break; case USB_DT_OTHER_SPEED_CONFIG: case USB_DT_CONFIG: value = config_buf (dev, w_value >> 8, w_value & 0xff); if (value >= 0) value = min (w_length, (u16) value); break; case USB_DT_STRING: goto unrecognized; default: // all others are errors break; } break; /* currently one config, two speeds */ case USB_REQ_SET_CONFIGURATION: if (ctrl->bRequestType != 0) goto unrecognized; if (0 == (u8) w_value) { value = 0; dev->current_config = 0; usb_gadget_vbus_draw(gadget, 8 /* mA */ ); // user mode expected to disable endpoints } else { u8 config, power; if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH) { config = dev->hs_config->bConfigurationValue; power = dev->hs_config->bMaxPower; } else { config = dev->config->bConfigurationValue; power = dev->config->bMaxPower; } if (config == (u8) w_value) { value = 0; dev->current_config = config; usb_gadget_vbus_draw(gadget, 2 * power); } } /* report SET_CONFIGURATION like any other control request, * except that usermode may not stall this. the next * request mustn't be allowed start until this finishes: * endpoints and threads set up, etc. * * NOTE: older PXA hardware (before PXA 255: without UDCCFR) * has bad/racey automagic that prevents synchronizing here. * even kernel mode drivers often miss them. */ if (value == 0) { INFO (dev, "configuration #%d\n", dev->current_config); usb_gadget_set_state(gadget, USB_STATE_CONFIGURED); if (dev->usermode_setup) { dev->setup_can_stall = 0; goto delegate; } } break; #ifndef CONFIG_USB_PXA25X /* PXA automagically handles this request too */ case USB_REQ_GET_CONFIGURATION: if (ctrl->bRequestType != 0x80) goto unrecognized; *(u8 *)req->buf = dev->current_config; value = min (w_length, (u16) 1); break; #endif default: unrecognized: VDEBUG (dev, "%s req%02x.%02x v%04x i%04x l%d\n", dev->usermode_setup ? "delegate" : "fail", ctrl->bRequestType, ctrl->bRequest, w_value, le16_to_cpu(ctrl->wIndex), w_length); /* if there's an ep0 reader, don't stall */ if (dev->usermode_setup) { dev->setup_can_stall = 1; delegate: dev->setup_in = (ctrl->bRequestType & USB_DIR_IN) ? 1 : 0; dev->setup_wLength = w_length; dev->setup_out_ready = 0; dev->setup_out_error = 0; /* read DATA stage for OUT right away */ if (unlikely (!dev->setup_in && w_length)) { value = setup_req (gadget->ep0, dev->req, w_length); if (value < 0) break; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; } /* we can't currently stall these */ dev->setup_can_stall = 0; } /* state changes when reader collects event */ event = next_event (dev, GADGETFS_SETUP); event->u.setup = *ctrl; ep0_readable (dev); spin_unlock (&dev->lock); /* * Return USB_GADGET_DELAYED_STATUS as a workaround to * stop some UDC drivers (e.g. dwc3) from automatically * proceeding with the status stage for 0-length * transfers. * Should be removed once all UDC drivers are fixed to * always delay the status stage until a response is * queued to EP0. */ return w_length == 0 ? USB_GADGET_DELAYED_STATUS : 0; } } /* proceed with data transfer and status phases? */ if (value >= 0 && dev->state != STATE_DEV_SETUP) { req->length = value; req->zero = value < w_length; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); spin_lock(&dev->lock); --dev->udc_usage; spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; } return value; } /* device stalls when value < 0 */ spin_unlock (&dev->lock); return value; } static void destroy_ep_files (struct dev_data *dev) { DBG (dev, "%s %d\n", __func__, dev->state); /* dev->state must prevent interference */ spin_lock_irq (&dev->lock); while (!list_empty(&dev->epfiles)) { struct ep_data *ep; struct inode *parent; struct dentry *dentry; /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); spin_unlock_irq (&dev->lock); dentry = ep->dentry; ep->dentry = NULL; parent = d_inode(dentry->d_parent); /* break link to controller */ mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; mutex_unlock(&ep->lock); wake_up (&ep->wait); put_ep (ep); /* break link to dcache */ inode_lock(parent); d_delete (dentry); dput (dentry); inode_unlock(parent); spin_lock_irq (&dev->lock); } spin_unlock_irq (&dev->lock); } static struct dentry * gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops); static int activate_ep_files (struct dev_data *dev) { struct usb_ep *ep; struct ep_data *data; gadget_for_each_ep (ep, dev->gadget) { data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto enomem0; data->state = STATE_EP_DISABLED; mutex_init(&data->lock); init_waitqueue_head (&data->wait); strncpy (data->name, ep->name, sizeof (data->name) - 1); refcount_set (&data->count, 1); data->dev = dev; get_dev (dev); data->ep = ep; ep->driver_data = data; data->req = usb_ep_alloc_request (ep, GFP_KERNEL); if (!data->req) goto enomem1; data->dentry = gadgetfs_create_file (dev->sb, data->name, data, &ep_io_operations); if (!data->dentry) goto enomem2; list_add_tail (&data->epfiles, &dev->epfiles); } return 0; enomem2: usb_ep_free_request (ep, data->req); enomem1: put_dev (dev); kfree (data); enomem0: DBG (dev, "%s enomem\n", __func__); destroy_ep_files (dev); return -ENOMEM; } static void gadgetfs_unbind (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); DBG (dev, "%s\n", __func__); spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; while (dev->udc_usage > 0) { spin_unlock_irq(&dev->lock); usleep_range(1000, 2000); spin_lock_irq(&dev->lock); } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); gadget->ep0->driver_data = NULL; set_gadget_data (gadget, NULL); /* we've already been disconnected ... no i/o is active */ if (dev->req) usb_ep_free_request (gadget->ep0, dev->req); DBG (dev, "%s done\n", __func__); put_dev (dev); } static struct dev_data *the_device; static int gadgetfs_bind(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { struct dev_data *dev = the_device; if (!dev) return -ESRCH; if (0 != strcmp (CHIP, gadget->name)) { pr_err("%s expected %s controller not %s\n", shortname, CHIP, gadget->name); return -ENODEV; } set_gadget_data (gadget, dev); dev->gadget = gadget; gadget->ep0->driver_data = dev; /* preallocate control response and buffer */ dev->req = usb_ep_alloc_request (gadget->ep0, GFP_KERNEL); if (!dev->req) goto enomem; dev->req->context = NULL; dev->req->complete = epio_complete; if (activate_ep_files (dev) < 0) goto enomem; INFO (dev, "bound to %s driver\n", gadget->name); spin_lock_irq(&dev->lock); dev->state = STATE_DEV_UNCONNECTED; spin_unlock_irq(&dev->lock); get_dev (dev); return 0; enomem: gadgetfs_unbind (gadget); return -ENOMEM; } static void gadgetfs_disconnect (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; spin_lock_irqsave (&dev->lock, flags); if (dev->state == STATE_DEV_UNCONNECTED) goto exit; dev->state = STATE_DEV_UNCONNECTED; INFO (dev, "disconnected\n"); next_event (dev, GADGETFS_DISCONNECT); ep0_readable (dev); exit: spin_unlock_irqrestore (&dev->lock, flags); } static void gadgetfs_suspend (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; INFO (dev, "suspended from state %d\n", dev->state); spin_lock_irqsave(&dev->lock, flags); switch (dev->state) { case STATE_DEV_SETUP: // VERY odd... host died?? case STATE_DEV_CONNECTED: case STATE_DEV_UNCONNECTED: next_event (dev, GADGETFS_SUSPEND); ep0_readable (dev); fallthrough; default: break; } spin_unlock_irqrestore(&dev->lock, flags); } static struct usb_gadget_driver gadgetfs_driver = { .function = (char *) driver_desc, .bind = gadgetfs_bind, .unbind = gadgetfs_unbind, .setup = gadgetfs_setup, .reset = gadgetfs_disconnect, .disconnect = gadgetfs_disconnect, .suspend = gadgetfs_suspend, .driver = { .name = shortname, }, }; /*----------------------------------------------------------------------*/ /* DEVICE INITIALIZATION * * fd = open ("/dev/gadget/$CHIP", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the device configuration, so the kernel can * bind to the controller ... guaranteeing it can handle enumeration * at all necessary speeds. Descriptor order is: * * . message tag (u32, host order) ... for now, must be zero; it * would change to support features like multi-config devices * . full/low speed config ... all wTotalLength bytes (with interface, * class, altsetting, endpoint, and other descriptors) * . high speed config ... all descriptors, for high speed operation; * this one's optional except for high-speed hardware * . device descriptor * * Endpoints are not yet enabled. Drivers must wait until device * configuration and interface altsetting changes create * the need to configure (or unconfigure) them. * * After initialization, the device stays active for as long as that * $CHIP file is open. Events must then be read from that descriptor, * such as configuration notifications. */ static int is_valid_config(struct usb_config_descriptor *config, unsigned int total) { return config->bDescriptorType == USB_DT_CONFIG && config->bLength == USB_DT_CONFIG_SIZE && total >= USB_DT_CONFIG_SIZE && config->bConfigurationValue != 0 && (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0 && (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0; /* FIXME if gadget->is_otg, _must_ include an otg descriptor */ /* FIXME check lengths: walk to end */ } static ssize_t dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t value, length = len; unsigned total; u32 tag; char *kbuf; spin_lock_irq(&dev->lock); if (dev->state > STATE_DEV_OPENED) { value = ep0_write(fd, buf, len, ptr); spin_unlock_irq(&dev->lock); return value; } spin_unlock_irq(&dev->lock); if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) || (len > PAGE_SIZE * 4)) return -EINVAL; /* we might need to change message format someday */ if (copy_from_user (&tag, buf, 4)) return -EFAULT; if (tag != 0) return -EINVAL; buf += 4; length -= 4; kbuf = memdup_user(buf, length); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); spin_lock_irq (&dev->lock); value = -EINVAL; if (dev->buf) { spin_unlock_irq(&dev->lock); kfree(kbuf); return value; } dev->buf = kbuf; /* full or low speed config */ dev->config = (void *) kbuf; total = le16_to_cpu(dev->config->wTotalLength); if (!is_valid_config(dev->config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; /* optional high speed config */ if (kbuf [1] == USB_DT_CONFIG) { dev->hs_config = (void *) kbuf; total = le16_to_cpu(dev->hs_config->wTotalLength); if (!is_valid_config(dev->hs_config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; } else { dev->hs_config = NULL; } /* could support multiple configs, using another encoding! */ /* device descriptor (tweaked for paranoia) */ if (length != USB_DT_DEVICE_SIZE) goto fail; dev->dev = (void *)kbuf; if (dev->dev->bLength != USB_DT_DEVICE_SIZE || dev->dev->bDescriptorType != USB_DT_DEVICE || dev->dev->bNumConfigurations != 1) goto fail; dev->dev->bcdUSB = cpu_to_le16 (0x0200); /* triggers gadgetfs_bind(); then we can enumerate. */ spin_unlock_irq (&dev->lock); if (dev->hs_config) gadgetfs_driver.max_speed = USB_SPEED_HIGH; else gadgetfs_driver.max_speed = USB_SPEED_FULL; value = usb_gadget_register_driver(&gadgetfs_driver); if (value != 0) { spin_lock_irq(&dev->lock); goto fail; } else { /* at this point "good" hardware has for the first time * let the USB the host see us. alternatively, if users * unplug/replug that will clear all the error state. * * note: everything running before here was guaranteed * to choke driver model style diagnostics. from here * on, they can work ... except in cleanup paths that * kick in after the ep0 descriptor is closed. */ value = len; dev->gadget_registered = true; } return value; fail: dev->config = NULL; dev->hs_config = NULL; dev->dev = NULL; spin_unlock_irq (&dev->lock); pr_debug ("%s: %s fail %zd, %p\n", shortname, __func__, value, dev); kfree (dev->buf); dev->buf = NULL; return value; } static int gadget_dev_open (struct inode *inode, struct file *fd) { struct dev_data *dev = inode->i_private; int value = -EBUSY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_DISABLED) { dev->ev_next = 0; dev->state = STATE_DEV_OPENED; fd->private_data = dev; get_dev (dev); value = 0; } spin_unlock_irq(&dev->lock); return value; } static const struct file_operations ep0_operations = { .llseek = no_llseek, .open = gadget_dev_open, .read = ep0_read, .write = dev_config, .fasync = ep0_fasync, .poll = ep0_poll, .unlocked_ioctl = gadget_dev_ioctl, .release = dev_release, }; /*----------------------------------------------------------------------*/ /* FILESYSTEM AND SUPERBLOCK OPERATIONS * * Mounting the filesystem creates a controller file, used first for * device configuration then later for event monitoring. */ /* FIXME PAM etc could set this security policy without mount options * if epfiles inherited ownership and permissons from ep0 ... */ static unsigned default_uid; static unsigned default_gid; static unsigned default_perm = S_IRUSR | S_IWUSR; module_param (default_uid, uint, 0644); module_param (default_gid, uint, 0644); module_param (default_perm, uint, 0644); static struct inode * gadgetfs_make_inode (struct super_block *sb, void *data, const struct file_operations *fops, int mode) { struct inode *inode = new_inode (sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = make_kuid(&init_user_ns, default_uid); inode->i_gid = make_kgid(&init_user_ns, default_gid); simple_inode_init_ts(inode); inode->i_private = data; inode->i_fop = fops; } return inode; } /* creates in fs root directory, so non-renamable and non-linkable. * so inode and dentry are paired, until device reconfig. */ static struct dentry * gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops) { struct dentry *dentry; struct inode *inode; dentry = d_alloc_name(sb->s_root, name); if (!dentry) return NULL; inode = gadgetfs_make_inode (sb, data, fops, S_IFREG | (default_perm & S_IRWXUGO)); if (!inode) { dput(dentry); return NULL; } d_add (dentry, inode); return dentry; } static const struct super_operations gadget_fs_operations = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, }; static int gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dev_data *dev; int rc; mutex_lock(&sb_mutex); if (the_device) { rc = -ESRCH; goto Done; } CHIP = usb_get_gadget_udc_name(); if (!CHIP) { rc = -ENODEV; goto Done; } /* superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = GADGETFS_MAGIC; sb->s_op = &gadget_fs_operations; sb->s_time_gran = 1; /* root inode */ inode = gadgetfs_make_inode (sb, NULL, &simple_dir_operations, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) goto Enomem; inode->i_op = &simple_dir_inode_operations; if (!(sb->s_root = d_make_root (inode))) goto Enomem; /* the ep0 file is named after the controller we expect; * user mode code can use it for sanity checks, like we do. */ dev = dev_new (); if (!dev) goto Enomem; dev->sb = sb; dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &ep0_operations); if (!dev->dentry) { put_dev(dev); goto Enomem; } /* other endpoint files are available after hardware setup, * from binding to a controller. */ the_device = dev; rc = 0; goto Done; Enomem: kfree(CHIP); CHIP = NULL; rc = -ENOMEM; Done: mutex_unlock(&sb_mutex); return rc; } /* "mount -t gadgetfs path /dev/gadget" ends up here */ static int gadgetfs_get_tree(struct fs_context *fc) { return get_tree_single(fc, gadgetfs_fill_super); } static const struct fs_context_operations gadgetfs_context_ops = { .get_tree = gadgetfs_get_tree, }; static int gadgetfs_init_fs_context(struct fs_context *fc) { fc->ops = &gadgetfs_context_ops; return 0; } static void gadgetfs_kill_sb (struct super_block *sb) { mutex_lock(&sb_mutex); kill_litter_super (sb); if (the_device) { put_dev (the_device); the_device = NULL; } kfree(CHIP); CHIP = NULL; mutex_unlock(&sb_mutex); } /*----------------------------------------------------------------------*/ static struct file_system_type gadgetfs_type = { .owner = THIS_MODULE, .name = shortname, .init_fs_context = gadgetfs_init_fs_context, .kill_sb = gadgetfs_kill_sb, }; MODULE_ALIAS_FS("gadgetfs"); /*----------------------------------------------------------------------*/ static int __init gadgetfs_init (void) { int status; status = register_filesystem (&gadgetfs_type); if (status == 0) pr_info ("%s: %s, version " DRIVER_VERSION "\n", shortname, driver_desc); return status; } module_init (gadgetfs_init); static void __exit gadgetfs_cleanup (void) { pr_debug ("unregister %s\n", shortname); unregister_filesystem (&gadgetfs_type); } module_exit (gadgetfs_cleanup); |
| 1236 1234 3 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (flags & IFF_UP) continue; dev_change_flags(cpriv->dev, flags | IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (!(flags & IFF_UP)) continue; dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } /* Check child interfaces */ down_read_nested(&priv->vlan_rwsem, nesting); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } up_read(&priv->vlan_rwsem); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_update_features(dev); dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); down_write(&ppriv->vlan_rwsem); list_add_tail(&priv->list, &ppriv->child_intfs); up_write(&ppriv->vlan_rwsem); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ASSERT_RTNL(); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); list_del(&priv->list); up_write(&ppriv->vlan_rwsem); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = ipoib_sendq_size * 2; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); up_read(&priv->vlan_rwsem); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 14 401 262 20 186 97 53 181 43 58 153 10 51 13 72 17 3 3 116 48 4 10 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_INODE_H__ #define __XFS_INODE_H__ #include "xfs_inode_buf.h" #include "xfs_inode_fork.h" /* * Kernel only inode definitions */ struct xfs_dinode; struct xfs_inode; struct xfs_buf; struct xfs_bmbt_irec; struct xfs_inode_log_item; struct xfs_mount; struct xfs_trans; struct xfs_dquot; typedef struct xfs_inode { /* Inode linking and identification information. */ struct xfs_mount *i_mount; /* fs mount struct ptr */ struct xfs_dquot *i_udquot; /* user dquot */ struct xfs_dquot *i_gdquot; /* group dquot */ struct xfs_dquot *i_pdquot; /* project dquot */ /* Inode location stuff */ xfs_ino_t i_ino; /* inode number (agno/agino)*/ struct xfs_imap i_imap; /* location for xfs_imap() */ /* Extent information. */ struct xfs_ifork *i_cowfp; /* copy on write extents */ struct xfs_ifork i_df; /* data fork */ struct xfs_ifork i_af; /* attribute fork */ /* Transaction and locking information. */ struct xfs_inode_log_item *i_itemp; /* logging information */ struct rw_semaphore i_lock; /* inode lock */ atomic_t i_pincount; /* inode pin count */ struct llist_node i_gclist; /* deferred inactivation list */ /* * Bitsets of inode metadata that have been checked and/or are sick. * Callers must hold i_flags_lock before accessing this field. */ uint16_t i_checked; uint16_t i_sick; spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ unsigned long i_flags; /* see defined flags below */ uint64_t i_delayed_blks; /* count of delay alloc blks */ xfs_fsize_t i_disk_size; /* number of bytes in file */ xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */ prid_t i_projid; /* owner's project id */ xfs_extlen_t i_extsize; /* basic/minimum extent size */ /* cowextsize is only used for v3 inodes, flushiter for v1/2 */ union { xfs_extlen_t i_cowextsize; /* basic cow extent size */ uint16_t i_flushiter; /* incremented on flush */ }; uint8_t i_forkoff; /* attr fork offset >> 3 */ uint16_t i_diflags; /* XFS_DIFLAG_... */ uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ /* * Unlinked list pointers. These point to the next and previous inodes * in the AGI unlinked bucket list, respectively. These fields can * only be updated with the AGI locked. * * i_next_unlinked caches di_next_unlinked. */ xfs_agino_t i_next_unlinked; /* * If the inode is not on an unlinked list, this field is zero. If the * inode is the first element in an unlinked list, this field is * NULLAGINO. Otherwise, i_prev_unlinked points to the previous inode * in the unlinked list. */ xfs_agino_t i_prev_unlinked; /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ /* pending io completions */ spinlock_t i_ioend_lock; struct work_struct i_ioend_work; struct list_head i_ioend_list; } xfs_inode_t; static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip) { return ip->i_prev_unlinked != 0; } static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip) { return ip->i_forkoff > 0; } static inline struct xfs_ifork * xfs_ifork_ptr( struct xfs_inode *ip, int whichfork) { switch (whichfork) { case XFS_DATA_FORK: return &ip->i_df; case XFS_ATTR_FORK: if (!xfs_inode_has_attr_fork(ip)) return NULL; return &ip->i_af; case XFS_COW_FORK: return ip->i_cowfp; default: ASSERT(0); return NULL; } } static inline unsigned int xfs_inode_fork_boff(struct xfs_inode *ip) { return ip->i_forkoff << 3; } static inline unsigned int xfs_inode_data_fork_size(struct xfs_inode *ip) { if (xfs_inode_has_attr_fork(ip)) return xfs_inode_fork_boff(ip); return XFS_LITINO(ip->i_mount); } static inline unsigned int xfs_inode_attr_fork_size(struct xfs_inode *ip) { if (xfs_inode_has_attr_fork(ip)) return XFS_LITINO(ip->i_mount) - xfs_inode_fork_boff(ip); return 0; } static inline unsigned int xfs_inode_fork_size( struct xfs_inode *ip, int whichfork) { switch (whichfork) { case XFS_DATA_FORK: return xfs_inode_data_fork_size(ip); case XFS_ATTR_FORK: return xfs_inode_attr_fork_size(ip); default: return 0; } } /* Convert from vfs inode to xfs inode */ static inline struct xfs_inode *XFS_I(struct inode *inode) { return container_of(inode, struct xfs_inode, i_vnode); } /* convert from xfs inode to vfs inode */ static inline struct inode *VFS_I(struct xfs_inode *ip) { return &ip->i_vnode; } /* convert from const xfs inode to const vfs inode */ static inline const struct inode *VFS_IC(const struct xfs_inode *ip) { return &ip->i_vnode; } /* * For regular files we only update the on-disk filesize when actually * writing data back to disk. Until then only the copy in the VFS inode * is uptodate. */ static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip) { if (S_ISREG(VFS_I(ip)->i_mode)) return i_size_read(VFS_I(ip)); return ip->i_disk_size; } /* * If this I/O goes past the on-disk inode size update it unless it would * be past the current in-core inode size. */ static inline xfs_fsize_t xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size) { xfs_fsize_t i_size = i_size_read(VFS_I(ip)); if (new_size > i_size || new_size < 0) new_size = i_size; return new_size > ip->i_disk_size ? new_size : 0; } /* * i_flags helper functions */ static inline void __xfs_iflags_set(xfs_inode_t *ip, unsigned long flags) { ip->i_flags |= flags; } static inline void xfs_iflags_set(xfs_inode_t *ip, unsigned long flags) { spin_lock(&ip->i_flags_lock); __xfs_iflags_set(ip, flags); spin_unlock(&ip->i_flags_lock); } static inline void xfs_iflags_clear(xfs_inode_t *ip, unsigned long flags) { spin_lock(&ip->i_flags_lock); ip->i_flags &= ~flags; spin_unlock(&ip->i_flags_lock); } static inline int __xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) { return (ip->i_flags & flags); } static inline int xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = __xfs_iflags_test(ip, flags); spin_unlock(&ip->i_flags_lock); return ret; } static inline int xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = ip->i_flags & flags; if (ret) ip->i_flags &= ~flags; spin_unlock(&ip->i_flags_lock); return ret; } static inline int xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = ip->i_flags & flags; if (!ret) ip->i_flags |= flags; spin_unlock(&ip->i_flags_lock); return ret; } static inline prid_t xfs_get_initial_prid(struct xfs_inode *dp) { if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT) return dp->i_projid; return XFS_PROJID_DEFAULT; } static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_REFLINK; } static inline bool xfs_is_metadata_inode(struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; return ip == mp->m_rbmip || ip == mp->m_rsumip || xfs_is_quota_inode(&mp->m_sb, ip->i_ino); } /* * Check if an inode has any data in the COW fork. This might be often false * even for inodes with the reflink flag when there is no pending COW operation. */ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip) { return ip->i_cowfp && ip->i_cowfp->if_bytes; } static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME; } static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_NREXT64; } /* * Decide if this file is a realtime file whose data allocation unit is larger * than a single filesystem block. */ static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip) { return XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1; } /* * Return the buftarg used for data allocations on a given inode. */ #define xfs_inode_buftarg(ip) \ (XFS_IS_REALTIME_INODE(ip) ? \ (ip)->i_mount->m_rtdev_targp : (ip)->i_mount->m_ddev_targp) /* * In-core inode flags. */ #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ #define XFS_INEW (1 << 3) /* inode has just been allocated */ #define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */ #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ #define XFS_IFLUSHING (1 << 7) /* inode is being flushed */ #define __XFS_IPINNED_BIT 8 /* wakeup key for zero pin count */ #define XFS_IPINNED (1 << __XFS_IPINNED_BIT) #define XFS_IEOFBLOCKS (1 << 9) /* has the preallocblocks tag set */ #define XFS_NEED_INACTIVE (1 << 10) /* see XFS_INACTIVATING below */ /* * If this unlinked inode is in the middle of recovery, don't let drop_inode * truncate and free the inode. This can happen if we iget the inode during * log recovery to replay a bmap operation on the inode. */ #define XFS_IRECOVERY (1 << 11) #define XFS_ICOWBLOCKS (1 << 12)/* has the cowblocks tag set */ /* * If we need to update on-disk metadata before this IRECLAIMABLE inode can be * freed, then NEED_INACTIVE will be set. Once we start the updates, the * INACTIVATING bit will be set to keep iget away from this inode. After the * inactivation completes, both flags will be cleared and the inode is a * plain old IRECLAIMABLE inode. */ #define XFS_INACTIVATING (1 << 13) /* Quotacheck is running but inode has not been added to quota counts. */ #define XFS_IQUOTAUNCHECKED (1 << 14) /* * Remap in progress. Callers that wish to update file data while * holding a shared IOLOCK or MMAPLOCK must drop the lock and retake * the lock in exclusive mode. Relocking the file will block until * IREMAPPING is cleared. */ #define XFS_IREMAPPING (1U << 15) /* All inode state flags related to inode reclaim. */ #define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \ XFS_IRECLAIM | \ XFS_NEED_INACTIVE | \ XFS_INACTIVATING) /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during * inode lookup. This prevents unintended behaviour on the new inode from * ocurring. */ #define XFS_IRECLAIM_RESET_FLAGS \ (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | XFS_NEED_INACTIVE | \ XFS_INACTIVATING | XFS_IQUOTAUNCHECKED) /* * Flags for inode locking. * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield) * 1<<16 - 1<<32-1 -- lockdep annotation (integers) */ #define XFS_IOLOCK_EXCL (1u << 0) #define XFS_IOLOCK_SHARED (1u << 1) #define XFS_ILOCK_EXCL (1u << 2) #define XFS_ILOCK_SHARED (1u << 3) #define XFS_MMAPLOCK_EXCL (1u << 4) #define XFS_MMAPLOCK_SHARED (1u << 5) #define XFS_LOCK_MASK (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \ | XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \ | XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED) #define XFS_LOCK_FLAGS \ { XFS_IOLOCK_EXCL, "IOLOCK_EXCL" }, \ { XFS_IOLOCK_SHARED, "IOLOCK_SHARED" }, \ { XFS_ILOCK_EXCL, "ILOCK_EXCL" }, \ { XFS_ILOCK_SHARED, "ILOCK_SHARED" }, \ { XFS_MMAPLOCK_EXCL, "MMAPLOCK_EXCL" }, \ { XFS_MMAPLOCK_SHARED, "MMAPLOCK_SHARED" } /* * Flags for lockdep annotations. * * XFS_LOCK_PARENT - for directory operations that require locking a * parent directory inode and a child entry inode. IOLOCK requires nesting, * MMAPLOCK does not support this class, ILOCK requires a single subclass * to differentiate parent from child. * * XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary * inodes do not participate in the normal lock order, and thus have their * own subclasses. * * XFS_LOCK_INUMORDER - for locking several inodes at the some time * with xfs_lock_inodes(). This flag is used as the starting subclass * and each subsequent lock acquired will increment the subclass by one. * However, MAX_LOCKDEP_SUBCLASSES == 8, which means we are greatly * limited to the subclasses we can represent via nesting. We need at least * 5 inodes nest depth for the ILOCK through rename, and we also have to support * XFS_ILOCK_PARENT, which gives 6 subclasses. Then we have XFS_ILOCK_RTBITMAP * and XFS_ILOCK_RTSUM, which are another 2 unique subclasses, so that's all * 8 subclasses supported by lockdep. * * This also means we have to number the sub-classes in the lowest bits of * the mask we keep, and we have to ensure we never exceed 3 bits of lockdep * mask and we can't use bit-masking to build the subclasses. What a mess. * * Bit layout: * * Bit Lock Region * 16-19 XFS_IOLOCK_SHIFT dependencies * 20-23 XFS_MMAPLOCK_SHIFT dependencies * 24-31 XFS_ILOCK_SHIFT dependencies * * IOLOCK values * * 0-3 subclass value * 4-7 unused * * MMAPLOCK values * * 0-3 subclass value * 4-7 unused * * ILOCK values * 0-4 subclass values * 5 PARENT subclass (not nestable) * 6 RTBITMAP subclass (not nestable) * 7 RTSUM subclass (not nestable) * */ #define XFS_IOLOCK_SHIFT 16 #define XFS_IOLOCK_MAX_SUBCLASS 3 #define XFS_IOLOCK_DEP_MASK 0x000f0000u #define XFS_MMAPLOCK_SHIFT 20 #define XFS_MMAPLOCK_NUMORDER 0 #define XFS_MMAPLOCK_MAX_SUBCLASS 3 #define XFS_MMAPLOCK_DEP_MASK 0x00f00000u #define XFS_ILOCK_SHIFT 24 #define XFS_ILOCK_PARENT_VAL 5u #define XFS_ILOCK_MAX_SUBCLASS (XFS_ILOCK_PARENT_VAL - 1) #define XFS_ILOCK_RTBITMAP_VAL 6u #define XFS_ILOCK_RTSUM_VAL 7u #define XFS_ILOCK_DEP_MASK 0xff000000u #define XFS_ILOCK_PARENT (XFS_ILOCK_PARENT_VAL << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTBITMAP (XFS_ILOCK_RTBITMAP_VAL << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTSUM (XFS_ILOCK_RTSUM_VAL << XFS_ILOCK_SHIFT) #define XFS_LOCK_SUBCLASS_MASK (XFS_IOLOCK_DEP_MASK | \ XFS_MMAPLOCK_DEP_MASK | \ XFS_ILOCK_DEP_MASK) #define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) \ >> XFS_IOLOCK_SHIFT) #define XFS_MMAPLOCK_DEP(flags) (((flags) & XFS_MMAPLOCK_DEP_MASK) \ >> XFS_MMAPLOCK_SHIFT) #define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) \ >> XFS_ILOCK_SHIFT) /* * Layouts are broken in the BREAK_WRITE case to ensure that * layout-holders do not collide with local writes. Additionally, * layouts are broken in the BREAK_UNMAP case to make sure the * layout-holder has a consistent view of the file's extent map. While * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases, * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to * go idle. */ enum layout_break_reason { BREAK_WRITE, BREAK_UNMAP, }; /* * For multiple groups support: if S_ISGID bit is set in the parent * directory, group of new file is set to that of the parent, and * new subdirectory gets S_ISGID bit from parent. */ #define XFS_INHERIT_GID(pip) \ (xfs_has_grpid((pip)->i_mount) || (VFS_I(pip)->i_mode & S_ISGID)) int xfs_release(struct xfs_inode *ip); int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, const struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(struct mnt_idmap *idmap, struct xfs_inode *dp, struct xfs_name *name, umode_t mode, dev_t rdev, bool need_xattr, struct xfs_inode **ipp); int xfs_create_tmpfile(struct mnt_idmap *idmap, struct xfs_inode *dp, umode_t mode, bool init_xattrs, struct xfs_inode **ipp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name); int xfs_rename(struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, struct xfs_inode *target_ip, unsigned int flags); void xfs_ilock(xfs_inode_t *, uint); int xfs_ilock_nowait(xfs_inode_t *, uint); void xfs_iunlock(xfs_inode_t *, uint); void xfs_ilock_demote(xfs_inode_t *, uint); void xfs_assert_ilocked(struct xfs_inode *, uint); uint xfs_ilock_data_map_shared(struct xfs_inode *); uint xfs_ilock_attr_map_shared(struct xfs_inode *); uint xfs_ip2xflags(struct xfs_inode *); int xfs_ifree(struct xfs_trans *, struct xfs_inode *); int xfs_itruncate_extents_flags(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t, int); void xfs_iext_realloc(xfs_inode_t *, int, int); int xfs_log_force_inode(struct xfs_inode *ip); void xfs_iunpin_wait(xfs_inode_t *); #define xfs_ipincount(ip) ((unsigned int) atomic_read(&ip->i_pincount)) int xfs_iflush_cluster(struct xfs_buf *); void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode, struct xfs_inode *ip1, uint ip1_mode); xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); int xfs_init_new_inode(struct mnt_idmap *idmap, struct xfs_trans *tp, struct xfs_inode *pip, xfs_ino_t ino, umode_t mode, xfs_nlink_t nlink, dev_t rdev, prid_t prid, bool init_xattrs, struct xfs_inode **ipp); static inline int xfs_itruncate_extents( struct xfs_trans **tpp, struct xfs_inode *ip, int whichfork, xfs_fsize_t new_size) { return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0); } int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); static inline void xfs_update_stable_writes(struct xfs_inode *ip) { if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev)) mapping_set_stable_writes(VFS_I(ip)->i_mapping); else mapping_clear_stable_writes(VFS_I(ip)->i_mapping); } /* * When setting up a newly allocated inode, we need to call * xfs_finish_inode_setup() once the inode is fully instantiated at * the VFS level to prevent the rest of the world seeing the inode * before we've completed instantiation. Otherwise we can do it * the moment the inode lookup is complete. */ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) { xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip) { xfs_setup_inode(ip); xfs_setup_iops(ip); xfs_finish_inode_setup(ip); } void xfs_irele(struct xfs_inode *ip); extern struct kmem_cache *xfs_inode_cache; /* The default CoW extent size hint. */ #define XFS_DEFAULT_COWEXTSZ_HINT 32 bool xfs_inode_needs_inactive(struct xfs_inode *ip); int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip); int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag, struct xfs_inode *ip); struct xfs_inode *xfs_iunlink_lookup(struct xfs_perag *pag, xfs_agino_t agino); void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_remapping(struct xfs_inode *ip1, struct xfs_inode *ip2); int xfs_droplink(struct xfs_trans *tp, struct xfs_inode *ip); void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip); void xfs_lock_inodes(struct xfs_inode **ips, int inodes, uint lock_mode); void xfs_sort_inodes(struct xfs_inode **i_tab, unsigned int num_inodes); static inline bool xfs_inode_unlinked_incomplete( struct xfs_inode *ip) { return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip); } int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); int xfs_inode_reload_unlinked(struct xfs_inode *ip); bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork); void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, xfs_filblks_t *dblocks, xfs_filblks_t *rblocks); unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip); struct xfs_dir_update_params { const struct xfs_inode *dp; const struct xfs_inode *ip; const struct xfs_name *name; int delta; }; #ifdef CONFIG_XFS_LIVE_HOOKS void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip, int delta, const struct xfs_name *name); struct xfs_dir_hook { struct xfs_hook dirent_hook; }; void xfs_dir_hook_disable(void); void xfs_dir_hook_enable(void); int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook); void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook); void xfs_dir_hook_setup(struct xfs_dir_hook *hook, notifier_fn_t mod_fn); #else # define xfs_dir_update_hook(dp, ip, delta, name) ((void)0) #endif /* CONFIG_XFS_LIVE_HOOKS */ #endif /* __XFS_INODE_H__ */ |
| 2 1 4 3 4 2 2 9 3 2 2 3 4 3 4 2 3 2 30 19 4 8 22 5 25 2 22 5 23 5 13 16 4 6 3 4 16 8 12 3 9 7 3 4 1 1 1 1 11 3 5 3 3 1 1 1 1 3 5 1 1 1 1 1 1 1 15 16 1 15 29 29 29 27 1 1 1 1 23 22 22 4 15 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <net/genetlink.h> #include <net/gro.h> #include <net/gue.h> #include <net/fou.h> #include <net/ip.h> #include <net/protocol.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <uapi/linux/fou.h> #include <uapi/linux/genetlink.h> #include "fou_nl.h" struct fou { struct socket *sock; u8 protocol; u8 flags; __be16 port; u8 family; u16 type; struct list_head list; struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) struct fou_cfg { u16 type; u8 protocol; u8 flags; struct udp_port_cfg udp_config; }; static unsigned int fou_net_id; struct fou_net { struct list_head fou_list; struct mutex fou_lock; }; static inline struct fou *fou_from_sock(struct sock *sk) { return sk->sk_user_data; } static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len) { /* Remove 'len' bytes from the packet (UDP header and * FOU header if present). */ if (fou->family == AF_INET) ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len); else ipv6_hdr(skb)->payload_len = htons(ntohs(ipv6_hdr(skb)->payload_len) - len); __skb_pull(skb, len); skb_postpull_rcsum(skb, udp_hdr(skb), len); skb_reset_transport_header(skb); return iptunnel_pull_offloads(skb); } static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); if (!fou) return 1; if (fou_recv_pull(skb, fou, sizeof(struct udphdr))) goto drop; return -fou->protocol; drop: kfree_skb(skb); return 0; } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, void *data, size_t hdrlen, u8 ipproto, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); size_t plen = sizeof(struct udphdr) + hdrlen + max_t(size_t, offset + sizeof(u16), start); if (skb->remcsum_offload) return guehdr; if (!pskb_may_pull(skb, plen)) return NULL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset, nopartial); return guehdr; } static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr) { /* No support yet */ kfree_skb(skb); return 0; } static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); size_t len, optlen, hdrlen; struct guehdr *guehdr; void *data; u16 doffset = 0; u8 proto_ctype; if (!fou) return 1; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (!pskb_may_pull(skb, len)) goto drop; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; switch (guehdr->version) { case 0: /* Full GUE header present */ break; case 1: { /* Direct encapsulation of IPv4 or IPv6 */ int prot; switch (((struct iphdr *)guehdr)->version) { case 4: prot = IPPROTO_IPIP; break; case 6: prot = IPPROTO_IPV6; break; default: goto drop; } if (fou_recv_pull(skb, fou, sizeof(struct udphdr))) goto drop; return -prot; } default: /* Undefined version */ goto drop; } optlen = guehdr->hlen << 2; len += optlen; if (!pskb_may_pull(skb, len)) goto drop; /* guehdr may change after pull */ guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) goto drop; hdrlen = sizeof(struct guehdr) + optlen; if (fou->family == AF_INET) ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len); else ipv6_hdr(skb)->payload_len = htons(ntohs(ipv6_hdr(skb)->payload_len) - len); /* Pull csum through the guehdr now . This can be used if * there is a remote checksum offload. */ skb_postpull_rcsum(skb, udp_hdr(skb), len); data = &guehdr[1]; if (guehdr->flags & GUE_FLAG_PRIV) { __be32 flags = *(__be32 *)(data + doffset); doffset += GUE_LEN_PRIV; if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_remcsum(skb, guehdr, data + doffset, hdrlen, guehdr->proto_ctype, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto drop; data = &guehdr[1]; doffset += GUE_PLEN_REMCSUM; } } if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; return -proto_ctype; drop: kfree_skb(skb); return 0; } static struct sk_buff *fou_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct net_offload __rcu **offloads; u8 proto = fou_from_sock(sk)->protocol; const struct net_offload *ops; struct sk_buff *pp = NULL; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out: return pp; } static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { const struct net_offload __rcu **offloads; u8 proto = fou_from_sock(sk)->protocol; const struct net_offload *ops; int err = -ENOSYS; offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; err = ops->callbacks.gro_complete(skb, nhoff); skb_set_inner_mac_header(skb, nhoff); out: return err; } static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, size_t hdrlen, struct gro_remcsum *grc, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); if (skb->remcsum_offload) return guehdr; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return guehdr; } static struct sk_buff *gue_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct net_offload __rcu **offloads; const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; struct guehdr *guehdr; size_t len, optlen, hdrlen, off; void *data; u16 doffset = 0; int flush = 1; struct fou *fou = fou_from_sock(sk); struct gro_remcsum grc; u8 proto; skb_gro_remcsum_init(&grc); off = skb_gro_offset(skb); len = off + sizeof(*guehdr); guehdr = skb_gro_header(skb, len, off); if (unlikely(!guehdr)) goto out; switch (guehdr->version) { case 0: break; case 1: switch (((struct iphdr *)guehdr)->version) { case 4: proto = IPPROTO_IPIP; break; case 6: proto = IPPROTO_IPV6; break; default: goto out; } goto next_proto; default: goto out; } optlen = guehdr->hlen << 2; len += optlen; if (!skb_gro_may_pull(skb, len)) { guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; } if (unlikely(guehdr->control) || guehdr->version != 0 || validate_gue_flags(guehdr, optlen)) goto out; hdrlen = sizeof(*guehdr) + optlen; /* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr, * this is needed if there is a remote checkcsum offload. */ skb_gro_postpull_rcsum(skb, guehdr, hdrlen); data = &guehdr[1]; if (guehdr->flags & GUE_FLAG_PRIV) { __be32 flags = *(__be32 *)(data + doffset); doffset += GUE_LEN_PRIV; if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, data + doffset, hdrlen, &grc, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto out; data = &guehdr[1]; doffset += GUE_PLEN_REMCSUM; } } skb_gro_pull(skb, hdrlen); list_for_each_entry(p, head, list) { const struct guehdr *guehdr2; if (!NAPI_GRO_CB(p)->same_flow) continue; guehdr2 = (struct guehdr *)(p->data + off); /* Compare base GUE header to be equal (covers * hlen, version, proto_ctype, and flags. */ if (guehdr->word != guehdr2->word) { NAPI_GRO_CB(p)->same_flow = 0; continue; } /* Compare optional fields are the same. */ if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1], guehdr->hlen << 2)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } proto = guehdr->proto_ctype; next_proto: /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); const struct net_offload __rcu **offloads; const struct net_offload *ops; unsigned int guehlen = 0; u8 proto; int err = -ENOENT; switch (guehdr->version) { case 0: proto = guehdr->proto_ctype; guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); break; case 1: switch (((struct iphdr *)guehdr)->version) { case 4: proto = IPPROTO_IPIP; break; case 6: proto = IPPROTO_IPV6; break; default: return err; } break; default: return err; } offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; err = ops->callbacks.gro_complete(skb, nhoff + guehlen); skb_set_inner_mac_header(skb, nhoff + guehlen); out: return err; } static bool fou_cfg_cmp(struct fou *fou, struct fou_cfg *cfg) { struct sock *sk = fou->sock->sk; struct udp_port_cfg *udp_cfg = &cfg->udp_config; if (fou->family != udp_cfg->family || fou->port != udp_cfg->local_udp_port || sk->sk_dport != udp_cfg->peer_udp_port || sk->sk_bound_dev_if != udp_cfg->bind_ifindex) return false; if (fou->family == AF_INET) { if (sk->sk_rcv_saddr != udp_cfg->local_ip.s_addr || sk->sk_daddr != udp_cfg->peer_ip.s_addr) return false; else return true; #if IS_ENABLED(CONFIG_IPV6) } else { if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, &udp_cfg->local_ip6) || ipv6_addr_cmp(&sk->sk_v6_daddr, &udp_cfg->peer_ip6)) return false; else return true; #endif } return false; } static int fou_add_to_port_list(struct net *net, struct fou *fou, struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (fou_cfg_cmp(fout, cfg)) { mutex_unlock(&fn->fou_lock); return -EALREADY; } } list_add(&fou->list, &fn->fou_list); mutex_unlock(&fn->fou_lock); return 0; } static void fou_release(struct fou *fou) { struct socket *sock = fou->sock; list_del(&fou->list); udp_tunnel_sock_release(sock); kfree_rcu(fou, rcu); } static int fou_create(struct net *net, struct fou_cfg *cfg, struct socket **sockp) { struct socket *sock = NULL; struct fou *fou = NULL; struct sock *sk; struct udp_tunnel_sock_cfg tunnel_cfg; int err; /* Open UDP socket */ err = udp_sock_create(net, &cfg->udp_config, &sock); if (err < 0) goto error; /* Allocate FOU port structure */ fou = kzalloc(sizeof(*fou), GFP_KERNEL); if (!fou) { err = -ENOMEM; goto error; } sk = sock->sk; fou->port = cfg->udp_config.local_udp_port; fou->family = cfg->udp_config.family; fou->flags = cfg->flags; fou->type = cfg->type; fou->sock = sock; memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.encap_type = 1; tunnel_cfg.sk_user_data = fou; tunnel_cfg.encap_destroy = NULL; /* Initial for fou type */ switch (cfg->type) { case FOU_ENCAP_DIRECT: tunnel_cfg.encap_rcv = fou_udp_recv; tunnel_cfg.gro_receive = fou_gro_receive; tunnel_cfg.gro_complete = fou_gro_complete; fou->protocol = cfg->protocol; break; case FOU_ENCAP_GUE: tunnel_cfg.encap_rcv = gue_udp_recv; tunnel_cfg.gro_receive = gue_gro_receive; tunnel_cfg.gro_complete = gue_gro_complete; break; default: err = -EINVAL; goto error; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); sk->sk_allocation = GFP_ATOMIC; err = fou_add_to_port_list(net, fou, cfg); if (err) goto error; if (sockp) *sockp = sock; return 0; error: kfree(fou); if (sock) udp_tunnel_sock_release(sock); return err; } static int fou_destroy(struct net *net, struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); int err = -EINVAL; struct fou *fou; mutex_lock(&fn->fou_lock); list_for_each_entry(fou, &fn->fou_list, list) { if (fou_cfg_cmp(fou, cfg)) { fou_release(fou); err = 0; break; } } mutex_unlock(&fn->fou_lock); return err; } static struct genl_family fou_nl_family; static int parse_nl_config(struct genl_info *info, struct fou_cfg *cfg) { bool has_local = false, has_peer = false; struct nlattr *attr; int ifindex; __be16 port; memset(cfg, 0, sizeof(*cfg)); cfg->udp_config.family = AF_INET; if (info->attrs[FOU_ATTR_AF]) { u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]); switch (family) { case AF_INET: break; case AF_INET6: cfg->udp_config.ipv6_v6only = 1; break; default: return -EAFNOSUPPORT; } cfg->udp_config.family = family; } if (info->attrs[FOU_ATTR_PORT]) { port = nla_get_be16(info->attrs[FOU_ATTR_PORT]); cfg->udp_config.local_udp_port = port; } if (info->attrs[FOU_ATTR_IPPROTO]) cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]); if (info->attrs[FOU_ATTR_TYPE]) cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]); if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL]) cfg->flags |= FOU_F_REMCSUM_NOPARTIAL; if (cfg->udp_config.family == AF_INET) { if (info->attrs[FOU_ATTR_LOCAL_V4]) { attr = info->attrs[FOU_ATTR_LOCAL_V4]; cfg->udp_config.local_ip.s_addr = nla_get_in_addr(attr); has_local = true; } if (info->attrs[FOU_ATTR_PEER_V4]) { attr = info->attrs[FOU_ATTR_PEER_V4]; cfg->udp_config.peer_ip.s_addr = nla_get_in_addr(attr); has_peer = true; } #if IS_ENABLED(CONFIG_IPV6) } else { if (info->attrs[FOU_ATTR_LOCAL_V6]) { attr = info->attrs[FOU_ATTR_LOCAL_V6]; cfg->udp_config.local_ip6 = nla_get_in6_addr(attr); has_local = true; } if (info->attrs[FOU_ATTR_PEER_V6]) { attr = info->attrs[FOU_ATTR_PEER_V6]; cfg->udp_config.peer_ip6 = nla_get_in6_addr(attr); has_peer = true; } #endif } if (has_peer) { if (info->attrs[FOU_ATTR_PEER_PORT]) { port = nla_get_be16(info->attrs[FOU_ATTR_PEER_PORT]); cfg->udp_config.peer_udp_port = port; } else { return -EINVAL; } } if (info->attrs[FOU_ATTR_IFINDEX]) { if (!has_local) return -EINVAL; ifindex = nla_get_s32(info->attrs[FOU_ATTR_IFINDEX]); cfg->udp_config.bind_ifindex = ifindex; } return 0; } int fou_nl_add_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_cfg cfg; int err; err = parse_nl_config(info, &cfg); if (err) return err; return fou_create(net, &cfg, NULL); } int fou_nl_del_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_cfg cfg; int err; err = parse_nl_config(info, &cfg); if (err) return err; return fou_destroy(net, &cfg); } static int fou_fill_info(struct fou *fou, struct sk_buff *msg) { struct sock *sk = fou->sock->sk; if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) || nla_put_be16(msg, FOU_ATTR_PORT, fou->port) || nla_put_be16(msg, FOU_ATTR_PEER_PORT, sk->sk_dport) || nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) || nla_put_u8(msg, FOU_ATTR_TYPE, fou->type) || nla_put_s32(msg, FOU_ATTR_IFINDEX, sk->sk_bound_dev_if)) return -1; if (fou->flags & FOU_F_REMCSUM_NOPARTIAL) if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL)) return -1; if (fou->sock->sk->sk_family == AF_INET) { if (nla_put_in_addr(msg, FOU_ATTR_LOCAL_V4, sk->sk_rcv_saddr)) return -1; if (nla_put_in_addr(msg, FOU_ATTR_PEER_V4, sk->sk_daddr)) return -1; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(msg, FOU_ATTR_LOCAL_V6, &sk->sk_v6_rcv_saddr)) return -1; if (nla_put_in6_addr(msg, FOU_ATTR_PEER_V6, &sk->sk_v6_daddr)) return -1; #endif } return 0; } static int fou_dump_info(struct fou *fou, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &fou_nl_family, flags, cmd); if (!hdr) return -ENOMEM; if (fou_fill_info(fou, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int fou_nl_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_net *fn = net_generic(net, fou_net_id); struct sk_buff *msg; struct fou_cfg cfg; struct fou *fout; __be16 port; u8 family; int ret; ret = parse_nl_config(info, &cfg); if (ret) return ret; port = cfg.udp_config.local_udp_port; if (port == 0) return -EINVAL; family = cfg.udp_config.family; if (family != AF_INET && family != AF_INET6) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = -ESRCH; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (fou_cfg_cmp(fout, &cfg)) { ret = fou_dump_info(fout, info->snd_portid, info->snd_seq, 0, msg, info->genlhdr->cmd); break; } } mutex_unlock(&fn->fou_lock); if (ret < 0) goto out_free; return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); return ret; } int fou_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; int idx = 0, ret; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (idx++ < cb->args[0]) continue; ret = fou_dump_info(fout, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, FOU_CMD_GET); if (ret) break; } mutex_unlock(&fn->fou_lock); cb->args[0] = idx; return skb->len; } static struct genl_family fou_nl_family __ro_after_init = { .hdrsize = 0, .name = FOU_GENL_NAME, .version = FOU_GENL_VERSION, .maxattr = FOU_ATTR_MAX, .policy = fou_nl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = fou_nl_ops, .n_small_ops = ARRAY_SIZE(fou_nl_ops), .resv_start_op = FOU_CMD_GET + 1, }; size_t fou_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct udphdr); } EXPORT_SYMBOL(fou_encap_hlen); size_t gue_encap_hlen(struct ip_tunnel_encap *e) { size_t len; bool need_priv = false; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) { len += GUE_PLEN_REMCSUM; need_priv = true; } len += need_priv ? GUE_LEN_PRIV : 0; return len; } EXPORT_SYMBOL(gue_encap_hlen); int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { int err; err = iptunnel_handle_offloads(skb, type); if (err) return err; *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), skb, 0, 0, false); return 0; } EXPORT_SYMBOL(__fou_build_header); int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { struct guehdr *guehdr; size_t hdrlen, optlen = 0; void *data; bool need_priv = false; int err; if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) && skb->ip_summed == CHECKSUM_PARTIAL) { optlen += GUE_PLEN_REMCSUM; type |= SKB_GSO_TUNNEL_REMCSUM; need_priv = true; } optlen += need_priv ? GUE_LEN_PRIV : 0; err = iptunnel_handle_offloads(skb, type); if (err) return err; /* Get source port (based on flow hash) before skb_push */ *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), skb, 0, 0, false); hdrlen = sizeof(struct guehdr) + optlen; skb_push(skb, hdrlen); guehdr = (struct guehdr *)skb->data; guehdr->control = 0; guehdr->version = 0; guehdr->hlen = optlen >> 2; guehdr->flags = 0; guehdr->proto_ctype = *protocol; data = &guehdr[1]; if (need_priv) { __be32 *flags = data; guehdr->flags |= GUE_FLAG_PRIV; *flags = 0; data += GUE_LEN_PRIV; if (type & SKB_GSO_TUNNEL_REMCSUM) { u16 csum_start = skb_checksum_start_offset(skb); __be16 *pd = data; if (csum_start < hdrlen) return -EINVAL; csum_start -= hdrlen; pd[0] = htons(csum_start); pd[1] = htons(csum_start + skb->csum_offset); if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } *flags |= GUE_PFLAG_REMCSUM; data += GUE_PLEN_REMCSUM; } } return 0; } EXPORT_SYMBOL(__gue_build_header); #ifdef CONFIG_NET_FOU_IP_TUNNELS static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, struct flowi4 *fl4, u8 *protocol, __be16 sport) { struct udphdr *uh; skb_push(skb, sizeof(struct udphdr)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = e->dport; uh->source = sport; uh->len = htons(skb->len); udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, fl4->saddr, fl4->daddr, skb->len); *protocol = IPPROTO_UDP; } static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 sport; int err; err = __fou_build_header(skb, e, protocol, &sport, type); if (err) return err; fou_build_udp(skb, e, fl4, protocol, sport); return 0; } static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 sport; int err; err = __gue_build_header(skb, e, protocol, &sport, type); if (err) return err; fou_build_udp(skb, e, fl4, protocol, sport); return 0; } static int gue_err_proto_handler(int proto, struct sk_buff *skb, u32 info) { const struct net_protocol *ipprot = rcu_dereference(inet_protos[proto]); if (ipprot && ipprot->err_handler) { if (!ipprot->err_handler(skb, info)) return 0; } return -ENOENT; } static int gue_err(struct sk_buff *skb, u32 info) { int transport_offset = skb_transport_offset(skb); struct guehdr *guehdr; size_t len, optlen; int ret; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (!pskb_may_pull(skb, transport_offset + len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; switch (guehdr->version) { case 0: /* Full GUE header present */ break; case 1: { /* Direct encapsulation of IPv4 or IPv6 */ skb_set_transport_header(skb, -(int)sizeof(struct icmphdr)); switch (((struct iphdr *)guehdr)->version) { case 4: ret = gue_err_proto_handler(IPPROTO_IPIP, skb, info); goto out; #if IS_ENABLED(CONFIG_IPV6) case 6: ret = gue_err_proto_handler(IPPROTO_IPV6, skb, info); goto out; #endif default: ret = -EOPNOTSUPP; goto out; } } default: /* Undefined version */ return -EOPNOTSUPP; } if (guehdr->control) return -ENOENT; optlen = guehdr->hlen << 2; if (!pskb_may_pull(skb, transport_offset + len + optlen)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) return -EINVAL; /* Handling exceptions for direct UDP encapsulation in GUE would lead to * recursion. Besides, this kind of encapsulation can't even be * configured currently. Discard this. */ if (guehdr->proto_ctype == IPPROTO_UDP || guehdr->proto_ctype == IPPROTO_UDPLITE) return -EOPNOTSUPP; skb_set_transport_header(skb, -(int)sizeof(struct icmphdr)); ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info); out: skb_set_transport_header(skb, transport_offset); return ret; } static const struct ip_tunnel_encap_ops fou_iptun_ops = { .encap_hlen = fou_encap_hlen, .build_header = fou_build_header, .err_handler = gue_err, }; static const struct ip_tunnel_encap_ops gue_iptun_ops = { .encap_hlen = gue_encap_hlen, .build_header = gue_build_header, .err_handler = gue_err, }; static int ip_tunnel_encap_add_fou_ops(void) { int ret; ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); if (ret < 0) { pr_err("can't add fou ops\n"); return ret; } ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); if (ret < 0) { pr_err("can't add gue ops\n"); ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); return ret; } return 0; } static void ip_tunnel_encap_del_fou_ops(void) { ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); } #else static int ip_tunnel_encap_add_fou_ops(void) { return 0; } static void ip_tunnel_encap_del_fou_ops(void) { } #endif static __net_init int fou_init_net(struct net *net) { struct fou_net *fn = net_generic(net, fou_net_id); INIT_LIST_HEAD(&fn->fou_list); mutex_init(&fn->fou_lock); return 0; } static __net_exit void fou_exit_net(struct net *net) { struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fou, *next; /* Close all the FOU sockets */ mutex_lock(&fn->fou_lock); list_for_each_entry_safe(fou, next, &fn->fou_list, list) fou_release(fou); mutex_unlock(&fn->fou_lock); } static struct pernet_operations fou_net_ops = { .init = fou_init_net, .exit = fou_exit_net, .id = &fou_net_id, .size = sizeof(struct fou_net), }; static int __init fou_init(void) { int ret; ret = register_pernet_device(&fou_net_ops); if (ret) goto exit; ret = genl_register_family(&fou_nl_family); if (ret < 0) goto unregister; ret = register_fou_bpf(); if (ret < 0) goto kfunc_failed; ret = ip_tunnel_encap_add_fou_ops(); if (ret == 0) return 0; kfunc_failed: genl_unregister_family(&fou_nl_family); unregister: unregister_pernet_device(&fou_net_ops); exit: return ret; } static void __exit fou_fini(void) { ip_tunnel_encap_del_fou_ops(); genl_unregister_family(&fou_nl_family); unregister_pernet_device(&fou_net_ops); } module_init(fou_init); module_exit(fou_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Foo over UDP"); |
| 44 44 44 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* mpihelp-add_1.c - MPI helper functions * Copyright (C) 1994, 1996, 1997, 1998, * 2000 Free Software Foundation, Inc. * * This file is part of GnuPG. * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. * The GNU MP Library itself is published under the LGPL; * however I decided to publish this code under the plain GPL. */ #include "mpi-internal.h" #include "longlong.h" mpi_limb_t mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_ptr_t s2_ptr, mpi_size_t size) { mpi_limb_t x, y, cy; mpi_size_t j; /* The loop counter and index J goes from -SIZE to -1. This way the loop becomes faster. */ j = -size; /* Offset the base pointers to compensate for the negative indices. */ s1_ptr -= j; s2_ptr -= j; res_ptr -= j; cy = 0; do { y = s2_ptr[j]; x = s1_ptr[j]; y += cy; /* add previous carry to one addend */ cy = y < cy; /* get out carry from that addition */ y += x; /* add other addend */ cy += y < x; /* get out carry from that add, combine */ res_ptr[j] = y; } while (++j); return cy; } |
| 4 24 19 1 1 1 1 1 3 3 95 96 2 95 1 1 93 94 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "journal_sb.h" #include "darray.h" #include <linux/sort.h> /* BCH_SB_FIELD_journal: */ static int u64_cmp(const void *_l, const void *_r) { const u64 *l = _l; const u64 *r = _r; return cmp_int(*l, *r); } static int bch2_sb_journal_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_journal *journal = field_to_type(f, journal); struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx); int ret = -BCH_ERR_invalid_sb_journal; unsigned nr; unsigned i; u64 *b; nr = bch2_nr_journal_buckets(journal); if (!nr) return 0; b = kmalloc_array(nr, sizeof(u64), GFP_KERNEL); if (!b) return -BCH_ERR_ENOMEM_sb_journal_validate; for (i = 0; i < nr; i++) b[i] = le64_to_cpu(journal->buckets[i]); sort(b, nr, sizeof(u64), u64_cmp, NULL); if (!b[0]) { prt_printf(err, "journal bucket at sector 0"); goto err; } if (b[0] < le16_to_cpu(m.first_bucket)) { prt_printf(err, "journal bucket %llu before first bucket %u", b[0], le16_to_cpu(m.first_bucket)); goto err; } if (b[nr - 1] >= le64_to_cpu(m.nbuckets)) { prt_printf(err, "journal bucket %llu past end of device (nbuckets %llu)", b[nr - 1], le64_to_cpu(m.nbuckets)); goto err; } for (i = 0; i + 1 < nr; i++) if (b[i] == b[i + 1]) { prt_printf(err, "duplicate journal buckets %llu", b[i]); goto err; } ret = 0; err: kfree(b); return ret; } static void bch2_sb_journal_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_journal *journal = field_to_type(f, journal); unsigned i, nr = bch2_nr_journal_buckets(journal); prt_printf(out, "Buckets: "); for (i = 0; i < nr; i++) prt_printf(out, " %llu", le64_to_cpu(journal->buckets[i])); prt_newline(out); } const struct bch_sb_field_ops bch_sb_field_ops_journal = { .validate = bch2_sb_journal_validate, .to_text = bch2_sb_journal_to_text, }; struct u64_range { u64 start; u64 end; }; static int u64_range_cmp(const void *_l, const void *_r) { const struct u64_range *l = _l; const struct u64_range *r = _r; return cmp_int(l->start, r->start); } static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_journal_v2 *journal = field_to_type(f, journal_v2); struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx); int ret = -BCH_ERR_invalid_sb_journal; unsigned nr; unsigned i; struct u64_range *b; nr = bch2_sb_field_journal_v2_nr_entries(journal); if (!nr) return 0; b = kmalloc_array(nr, sizeof(*b), GFP_KERNEL); if (!b) return -BCH_ERR_ENOMEM_sb_journal_v2_validate; for (i = 0; i < nr; i++) { b[i].start = le64_to_cpu(journal->d[i].start); b[i].end = b[i].start + le64_to_cpu(journal->d[i].nr); } sort(b, nr, sizeof(*b), u64_range_cmp, NULL); if (!b[0].start) { prt_printf(err, "journal bucket at sector 0"); goto err; } if (b[0].start < le16_to_cpu(m.first_bucket)) { prt_printf(err, "journal bucket %llu before first bucket %u", b[0].start, le16_to_cpu(m.first_bucket)); goto err; } if (b[nr - 1].end > le64_to_cpu(m.nbuckets)) { prt_printf(err, "journal bucket %llu past end of device (nbuckets %llu)", b[nr - 1].end - 1, le64_to_cpu(m.nbuckets)); goto err; } for (i = 0; i + 1 < nr; i++) { if (b[i].end > b[i + 1].start) { prt_printf(err, "duplicate journal buckets in ranges %llu-%llu, %llu-%llu", b[i].start, b[i].end, b[i + 1].start, b[i + 1].end); goto err; } } ret = 0; err: kfree(b); return ret; } static void bch2_sb_journal_v2_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_journal_v2 *journal = field_to_type(f, journal_v2); unsigned i, nr = bch2_sb_field_journal_v2_nr_entries(journal); prt_printf(out, "Buckets: "); for (i = 0; i < nr; i++) prt_printf(out, " %llu-%llu", le64_to_cpu(journal->d[i].start), le64_to_cpu(journal->d[i].start) + le64_to_cpu(journal->d[i].nr)); prt_newline(out); } const struct bch_sb_field_ops bch_sb_field_ops_journal_v2 = { .validate = bch2_sb_journal_v2_validate, .to_text = bch2_sb_journal_v2_to_text, }; int bch2_journal_buckets_to_sb(struct bch_fs *c, struct bch_dev *ca, u64 *buckets, unsigned nr) { struct bch_sb_field_journal_v2 *j; unsigned i, dst = 0, nr_compacted = 1; if (c) lockdep_assert_held(&c->sb_lock); if (!nr) { bch2_sb_field_delete(&ca->disk_sb, BCH_SB_FIELD_journal); bch2_sb_field_delete(&ca->disk_sb, BCH_SB_FIELD_journal_v2); return 0; } for (i = 0; i + 1 < nr; i++) if (buckets[i] + 1 != buckets[i + 1]) nr_compacted++; j = bch2_sb_field_resize(&ca->disk_sb, journal_v2, (sizeof(*j) + sizeof(j->d[0]) * nr_compacted) / sizeof(u64)); if (!j) return -BCH_ERR_ENOSPC_sb_journal; bch2_sb_field_delete(&ca->disk_sb, BCH_SB_FIELD_journal); j->d[dst].start = cpu_to_le64(buckets[0]); j->d[dst].nr = cpu_to_le64(1); for (i = 1; i < nr; i++) { if (buckets[i] == buckets[i - 1] + 1) { le64_add_cpu(&j->d[dst].nr, 1); } else { dst++; j->d[dst].start = cpu_to_le64(buckets[i]); j->d[dst].nr = cpu_to_le64(1); } } BUG_ON(dst + 1 != nr_compacted); return 0; } |
| 123 13 101 101 47 47 115 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_BKEY_BUF_H #define _BCACHEFS_BKEY_BUF_H #include "bcachefs.h" #include "bkey.h" struct bkey_buf { struct bkey_i *k; u64 onstack[12]; }; static inline void bch2_bkey_buf_realloc(struct bkey_buf *s, struct bch_fs *c, unsigned u64s) { if (s->k == (void *) s->onstack && u64s > ARRAY_SIZE(s->onstack)) { s->k = mempool_alloc(&c->large_bkey_pool, GFP_NOFS); memcpy(s->k, s->onstack, sizeof(s->onstack)); } } static inline void bch2_bkey_buf_reassemble(struct bkey_buf *s, struct bch_fs *c, struct bkey_s_c k) { bch2_bkey_buf_realloc(s, c, k.k->u64s); bkey_reassemble(s->k, k); } static inline void bch2_bkey_buf_copy(struct bkey_buf *s, struct bch_fs *c, struct bkey_i *src) { bch2_bkey_buf_realloc(s, c, src->k.u64s); bkey_copy(s->k, src); } static inline void bch2_bkey_buf_unpack(struct bkey_buf *s, struct bch_fs *c, struct btree *b, struct bkey_packed *src) { bch2_bkey_buf_realloc(s, c, BKEY_U64s + bkeyp_val_u64s(&b->format, src)); bch2_bkey_unpack(b, s->k, src); } static inline void bch2_bkey_buf_init(struct bkey_buf *s) { s->k = (void *) s->onstack; } static inline void bch2_bkey_buf_exit(struct bkey_buf *s, struct bch_fs *c) { if (s->k != (void *) s->onstack) mempool_free(s->k, &c->large_bkey_pool); s->k = NULL; } #endif /* _BCACHEFS_BKEY_BUF_H */ |
| 398 146 3 66 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_SPACE_INFO_H #define BTRFS_SPACE_INFO_H #include <trace/events/btrfs.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/kobject.h> #include <linux/lockdep.h> #include <linux/wait.h> #include <linux/rwsem.h> #include "volumes.h" struct btrfs_fs_info; struct btrfs_block_group; /* * Different levels for to flush space when doing space reservations. * * The higher the level, the more methods we try to reclaim space. */ enum btrfs_reserve_flush_enum { /* If we are in the transaction, we can't flush anything.*/ BTRFS_RESERVE_NO_FLUSH, /* * Flush space by: * - Running delayed inode items * - Allocating a new chunk */ BTRFS_RESERVE_FLUSH_LIMIT, /* * Flush space by: * - Running delayed inode items * - Running delayed refs * - Running delalloc and waiting for ordered extents * - Allocating a new chunk * - Committing transaction */ BTRFS_RESERVE_FLUSH_EVICT, /* * Flush space by above mentioned methods and by: * - Running delayed iputs * - Committing transaction * * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_DATA, BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE, BTRFS_RESERVE_FLUSH_ALL, /* * Pretty much the same as FLUSH_ALL, but can also steal space from * global rsv. * * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_ALL_STEAL, /* * This is for btrfs_use_block_rsv only. We have exhausted our block * rsv and our global block rsv. This can happen for things like * delalloc where we are overwriting a lot of extents with a single * extent and didn't reserve enough space. Alternatively it can happen * with delalloc where we reserve 1 extents worth for a large extent but * fragmentation leads to multiple extents being created. This will * give us the reservation in the case of * * if (num_bytes < (space_info->total_bytes - * btrfs_space_info_used(space_info, false)) * * Which ignores bytes_may_use. This is potentially dangerous, but our * reservation system is generally pessimistic so is able to absorb this * style of mistake. */ BTRFS_RESERVE_FLUSH_EMERGENCY, }; enum btrfs_flush_state { FLUSH_DELAYED_ITEMS_NR = 1, FLUSH_DELAYED_ITEMS = 2, FLUSH_DELAYED_REFS_NR = 3, FLUSH_DELAYED_REFS = 4, FLUSH_DELALLOC = 5, FLUSH_DELALLOC_WAIT = 6, FLUSH_DELALLOC_FULL = 7, ALLOC_CHUNK = 8, ALLOC_CHUNK_FORCE = 9, RUN_DELAYED_IPUTS = 10, COMMIT_TRANS = 11, }; struct btrfs_space_info { spinlock_t lock; u64 total_bytes; /* total bytes in the space, this doesn't take mirrors into account */ u64 bytes_used; /* total bytes used, this doesn't take mirrors into account */ u64 bytes_pinned; /* total bytes pinned, will be freed when the transaction finishes */ u64 bytes_reserved; /* total bytes the allocator has reserved for current allocations */ u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ u64 bytes_zone_unusable; /* total bytes that are unusable until resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the allocator. */ /* Chunk size in bytes */ u64 chunk_size; /* * Once a block group drops below this threshold (percents) we'll * schedule it for reclaim. */ int bg_reclaim_threshold; int clamp; /* Used to scale our threshold for preemptive flushing. The value is >> clamp, so turns out to be a 2^clamp divisor. */ unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ unsigned int flush:1; /* set if we are trying to make space */ unsigned int force_alloc; /* set if we need to force a chunk alloc for this space */ u64 disk_used; /* total bytes used on disk */ u64 disk_total; /* total bytes on disk, takes mirrors into account */ u64 flags; struct list_head list; /* Protected by the spinlock 'lock'. */ struct list_head ro_bgs; struct list_head priority_tickets; struct list_head tickets; /* * Size of space that needs to be reclaimed in order to satisfy pending * tickets */ u64 reclaim_size; /* * tickets_id just indicates the next ticket will be handled, so note * it's not stored per ticket. */ u64 tickets_id; struct rw_semaphore groups_sem; /* for block groups in our same type */ struct list_head block_groups[BTRFS_NR_RAID_TYPES]; struct kobject kobj; struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES]; }; struct reserve_ticket { u64 bytes; int error; bool steal; struct list_head list; wait_queue_head_t wait; }; static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) { return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) && (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); } /* * * Declare a helper function to detect underflow of various space info members */ #define DECLARE_SPACE_INFO_UPDATE(name, trace_name) \ static inline void \ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ struct btrfs_space_info *sinfo, \ s64 bytes) \ { \ const u64 abs_bytes = (bytes < 0) ? -bytes : bytes; \ lockdep_assert_held(&sinfo->lock); \ trace_update_##name(fs_info, sinfo, sinfo->name, bytes); \ trace_btrfs_space_reservation(fs_info, trace_name, \ sinfo->flags, abs_bytes, \ bytes > 0); \ if (bytes < 0 && sinfo->name < -bytes) { \ WARN_ON(1); \ sinfo->name = 0; \ return; \ } \ sinfo->name += bytes; \ } DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info"); DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, struct btrfs_block_group *block_group); void btrfs_update_space_info_chunk_size(struct btrfs_space_info *space_info, u64 chunk_size); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *info, u64 bytes, int dump_block_groups); int btrfs_reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, enum btrfs_reserve_flush_enum flush); void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes) { spin_lock(&space_info->lock); btrfs_space_info_update_bytes_may_use(fs_info, space_info, -num_bytes); btrfs_try_granting_tickets(fs_info, space_info); spin_unlock(&space_info->lock); } int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush); void btrfs_dump_space_info_for_trans_abort(struct btrfs_fs_info *fs_info); void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); #endif /* BTRFS_SPACE_INFO_H */ |
| 4 112 200 171 359 398 700 125 40 112 40 186 126 101 181 51 161 109 33 77 57 389 83 365 353 160 118 113 53 33 347 58 57 150 96 6 33 31 206 206 221 169 14 46 23 14 37 37 197 197 7 2 486 221 486 221 292 216 807 4 7 81 59 427 71 113 1 117 113 675 434 508 218 218 895 895 4 3 3 5 4 3 37 14 14 11 24 24 11 6 382 44 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ext4 #if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EXT4_H #include <linux/writeback.h> #include <linux/tracepoint.h> struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_extent; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; struct ext4_map_blocks; struct extent_status; struct ext4_fsmap; struct partial_cluster; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \ { EXT4_MB_HINT_RESERVED, "HINT_RESV" }, \ { EXT4_MB_HINT_METADATA, "HINT_MDATA" }, \ { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \ { EXT4_MB_HINT_BEST, "HINT_BEST" }, \ { EXT4_MB_HINT_DATA, "HINT_DATA" }, \ { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \ { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \ { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \ { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \ { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \ { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \ { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \ { EXT4_MB_USE_RESERVED, "USE_RESV" }, \ { EXT4_MB_STRICT_CHECK, "STRICT_CHECK" }) #define show_map_flags(flags) __print_flags(flags, "|", \ { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \ { EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \ { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \ { EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \ { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ { EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, "CONVERT_UNWRITTEN" }, \ { EXT4_GET_BLOCKS_ZERO, "ZERO" }, \ { EXT4_GET_BLOCKS_IO_SUBMIT, "IO_SUBMIT" }, \ { EXT4_EX_NOCACHE, "EX_NOCACHE" }) /* * __print_flags() requires that all enum values be wrapped in the * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace * ring buffer. */ TRACE_DEFINE_ENUM(BH_New); TRACE_DEFINE_ENUM(BH_Mapped); TRACE_DEFINE_ENUM(BH_Unwritten); TRACE_DEFINE_ENUM(BH_Boundary); #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ { EXT4_MAP_MAPPED, "M" }, \ { EXT4_MAP_UNWRITTEN, "U" }, \ { EXT4_MAP_BOUNDARY, "B" }) #define show_free_flags(flags) __print_flags(flags, "|", \ { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \ { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \ { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \ { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \ { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\ { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" }) TRACE_DEFINE_ENUM(ES_WRITTEN_B); TRACE_DEFINE_ENUM(ES_UNWRITTEN_B); TRACE_DEFINE_ENUM(ES_DELAYED_B); TRACE_DEFINE_ENUM(ES_HOLE_B); TRACE_DEFINE_ENUM(ES_REFERENCED_B); #define show_extent_status(status) __print_flags(status, "", \ { EXTENT_STATUS_WRITTEN, "W" }, \ { EXTENT_STATUS_UNWRITTEN, "U" }, \ { EXTENT_STATUS_DELAYED, "D" }, \ { EXTENT_STATUS_HOLE, "H" }, \ { EXTENT_STATUS_REFERENCED, "R" }) #define show_falloc_mode(mode) __print_flags(mode, "|", \ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}, \ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_NOMEM); TRACE_DEFINE_ENUM(EXT4_FC_REASON_SWAP_BOOT); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA); TRACE_DEFINE_ENUM(EXT4_FC_REASON_ENCRYPTED_FILENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); #define show_fc_reason(reason) \ __print_symbolic(reason, \ { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}, \ { EXT4_FC_REASON_ENCRYPTED_FILENAME, "ENCRYPTED_FILENAME"}) TRACE_DEFINE_ENUM(CR_POWER2_ALIGNED); TRACE_DEFINE_ENUM(CR_GOAL_LEN_FAST); TRACE_DEFINE_ENUM(CR_BEST_AVAIL_LEN); TRACE_DEFINE_ENUM(CR_GOAL_LEN_SLOW); TRACE_DEFINE_ENUM(CR_ANY_FREE); #define show_criteria(cr) \ __print_symbolic(cr, \ { CR_POWER2_ALIGNED, "CR_POWER2_ALIGNED" }, \ { CR_GOAL_LEN_FAST, "CR_GOAL_LEN_FAST" }, \ { CR_BEST_AVAIL_LEN, "CR_BEST_AVAIL_LEN" }, \ { CR_GOAL_LEN_SLOW, "CR_GOAL_LEN_SLOW" }, \ { CR_ANY_FREE, "CR_ANY_FREE" }) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), TP_ARGS(inode, orig_ino), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, orig_ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u16, mode ) ), TP_fast_assign( __entry->orig_ino = orig_ino; __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d orig_ino %lu ino %lu mode 0%o uid %u gid %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->orig_ino, (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid) ); TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u64, blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, TP_PROTO(struct inode *dir, int mode), TP_ARGS(dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_allocate_inode, TP_PROTO(struct inode *inode, struct inode *dir, int mode), TP_ARGS(inode, dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_evict_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, nlink ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %lu nlink %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nlink) ); TRACE_EVENT(ext4_drop_inode, TP_PROTO(struct inode *inode, int drop), TP_ARGS(inode, drop), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, drop ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %lu drop %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->drop) ); TRACE_EVENT(ext4_nfs_commit_metadata, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(ext4_mark_inode_dirty, TP_PROTO(struct inode *inode, unsigned long IP), TP_ARGS(inode, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, ip ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %lu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_begin_ordered_truncate, TP_PROTO(struct inode *inode, loff_t new_size), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, new_size ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %lu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; ), TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) __field( unsigned int, copied ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; __entry->copied = copied; ), TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); TRACE_EVENT(ext4_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) __field( char, for_kupdate ) __field( char, range_cyclic ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->range_cyclic = wbc->range_cyclic; ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " "range_start %lld range_end %lld sync_mode %d " "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_pages, TP_PROTO(struct inode *inode, pgoff_t first_page, struct writeback_control *wbc), TP_ARGS(inode, first_page, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, first_page ) __field( long, nr_to_write ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->first_page = first_page; __entry->nr_to_write = wbc->nr_to_write; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu first_page %lu nr_to_write %ld " "sync_mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->first_page, __entry->nr_to_write, __entry->sync_mode) ); TRACE_EVENT(ext4_da_write_pages_extent, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map), TP_ARGS(inode, map), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, lblk ) __field( __u32, len ) __field( __u32, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->flags = map->m_flags; ), TP_printk("dev %d,%d ino %lu lblk %llu len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, show_mflags(__entry->flags)) ); TRACE_EVENT(ext4_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) __field( int, pages_written ) __field( long, pages_skipped ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld " "sync_mode %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); DECLARE_EVENT_CLASS(ext4__folio_op, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->index = folio->index; ), TP_printk("dev %d,%d ino %lu folio_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index) ); DEFINE_EVENT(ext4__folio_op, ext4_read_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DEFINE_EVENT(ext4__folio_op, ext4_release_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DECLARE_EVENT_CLASS(ext4_invalidate_folio_op, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) __field( size_t, offset ) __field( size_t, length ) ), TP_fast_assign( __entry->dev = folio->mapping->host->i_sb->s_dev; __entry->ino = folio->mapping->host->i_ino; __entry->index = folio->index; __entry->offset = offset; __entry->length = length; ), TP_printk("dev %d,%d ino %lu folio_index %lu offset %zu length %zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index, __entry->offset, __entry->length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_journalled_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), TP_ARGS(sb, blk, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, pa_pstart ) __field( __u64, pa_lstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_lstart = pa->pa_lstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); TRACE_EVENT(ext4_mb_release_inode_pa, TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( __u32, count ) ), TP_fast_assign( __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %lu block %llu count %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, TP_PROTO(struct super_block *sb, struct ext4_prealloc_space *pa), TP_ARGS(sb, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); TRACE_EVENT(ext4_discard_preallocations, TP_PROTO(struct inode *inode, unsigned int len), TP_ARGS(inode, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->len = len; ), TP_printk("dev %d,%d ino %lu len: %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->len) ); TRACE_EVENT(ext4_mb_discard_preallocations, TP_PROTO(struct super_block *sb, int needed), TP_ARGS(sb, needed), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->needed) ); TRACE_EVENT(ext4_request_blocks, TP_PROTO(struct ext4_allocation_request *ar), TP_ARGS(ar), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u lblk %u goal %llu " "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block), TP_ARGS(ar, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u block %llu lblk %u " "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->block, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, TP_PROTO(struct inode *inode, __u64 block, unsigned long count, int flags), TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned long, count ) __field( int, flags ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; __entry->flags = flags; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, show_free_flags(__entry->flags)) ); TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) ), TP_fast_assign( struct dentry *dentry = file->f_path.dentry; __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->datasync = datasync; __entry->parent = d_inode(dentry->d_parent)->i_ino; ), TP_printk("dev %d,%d ino %lu parent %lu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) ); TRACE_EVENT(ext4_sync_file_exit, TP_PROTO(struct inode *inode, int ret), TP_ARGS(inode, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) ); TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->wait = wait; ), TP_printk("dev %d,%d wait %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, data_blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; ), TP_printk("dev %d,%d ino %lu reserved_data_blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->data_blocks) ); TRACE_EVENT(ext4_mballoc_alloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, goal_logical ) __field( int, goal_start ) __field( __u32, goal_group ) __field( int, goal_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) __field( __u16, found ) __field( __u16, groups ) __field( __u16, buddy ) __field( __u16, flags ) __field( __u16, tail ) __field( __u8, cr ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->goal_logical = ac->ac_g_ex.fe_logical; __entry->goal_start = ac->ac_g_ex.fe_start; __entry->goal_group = ac->ac_g_ex.fe_group; __entry->goal_len = ac->ac_g_ex.fe_len; __entry->result_logical = ac->ac_f_ex.fe_logical; __entry->result_start = ac->ac_f_ex.fe_start; __entry->result_group = ac->ac_f_ex.fe_group; __entry->result_len = ac->ac_f_ex.fe_len; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; __entry->groups = ac->ac_groups_scanned; __entry->buddy = ac->ac_buddy; __entry->tail = ac->ac_tail; __entry->cr = ac->ac_criteria; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %s flags %s " "tail %u broken %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->goal_group, __entry->goal_start, __entry->goal_len, __entry->goal_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical, __entry->found, __entry->groups, show_criteria(__entry->cr), show_mballoc_flags(__entry->flags), __entry->tail, __entry->buddy ? 1 << __entry->buddy : 0) ); TRACE_EVENT(ext4_mballoc_prealloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->result_logical = ac->ac_b_ex.fe_logical; __entry->result_start = ac->ac_b_ex.fe_start; __entry->result_group = ac->ac_b_ex.fe_group; __entry->result_len = ac->ac_b_ex.fe_len; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical) ); DECLARE_EVENT_CLASS(ext4__mballoc, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; __entry->result_len = len; ), TP_printk("dev %d,%d inode %lu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); TRACE_EVENT(ext4_forget, TP_PROTO(struct inode *inode, int is_metadata, __u64 block), TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( int, is_metadata ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->is_metadata = is_metadata; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, used_blocks ) __field( int, reserved_data_blocks ) __field( int, quota_claim ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->quota_claim = quota_claim; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->reserved_data_blocks) ); TRACE_EVENT(ext4_da_release_space, TP_PROTO(struct inode *inode, int freed_blocks), TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, freed_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->freed_blocks = freed_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks) ); DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); TRACE_EVENT(ext4_read_block_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), TP_ARGS(sb, group, prefetch), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( bool, prefetch ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->prefetch = prefetch; ), TP_printk("dev %d,%d group %u prefetch %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->prefetch) ); DECLARE_EVENT_CLASS(ext4__fallocate_mode, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, offset ) __field( loff_t, len ) __field( int, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len, show_falloc_mode(__entry->mode)) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); TRACE_EVENT(ext4_fallocate_exit, TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), TP_ARGS(inode, offset, max_blocks, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, blocks ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = offset; __entry->blocks = max_blocks; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu pos %lld blocks %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->blocks, __entry->ret) ); TRACE_EVENT(ext4_unlink_enter, TP_PROTO(struct inode *parent, struct dentry *dentry), TP_ARGS(parent, dentry), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( loff_t, size ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->parent = parent->i_ino; __entry->size = d_inode(dentry)->i_size; ), TP_printk("dev %d,%d ino %lu size %lld parent %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->size, (unsigned long) __entry->parent) ); TRACE_EVENT(ext4_unlink_exit, TP_PROTO(struct dentry *dentry, int ret), TP_ARGS(dentry, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) ); DECLARE_EVENT_CLASS(ext4__truncate, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->blocks = inode->i_blocks; ), TP_printk("dev %d,%d ino %lu blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->blocks) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* 'ux' is the unwritten extent. */ TRACE_EVENT(ext4_ext_convert_to_initialized_enter, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux), TP_ARGS(inode, map, ux), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) __field( ext4_fsblk_t, u_pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); ), TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u u_lblk %u u_len %u " "u_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk) ); /* * 'ux' is the unwritten extent. * 'ix' is the initialized extent to which blocks are transferred. */ TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux, struct ext4_extent *ix), TP_ARGS(inode, map, ux, ix), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) __field( ext4_fsblk_t, u_pblk ) __field( ext4_lblk_t, i_lblk ) __field( unsigned, i_len ) __field( ext4_fsblk_t, i_pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); __entry->i_lblk = le32_to_cpu(ix->ee_block); __entry->i_len = ext4_ext_get_actual_len(ix); __entry->i_pblk = ext4_ext_pblock(ix); ), TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u " "u_lblk %u u_len %u u_pblk %llu " "i_lblk %u i_len %u i_pblk %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk, __entry->i_lblk, __entry->i_len, __entry->i_pblk) ); DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len, unsigned int flags), TP_ARGS(inode, lblk, len, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; __entry->flags = flags; ), TP_printk("dev %d,%d ino %lu lblk %u len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, show_map_flags(__entry->flags)) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, flags ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, mflags ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->pblk = map->m_pblk; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->mflags = map->m_flags; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu flags %s lblk %u pblk %llu len %u " "mflags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_map_flags(__entry->flags), __entry->lblk, __entry->pblk, __entry->len, show_mflags(__entry->mflags), __entry->ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); TRACE_EVENT(ext4_ext_load_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk), TP_ARGS(inode, lblk, pblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->pblk) ); TRACE_EVENT(ext4_load_inode, TP_PROTO(struct super_block *sb, unsigned long ino), TP_ARGS(sb, ino), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = ino; ), TP_printk("dev %d,%d ino %ld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(ext4_journal_start_sb, TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(sb, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_inode, TP_PROTO(struct inode *inode, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(inode, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( unsigned long, ino ) __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, ino %lu, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_reserved, TP_PROTO(struct super_block *sb, int blocks, unsigned long IP), TP_ARGS(sb, blocks, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, ip ) __field( int, blocks ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; ), TP_printk("dev %d,%d blocks, %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, (void *)__entry->ip) ); DECLARE_EVENT_CLASS(ext4__trim, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len), TP_STRUCT__entry( __field( int, dev_major ) __field( int, dev_minor ) __field( __u32, group ) __field( int, start ) __field( int, len ) ), TP_fast_assign( __entry->dev_major = MAJOR(sb->s_dev); __entry->dev_minor = MINOR(sb->s_dev); __entry->group = group; __entry->start = start; __entry->len = len; ), TP_printk("dev %d,%d group %u, start %d, len %d", __entry->dev_major, __entry->dev_minor, __entry->group, __entry->start, __entry->len) ); DEFINE_EVENT(ext4__trim, ext4_trim_extent, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); DEFINE_EVENT(ext4__trim, ext4_trim_all_free, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); TRACE_EVENT(ext4_ext_handle_unwritten_extents, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags, unsigned int allocated, ext4_fsblk_t newblock), TP_ARGS(inode, map, flags, allocated, newblock), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, flags ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) __field( unsigned int, len ) __field( unsigned int, allocated ) __field( ext4_fsblk_t, newblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->allocated = allocated; __entry->newblk = newblock; ), TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %s " "allocated %d newblock %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_map_flags(__entry->flags), (unsigned int) __entry->allocated, (unsigned long long) __entry->newblk) ); TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret), TP_ARGS(sb, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned int, flags ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) __field( unsigned int, len ) __field( int, ret ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = map->m_flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->ret = ret; ), TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_mflags(__entry->flags), __entry->ret) ); TRACE_EVENT(ext4_ext_show_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, unsigned short len), TP_ARGS(inode, lblk, pblk, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned short, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; __entry->len = len; ), TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, (unsigned short) __entry->len) ); TRACE_EVENT(ext4_remove_blocks, TP_PROTO(struct inode *inode, struct ext4_extent *ex, ext4_lblk_t from, ext4_fsblk_t to, struct partial_cluster *pc), TP_ARGS(inode, ex, from, to, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, from ) __field( ext4_lblk_t, to ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_lblk_t, ee_lblk ) __field( unsigned short, ee_len ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->from = from; __entry->to = to; __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" "from %u to %u partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (unsigned) __entry->from, (unsigned) __entry->to, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_leaf, TP_PROTO(struct inode *inode, ext4_lblk_t start, struct ext4_extent *ex, struct partial_cluster *pc), TP_ARGS(inode, start, ex, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, ee_lblk ) __field( ext4_fsblk_t, ee_pblk ) __field( short, ee_len ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" "partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_idx, TP_PROTO(struct inode *inode, ext4_fsblk_t pblk), TP_ARGS(inode, pblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; ), TP_printk("dev %d,%d ino %lu index_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long long) __entry->pblk) ); TRACE_EVENT(ext4_ext_remove_space, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth), TP_ARGS(inode, start, end, depth), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; ), TP_printk("dev %d,%d ino %lu since %u end %u depth %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth) ); TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth, struct partial_cluster *pc, __le16 eh_entries), TP_ARGS(inode, start, end, depth, pc, eh_entries), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state ) __field( unsigned short, eh_entries ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; __entry->eh_entries = le16_to_cpu(eh_entries); ), TP_printk("dev %d,%d ino %lu since %u end %u depth %d " "partial [pclu %lld lblk %u state %d] " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state, (unsigned short) __entry->eh_entries) ); DECLARE_EVENT_CLASS(ext4__es_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status)) ); DEFINE_EVENT(ext4__es_extent, ext4_es_insert_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); DEFINE_EVENT(ext4__es_extent, ext4_es_cache_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); TRACE_EVENT(ext4_es_remove_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len), TP_ARGS(inode, lblk, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, lblk ) __field( loff_t, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; ), TP_printk("dev %d,%d ino %lu es [%lld/%lld)", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len) ); TRACE_EVENT(ext4_es_find_extent_range_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_find_extent_range_exit, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status)) ); TRACE_EVENT(ext4_es_lookup_extent_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_lookup_extent_exit, TP_PROTO(struct inode *inode, struct extent_status *es, int found), TP_ARGS(inode, es, found), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) __field( int, found ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->found = found; ), TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->found, __entry->lblk, __entry->len, __entry->found ? __entry->pblk : 0, show_extent_status(__entry->found ? __entry->status : 0)) ); DECLARE_EVENT_CLASS(ext4__es_shrink_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_to_scan ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_to_scan = nr_to_scan; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_to_scan %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_to_scan, __entry->cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); TRACE_EVENT(ext4_es_shrink_scan_exit, TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt), TP_ARGS(sb, nr_shrunk, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->cache_cnt) ); TRACE_EVENT(ext4_collapse_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, offset) __field(loff_t, len) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_insert_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, offset) __field(loff_t, len) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_es_shrink, TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time, int nr_skipped, int retried), TP_ARGS(sb, nr_shrunk, scan_time, nr_skipped, retried), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( unsigned long long, scan_time ) __field( int, nr_skipped ) __field( int, retried ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->scan_time = div_u64(scan_time, 1000); __entry->nr_skipped = nr_skipped; __entry->retried = retried; ), TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu " "nr_skipped %d retried %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->scan_time, __entry->nr_skipped, __entry->retried) ); TRACE_EVENT(ext4_es_insert_delayed_block, TP_PROTO(struct inode *inode, struct extent_status *es, bool allocated), TP_ARGS(inode, es, allocated), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) __field( bool, allocated ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->allocated = allocated; ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s " "allocated %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status), __entry->allocated) ); /* fsmap traces */ DECLARE_EVENT_CLASS(ext4_fsmap_class, TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, u64 owner), TP_ARGS(sb, keydev, agno, bno, len, owner), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u32, agno) __field(u64, bno) __field(u64, len) __field(u64, owner) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(keydev); __entry->agno = agno; __entry->bno = bno; __entry->len = len; __entry->owner = owner; ), TP_printk("dev %d:%d keydev %d:%d agno %u bno %llu len %llu owner %lld\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, __entry->bno, __entry->len, __entry->owner) ) #define DEFINE_FSMAP_EVENT(name) \ DEFINE_EVENT(ext4_fsmap_class, name, \ TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, \ u64 owner), \ TP_ARGS(sb, keydev, agno, bno, len, owner)) DEFINE_FSMAP_EVENT(ext4_fsmap_low_key); DEFINE_FSMAP_EVENT(ext4_fsmap_high_key); DEFINE_FSMAP_EVENT(ext4_fsmap_mapping); DECLARE_EVENT_CLASS(ext4_getfsmap_class, TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), TP_ARGS(sb, fsmap), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u64, block) __field(u64, len) __field(u64, owner) __field(u64, flags) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(fsmap->fmr_device); __entry->block = fsmap->fmr_physical; __entry->len = fsmap->fmr_length; __entry->owner = fsmap->fmr_owner; __entry->flags = fsmap->fmr_flags; ), TP_printk("dev %d:%d keydev %d:%d block %llu len %llu owner %lld flags 0x%llx\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->block, __entry->len, __entry->owner, __entry->flags) ) #define DEFINE_GETFSMAP_EVENT(name) \ DEFINE_EVENT(ext4_getfsmap_class, name, \ TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), \ TP_ARGS(sb, fsmap)) DEFINE_GETFSMAP_EVENT(ext4_getfsmap_low_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_high_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_mapping); TRACE_EVENT(ext4_shutdown, TP_PROTO(struct super_block *sb, unsigned long flags), TP_ARGS(sb, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned, flags ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = flags; ), TP_printk("dev %d,%d flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->flags) ); TRACE_EVENT(ext4_error, TP_PROTO(struct super_block *sb, const char *function, unsigned int line), TP_ARGS(sb, function, line), TP_STRUCT__entry( __field( dev_t, dev ) __field( const char *, function ) __field( unsigned, line ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->function = function; __entry->line = line; ), TP_printk("dev %d,%d function %s line %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->function, __entry->line) ); TRACE_EVENT(ext4_prefetch_bitmaps, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_group_t next, unsigned int prefetch_ios), TP_ARGS(sb, group, next, prefetch_ios), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( __u32, next ) __field( __u32, ios ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->next = next; __entry->ios = prefetch_ios; ), TP_printk("dev %d,%d group %u next %u ios %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->next, __entry->ios) ); TRACE_EVENT(ext4_lazy_itable_init, TP_PROTO(struct super_block *sb, ext4_group_t group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); TRACE_EVENT(ext4_fc_replay_scan, TP_PROTO(struct super_block *sb, int error, int off), TP_ARGS(sb, error, off), TP_STRUCT__entry( __field(dev_t, dev) __field(int, error) __field(int, off) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->error = error; __entry->off = off; ), TP_printk("dev %d,%d error %d, off %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->error, __entry->off) ); TRACE_EVENT(ext4_fc_replay, TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2), TP_ARGS(sb, tag, ino, priv1, priv2), TP_STRUCT__entry( __field(dev_t, dev) __field(int, tag) __field(int, ino) __field(int, priv1) __field(int, priv2) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tag = tag; __entry->ino = ino; __entry->priv1 = priv1; __entry->priv2 = priv2; ), TP_printk("dev %d,%d: tag %d, ino %d, data1 %d, data2 %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tag, __entry->ino, __entry->priv1, __entry->priv2) ); TRACE_EVENT(ext4_fc_commit_start, TP_PROTO(struct super_block *sb, tid_t commit_tid), TP_ARGS(sb, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tid = commit_tid; ), TP_printk("dev %d,%d tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid) ); TRACE_EVENT(ext4_fc_commit_stop, TP_PROTO(struct super_block *sb, int nblks, int reason, tid_t commit_tid), TP_ARGS(sb, nblks, reason, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, nblks) __field(int, reason) __field(int, num_fc) __field(int, num_fc_ineligible) __field(int, nblks_agg) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nblks = nblks; __entry->reason = reason; __entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->num_fc_ineligible = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks; __entry->tid = commit_tid; ), TP_printk("dev %d,%d nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nblks, __entry->reason, __entry->num_fc, __entry->num_fc_ineligible, __entry->nblks_agg, __entry->tid) ); #define FC_REASON_NAME_STAT(reason) \ show_fc_reason(reason), \ __entry->fc_ineligible_rc[reason] TRACE_EVENT(ext4_fc_stats, TP_PROTO(struct super_block *sb), TP_ARGS(sb), TP_STRUCT__entry( __field(dev_t, dev) __array(unsigned int, fc_ineligible_rc, EXT4_FC_REASON_MAX) __field(unsigned long, fc_commits) __field(unsigned long, fc_ineligible_commits) __field(unsigned long, fc_numblks) ), TP_fast_assign( int i; __entry->dev = sb->s_dev; for (i = 0; i < EXT4_FC_REASON_MAX; i++) { __entry->fc_ineligible_rc[i] = EXT4_SB(sb)->s_fc_stats.fc_ineligible_reason_count[i]; } __entry->fc_commits = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->fc_ineligible_commits = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->fc_numblks = EXT4_SB(sb)->s_fc_stats.fc_numblks; ), TP_printk("dev %d,%d fc ineligible reasons:\n" "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u" "num_commits:%lu, ineligible: %lu, numblks: %lu", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), FC_REASON_NAME_STAT(EXT4_FC_REASON_ENCRYPTED_FILENAME), __entry->fc_commits, __entry->fc_ineligible_commits, __entry->fc_numblks) ); DECLARE_EVENT_CLASS(ext4_fc_track_dentry, TP_PROTO(handle_t *handle, struct inode *inode, struct dentry *dentry, int ret), TP_ARGS(handle, inode, dentry, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d,%d, t_tid %u, ino %lu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error ) ); #define DEFINE_EVENT_CLASS_DENTRY(__type) \ DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type, \ TP_PROTO(handle_t *handle, struct inode *inode, \ struct dentry *dentry, int ret), \ TP_ARGS(handle, inode, dentry, ret) \ ) DEFINE_EVENT_CLASS_DENTRY(create); DEFINE_EVENT_CLASS_DENTRY(link); DEFINE_EVENT_CLASS_DENTRY(unlink); TRACE_EVENT(ext4_fc_track_inode, TP_PROTO(handle_t *handle, struct inode *inode, int ret), TP_ARGS(handle, inode, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error) ); TRACE_EVENT(ext4_fc_track_range, TP_PROTO(handle_t *handle, struct inode *inode, long start, long end, int ret), TP_ARGS(handle, inode, start, end, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(long, start) __field(long, end) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->start = start; __entry->end = end; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d, start %ld, end %ld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error, __entry->start, __entry->end) ); TRACE_EVENT(ext4_fc_cleanup, TP_PROTO(journal_t *journal, int full, tid_t tid), TP_ARGS(journal, full, tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, j_fc_off) __field(int, full) __field(tid_t, tid) ), TP_fast_assign( struct super_block *sb = journal->j_private; __entry->dev = sb->s_dev; __entry->j_fc_off = journal->j_fc_off; __entry->full = full; __entry->tid = tid; ), TP_printk("dev %d,%d, j_fc_off %d, full %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->j_fc_off, __entry->full, __entry->tid) ); TRACE_EVENT(ext4_update_sb, TP_PROTO(struct super_block *sb, ext4_fsblk_t fsblk, unsigned int flags), TP_ARGS(sb, fsblk, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(ext4_fsblk_t, fsblk) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->fsblk = fsblk; __entry->flags = flags; ), TP_printk("dev %d,%d fsblk %llu flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fsblk, __entry->flags) ); #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 55 77 76 2 54 54 5 1 77 77 105 14 99 8 7 8 8 8 8 107 107 10 10 10 10 10 10 1 1 1 1 1 1 1 1 1 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 72 40 10 10 10 10 97 113 110 116 113 113 4 4 94 97 96 94 97 97 97 96 10 96 1 97 94 94 94 94 94 94 94 94 94 94 97 97 97 10 10 62 53 10 99 89 10 135 49 45 32 87 5 2 25 23 2 2 2 25 21 4 4 24 23 24 6 3 9 74 42 92 19 2 19 19 4 1 3 9 13 9 20 4 2 2 19 19 19 19 1 1 20 20 20 20 20 20 12 8 8 12 8 103 20 101 44 27 24 27 43 45 41 8 92 92 89 91 54 2 11 31 2 17 19 19 19 1 92 91 54 2 92 19 9 31 15 15 3 31 31 31 31 31 19 21 21 7 5 33 37 21 20 23 21 22 88 76 1 14 16 4 3 7 15 1 1 9 1 9 3 6 41 41 37 9 37 37 37 41 37 37 41 41 36 36 31 27 27 93 8 83 4 13 92 80 28 73 31 27 56 5 50 32 2 24 45 8 46 49 2 24 24 9 4 4 4 1 5 1 3 1 4 1 5 4 2 3 3 2 2 104 2 2 104 49 43 77 23 76 50 40 51 51 50 3 3 15 65 75 76 13 36 49 17 42 26 56 16 16 20 20 9 7 16 16 14 14 7 14 20 20 10 14 20 20 1 15 9 105 98 23 3 105 22 22 2 93 11 9 6 56 56 54 7 53 41 7 9 19 71 20 77 27 56 76 27 24 41 20 73 28 99 20 20 101 3 104 99 3 20 17 15 15 15 15 15 7 1 9 1 1 2 9 4 66 2 1 66 71 66 9 9 9 9 9 116 8 108 1 106 1 51 51 11 58 17 68 3 4 70 4 105 110 22 14 3 2 6 1 39 8 33 7 25 11 6 2 14 14 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 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/list_sort.h> #include <linux/iversion.h> #include "misc.h" #include "ctree.h" #include "tree-log.h" #include "disk-io.h" #include "locking.h" #include "backref.h" #include "compression.h" #include "qgroup.h" #include "block-group.h" #include "space-info.h" #include "inode-item.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" #include "dir-item.h" #include "file-item.h" #include "file.h" #include "orphan.h" #include "tree-checker.h" #define MAX_CONFLICT_INODES 10 /* magic values for the inode_only field in btrfs_log_inode: * * LOG_INODE_ALL means to log everything * LOG_INODE_EXISTS means to log just enough to recreate the inode * during log replay */ enum { LOG_INODE_ALL, LOG_INODE_EXISTS, }; /* * directory trouble cases * * 1) on rename or unlink, if the inode being unlinked isn't in the fsync * log, we must force a full commit before doing an fsync of the directory * where the unlink was done. * ---> record transid of last unlink/rename per directory * * mkdir foo/some_dir * normal commit * rename foo/some_dir foo2/some_dir * mkdir foo/some_dir * fsync foo/some_dir/some_file * * The fsync above will unlink the original some_dir without recording * it in its new location (foo2). After a crash, some_dir will be gone * unless the fsync of some_file forces a full commit * * 2) we must log any new names for any file or dir that is in the fsync * log. ---> check inode while renaming/linking. * * 2a) we must log any new names for any file or dir during rename * when the directory they are being removed from was logged. * ---> check inode and old parent dir during rename * * 2a is actually the more important variant. With the extra logging * a crash might unlink the old name without recreating the new one * * 3) after a crash, we must go through any directories with a link count * of zero and redo the rm -rf * * mkdir f1/foo * normal commit * rm -rf f1/foo * fsync(f1) * * The directory f1 was fully removed from the FS, but fsync was never * called on f1, only its parent dir. After a crash the rm -rf must * be replayed. This must be able to recurse down the entire * directory tree. The inode link count fixup code takes care of the * ugly details. */ /* * stages for the tree walking. The first * stage (0) is to only pin down the blocks we find * the second stage (1) is to make sure that all the inodes * we find in the log are created in the subvolume. * * The last stage is to deal with directories and links and extents * and all the other fun semantics */ enum { LOG_WALK_PIN_ONLY, LOG_WALK_REPLAY_INODES, LOG_WALK_REPLAY_DIR_INDEX, LOG_WALK_REPLAY_ALL, }; static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx); static int link_to_fixup_dir(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid); static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all); static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that * fsyncs and O_SYNCs can happen without doing full tree commits. * * Full tree commits are expensive because they require commonly * modified blocks to be recowed, creating many dirty pages in the * extent tree an 4x-6x higher write load than ext3. * * Instead of doing a tree commit on every fsync, we use the * key ranges and transaction ids to find items for a given file or directory * that have changed in this transaction. Those items are copied into * a special tree (one per subvolume root), that tree is written to disk * and then the fsync is considered complete. * * After a crash, items are copied out of the log-tree back into the * subvolume tree. Any file data extents found are recorded in the extent * allocation tree, and the log-tree freed. * * The log tree is read three times, once to pin down all the extents it is * using in ram and once, once to create all the inodes logged in the tree * and once to do all the other items. */ static struct inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *root) { unsigned int nofs_flag; struct inode *inode; /* * We're holding a transaction handle whether we are logging or * replaying a log tree, so we must make sure NOFS semantics apply * because btrfs_alloc_inode() may be triggered and it uses GFP_KERNEL * to allocate an inode, which can recurse back into the filesystem and * attempt a transaction commit, resulting in a deadlock. */ nofs_flag = memalloc_nofs_save(); inode = btrfs_iget(root->fs_info->sb, objectid, root); memalloc_nofs_restore(nofs_flag); return inode; } /* * start a sub transaction and setup the log tree * this increments the log tree writer count to make the people * syncing the tree wait for us to finish */ static int start_log_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *tree_root = fs_info->tree_root; const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; bool created = false; /* * First check if the log root tree was already created. If not, create * it before locking the root's log_mutex, just to keep lockdep happy. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state)) { mutex_lock(&tree_root->log_mutex); if (!fs_info->log_root_tree) { ret = btrfs_init_log_root_tree(trans, fs_info); if (!ret) { set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); created = true; } } mutex_unlock(&tree_root->log_mutex); if (ret) return ret; } mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } else if (root->log_start_pid != current->pid) { set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { /* * This means fs_info->log_root_tree was already created * for some other FS trees. Do the full commit not to mix * nodes from multiple log transactions to do sequential * writing. */ if (zoned && !created) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } ret = btrfs_add_log_tree(trans, root); if (ret) goto out; set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } atomic_inc(&root->log_writers); if (!ctx->logging_new_name) { int index = root->log_transid % 2; list_add_tail(&ctx->list, &root->log_ctxs[index]); ctx->log_transid = root->log_transid; } out: mutex_unlock(&root->log_mutex); return ret; } /* * returns 0 if there was a log transaction running and we were able * to join, or returns -ENOENT if there were not transactions * in progress */ static int join_running_log_trans(struct btrfs_root *root) { const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; ret = 0; if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); return ret; } /* * This either makes the current running log transaction wait * until you call btrfs_end_log_trans() or it makes any future * log transactions wait until you call btrfs_end_log_trans() */ void btrfs_pin_log_trans(struct btrfs_root *root) { atomic_inc(&root->log_writers); } /* * indicate we're done making changes to the log tree * and wake up anyone waiting to do a sync */ void btrfs_end_log_trans(struct btrfs_root *root) { if (atomic_dec_and_test(&root->log_writers)) { /* atomic_dec_and_test implies a barrier */ cond_wake_up_nomb(&root->log_writer_wait); } } /* * the walk control struct is used to pass state down the chain when * processing the log tree. The stage field tells us which part * of the log tree processing we are currently doing. The others * are state fields used for that specific part */ struct walk_control { /* should we free the extent on disk when done? This is used * at transaction commit time while freeing a log tree */ int free; /* pin only walk, we record which extents on disk belong to the * log trees */ int pin; /* what stage of the replay code we're currently in */ int stage; /* * Ignore any items from the inode currently being processed. Needs * to be set every time we find a BTRFS_INODE_ITEM_KEY and we are in * the LOG_WALK_REPLAY_INODES stage. */ bool ignore_cur_inode; /* the root we are currently replaying */ struct btrfs_root *replay_dest; /* the trans handle for the current replay */ struct btrfs_trans_handle *trans; /* the function that gets used to process blocks we find in the * tree. Note the extent_buffer might not be up to date when it is * passed in, and it must be checked or read if you need the data * inside it */ int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level); }; /* * process_func used to pin down extents, write them or wait on them */ static int process_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { struct btrfs_fs_info *fs_info = log->fs_info; int ret = 0; /* * If this fs is mixed then we need to be able to process the leaves to * pin down any logged extents, so we have to read the block. */ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { struct btrfs_tree_parent_check check = { .level = level, .transid = gen }; ret = btrfs_read_extent_buffer(eb, &check); if (ret) return ret; } if (wc->pin) { ret = btrfs_pin_extent_for_log_replay(wc->trans, eb); if (ret) return ret; if (btrfs_buffer_uptodate(eb, gen, 0) && btrfs_header_level(eb) == 0) ret = btrfs_exclude_logged_extents(eb); } return ret; } /* * Item overwrite used by replay and tree logging. eb, slot and key all refer * to the src data we are copying out. * * root is the tree we are copying into, and path is a scratch * path for use in this function (it should be released on entry and * will be released on exit). * * If the key is already in the destination tree the existing item is * overwritten. If the existing item isn't big enough, it is extended. * If it is too large, it is truncated. * * If the key isn't in the destination yet, a new item is inserted. */ static int overwrite_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { int ret; u32 item_size; u64 saved_i_size = 0; int save_old_i_size = 0; unsigned long src_ptr; unsigned long dst_ptr; bool inode_item = key->type == BTRFS_INODE_ITEM_KEY; /* * This is only used during log replay, so the root is always from a * fs/subvolume tree. In case we ever need to support a log root, then * we'll have to clone the leaf in the path, release the path and use * the leaf before writing into the log tree. See the comments at * copy_items() for more details. */ ASSERT(btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID); item_size = btrfs_item_size(eb, slot); src_ptr = btrfs_item_ptr_offset(eb, slot); /* Look for the key in the destination tree. */ ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { char *src_copy; char *dst_copy; u32 dst_size = btrfs_item_size(path->nodes[0], path->slots[0]); if (dst_size != item_size) goto insert; if (item_size == 0) { btrfs_release_path(path); return 0; } dst_copy = kmalloc(item_size, GFP_NOFS); src_copy = kmalloc(item_size, GFP_NOFS); if (!dst_copy || !src_copy) { btrfs_release_path(path); kfree(dst_copy); kfree(src_copy); return -ENOMEM; } read_extent_buffer(eb, src_copy, src_ptr, item_size); dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); read_extent_buffer(path->nodes[0], dst_copy, dst_ptr, item_size); ret = memcmp(dst_copy, src_copy, item_size); kfree(dst_copy); kfree(src_copy); /* * they have the same contents, just return, this saves * us from cowing blocks in the destination tree and doing * extra writes that may not have been done by a previous * sync */ if (ret == 0) { btrfs_release_path(path); return 0; } /* * We need to load the old nbytes into the inode so when we * replay the extents we've logged we get the right nbytes. */ if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); nbytes = btrfs_inode_nbytes(path->nodes[0], item); item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); /* * If this is a directory we need to reset the i_size to * 0 so that we can set it up properly when replaying * the rest of the items in this log. */ mode = btrfs_inode_mode(eb, item); if (S_ISDIR(mode)) btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out * properly when we replay the extents. */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); /* * If this is a directory we need to reset the i_size to 0 so * that we can set it up properly when replaying the rest of * the items in this log. */ mode = btrfs_inode_mode(eb, item); if (S_ISDIR(mode)) btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); /* try to insert the key into the destination tree */ path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, path, key, item_size); path->skip_release_on_error = 0; /* make sure any existing item is the correct size */ if (ret == -EEXIST || ret == -EOVERFLOW) { u32 found_size; found_size = btrfs_item_size(path->nodes[0], path->slots[0]); if (found_size > item_size) btrfs_truncate_item(trans, path, item_size, 1); else if (found_size < item_size) btrfs_extend_item(trans, path, item_size - found_size); } else if (ret) { return ret; } dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); /* don't overwrite an existing inode if the generation number * was logged as zero. This is done when the tree logging code * is just logging an inode to make sure it exists after recovery. * * Also, don't overwrite i_size on directories during replay. * log replay inserts and removes directory items based on the * state of the tree found in the subvolume, and i_size is modified * as it goes */ if (key->type == BTRFS_INODE_ITEM_KEY && ret == -EEXIST) { struct btrfs_inode_item *src_item; struct btrfs_inode_item *dst_item; src_item = (struct btrfs_inode_item *)src_ptr; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(eb, src_item) == 0) { struct extent_buffer *dst_eb = path->nodes[0]; const u64 ino_size = btrfs_inode_size(eb, src_item); /* * For regular files an ino_size == 0 is used only when * logging that an inode exists, as part of a directory * fsync, and the inode wasn't fsynced before. In this * case don't set the size of the inode in the fs/subvol * tree, otherwise we would be throwing valid data away. */ if (S_ISREG(btrfs_inode_mode(eb, src_item)) && S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) && ino_size != 0) btrfs_set_inode_size(dst_eb, dst_item, ino_size); goto no_copy; } if (S_ISDIR(btrfs_inode_mode(eb, src_item)) && S_ISDIR(btrfs_inode_mode(path->nodes[0], dst_item))) { save_old_i_size = 1; saved_i_size = btrfs_inode_size(path->nodes[0], dst_item); } } copy_extent_buffer(path->nodes[0], eb, dst_ptr, src_ptr, item_size); if (save_old_i_size) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; btrfs_set_inode_size(path->nodes[0], dst_item, saved_i_size); } /* make sure the generation is filled in */ if (key->type == BTRFS_INODE_ITEM_KEY) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(path->nodes[0], dst_item) == 0) { btrfs_set_inode_generation(path->nodes[0], dst_item, trans->transid); } } no_copy: btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len, struct fscrypt_str *name) { char *buf; buf = kmalloc(len, GFP_NOFS); if (!buf) return -ENOMEM; read_extent_buffer(eb, buf, (unsigned long)start, len); name->name = buf; name->len = len; return 0; } /* * simple helper to read an inode off the disk from a given root * This can only be called for subvolume roots and not for the log */ static noinline struct inode *read_one_inode(struct btrfs_root *root, u64 objectid) { struct inode *inode; inode = btrfs_iget_logging(objectid, root); if (IS_ERR(inode)) inode = NULL; return inode; } /* replays a single extent in 'eb' at 'slot' with 'key' into the * subvolume 'root'. path is released on entry and should be released * on exit. * * extents in the log tree have not been allocated out of the extent * tree yet. So, this completes the allocation, taking a reference * as required if the extent already exists or creating a new extent * if it isn't in the extent allocation tree yet. * * The extent is inserted into the file, dropping any existing extents * from the file that overlap the new one. */ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_fs_info *fs_info = root->fs_info; int found_type; u64 extent_end; u64 start = key->offset; u64 nbytes = 0; struct btrfs_file_extent_item *item; struct inode *inode = NULL; unsigned long size; int ret = 0; item = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); found_type = btrfs_file_extent_type(eb, item); if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { nbytes = btrfs_file_extent_num_bytes(eb, item); extent_end = start + nbytes; /* * We don't add to the inodes nbytes if we are prealloc or a * hole. */ if (btrfs_file_extent_disk_bytenr(eb, item) == 0) nbytes = 0; } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { size = btrfs_file_extent_ram_bytes(eb, item); nbytes = btrfs_file_extent_ram_bytes(eb, item); extent_end = ALIGN(start + size, fs_info->sectorsize); } else { ret = 0; goto out; } inode = read_one_inode(root, key->objectid); if (!inode) { ret = -EIO; goto out; } /* * first check to see if we already have this extent in the * file. This must be done before the btrfs_drop_extents run * so we don't try to drop this extent. */ ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(BTRFS_I(inode)), start, 0); if (ret == 0 && (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC)) { struct btrfs_file_extent_item cmp1; struct btrfs_file_extent_item cmp2; struct btrfs_file_extent_item *existing; struct extent_buffer *leaf; leaf = path->nodes[0]; existing = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); read_extent_buffer(eb, &cmp1, (unsigned long)item, sizeof(cmp1)); read_extent_buffer(leaf, &cmp2, (unsigned long)existing, sizeof(cmp2)); /* * we already have a pointer to this exact extent, * we don't have to do anything */ if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) { btrfs_release_path(path); goto out; } } btrfs_release_path(path); /* drop any overlapping extents */ drop_args.start = start; drop_args.end = extent_end; drop_args.drop_cache = true; ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args); if (ret) goto out; if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { u64 offset; unsigned long dest_offset; struct btrfs_key ins; if (btrfs_file_extent_disk_bytenr(eb, item) == 0 && btrfs_fs_incompat(fs_info, NO_HOLES)) goto update_inode; ret = btrfs_insert_empty_item(trans, root, path, key, sizeof(*item)); if (ret) goto out; dest_offset = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); copy_extent_buffer(path->nodes[0], eb, dest_offset, (unsigned long)item, sizeof(*item)); ins.objectid = btrfs_file_extent_disk_bytenr(eb, item); ins.offset = btrfs_file_extent_disk_num_bytes(eb, item); ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); /* * Manually record dirty extent, as here we did a shallow * file extent item copy and skip normal backref update, * but modifying extent tree all by ourselves. * So need to manually record dirty extent for qgroup, * as the owner of the file extent changed from log tree * (doesn't affect qgroup) to fs/file tree(affects qgroup) */ ret = btrfs_qgroup_trace_extent(trans, btrfs_file_extent_disk_bytenr(eb, item), btrfs_file_extent_disk_num_bytes(eb, item)); if (ret < 0) goto out; if (ins.objectid > 0) { u64 csum_start; u64 csum_end; LIST_HEAD(ordered_sums); /* * is this extent already allocated in the extent * allocation tree? If so, just add a reference */ ret = btrfs_lookup_data_extent(fs_info, ins.objectid, ins.offset); if (ret < 0) { goto out; } else if (ret == 0) { struct btrfs_ref ref = { .action = BTRFS_ADD_DELAYED_REF, .bytenr = ins.objectid, .num_bytes = ins.offset, .owning_root = btrfs_root_id(root), .ref_root = btrfs_root_id(root), }; btrfs_init_data_ref(&ref, key->objectid, offset, 0, false); ret = btrfs_inc_extent_ref(trans, &ref); if (ret) goto out; } else { /* * insert the extent pointer in the extent * allocation tree */ ret = btrfs_alloc_logged_file_extent(trans, btrfs_root_id(root), key->objectid, offset, &ins); if (ret) goto out; } btrfs_release_path(path); if (btrfs_file_extent_compression(eb, item)) { csum_start = ins.objectid; csum_end = csum_start + ins.offset; } else { csum_start = ins.objectid + btrfs_file_extent_offset(eb, item); csum_end = csum_start + btrfs_file_extent_num_bytes(eb, item); } ret = btrfs_lookup_csums_list(root->log_root, csum_start, csum_end - 1, &ordered_sums, false); if (ret < 0) goto out; ret = 0; /* * Now delete all existing cums in the csum root that * cover our range. We do this because we can have an * extent that is completely referenced by one file * extent item and partially referenced by another * file extent item (like after using the clone or * extent_same ioctls). In this case if we end up doing * the replay of the one that partially references the * extent first, and we do not do the csum deletion * below, we can get 2 csum items in the csum tree that * overlap each other. For example, imagine our log has * the two following file extent items: * * key (257 EXTENT_DATA 409600) * extent data disk byte 12845056 nr 102400 * extent data offset 20480 nr 20480 ram 102400 * * key (257 EXTENT_DATA 819200) * extent data disk byte 12845056 nr 102400 * extent data offset 0 nr 102400 ram 102400 * * Where the second one fully references the 100K extent * that starts at disk byte 12845056, and the log tree * has a single csum item that covers the entire range * of the extent: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * * After the first file extent item is replayed, the * csum tree gets the following csum item: * * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which covers the 20K sub-range starting at offset 20K * of our extent. Now when we replay the second file * extent item, if we do not delete existing csum items * that cover any of its blocks, we end up getting two * csum items in our csum tree that overlap each other: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which is a problem, because after this anyone trying * to lookup up for the checksum of any block of our * extent starting at an offset of 40K or higher, will * end up looking at the second csum item only, which * does not contain the checksum for any block starting * at offset 40K or higher of our extent. */ while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums; struct btrfs_root *csum_root; sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, list); csum_root = btrfs_csum_root(fs_info, sums->logical); if (!ret) ret = btrfs_del_csums(trans, csum_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, csum_root, sums); list_del(&sums->list); kfree(sums); } if (ret) goto out; } else { btrfs_release_path(path); } } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { /* inline extents are easy, we just overwrite them */ ret = overwrite_item(trans, root, path, eb, slot, key); if (ret) goto out; } ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start, extent_end - start); if (ret) goto out; update_inode: btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found); ret = btrfs_update_inode(trans, BTRFS_I(inode)); out: iput(inode); return ret; } static int unlink_inode_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, const struct fscrypt_str *name) { int ret; ret = btrfs_unlink_inode(trans, dir, inode, name); if (ret) return ret; /* * Whenever we need to check if a name exists or not, we check the * fs/subvolume tree. So after an unlink we must run delayed items, so * that future checks for a name during log replay see that the name * does not exists anymore. */ return btrfs_run_delayed_items(trans); } /* * when cleaning up conflicts between the directory names in the * subvolume, directory names in the log and directory names in the * inode back references, we may have to unlink inodes from directories. * * This is a helper function to do the unlink of a specific directory * item */ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_inode *dir, struct btrfs_dir_item *di) { struct btrfs_root *root = dir->root; struct inode *inode; struct fscrypt_str name; struct extent_buffer *leaf; struct btrfs_key location; int ret; leaf = path->nodes[0]; btrfs_dir_item_key_to_cpu(leaf, di, &location); ret = read_alloc_one_name(leaf, di + 1, btrfs_dir_name_len(leaf, di), &name); if (ret) return -ENOMEM; btrfs_release_path(path); inode = read_one_inode(root, location.objectid); if (!inode) { ret = -EIO; goto out; } ret = link_to_fixup_dir(trans, root, path, location.objectid); if (ret) goto out; ret = unlink_inode_for_log_replay(trans, dir, BTRFS_I(inode), &name); out: kfree(name.name); iput(inode); return ret; } /* * See if a given name and sequence number found in an inode back reference are * already in a directory and correctly point to this inode. * * Returns: < 0 on error, 0 if the directory entry does not exists and 1 if it * exists. */ static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 objectid, u64 index, struct fscrypt_str *name) { struct btrfs_dir_item *di; struct btrfs_key location; int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid != objectid) goto out; } else { goto out; } btrfs_release_path(path); di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid == objectid) ret = 1; } out: btrfs_release_path(path); return ret; } /* * helper function to check a log tree for a named back reference in * an inode. This is used to decide if a back reference that is * found in the subvolume conflicts with what we find in the log. * * inode backreferences may have multiple refs in a single item, * during replay we process one reference at a time, and we don't * want to delete valid links to a file from the subvolume if that * link is also in the log. */ static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, const struct fscrypt_str *name) { struct btrfs_path *path; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(NULL, log, key, path, 0, 0); if (ret < 0) { goto out; } else if (ret == 1) { ret = 0; goto out; } if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], ref_objectid, name); else ret = !!btrfs_find_name_in_backref(path->nodes[0], path->slots[0], name); out: btrfs_free_path(path); return ret; } static inline int __add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_root *log_root, struct btrfs_inode *dir, struct btrfs_inode *inode, u64 inode_objectid, u64 parent_objectid, u64 ref_index, struct fscrypt_str *name) { int ret; struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key search_key; struct btrfs_inode_extref *extref; again: /* Search old style refs */ search_key.objectid = inode_objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = parent_objectid; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret == 0) { struct btrfs_inode_ref *victim_ref; unsigned long ptr; unsigned long ptr_end; leaf = path->nodes[0]; /* are we trying to overwrite a back ref for the root directory * if so, just jump out, we're done */ if (search_key.objectid == search_key.offset) return 1; /* check all the names in this back reference to see * if they are in the log. if so, we allow them to stay * otherwise they must be unlinked as a conflict */ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); ptr_end = ptr + btrfs_item_size(leaf, path->slots[0]); while (ptr < ptr_end) { struct fscrypt_str victim_name; victim_ref = (struct btrfs_inode_ref *)ptr; ret = read_alloc_one_name(leaf, (victim_ref + 1), btrfs_inode_ref_name_len(leaf, victim_ref), &victim_name); if (ret) return ret; ret = backref_in_log(log_root, &search_key, parent_objectid, &victim_name); if (ret < 0) { kfree(victim_name.name); return ret; } else if (!ret) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = unlink_inode_for_log_replay(trans, dir, inode, &victim_name); kfree(victim_name.name); if (ret) return ret; goto again; } kfree(victim_name.name); ptr = (unsigned long)(victim_ref + 1) + victim_name.len; } } btrfs_release_path(path); /* Same search but for extended refs */ extref = btrfs_lookup_inode_extref(NULL, root, path, name, inode_objectid, parent_objectid, 0, 0); if (IS_ERR(extref)) { return PTR_ERR(extref); } else if (extref) { u32 item_size; u32 cur_offset = 0; unsigned long base; struct inode *victim_parent; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { struct fscrypt_str victim_name; extref = (struct btrfs_inode_extref *)(base + cur_offset); if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid) goto next; ret = read_alloc_one_name(leaf, &extref->name, btrfs_inode_extref_name_len(leaf, extref), &victim_name); if (ret) return ret; search_key.objectid = inode_objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = btrfs_extref_hash(parent_objectid, victim_name.name, victim_name.len); ret = backref_in_log(log_root, &search_key, parent_objectid, &victim_name); if (ret < 0) { kfree(victim_name.name); return ret; } else if (!ret) { ret = -ENOENT; victim_parent = read_one_inode(root, parent_objectid); if (victim_parent) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = unlink_inode_for_log_replay(trans, BTRFS_I(victim_parent), inode, &victim_name); } iput(victim_parent); kfree(victim_name.name); if (ret) return ret; goto again; } kfree(victim_name.name); next: cur_offset += victim_name.len + sizeof(*extref); } } btrfs_release_path(path); /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, path, dir, di); if (ret) return ret; } btrfs_release_path(path); /* look for a conflicting name */ di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, path, dir, di); if (ret) return ret; } btrfs_release_path(path); return 0; } static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; int ret; extref = (struct btrfs_inode_extref *)ref_ptr; ret = read_alloc_one_name(eb, &extref->name, btrfs_inode_extref_name_len(eb, extref), name); if (ret) return ret; if (index) *index = btrfs_inode_extref_index(eb, extref); if (parent_objectid) *parent_objectid = btrfs_inode_extref_parent(eb, extref); return 0; } static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index) { struct btrfs_inode_ref *ref; int ret; ref = (struct btrfs_inode_ref *)ref_ptr; ret = read_alloc_one_name(eb, ref + 1, btrfs_inode_ref_name_len(eb, ref), name); if (ret) return ret; if (index) *index = btrfs_inode_ref_index(eb, ref); return 0; } /* * Take an inode reference item from the log tree and iterate all names from the * inode reference item in the subvolume tree with the same key (if it exists). * For any name that is not in the inode reference item from the log tree, do a * proper unlink of that name (that is, remove its entry from the inode * reference item and both dir index keys). */ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_inode *inode, struct extent_buffer *log_eb, int log_slot, struct btrfs_key *key) { int ret; unsigned long ref_ptr; unsigned long ref_end; struct extent_buffer *eb; again: btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret > 0) { ret = 0; goto out; } if (ret < 0) goto out; eb = path->nodes[0]; ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); ref_end = ref_ptr + btrfs_item_size(eb, path->slots[0]); while (ref_ptr < ref_end) { struct fscrypt_str name; u64 parent_id; if (key->type == BTRFS_INODE_EXTREF_KEY) { ret = extref_get_fields(eb, ref_ptr, &name, NULL, &parent_id); } else { parent_id = key->offset; ret = ref_get_fields(eb, ref_ptr, &name, NULL); } if (ret) goto out; if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(log_eb, log_slot, parent_id, &name); else ret = !!btrfs_find_name_in_backref(log_eb, log_slot, &name); if (!ret) { struct inode *dir; btrfs_release_path(path); dir = read_one_inode(root, parent_id); if (!dir) { ret = -ENOENT; kfree(name.name); goto out; } ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), inode, &name); kfree(name.name); iput(dir); if (ret) goto out; goto again; } kfree(name.name); ref_ptr += name.len; if (key->type == BTRFS_INODE_EXTREF_KEY) ref_ptr += sizeof(struct btrfs_inode_extref); else ref_ptr += sizeof(struct btrfs_inode_ref); } ret = 0; out: btrfs_release_path(path); return ret; } /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. * root is the destination we are replaying into, and path is for temp * use by this function. (it should be released on return). */ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { struct inode *dir = NULL; struct inode *inode = NULL; unsigned long ref_ptr; unsigned long ref_end; struct fscrypt_str name; int ret; int log_ref_ver = 0; u64 parent_objectid; u64 inode_objectid; u64 ref_index = 0; int ref_struct_size; ref_ptr = btrfs_item_ptr_offset(eb, slot); ref_end = ref_ptr + btrfs_item_size(eb, slot); if (key->type == BTRFS_INODE_EXTREF_KEY) { struct btrfs_inode_extref *r; ref_struct_size = sizeof(struct btrfs_inode_extref); log_ref_ver = 1; r = (struct btrfs_inode_extref *)ref_ptr; parent_objectid = btrfs_inode_extref_parent(eb, r); } else { ref_struct_size = sizeof(struct btrfs_inode_ref); parent_objectid = key->offset; } inode_objectid = key->objectid; /* * it is possible that we didn't log all the parent directories * for a given inode. If we don't find the dir, just don't * copy the back ref in. The link count fixup code will take * care of the rest */ dir = read_one_inode(root, parent_objectid); if (!dir) { ret = -ENOENT; goto out; } inode = read_one_inode(root, inode_objectid); if (!inode) { ret = -EIO; goto out; } while (ref_ptr < ref_end) { if (log_ref_ver) { ret = extref_get_fields(eb, ref_ptr, &name, &ref_index, &parent_objectid); /* * parent object can change from one array * item to another. */ if (!dir) dir = read_one_inode(root, parent_objectid); if (!dir) { ret = -ENOENT; goto out; } } else { ret = ref_get_fields(eb, ref_ptr, &name, &ref_index); } if (ret) goto out; ret = inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), btrfs_ino(BTRFS_I(inode)), ref_index, &name); if (ret < 0) { goto out; } else if (ret == 0) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name * of the file before we add our new link. Later on, we * overwrite any existing back reference, and we don't * want to create dangling pointers in the directory. */ ret = __add_inode_ref(trans, root, path, log, BTRFS_I(dir), BTRFS_I(inode), inode_objectid, parent_objectid, ref_index, &name); if (ret) { if (ret == 1) ret = 0; goto out; } /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), &name, 0, ref_index); if (ret) goto out; ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) goto out; } /* Else, ret == 1, we already have a perfect match, we're done. */ ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + name.len; kfree(name.name); name.name = NULL; if (log_ref_ver) { iput(dir); dir = NULL; } } /* * Before we overwrite the inode reference item in the subvolume tree * with the item from the log tree, we must unlink all names from the * parent directory that are in the subvolume's tree inode reference * item, otherwise we end up with an inconsistent subvolume tree where * dir index entries exist for a name but there is no inode reference * item with the same name. */ ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot, key); if (ret) goto out; /* finally write the back reference in the inode */ ret = overwrite_item(trans, root, path, eb, slot, key); out: btrfs_release_path(path); kfree(name.name); iput(dir); iput(inode); return ret; } static int count_inode_extrefs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret = 0; int name_len; unsigned int nlink = 0; u32 item_size; u32 cur_offset = 0; u64 inode_objectid = btrfs_ino(inode); u64 offset = 0; unsigned long ptr; struct btrfs_inode_extref *extref; struct extent_buffer *leaf; while (1) { ret = btrfs_find_one_extref(inode->root, inode_objectid, offset, path, &extref, &offset); if (ret) break; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); cur_offset = 0; while (cur_offset < item_size) { extref = (struct btrfs_inode_extref *) (ptr + cur_offset); name_len = btrfs_inode_extref_name_len(leaf, extref); nlink++; cur_offset += name_len + sizeof(*extref); } offset++; btrfs_release_path(path); } btrfs_release_path(path); if (ret < 0 && ret != -ENOENT) return ret; return nlink; } static int count_inode_refs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret; struct btrfs_key key; unsigned int nlink = 0; unsigned long ptr; unsigned long ptr_end; int name_len; u64 ino = btrfs_ino(inode); key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0); if (ret < 0) break; if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } process_slot: btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_INODE_REF_KEY) break; ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); ptr_end = ptr + btrfs_item_size(path->nodes[0], path->slots[0]); while (ptr < ptr_end) { struct btrfs_inode_ref *ref; ref = (struct btrfs_inode_ref *)ptr; name_len = btrfs_inode_ref_name_len(path->nodes[0], ref); ptr = (unsigned long)(ref + 1) + name_len; nlink++; } if (key.offset == 0) break; if (path->slots[0] > 0) { path->slots[0]--; goto process_slot; } key.offset--; btrfs_release_path(path); } btrfs_release_path(path); return nlink; } /* * There are a few corners where the link count of the file can't * be properly maintained during replay. So, instead of adding * lots of complexity to the log code, we just scan the backrefs * for any file that has been through replay. * * The scan will update the link count on the inode to reflect the * number of back refs found. If it goes down to zero, the iput * will free the inode. */ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, struct inode *inode) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; int ret; u64 nlink = 0; u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = count_inode_refs(BTRFS_I(inode), path); if (ret < 0) goto out; nlink = ret; ret = count_inode_extrefs(BTRFS_I(inode), path); if (ret < 0) goto out; nlink += ret; ret = 0; if (nlink != inode->i_nlink) { set_nlink(inode, nlink); ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) goto out; } BTRFS_I(inode)->index_cnt = (u64)-1; if (inode->i_nlink == 0) { if (S_ISDIR(inode->i_mode)) { ret = replay_dir_deletes(trans, root, NULL, path, ino, 1); if (ret) goto out; } ret = btrfs_insert_orphan_item(trans, root, ino); if (ret == -EEXIST) ret = 0; } out: btrfs_free_path(path); return ret; } static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path) { int ret; struct btrfs_key key; struct inode *inode; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) break; if (ret == 1) { ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID || key.type != BTRFS_ORPHAN_ITEM_KEY) break; ret = btrfs_del_item(trans, root, path); if (ret) break; btrfs_release_path(path); inode = read_one_inode(root, key.offset); if (!inode) { ret = -EIO; break; } ret = fixup_inode_link_count(trans, inode); iput(inode); if (ret) break; /* * fixup on a directory may create new entries, * make sure we always look for the highset possible * offset */ key.offset = (u64)-1; } btrfs_release_path(path); return ret; } /* * record a given inode in the fixup dir so we can check its link * count when replay is done. The link count is incremented here * so the inode won't go away until we check it */ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid) { struct btrfs_key key; int ret = 0; struct inode *inode; inode = read_one_inode(root, objectid); if (!inode) return -EIO; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = objectid; ret = btrfs_insert_empty_item(trans, root, path, &key, 0); btrfs_release_path(path); if (ret == 0) { if (!inode->i_nlink) set_nlink(inode, 1); else inc_nlink(inode); ret = btrfs_update_inode(trans, BTRFS_I(inode)); } else if (ret == -EEXIST) { ret = 0; } iput(inode); return ret; } /* * when replaying the log for a directory, we only insert names * for inodes that actually exist. This means an fsync on a directory * does not implicitly fsync all the new files in it */ static noinline int insert_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 dirid, u64 index, const struct fscrypt_str *name, struct btrfs_key *location) { struct inode *inode; struct inode *dir; int ret; inode = read_one_inode(root, location->objectid); if (!inode) return -ENOENT; dir = read_one_inode(root, dirid); if (!dir) { iput(inode); return -EIO; } ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, 1, index); /* FIXME, put inode into FIXUP list */ iput(inode); iput(dir); return ret; } static int delete_conflicting_dir_entry(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_path *path, struct btrfs_dir_item *dst_di, const struct btrfs_key *log_key, u8 log_flags, bool exists) { struct btrfs_key found_key; btrfs_dir_item_key_to_cpu(path->nodes[0], dst_di, &found_key); /* The existing dentry points to the same inode, don't delete it. */ if (found_key.objectid == log_key->objectid && found_key.type == log_key->type && found_key.offset == log_key->offset && btrfs_dir_flags(path->nodes[0], dst_di) == log_flags) return 1; /* * Don't drop the conflicting directory entry if the inode for the new * entry doesn't exist. */ if (!exists) return 0; return drop_one_dir_item(trans, path, dir, dst_di); } /* * take a single entry in a log directory item and replay it into * the subvolume. * * if a conflicting item exists in the subdirectory already, * the inode it points to is unlinked and put into the link count * fix up tree. * * If a name from the log points to a file or directory that does * not exist in the FS, it is skipped. fsyncs on directories * do not force down inodes inside that directory, just changes to the * names or unlinks in a directory. * * Returns < 0 on error, 0 if the name wasn't replayed (dentry points to a * non-existing inode) and 1 if the name was replayed. */ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, struct btrfs_dir_item *di, struct btrfs_key *key) { struct fscrypt_str name; struct btrfs_dir_item *dir_dst_di; struct btrfs_dir_item *index_dst_di; bool dir_dst_matches = false; bool index_dst_matches = false; struct btrfs_key log_key; struct btrfs_key search_key; struct inode *dir; u8 log_flags; bool exists; int ret; bool update_size = true; bool name_added = false; dir = read_one_inode(root, key->objectid); if (!dir) return -EIO; ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); if (ret) goto out; log_flags = btrfs_dir_flags(eb, di); btrfs_dir_item_key_to_cpu(eb, di, &log_key); ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); if (ret < 0) goto out; exists = (ret == 0); ret = 0; dir_dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid, &name, 1); if (IS_ERR(dir_dst_di)) { ret = PTR_ERR(dir_dst_di); goto out; } else if (dir_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, dir_dst_di, &log_key, log_flags, exists); if (ret < 0) goto out; dir_dst_matches = (ret == 1); } btrfs_release_path(path); index_dst_di = btrfs_lookup_dir_index_item(trans, root, path, key->objectid, key->offset, &name, 1); if (IS_ERR(index_dst_di)) { ret = PTR_ERR(index_dst_di); goto out; } else if (index_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, index_dst_di, &log_key, log_flags, exists); if (ret < 0) goto out; index_dst_matches = (ret == 1); } btrfs_release_path(path); if (dir_dst_matches && index_dst_matches) { ret = 0; update_size = false; goto out; } /* * Check if the inode reference exists in the log for the given name, * inode and parent inode */ search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = key->objectid; ret = backref_in_log(root->log_root, &search_key, 0, &name); if (ret < 0) { goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = key->objectid; ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } btrfs_release_path(path); ret = insert_one_name(trans, root, key->objectid, key->offset, &name, &log_key); if (ret && ret != -ENOENT && ret != -EEXIST) goto out; if (!ret) name_added = true; update_size = false; ret = 0; out: if (!ret && update_size) { btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name.len * 2); ret = btrfs_update_inode(trans, BTRFS_I(dir)); } kfree(name.name); iput(dir); if (!ret && name_added) ret = 1; return ret; } /* Replay one dir item from a BTRFS_DIR_INDEX_KEY key. */ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { int ret; struct btrfs_dir_item *di; /* We only log dir index keys, which only contain a single dir item. */ ASSERT(key->type == BTRFS_DIR_INDEX_KEY); di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); ret = replay_one_name(trans, root, path, eb, di, key); if (ret < 0) return ret; /* * If this entry refers to a non-directory (directories can not have a * link count > 1) and it was added in the transaction that was not * committed, make sure we fixup the link count of the inode the entry * points to. Otherwise something like the following would result in a * directory pointing to an inode with a wrong link that does not account * for this dir entry: * * mkdir testdir * touch testdir/foo * touch testdir/bar * sync * * ln testdir/bar testdir/bar_link * ln testdir/foo testdir/foo_link * xfs_io -c "fsync" testdir/bar * * <power failure> * * mount fs, log replay happens * * File foo would remain with a link count of 1 when it has two entries * pointing to it in the directory testdir. This would make it impossible * to ever delete the parent directory has it would result in stale * dentries that can never be deleted. */ if (ret == 1 && btrfs_dir_ftype(eb, di) != BTRFS_FT_DIR) { struct btrfs_path *fixup_path; struct btrfs_key di_key; fixup_path = btrfs_alloc_path(); if (!fixup_path) return -ENOMEM; btrfs_dir_item_key_to_cpu(eb, di, &di_key); ret = link_to_fixup_dir(trans, root, fixup_path, di_key.objectid); btrfs_free_path(fixup_path); } return ret; } /* * directory replay has two parts. There are the standard directory * items in the log copied from the subvolume, and range items * created in the log while the subvolume was logged. * * The range items tell us which parts of the key space the log * is authoritative for. During replay, if a key in the subvolume * directory is in a logged range item, but not actually in the log * that means it was deleted from the directory before the fsync * and should be removed. */ static noinline int find_dir_range(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 *start_ret, u64 *end_ret) { struct btrfs_key key; u64 found_end; struct btrfs_dir_log_item *item; int ret; int nritems; if (*start_ret == (u64)-1) return 1; key.objectid = dirid; key.type = BTRFS_DIR_LOG_INDEX_KEY; key.offset = *start_ret; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret > 0) { if (path->slots[0] == 0) goto out; path->slots[0]--; } if (ret != 0) btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto next; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); if (*start_ret >= key.offset && *start_ret <= found_end) { ret = 0; *start_ret = key.offset; *end_ret = found_end; goto out; } ret = 1; next: /* check the next slot in the tree to see if it is a valid item */ nritems = btrfs_header_nritems(path->nodes[0]); path->slots[0]++; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) goto out; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto out; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); *start_ret = key.offset; *end_ret = found_end; ret = 0; out: btrfs_release_path(path); return ret; } /* * this looks for a given directory item in the log. If the directory * item is not in the log, the item is removed and the inode it points * to is unlinked */ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_path *log_path, struct inode *dir, struct btrfs_key *dir_key) { struct btrfs_root *root = BTRFS_I(dir)->root; int ret; struct extent_buffer *eb; int slot; struct btrfs_dir_item *di; struct fscrypt_str name; struct inode *inode = NULL; struct btrfs_key location; /* * Currently we only log dir index keys. Even if we replay a log created * by an older kernel that logged both dir index and dir item keys, all * we need to do is process the dir index keys, we (and our caller) can * safely ignore dir item keys (key type BTRFS_DIR_ITEM_KEY). */ ASSERT(dir_key->type == BTRFS_DIR_INDEX_KEY); eb = path->nodes[0]; slot = path->slots[0]; di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); if (ret) goto out; if (log) { struct btrfs_dir_item *log_di; log_di = btrfs_lookup_dir_index_item(trans, log, log_path, dir_key->objectid, dir_key->offset, &name, 0); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); goto out; } else if (log_di) { /* The dentry exists in the log, we have nothing to do. */ ret = 0; goto out; } } btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); inode = read_one_inode(root, location.objectid); if (!inode) { ret = -EIO; goto out; } ret = link_to_fixup_dir(trans, root, path, location.objectid); if (ret) goto out; inc_nlink(inode); ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), BTRFS_I(inode), &name); /* * Unlike dir item keys, dir index keys can only have one name (entry) in * them, as there are no key collisions since each key has a unique offset * (an index number), so we're done. */ out: btrfs_release_path(path); btrfs_release_path(log_path); kfree(name.name); iput(inode); return ret; } static int replay_xattr_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, const u64 ino) { struct btrfs_key search_key; struct btrfs_path *log_path; int i; int nritems; int ret; log_path = btrfs_alloc_path(); if (!log_path) return -ENOMEM; search_key.objectid = ino; search_key.type = BTRFS_XATTR_ITEM_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto out; process_leaf: nritems = btrfs_header_nritems(path->nodes[0]); for (i = path->slots[0]; i < nritems; i++) { struct btrfs_key key; struct btrfs_dir_item *di; struct btrfs_dir_item *log_di; u32 total_size; u32 cur; btrfs_item_key_to_cpu(path->nodes[0], &key, i); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) { ret = 0; goto out; } di = btrfs_item_ptr(path->nodes[0], i, struct btrfs_dir_item); total_size = btrfs_item_size(path->nodes[0], i); cur = 0; while (cur < total_size) { u16 name_len = btrfs_dir_name_len(path->nodes[0], di); u16 data_len = btrfs_dir_data_len(path->nodes[0], di); u32 this_len = sizeof(*di) + name_len + data_len; char *name; name = kmalloc(name_len, GFP_NOFS); if (!name) { ret = -ENOMEM; goto out; } read_extent_buffer(path->nodes[0], name, (unsigned long)(di + 1), name_len); log_di = btrfs_lookup_xattr(NULL, log, log_path, ino, name, name_len, 0); btrfs_release_path(log_path); if (!log_di) { /* Doesn't exist in log tree, so delete it. */ btrfs_release_path(path); di = btrfs_lookup_xattr(trans, root, path, ino, name, name_len, -1); kfree(name); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } ASSERT(di); ret = btrfs_delete_one_dir_name(trans, root, path, di); if (ret) goto out; btrfs_release_path(path); search_key = key; goto again; } kfree(name); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); goto out; } cur += this_len; di = (struct btrfs_dir_item *)((char *)di + this_len); } } ret = btrfs_next_leaf(root, path); if (ret > 0) ret = 0; else if (ret == 0) goto process_leaf; out: btrfs_free_path(log_path); btrfs_release_path(path); return ret; } /* * deletion replay happens before we copy any new directory items * out of the log or out of backreferences from inodes. It * scans the log to find ranges of keys that log is authoritative for, * and then scans the directory to find items in those ranges that are * not present in the log. * * Anything we don't find in the log is unlinked and removed from the * directory. */ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all) { u64 range_start; u64 range_end; int ret = 0; struct btrfs_key dir_key; struct btrfs_key found_key; struct btrfs_path *log_path; struct inode *dir; dir_key.objectid = dirid; dir_key.type = BTRFS_DIR_INDEX_KEY; log_path = btrfs_alloc_path(); if (!log_path) return -ENOMEM; dir = read_one_inode(root, dirid); /* it isn't an error if the inode isn't there, that can happen * because we replay the deletes before we copy in the inode item * from the log */ if (!dir) { btrfs_free_path(log_path); return 0; } range_start = 0; range_end = 0; while (1) { if (del_all) range_end = (u64)-1; else { ret = find_dir_range(log, path, dirid, &range_start, &range_end); if (ret < 0) goto out; else if (ret > 0) break; } dir_key.offset = range_start; while (1) { int nritems; ret = btrfs_search_slot(NULL, root, &dir_key, path, 0, 0); if (ret < 0) goto out; nritems = btrfs_header_nritems(path->nodes[0]); if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret == 1) break; else if (ret < 0) goto out; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != dirid || found_key.type != dir_key.type) { ret = 0; goto out; } if (found_key.offset > range_end) break; ret = check_item_in_log(trans, log, path, log_path, dir, &found_key); if (ret) goto out; if (found_key.offset == (u64)-1) break; dir_key.offset = found_key.offset + 1; } btrfs_release_path(path); if (range_end == (u64)-1) break; range_start = range_end + 1; } ret = 0; out: btrfs_release_path(path); btrfs_free_path(log_path); iput(dir); return ret; } /* * the process_func used to replay items from the log tree. This * gets called in two different stages. The first stage just looks * for inodes and makes sure they are all copied into the subvolume. * * The second stage copies all the other item types from the log into * the subvolume. The two stage approach is slower, but gets rid of * lots of complexity around inodes referencing other inodes that exist * only in the log (references come from either directory items or inode * back refs). */ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { int nritems; struct btrfs_tree_parent_check check = { .transid = gen, .level = level }; struct btrfs_path *path; struct btrfs_root *root = wc->replay_dest; struct btrfs_key key; int i; int ret; ret = btrfs_read_extent_buffer(eb, &check); if (ret) return ret; level = btrfs_header_level(eb); if (level != 0) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; nritems = btrfs_header_nritems(eb); for (i = 0; i < nritems; i++) { btrfs_item_key_to_cpu(eb, &key, i); /* inode keys are done during the first stage */ if (key.type == BTRFS_INODE_ITEM_KEY && wc->stage == LOG_WALK_REPLAY_INODES) { struct btrfs_inode_item *inode_item; u32 mode; inode_item = btrfs_item_ptr(eb, i, struct btrfs_inode_item); /* * If we have a tmpfile (O_TMPFILE) that got fsync'ed * and never got linked before the fsync, skip it, as * replaying it is pointless since it would be deleted * later. We skip logging tmpfiles, but it's always * possible we are replaying a log created with a kernel * that used to log tmpfiles. */ if (btrfs_inode_nlink(eb, inode_item) == 0) { wc->ignore_cur_inode = true; continue; } else { wc->ignore_cur_inode = false; } ret = replay_xattr_deletes(wc->trans, root, log, path, key.objectid); if (ret) break; mode = btrfs_inode_mode(eb, inode_item); if (S_ISDIR(mode)) { ret = replay_dir_deletes(wc->trans, root, log, path, key.objectid, 0); if (ret) break; } ret = overwrite_item(wc->trans, root, path, eb, i, &key); if (ret) break; /* * Before replaying extents, truncate the inode to its * size. We need to do it now and not after log replay * because before an fsync we can have prealloc extents * added beyond the inode's i_size. If we did it after, * through orphan cleanup for example, we would drop * those prealloc extents just after replaying them. */ if (S_ISREG(mode)) { struct btrfs_drop_extents_args drop_args = { 0 }; struct inode *inode; u64 from; inode = read_one_inode(root, key.objectid); if (!inode) { ret = -EIO; break; } from = ALIGN(i_size_read(inode), root->fs_info->sectorsize); drop_args.start = from; drop_args.end = (u64)-1; drop_args.drop_cache = true; ret = btrfs_drop_extents(wc->trans, root, BTRFS_I(inode), &drop_args); if (!ret) { inode_sub_bytes(inode, drop_args.bytes_found); /* Update the inode's nbytes. */ ret = btrfs_update_inode(wc->trans, BTRFS_I(inode)); } iput(inode); if (ret) break; } ret = link_to_fixup_dir(wc->trans, root, path, key.objectid); if (ret) break; } if (wc->ignore_cur_inode) continue; if (key.type == BTRFS_DIR_INDEX_KEY && wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) break; } if (wc->stage < LOG_WALK_REPLAY_ALL) continue; /* these keys are simply copied */ if (key.type == BTRFS_XATTR_ITEM_KEY) { ret = overwrite_item(wc->trans, root, path, eb, i, &key); if (ret) break; } else if (key.type == BTRFS_INODE_REF_KEY || key.type == BTRFS_INODE_EXTREF_KEY) { ret = add_inode_ref(wc->trans, root, log, path, eb, i, &key); if (ret && ret != -ENOENT) break; ret = 0; } else if (key.type == BTRFS_EXTENT_DATA_KEY) { ret = replay_one_extent(wc->trans, root, path, eb, i, &key); if (ret) break; } /* * We don't log BTRFS_DIR_ITEM_KEY keys anymore, only the * BTRFS_DIR_INDEX_KEY items which we use to derive the * BTRFS_DIR_ITEM_KEY items. If we are replaying a log from an * older kernel with such keys, ignore them. */ } btrfs_free_path(path); return ret; } /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); return; } spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->reserved -= fs_info->nodesize; cache->space_info->bytes_reserved -= fs_info->nodesize; spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { int ret; btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); if (trans) { ret = btrfs_pin_reserved_extent(trans, eb); if (ret) return ret; } else { unaccount_log_buffer(eb->fs_info, eb->start); } return 0; } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int *level, struct walk_control *wc) { struct btrfs_fs_info *fs_info = root->fs_info; u64 bytenr; u64 ptr_gen; struct extent_buffer *next; struct extent_buffer *cur; int ret = 0; while (*level > 0) { struct btrfs_tree_parent_check check = { 0 }; cur = path->nodes[*level]; WARN_ON(btrfs_header_level(cur) != *level); if (path->slots[*level] >= btrfs_header_nritems(cur)) break; bytenr = btrfs_node_blockptr(cur, path->slots[*level]); ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]); check.transid = ptr_gen; check.level = *level - 1; check.has_first_key = true; btrfs_node_key_to_cpu(cur, &check.first_key, path->slots[*level]); next = btrfs_find_create_tree_block(fs_info, bytenr, btrfs_header_owner(cur), *level - 1); if (IS_ERR(next)) return PTR_ERR(next); if (*level == 1) { ret = wc->process_func(root, next, wc, ptr_gen, *level - 1); if (ret) { free_extent_buffer(next); return ret; } path->slots[*level]++; if (wc->free) { ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); return ret; } ret = clean_log_buffer(trans, next); if (ret) { free_extent_buffer(next); return ret; } } free_extent_buffer(next); continue; } ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); return ret; } if (path->nodes[*level-1]) free_extent_buffer(path->nodes[*level-1]); path->nodes[*level-1] = next; *level = btrfs_header_level(next); path->slots[*level] = 0; cond_resched(); } path->slots[*level] = btrfs_header_nritems(path->nodes[*level]); cond_resched(); return 0; } static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int *level, struct walk_control *wc) { int i; int slot; int ret; for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) { slot = path->slots[i]; if (slot + 1 < btrfs_header_nritems(path->nodes[i])) { path->slots[i]++; *level = i; WARN_ON(*level == 0); return 0; } else { ret = wc->process_func(root, path->nodes[*level], wc, btrfs_header_generation(path->nodes[*level]), *level); if (ret) return ret; if (wc->free) { ret = clean_log_buffer(trans, path->nodes[*level]); if (ret) return ret; } free_extent_buffer(path->nodes[*level]); path->nodes[*level] = NULL; *level = i + 1; } } return 1; } /* * drop the reference count on the tree rooted at 'snap'. This traverses * the tree freeing any blocks that have a ref count of zero after being * decremented. */ static int walk_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct walk_control *wc) { int ret = 0; int wret; int level; struct btrfs_path *path; int orig_level; path = btrfs_alloc_path(); if (!path) return -ENOMEM; level = btrfs_header_level(log->node); orig_level = level; path->nodes[level] = log->node; atomic_inc(&log->node->refs); path->slots[level] = 0; while (1) { wret = walk_down_log_tree(trans, log, path, &level, wc); if (wret > 0) break; if (wret < 0) { ret = wret; goto out; } wret = walk_up_log_tree(trans, log, path, &level, wc); if (wret > 0) break; if (wret < 0) { ret = wret; goto out; } } /* was the root node processed? if not, catch it here */ if (path->nodes[orig_level]) { ret = wc->process_func(log, path->nodes[orig_level], wc, btrfs_header_generation(path->nodes[orig_level]), orig_level); if (ret) goto out; if (wc->free) ret = clean_log_buffer(trans, path->nodes[orig_level]); } out: btrfs_free_path(path); return ret; } /* * helper function to update the item for a given subvolumes log root * in the tree of log roots */ static int update_log_root(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_root_item *root_item) { struct btrfs_fs_info *fs_info = log->fs_info; int ret; if (log->log_transid == 1) { /* insert root item on the first sync */ ret = btrfs_insert_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } else { ret = btrfs_update_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } return ret; } static void wait_log_commit(struct btrfs_root *root, int transid) { DEFINE_WAIT(wait); int index = transid % 2; /* * we only allow two pending log transactions at a time, * so we know that if ours is more than 2 older than the * current transaction, we're done */ for (;;) { prepare_to_wait(&root->log_commit_wait[index], &wait, TASK_UNINTERRUPTIBLE); if (!(root->log_transid_committed < transid && atomic_read(&root->log_commit[index]))) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_commit_wait[index], &wait); } static void wait_for_writer(struct btrfs_root *root) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&root->log_writer_wait, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_read(&root->log_writers)) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_writer_wait, &wait); } void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->log_new_dentries = false; ctx->logging_new_name = false; ctx->logging_new_delayed_dentries = false; ctx->logged_before = false; ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); INIT_LIST_HEAD(&ctx->ordered_extents); INIT_LIST_HEAD(&ctx->conflict_inodes); ctx->num_conflict_inodes = 0; ctx->logging_conflict_inodes = false; ctx->scratch_eb = NULL; } void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx) { struct btrfs_inode *inode = BTRFS_I(ctx->inode); if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return; /* * Don't care about allocation failure. This is just for optimization, * if we fail to allocate here, we will try again later if needed. */ ctx->scratch_eb = alloc_dummy_extent_buffer(inode->root->fs_info, 0); } void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; ASSERT(inode_is_locked(ctx->inode)); list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); btrfs_put_ordered_extent(ordered); } } static inline void btrfs_remove_log_ctx(struct btrfs_root *root, struct btrfs_log_ctx *ctx) { mutex_lock(&root->log_mutex); list_del_init(&ctx->list); mutex_unlock(&root->log_mutex); } /* * Invoked in log mutex context, or be sure there is no other task which * can access the list. */ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; struct btrfs_log_ctx *safe; list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { list_del_init(&ctx->list); ctx->log_ret = error; } } /* * Sends a given tree log down to the disk and updates the super blocks to * record it. When this call is done, you know that any inodes previously * logged are safely on disk only if it returns 0. * * Any other return value means you need to call btrfs_commit_transaction. * Some of the edge cases for fsyncing directories that have had unlinks * or renames done in the past mean that sometimes the only safe * fsync is to commit the whole FS. When btrfs_sync_log returns -EAGAIN, * that has happened. */ int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int index1; int index2; int mark; int ret; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log = root->log_root; struct btrfs_root *log_root_tree = fs_info->log_root_tree; struct btrfs_root_item new_root_item; int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; u64 log_root_start; u64 log_root_level; mutex_lock(&root->log_mutex); log_transid = ctx->log_transid; if (root->log_transid_committed >= log_transid) { mutex_unlock(&root->log_mutex); return ctx->log_ret; } index1 = log_transid % 2; if (atomic_read(&root->log_commit[index1])) { wait_log_commit(root, log_transid); mutex_unlock(&root->log_mutex); return ctx->log_ret; } ASSERT(log_transid == root->log_transid); atomic_set(&root->log_commit[index1], 1); /* wait for previous tree log sync to complete */ if (atomic_read(&root->log_commit[(index1 + 1) % 2])) wait_log_commit(root, log_transid - 1); while (1) { int batch = atomic_read(&root->log_batch); /* when we're on an ssd, just kick the log commit out */ if (!btrfs_test_opt(fs_info, SSD) && test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) { mutex_unlock(&root->log_mutex); schedule_timeout_uninterruptible(1); mutex_lock(&root->log_mutex); } wait_for_writer(root); if (batch == atomic_read(&root->log_batch)) break; } /* bail out if we need to do a full commit */ if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; mutex_unlock(&root->log_mutex); goto out; } if (log_transid % 2 == 0) mark = EXTENT_DIRTY; else mark = EXTENT_NEW; /* we start IO on all the marked extents here, but we don't actually * wait for them until later. */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); /* * -EAGAIN happens when someone, e.g., a concurrent transaction * commit, writes a dirty extent in this tree-log commit. This * concurrent write will create a hole writing out the extents, * and we cannot proceed on a zoned filesystem, requiring * sequential writing. While we can bail out to a full commit * here, but we can continue hoping the concurrent writing fills * the hole. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; } /* * We _must_ update under the root->log_mutex in order to make sure we * have a consistent view of the log root we are trying to commit at * this moment. * * We _must_ copy this into a local copy, because we are not holding the * log_root_tree->log_mutex yet. This is important because when we * commit the log_root_tree we must have a consistent view of the * log_root_tree when we update the super block to point at the * log_root_tree bytenr. If we update the log_root_tree here we'll race * with the commit and possibly point at the new block which we may not * have written out. */ btrfs_set_root_node(&log->root_item, log->node); memcpy(&new_root_item, &log->root_item, sizeof(new_root_item)); btrfs_set_root_log_transid(root, root->log_transid + 1); log->log_transid = root->log_transid; root->log_start_pid = 0; /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. */ mutex_unlock(&root->log_mutex); if (btrfs_is_zoned(fs_info)) { mutex_lock(&fs_info->tree_root->log_mutex); if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); blk_finish_plug(&plug); goto out; } } mutex_unlock(&fs_info->tree_root->log_mutex); } btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); index2 = log_root_tree->log_transid % 2; list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit * open until we drop the log_mutex. */ ret = update_log_root(trans, log, &new_root_item); if (ret) { list_del_init(&root_log_ctx.list); blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); if (ret != -ENOSPC) btrfs_err(fs_info, "failed to update log for root %llu ret %d", btrfs_root_id(root), ret); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out; } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; } if (atomic_read(&log_root_tree->log_commit[index2])) { blk_finish_plug(&plug); ret = btrfs_wait_tree_log_extents(log, mark); wait_log_commit(log_root_tree, root_log_ctx.log_transid); mutex_unlock(&log_root_tree->log_mutex); if (!ret) ret = root_log_ctx.log_ret; goto out; } ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid); atomic_set(&log_root_tree->log_commit[index2], 1); if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) { wait_log_commit(log_root_tree, root_log_ctx.log_transid - 1); } /* * now that we've moved on to the tree of log tree roots, * check the full commit flag again */ if (btrfs_need_log_full_commit(trans)) { blk_finish_plug(&plug); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); ret = BTRFS_LOG_FORCE_COMMIT; goto out_wake_log_root; } ret = btrfs_write_marked_extents(fs_info, &log_root_tree->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); /* * As described above, -EAGAIN indicates a hole in the extents. We * cannot wait for these write outs since the waiting cause a * deadlock. Bail out to the full commit instead. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { btrfs_set_log_full_commit(trans); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } else if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } ret = btrfs_wait_tree_log_extents(log, mark); if (!ret) ret = btrfs_wait_tree_log_extents(log_root_tree, EXTENT_NEW | EXTENT_DIRTY); if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } log_root_start = log_root_tree->node->start; log_root_level = btrfs_header_level(log_root_tree->node); log_root_tree->log_transid++; mutex_unlock(&log_root_tree->log_mutex); /* * Here we are guaranteed that nobody is going to write the superblock * for the current transaction before us and that neither we do write * our superblock before the previous transaction finishes its commit * and writes its superblock, because: * * 1) We are holding a handle on the current transaction, so no body * can commit it until we release the handle; * * 2) Before writing our superblock we acquire the tree_log_mutex, so * if the previous transaction is still committing, and hasn't yet * written its superblock, we wait for it to do it, because a * transaction commit acquires the tree_log_mutex when the commit * begins and releases it only after writing its superblock. */ mutex_lock(&fs_info->tree_log_mutex); /* * The previous transaction writeout phase could have failed, and thus * marked the fs in an error state. We must not commit here, as we * could have updated our generation in the super_for_commit and * writing the super here would result in transid mismatches. If there * is an error here just bail. */ if (BTRFS_FS_ERROR(fs_info)) { ret = -EIO; btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&fs_info->tree_log_mutex); goto out_wake_log_root; } btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start); btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level); ret = write_all_supers(fs_info, 1); mutex_unlock(&fs_info->tree_log_mutex); if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); goto out_wake_log_root; } /* * We know there can only be one task here, since we have not yet set * root->log_commit[index1] to 0 and any task attempting to sync the * log must wait for the previous log transaction to commit if it's * still in progress or wait for the current log transaction commit if * someone else already started it. We use <= and not < because the * first log transaction has an ID of 0. */ ASSERT(btrfs_get_root_last_log_commit(root) <= log_transid); btrfs_set_root_last_log_commit(root, log_transid); out_wake_log_root: mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&log_root_tree->log_commit_wait[index2]); out: mutex_lock(&root->log_mutex); btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&root->log_commit_wait[index1]); return ret; } static void free_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *log) { int ret; struct walk_control wc = { .free = 1, .process_func = process_one_buffer }; if (log->node) { ret = walk_log_tree(trans, log, &wc); if (ret) { /* * We weren't able to traverse the entire log tree, the * typical scenario is getting an -EIO when reading an * extent buffer of the tree, due to a previous writeback * failure of it. */ set_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, &log->fs_info->fs_state); /* * Some extent buffers of the log tree may still be dirty * and not yet written back to storage, because we may * have updates to a log tree without syncing a log tree, * such as during rename and link operations. So flush * them out and wait for their writeback to complete, so * that we properly cleanup their state and pages. */ btrfs_write_marked_extents(log->fs_info, &log->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); btrfs_wait_tree_log_extents(log, EXTENT_DIRTY | EXTENT_NEW); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(log->fs_info, ret, NULL); } } extent_io_tree_release(&log->dirty_log_pages); extent_io_tree_release(&log->log_csum_range); btrfs_put_root(log); } /* * free all the extents used by the tree log. This should be called * at commit time of the full transaction */ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) { if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { if (fs_info->log_root_tree) { free_log_tree(trans, fs_info->log_root_tree); fs_info->log_root_tree = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &fs_info->tree_root->state); } return 0; } /* * Check if an inode was logged in the current transaction. This correctly deals * with the case where the inode was logged but has a logged_trans of 0, which * happens if the inode is evicted and loaded again, as logged_trans is an in * memory only field (not persisted). * * Returns 1 if the inode was logged before in the transaction, 0 if it was not, * and < 0 on error. */ static int inode_logged(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path_in) { struct btrfs_path *path = path_in; struct btrfs_key key; int ret; if (inode->logged_trans == trans->transid) return 1; /* * If logged_trans is not 0, then we know the inode logged was not logged * in this transaction, so we can return false right away. */ if (inode->logged_trans > 0) return 0; /* * If no log tree was created for this root in this transaction, then * the inode can not have been logged in this transaction. In that case * set logged_trans to anything greater than 0 and less than the current * transaction's ID, to avoid the search below in a future call in case * a log tree gets created after this. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) { inode->logged_trans = trans->transid - 1; return 0; } /* * We have a log tree and the inode's logged_trans is 0. We can't tell * for sure if the inode was logged before in this transaction by looking * only at logged_trans. We could be pessimistic and assume it was, but * that can lead to unnecessarily logging an inode during rename and link * operations, and then further updating the log in followup rename and * link operations, specially if it's a directory, which adds latency * visible to applications doing a series of rename or link operations. * * A logged_trans of 0 here can mean several things: * * 1) The inode was never logged since the filesystem was mounted, and may * or may have not been evicted and loaded again; * * 2) The inode was logged in a previous transaction, then evicted and * then loaded again; * * 3) The inode was logged in the current transaction, then evicted and * then loaded again. * * For cases 1) and 2) we don't want to return true, but we need to detect * case 3) and return true. So we do a search in the log root for the inode * item. */ key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; if (!path) { path = btrfs_alloc_path(); if (!path) return -ENOMEM; } ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); if (path_in) btrfs_release_path(path); else btrfs_free_path(path); /* * Logging an inode always results in logging its inode item. So if we * did not find the item we know the inode was not logged for sure. */ if (ret < 0) { return ret; } else if (ret > 0) { /* * Set logged_trans to a value greater than 0 and less then the * current transaction to avoid doing the search in future calls. */ inode->logged_trans = trans->transid - 1; return 0; } /* * The inode was previously logged and then evicted, set logged_trans to * the current transacion's ID, to avoid future tree searches as long as * the inode is not evicted again. */ inode->logged_trans = trans->transid; /* * If it's a directory, then we must set last_dir_index_offset to the * maximum possible value, so that the next attempt to log the inode does * not skip checking if dir index keys found in modified subvolume tree * leaves have been logged before, otherwise it would result in attempts * to insert duplicate dir index keys in the log tree. This must be done * because last_dir_index_offset is an in-memory only field, not persisted * in the inode item or any other on-disk structure, so its value is lost * once the inode is evicted. */ if (S_ISDIR(inode->vfs_inode.i_mode)) inode->last_dir_index_offset = (u64)-1; return 1; } /* * Delete a directory entry from the log if it exists. * * Returns < 0 on error * 1 if the entry does not exists * 0 if the entry existed and was successfully deleted */ static int del_logged_dentry(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dir_ino, const struct fscrypt_str *name, u64 index) { struct btrfs_dir_item *di; /* * We only log dir index items of a directory, so we don't need to look * for dir item keys. */ di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino, index, name, -1); if (IS_ERR(di)) return PTR_ERR(di); else if (!di) return 1; /* * We do not need to update the size field of the directory's * inode item because on log replay we update the field to reflect * all existing entries in the directory (see overwrite_item()). */ return btrfs_delete_one_dir_name(trans, log, path, di); } /* * If both a file and directory are logged, and unlinks or renames are * mixed in, we have a few interesting corners: * * create file X in dir Y * link file X to X.link in dir Y * fsync file X * unlink file X but leave X.link * fsync dir Y * * After a crash we would expect only X.link to exist. But file X * didn't get fsync'd again so the log has back refs for X and X.link. * * We solve this by removing directory entries and inode backrefs from the * log when a file that was logged in the current transaction is * unlinked. Any later fsync will include the updated log entries, and * we'll be able to reconstruct the proper directory items from backrefs. * * This optimizations allows us to avoid relogging the entire inode * or the entire directory. */ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index) { struct btrfs_path *path; int ret; ret = inode_logged(trans, dir, NULL); if (ret == 0) return; else if (ret < 0) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); if (ret) return; mutex_lock(&dir->log_mutex); path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out_unlock; } ret = del_logged_dentry(trans, root->log_root, path, btrfs_ino(dir), name, index); btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); if (ret < 0) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* see comments for btrfs_del_dir_entries_in_log */ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid) { struct btrfs_root *log; u64 index; int ret; ret = inode_logged(trans, inode, NULL); if (ret == 0) return; else if (ret < 0) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); if (ret) return; log = root->log_root; mutex_lock(&inode->log_mutex); ret = btrfs_del_inode_ref(trans, log, name, btrfs_ino(inode), dirid, &index); mutex_unlock(&inode->log_mutex); if (ret < 0 && ret != -ENOENT) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* * creates a range item in the log for 'dirid'. first_offset and * last_offset tell us which parts of the key space the log should * be considered authoritative for. */ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, u64 first_offset, u64 last_offset) { int ret; struct btrfs_key key; struct btrfs_dir_log_item *item; key.objectid = dirid; key.offset = first_offset; key.type = BTRFS_DIR_LOG_INDEX_KEY; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); /* * -EEXIST is fine and can happen sporadically when we are logging a * directory and have concurrent insertions in the subvolume's tree for * items from other inodes and that result in pushing off some dir items * from one leaf to another in order to accommodate for the new items. * This results in logging the same dir index range key. */ if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); if (ret == -EEXIST) { const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); /* * btrfs_del_dir_entries_in_log() might have been called during * an unlink between the initial insertion of this key and the * current update, or we might be logging a single entry deletion * during a rename, so set the new last_offset to the max value. */ last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } static int flush_dir_items_batch(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct extent_buffer *src, struct btrfs_path *dst_path, int start_slot, int count) { struct btrfs_root *log = inode->root->log_root; char *ins_data = NULL; struct btrfs_item_batch batch; struct extent_buffer *dst; unsigned long src_offset; unsigned long dst_offset; u64 last_index; struct btrfs_key key; u32 item_size; int ret; int i; ASSERT(count > 0); batch.nr = count; if (count == 1) { btrfs_item_key_to_cpu(src, &key, start_slot); item_size = btrfs_item_size(src, start_slot); batch.keys = &key; batch.data_sizes = &item_size; batch.total_data_size = item_size; } else { struct btrfs_key *ins_keys; u32 *ins_sizes; ins_data = kmalloc(count * sizeof(u32) + count * sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + count * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; for (i = 0; i < count; i++) { const int slot = start_slot + i; btrfs_item_key_to_cpu(src, &ins_keys[i], slot); ins_sizes[i] = btrfs_item_size(src, slot); batch.total_data_size += ins_sizes[i]; } } ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst = dst_path->nodes[0]; /* * Copy all the items in bulk, in a single copy operation. Item data is * organized such that it's placed at the end of a leaf and from right * to left. For example, the data for the second item ends at an offset * that matches the offset where the data for the first item starts, the * data for the third item ends at an offset that matches the offset * where the data of the second items starts, and so on. * Therefore our source and destination start offsets for copy match the * offsets of the last items (highest slots). */ dst_offset = btrfs_item_ptr_offset(dst, dst_path->slots[0] + count - 1); src_offset = btrfs_item_ptr_offset(src, start_slot + count - 1); copy_extent_buffer(dst, src, dst_offset, src_offset, batch.total_data_size); btrfs_release_path(dst_path); last_index = batch.keys[count - 1].offset; ASSERT(last_index > inode->last_dir_index_offset); /* * If for some unexpected reason the last item's index is not greater * than the last index we logged, warn and force a transaction commit. */ if (WARN_ON(last_index <= inode->last_dir_index_offset)) ret = BTRFS_LOG_FORCE_COMMIT; else inode->last_dir_index_offset = last_index; if (btrfs_get_first_dir_index_to_log(inode) == 0) btrfs_set_first_dir_index_to_log(inode, batch.keys[0].offset); out: kfree(ins_data); return ret; } static int clone_leaf(struct btrfs_path *path, struct btrfs_log_ctx *ctx) { const int slot = path->slots[0]; if (ctx->scratch_eb) { copy_extent_buffer_full(ctx->scratch_eb, path->nodes[0]); } else { ctx->scratch_eb = btrfs_clone_extent_buffer(path->nodes[0]); if (!ctx->scratch_eb) return -ENOMEM; } btrfs_release_path(path); path->nodes[0] = ctx->scratch_eb; path->slots[0] = slot; /* * Add extra ref to scratch eb so that it is not freed when callers * release the path, so we can reuse it later if needed. */ atomic_inc(&ctx->scratch_eb->refs); return 0; } static int process_dir_items_leaf(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 *last_old_dentry_offset) { struct btrfs_root *log = inode->root->log_root; struct extent_buffer *src; const int nritems = btrfs_header_nritems(path->nodes[0]); const u64 ino = btrfs_ino(inode); bool last_found = false; int batch_start = 0; int batch_size = 0; int ret; /* * We need to clone the leaf, release the read lock on it, and use the * clone before modifying the log tree. See the comment at copy_items() * about why we need to do this. */ ret = clone_leaf(path, ctx); if (ret < 0) return ret; src = path->nodes[0]; for (int i = path->slots[0]; i < nritems; i++) { struct btrfs_dir_item *di; struct btrfs_key key; int ret; btrfs_item_key_to_cpu(src, &key, i); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY) { last_found = true; break; } di = btrfs_item_ptr(src, i, struct btrfs_dir_item); /* * Skip ranges of items that consist only of dir item keys created * in past transactions. However if we find a gap, we must log a * dir index range item for that gap, so that index keys in that * gap are deleted during log replay. */ if (btrfs_dir_transid(src, di) < trans->transid) { if (key.offset > *last_old_dentry_offset + 1) { ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); if (ret < 0) return ret; } *last_old_dentry_offset = key.offset; continue; } /* If we logged this dir index item before, we can skip it. */ if (key.offset <= inode->last_dir_index_offset) continue; /* * We must make sure that when we log a directory entry, the * corresponding inode, after log replay, has a matching link * count. For example: * * touch foo * mkdir mydir * sync * ln foo mydir/bar * xfs_io -c "fsync" mydir * <crash> * <mount fs and log replay> * * Would result in a fsync log that when replayed, our file inode * would have a link count of 1, but we get two directory entries * pointing to the same inode. After removing one of the names, * it would not be possible to remove the other name, which * resulted always in stale file handle errors, and would not be * possible to rmdir the parent directory, since its i_size could * never be decremented to the value BTRFS_EMPTY_DIR_SIZE, * resulting in -ENOTEMPTY errors. */ if (!ctx->log_new_dentries) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(src, di, &di_key); if (di_key.type != BTRFS_ROOT_ITEM_KEY) ctx->log_new_dentries = true; } if (batch_size == 0) batch_start = i; batch_size++; } if (batch_size > 0) { int ret; ret = flush_dir_items_batch(trans, inode, src, dst_path, batch_start, batch_size); if (ret < 0) return ret; } return last_found ? 1 : 0; } /* * log all the items included in the current transaction for a given * directory. This also creates the range items in the log tree required * to replay anything deleted before the fsync */ static noinline int log_dir_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 min_offset, u64 *last_offset_ret) { struct btrfs_key min_key; struct btrfs_root *root = inode->root; struct btrfs_root *log = root->log_root; int ret; u64 last_old_dentry_offset = min_offset - 1; u64 last_offset = (u64)-1; u64 ino = btrfs_ino(inode); min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = min_offset; ret = btrfs_search_forward(root, &min_key, path, trans->transid); /* * we didn't find anything from this transaction, see if there * is anything at all */ if (ret != 0 || min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = (u64)-1; btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret < 0) { btrfs_release_path(path); return ret; } ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); /* if ret == 0 there are items for this type, * create a range to tell us the last key of this type. * otherwise, there are no items in this directory after * *min_offset, and we create a range to indicate that. */ if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret > 0) { ret = 0; } goto done; } /* go backward to find any previous key */ ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); /* * The dir index key before the first one we found that needs to * be logged might be in a previous leaf, and there might be a * gap between these keys, meaning that we had deletions that * happened. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must cover a range that starts at the * previous key's offset plus 1, so that those deletes are replayed. */ if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret < 0) { goto done; } btrfs_release_path(path); /* * Find the first key from this transaction again or the one we were at * in the loop below in case we had to reschedule. We may be logging the * directory without holding its VFS lock, which happen when logging new * dentries (through log_new_dir_dentries()) or in some cases when we * need to log the parent directory of an inode. This means a dir index * key might be deleted from the inode's root, and therefore we may not * find it anymore. If we can't find it, just move to the next key. We * can not bail out and ignore, because if we do that we will simply * not log dir index keys that come after the one that was just deleted * and we can end up logging a dir index range that ends at (u64)-1 * (@last_offset is initialized to that), resulting in removing dir * entries we should not remove at log replay time. */ search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret > 0) { ret = btrfs_next_item(root, path); if (ret > 0) { /* There are no more keys in the inode's root. */ ret = 0; goto done; } } if (ret < 0) goto done; /* * we have a block from this transaction, log every item in it * from our directory */ while (1) { ret = process_dir_items_leaf(trans, inode, path, dst_path, ctx, &last_old_dentry_offset); if (ret != 0) { if (ret > 0) ret = 0; goto done; } path->slots[0] = btrfs_header_nritems(path->nodes[0]); /* * look ahead to the next item and see if it is also * from this directory and from this transaction */ ret = btrfs_next_leaf(root, path); if (ret) { if (ret == 1) { last_offset = (u64)-1; ret = 0; } goto done; } btrfs_item_key_to_cpu(path->nodes[0], &min_key, path->slots[0]); if (min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { last_offset = (u64)-1; goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { /* * The next leaf was not changed in the current transaction * and has at least one dir index key. * We check for the next key because there might have been * one or more deletions between the last key we logged and * that next key. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must end at the next key's * offset minus 1, so that those deletes are replayed. */ last_offset = min_key.offset - 1; goto done; } if (need_resched()) { btrfs_release_path(path); cond_resched(); goto search; } } done: btrfs_release_path(path); btrfs_release_path(dst_path); if (ret == 0) { *last_offset_ret = last_offset; /* * In case the leaf was changed in the current transaction but * all its dir items are from a past transaction, the last item * in the leaf is a dir item and there's no gap between that last * dir item and the first one on the next leaf (which did not * change in the current transaction), then we don't need to log * a range, last_old_dentry_offset is == to last_offset. */ ASSERT(last_old_dentry_offset <= last_offset); if (last_old_dentry_offset < last_offset) ret = insert_dir_log_key(trans, log, path, ino, last_old_dentry_offset + 1, last_offset); } return ret; } /* * If the inode was logged before and it was evicted, then its * last_dir_index_offset is (u64)-1, so we don't the value of the last index * key offset. If that's the case, search for it and update the inode. This * is to avoid lookups in the log tree every time we try to insert a dir index * key from a leaf changed in the current transaction, and to allow us to always * do batch insertions of dir index keys. */ static int update_last_dir_index_offset(struct btrfs_inode *inode, struct btrfs_path *path, const struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); struct btrfs_key key; int ret; lockdep_assert_held(&inode->log_mutex); if (inode->last_dir_index_offset != (u64)-1) return 0; if (!ctx->logged_before) { inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; return 0; } key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); /* * An error happened or we actually have an index key with an offset * value of (u64)-1. Bail out, we're done. */ if (ret <= 0) goto out; ret = 0; inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; /* * No dir index items, bail out and leave last_dir_index_offset with * the value right before the first valid index value. */ if (path->slots[0] == 0) goto out; /* * btrfs_search_slot() left us at one slot beyond the slot with the last * index key, or beyond the last key of the directory that is not an * index key. If we have an index key before, set last_dir_index_offset * to its offset value, otherwise leave it with a value right before the * first valid index value, as it means we have an empty directory. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); if (key.objectid == ino && key.type == BTRFS_DIR_INDEX_KEY) inode->last_dir_index_offset = key.offset; out: btrfs_release_path(path); return ret; } /* * logging directories is very similar to logging inodes, We find all the items * from the current transaction and write them to the log. * * The recovery code scans the directory in the subvolume, and if it finds a * key in the range logged that is not present in the log tree, then it means * that dir entry was unlinked during the transaction. * * In order for that scan to work, we must include one key smaller than * the smallest logged by this transaction and one key larger than the largest * key logged by this transaction. */ static noinline int log_directory_changes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { u64 min_key; u64 max_key; int ret; ret = update_last_dir_index_offset(inode, path, ctx); if (ret) return ret; min_key = BTRFS_DIR_START_INDEX; max_key = 0; while (1) { ret = log_dir_items(trans, inode, path, dst_path, ctx, min_key, &max_key); if (ret) return ret; if (max_key == (u64)-1) break; min_key = max_key + 1; } return 0; } /* * a helper function to drop items from the log before we relog an * inode. max_key_type indicates the highest item type to remove. * This cannot be run for file data extents because it does not * free the extents they point to. */ static int drop_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, int max_key_type) { int ret; struct btrfs_key key; struct btrfs_key found_key; int start_slot; key.objectid = btrfs_ino(inode); key.type = max_key_type; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { break; } else if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != key.objectid) break; found_key.offset = 0; found_key.type = 0; ret = btrfs_bin_search(path->nodes[0], 0, &found_key, &start_slot); if (ret < 0) break; ret = btrfs_del_items(trans, log, path, start_slot, path->slots[0] - start_slot + 1); /* * If start slot isn't 0 then we don't need to re-search, we've * found the last guy with the objectid in this tree. */ if (ret || start_slot != 0) break; btrfs_release_path(path); } btrfs_release_path(path); if (ret > 0) ret = 0; return ret; } static int truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log_root, struct btrfs_inode *inode, u64 new_size, u32 min_type) { struct btrfs_truncate_control control = { .new_size = new_size, .ino = btrfs_ino(inode), .min_type = min_type, .skip_ref_updates = true, }; return btrfs_truncate_inode_items(trans, log_root, &control); } static void fill_inode_item(struct btrfs_trans_handle *trans, struct extent_buffer *leaf, struct btrfs_inode_item *item, struct inode *inode, int log_inode_only, u64 logged_isize) { struct btrfs_map_token token; u64 flags; btrfs_init_map_token(&token, leaf); if (log_inode_only) { /* set the generation to zero so the recover code * can tell the difference between an logging * just to say 'this inode exists' and a logging * to say 'update this inode with these values' */ btrfs_set_token_inode_generation(&token, item, 0); btrfs_set_token_inode_size(&token, item, logged_isize); } else { btrfs_set_token_inode_generation(&token, item, BTRFS_I(inode)->generation); btrfs_set_token_inode_size(&token, item, inode->i_size); } btrfs_set_token_inode_uid(&token, item, i_uid_read(inode)); btrfs_set_token_inode_gid(&token, item, i_gid_read(inode)); btrfs_set_token_inode_mode(&token, item, inode->i_mode); btrfs_set_token_inode_nlink(&token, item, inode->i_nlink); btrfs_set_token_timespec_sec(&token, &item->atime, inode_get_atime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->atime, inode_get_atime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->mtime, inode_get_mtime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->mtime, inode_get_mtime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->ctime, inode_get_ctime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->ctime, inode_get_ctime_nsec(inode)); /* * We do not need to set the nbytes field, in fact during a fast fsync * its value may not even be correct, since a fast fsync does not wait * for ordered extent completion, which is where we update nbytes, it * only waits for writeback to complete. During log replay as we find * file extent items and replay them, we adjust the nbytes field of the * inode item in subvolume tree as needed (see overwrite_item()). */ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode)); btrfs_set_token_inode_transid(&token, item, trans->transid); btrfs_set_token_inode_rdev(&token, item, inode->i_rdev); flags = btrfs_inode_combine_flags(BTRFS_I(inode)->flags, BTRFS_I(inode)->ro_flags); btrfs_set_token_inode_flags(&token, item, flags); btrfs_set_token_inode_block_group(&token, item, 0); } static int log_inode_item(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, bool inode_item_dropped) { struct btrfs_inode_item *inode_item; int ret; /* * If we are doing a fast fsync and the inode was logged before in the * current transaction, then we know the inode was previously logged and * it exists in the log tree. For performance reasons, in this case use * btrfs_search_slot() directly with ins_len set to 0 so that we never * attempt a write lock on the leaf's parent, which adds unnecessary lock * contention in case there are concurrent fsyncs for other inodes of the * same subvolume. Using btrfs_insert_empty_item() when the inode item * already exists can also result in unnecessarily splitting a leaf. */ if (!inode_item_dropped && inode->logged_trans == trans->transid) { ret = btrfs_search_slot(trans, log, &inode->location, path, 0, 1); ASSERT(ret <= 0); if (ret > 0) ret = -ENOENT; } else { /* * This means it is the first fsync in the current transaction, * so the inode item is not in the log and we need to insert it. * We can never get -EEXIST because we are only called for a fast * fsync and in case an inode eviction happens after the inode was * logged before in the current transaction, when we load again * the inode, we set BTRFS_INODE_NEEDS_FULL_SYNC on its runtime * flags and set ->logged_trans to 0. */ ret = btrfs_insert_empty_item(trans, log, path, &inode->location, sizeof(*inode_item)); ASSERT(ret != -EEXIST); } if (ret) return ret; inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); fill_inode_item(trans, path->nodes[0], inode_item, &inode->vfs_inode, 0, 0); btrfs_release_path(path); return 0; } static int log_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { const u64 lock_end = sums->logical + sums->len - 1; struct extent_state *cached_state = NULL; int ret; /* * If this inode was not used for reflink operations in the current * transaction with new extents, then do the fast path, no need to * worry about logging checksum items with overlapping ranges. */ if (inode->last_reflink_trans < trans->transid) return btrfs_csum_file_blocks(trans, log_root, sums); /* * Serialize logging for checksums. This is to avoid racing with the * same checksum being logged by another task that is logging another * file which happens to refer to the same extent as well. Such races * can leave checksum items in the log with overlapping ranges. */ ret = lock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); if (ret) return ret; /* * Due to extent cloning, we might have logged a csum item that covers a * subrange of a cloned extent, and later we can end up logging a csum * item for a larger subrange of the same extent or the entire range. * This would leave csum items in the log tree that cover the same range * and break the searches for checksums in the log tree, resulting in * some checksums missing in the fs/subvolume tree. So just delete (or * trim and adjust) any existing csum items in the log for this range. */ ret = btrfs_del_csums(trans, log_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, log_root, sums); unlock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); return ret; } static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, struct btrfs_path *src_path, int start_slot, int nr, int inode_only, u64 logged_isize, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; struct extent_buffer *src; int ret; struct btrfs_key *ins_keys; u32 *ins_sizes; struct btrfs_item_batch batch; char *ins_data; int dst_index; const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM); const u64 i_size = i_size_read(&inode->vfs_inode); /* * To keep lockdep happy and avoid deadlocks, clone the source leaf and * use the clone. This is because otherwise we would be changing the log * tree, to insert items from the subvolume tree or insert csum items, * while holding a read lock on a leaf from the subvolume tree, which * creates a nasty lock dependency when COWing log tree nodes/leaves: * * 1) Modifying the log tree triggers an extent buffer allocation while * holding a write lock on a parent extent buffer from the log tree. * Allocating the pages for an extent buffer, or the extent buffer * struct, can trigger inode eviction and finally the inode eviction * will trigger a release/remove of a delayed node, which requires * taking the delayed node's mutex; * * 2) Allocating a metadata extent for a log tree can trigger the async * reclaim thread and make us wait for it to release enough space and * unblock our reservation ticket. The reclaim thread can start * flushing delayed items, and that in turn results in the need to * lock delayed node mutexes and in the need to write lock extent * buffers of a subvolume tree - all this while holding a write lock * on the parent extent buffer in the log tree. * * So one task in scenario 1) running in parallel with another task in * scenario 2) could lead to a deadlock, one wanting to lock a delayed * node mutex while having a read lock on a leaf from the subvolume, * while the other is holding the delayed node's mutex and wants to * write lock the same subvolume leaf for flushing delayed items. */ ret = clone_leaf(src_path, ctx); if (ret < 0) return ret; src = src_path->nodes[0]; ins_data = kmalloc(nr * sizeof(struct btrfs_key) + nr * sizeof(u32), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; batch.nr = 0; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; struct btrfs_root *csum_root; struct btrfs_ordered_sum *sums; struct btrfs_ordered_sum *sums_next; LIST_HEAD(ordered_sums); u64 disk_bytenr; u64 disk_num_bytes; u64 extent_offset; u64 extent_num_bytes; bool is_old_extent; btrfs_item_key_to_cpu(src, &ins_keys[dst_index], src_slot); if (ins_keys[dst_index].type != BTRFS_EXTENT_DATA_KEY) goto add_to_batch; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); is_old_extent = (btrfs_file_extent_generation(src, extent) < trans->transid); /* * Don't copy extents from past generations. That would make us * log a lot more metadata for common cases like doing only a * few random writes into a file and then fsync it for the first * time or after the full sync flag is set on the inode. We can * get leaves full of extent items, most of which are from past * generations, so we can skip them - as long as the inode has * not been the target of a reflink operation in this transaction, * as in that case it might have had file extent items with old * generations copied into it. We also must always log prealloc * extents that start at or beyond eof, otherwise we would lose * them on log replay. */ if (is_old_extent && ins_keys[dst_index].offset < i_size && inode->last_reflink_trans < trans->transid) continue; if (skip_csum) goto add_to_batch; /* Only regular extents have checksums. */ if (btrfs_file_extent_type(src, extent) != BTRFS_FILE_EXTENT_REG) goto add_to_batch; /* * If it's an extent created in a past transaction, then its * checksums are already accessible from the committed csum tree, * no need to log them. */ if (is_old_extent) goto add_to_batch; disk_bytenr = btrfs_file_extent_disk_bytenr(src, extent); /* If it's an explicit hole, there are no checksums. */ if (disk_bytenr == 0) goto add_to_batch; disk_num_bytes = btrfs_file_extent_disk_num_bytes(src, extent); if (btrfs_file_extent_compression(src, extent)) { extent_offset = 0; extent_num_bytes = disk_num_bytes; } else { extent_offset = btrfs_file_extent_offset(src, extent); extent_num_bytes = btrfs_file_extent_num_bytes(src, extent); } csum_root = btrfs_csum_root(trans->fs_info, disk_bytenr); disk_bytenr += extent_offset; ret = btrfs_lookup_csums_list(csum_root, disk_bytenr, disk_bytenr + extent_num_bytes - 1, &ordered_sums, false); if (ret < 0) goto out; ret = 0; list_for_each_entry_safe(sums, sums_next, &ordered_sums, list) { if (!ret) ret = log_csums(trans, inode, log, sums); list_del(&sums->list); kfree(sums); } if (ret) goto out; add_to_batch: ins_sizes[dst_index] = btrfs_item_size(src, src_slot); batch.total_data_size += ins_sizes[dst_index]; batch.nr++; dst_index++; } /* * We have a leaf full of old extent items that don't need to be logged, * so we don't need to do anything. */ if (batch.nr == 0) goto out; ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; const int dst_slot = dst_path->slots[0] + dst_index; struct btrfs_key key; unsigned long src_offset; unsigned long dst_offset; /* * We're done, all the remaining items in the source leaf * correspond to old file extent items. */ if (dst_index >= batch.nr) break; btrfs_item_key_to_cpu(src, &key, src_slot); if (key.type != BTRFS_EXTENT_DATA_KEY) goto copy_item; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); /* See the comment in the previous loop, same logic. */ if (btrfs_file_extent_generation(src, extent) < trans->transid && key.offset < i_size && inode->last_reflink_trans < trans->transid) continue; copy_item: dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0], dst_slot); src_offset = btrfs_item_ptr_offset(src, src_slot); if (key.type == BTRFS_INODE_ITEM_KEY) { struct btrfs_inode_item *inode_item; inode_item = btrfs_item_ptr(dst_path->nodes[0], dst_slot, struct btrfs_inode_item); fill_inode_item(trans, dst_path->nodes[0], inode_item, &inode->vfs_inode, inode_only == LOG_INODE_EXISTS, logged_isize); } else { copy_extent_buffer(dst_path->nodes[0], src, dst_offset, src_offset, ins_sizes[dst_index]); } dst_index++; } btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]); btrfs_release_path(dst_path); out: kfree(ins_data); return ret; } static int extent_cmp(void *priv, const struct list_head *a, const struct list_head *b) { const struct extent_map *em1, *em2; em1 = list_entry(a, struct extent_map, list); em2 = list_entry(b, struct extent_map, list); if (em1->start < em2->start) return -1; else if (em1->start > em2->start) return 1; return 0; } static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, const struct extent_map *em, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_root *csum_root; u64 csum_offset; u64 csum_len; u64 mod_start = em->start; u64 mod_len = em->len; LIST_HEAD(ordered_sums); int ret = 0; if (inode->flags & BTRFS_INODE_NODATASUM || (em->flags & EXTENT_FLAG_PREALLOC) || em->block_start == EXTENT_MAP_HOLE) return 0; list_for_each_entry(ordered, &ctx->ordered_extents, log_list) { const u64 ordered_end = ordered->file_offset + ordered->num_bytes; const u64 mod_end = mod_start + mod_len; struct btrfs_ordered_sum *sums; if (mod_len == 0) break; if (ordered_end <= mod_start) continue; if (mod_end <= ordered->file_offset) break; /* * We are going to copy all the csums on this ordered extent, so * go ahead and adjust mod_start and mod_len in case this ordered * extent has already been logged. */ if (ordered->file_offset > mod_start) { if (ordered_end >= mod_end) mod_len = ordered->file_offset - mod_start; /* * If we have this case * * |--------- logged extent ---------| * |----- ordered extent ----| * * Just don't mess with mod_start and mod_len, we'll * just end up logging more csums than we need and it * will be ok. */ } else { if (ordered_end < mod_end) { mod_len = mod_end - ordered_end; mod_start = ordered_end; } else { mod_len = 0; } } /* * To keep us from looping for the above case of an ordered * extent that falls inside of the logged extent. */ if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM, &ordered->flags)) continue; list_for_each_entry(sums, &ordered->list, list) { ret = log_csums(trans, inode, log_root, sums); if (ret) return ret; } } /* We're done, found all csums in the ordered extents. */ if (mod_len == 0) return 0; /* If we're compressed we have to save the entire range of csums. */ if (extent_map_is_compressed(em)) { csum_offset = 0; csum_len = max(em->block_len, em->orig_block_len); } else { csum_offset = mod_start - em->start; csum_len = mod_len; } /* block start is already adjusted for the file extent offset. */ csum_root = btrfs_csum_root(trans->fs_info, em->block_start); ret = btrfs_lookup_csums_list(csum_root, em->block_start + csum_offset, em->block_start + csum_offset + csum_len - 1, &ordered_sums, false); if (ret < 0) return ret; ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, list); if (!ret) ret = log_csums(trans, inode, log_root, sums); list_del(&sums->list); kfree(sums); } return ret; } static int log_one_extent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct extent_map *em, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item fi = { 0 }; struct extent_buffer *leaf; struct btrfs_key key; enum btrfs_compression_type compress_type; u64 extent_offset = em->start - em->orig_start; u64 block_len; int ret; btrfs_set_stack_file_extent_generation(&fi, trans->transid); if (em->flags & EXTENT_FLAG_PREALLOC) btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_PREALLOC); else btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG); block_len = max(em->block_len, em->orig_block_len); compress_type = extent_map_compression(em); if (compress_type != BTRFS_COMPRESS_NONE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } else if (em->block_start < EXTENT_MAP_LAST_BYTE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start - extent_offset); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } btrfs_set_stack_file_extent_offset(&fi, extent_offset); btrfs_set_stack_file_extent_num_bytes(&fi, em->len); btrfs_set_stack_file_extent_ram_bytes(&fi, em->ram_bytes); btrfs_set_stack_file_extent_compression(&fi, compress_type); ret = log_extent_csums(trans, inode, log, em, ctx); if (ret) return ret; /* * If this is the first time we are logging the inode in the current * transaction, we can avoid btrfs_drop_extents(), which is expensive * because it does a deletion search, which always acquires write locks * for extent buffers at levels 2, 1 and 0. This not only wastes time * but also adds significant contention in a log tree, since log trees * are small, with a root at level 2 or 3 at most, due to their short * life span. */ if (ctx->logged_before) { drop_args.path = path; drop_args.start = em->start; drop_args.end = em->start + em->len; drop_args.replace_extent = true; drop_args.extent_item_size = sizeof(fi); ret = btrfs_drop_extents(trans, log, inode, &drop_args); if (ret) return ret; } if (!drop_args.extent_inserted) { key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = em->start; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(fi)); if (ret) return ret; } leaf = path->nodes[0]; write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return ret; } /* * Log all prealloc extents beyond the inode's i_size to make sure we do not * lose them after doing a full/fast fsync and replaying the log. We scan the * subvolume's root instead of iterating the inode's extent map tree because * otherwise we can log incorrect extent items based on extent map conversion. * That can happen due to the fact that extent maps are merged when they * are not in the extent map tree's list of modified extents. */ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_key key; const u64 i_size = i_size_read(&inode->vfs_inode); const u64 ino = btrfs_ino(inode); struct btrfs_path *dst_path = NULL; bool dropped_extents = false; u64 truncate_offset = i_size; struct extent_buffer *leaf; int slot; int ins_nr = 0; int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = i_size; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; /* * We must check if there is a prealloc extent that starts before the * i_size and crosses the i_size boundary. This is to ensure later we * truncate down to the end of that extent and not to the i_size, as * otherwise we end up losing part of the prealloc extent after a log * replay and with an implicit hole if there is another prealloc extent * that starts at an offset beyond i_size. */ ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); if (ret < 0) goto out; if (ret == 0) { struct btrfs_file_extent_item *ei; leaf = path->nodes[0]; slot = path->slots[0]; ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_PREALLOC) { u64 extent_end; btrfs_item_key_to_cpu(leaf, &key, slot); extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, ei); if (extent_end > i_size) truncate_offset = extent_end; } } else { ret = 0; } while (true) { leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) goto out; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; if (ret > 0) { ret = 0; break; } continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid > ino) break; if (WARN_ON_ONCE(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY || key.offset < i_size) { path->slots[0]++; continue; } /* * Avoid overlapping items in the log tree. The first time we * get here, get rid of everything from a past fsync. After * that, if the current extent starts before the end of the last * extent we copied, truncate the last one. This can happen if * an ordered extent completion modifies the subvolume tree * while btrfs_next_leaf() has the tree unlocked. */ if (!dropped_extents || key.offset < truncate_offset) { ret = truncate_inode_items(trans, root->log_root, inode, min(key.offset, truncate_offset), BTRFS_EXTENT_DATA_KEY); if (ret) goto out; dropped_extents = true; } truncate_offset = btrfs_file_extent_end(path); if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; if (!dst_path) { dst_path = btrfs_alloc_path(); if (!dst_path) { ret = -ENOMEM; goto out; } } } if (ins_nr > 0) ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); out: btrfs_release_path(path); btrfs_free_path(dst_path); return ret; } static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; struct extent_map *em, *n; LIST_HEAD(extents); struct extent_map_tree *tree = &inode->extent_tree; int ret = 0; int num = 0; write_lock(&tree->lock); list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we * have a bunch of extents we just want to commit since it will * be faster. */ if (++num > 32768) { list_del_init(&tree->modified_extents); ret = -EFBIG; goto process; } if (em->generation < trans->transid) continue; /* We log prealloc extents beyond eof later. */ if ((em->flags & EXTENT_FLAG_PREALLOC) && em->start >= i_size_read(&inode->vfs_inode)) continue; /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); em->flags |= EXTENT_FLAG_LOGGING; list_add_tail(&em->list, &extents); num++; } list_sort(NULL, &extents, extent_cmp); process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); list_del_init(&em->list); /* * If we had an error we just need to delete everybody from our * private list. */ if (ret) { clear_em_logging(inode, em); free_extent_map(em); continue; } write_unlock(&tree->lock); ret = log_one_extent(trans, inode, em, path, ctx); write_lock(&tree->lock); clear_em_logging(inode, em); free_extent_map(em); } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); if (!ret) ret = btrfs_log_prealloc_extents(trans, inode, path, ctx); if (ret) return ret; /* * We have logged all extents successfully, now make sure the commit of * the current transaction waits for the ordered extents to complete * before it commits and wipes out the log trees, otherwise we would * lose data if an ordered extents completes after the transaction * commits and a power failure happens after the transaction commit. */ list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { spin_lock_irq(&inode->ordered_tree_lock); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); atomic_inc(&trans->transaction->pending_ordered); } spin_unlock_irq(&inode->ordered_tree_lock); } btrfs_put_ordered_extent(ordered); } return 0; } static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; int ret; key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, log, &key, path, 0, 0); if (ret < 0) { return ret; } else if (ret > 0) { *size_ret = 0; } else { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); /* * If the in-memory inode's i_size is smaller then the inode * size stored in the btree, return the inode's i_size, so * that we get a correct inode size after replaying the log * when before a power failure we had a shrinking truncate * followed by addition of a new name (rename / new hard link). * Otherwise return the inode size from the btree, to avoid * data loss when replaying a log due to previously doing a * write that expands the inode's size and logging a new name * immediately after. */ if (*size_ret > inode->vfs_inode.i_size) *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); return 0; } /* * At the moment we always log all xattrs. This is to figure out at log replay * time which xattrs must have their deletion replayed. If a xattr is missing * in the log tree and exists in the fs/subvol tree, we delete it. This is * because if a xattr is deleted, the inode is fsynced and a power failure * happens, causing the log to be replayed the next time the fs is mounted, * we want the xattr to not exist anymore (same behaviour as other filesystems * with a journal, ext3/4, xfs, f2fs, etc). */ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; int ret; struct btrfs_key key; const u64 ino = btrfs_ino(inode); int ins_nr = 0; int start_slot = 0; bool found_xattrs = false; if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags)) return 0; key.objectid = ino; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { int slot = path->slots[0]; struct extent_buffer *leaf = path->nodes[0]; int nritems = btrfs_header_nritems(leaf); if (slot >= nritems) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) break; if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; found_xattrs = true; cond_resched(); } if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; } if (!found_xattrs) set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags); return 0; } /* * When using the NO_HOLES feature if we punched a hole that causes the * deletion of entire leafs or all the extent items of the first leaf (the one * that contains the inode item and references) we may end up not processing * any extents, because there are no leafs with a generation matching the * current transaction that have extent items for our inode. So we need to find * if any holes exist and then log them. We also need to log holes after any * truncate operation that changes the inode's size. */ static int btrfs_log_holes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; const u64 ino = btrfs_ino(inode); const u64 i_size = i_size_read(&inode->vfs_inode); u64 prev_extent_end = 0; int ret; if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { struct extent_buffer *leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; /* We have a hole, log it. */ if (prev_extent_end < key.offset) { const u64 hole_len = key.offset - prev_extent_end; /* * Release the path to avoid deadlocks with other code * paths that search the root while holding locks on * leafs from the log root. */ btrfs_release_path(path); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; /* * Search for the same key again in the root. Since it's * an extent item and we are holding the inode lock, the * key must still exist. If it doesn't just emit warning * and return an error to fall back to a transaction * commit. */ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; if (WARN_ON(ret > 0)) return -ENOENT; leaf = path->nodes[0]; } prev_extent_end = btrfs_file_extent_end(path); path->slots[0]++; cond_resched(); } if (prev_extent_end < i_size) { u64 hole_len; btrfs_release_path(path); hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; } return 0; } /* * When we are logging a new inode X, check if it doesn't have a reference that * matches the reference from some other inode Y created in a past transaction * and that was renamed in the current transaction. If we don't do this, then at * log replay time we can lose inode Y (and all its files if it's a directory): * * mkdir /mnt/x * echo "hello world" > /mnt/x/foobar * sync * mv /mnt/x /mnt/y * mkdir /mnt/x # or touch /mnt/x * xfs_io -c fsync /mnt/x * <power fail> * mount fs, trigger log replay * * After the log replay procedure, we would lose the first directory and all its * files (file foobar). * For the case where inode Y is not a directory we simply end up losing it: * * echo "123" > /mnt/foo * sync * mv /mnt/foo /mnt/bar * echo "abc" > /mnt/foo * xfs_io -c fsync /mnt/foo * <power fail> * * We also need this for cases where a snapshot entry is replaced by some other * entry (file or directory) otherwise we end up with an unreplayable log due to * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as * if it were a regular entry: * * mkdir /mnt/x * btrfs subvolume snapshot /mnt /mnt/x/snap * btrfs subvolume delete /mnt/x/snap * rmdir /mnt/x * mkdir /mnt/x * fsync /mnt/x or fsync some new file inside it * <power fail> * * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in * the same transaction. */ static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, struct btrfs_inode *inode, u64 *other_ino, u64 *other_parent) { int ret; struct btrfs_path *search_path; char *name = NULL; u32 name_len = 0; u32 item_size = btrfs_item_size(eb, slot); u32 cur_offset = 0; unsigned long ptr = btrfs_item_ptr_offset(eb, slot); search_path = btrfs_alloc_path(); if (!search_path) return -ENOMEM; search_path->search_commit_root = 1; search_path->skip_locking = 1; while (cur_offset < item_size) { u64 parent; u32 this_name_len; u32 this_len; unsigned long name_ptr; struct btrfs_dir_item *di; struct fscrypt_str name_str; if (key->type == BTRFS_INODE_REF_KEY) { struct btrfs_inode_ref *iref; iref = (struct btrfs_inode_ref *)(ptr + cur_offset); parent = key->offset; this_name_len = btrfs_inode_ref_name_len(eb, iref); name_ptr = (unsigned long)(iref + 1); this_len = sizeof(*iref) + this_name_len; } else { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *)(ptr + cur_offset); parent = btrfs_inode_extref_parent(eb, extref); this_name_len = btrfs_inode_extref_name_len(eb, extref); name_ptr = (unsigned long)&extref->name; this_len = sizeof(*extref) + this_name_len; } if (this_name_len > name_len) { char *new_name; new_name = krealloc(name, this_name_len, GFP_NOFS); if (!new_name) { ret = -ENOMEM; goto out; } name_len = this_name_len; name = new_name; } read_extent_buffer(eb, name, name_ptr, this_name_len); name_str.name = name; name_str.len = this_name_len; di = btrfs_lookup_dir_item(NULL, inode->root, search_path, parent, &name_str, 0); if (di && !IS_ERR(di)) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(search_path->nodes[0], di, &di_key); if (di_key.type == BTRFS_INODE_ITEM_KEY) { if (di_key.objectid != key->objectid) { ret = 1; *other_ino = di_key.objectid; *other_parent = parent; } else { ret = 0; } } else { ret = -EAGAIN; } goto out; } else if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } btrfs_release_path(search_path); cur_offset += this_len; } ret = 0; out: btrfs_free_path(search_path); kfree(name); return ret; } /* * Check if we need to log an inode. This is used in contexts where while * logging an inode we need to log another inode (either that it exists or in * full mode). This is used instead of btrfs_inode_in_log() because the later * requires the inode to be in the log and have the log transaction committed, * while here we do not care if the log transaction was already committed - our * caller will commit the log later - and we want to avoid logging an inode * multiple times when multiple tasks have joined the same log transaction. */ static bool need_log_inode(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { /* * If a directory was not modified, no dentries added or removed, we can * and should avoid logging it. */ if (S_ISDIR(inode->vfs_inode.i_mode) && inode->last_trans < trans->transid) return false; /* * If this inode does not have new/updated/deleted xattrs since the last * time it was logged and is flagged as logged in the current transaction, * we can skip logging it. As for new/deleted names, those are updated in * the log by link/unlink/rename operations. * In case the inode was logged and then evicted and reloaded, its * logged_trans will be 0, in which case we have to fully log it since * logged_trans is a transient field, not persisted. */ if (inode_logged(trans, inode, NULL) == 1 && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return false; return true; } struct btrfs_dir_list { u64 ino; struct list_head list; }; /* * Log the inodes of the new dentries of a directory. * See process_dir_items_leaf() for details about why it is needed. * This is a recursive operation - if an existing dentry corresponds to a * directory, that directory's new entries are logged too (same behaviour as * ext3/4, xfs, f2fs, reiserfs, nilfs2). Note that when logging the inodes * the dentries point to we do not acquire their VFS lock, otherwise lockdep * complains about the following circular lock dependency / possible deadlock: * * CPU0 CPU1 * ---- ---- * lock(&type->i_mutex_dir_key#3/2); * lock(sb_internal#2); * lock(&type->i_mutex_dir_key#3/2); * lock(&sb->s_type->i_mutex_key#14); * * Where sb_internal is the lock (a counter that works as a lock) acquired by * sb_start_intwrite() in btrfs_start_transaction(). * Not acquiring the VFS lock of the inodes is still safe because: * * 1) For regular files we log with a mode of LOG_INODE_EXISTS. It's possible * that while logging the inode new references (names) are added or removed * from the inode, leaving the logged inode item with a link count that does * not match the number of logged inode reference items. This is fine because * at log replay time we compute the real number of links and correct the * link count in the inode item (see replay_one_buffer() and * link_to_fixup_dir()); * * 2) For directories we log with a mode of LOG_INODE_ALL. It's possible that * while logging the inode's items new index items (key type * BTRFS_DIR_INDEX_KEY) are added to fs/subvol tree and the logged inode item * has a size that doesn't match the sum of the lengths of all the logged * names - this is ok, not a problem, because at log replay time we set the * directory's i_size to the correct value (see replay_one_name() and * overwrite_item()). */ static int log_new_dir_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *start_inode, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = start_inode->root; struct btrfs_path *path; LIST_HEAD(dir_list); struct btrfs_dir_list *dir_elem; u64 ino = btrfs_ino(start_inode); struct btrfs_inode *curr_inode = start_inode; int ret = 0; /* * If we are logging a new name, as part of a link or rename operation, * don't bother logging new dentries, as we just want to log the names * of an inode and that any new parents exist. */ if (ctx->logging_new_name) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* Pairs with btrfs_add_delayed_iput below. */ ihold(&curr_inode->vfs_inode); while (true) { struct inode *vfs_inode; struct btrfs_key key; struct btrfs_key found_key; u64 next_index; bool continue_curr_inode = true; int iter_ret; key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = btrfs_get_first_dir_index_to_log(curr_inode); next_index = key.offset; again: btrfs_for_each_slot(root->log_root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_dir_item *di; struct btrfs_key di_key; struct inode *di_inode; int log_mode = LOG_INODE_EXISTS; int type; if (found_key.objectid != ino || found_key.type != BTRFS_DIR_INDEX_KEY) { continue_curr_inode = false; break; } next_index = found_key.offset + 1; di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); type = btrfs_dir_ftype(leaf, di); if (btrfs_dir_transid(leaf, di) < trans->transid) continue; btrfs_dir_item_key_to_cpu(leaf, di, &di_key); if (di_key.type == BTRFS_ROOT_ITEM_KEY) continue; btrfs_release_path(path); di_inode = btrfs_iget_logging(di_key.objectid, root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); goto out; } if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(BTRFS_I(di_inode)); break; } ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); btrfs_add_delayed_iput(BTRFS_I(di_inode)); if (ret) goto out; if (ctx->log_new_dentries) { dir_elem = kmalloc(sizeof(*dir_elem), GFP_NOFS); if (!dir_elem) { ret = -ENOMEM; goto out; } dir_elem->ino = di_key.objectid; list_add_tail(&dir_elem->list, &dir_list); } break; } btrfs_release_path(path); if (iter_ret < 0) { ret = iter_ret; goto out; } else if (iter_ret > 0) { continue_curr_inode = false; } else { key = found_key; } if (continue_curr_inode && key.offset < (u64)-1) { key.offset++; goto again; } btrfs_set_first_dir_index_to_log(curr_inode, next_index); if (list_empty(&dir_list)) break; dir_elem = list_first_entry(&dir_list, struct btrfs_dir_list, list); ino = dir_elem->ino; list_del(&dir_elem->list); kfree(dir_elem); btrfs_add_delayed_iput(curr_inode); curr_inode = NULL; vfs_inode = btrfs_iget_logging(ino, root); if (IS_ERR(vfs_inode)) { ret = PTR_ERR(vfs_inode); break; } curr_inode = BTRFS_I(vfs_inode); } out: btrfs_free_path(path); if (curr_inode) btrfs_add_delayed_iput(curr_inode); if (ret) { struct btrfs_dir_list *next; list_for_each_entry_safe(dir_elem, next, &dir_list, list) kfree(dir_elem); } return ret; } struct btrfs_ino_list { u64 ino; u64 parent; struct list_head list; }; static void free_conflicting_inodes(struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *curr; struct btrfs_ino_list *next; list_for_each_entry_safe(curr, next, &ctx->conflict_inodes, list) { list_del(&curr->list); kfree(curr); } } static int conflicting_inode_is_dir(struct btrfs_root *root, u64 ino, struct btrfs_path *path) { struct btrfs_key key; int ret; key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; path->search_commit_root = 1; path->skip_locking = 1; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (WARN_ON_ONCE(ret > 0)) { /* * We have previously found the inode through the commit root * so this should not happen. If it does, just error out and * fallback to a transaction commit. */ ret = -ENOENT; } else if (ret == 0) { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); if (S_ISDIR(btrfs_inode_mode(path->nodes[0], item))) ret = 1; } btrfs_release_path(path); path->search_commit_root = 0; path->skip_locking = 0; return ret; } static int add_conflicting_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 ino, u64 parent, struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *ino_elem; struct inode *inode; /* * It's rare to have a lot of conflicting inodes, in practice it is not * common to have more than 1 or 2. We don't want to collect too many, * as we could end up logging too many inodes (even if only in * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction * commits. */ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) return BTRFS_LOG_FORCE_COMMIT; inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was deleted in * the current transaction then we either: * * 1) Log the parent directory (later after adding it to the list) if * the inode is a directory. This is because it may be a deleted * subvolume/snapshot or it may be a regular directory that had * deleted subvolumes/snapshots (or subdirectories that had them), * and at the moment we can't deal with dropping subvolumes/snapshots * during log replay. So we just log the parent, which will result in * a fallback to a transaction commit if we are dealing with those * cases (last_unlink_trans will match the current transaction); * * 2) Do nothing if it's not a directory. During log replay we simply * unlink the conflicting dentry from the parent directory and then * add the dentry for our inode. Like this we can avoid logging the * parent directory (and maybe fallback to a transaction commit in * case it has a last_unlink_trans == trans->transid, due to moving * some inode from it to some other directory). */ if (IS_ERR(inode)) { int ret = PTR_ERR(inode); if (ret != -ENOENT) return ret; ret = conflicting_inode_is_dir(root, ino, path); /* Not a directory or we got an error. */ if (ret <= 0) return ret; /* Conflicting inode is a directory, so we'll log its parent. */ ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } /* * If the inode was already logged skip it - otherwise we can hit an * infinite loop. Example: * * From the commit root (previous transaction) we have the following * inodes: * * inode 257 a directory * inode 258 with references "zz" and "zz_link" on inode 257 * inode 259 with reference "a" on inode 257 * * And in the current (uncommitted) transaction we have: * * inode 257 a directory, unchanged * inode 258 with references "a" and "a2" on inode 257 * inode 259 with reference "zz_link" on inode 257 * inode 261 with reference "zz" on inode 257 * * When logging inode 261 the following infinite loop could * happen if we don't skip already logged inodes: * * - we detect inode 258 as a conflicting inode, with inode 261 * on reference "zz", and log it; * * - we detect inode 259 as a conflicting inode, with inode 258 * on reference "a", and log it; * * - we detect inode 258 as a conflicting inode, with inode 259 * on reference "zz_link", and log it - again! After this we * repeat the above steps forever. * * Here we can use need_log_inode() because we only need to log the * inode in LOG_INODE_EXISTS mode and rename operations update the log, * so that the log ends up with the new name and without the old name. */ if (!need_log_inode(trans, BTRFS_I(inode))) { btrfs_add_delayed_iput(BTRFS_I(inode)); return 0; } btrfs_add_delayed_iput(BTRFS_I(inode)); ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } static int log_conflicting_inodes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int ret = 0; /* * Conflicting inodes are logged by the first call to btrfs_log_inode(), * otherwise we could have unbounded recursion of btrfs_log_inode() * calls. This check guarantees we can have only 1 level of recursion. */ if (ctx->logging_conflict_inodes) return 0; ctx->logging_conflict_inodes = true; /* * New conflicting inodes may be found and added to the list while we * are logging a conflicting inode, so keep iterating while the list is * not empty. */ while (!list_empty(&ctx->conflict_inodes)) { struct btrfs_ino_list *curr; struct inode *inode; u64 ino; u64 parent; curr = list_first_entry(&ctx->conflict_inodes, struct btrfs_ino_list, list); ino = curr->ino; parent = curr->parent; list_del(&curr->list); kfree(curr); inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was * deleted in the current transaction, we need to log its parent * directory. See the comment at add_conflicting_inode(). */ if (IS_ERR(inode)) { ret = PTR_ERR(inode); if (ret != -ENOENT) break; inode = btrfs_iget_logging(parent, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); break; } /* * Always log the directory, we cannot make this * conditional on need_log_inode() because the directory * might have been logged in LOG_INODE_EXISTS mode or * the dir index of the conflicting inode is not in a * dir index key range logged for the directory. So we * must make sure the deletion is recorded. */ ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_ALL, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) break; continue; } /* * Here we can use need_log_inode() because we only need to log * the inode in LOG_INODE_EXISTS mode and rename operations * update the log, so that the log ends up with the new name and * without the old name. * * We did this check at add_conflicting_inode(), but here we do * it again because if some other task logged the inode after * that, we can avoid doing it again. */ if (!need_log_inode(trans, BTRFS_I(inode))) { btrfs_add_delayed_iput(BTRFS_I(inode)); continue; } /* * We are safe logging the other inode without acquiring its * lock as long as we log with the LOG_INODE_EXISTS mode. We * are safe against concurrent renames of the other inode as * well because during a rename we pin the log and update the * log with the new name before we unpin it. */ ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) break; } ctx->logging_conflict_inodes = false; if (ret) free_conflicting_inodes(ctx); return ret; } static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_key *min_key, const struct btrfs_key *max_key, struct btrfs_path *path, struct btrfs_path *dst_path, const u64 logged_isize, const int inode_only, struct btrfs_log_ctx *ctx, bool *need_log_inode_item) { const u64 i_size = i_size_read(&inode->vfs_inode); struct btrfs_root *root = inode->root; int ins_start_slot = 0; int ins_nr = 0; int ret; while (1) { ret = btrfs_search_forward(root, min_key, path, trans->transid); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } again: /* Note, ins_nr might be > 0 here, cleanup outside the loop */ if (min_key->objectid != max_key->objectid) break; if (min_key->type > max_key->type) break; if (min_key->type == BTRFS_INODE_ITEM_KEY) { *need_log_inode_item = false; } else if (min_key->type == BTRFS_EXTENT_DATA_KEY && min_key->offset >= i_size) { /* * Extents at and beyond eof are logged with * btrfs_log_prealloc_extents(). * Only regular files have BTRFS_EXTENT_DATA_KEY keys, * and no keys greater than that, so bail out. */ break; } else if ((min_key->type == BTRFS_INODE_REF_KEY || min_key->type == BTRFS_INODE_EXTREF_KEY) && (inode->generation == trans->transid || ctx->logging_conflict_inodes)) { u64 other_ino = 0; u64 other_parent = 0; ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], min_key, inode, &other_ino, &other_parent); if (ret < 0) { return ret; } else if (ret > 0 && other_ino != btrfs_ino(BTRFS_I(ctx->inode))) { if (ins_nr > 0) { ins_nr++; } else { ins_nr = 1; ins_start_slot = path->slots[0]; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; btrfs_release_path(path); ret = add_conflicting_inode(trans, root, path, other_ino, other_parent, ctx); if (ret) return ret; goto next_key; } } else if (min_key->type == BTRFS_XATTR_ITEM_KEY) { /* Skip xattrs, logged later with btrfs_log_all_xattrs() */ if (ins_nr == 0) goto next_slot; ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; goto next_slot; } if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; goto next_slot; } else if (!ins_nr) { ins_start_slot = path->slots[0]; ins_nr = 1; goto next_slot; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 1; ins_start_slot = path->slots[0]; next_slot: path->slots[0]++; if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key_to_cpu(path->nodes[0], min_key, path->slots[0]); goto again; } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; } btrfs_release_path(path); next_key: if (min_key->offset < (u64)-1) { min_key->offset++; } else if (min_key->type < max_key->type) { min_key->type++; min_key->offset = 0; } else { break; } /* * We may process many leaves full of items for our inode, so * avoid monopolizing a cpu for too long by rescheduling while * not holding locks on any tree. */ cond_resched(); } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret) return ret; } if (inode_only == LOG_INODE_ALL && S_ISREG(inode->vfs_inode.i_mode)) { /* * Release the path because otherwise we might attempt to double * lock the same leaf with btrfs_log_prealloc_extents() below. */ btrfs_release_path(path); ret = btrfs_log_prealloc_extents(trans, inode, dst_path, ctx); } return ret; } static int insert_delayed_items_batch(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, const struct btrfs_item_batch *batch, const struct btrfs_delayed_item *first_item) { const struct btrfs_delayed_item *curr = first_item; int ret; ret = btrfs_insert_empty_items(trans, log, path, batch); if (ret) return ret; for (int i = 0; i < batch->nr; i++) { char *data_ptr; data_ptr = btrfs_item_ptr(path->nodes[0], path->slots[0], char); write_extent_buffer(path->nodes[0], &curr->data, (unsigned long)data_ptr, curr->data_len); curr = list_next_entry(curr, log_list); path->slots[0]++; } btrfs_release_path(path); return 0; } static int log_delayed_insertion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { /* 195 (4095 bytes of keys and sizes) fits in a single 4K page. */ const int max_batch_size = 195; const int leaf_data_size = BTRFS_LEAF_DATA_SIZE(trans->fs_info); const u64 ino = btrfs_ino(inode); struct btrfs_root *log = inode->root->log_root; struct btrfs_item_batch batch = { .nr = 0, .total_data_size = 0, }; const struct btrfs_delayed_item *first = NULL; const struct btrfs_delayed_item *curr; char *ins_data; struct btrfs_key *ins_keys; u32 *ins_sizes; u64 curr_batch_size = 0; int batch_idx = 0; int ret; /* We are adding dir index items to the log tree. */ lockdep_assert_held(&inode->log_mutex); /* * We collect delayed items before copying index keys from the subvolume * to the log tree. However just after we collected them, they may have * been flushed (all of them or just some of them), and therefore we * could have copied them from the subvolume tree to the log tree. * So find the first delayed item that was not yet logged (they are * sorted by index number). */ list_for_each_entry(curr, delayed_ins_list, log_list) { if (curr->index > inode->last_dir_index_offset) { first = curr; break; } } /* Empty list or all delayed items were already logged. */ if (!first) return 0; ins_data = kmalloc(max_batch_size * sizeof(u32) + max_batch_size * sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; batch.data_sizes = ins_sizes; ins_keys = (struct btrfs_key *)(ins_data + max_batch_size * sizeof(u32)); batch.keys = ins_keys; curr = first; while (!list_entry_is_head(curr, delayed_ins_list, log_list)) { const u32 curr_size = curr->data_len + sizeof(struct btrfs_item); if (curr_batch_size + curr_size > leaf_data_size || batch.nr == max_batch_size) { ret = insert_delayed_items_batch(trans, log, path, &batch, first); if (ret) goto out; batch_idx = 0; batch.nr = 0; batch.total_data_size = 0; curr_batch_size = 0; first = curr; } ins_sizes[batch_idx] = curr->data_len; ins_keys[batch_idx].objectid = ino; ins_keys[batch_idx].type = BTRFS_DIR_INDEX_KEY; ins_keys[batch_idx].offset = curr->index; curr_batch_size += curr_size; batch.total_data_size += curr->data_len; batch.nr++; batch_idx++; curr = list_next_entry(curr, log_list); } ASSERT(batch.nr >= 1); ret = insert_delayed_items_batch(trans, log, path, &batch, first); curr = list_last_entry(delayed_ins_list, struct btrfs_delayed_item, log_list); inode->last_dir_index_offset = curr->index; out: kfree(ins_data); return ret; } static int log_delayed_deletions_full(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); const struct btrfs_delayed_item *curr; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { u64 first_dir_index = curr->index; u64 last_dir_index; const struct btrfs_delayed_item *next; int ret; /* * Find a range of consecutive dir index items to delete. Like * this we log a single dir range item spanning several contiguous * dir items instead of logging one range item per dir index item. */ next = list_next_entry(curr, log_list); while (!list_entry_is_head(next, delayed_del_list, log_list)) { if (next->index != curr->index + 1) break; curr = next; next = list_next_entry(next, log_list); } last_dir_index = curr->index; ASSERT(last_dir_index >= first_dir_index); ret = insert_dir_log_key(trans, inode->root->log_root, path, ino, first_dir_index, last_dir_index); if (ret) return ret; curr = list_next_entry(curr, log_list); } return 0; } static int batch_delete_dir_index_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx, const struct list_head *delayed_del_list, const struct btrfs_delayed_item *first, const struct btrfs_delayed_item **last_ret) { const struct btrfs_delayed_item *next; struct extent_buffer *leaf = path->nodes[0]; const int last_slot = btrfs_header_nritems(leaf) - 1; int slot = path->slots[0] + 1; const u64 ino = btrfs_ino(inode); next = list_next_entry(first, log_list); while (slot < last_slot && !list_entry_is_head(next, delayed_del_list, log_list)) { struct btrfs_key key; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY || key.offset != next->index) break; slot++; *last_ret = next; next = list_next_entry(next, log_list); } return btrfs_del_items(trans, inode->root->log_root, path, path->slots[0], slot - path->slots[0]); } static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; key.objectid = btrfs_ino(inode); key.type = BTRFS_DIR_INDEX_KEY; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { const struct btrfs_delayed_item *last = curr; u64 first_dir_index = curr->index; u64 last_dir_index; bool deleted_items = false; int ret; key.offset = curr->index; ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { return ret; } else if (ret == 0) { ret = batch_delete_dir_index_items(trans, inode, path, ctx, delayed_del_list, curr, &last); if (ret) return ret; deleted_items = true; } btrfs_release_path(path); /* * If we deleted items from the leaf, it means we have a range * item logging their range, so no need to add one or update an * existing one. Otherwise we have to log a dir range item. */ if (deleted_items) goto next_batch; last_dir_index = last->index; ASSERT(last_dir_index >= first_dir_index); /* * If this range starts right after where the previous one ends, * then we want to reuse the previous range item and change its * end offset to the end of this range. This is just to minimize * leaf space usage, by avoiding adding a new range item. */ if (last_range_end != 0 && first_dir_index == last_range_end + 1) first_dir_index = last_range_start; ret = insert_dir_log_key(trans, log, path, key.objectid, first_dir_index, last_dir_index); if (ret) return ret; last_range_start = first_dir_index; last_range_end = last_dir_index; next_batch: curr = list_next_entry(last, log_list); } return 0; } static int log_delayed_deletion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { /* * We are deleting dir index items from the log tree or adding range * items to it. */ lockdep_assert_held(&inode->log_mutex); if (list_empty(delayed_del_list)) return 0; if (ctx->logged_before) return log_delayed_deletions_incremental(trans, inode, path, delayed_del_list, ctx); return log_delayed_deletions_full(trans, inode, path, delayed_del_list, ctx); } /* * Similar logic as for log_new_dir_dentries(), but it iterates over the delayed * items instead of the subvolume tree. */ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { const bool orig_log_new_dentries = ctx->log_new_dentries; struct btrfs_delayed_item *item; int ret = 0; /* * No need for the log mutex, plus to avoid potential deadlocks or * lockdep annotations due to nesting of delayed inode mutexes and log * mutexes. */ lockdep_assert_not_held(&inode->log_mutex); ASSERT(!ctx->logging_new_delayed_dentries); ctx->logging_new_delayed_dentries = true; list_for_each_entry(item, delayed_ins_list, log_list) { struct btrfs_dir_item *dir_item; struct inode *di_inode; struct btrfs_key key; int log_mode = LOG_INODE_EXISTS; dir_item = (struct btrfs_dir_item *)item->data; btrfs_disk_key_to_cpu(&key, &dir_item->location); if (key.type == BTRFS_ROOT_ITEM_KEY) continue; di_inode = btrfs_iget_logging(key.objectid, inode->root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); break; } if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(BTRFS_I(di_inode)); continue; } if (btrfs_stack_dir_ftype(dir_item) == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, BTRFS_I(di_inode), ctx); btrfs_add_delayed_iput(BTRFS_I(di_inode)); if (ret) break; } ctx->log_new_dentries = orig_log_new_dentries; ctx->logging_new_delayed_dentries = false; return ret; } /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. * * Any items from this inode changed by the current transaction are copied * to the log tree. An extra reference is taken on any extents in this * file, allowing us to avoid a whole pile of corner cases around logging * blocks that have been removed from the tree. * * See LOG_INODE_ALL and related defines for a description of what inode_only * does. * * This handles both files and directories. */ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; struct btrfs_key max_key; struct btrfs_root *log = inode->root->log_root; int ret; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; bool xattrs_logged = false; bool inode_item_dropped = true; bool full_dir_logging = false; LIST_HEAD(delayed_ins_list); LIST_HEAD(delayed_del_list); path = btrfs_alloc_path(); if (!path) return -ENOMEM; dst_path = btrfs_alloc_path(); if (!dst_path) { btrfs_free_path(path); return -ENOMEM; } min_key.objectid = ino; min_key.type = BTRFS_INODE_ITEM_KEY; min_key.offset = 0; max_key.objectid = ino; /* today the code can only do partial logging of directories */ if (S_ISDIR(inode->vfs_inode.i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else max_key.type = (u8)-1; max_key.offset = (u64)-1; if (S_ISDIR(inode->vfs_inode.i_mode) && inode_only == LOG_INODE_ALL) full_dir_logging = true; /* * If we are logging a directory while we are logging dentries of the * delayed items of some other inode, then we need to flush the delayed * items of this directory and not log the delayed items directly. This * is to prevent more than one level of recursion into btrfs_log_inode() * by having something like this: * * $ mkdir -p a/b/c/d/e/f/g/h/... * $ xfs_io -c "fsync" a * * Where all directories in the path did not exist before and are * created in the current transaction. * So in such a case we directly log the delayed items of the main * directory ("a") without flushing them first, while for each of its * subdirectories we flush their delayed items before logging them. * This prevents a potential unbounded recursion like this: * * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * (...) * * We have thresholds for the maximum number of delayed items to have in * memory, and once they are hit, the items are flushed asynchronously. * However the limit is quite high, so lets prevent deep levels of * recursion to happen by limiting the maximum depth to be 1. */ if (full_dir_logging && ctx->logging_new_delayed_dentries) { ret = btrfs_commit_inode_delayed_items(trans, inode); if (ret) goto out; } mutex_lock(&inode->log_mutex); /* * For symlinks, we must always log their content, which is stored in an * inline extent, otherwise we could end up with an empty symlink after * log replay, which is invalid on linux (symlink(2) returns -ENOENT if * one attempts to create an empty symlink). * We don't need to worry about flushing delalloc, because when we create * the inline extent when the symlink is created (we never have delalloc * for symlinks). */ if (S_ISLNK(inode->vfs_inode.i_mode)) inode_only = LOG_INODE_ALL; /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if * the inode was previously logged in this transaction. */ ret = inode_logged(trans, inode, path); if (ret < 0) goto out_unlock; ctx->logged_before = (ret == 1); ret = 0; /* * This is for cases where logging a directory could result in losing a * a file after replaying the log. For example, if we move a file from a * directory A to a directory B, then fsync directory A, we have no way * to known the file was moved from A to B, so logging just A would * result in losing the file after a log replay. */ if (full_dir_logging && inode->last_unlink_trans >= trans->transid) { ret = BTRFS_LOG_FORCE_COMMIT; goto out_unlock; } /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ if (S_ISDIR(inode->vfs_inode.i_mode)) { clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, BTRFS_XATTR_ITEM_KEY); } else { if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) { /* * Make sure the new inode item we write to the log has * the same isize as the current one (if it exists). * This is necessary to prevent data loss after log * replay, and also to prevent doing a wrong expanding * truncate - for e.g. create file, write 4K into offset * 0, fsync, write 4K into offset 4096, add hard link, * fsync some other file (to sync log), power fail - if * we use the inode's current i_size, after log replay * we get a 8Kb file, with the last 4Kb extent as a hole * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ ret = logged_inode_size(log, inode, path, &logged_isize); if (ret) goto out_unlock; } if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) { if (inode_only == LOG_INODE_EXISTS) { max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = truncate_inode_items(trans, log, inode, 0, 0); } } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags) || inode_only == LOG_INODE_EXISTS) { if (inode_only == LOG_INODE_ALL) fast_search = true; max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { if (inode_only == LOG_INODE_ALL) fast_search = true; inode_item_dropped = false; goto log_extents; } } if (ret) goto out_unlock; /* * If we are logging a directory in full mode, collect the delayed items * before iterating the subvolume tree, so that we don't miss any new * dir index items in case they get flushed while or right after we are * iterating the subvolume tree. */ if (full_dir_logging && !ctx->logging_new_delayed_dentries) btrfs_log_get_delayed_items(inode, &delayed_ins_list, &delayed_del_list); ret = copy_inode_items_to_log(trans, inode, &min_key, &max_key, path, dst_path, logged_isize, inode_only, ctx, &need_log_inode_item); if (ret) goto out_unlock; btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; xattrs_logged = true; if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_holes(trans, inode, path); if (ret) goto out_unlock; } log_extents: btrfs_release_path(path); btrfs_release_path(dst_path); if (need_log_inode_item) { ret = log_inode_item(trans, log, dst_path, inode, inode_item_dropped); if (ret) goto out_unlock; /* * If we are doing a fast fsync and the inode was logged before * in this transaction, we don't need to log the xattrs because * they were logged before. If xattrs were added, changed or * deleted since the last time we logged the inode, then we have * already logged them because the inode had the runtime flag * BTRFS_INODE_COPY_EVERYTHING set. */ if (!xattrs_logged && inode->logged_trans < trans->transid) { ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; btrfs_release_path(path); } } if (fast_search) { ret = btrfs_log_changed_extents(trans, inode, dst_path, ctx); if (ret) goto out_unlock; } else if (inode_only == LOG_INODE_ALL) { struct extent_map *em, *n; write_lock(&em_tree->lock); list_for_each_entry_safe(em, n, &em_tree->modified_extents, list) list_del_init(&em->list); write_unlock(&em_tree->lock); } if (full_dir_logging) { ret = log_directory_changes(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; ret = log_delayed_insertion_items(trans, inode, path, &delayed_ins_list, ctx); if (ret) goto out_unlock; ret = log_delayed_deletion_items(trans, inode, path, &delayed_del_list, ctx); if (ret) goto out_unlock; } spin_lock(&inode->lock); inode->logged_trans = trans->transid; /* * Don't update last_log_commit if we logged that an inode exists. * We do this for three reasons: * * 1) We might have had buffered writes to this inode that were * flushed and had their ordered extents completed in this * transaction, but we did not previously log the inode with * LOG_INODE_ALL. Later the inode was evicted and after that * it was loaded again and this LOG_INODE_EXISTS log operation * happened. We must make sure that if an explicit fsync against * the inode is performed later, it logs the new extents, an * updated inode item, etc, and syncs the log. The same logic * applies to direct IO writes instead of buffered writes. * * 2) When we log the inode with LOG_INODE_EXISTS, its inode item * is logged with an i_size of 0 or whatever value was logged * before. If later the i_size of the inode is increased by a * truncate operation, the log is synced through an fsync of * some other inode and then finally an explicit fsync against * this inode is made, we must make sure this fsync logs the * inode with the new i_size, the hole between old i_size and * the new i_size, and syncs the log. * * 3) If we are logging that an ancestor inode exists as part of * logging a new name from a link or rename operation, don't update * its last_log_commit - otherwise if an explicit fsync is made * against an ancestor, the fsync considers the inode in the log * and doesn't sync the log, resulting in the ancestor missing after * a power failure unless the log was synced as part of an fsync * against any other unrelated inode. */ if (inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); /* * Reset the last_reflink_trans so that the next fsync does not need to * go through the slower path when logging extents and their checksums. */ if (inode_only == LOG_INODE_ALL) inode->last_reflink_trans = 0; out_unlock: mutex_unlock(&inode->log_mutex); out: btrfs_free_path(path); btrfs_free_path(dst_path); if (ret) free_conflicting_inodes(ctx); else ret = log_conflicting_inodes(trans, inode->root, ctx); if (full_dir_logging && !ctx->logging_new_delayed_dentries) { if (!ret) ret = log_new_delayed_dentries(trans, inode, &delayed_ins_list, ctx); btrfs_log_put_delayed_items(inode, &delayed_ins_list, &delayed_del_list); } return ret; } static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_log_ctx *ctx) { int ret; struct btrfs_path *path; struct btrfs_key key; struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->skip_locking = 1; path->search_commit_root = 1; key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; u32 cur_offset = 0; u32 item_size; unsigned long ptr; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); /* BTRFS_INODE_EXTREF_KEY is BTRFS_INODE_REF_KEY + 1 */ if (key.objectid != ino || key.type > BTRFS_INODE_EXTREF_KEY) break; item_size = btrfs_item_size(leaf, slot); ptr = btrfs_item_ptr_offset(leaf, slot); while (cur_offset < item_size) { struct btrfs_key inode_key; struct inode *dir_inode; inode_key.type = BTRFS_INODE_ITEM_KEY; inode_key.offset = 0; if (key.type == BTRFS_INODE_EXTREF_KEY) { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *) (ptr + cur_offset); inode_key.objectid = btrfs_inode_extref_parent( leaf, extref); cur_offset += sizeof(*extref); cur_offset += btrfs_inode_extref_name_len(leaf, extref); } else { inode_key.objectid = key.offset; cur_offset = item_size; } dir_inode = btrfs_iget_logging(inode_key.objectid, root); /* * If the parent inode was deleted, return an error to * fallback to a transaction commit. This is to prevent * getting an inode that was moved from one parent A to * a parent B, got its former parent A deleted and then * it got fsync'ed, from existing at both parents after * a log replay (and the old parent still existing). * Example: * * mkdir /mnt/A * mkdir /mnt/B * touch /mnt/B/bar * sync * mv /mnt/B/bar /mnt/A/bar * mv -T /mnt/A /mnt/B * fsync /mnt/B/bar * <power fail> * * If we ignore the old parent B which got deleted, * after a log replay we would have file bar linked * at both parents and the old parent B would still * exist. */ if (IS_ERR(dir_inode)) { ret = PTR_ERR(dir_inode); goto out; } if (!need_log_inode(trans, BTRFS_I(dir_inode))) { btrfs_add_delayed_iput(BTRFS_I(dir_inode)); continue; } ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, BTRFS_I(dir_inode), LOG_INODE_ALL, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, BTRFS_I(dir_inode), ctx); btrfs_add_delayed_iput(BTRFS_I(dir_inode)); if (ret) goto out; } path->slots[0]++; } ret = 0; out: btrfs_free_path(path); return ret; } static int log_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_key found_key; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); while (true) { struct extent_buffer *leaf; int slot; struct btrfs_key search_key; struct inode *inode; u64 ino; int ret = 0; btrfs_release_path(path); ino = found_key.offset; search_key.objectid = found_key.offset; search_key.type = BTRFS_INODE_ITEM_KEY; search_key.offset = 0; inode = btrfs_iget_logging(ino, root); if (IS_ERR(inode)) return PTR_ERR(inode); if (BTRFS_I(inode)->generation >= trans->transid && need_log_inode(trans, BTRFS_I(inode))) ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) return ret; if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID) break; search_key.type = BTRFS_INODE_REF_KEY; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) return ret; leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) return -ENOENT; leaf = path->nodes[0]; slot = path->slots[0]; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != search_key.objectid || found_key.type != BTRFS_INODE_REF_KEY) return -ENOENT; } return 0; } static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct dentry *old_parent = NULL; struct super_block *sb = inode->vfs_inode.i_sb; int ret = 0; while (true) { if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; inode = BTRFS_I(d_inode(parent)); if (root != inode->root) break; if (inode->generation >= trans->transid && need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, inode, LOG_INODE_EXISTS, ctx); if (ret) break; } if (IS_ROOT(parent)) break; parent = dget_parent(parent); dput(old_parent); old_parent = parent; } dput(old_parent); return ret; } static int log_all_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); struct btrfs_path *path; struct btrfs_key search_key; int ret; /* * For a single hard link case, go through a fast path that does not * need to iterate the fs/subvolume tree. */ if (inode->vfs_inode.i_nlink < 2) return log_new_ancestors_fast(trans, inode, parent, ctx); path = btrfs_alloc_path(); if (!path) return -ENOMEM; search_key.objectid = ino; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto out; if (ret == 0) path->slots[0]++; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; struct btrfs_key found_key; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != ino || found_key.type > BTRFS_INODE_EXTREF_KEY) break; /* * Don't deal with extended references because they are rare * cases and too complex to deal with (we would need to keep * track of which subitem we are processing for each item in * this loop, etc). So just return some error to fallback to * a transaction commit. */ if (found_key.type == BTRFS_INODE_EXTREF_KEY) { ret = -EMLINK; goto out; } /* * Logging ancestors needs to do more searches on the fs/subvol * tree, so it releases the path as needed to avoid deadlocks. * Keep track of the last inode ref key and resume from that key * after logging all new ancestors for the current hard link. */ memcpy(&search_key, &found_key, sizeof(search_key)); ret = log_new_ancestors(trans, root, path, ctx); if (ret) goto out; btrfs_release_path(path); goto again; } ret = 0; out: btrfs_free_path(path); return ret; } /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref * only logging is done of any parent directories that are older than * the last committed transaction */ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; bool log_dentries = false; if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = BTRFS_LOG_FORCE_COMMIT; goto end_no_trans; } if (btrfs_root_refs(&root->root_item) == 0) { ret = BTRFS_LOG_FORCE_COMMIT; goto end_no_trans; } /* * Skip already logged inodes or inodes corresponding to tmpfiles * (since logging them is pointless, a link count of 0 means they * will never be accessible). */ if ((btrfs_inode_in_log(inode, trans->transid) && list_empty(&ctx->ordered_extents)) || inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } ret = start_log_trans(trans, root, ctx); if (ret) goto end_no_trans; ret = btrfs_log_inode(trans, inode, inode_only, ctx); if (ret) goto end_trans; /* * for regular files, if its inode is already on disk, we don't * have to worry about the parents at all. This is because * we can use the last_unlink_trans field to record renames * and other fun in this file. */ if (S_ISREG(inode->vfs_inode.i_mode) && inode->generation < trans->transid && inode->last_unlink_trans < trans->transid) { ret = 0; goto end_trans; } if (S_ISDIR(inode->vfs_inode.i_mode) && ctx->log_new_dentries) log_dentries = true; /* * On unlink we must make sure all our current and old parent directory * inodes are fully logged. This is to prevent leaving dangling * directory index entries in directories that were our parents but are * not anymore. Not doing this results in old parent directory being * impossible to delete after log replay (rmdir will always fail with * error -ENOTEMPTY). * * Example 1: * * mkdir testdir * touch testdir/foo * ln testdir/foo testdir/bar * sync * unlink testdir/bar * xfs_io -c fsync testdir/foo * <power failure> * mount fs, triggers log replay * * If we don't log the parent directory (testdir), after log replay the * directory still has an entry pointing to the file inode using the bar * name, but a matching BTRFS_INODE_[REF|EXTREF]_KEY does not exist and * the file inode has a link count of 1. * * Example 2: * * mkdir testdir * touch foo * ln foo testdir/foo2 * ln foo testdir/foo3 * sync * unlink testdir/foo3 * xfs_io -c fsync foo * <power failure> * mount fs, triggers log replay * * Similar as the first example, after log replay the parent directory * testdir still has an entry pointing to the inode file with name foo3 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item * and has a link count of 2. */ if (inode->last_unlink_trans >= trans->transid) { ret = btrfs_log_all_parents(trans, inode, ctx); if (ret) goto end_trans; } ret = log_all_new_ancestors(trans, inode, parent, ctx); if (ret) goto end_trans; if (log_dentries) ret = log_new_dir_dentries(trans, inode, ctx); else ret = 0; end_trans: if (ret < 0) { btrfs_set_log_full_commit(trans); ret = BTRFS_LOG_FORCE_COMMIT; } if (ret) btrfs_remove_log_ctx(root, ctx); btrfs_end_log_trans(root); end_no_trans: return ret; } /* * it is not safe to log dentry if the chunk root has added new * chunks. This returns 0 if the dentry was logged, and 1 otherwise. * If this returns 1, you must commit the transaction to safely get your * data on disk. */ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct dentry *dentry, struct btrfs_log_ctx *ctx) { struct dentry *parent = dget_parent(dentry); int ret; ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent, LOG_INODE_ALL, ctx); dput(parent); return ret; } /* * should be called during mount to recover any replay any log trees * from the FS */ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) { int ret; struct btrfs_path *path; struct btrfs_trans_handle *trans; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *log; struct btrfs_fs_info *fs_info = log_root_tree->fs_info; struct walk_control wc = { .process_func = process_one_buffer, .stage = LOG_WALK_PIN_ONLY, }; path = btrfs_alloc_path(); if (!path) return -ENOMEM; set_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto error; } wc.trans = trans; wc.pin = 1; ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { btrfs_abort_transaction(trans, ret); goto error; } again: key.objectid = BTRFS_TREE_LOG_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_ROOT_ITEM_KEY; while (1) { ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto error; } if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); btrfs_release_path(path); if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID) break; log = btrfs_read_tree_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); btrfs_abort_transaction(trans, ret); goto error; } wc.replay_dest = btrfs_get_fs_root(fs_info, found_key.offset, true); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); /* * We didn't find the subvol, likely because it was * deleted. This is ok, simply skip this log and go to * the next one. * * We need to exclude the root because we can't have * other log replays overwriting this log as we'll read * it back in a few more times. This will keep our * block from being modified, and we'll just bail for * each subsequent pass. */ if (ret == -ENOENT) ret = btrfs_pin_extent_for_log_replay(trans, log->node); btrfs_put_root(log); if (!ret) goto next; btrfs_abort_transaction(trans, ret); goto error; } wc.replay_dest->log_root = log; ret = btrfs_record_root_in_trans(trans, wc.replay_dest); if (ret) /* The loop needs to continue due to the root refs */ btrfs_abort_transaction(trans, ret); else ret = walk_log_tree(trans, log, &wc); if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { ret = fixup_inode_link_counts(trans, wc.replay_dest, path); if (ret) btrfs_abort_transaction(trans, ret); } if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { struct btrfs_root *root = wc.replay_dest; btrfs_release_path(path); /* * We have just replayed everything, and the highest * objectid of fs roots probably has changed in case * some inode_item's got replayed. * * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ ret = btrfs_init_root_free_objectid(root); if (ret) btrfs_abort_transaction(trans, ret); } wc.replay_dest->log_root = NULL; btrfs_put_root(wc.replay_dest); btrfs_put_root(log); if (ret) goto error; next: if (found_key.offset == 0) break; key.offset = found_key.offset - 1; } btrfs_release_path(path); /* step one is to pin it all, step two is to replay just inodes */ if (wc.pin) { wc.pin = 0; wc.process_func = replay_one_buffer; wc.stage = LOG_WALK_REPLAY_INODES; goto again; } /* step three is to replay everything */ if (wc.stage < LOG_WALK_REPLAY_ALL) { wc.stage++; goto again; } btrfs_free_path(path); /* step 4: commit the transaction, which also unpins the blocks */ ret = btrfs_commit_transaction(trans); if (ret) return ret; log_root_tree->log_root = NULL; clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_put_root(log_root_tree); return 0; error: if (wc.trans) btrfs_end_transaction(wc.trans); clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_free_path(path); return ret; } /* * there are some corner cases where we want to force a full * commit instead of allowing a directory to be logged. * * They revolve around files there were unlinked from the directory, and * this function updates the parent directory so that a full commit is * properly done if it is fsync'd later after the unlinks are done. * * Must be called before the unlink operations (updates to the subvolume tree, * inodes, etc) are done. */ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, bool for_rename) { /* * when we're logging a file, if it hasn't been renamed * or unlinked, and its inode is fully committed on disk, * we don't have to worry about walking up the directory chain * to log its parents. * * So, we use the last_unlink_trans field to put this transid * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ mutex_lock(&inode->log_mutex); inode->last_unlink_trans = trans->transid; mutex_unlock(&inode->log_mutex); if (!for_rename) return; /* * If this directory was already logged, any new names will be logged * with btrfs_log_new_name() and old names will be deleted from the log * tree with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, dir, NULL) == 1) return; /* * If the inode we're about to unlink was logged before, the log will be * properly updated with the new name with btrfs_log_new_name() and the * old name removed with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, inode, NULL) == 1) return; /* * when renaming files across directories, if the directory * there we're unlinking from gets fsync'd later on, there's * no way to find the destination directory later and fsync it * properly. So, we have to be conservative and force commits * so the new name gets discovered. */ mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Make sure that if someone attempts to fsync the parent directory of a deleted * snapshot, it ends up triggering a transaction commit. This is to guarantee * that after replaying the log tree of the parent directory's root we will not * see the snapshot anymore and at log replay time we will not see any log tree * corresponding to the deleted snapshot's root, which could lead to replaying * it after replaying the log tree of the parent directory (which would replay * the snapshot delete operation). * * Must be called before the actual snapshot destroy operation (updates to the * parent root and tree of tree roots trees, etc) are done. */ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir) { mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Update the log after adding a new name for an inode. * * @trans: Transaction handle. * @old_dentry: The dentry associated with the old name and the old * parent directory. * @old_dir: The inode of the previous parent directory for the case * of a rename. For a link operation, it must be NULL. * @old_dir_index: The index number associated with the old name, meaningful * only for rename operations (when @old_dir is not NULL). * Ignored for link operations. * @parent: The dentry associated with the directory under which the * new name is located. * * Call this after adding a new name for an inode, as a result of a link or * rename operation, and it will properly update the log to reflect the new name. */ void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct dentry *old_dentry, struct btrfs_inode *old_dir, u64 old_dir_index, struct dentry *parent) { struct btrfs_inode *inode = BTRFS_I(d_inode(old_dentry)); struct btrfs_root *root = inode->root; struct btrfs_log_ctx ctx; bool log_pinned = false; int ret; /* * this will force the logging code to walk the dentry chain * up for the file */ if (!S_ISDIR(inode->vfs_inode.i_mode)) inode->last_unlink_trans = trans->transid; /* * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ ret = inode_logged(trans, inode, NULL); if (ret < 0) { goto out; } else if (ret == 0) { if (!old_dir) return; /* * If the inode was not logged and we are doing a rename (old_dir is not * NULL), check if old_dir was logged - if it was not we can return and * do nothing. */ ret = inode_logged(trans, old_dir, NULL); if (ret < 0) goto out; else if (ret == 0) return; } ret = 0; /* * If we are doing a rename (old_dir is not NULL) from a directory that * was previously logged, make sure that on log replay we get the old * dir entry deleted. This is needed because we will also log the new * name of the renamed inode, so we need to make sure that after log * replay we don't end up with both the new and old dir entries existing. */ if (old_dir && old_dir->logged_trans == trans->transid) { struct btrfs_root *log = old_dir->root->log_root; struct btrfs_path *path; struct fscrypt_name fname; ASSERT(old_dir_index >= BTRFS_DIR_START_INDEX); ret = fscrypt_setup_filename(&old_dir->vfs_inode, &old_dentry->d_name, 0, &fname); if (ret) goto out; /* * We have two inodes to update in the log, the old directory and * the inode that got renamed, so we must pin the log to prevent * anyone from syncing the log until we have updated both inodes * in the log. */ ret = join_running_log_trans(root); /* * At least one of the inodes was logged before, so this should * not fail, but if it does, it's not serious, just bail out and * mark the log for a full commit. */ if (WARN_ON_ONCE(ret < 0)) { fscrypt_free_filename(&fname); goto out; } log_pinned = true; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; fscrypt_free_filename(&fname); goto out; } /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or * still has a dentry in the old directory. We lock the old * directory's log_mutex to ensure the deletion of the old * name is persisted, because during directory logging we * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of * the old name's dir index item is in the delayed items, so * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), &fname.disk_name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its * deletion. */ btrfs_release_path(path); ret = insert_dir_log_key(trans, log, path, btrfs_ino(old_dir), old_dir_index, old_dir_index); } mutex_unlock(&old_dir->log_mutex); btrfs_free_path(path); fscrypt_free_filename(&fname); if (ret < 0) goto out; } btrfs_init_log_ctx(&ctx, &inode->vfs_inode); ctx.logging_new_name = true; btrfs_init_log_ctx_scratch_eb(&ctx); /* * We don't care about the return value. If we fail to log the new name * then we know the next attempt to sync the log will fallback to a full * transaction commit (due to a call to btrfs_set_log_full_commit()), so * we don't need to worry about getting a log committed that has an * inconsistent state after a rename operation. */ btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx); free_extent_buffer(ctx.scratch_eb); ASSERT(list_empty(&ctx.conflict_inodes)); out: /* * If an error happened mark the log for a full commit because it's not * consistent and up to date or we couldn't find out if one of the * inodes was logged before in this transaction. Do it before unpinning * the log, to avoid any races with someone else trying to commit it. */ if (ret < 0) btrfs_set_log_full_commit(trans); if (log_pinned) btrfs_end_log_trans(root); } |
| 15 1 8 9 5 3 1 11 5 2 6 10 9 9 5 5 1 1 1 2 5 1 1 1 2 3 3 5 2 4 2 2 2 2 2 1 2 2 1 3 1 1 1 2 1 1 7 3 4 1 1 9 1 2 3 5 1 2 2 2 1 1 15 2 2 3 7 1 1 2 1 1 1 12 5 5 106 2 1 9 9 8 2 4 19 2 3 7 5 8 10 7 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 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 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS ioctl operations. * * Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #include <linux/fs.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/capability.h> /* capable() */ #include <linux/uaccess.h> /* copy_from_user(), copy_to_user() */ #include <linux/vmalloc.h> #include <linux/compat.h> /* compat_ptr() */ #include <linux/mount.h> /* mnt_want_write_file(), mnt_drop_write_file() */ #include <linux/buffer_head.h> #include <linux/fileattr.h> #include "nilfs.h" #include "segment.h" #include "bmap.h" #include "cpfile.h" #include "sufile.h" #include "dat.h" /** * nilfs_ioctl_wrap_copy - wrapping function of get/set metadata info * @nilfs: nilfs object * @argv: vector of arguments from userspace * @dir: set of direction flags * @dofunc: concrete function of get/set metadata info * * Description: nilfs_ioctl_wrap_copy() gets/sets metadata info by means of * calling dofunc() function on the basis of @argv argument. * * Return Value: On success, 0 is returned and requested metadata info * is copied into userspace. On error, one of the following * negative error codes is returned. * * %-EINVAL - Invalid arguments from userspace. * * %-ENOMEM - Insufficient amount of memory available. * * %-EFAULT - Failure during execution of requested operation. */ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, struct nilfs_argv *argv, int dir, ssize_t (*dofunc)(struct the_nilfs *, __u64 *, int, void *, size_t, size_t)) { void *buf; void __user *base = (void __user *)(unsigned long)argv->v_base; size_t maxmembs, total, n; ssize_t nr; int ret, i; __u64 pos, ppos; if (argv->v_nmembs == 0) return 0; if ((size_t)argv->v_size > PAGE_SIZE) return -EINVAL; /* * Reject pairs of a start item position (argv->v_index) and a * total count (argv->v_nmembs) which leads position 'pos' to * overflow by the increment at the end of the loop. */ if (argv->v_index > ~(__u64)0 - argv->v_nmembs) return -EINVAL; buf = (void *)get_zeroed_page(GFP_NOFS); if (unlikely(!buf)) return -ENOMEM; maxmembs = PAGE_SIZE / argv->v_size; ret = 0; total = 0; pos = argv->v_index; for (i = 0; i < argv->v_nmembs; i += n) { n = (argv->v_nmembs - i < maxmembs) ? argv->v_nmembs - i : maxmembs; if ((dir & _IOC_WRITE) && copy_from_user(buf, base + argv->v_size * i, argv->v_size * n)) { ret = -EFAULT; break; } ppos = pos; nr = dofunc(nilfs, &pos, argv->v_flags, buf, argv->v_size, n); if (nr < 0) { ret = nr; break; } if ((dir & _IOC_READ) && copy_to_user(base + argv->v_size * i, buf, argv->v_size * nr)) { ret = -EFAULT; break; } total += nr; if ((size_t)nr < n) break; if (pos == ppos) pos += n; } argv->v_nmembs = total; free_pages((unsigned long)buf, 0); return ret; } /** * nilfs_fileattr_get - ioctl to support lsattr */ int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); fileattr_fill_flags(fa, NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE); return 0; } /** * nilfs_fileattr_set - ioctl to support chattr */ int nilfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct nilfs_transaction_info ti; unsigned int flags, oldflags; int ret; if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; flags = nilfs_mask_flags(inode->i_mode, fa->flags); ret = nilfs_transaction_begin(inode->i_sb, &ti, 0); if (ret) return ret; oldflags = NILFS_I(inode)->i_flags & ~FS_FL_USER_MODIFIABLE; NILFS_I(inode)->i_flags = oldflags | (flags & FS_FL_USER_MODIFIABLE); nilfs_set_inode_flags(inode); inode_set_ctime_current(inode); if (IS_SYNC(inode)) nilfs_set_transaction_flag(NILFS_TI_SYNC); nilfs_mark_inode_dirty(inode); return nilfs_transaction_commit(inode->i_sb); } /** * nilfs_ioctl_getversion - get info about a file's version (generation number) */ static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp) { return put_user(inode->i_generation, (int __user *)argp); } /** * nilfs_ioctl_change_cpmode - change checkpoint mode (checkpoint/snapshot) * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_change_cpmode() function changes mode of * given checkpoint between checkpoint and snapshot state. This ioctl * is used in chcp and mkcp utilities. * * Return Value: On success, 0 is returned and mode of a checkpoint is * changed. On error, one of the following negative error codes * is returned. * * %-EPERM - Operation not permitted. * * %-EFAULT - Failure during checkpoint mode changing. */ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_transaction_info ti; struct nilfs_cpmode cpmode; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) return ret; ret = -EFAULT; if (copy_from_user(&cpmode, argp, sizeof(cpmode))) goto out; mutex_lock(&nilfs->ns_snapshot_mount_mutex); nilfs_transaction_begin(inode->i_sb, &ti, 0); ret = nilfs_cpfile_change_cpmode( nilfs->ns_cpfile, cpmode.cm_cno, cpmode.cm_mode); if (unlikely(ret < 0)) nilfs_transaction_abort(inode->i_sb); else nilfs_transaction_commit(inode->i_sb); /* never fails */ mutex_unlock(&nilfs->ns_snapshot_mount_mutex); out: mnt_drop_write_file(filp); return ret; } /** * nilfs_ioctl_delete_checkpoint - remove checkpoint * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_delete_checkpoint() function removes * checkpoint from NILFS2 file system. This ioctl is used in rmcp * utility. * * Return Value: On success, 0 is returned and a checkpoint is * removed. On error, one of the following negative error codes * is returned. * * %-EPERM - Operation not permitted. * * %-EFAULT - Failure during checkpoint removing. */ static int nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_transaction_info ti; __u64 cno; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) return ret; ret = -EFAULT; if (copy_from_user(&cno, argp, sizeof(cno))) goto out; nilfs_transaction_begin(inode->i_sb, &ti, 0); ret = nilfs_cpfile_delete_checkpoint(nilfs->ns_cpfile, cno); if (unlikely(ret < 0)) nilfs_transaction_abort(inode->i_sb); else nilfs_transaction_commit(inode->i_sb); /* never fails */ out: mnt_drop_write_file(filp); return ret; } /** * nilfs_ioctl_do_get_cpinfo - callback method getting info about checkpoints * @nilfs: nilfs object * @posp: pointer on array of checkpoint's numbers * @flags: checkpoint mode (checkpoint or snapshot) * @buf: buffer for storing checkponts' info * @size: size in bytes of one checkpoint info item in array * @nmembs: number of checkpoints in array (numbers and infos) * * Description: nilfs_ioctl_do_get_cpinfo() function returns info about * requested checkpoints. The NILFS_IOCTL_GET_CPINFO ioctl is used in * lscp utility and by nilfs_cleanerd daemon. * * Return value: count of nilfs_cpinfo structures in output buffer. */ static ssize_t nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, void *buf, size_t size, size_t nmembs) { int ret; down_read(&nilfs->ns_segctor_sem); ret = nilfs_cpfile_get_cpinfo(nilfs->ns_cpfile, posp, flags, buf, size, nmembs); up_read(&nilfs->ns_segctor_sem); return ret; } /** * nilfs_ioctl_get_cpstat - get checkpoints statistics * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_get_cpstat() returns information about checkpoints. * The NILFS_IOCTL_GET_CPSTAT ioctl is used by lscp, rmcp utilities * and by nilfs_cleanerd daemon. * * Return Value: On success, 0 is returned, and checkpoints information is * copied into userspace pointer @argp. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EFAULT - Failure during getting checkpoints statistics. */ static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_cpstat cpstat; int ret; down_read(&nilfs->ns_segctor_sem); ret = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat); up_read(&nilfs->ns_segctor_sem); if (ret < 0) return ret; if (copy_to_user(argp, &cpstat, sizeof(cpstat))) ret = -EFAULT; return ret; } /** * nilfs_ioctl_do_get_suinfo - callback method getting segment usage info * @nilfs: nilfs object * @posp: pointer on array of segment numbers * @flags: *not used* * @buf: buffer for storing suinfo array * @size: size in bytes of one suinfo item in array * @nmembs: count of segment numbers and suinfos in array * * Description: nilfs_ioctl_do_get_suinfo() function returns segment usage * info about requested segments. The NILFS_IOCTL_GET_SUINFO ioctl is used * in lssu, nilfs_resize utilities and by nilfs_cleanerd daemon. * * Return value: count of nilfs_suinfo structures in output buffer. */ static ssize_t nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, void *buf, size_t size, size_t nmembs) { int ret; down_read(&nilfs->ns_segctor_sem); ret = nilfs_sufile_get_suinfo(nilfs->ns_sufile, *posp, buf, size, nmembs); up_read(&nilfs->ns_segctor_sem); return ret; } /** * nilfs_ioctl_get_sustat - get segment usage statistics * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_get_sustat() returns segment usage statistics. * The NILFS_IOCTL_GET_SUSTAT ioctl is used in lssu, nilfs_resize utilities * and by nilfs_cleanerd daemon. * * Return Value: On success, 0 is returned, and segment usage information is * copied into userspace pointer @argp. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EFAULT - Failure during getting segment usage statistics. */ static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_sustat sustat; int ret; down_read(&nilfs->ns_segctor_sem); ret = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat); up_read(&nilfs->ns_segctor_sem); if (ret < 0) return ret; if (copy_to_user(argp, &sustat, sizeof(sustat))) ret = -EFAULT; return ret; } /** * nilfs_ioctl_do_get_vinfo - callback method getting virtual blocks info * @nilfs: nilfs object * @posp: *not used* * @flags: *not used* * @buf: buffer for storing array of nilfs_vinfo structures * @size: size in bytes of one vinfo item in array * @nmembs: count of vinfos in array * * Description: nilfs_ioctl_do_get_vinfo() function returns information * on virtual block addresses. The NILFS_IOCTL_GET_VINFO ioctl is used * by nilfs_cleanerd daemon. * * Return value: count of nilfs_vinfo structures in output buffer. */ static ssize_t nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, void *buf, size_t size, size_t nmembs) { int ret; down_read(&nilfs->ns_segctor_sem); ret = nilfs_dat_get_vinfo(nilfs->ns_dat, buf, size, nmembs); up_read(&nilfs->ns_segctor_sem); return ret; } /** * nilfs_ioctl_do_get_bdescs - callback method getting disk block descriptors * @nilfs: nilfs object * @posp: *not used* * @flags: *not used* * @buf: buffer for storing array of nilfs_bdesc structures * @size: size in bytes of one bdesc item in array * @nmembs: count of bdescs in array * * Description: nilfs_ioctl_do_get_bdescs() function returns information * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl * is used by nilfs_cleanerd daemon. * * Return value: count of nilfs_bdescs structures in output buffer. */ static ssize_t nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags, void *buf, size_t size, size_t nmembs) { struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap; struct nilfs_bdesc *bdescs = buf; int ret, i; down_read(&nilfs->ns_segctor_sem); for (i = 0; i < nmembs; i++) { ret = nilfs_bmap_lookup_at_level(bmap, bdescs[i].bd_offset, bdescs[i].bd_level + 1, &bdescs[i].bd_blocknr); if (ret < 0) { if (ret != -ENOENT) { up_read(&nilfs->ns_segctor_sem); return ret; } bdescs[i].bd_blocknr = 0; } } up_read(&nilfs->ns_segctor_sem); return nmembs; } /** * nilfs_ioctl_get_bdescs - get disk block descriptors * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_do_get_bdescs() function returns information * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl * is used by nilfs_cleanerd daemon. * * Return Value: On success, 0 is returned, and disk block descriptors are * copied into userspace pointer @argp. On error, one of the following * negative error codes is returned. * * %-EINVAL - Invalid arguments from userspace. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EFAULT - Failure during getting disk block descriptors. */ static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_argv argv; int ret; if (copy_from_user(&argv, argp, sizeof(argv))) return -EFAULT; if (argv.v_size != sizeof(struct nilfs_bdesc)) return -EINVAL; ret = nilfs_ioctl_wrap_copy(nilfs, &argv, _IOC_DIR(cmd), nilfs_ioctl_do_get_bdescs); if (ret < 0) return ret; if (copy_to_user(argp, &argv, sizeof(argv))) ret = -EFAULT; return ret; } /** * nilfs_ioctl_move_inode_block - prepare data/node block for moving by GC * @inode: inode object * @vdesc: descriptor of virtual block number * @buffers: list of moving buffers * * Description: nilfs_ioctl_move_inode_block() function registers data/node * buffer in the GC pagecache and submit read request. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-ENOENT - Requested block doesn't exist. * * %-EEXIST - Blocks conflict is detected. */ static int nilfs_ioctl_move_inode_block(struct inode *inode, struct nilfs_vdesc *vdesc, struct list_head *buffers) { struct buffer_head *bh; int ret; if (vdesc->vd_flags == 0) ret = nilfs_gccache_submit_read_data( inode, vdesc->vd_offset, vdesc->vd_blocknr, vdesc->vd_vblocknr, &bh); else ret = nilfs_gccache_submit_read_node( inode, vdesc->vd_blocknr, vdesc->vd_vblocknr, &bh); if (unlikely(ret < 0)) { if (ret == -ENOENT) nilfs_crit(inode->i_sb, "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", __func__, vdesc->vd_flags ? "node" : "data", (unsigned long long)vdesc->vd_ino, (unsigned long long)vdesc->vd_cno, (unsigned long long)vdesc->vd_offset, (unsigned long long)vdesc->vd_blocknr, (unsigned long long)vdesc->vd_vblocknr); return ret; } if (unlikely(!list_empty(&bh->b_assoc_buffers))) { nilfs_crit(inode->i_sb, "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu", __func__, vdesc->vd_flags ? "node" : "data", (unsigned long long)vdesc->vd_ino, (unsigned long long)vdesc->vd_cno, (unsigned long long)vdesc->vd_offset, (unsigned long long)vdesc->vd_blocknr, (unsigned long long)vdesc->vd_vblocknr); brelse(bh); return -EEXIST; } list_add_tail(&bh->b_assoc_buffers, buffers); return 0; } /** * nilfs_ioctl_move_blocks - move valid inode's blocks during garbage collection * @sb: superblock object * @argv: vector of arguments from userspace * @buf: array of nilfs_vdesc structures * * Description: nilfs_ioctl_move_blocks() function reads valid data/node * blocks that garbage collector specified with the array of nilfs_vdesc * structures and stores them into page caches of GC inodes. * * Return Value: Number of processed nilfs_vdesc structures or * error code, otherwise. */ static int nilfs_ioctl_move_blocks(struct super_block *sb, struct nilfs_argv *argv, void *buf) { size_t nmembs = argv->v_nmembs; struct the_nilfs *nilfs = sb->s_fs_info; struct inode *inode; struct nilfs_vdesc *vdesc; struct buffer_head *bh, *n; LIST_HEAD(buffers); ino_t ino; __u64 cno; int i, ret; for (i = 0, vdesc = buf; i < nmembs; ) { ino = vdesc->vd_ino; cno = vdesc->vd_cno; inode = nilfs_iget_for_gc(sb, ino, cno); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto failed; } if (list_empty(&NILFS_I(inode)->i_dirty)) { /* * Add the inode to GC inode list. Garbage Collection * is serialized and no two processes manipulate the * list simultaneously. */ igrab(inode); list_add(&NILFS_I(inode)->i_dirty, &nilfs->ns_gc_inodes); } do { ret = nilfs_ioctl_move_inode_block(inode, vdesc, &buffers); if (unlikely(ret < 0)) { iput(inode); goto failed; } vdesc++; } while (++i < nmembs && vdesc->vd_ino == ino && vdesc->vd_cno == cno); iput(inode); /* The inode still remains in GC inode list */ } list_for_each_entry_safe(bh, n, &buffers, b_assoc_buffers) { ret = nilfs_gccache_wait_and_mark_dirty(bh); if (unlikely(ret < 0)) { WARN_ON(ret == -EEXIST); goto failed; } list_del_init(&bh->b_assoc_buffers); brelse(bh); } return nmembs; failed: list_for_each_entry_safe(bh, n, &buffers, b_assoc_buffers) { list_del_init(&bh->b_assoc_buffers); brelse(bh); } return ret; } /** * nilfs_ioctl_delete_checkpoints - delete checkpoints * @nilfs: nilfs object * @argv: vector of arguments from userspace * @buf: array of periods of checkpoints numbers * * Description: nilfs_ioctl_delete_checkpoints() function deletes checkpoints * in the period from p_start to p_end, excluding p_end itself. The checkpoints * which have been already deleted are ignored. * * Return Value: Number of processed nilfs_period structures or * error code, otherwise. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EINVAL - invalid checkpoints. */ static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) { size_t nmembs = argv->v_nmembs; struct inode *cpfile = nilfs->ns_cpfile; struct nilfs_period *periods = buf; int ret, i; for (i = 0; i < nmembs; i++) { ret = nilfs_cpfile_delete_checkpoints( cpfile, periods[i].p_start, periods[i].p_end); if (ret < 0) return ret; } return nmembs; } /** * nilfs_ioctl_free_vblocknrs - free virtual block numbers * @nilfs: nilfs object * @argv: vector of arguments from userspace * @buf: array of virtual block numbers * * Description: nilfs_ioctl_free_vblocknrs() function frees * the virtual block numbers specified by @buf and @argv->v_nmembs. * * Return Value: Number of processed virtual block numbers or * error code, otherwise. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-ENOENT - The virtual block number have not been allocated. */ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) { size_t nmembs = argv->v_nmembs; int ret; ret = nilfs_dat_freev(nilfs->ns_dat, buf, nmembs); return (ret < 0) ? ret : nmembs; } /** * nilfs_ioctl_mark_blocks_dirty - mark blocks dirty * @nilfs: nilfs object * @argv: vector of arguments from userspace * @buf: array of block descriptors * * Description: nilfs_ioctl_mark_blocks_dirty() function marks * metadata file or data blocks as dirty. * * Return Value: Number of processed block descriptors or * error code, otherwise. * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error * * %-ENOENT - the specified block does not exist (hole block) */ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) { size_t nmembs = argv->v_nmembs; struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap; struct nilfs_bdesc *bdescs = buf; struct buffer_head *bh; int ret, i; for (i = 0; i < nmembs; i++) { /* XXX: use macro or inline func to check liveness */ ret = nilfs_bmap_lookup_at_level(bmap, bdescs[i].bd_offset, bdescs[i].bd_level + 1, &bdescs[i].bd_blocknr); if (ret < 0) { if (ret != -ENOENT) return ret; bdescs[i].bd_blocknr = 0; } if (bdescs[i].bd_blocknr != bdescs[i].bd_oblocknr) /* skip dead block */ continue; if (bdescs[i].bd_level == 0) { ret = nilfs_mdt_get_block(nilfs->ns_dat, bdescs[i].bd_offset, false, NULL, &bh); if (unlikely(ret)) { WARN_ON(ret == -ENOENT); return ret; } mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(nilfs->ns_dat); put_bh(bh); } else { ret = nilfs_bmap_mark(bmap, bdescs[i].bd_offset, bdescs[i].bd_level); if (ret < 0) { WARN_ON(ret == -ENOENT); return ret; } } } return nmembs; } int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs, struct nilfs_argv *argv, void **kbufs) { const char *msg; int ret; ret = nilfs_ioctl_delete_checkpoints(nilfs, &argv[1], kbufs[1]); if (ret < 0) { /* * can safely abort because checkpoints can be removed * independently. */ msg = "cannot delete checkpoints"; goto failed; } ret = nilfs_ioctl_free_vblocknrs(nilfs, &argv[2], kbufs[2]); if (ret < 0) { /* * can safely abort because DAT file is updated atomically * using a copy-on-write technique. */ msg = "cannot delete virtual blocks from DAT file"; goto failed; } ret = nilfs_ioctl_mark_blocks_dirty(nilfs, &argv[3], kbufs[3]); if (ret < 0) { /* * can safely abort because the operation is nondestructive. */ msg = "cannot mark copying blocks dirty"; goto failed; } return 0; failed: nilfs_err(nilfs->ns_sb, "error %d preparing GC: %s", ret, msg); return ret; } /** * nilfs_ioctl_clean_segments - clean segments * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_clean_segments() function makes garbage * collection operation in the environment of requested parameters * from userspace. The NILFS_IOCTL_CLEAN_SEGMENTS ioctl is used by * nilfs_cleanerd daemon. * * Return Value: On success, 0 is returned or error code, otherwise. */ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct nilfs_argv argv[5]; static const size_t argsz[5] = { sizeof(struct nilfs_vdesc), sizeof(struct nilfs_period), sizeof(__u64), sizeof(struct nilfs_bdesc), sizeof(__u64), }; void __user *base; void *kbufs[5]; struct the_nilfs *nilfs; size_t len, nsegs; int n, ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) return ret; ret = -EFAULT; if (copy_from_user(argv, argp, sizeof(argv))) goto out; ret = -EINVAL; nsegs = argv[4].v_nmembs; if (argv[4].v_size != argsz[4]) goto out; /* * argv[4] points to segment numbers this ioctl cleans. We * use kmalloc() for its buffer because the memory used for the * segment numbers is small enough. */ kbufs[4] = memdup_array_user((void __user *)(unsigned long)argv[4].v_base, nsegs, sizeof(__u64)); if (IS_ERR(kbufs[4])) { ret = PTR_ERR(kbufs[4]); goto out; } nilfs = inode->i_sb->s_fs_info; for (n = 0; n < 4; n++) { ret = -EINVAL; if (argv[n].v_size != argsz[n]) goto out_free; if (argv[n].v_nmembs > nsegs * nilfs->ns_blocks_per_segment) goto out_free; if (argv[n].v_nmembs >= UINT_MAX / argv[n].v_size) goto out_free; len = argv[n].v_size * argv[n].v_nmembs; base = (void __user *)(unsigned long)argv[n].v_base; if (len == 0) { kbufs[n] = NULL; continue; } kbufs[n] = vmalloc(len); if (!kbufs[n]) { ret = -ENOMEM; goto out_free; } if (copy_from_user(kbufs[n], base, len)) { ret = -EFAULT; vfree(kbufs[n]); goto out_free; } } /* * nilfs_ioctl_move_blocks() will call nilfs_iget_for_gc(), * which will operates an inode list without blocking. * To protect the list from concurrent operations, * nilfs_ioctl_move_blocks should be atomic operation. */ if (test_and_set_bit(THE_NILFS_GC_RUNNING, &nilfs->ns_flags)) { ret = -EBUSY; goto out_free; } ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]); if (ret < 0) { nilfs_err(inode->i_sb, "error %d preparing GC: cannot read source blocks", ret); } else { if (nilfs_sb_need_update(nilfs)) set_nilfs_discontinued(nilfs); ret = nilfs_clean_segments(inode->i_sb, argv, kbufs); } nilfs_remove_all_gcinodes(nilfs); clear_nilfs_gc_running(nilfs); out_free: while (--n >= 0) vfree(kbufs[n]); kfree(kbufs[4]); out: mnt_drop_write_file(filp); return ret; } /** * nilfs_ioctl_sync - make a checkpoint * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_sync() function constructs a logical segment * for checkpointing. This function guarantees that all modified data * and metadata are written out to the device when it successfully * returned. * * Return Value: On success, 0 is retured. On errors, one of the following * negative error code is returned. * * %-EROFS - Read only filesystem. * * %-EIO - I/O error * * %-ENOSPC - No space left on device (only in a panic state). * * %-ERESTARTSYS - Interrupted. * * %-ENOMEM - Insufficient memory available. * * %-EFAULT - Failure during execution of requested operation. */ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { __u64 cno; int ret; struct the_nilfs *nilfs; ret = nilfs_construct_segment(inode->i_sb); if (ret < 0) return ret; nilfs = inode->i_sb->s_fs_info; ret = nilfs_flush_device(nilfs); if (ret < 0) return ret; if (argp != NULL) { down_read(&nilfs->ns_segctor_sem); cno = nilfs->ns_cno - 1; up_read(&nilfs->ns_segctor_sem); if (copy_to_user(argp, &cno, sizeof(cno))) return -EFAULT; } return 0; } /** * nilfs_ioctl_resize - resize NILFS2 volume * @inode: inode object * @filp: file object * @argp: pointer on argument from userspace * * Return Value: On success, 0 is returned or error code, otherwise. */ static int nilfs_ioctl_resize(struct inode *inode, struct file *filp, void __user *argp) { __u64 newsize; int ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; ret = mnt_want_write_file(filp); if (ret) goto out; ret = -EFAULT; if (copy_from_user(&newsize, argp, sizeof(newsize))) goto out_drop_write; ret = nilfs_resize_fs(inode->i_sb, newsize); out_drop_write: mnt_drop_write_file(filp); out: return ret; } /** * nilfs_ioctl_trim_fs() - trim ioctl handle function * @inode: inode object * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which * performs the actual trim operation. * * Return Value: On success, 0 is returned or negative error code, otherwise. */ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct fstrim_range range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bdev_max_discard_sectors(nilfs->ns_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; range.minlen = max_t(u64, range.minlen, bdev_discard_granularity(nilfs->ns_bdev)); down_read(&nilfs->ns_segctor_sem); ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range); up_read(&nilfs->ns_segctor_sem); if (ret < 0) return ret; if (copy_to_user(argp, &range, sizeof(range))) return -EFAULT; return 0; } /** * nilfs_ioctl_set_alloc_range - limit range of segments to be allocated * @inode: inode object * @argp: pointer on argument from userspace * * Description: nilfs_ioctl_set_alloc_range() function defines lower limit * of segments in bytes and upper limit of segments in bytes. * The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility. * * Return Value: On success, 0 is returned or error code, otherwise. */ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; __u64 range[2]; __u64 minseg, maxseg; unsigned long segbytes; int ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; ret = -EFAULT; if (copy_from_user(range, argp, sizeof(__u64[2]))) goto out; ret = -ERANGE; if (range[1] > bdev_nr_bytes(inode->i_sb->s_bdev)) goto out; segbytes = nilfs->ns_blocks_per_segment * nilfs->ns_blocksize; minseg = range[0] + segbytes - 1; minseg = div64_ul(minseg, segbytes); if (range[1] < 4096) goto out; maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); if (maxseg < segbytes) goto out; maxseg = div64_ul(maxseg, segbytes); maxseg--; ret = nilfs_sufile_set_alloc_range(nilfs->ns_sufile, minseg, maxseg); out: return ret; } /** * nilfs_ioctl_get_info - wrapping function of get metadata info * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * @membsz: size of an item in bytes * @dofunc: concrete function of getting metadata info * * Description: nilfs_ioctl_get_info() gets metadata info by means of * calling dofunc() function. * * Return Value: On success, 0 is returned and requested metadata info * is copied into userspace. On error, one of the following * negative error codes is returned. * * %-EINVAL - Invalid arguments from userspace. * * %-ENOMEM - Insufficient amount of memory available. * * %-EFAULT - Failure during execution of requested operation. */ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp, size_t membsz, ssize_t (*dofunc)(struct the_nilfs *, __u64 *, int, void *, size_t, size_t)) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_argv argv; int ret; if (copy_from_user(&argv, argp, sizeof(argv))) return -EFAULT; if (argv.v_size < membsz) return -EINVAL; ret = nilfs_ioctl_wrap_copy(nilfs, &argv, _IOC_DIR(cmd), dofunc); if (ret < 0) return ret; if (copy_to_user(argp, &argv, sizeof(argv))) ret = -EFAULT; return ret; } /** * nilfs_ioctl_set_suinfo - set segment usage info * @inode: inode object * @filp: file object * @cmd: ioctl's request code * @argp: pointer on argument from userspace * * Description: Expects an array of nilfs_suinfo_update structures * encapsulated in nilfs_argv and updates the segment usage info * according to the flags in nilfs_suinfo_update. * * Return Value: On success, 0 is returned. On error, one of the * following negative error codes is returned. * * %-EPERM - Not enough permissions * * %-EFAULT - Error copying input data * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EINVAL - Invalid values in input (segment number, flags or nblocks) */ static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct nilfs_transaction_info ti; struct nilfs_argv argv; size_t len; void __user *base; void *kbuf; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) return ret; ret = -EFAULT; if (copy_from_user(&argv, argp, sizeof(argv))) goto out; ret = -EINVAL; if (argv.v_size < sizeof(struct nilfs_suinfo_update)) goto out; if (argv.v_nmembs > nilfs->ns_nsegments) goto out; if (argv.v_nmembs >= UINT_MAX / argv.v_size) goto out; len = argv.v_size * argv.v_nmembs; if (!len) { ret = 0; goto out; } base = (void __user *)(unsigned long)argv.v_base; kbuf = vmalloc(len); if (!kbuf) { ret = -ENOMEM; goto out; } if (copy_from_user(kbuf, base, len)) { ret = -EFAULT; goto out_free; } nilfs_transaction_begin(inode->i_sb, &ti, 0); ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size, argv.v_nmembs); if (unlikely(ret < 0)) nilfs_transaction_abort(inode->i_sb); else nilfs_transaction_commit(inode->i_sb); /* never fails */ out_free: vfree(kbuf); out: mnt_drop_write_file(filp); return ret; } long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); void __user *argp = (void __user *)arg; switch (cmd) { case FS_IOC_GETVERSION: return nilfs_ioctl_getversion(inode, argp); case NILFS_IOCTL_CHANGE_CPMODE: return nilfs_ioctl_change_cpmode(inode, filp, cmd, argp); case NILFS_IOCTL_DELETE_CHECKPOINT: return nilfs_ioctl_delete_checkpoint(inode, filp, cmd, argp); case NILFS_IOCTL_GET_CPINFO: return nilfs_ioctl_get_info(inode, filp, cmd, argp, sizeof(struct nilfs_cpinfo), nilfs_ioctl_do_get_cpinfo); case NILFS_IOCTL_GET_CPSTAT: return nilfs_ioctl_get_cpstat(inode, filp, cmd, argp); case NILFS_IOCTL_GET_SUINFO: return nilfs_ioctl_get_info(inode, filp, cmd, argp, sizeof(struct nilfs_suinfo), nilfs_ioctl_do_get_suinfo); case NILFS_IOCTL_SET_SUINFO: return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp); case NILFS_IOCTL_GET_SUSTAT: return nilfs_ioctl_get_sustat(inode, filp, cmd, argp); case NILFS_IOCTL_GET_VINFO: return nilfs_ioctl_get_info(inode, filp, cmd, argp, sizeof(struct nilfs_vinfo), nilfs_ioctl_do_get_vinfo); case NILFS_IOCTL_GET_BDESCS: return nilfs_ioctl_get_bdescs(inode, filp, cmd, argp); case NILFS_IOCTL_CLEAN_SEGMENTS: return nilfs_ioctl_clean_segments(inode, filp, cmd, argp); case NILFS_IOCTL_SYNC: return nilfs_ioctl_sync(inode, filp, cmd, argp); case NILFS_IOCTL_RESIZE: return nilfs_ioctl_resize(inode, filp, argp); case NILFS_IOCTL_SET_ALLOC_RANGE: return nilfs_ioctl_set_alloc_range(inode, argp); case FITRIM: return nilfs_ioctl_trim_fs(inode, argp); default: return -ENOTTY; } } #ifdef CONFIG_COMPAT long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case NILFS_IOCTL_CHANGE_CPMODE: case NILFS_IOCTL_DELETE_CHECKPOINT: case NILFS_IOCTL_GET_CPINFO: case NILFS_IOCTL_GET_CPSTAT: case NILFS_IOCTL_GET_SUINFO: case NILFS_IOCTL_SET_SUINFO: case NILFS_IOCTL_GET_SUSTAT: case NILFS_IOCTL_GET_VINFO: case NILFS_IOCTL_GET_BDESCS: case NILFS_IOCTL_CLEAN_SEGMENTS: case NILFS_IOCTL_SYNC: case NILFS_IOCTL_RESIZE: case NILFS_IOCTL_SET_ALLOC_RANGE: case FITRIM: break; default: return -ENOIOCTLCMD; } return nilfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); } #endif |
| 84 84 84 84 84 84 84 84 84 84 84 84 84 84 84 84 19 84 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Add configfs and memory store: Kyungchan Koh <kkc6196@fb.com> and * Shaohua Li <shli@fb.com> */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/init.h> #include "null_blk.h" #undef pr_fmt #define pr_fmt(fmt) "null_blk: " fmt #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL #define TIMER_INTERVAL (NSEC_PER_SEC / TICKS_PER_SEC) #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static DECLARE_FAULT_ATTR(null_timeout_attr); static DECLARE_FAULT_ATTR(null_requeue_attr); static DECLARE_FAULT_ATTR(null_init_hctx_attr); #endif static inline u64 mb_per_tick(int mbps) { return (1 << 20) / TICKS_PER_SEC * ((u64) mbps); } /* * Status flags for nullb_device. * * CONFIGURED: Device has been configured and turned on. Cannot reconfigure. * UP: Device is currently on and visible in userspace. * THROTTLED: Device is being throttled. * CACHE: Device is using a write-back cache. */ enum nullb_device_flags { NULLB_DEV_FL_CONFIGURED = 0, NULLB_DEV_FL_UP = 1, NULLB_DEV_FL_THROTTLED = 2, NULLB_DEV_FL_CACHE = 3, }; #define MAP_SZ ((PAGE_SIZE >> SECTOR_SHIFT) + 2) /* * nullb_page is a page in memory for nullb devices. * * @page: The page holding the data. * @bitmap: The bitmap represents which sector in the page has data. * Each bit represents one block size. For example, sector 8 * will use the 7th bit * The highest 2 bits of bitmap are for special purpose. LOCK means the cache * page is being flushing to storage. FREE means the cache page is freed and * should be skipped from flushing to storage. Please see * null_make_cache_space */ struct nullb_page { struct page *page; DECLARE_BITMAP(bitmap, MAP_SZ); }; #define NULLB_PAGE_LOCK (MAP_SZ - 1) #define NULLB_PAGE_FREE (MAP_SZ - 2) static LIST_HEAD(nullb_list); static struct mutex lock; static int null_major; static DEFINE_IDA(nullb_indexes); static struct blk_mq_tag_set tag_set; enum { NULL_IRQ_NONE = 0, NULL_IRQ_SOFTIRQ = 1, NULL_IRQ_TIMER = 2, }; static bool g_virt_boundary = false; module_param_named(virt_boundary, g_virt_boundary, bool, 0444); MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False"); static int g_no_sched; module_param_named(no_sched, g_no_sched, int, 0444); MODULE_PARM_DESC(no_sched, "No io scheduler"); static int g_submit_queues = 1; module_param_named(submit_queues, g_submit_queues, int, 0444); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); static int g_poll_queues = 1; module_param_named(poll_queues, g_poll_queues, int, 0444); MODULE_PARM_DESC(poll_queues, "Number of IOPOLL submission queues"); static int g_home_node = NUMA_NO_NODE; module_param_named(home_node, g_home_node, int, 0444); MODULE_PARM_DESC(home_node, "Home node for the device"); #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION /* * For more details about fault injection, please refer to * Documentation/fault-injection/fault-injection.rst. */ static char g_timeout_str[80]; module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444); MODULE_PARM_DESC(timeout, "Fault injection. timeout=<interval>,<probability>,<space>,<times>"); static char g_requeue_str[80]; module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444); MODULE_PARM_DESC(requeue, "Fault injection. requeue=<interval>,<probability>,<space>,<times>"); static char g_init_hctx_str[80]; module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444); MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>"); #endif /* * Historic queue modes. * * These days nothing but NULL_Q_MQ is actually supported, but we keep it the * enum for error reporting. */ enum { NULL_Q_BIO = 0, NULL_Q_RQ = 1, NULL_Q_MQ = 2, }; static int g_queue_mode = NULL_Q_MQ; static int null_param_store_val(const char *str, int *val, int min, int max) { int ret, new_val; ret = kstrtoint(str, 10, &new_val); if (ret) return -EINVAL; if (new_val < min || new_val > max) return -EINVAL; *val = new_val; return 0; } static int null_set_queue_mode(const char *str, const struct kernel_param *kp) { return null_param_store_val(str, &g_queue_mode, NULL_Q_BIO, NULL_Q_MQ); } static const struct kernel_param_ops null_queue_mode_param_ops = { .set = null_set_queue_mode, .get = param_get_int, }; device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444); MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)"); static int g_gb = 250; module_param_named(gb, g_gb, int, 0444); MODULE_PARM_DESC(gb, "Size in GB"); static int g_bs = 512; module_param_named(bs, g_bs, int, 0444); MODULE_PARM_DESC(bs, "Block size (in bytes)"); static int g_max_sectors; module_param_named(max_sectors, g_max_sectors, int, 0444); MODULE_PARM_DESC(max_sectors, "Maximum size of a command (in 512B sectors)"); static unsigned int nr_devices = 1; module_param(nr_devices, uint, 0444); MODULE_PARM_DESC(nr_devices, "Number of devices to register"); static bool g_blocking; module_param_named(blocking, g_blocking, bool, 0444); MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device"); static bool g_shared_tags; module_param_named(shared_tags, g_shared_tags, bool, 0444); MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq"); static bool g_shared_tag_bitmap; module_param_named(shared_tag_bitmap, g_shared_tag_bitmap, bool, 0444); MODULE_PARM_DESC(shared_tag_bitmap, "Use shared tag bitmap for all submission queues for blk-mq"); static int g_irqmode = NULL_IRQ_SOFTIRQ; static int null_set_irqmode(const char *str, const struct kernel_param *kp) { return null_param_store_val(str, &g_irqmode, NULL_IRQ_NONE, NULL_IRQ_TIMER); } static const struct kernel_param_ops null_irqmode_param_ops = { .set = null_set_irqmode, .get = param_get_int, }; device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444); MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer"); static unsigned long g_completion_nsec = 10000; module_param_named(completion_nsec, g_completion_nsec, ulong, 0444); MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns"); static int g_hw_queue_depth = 64; module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64"); static bool g_use_per_node_hctx; module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444); MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); static bool g_memory_backed; module_param_named(memory_backed, g_memory_backed, bool, 0444); MODULE_PARM_DESC(memory_backed, "Create a memory-backed block device. Default: false"); static bool g_discard; module_param_named(discard, g_discard, bool, 0444); MODULE_PARM_DESC(discard, "Support discard operations (requires memory-backed null_blk device). Default: false"); static unsigned long g_cache_size; module_param_named(cache_size, g_cache_size, ulong, 0444); MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (none)"); static bool g_fua = true; module_param_named(fua, g_fua, bool, 0444); MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true"); static unsigned int g_mbps; module_param_named(mbps, g_mbps, uint, 0444); MODULE_PARM_DESC(mbps, "Limit maximum bandwidth (in MiB/s). Default: 0 (no limit)"); static bool g_zoned; module_param_named(zoned, g_zoned, bool, S_IRUGO); MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false"); static unsigned long g_zone_size = 256; module_param_named(zone_size, g_zone_size, ulong, S_IRUGO); MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256"); static unsigned long g_zone_capacity; module_param_named(zone_capacity, g_zone_capacity, ulong, 0444); MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size"); static unsigned int g_zone_nr_conv; module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444); MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0"); static unsigned int g_zone_max_open; module_param_named(zone_max_open, g_zone_max_open, uint, 0444); MODULE_PARM_DESC(zone_max_open, "Maximum number of open zones when block device is zoned. Default: 0 (no limit)"); static unsigned int g_zone_max_active; module_param_named(zone_max_active, g_zone_max_active, uint, 0444); MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)"); static int g_zone_append_max_sectors = INT_MAX; module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444); MODULE_PARM_DESC(zone_append_max_sectors, "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation"); static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); static int null_add_dev(struct nullb_device *dev); static struct nullb *null_find_dev_by_name(const char *name); static void null_free_device_storage(struct nullb_device *dev, bool is_cache); static inline struct nullb_device *to_nullb_device(struct config_item *item) { return item ? container_of(to_config_group(item), struct nullb_device, group) : NULL; } static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page) { return snprintf(page, PAGE_SIZE, "%u\n", val); } static inline ssize_t nullb_device_ulong_attr_show(unsigned long val, char *page) { return snprintf(page, PAGE_SIZE, "%lu\n", val); } static inline ssize_t nullb_device_bool_attr_show(bool val, char *page) { return snprintf(page, PAGE_SIZE, "%u\n", val); } static ssize_t nullb_device_uint_attr_store(unsigned int *val, const char *page, size_t count) { unsigned int tmp; int result; result = kstrtouint(page, 0, &tmp); if (result < 0) return result; *val = tmp; return count; } static ssize_t nullb_device_ulong_attr_store(unsigned long *val, const char *page, size_t count) { int result; unsigned long tmp; result = kstrtoul(page, 0, &tmp); if (result < 0) return result; *val = tmp; return count; } static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, size_t count) { bool tmp; int result; result = kstrtobool(page, &tmp); if (result < 0) return result; *val = tmp; return count; } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ #define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ static ssize_t \ nullb_device_##NAME##_show(struct config_item *item, char *page) \ { \ return nullb_device_##TYPE##_attr_show( \ to_nullb_device(item)->NAME, page); \ } \ static ssize_t \ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ size_t count) \ { \ int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;\ struct nullb_device *dev = to_nullb_device(item); \ TYPE new_value = 0; \ int ret; \ \ ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);\ if (ret < 0) \ return ret; \ if (apply_fn) \ ret = apply_fn(dev, new_value); \ else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ ret = -EBUSY; \ if (ret < 0) \ return ret; \ dev->NAME = new_value; \ return count; \ } \ CONFIGFS_ATTR(nullb_device_, NAME); static int nullb_update_nr_hw_queues(struct nullb_device *dev, unsigned int submit_queues, unsigned int poll_queues) { struct blk_mq_tag_set *set; int ret, nr_hw_queues; if (!dev->nullb) return 0; /* * Make sure at least one submit queue exists. */ if (!submit_queues) return -EINVAL; /* * Make sure that null_init_hctx() does not access nullb->queues[] past * the end of that array. */ if (submit_queues > nr_cpu_ids || poll_queues > g_poll_queues) return -EINVAL; /* * Keep previous and new queue numbers in nullb_device for reference in * the call back function null_map_queues(). */ dev->prev_submit_queues = dev->submit_queues; dev->prev_poll_queues = dev->poll_queues; dev->submit_queues = submit_queues; dev->poll_queues = poll_queues; set = dev->nullb->tag_set; nr_hw_queues = submit_queues + poll_queues; blk_mq_update_nr_hw_queues(set, nr_hw_queues); ret = set->nr_hw_queues == nr_hw_queues ? 0 : -ENOMEM; if (ret) { /* on error, revert the queue numbers */ dev->submit_queues = dev->prev_submit_queues; dev->poll_queues = dev->prev_poll_queues; } return ret; } static int nullb_apply_submit_queues(struct nullb_device *dev, unsigned int submit_queues) { int ret; mutex_lock(&lock); ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); mutex_unlock(&lock); return ret; } static int nullb_apply_poll_queues(struct nullb_device *dev, unsigned int poll_queues) { int ret; mutex_lock(&lock); ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); mutex_unlock(&lock); return ret; } NULLB_DEVICE_ATTR(size, ulong, NULL); NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL); NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues); NULLB_DEVICE_ATTR(poll_queues, uint, nullb_apply_poll_queues); NULLB_DEVICE_ATTR(home_node, uint, NULL); NULLB_DEVICE_ATTR(queue_mode, uint, NULL); NULLB_DEVICE_ATTR(blocksize, uint, NULL); NULLB_DEVICE_ATTR(max_sectors, uint, NULL); NULLB_DEVICE_ATTR(irqmode, uint, NULL); NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL); NULLB_DEVICE_ATTR(index, uint, NULL); NULLB_DEVICE_ATTR(blocking, bool, NULL); NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL); NULLB_DEVICE_ATTR(memory_backed, bool, NULL); NULLB_DEVICE_ATTR(discard, bool, NULL); NULLB_DEVICE_ATTR(mbps, uint, NULL); NULLB_DEVICE_ATTR(cache_size, ulong, NULL); NULLB_DEVICE_ATTR(zoned, bool, NULL); NULLB_DEVICE_ATTR(zone_size, ulong, NULL); NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL); NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); NULLB_DEVICE_ATTR(zone_max_open, uint, NULL); NULLB_DEVICE_ATTR(zone_max_active, uint, NULL); NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL); NULLB_DEVICE_ATTR(virt_boundary, bool, NULL); NULLB_DEVICE_ATTR(no_sched, bool, NULL); NULLB_DEVICE_ATTR(shared_tags, bool, NULL); NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL); NULLB_DEVICE_ATTR(fua, bool, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { return nullb_device_bool_attr_show(to_nullb_device(item)->power, page); } static ssize_t nullb_device_power_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *dev = to_nullb_device(item); bool newp = false; ssize_t ret; ret = nullb_device_bool_attr_store(&newp, page, count); if (ret < 0) return ret; ret = count; mutex_lock(&lock); if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) goto out; ret = null_add_dev(dev); if (ret) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); goto out; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); dev->power = newp; ret = count; } else if (dev->power && !newp) { if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { dev->power = newp; null_del_dev(dev->nullb); } clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); } out: mutex_unlock(&lock); return ret; } CONFIGFS_ATTR(nullb_device_, power); static ssize_t nullb_device_badblocks_show(struct config_item *item, char *page) { struct nullb_device *t_dev = to_nullb_device(item); return badblocks_show(&t_dev->badblocks, page, 0); } static ssize_t nullb_device_badblocks_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *t_dev = to_nullb_device(item); char *orig, *buf, *tmp; u64 start, end; int ret; orig = kstrndup(page, count, GFP_KERNEL); if (!orig) return -ENOMEM; buf = strstrip(orig); ret = -EINVAL; if (buf[0] != '+' && buf[0] != '-') goto out; tmp = strchr(&buf[1], '-'); if (!tmp) goto out; *tmp = '\0'; ret = kstrtoull(buf + 1, 0, &start); if (ret) goto out; ret = kstrtoull(tmp + 1, 0, &end); if (ret) goto out; ret = -EINVAL; if (start > end) goto out; /* enable badblocks */ cmpxchg(&t_dev->badblocks.shift, -1, 0); if (buf[0] == '+') ret = badblocks_set(&t_dev->badblocks, start, end - start + 1, 1); else ret = badblocks_clear(&t_dev->badblocks, start, end - start + 1); if (ret == 0) ret = count; out: kfree(orig); return ret; } CONFIGFS_ATTR(nullb_device_, badblocks); static ssize_t nullb_device_zone_readonly_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *dev = to_nullb_device(item); return zone_cond_store(dev, page, count, BLK_ZONE_COND_READONLY); } CONFIGFS_ATTR_WO(nullb_device_, zone_readonly); static ssize_t nullb_device_zone_offline_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *dev = to_nullb_device(item); return zone_cond_store(dev, page, count, BLK_ZONE_COND_OFFLINE); } CONFIGFS_ATTR_WO(nullb_device_, zone_offline); static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_size, &nullb_device_attr_completion_nsec, &nullb_device_attr_submit_queues, &nullb_device_attr_poll_queues, &nullb_device_attr_home_node, &nullb_device_attr_queue_mode, &nullb_device_attr_blocksize, &nullb_device_attr_max_sectors, &nullb_device_attr_irqmode, &nullb_device_attr_hw_queue_depth, &nullb_device_attr_index, &nullb_device_attr_blocking, &nullb_device_attr_use_per_node_hctx, &nullb_device_attr_power, &nullb_device_attr_memory_backed, &nullb_device_attr_discard, &nullb_device_attr_mbps, &nullb_device_attr_cache_size, &nullb_device_attr_badblocks, &nullb_device_attr_zoned, &nullb_device_attr_zone_size, &nullb_device_attr_zone_capacity, &nullb_device_attr_zone_nr_conv, &nullb_device_attr_zone_max_open, &nullb_device_attr_zone_max_active, &nullb_device_attr_zone_append_max_sectors, &nullb_device_attr_zone_readonly, &nullb_device_attr_zone_offline, &nullb_device_attr_virt_boundary, &nullb_device_attr_no_sched, &nullb_device_attr_shared_tags, &nullb_device_attr_shared_tag_bitmap, &nullb_device_attr_fua, NULL, }; static void nullb_device_release(struct config_item *item) { struct nullb_device *dev = to_nullb_device(item); null_free_device_storage(dev, false); null_free_dev(dev); } static struct configfs_item_operations nullb_device_ops = { .release = nullb_device_release, }; static const struct config_item_type nullb_device_type = { .ct_item_ops = &nullb_device_ops, .ct_attrs = nullb_device_attrs, .ct_owner = THIS_MODULE, }; #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static void nullb_add_fault_config(struct nullb_device *dev) { fault_config_init(&dev->timeout_config, "timeout_inject"); fault_config_init(&dev->requeue_config, "requeue_inject"); fault_config_init(&dev->init_hctx_fault_config, "init_hctx_fault_inject"); configfs_add_default_group(&dev->timeout_config.group, &dev->group); configfs_add_default_group(&dev->requeue_config.group, &dev->group); configfs_add_default_group(&dev->init_hctx_fault_config.group, &dev->group); } #else static void nullb_add_fault_config(struct nullb_device *dev) { } #endif static struct config_group *nullb_group_make_group(struct config_group *group, const char *name) { struct nullb_device *dev; if (null_find_dev_by_name(name)) return ERR_PTR(-EEXIST); dev = null_alloc_dev(); if (!dev) return ERR_PTR(-ENOMEM); config_group_init_type_name(&dev->group, name, &nullb_device_type); nullb_add_fault_config(dev); return &dev->group; } static void nullb_group_drop_item(struct config_group *group, struct config_item *item) { struct nullb_device *dev = to_nullb_device(item); if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { mutex_lock(&lock); dev->power = false; null_del_dev(dev->nullb); mutex_unlock(&lock); } config_item_put(item); } static ssize_t memb_group_features_show(struct config_item *item, char *page) { return snprintf(page, PAGE_SIZE, "badblocks,blocking,blocksize,cache_size,fua," "completion_nsec,discard,home_node,hw_queue_depth," "irqmode,max_sectors,mbps,memory_backed,no_sched," "poll_queues,power,queue_mode,shared_tag_bitmap," "shared_tags,size,submit_queues,use_per_node_hctx," "virt_boundary,zoned,zone_capacity,zone_max_active," "zone_max_open,zone_nr_conv,zone_offline,zone_readonly," "zone_size,zone_append_max_sectors\n"); } CONFIGFS_ATTR_RO(memb_group_, features); static struct configfs_attribute *nullb_group_attrs[] = { &memb_group_attr_features, NULL, }; static struct configfs_group_operations nullb_group_ops = { .make_group = nullb_group_make_group, .drop_item = nullb_group_drop_item, }; static const struct config_item_type nullb_group_type = { .ct_group_ops = &nullb_group_ops, .ct_attrs = nullb_group_attrs, .ct_owner = THIS_MODULE, }; static struct configfs_subsystem nullb_subsys = { .su_group = { .cg_item = { .ci_namebuf = "nullb", .ci_type = &nullb_group_type, }, }, }; static inline int null_cache_active(struct nullb *nullb) { return test_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); } static struct nullb_device *null_alloc_dev(void) { struct nullb_device *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION dev->timeout_config.attr = null_timeout_attr; dev->requeue_config.attr = null_requeue_attr; dev->init_hctx_fault_config.attr = null_init_hctx_attr; #endif INIT_RADIX_TREE(&dev->data, GFP_ATOMIC); INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC); if (badblocks_init(&dev->badblocks, 0)) { kfree(dev); return NULL; } dev->size = g_gb * 1024; dev->completion_nsec = g_completion_nsec; dev->submit_queues = g_submit_queues; dev->prev_submit_queues = g_submit_queues; dev->poll_queues = g_poll_queues; dev->prev_poll_queues = g_poll_queues; dev->home_node = g_home_node; dev->queue_mode = g_queue_mode; dev->blocksize = g_bs; dev->max_sectors = g_max_sectors; dev->irqmode = g_irqmode; dev->hw_queue_depth = g_hw_queue_depth; dev->blocking = g_blocking; dev->memory_backed = g_memory_backed; dev->discard = g_discard; dev->cache_size = g_cache_size; dev->mbps = g_mbps; dev->use_per_node_hctx = g_use_per_node_hctx; dev->zoned = g_zoned; dev->zone_size = g_zone_size; dev->zone_capacity = g_zone_capacity; dev->zone_nr_conv = g_zone_nr_conv; dev->zone_max_open = g_zone_max_open; dev->zone_max_active = g_zone_max_active; dev->zone_append_max_sectors = g_zone_append_max_sectors; dev->virt_boundary = g_virt_boundary; dev->no_sched = g_no_sched; dev->shared_tags = g_shared_tags; dev->shared_tag_bitmap = g_shared_tag_bitmap; dev->fua = g_fua; return dev; } static void null_free_dev(struct nullb_device *dev) { if (!dev) return; null_free_zoned_dev(dev); badblocks_exit(&dev->badblocks); kfree(dev); } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) { struct nullb_cmd *cmd = container_of(timer, struct nullb_cmd, timer); blk_mq_end_request(blk_mq_rq_from_pdu(cmd), cmd->error); return HRTIMER_NORESTART; } static void null_cmd_end_timer(struct nullb_cmd *cmd) { ktime_t kt = cmd->nq->dev->completion_nsec; hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL); } static void null_complete_rq(struct request *rq) { struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_mq_end_request(rq, cmd->error); } static struct nullb_page *null_alloc_page(void) { struct nullb_page *t_page; t_page = kmalloc(sizeof(struct nullb_page), GFP_NOIO); if (!t_page) return NULL; t_page->page = alloc_pages(GFP_NOIO, 0); if (!t_page->page) { kfree(t_page); return NULL; } memset(t_page->bitmap, 0, sizeof(t_page->bitmap)); return t_page; } static void null_free_page(struct nullb_page *t_page) { __set_bit(NULLB_PAGE_FREE, t_page->bitmap); if (test_bit(NULLB_PAGE_LOCK, t_page->bitmap)) return; __free_page(t_page->page); kfree(t_page); } static bool null_page_empty(struct nullb_page *page) { int size = MAP_SZ - 2; return find_first_bit(page->bitmap, size) == size; } static void null_free_sector(struct nullb *nullb, sector_t sector, bool is_cache) { unsigned int sector_bit; u64 idx; struct nullb_page *t_page, *ret; struct radix_tree_root *root; root = is_cache ? &nullb->dev->cache : &nullb->dev->data; idx = sector >> PAGE_SECTORS_SHIFT; sector_bit = (sector & SECTOR_MASK); t_page = radix_tree_lookup(root, idx); if (t_page) { __clear_bit(sector_bit, t_page->bitmap); if (null_page_empty(t_page)) { ret = radix_tree_delete_item(root, idx, t_page); WARN_ON(ret != t_page); null_free_page(ret); if (is_cache) nullb->dev->curr_cache -= PAGE_SIZE; } } } static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx, struct nullb_page *t_page, bool is_cache) { struct radix_tree_root *root; root = is_cache ? &nullb->dev->cache : &nullb->dev->data; if (radix_tree_insert(root, idx, t_page)) { null_free_page(t_page); t_page = radix_tree_lookup(root, idx); WARN_ON(!t_page || t_page->page->index != idx); } else if (is_cache) nullb->dev->curr_cache += PAGE_SIZE; return t_page; } static void null_free_device_storage(struct nullb_device *dev, bool is_cache) { unsigned long pos = 0; int nr_pages; struct nullb_page *ret, *t_pages[FREE_BATCH]; struct radix_tree_root *root; root = is_cache ? &dev->cache : &dev->data; do { int i; nr_pages = radix_tree_gang_lookup(root, (void **)t_pages, pos, FREE_BATCH); for (i = 0; i < nr_pages; i++) { pos = t_pages[i]->page->index; ret = radix_tree_delete_item(root, pos, t_pages[i]); WARN_ON(ret != t_pages[i]); null_free_page(ret); } pos++; } while (nr_pages == FREE_BATCH); if (is_cache) dev->curr_cache = 0; } static struct nullb_page *__null_lookup_page(struct nullb *nullb, sector_t sector, bool for_write, bool is_cache) { unsigned int sector_bit; u64 idx; struct nullb_page *t_page; struct radix_tree_root *root; idx = sector >> PAGE_SECTORS_SHIFT; sector_bit = (sector & SECTOR_MASK); root = is_cache ? &nullb->dev->cache : &nullb->dev->data; t_page = radix_tree_lookup(root, idx); WARN_ON(t_page && t_page->page->index != idx); if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap))) return t_page; return NULL; } static struct nullb_page *null_lookup_page(struct nullb *nullb, sector_t sector, bool for_write, bool ignore_cache) { struct nullb_page *page = NULL; if (!ignore_cache) page = __null_lookup_page(nullb, sector, for_write, true); if (page) return page; return __null_lookup_page(nullb, sector, for_write, false); } static struct nullb_page *null_insert_page(struct nullb *nullb, sector_t sector, bool ignore_cache) __releases(&nullb->lock) __acquires(&nullb->lock) { u64 idx; struct nullb_page *t_page; t_page = null_lookup_page(nullb, sector, true, ignore_cache); if (t_page) return t_page; spin_unlock_irq(&nullb->lock); t_page = null_alloc_page(); if (!t_page) goto out_lock; if (radix_tree_preload(GFP_NOIO)) goto out_freepage; spin_lock_irq(&nullb->lock); idx = sector >> PAGE_SECTORS_SHIFT; t_page->page->index = idx; t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache); radix_tree_preload_end(); return t_page; out_freepage: null_free_page(t_page); out_lock: spin_lock_irq(&nullb->lock); return null_lookup_page(nullb, sector, true, ignore_cache); } static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page) { int i; unsigned int offset; u64 idx; struct nullb_page *t_page, *ret; void *dst, *src; idx = c_page->page->index; t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true); __clear_bit(NULLB_PAGE_LOCK, c_page->bitmap); if (test_bit(NULLB_PAGE_FREE, c_page->bitmap)) { null_free_page(c_page); if (t_page && null_page_empty(t_page)) { ret = radix_tree_delete_item(&nullb->dev->data, idx, t_page); null_free_page(t_page); } return 0; } if (!t_page) return -ENOMEM; src = kmap_local_page(c_page->page); dst = kmap_local_page(t_page->page); for (i = 0; i < PAGE_SECTORS; i += (nullb->dev->blocksize >> SECTOR_SHIFT)) { if (test_bit(i, c_page->bitmap)) { offset = (i << SECTOR_SHIFT); memcpy(dst + offset, src + offset, nullb->dev->blocksize); __set_bit(i, t_page->bitmap); } } kunmap_local(dst); kunmap_local(src); ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page); null_free_page(ret); nullb->dev->curr_cache -= PAGE_SIZE; return 0; } static int null_make_cache_space(struct nullb *nullb, unsigned long n) { int i, err, nr_pages; struct nullb_page *c_pages[FREE_BATCH]; unsigned long flushed = 0, one_round; again: if ((nullb->dev->cache_size * 1024 * 1024) > nullb->dev->curr_cache + n || nullb->dev->curr_cache == 0) return 0; nr_pages = radix_tree_gang_lookup(&nullb->dev->cache, (void **)c_pages, nullb->cache_flush_pos, FREE_BATCH); /* * nullb_flush_cache_page could unlock before using the c_pages. To * avoid race, we don't allow page free */ for (i = 0; i < nr_pages; i++) { nullb->cache_flush_pos = c_pages[i]->page->index; /* * We found the page which is being flushed to disk by other * threads */ if (test_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap)) c_pages[i] = NULL; else __set_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap); } one_round = 0; for (i = 0; i < nr_pages; i++) { if (c_pages[i] == NULL) continue; err = null_flush_cache_page(nullb, c_pages[i]); if (err) return err; one_round++; } flushed += one_round << PAGE_SHIFT; if (n > flushed) { if (nr_pages == 0) nullb->cache_flush_pos = 0; if (one_round == 0) { /* give other threads a chance */ spin_unlock_irq(&nullb->lock); spin_lock_irq(&nullb->lock); } goto again; } return 0; } static int copy_to_nullb(struct nullb *nullb, struct page *source, unsigned int off, sector_t sector, size_t n, bool is_fua) { size_t temp, count = 0; unsigned int offset; struct nullb_page *t_page; while (count < n) { temp = min_t(size_t, nullb->dev->blocksize, n - count); if (null_cache_active(nullb) && !is_fua) null_make_cache_space(nullb, PAGE_SIZE); offset = (sector & SECTOR_MASK) << SECTOR_SHIFT; t_page = null_insert_page(nullb, sector, !null_cache_active(nullb) || is_fua); if (!t_page) return -ENOSPC; memcpy_page(t_page->page, offset, source, off + count, temp); __set_bit(sector & SECTOR_MASK, t_page->bitmap); if (is_fua) null_free_sector(nullb, sector, true); count += temp; sector += temp >> SECTOR_SHIFT; } return 0; } static int copy_from_nullb(struct nullb *nullb, struct page *dest, unsigned int off, sector_t sector, size_t n) { size_t temp, count = 0; unsigned int offset; struct nullb_page *t_page; while (count < n) { temp = min_t(size_t, nullb->dev->blocksize, n - count); offset = (sector & SECTOR_MASK) << SECTOR_SHIFT; t_page = null_lookup_page(nullb, sector, false, !null_cache_active(nullb)); if (t_page) memcpy_page(dest, off + count, t_page->page, offset, temp); else zero_user(dest, off + count, temp); count += temp; sector += temp >> SECTOR_SHIFT; } return 0; } static void nullb_fill_pattern(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off) { memset_page(page, off, 0xff, len); } blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector, sector_t nr_sectors) { struct nullb *nullb = dev->nullb; size_t n = nr_sectors << SECTOR_SHIFT; size_t temp; spin_lock_irq(&nullb->lock); while (n > 0) { temp = min_t(size_t, n, dev->blocksize); null_free_sector(nullb, sector, false); if (null_cache_active(nullb)) null_free_sector(nullb, sector, true); sector += temp >> SECTOR_SHIFT; n -= temp; } spin_unlock_irq(&nullb->lock); return BLK_STS_OK; } static blk_status_t null_handle_flush(struct nullb *nullb) { int err; if (!null_cache_active(nullb)) return 0; spin_lock_irq(&nullb->lock); while (true) { err = null_make_cache_space(nullb, nullb->dev->cache_size * 1024 * 1024); if (err || nullb->dev->curr_cache == 0) break; } WARN_ON(!radix_tree_empty(&nullb->dev->cache)); spin_unlock_irq(&nullb->lock); return errno_to_blk_status(err); } static int null_transfer(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector, bool is_fua) { struct nullb_device *dev = nullb->dev; unsigned int valid_len = len; int err = 0; if (!is_write) { if (dev->zoned) valid_len = null_zone_valid_read_len(nullb, sector, len); if (valid_len) { err = copy_from_nullb(nullb, page, off, sector, valid_len); off += valid_len; len -= valid_len; } if (len) nullb_fill_pattern(nullb, page, len, off); flush_dcache_page(page); } else { flush_dcache_page(page); err = copy_to_nullb(nullb, page, off, sector, len, is_fua); } return err; } static blk_status_t null_handle_rq(struct nullb_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); struct nullb *nullb = cmd->nq->dev->nullb; int err = 0; unsigned int len; sector_t sector = blk_rq_pos(rq); struct req_iterator iter; struct bio_vec bvec; spin_lock_irq(&nullb->lock); rq_for_each_segment(bvec, rq, iter) { len = bvec.bv_len; err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, op_is_write(req_op(rq)), sector, rq->cmd_flags & REQ_FUA); if (err) break; sector += len >> SECTOR_SHIFT; } spin_unlock_irq(&nullb->lock); return errno_to_blk_status(err); } static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; blk_status_t sts = BLK_STS_OK; struct request *rq = blk_mq_rq_from_pdu(cmd); if (!hrtimer_active(&nullb->bw_timer)) hrtimer_restart(&nullb->bw_timer); if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) { blk_mq_stop_hw_queues(nullb->q); /* race with timer */ if (atomic_long_read(&nullb->cur_bytes) > 0) blk_mq_start_stopped_hw_queues(nullb->q, true); /* requeue request */ sts = BLK_STS_DEV_RESOURCE; } return sts; } static inline blk_status_t null_handle_badblocks(struct nullb_cmd *cmd, sector_t sector, sector_t nr_sectors) { struct badblocks *bb = &cmd->nq->dev->badblocks; sector_t first_bad; int bad_sectors; if (badblocks_check(bb, sector, nr_sectors, &first_bad, &bad_sectors)) return BLK_STS_IOERR; return BLK_STS_OK; } static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd, enum req_op op, sector_t sector, sector_t nr_sectors) { struct nullb_device *dev = cmd->nq->dev; if (op == REQ_OP_DISCARD) return null_handle_discard(dev, sector, nr_sectors); return null_handle_rq(cmd); } static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); struct nullb_device *dev = cmd->nq->dev; struct bio *bio; if (!dev->memory_backed && req_op(rq) == REQ_OP_READ) { __rq_for_each_bio(bio, rq) zero_fill_bio(bio); } } static inline void nullb_complete_cmd(struct nullb_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); /* * Since root privileges are required to configure the null_blk * driver, it is fine that this driver does not initialize the * data buffers of read commands. Zero-initialize these buffers * anyway if KMSAN is enabled to prevent that KMSAN complains * about null_blk not initializing read data buffers. */ if (IS_ENABLED(CONFIG_KMSAN)) nullb_zero_read_cmd_buffer(cmd); /* Complete IO by inline, softirq or timer */ switch (cmd->nq->dev->irqmode) { case NULL_IRQ_SOFTIRQ: blk_mq_complete_request(rq); break; case NULL_IRQ_NONE: blk_mq_end_request(rq, cmd->error); break; case NULL_IRQ_TIMER: null_cmd_end_timer(cmd); break; } } blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op, sector_t sector, unsigned int nr_sectors) { struct nullb_device *dev = cmd->nq->dev; blk_status_t ret; if (dev->badblocks.shift != -1) { ret = null_handle_badblocks(cmd, sector, nr_sectors); if (ret != BLK_STS_OK) return ret; } if (dev->memory_backed) return null_handle_memory_backed(cmd, op, sector, nr_sectors); return BLK_STS_OK; } static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector, sector_t nr_sectors, enum req_op op) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; blk_status_t sts; if (op == REQ_OP_FLUSH) { cmd->error = null_handle_flush(nullb); goto out; } if (dev->zoned) sts = null_process_zoned_cmd(cmd, op, sector, nr_sectors); else sts = null_process_cmd(cmd, op, sector, nr_sectors); /* Do not overwrite errors (e.g. timeout errors) */ if (cmd->error == BLK_STS_OK) cmd->error = sts; out: nullb_complete_cmd(cmd); } static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer) { struct nullb *nullb = container_of(timer, struct nullb, bw_timer); ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL); unsigned int mbps = nullb->dev->mbps; if (atomic_long_read(&nullb->cur_bytes) == mb_per_tick(mbps)) return HRTIMER_NORESTART; atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps)); blk_mq_start_stopped_hw_queues(nullb->q, true); hrtimer_forward_now(&nullb->bw_timer, timer_interval); return HRTIMER_RESTART; } static void nullb_setup_bwtimer(struct nullb *nullb) { ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL); hrtimer_init(&nullb->bw_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); nullb->bw_timer.function = nullb_bwtimer_fn; atomic_long_set(&nullb->cur_bytes, mb_per_tick(nullb->dev->mbps)); hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL); } #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static bool should_timeout_request(struct request *rq) { struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); struct nullb_device *dev = cmd->nq->dev; return should_fail(&dev->timeout_config.attr, 1); } static bool should_requeue_request(struct request *rq) { struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); struct nullb_device *dev = cmd->nq->dev; return should_fail(&dev->requeue_config.attr, 1); } static bool should_init_hctx_fail(struct nullb_device *dev) { return should_fail(&dev->init_hctx_fault_config.attr, 1); } #else static bool should_timeout_request(struct request *rq) { return false; } static bool should_requeue_request(struct request *rq) { return false; } static bool should_init_hctx_fail(struct nullb_device *dev) { return false; } #endif static void null_map_queues(struct blk_mq_tag_set *set) { struct nullb *nullb = set->driver_data; int i, qoff; unsigned int submit_queues = g_submit_queues; unsigned int poll_queues = g_poll_queues; if (nullb) { struct nullb_device *dev = nullb->dev; /* * Refer nr_hw_queues of the tag set to check if the expected * number of hardware queues are prepared. If block layer failed * to prepare them, use previous numbers of submit queues and * poll queues to map queues. */ if (set->nr_hw_queues == dev->submit_queues + dev->poll_queues) { submit_queues = dev->submit_queues; poll_queues = dev->poll_queues; } else if (set->nr_hw_queues == dev->prev_submit_queues + dev->prev_poll_queues) { submit_queues = dev->prev_submit_queues; poll_queues = dev->prev_poll_queues; } else { pr_warn("tag set has unexpected nr_hw_queues: %d\n", set->nr_hw_queues); WARN_ON_ONCE(true); submit_queues = 1; poll_queues = 0; } } for (i = 0, qoff = 0; i < set->nr_maps; i++) { struct blk_mq_queue_map *map = &set->map[i]; switch (i) { case HCTX_TYPE_DEFAULT: map->nr_queues = submit_queues; break; case HCTX_TYPE_READ: map->nr_queues = 0; continue; case HCTX_TYPE_POLL: map->nr_queues = poll_queues; break; } map->queue_offset = qoff; qoff += map->nr_queues; blk_mq_map_queues(map); } } static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct nullb_queue *nq = hctx->driver_data; LIST_HEAD(list); int nr = 0; struct request *rq; spin_lock(&nq->poll_lock); list_splice_init(&nq->poll_list, &list); list_for_each_entry(rq, &list, queuelist) blk_mq_set_request_complete(rq); spin_unlock(&nq->poll_lock); while (!list_empty(&list)) { struct nullb_cmd *cmd; struct request *req; req = list_first_entry(&list, struct request, queuelist); list_del_init(&req->queuelist); cmd = blk_mq_rq_to_pdu(req); cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req), blk_rq_sectors(req)); if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error, blk_mq_end_request_batch)) blk_mq_end_request(req, cmd->error); nr++; } return nr; } static enum blk_eh_timer_return null_timeout_rq(struct request *rq) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); if (hctx->type == HCTX_TYPE_POLL) { struct nullb_queue *nq = hctx->driver_data; spin_lock(&nq->poll_lock); /* The request may have completed meanwhile. */ if (blk_mq_request_completed(rq)) { spin_unlock(&nq->poll_lock); return BLK_EH_DONE; } list_del_init(&rq->queuelist); spin_unlock(&nq->poll_lock); } pr_info("rq %p timed out\n", rq); /* * If the device is marked as blocking (i.e. memory backed or zoned * device), the submission path may be blocked waiting for resources * and cause real timeouts. For these real timeouts, the submission * path will complete the request using blk_mq_complete_request(). * Only fake timeouts need to execute blk_mq_complete_request() here. */ cmd->error = BLK_STS_TIMEOUT; if (cmd->fake_timeout || hctx->type == HCTX_TYPE_POLL) blk_mq_complete_request(rq); return BLK_EH_DONE; } static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); struct nullb_queue *nq = hctx->driver_data; sector_t nr_sectors = blk_rq_sectors(rq); sector_t sector = blk_rq_pos(rq); const bool is_poll = hctx->type == HCTX_TYPE_POLL; might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); if (!is_poll && nq->dev->irqmode == NULL_IRQ_TIMER) { hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cmd->timer.function = null_cmd_timer_expired; } cmd->error = BLK_STS_OK; cmd->nq = nq; cmd->fake_timeout = should_timeout_request(rq) || blk_should_fake_timeout(rq->q); if (should_requeue_request(rq)) { /* * Alternate between hitting the core BUSY path, and the * driver driven requeue path */ nq->requeue_selection++; if (nq->requeue_selection & 1) return BLK_STS_RESOURCE; blk_mq_requeue_request(rq, true); return BLK_STS_OK; } if (test_bit(NULLB_DEV_FL_THROTTLED, &nq->dev->flags)) { blk_status_t sts = null_handle_throttled(cmd); if (sts != BLK_STS_OK) return sts; } blk_mq_start_request(rq); if (is_poll) { spin_lock(&nq->poll_lock); list_add_tail(&rq->queuelist, &nq->poll_list); spin_unlock(&nq->poll_lock); return BLK_STS_OK; } if (cmd->fake_timeout) return BLK_STS_OK; null_handle_cmd(cmd, sector, nr_sectors, req_op(rq)); return BLK_STS_OK; } static void null_queue_rqs(struct request **rqlist) { struct request *requeue_list = NULL; struct request **requeue_lastp = &requeue_list; struct blk_mq_queue_data bd = { }; blk_status_t ret; do { struct request *rq = rq_list_pop(rqlist); bd.rq = rq; ret = null_queue_rq(rq->mq_hctx, &bd); if (ret != BLK_STS_OK) rq_list_add_tail(&requeue_lastp, rq); } while (!rq_list_empty(*rqlist)); *rqlist = requeue_list; } static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) { nq->dev = nullb->dev; INIT_LIST_HEAD(&nq->poll_list); spin_lock_init(&nq->poll_lock); } static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, unsigned int hctx_idx) { struct nullb *nullb = hctx->queue->queuedata; struct nullb_queue *nq; if (should_init_hctx_fail(nullb->dev)) return -EFAULT; nq = &nullb->queues[hctx_idx]; hctx->driver_data = nq; null_init_queue(nullb, nq); return 0; } static const struct blk_mq_ops null_mq_ops = { .queue_rq = null_queue_rq, .queue_rqs = null_queue_rqs, .complete = null_complete_rq, .timeout = null_timeout_rq, .poll = null_poll, .map_queues = null_map_queues, .init_hctx = null_init_hctx, }; static void null_del_dev(struct nullb *nullb) { struct nullb_device *dev; if (!nullb) return; dev = nullb->dev; ida_free(&nullb_indexes, nullb->index); list_del_init(&nullb->list); del_gendisk(nullb->disk); if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) { hrtimer_cancel(&nullb->bw_timer); atomic_long_set(&nullb->cur_bytes, LONG_MAX); blk_mq_start_stopped_hw_queues(nullb->q, true); } put_disk(nullb->disk); if (nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); kfree(nullb->queues); if (null_cache_active(nullb)) null_free_device_storage(nullb->dev, true); kfree(nullb); dev->nullb = NULL; } static void null_config_discard(struct nullb *nullb, struct queue_limits *lim) { if (nullb->dev->discard == false) return; if (!nullb->dev->memory_backed) { nullb->dev->discard = false; pr_info("discard option is ignored without memory backing\n"); return; } if (nullb->dev->zoned) { nullb->dev->discard = false; pr_info("discard option is ignored in zoned mode\n"); return; } lim->max_hw_discard_sectors = UINT_MAX >> 9; } static const struct block_device_operations null_ops = { .owner = THIS_MODULE, .report_zones = null_report_zones, }; static int setup_queues(struct nullb *nullb) { int nqueues = nr_cpu_ids; if (g_poll_queues) nqueues += g_poll_queues; nullb->queues = kcalloc(nqueues, sizeof(struct nullb_queue), GFP_KERNEL); if (!nullb->queues) return -ENOMEM; return 0; } static int null_init_tag_set(struct blk_mq_tag_set *set, int poll_queues) { set->ops = &null_mq_ops; set->cmd_size = sizeof(struct nullb_cmd); set->timeout = 5 * HZ; set->nr_maps = 1; if (poll_queues) { set->nr_hw_queues += poll_queues; set->nr_maps += 2; } return blk_mq_alloc_tag_set(set); } static int null_init_global_tag_set(void) { int error; if (tag_set.ops) return 0; tag_set.nr_hw_queues = g_submit_queues; tag_set.queue_depth = g_hw_queue_depth; tag_set.numa_node = g_home_node; tag_set.flags = BLK_MQ_F_SHOULD_MERGE; if (g_no_sched) tag_set.flags |= BLK_MQ_F_NO_SCHED; if (g_shared_tag_bitmap) tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED; if (g_blocking) tag_set.flags |= BLK_MQ_F_BLOCKING; error = null_init_tag_set(&tag_set, g_poll_queues); if (error) tag_set.ops = NULL; return error; } static int null_setup_tagset(struct nullb *nullb) { if (nullb->dev->shared_tags) { nullb->tag_set = &tag_set; return null_init_global_tag_set(); } nullb->tag_set = &nullb->__tag_set; nullb->tag_set->driver_data = nullb; nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues; nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth; nullb->tag_set->numa_node = nullb->dev->home_node; nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE; if (nullb->dev->no_sched) nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED; if (nullb->dev->shared_tag_bitmap) nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; if (nullb->dev->blocking) nullb->tag_set->flags |= BLK_MQ_F_BLOCKING; return null_init_tag_set(nullb->tag_set, nullb->dev->poll_queues); } static int null_validate_conf(struct nullb_device *dev) { if (dev->queue_mode == NULL_Q_RQ) { pr_err("legacy IO path is no longer available\n"); return -EINVAL; } if (dev->queue_mode == NULL_Q_BIO) { pr_err("BIO-based IO path is no longer available, using blk-mq instead.\n"); dev->queue_mode = NULL_Q_MQ; } if (blk_validate_block_size(dev->blocksize)) return -EINVAL; if (dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) dev->submit_queues = nr_online_nodes; } else if (dev->submit_queues > nr_cpu_ids) dev->submit_queues = nr_cpu_ids; else if (dev->submit_queues == 0) dev->submit_queues = 1; dev->prev_submit_queues = dev->submit_queues; if (dev->poll_queues > g_poll_queues) dev->poll_queues = g_poll_queues; dev->prev_poll_queues = dev->poll_queues; dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER); /* Do memory allocation, so set blocking */ if (dev->memory_backed) dev->blocking = true; else /* cache is meaningless */ dev->cache_size = 0; dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024, dev->cache_size); dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps); if (dev->zoned && (!dev->zone_size || !is_power_of_2(dev->zone_size))) { pr_err("zone_size must be power-of-two\n"); return -EINVAL; } return 0; } #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static bool __null_setup_fault(struct fault_attr *attr, char *str) { if (!str[0]) return true; if (!setup_fault_attr(attr, str)) return false; attr->verbose = 0; return true; } #endif static bool null_setup_fault(void) { #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION if (!__null_setup_fault(&null_timeout_attr, g_timeout_str)) return false; if (!__null_setup_fault(&null_requeue_attr, g_requeue_str)) return false; if (!__null_setup_fault(&null_init_hctx_attr, g_init_hctx_str)) return false; #endif return true; } static int null_add_dev(struct nullb_device *dev) { struct queue_limits lim = { .logical_block_size = dev->blocksize, .physical_block_size = dev->blocksize, .max_hw_sectors = dev->max_sectors, }; struct nullb *nullb; int rv; rv = null_validate_conf(dev); if (rv) return rv; nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, dev->home_node); if (!nullb) { rv = -ENOMEM; goto out; } nullb->dev = dev; dev->nullb = nullb; spin_lock_init(&nullb->lock); rv = setup_queues(nullb); if (rv) goto out_free_nullb; rv = null_setup_tagset(nullb); if (rv) goto out_cleanup_queues; if (dev->virt_boundary) lim.virt_boundary_mask = PAGE_SIZE - 1; null_config_discard(nullb, &lim); if (dev->zoned) { rv = null_init_zoned_dev(dev, &lim); if (rv) goto out_cleanup_tags; } nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb); if (IS_ERR(nullb->disk)) { rv = PTR_ERR(nullb->disk); goto out_cleanup_zone; } nullb->q = nullb->disk->queue; if (dev->mbps) { set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags); nullb_setup_bwtimer(nullb); } if (dev->cache_size > 0) { set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); blk_queue_write_cache(nullb->q, true, dev->fua); } nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); rv = ida_alloc(&nullb_indexes, GFP_KERNEL); if (rv < 0) goto out_cleanup_disk; nullb->index = rv; dev->index = rv; if (config_item_name(&dev->group.cg_item)) { /* Use configfs dir name as the device name */ snprintf(nullb->disk_name, sizeof(nullb->disk_name), "%s", config_item_name(&dev->group.cg_item)); } else { sprintf(nullb->disk_name, "nullb%d", nullb->index); } set_capacity(nullb->disk, ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT); nullb->disk->major = null_major; nullb->disk->first_minor = nullb->index; nullb->disk->minors = 1; nullb->disk->fops = &null_ops; nullb->disk->private_data = nullb; strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN); if (nullb->dev->zoned) { rv = null_register_zoned_dev(nullb); if (rv) goto out_ida_free; } rv = add_disk(nullb->disk); if (rv) goto out_ida_free; list_add_tail(&nullb->list, &nullb_list); pr_info("disk %s created\n", nullb->disk_name); return 0; out_ida_free: ida_free(&nullb_indexes, nullb->index); out_cleanup_disk: put_disk(nullb->disk); out_cleanup_zone: null_free_zoned_dev(dev); out_cleanup_tags: if (nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); out_cleanup_queues: kfree(nullb->queues); out_free_nullb: kfree(nullb); dev->nullb = NULL; out: return rv; } static struct nullb *null_find_dev_by_name(const char *name) { struct nullb *nullb = NULL, *nb; mutex_lock(&lock); list_for_each_entry(nb, &nullb_list, list) { if (strcmp(nb->disk_name, name) == 0) { nullb = nb; break; } } mutex_unlock(&lock); return nullb; } static int null_create_dev(void) { struct nullb_device *dev; int ret; dev = null_alloc_dev(); if (!dev) return -ENOMEM; mutex_lock(&lock); ret = null_add_dev(dev); mutex_unlock(&lock); if (ret) { null_free_dev(dev); return ret; } return 0; } static void null_destroy_dev(struct nullb *nullb) { struct nullb_device *dev = nullb->dev; null_del_dev(nullb); null_free_device_storage(dev, false); null_free_dev(dev); } static int __init null_init(void) { int ret = 0; unsigned int i; struct nullb *nullb; if (g_bs > PAGE_SIZE) { pr_warn("invalid block size\n"); pr_warn("defaults block size to %lu\n", PAGE_SIZE); g_bs = PAGE_SIZE; } if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) { pr_err("invalid home_node value\n"); g_home_node = NUMA_NO_NODE; } if (!null_setup_fault()) return -EINVAL; if (g_queue_mode == NULL_Q_RQ) { pr_err("legacy IO path is no longer available\n"); return -EINVAL; } if (g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("submit_queues param is set to %u.\n", nr_online_nodes); g_submit_queues = nr_online_nodes; } } else if (g_submit_queues > nr_cpu_ids) { g_submit_queues = nr_cpu_ids; } else if (g_submit_queues <= 0) { g_submit_queues = 1; } config_group_init(&nullb_subsys.su_group); mutex_init(&nullb_subsys.su_mutex); ret = configfs_register_subsystem(&nullb_subsys); if (ret) return ret; mutex_init(&lock); null_major = register_blkdev(0, "nullb"); if (null_major < 0) { ret = null_major; goto err_conf; } for (i = 0; i < nr_devices; i++) { ret = null_create_dev(); if (ret) goto err_dev; } pr_info("module loaded\n"); return 0; err_dev: while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); null_destroy_dev(nullb); } unregister_blkdev(null_major, "nullb"); err_conf: configfs_unregister_subsystem(&nullb_subsys); return ret; } static void __exit null_exit(void) { struct nullb *nullb; configfs_unregister_subsystem(&nullb_subsys); unregister_blkdev(null_major, "nullb"); mutex_lock(&lock); while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); null_destroy_dev(nullb); } mutex_unlock(&lock); if (tag_set.ops) blk_mq_free_tag_set(&tag_set); mutex_destroy(&lock); } module_init(null_init); module_exit(null_exit); MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>"); MODULE_DESCRIPTION("multi queue aware block test driver"); MODULE_LICENSE("GPL"); |
| 1804 1809 14 1674 890 1682 1548 1199 1402 77 1791 1048 | 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 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2019-2020 Arm Ltd. #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kernel.h> #include <net/checksum.h> /* Looks dumb, but generates nice-ish code */ static u64 accumulate(u64 sum, u64 data) { __uint128_t tmp = (__uint128_t)sum + data; return tmp + (tmp >> 64); } /* * We over-read the buffer and this makes KASAN unhappy. Instead, disable * instrumentation and call kasan explicitly. */ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) { unsigned int offset, shift, sum; const u64 *ptr; u64 data, sum64 = 0; if (unlikely(len <= 0)) return 0; offset = (unsigned long)buff & 7; /* * This is to all intents and purposes safe, since rounding down cannot * result in a different page or cache line being accessed, and @buff * should absolutely not be pointing to anything read-sensitive. We do, * however, have to be careful not to piss off KASAN, which means using * unchecked reads to accommodate the head and tail, for which we'll * compensate with an explicit check up-front. */ kasan_check_read(buff, len); ptr = (u64 *)(buff - offset); len = len + offset - 8; /* * Head: zero out any excess leading bytes. Shifting back by the same * amount should be at least as fast as any other way of handling the * odd/even alignment, and means we can ignore it until the very end. */ shift = offset * 8; data = *ptr++; #ifdef __LITTLE_ENDIAN data = (data >> shift) << shift; #else data = (data << shift) >> shift; #endif /* * Body: straightforward aligned loads from here on (the paired loads * underlying the quadword type still only need dword alignment). The * main loop strictly excludes the tail, so the second loop will always * run at least once. */ while (unlikely(len > 64)) { __uint128_t tmp1, tmp2, tmp3, tmp4; tmp1 = *(__uint128_t *)ptr; tmp2 = *(__uint128_t *)(ptr + 2); tmp3 = *(__uint128_t *)(ptr + 4); tmp4 = *(__uint128_t *)(ptr + 6); len -= 64; ptr += 8; /* This is the "don't dump the carry flag into a GPR" idiom */ tmp1 += (tmp1 >> 64) | (tmp1 << 64); tmp2 += (tmp2 >> 64) | (tmp2 << 64); tmp3 += (tmp3 >> 64) | (tmp3 << 64); tmp4 += (tmp4 >> 64) | (tmp4 << 64); tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64); tmp1 += (tmp1 >> 64) | (tmp1 << 64); tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64); tmp3 += (tmp3 >> 64) | (tmp3 << 64); tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64); tmp1 += (tmp1 >> 64) | (tmp1 << 64); tmp1 = ((tmp1 >> 64) << 64) | sum64; tmp1 += (tmp1 >> 64) | (tmp1 << 64); sum64 = tmp1 >> 64; } while (len > 8) { __uint128_t tmp; sum64 = accumulate(sum64, data); tmp = *(__uint128_t *)ptr; len -= 16; ptr += 2; #ifdef __LITTLE_ENDIAN data = tmp >> 64; sum64 = accumulate(sum64, tmp); #else data = tmp; sum64 = accumulate(sum64, tmp >> 64); #endif } if (len > 0) { sum64 = accumulate(sum64, data); data = *ptr; len -= 8; } /* * Tail: zero any over-read bytes similarly to the head, again * preserving odd/even alignment. */ shift = len * -8; #ifdef __LITTLE_ENDIAN data = (data << shift) >> shift; #else data = (data >> shift) << shift; #endif sum64 = accumulate(sum64, data); /* Finally, folding */ sum64 += (sum64 >> 32) | (sum64 << 32); sum = sum64 >> 32; sum += (sum >> 16) | (sum << 16); if (offset & 1) return (u16)swab32(sum); return sum >> 16; } __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum csum) { __uint128_t src, dst; u64 sum = (__force u64)csum; src = *(const __uint128_t *)saddr->s6_addr; dst = *(const __uint128_t *)daddr->s6_addr; sum += (__force u32)htonl(len); #ifdef __LITTLE_ENDIAN sum += (u32)proto << 24; #else sum += proto; #endif src += (src >> 64) | (src << 64); dst += (dst >> 64) | (dst << 64); sum = accumulate(sum, src >> 64); sum = accumulate(sum, dst >> 64); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force __wsum)(sum >> 32)); } EXPORT_SYMBOL(csum_ipv6_magic); |
| 26 1 1 1 1 1 1 20 15 5 1 14 2 1 4 1 2 1 95 2 94 13 90 1 1 95 5 1 1 3 2 1 3 4 1 3 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Routines for handling Netlink messages for HSR and PRP. */ #include "hsr_netlink.h" #include <linux/kernel.h> #include <net/rtnetlink.h> #include <net/genetlink.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_framereg.h" static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_SLAVE1] = { .type = NLA_U32 }, [IFLA_HSR_SLAVE2] = { .type = NLA_U32 }, [IFLA_HSR_MULTICAST_SPEC] = { .type = NLA_U8 }, [IFLA_HSR_VERSION] = { .type = NLA_U8 }, [IFLA_HSR_SUPERVISION_ADDR] = { .len = ETH_ALEN }, [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, [IFLA_HSR_PROTOCOL] = { .type = NLA_U8 }, [IFLA_HSR_INTERLINK] = { .type = NLA_U32 }, }; /* Here, it seems a netdevice has already been allocated for us, and the * hsr_dev_setup routine has been executed. Nice! */ static int hsr_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; struct net_device *link[2], *interlink = NULL; if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; } if (!data[IFLA_HSR_SLAVE1]) { NL_SET_ERR_MSG_MOD(extack, "Slave1 device not specified"); return -EINVAL; } link[0] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE1])); if (!link[0]) { NL_SET_ERR_MSG_MOD(extack, "Slave1 does not exist"); return -EINVAL; } if (!data[IFLA_HSR_SLAVE2]) { NL_SET_ERR_MSG_MOD(extack, "Slave2 device not specified"); return -EINVAL; } link[1] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE2])); if (!link[1]) { NL_SET_ERR_MSG_MOD(extack, "Slave2 does not exist"); return -EINVAL; } if (link[0] == link[1]) { NL_SET_ERR_MSG_MOD(extack, "Slave1 and Slave2 are same"); return -EINVAL; } if (data[IFLA_HSR_INTERLINK]) interlink = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_INTERLINK])); if (interlink && interlink == link[0]) { NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave1 are the same"); return -EINVAL; } if (interlink && interlink == link[1]) { NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave2 are the same"); return -EINVAL; } if (!data[IFLA_HSR_MULTICAST_SPEC]) multicast_spec = 0; else multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); if (data[IFLA_HSR_PROTOCOL]) proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]); if (proto >= HSR_PROTOCOL_MAX) { NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol"); return -EINVAL; } if (!data[IFLA_HSR_VERSION]) { proto_version = HSR_V0; } else { if (proto == HSR_PROTOCOL_PRP) { NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported"); return -EINVAL; } proto_version = nla_get_u8(data[IFLA_HSR_VERSION]); if (proto_version > HSR_V1) { NL_SET_ERR_MSG_MOD(extack, "Only HSR version 0/1 supported"); return -EINVAL; } } if (proto == HSR_PROTOCOL_PRP) { proto_version = PRP_V1; if (interlink) { NL_SET_ERR_MSG_MOD(extack, "Interlink only works with HSR"); return -EINVAL; } } return hsr_dev_finalize(dev, link, interlink, multicast_spec, proto_version, extack); } static void hsr_dellink(struct net_device *dev, struct list_head *head) { struct hsr_priv *hsr = netdev_priv(dev); del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->prune_proxy_timer); del_timer_sync(&hsr->announce_timer); hsr_debugfs_term(hsr); hsr_del_ports(hsr); hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); hsr_del_nodes(&hsr->proxy_node_db); unregister_netdevice_queue(dev, head); } static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); u8 proto = HSR_PROTOCOL_HSR; struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) { if (nla_put_u32(skb, IFLA_HSR_SLAVE1, port->dev->ifindex)) goto nla_put_failure; } port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) { if (nla_put_u32(skb, IFLA_HSR_SLAVE2, port->dev->ifindex)) goto nla_put_failure; } if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, hsr->sup_multicast_addr) || nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr)) goto nla_put_failure; if (hsr->prot_version == PRP_V1) proto = HSR_PROTOCOL_PRP; if (nla_put_u8(skb, IFLA_HSR_PROTOCOL, proto)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops hsr_link_ops __read_mostly = { .kind = "hsr", .maxtype = IFLA_HSR_MAX, .policy = hsr_policy, .priv_size = sizeof(struct hsr_priv), .setup = hsr_dev_setup, .newlink = hsr_newlink, .dellink = hsr_dellink, .fill_info = hsr_fill_info, }; /* attribute policy */ static const struct nla_policy hsr_genl_policy[HSR_A_MAX + 1] = { [HSR_A_NODE_ADDR] = { .len = ETH_ALEN }, [HSR_A_NODE_ADDR_B] = { .len = ETH_ALEN }, [HSR_A_IFINDEX] = { .type = NLA_U32 }, [HSR_A_IF1_AGE] = { .type = NLA_U32 }, [HSR_A_IF2_AGE] = { .type = NLA_U32 }, [HSR_A_IF1_SEQ] = { .type = NLA_U16 }, [HSR_A_IF2_SEQ] = { .type = NLA_U16 }, }; static struct genl_family hsr_genl_family; static const struct genl_multicast_group hsr_mcgrps[] = { { .name = "hsr-network", }, }; /* This is called if for some node with MAC address addr, we only get frames * over one of the slave interfaces. This would indicate an open network ring * (i.e. a link has failed somewhere). */ void hsr_nl_ringerror(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN], struct hsr_port *port) { struct sk_buff *skb; void *msg_head; struct hsr_port *master; int res; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) goto fail; msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_RING_ERROR); if (!msg_head) goto nla_put_failure; res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) goto nla_put_failure; res = nla_put_u32(skb, HSR_A_IFINDEX, port->dev->ifindex); if (res < 0) goto nla_put_failure; genlmsg_end(skb, msg_head); genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC); return; nla_put_failure: kfree_skb(skb); fail: rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_warn(master->dev, "Could not send HSR ring error message\n"); rcu_read_unlock(); } /* This is called when we haven't heard from the node with MAC address addr for * some time (just before the node is removed from the node table/list). */ void hsr_nl_nodedown(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN]) { struct sk_buff *skb; void *msg_head; struct hsr_port *master; int res; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) goto fail; msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_NODE_DOWN); if (!msg_head) goto nla_put_failure; res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) goto nla_put_failure; genlmsg_end(skb, msg_head); genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC); return; nla_put_failure: kfree_skb(skb); fail: rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_warn(master->dev, "Could not send HSR node down\n"); rcu_read_unlock(); } /* HSR_C_GET_NODE_STATUS lets userspace query the internal HSR node table * about the status of a specific node in the network, defined by its MAC * address. * * Input: hsr ifindex, node mac address * Output: hsr ifindex, node mac address (copied from request), * age of latest frame from node over slave 1, slave 2 [ms] */ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) { /* For receiving */ struct nlattr *na; struct net_device *hsr_dev; /* For sending */ struct sk_buff *skb_out; void *msg_head; struct hsr_priv *hsr; struct hsr_port *port; unsigned char hsr_node_addr_b[ETH_ALEN]; int hsr_node_if1_age; u16 hsr_node_if1_seq; int hsr_node_if2_age; u16 hsr_node_if2_seq; int addr_b_ifindex; int res; if (!info) goto invalid; na = info->attrs[HSR_A_IFINDEX]; if (!na) goto invalid; na = info->attrs[HSR_A_NODE_ADDR]; if (!na) goto invalid; rcu_read_lock(); hsr_dev = dev_get_by_index_rcu(genl_info_net(info), nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) goto rcu_unlock; if (!is_hsr_master(hsr_dev)) goto rcu_unlock; /* Send reply */ skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; } msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid, info->snd_seq, &hsr_genl_family, 0, HSR_C_SET_NODE_STATUS); if (!msg_head) { res = -ENOMEM; goto nla_put_failure; } res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); if (res < 0) goto nla_put_failure; hsr = netdev_priv(hsr_dev); res = hsr_get_node_data(hsr, (unsigned char *) nla_data(info->attrs[HSR_A_NODE_ADDR]), hsr_node_addr_b, &addr_b_ifindex, &hsr_node_if1_age, &hsr_node_if1_seq, &hsr_node_if2_age, &hsr_node_if2_seq); if (res < 0) goto nla_put_failure; res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, nla_data(info->attrs[HSR_A_NODE_ADDR])); if (res < 0) goto nla_put_failure; if (addr_b_ifindex > -1) { res = nla_put(skb_out, HSR_A_NODE_ADDR_B, ETH_ALEN, hsr_node_addr_b); if (res < 0) goto nla_put_failure; res = nla_put_u32(skb_out, HSR_A_ADDR_B_IFINDEX, addr_b_ifindex); if (res < 0) goto nla_put_failure; } res = nla_put_u32(skb_out, HSR_A_IF1_AGE, hsr_node_if1_age); if (res < 0) goto nla_put_failure; res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq); if (res < 0) goto nla_put_failure; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX, port->dev->ifindex); if (res < 0) goto nla_put_failure; res = nla_put_u32(skb_out, HSR_A_IF2_AGE, hsr_node_if2_age); if (res < 0) goto nla_put_failure; res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq); if (res < 0) goto nla_put_failure; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX, port->dev->ifindex); if (res < 0) goto nla_put_failure; rcu_read_unlock(); genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); return 0; rcu_unlock: rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; nla_put_failure: kfree_skb(skb_out); /* Fall through */ fail: rcu_read_unlock(); return res; } /* Get a list of MacAddressA of all nodes known to this node (including self). */ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) { unsigned char addr[ETH_ALEN]; struct net_device *hsr_dev; struct sk_buff *skb_out; struct hsr_priv *hsr; bool restart = false; struct nlattr *na; void *pos = NULL; void *msg_head; int res; if (!info) goto invalid; na = info->attrs[HSR_A_IFINDEX]; if (!na) goto invalid; rcu_read_lock(); hsr_dev = dev_get_by_index_rcu(genl_info_net(info), nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) goto rcu_unlock; if (!is_hsr_master(hsr_dev)) goto rcu_unlock; restart: /* Send reply */ skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; } msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid, info->snd_seq, &hsr_genl_family, 0, HSR_C_SET_NODE_LIST); if (!msg_head) { res = -ENOMEM; goto nla_put_failure; } if (!restart) { res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); if (res < 0) goto nla_put_failure; } hsr = netdev_priv(hsr_dev); if (!pos) pos = hsr_get_next_node(hsr, NULL, addr); while (pos) { res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) { if (res == -EMSGSIZE) { genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); restart = true; goto restart; } goto nla_put_failure; } pos = hsr_get_next_node(hsr, pos, addr); } rcu_read_unlock(); genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); return 0; rcu_unlock: rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; nla_put_failure: nlmsg_free(skb_out); /* Fall through */ fail: rcu_read_unlock(); return res; } static const struct genl_small_ops hsr_ops[] = { { .cmd = HSR_C_GET_NODE_STATUS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = hsr_get_node_status, .dumpit = NULL, }, { .cmd = HSR_C_GET_NODE_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = hsr_get_node_list, .dumpit = NULL, }, }; static struct genl_family hsr_genl_family __ro_after_init = { .hdrsize = 0, .name = "HSR", .version = 1, .maxattr = HSR_A_MAX, .policy = hsr_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = hsr_ops, .n_small_ops = ARRAY_SIZE(hsr_ops), .resv_start_op = HSR_C_SET_NODE_LIST + 1, .mcgrps = hsr_mcgrps, .n_mcgrps = ARRAY_SIZE(hsr_mcgrps), }; int __init hsr_netlink_init(void) { int rc; rc = rtnl_link_register(&hsr_link_ops); if (rc) goto fail_rtnl_link_register; rc = genl_register_family(&hsr_genl_family); if (rc) goto fail_genl_register_family; hsr_debugfs_create_root(); return 0; fail_genl_register_family: rtnl_link_unregister(&hsr_link_ops); fail_rtnl_link_register: return rc; } void __exit hsr_netlink_exit(void) { genl_unregister_family(&hsr_genl_family); rtnl_link_unregister(&hsr_link_ops); } MODULE_ALIAS_RTNL_LINK("hsr"); |
| 27 1 1027 1040 1042 1143 488 1143 1143 865 18 610 237 24 297 18 17 7 127 7 73 65 485 548 18 197 8 18 3 27 27 4472 19 65 9290 5390 10201 10201 15 63 15 109 185 194 185 3451 3 25 1616 30169 4676 9 3699 8 10154 60 2290 16 16 50 10212 1302 2809 18 187 3390 3387 3394 335 63 63 3263 285 3210 285 12 4 103 4 58 23 11681 344 1461 48 70 191 380 6 8854 118 125 58 50 36 29 1262 2124 789 9 9 40 9 50 2 2 429 23 142 473 676 244 373 97 189 74 411 90 1122 2 333 8019 8016 8016 68 8005 90 119 1172 397 408 2 411 90 90 189 74 74 28 8 4 1 5 2 356 29 1 4 4455 9 89 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; struct folio_batch; extern int sysctl_page_lock_unfairness; void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; extern int page_cluster; extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> #include <asm/processor.h> #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { case 96: _pp[11] = 0; fallthrough; case 88: _pp[10] = 0; fallthrough; case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) #define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* to align the pointer to the (prev) page boundary */ #define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); } void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); /* Use only if VMA has no other users */ void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #ifdef CONFIG_MMU #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #else /* CONFIG_MMU */ #define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ #define VM_UFFD_MISSING 0 #endif /* CONFIG_MMU */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #ifdef CONFIG_X86_USER_SHADOW_STACK /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. * * These VMAs will get a single end guard page. This helps userspace protect * itself from attacks. A single page is enough for current shadow stack archs * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c * for more details on the guard size. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 #else # define VM_SHADOW_STACK VM_NONE #endif #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR # define VM_UFFD_MINOR_BIT 38 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ /* * This flag is used to connect VFIO to arch specific KVM code. It * indicates that the memory under this VMA is safe for use with any * non-cachable memory type inside KVM. Some VFIO devices, on some * platforms, are thought to be unsafe and can cause machine crashes * if KVM does not lock down the memory type. */ #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED_BIT 39 #define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) #else #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #define VM_STACK_EARLY VM_GROWSDOWN #else #define VM_STACK VM_GROWSDOWN #define VM_STACK_EARLY 0 #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address - masked */ unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ union { pte_t orig_pte; /* Value of PTE at the time of fault */ pmd_t orig_pmd; /* Value of PMD at the time of fault, * used by PMD fault only. */ }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() sets up a page * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); /** * @close: Called when the VMA is being removed from the MM. * Context: User context. May sleep. Caller holds mmap_lock. */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); int (*mremap)(struct vm_area_struct *area); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not * be modified. Returns 0 if mprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs. See also generic_access_phys() for a generic * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; #ifdef CONFIG_NUMA_BALANCING static inline void vma_numab_state_init(struct vm_area_struct *vma) { vma->numab_state = NULL; } static inline void vma_numab_state_free(struct vm_area_struct *vma) { kfree(vma->numab_state); } #else static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. */ static inline bool vma_start_read(struct vm_area_struct *vma) { /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need * ACQUIRE semantics, because this is just a lockless check whose result * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) return false; if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) return false; /* * Overflow might produce false locked result. * False unlocked result is impossible because we modify and check * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are * racing with vma_end_write_all(), we only start reading from the VMA * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { up_read(&vma->vm_lock->lock); return false; } return true; } static inline void vma_end_read(struct vm_area_struct *vma) { rcu_read_lock(); /* keeps vma alive till the end of up_read */ up_read(&vma->vm_lock->lock); rcu_read_unlock(); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ *mm_lock_seq = vma->vm_mm->mm_lock_seq; return (vma->vm_lock_seq == *mm_lock_seq); } /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; down_write(&vma->vm_lock->lock); /* * We should use WRITE_ONCE() here because we can have concurrent reads * from the early lockless pessimistic check in vma_start_read(). * We don't really care about the correctness of that early check, but * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. */ WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); up_write(&vma->vm_lock->lock); } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } static inline void vma_assert_locked(struct vm_area_struct *vma) { if (!rwsem_is_locked(&vma->vm_lock->lock)) vma_assert_write_locked(vma); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) { /* When detaching vma should be write-locked */ if (detached) vma_assert_write_locked(vma); vma->detached = detached; } static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_end_read(vmf->vma); else mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); else mmap_assert_locked(vmf->vma->vm_mm); } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ extern const struct vm_operations_struct vma_dummy_vm_ops; /* * WARNING: vma_init does not initialize vma->vm_lock. * Use vm_area_alloc()/vm_area_free() if vma needs locking. */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { ACCESS_PRIVATE(vma, __vm_flags) = flags; } /* * Use when VMA is part of the VMA tree and modifications need coordination * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and * it should be locked explicitly beforehand. */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } /* * Use only if VMA is not part of the VMA tree or has no other users and * therefore needs no locking. */ static inline void __vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vm_flags_init(vma, (vma->vm_flags | set) & ~clear); } /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. */ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vma_start_write(vma); __vm_flags_mod(vma, set, clear); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } /* * Indicate if the VMA is a heap for the given task; for * /proc/PID/maps that is the heap of the main task. */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { return vma->vm_start < vma->vm_mm->brk && vma->vm_end > vma->vm_mm->start_brk; } /* * Indicate if the VMA is a stack for the given task; for * /proc/PID/maps that is the stack of the main task. */ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) { /* * We make no effort to guess what a given thread considers to be * its "stack". It's not even well-defined for programs written * languages like Go. */ return vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) { return mas_next_range(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { return mas_prev(&vmi->mas, 0); } static inline struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) { return mas_prev_range(&vmi->mas, 0); } static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; } static inline unsigned long vma_iter_end(struct vma_iterator *vmi) { return vmi->mas.last + 1; } static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, unsigned long count) { return mas_expected_entries(&vmi->mas, count); } static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { __mas_set_range(&vmi->mas, start, end - 1); mas_store_gfp(&vmi->mas, NULL, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { mas_destroy(&vmi->mas); } static inline int vma_iter_bulk_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { vmi->mas.index = vma->vm_start; vmi->mas.last = vma->vm_end - 1; mas_store(&vmi->mas, vma); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); } static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) { mas_set(&vmi->mas, addr); } #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); bool vma_is_anon_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 0; return folio->_flags_1 & 0xff; } /** * folio_order - The allocation order of a folio. * @folio: The folio. * * A folio is composed of 2^order pages. See get_order() for the definition * of order. * * Return: The order of the folio. */ static inline unsigned int folio_order(struct folio *folio) { if (!folio_test_large(folio)) return 0; return folio->_flags_1 & 0xff; } #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } static inline int folio_put_testzero(struct folio *folio) { return put_page_testzero(&folio->page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } static inline struct folio *folio_get_nontail_page(struct page *page) { if (unlikely(!get_page_unless_zero(page))) return NULL; return (struct folio *)page; } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes - it does not include PTE-mapped sub-pages; look * at folio_mapcount() or page_mapcount() instead. */ static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_entire_mapcount) + 1; } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } /** * page_mapcount() - Number of times this precise page is mapped. * @page: The page. * * The number of times this page is mapped. If this page is part of * a large folio, it includes the number of times this page is mapped * as part of that folio. * * Will report 0 for pages which cannot be mapped into userspace, eg * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; /* Handle page_has_type() pages */ if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); return mapcount; } static inline int folio_large_mapcount(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_large_mapcount) + 1; } /** * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * * The folio mapcount corresponds to the number of present user page table * entries that reference any part of a folio. Each such present user page * table entry must be paired with exactly on folio reference. * * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts * exactly once. * * For hugetlb folios, each abstracted "hugetlb" user page table entry that * references the entire folio counts exactly once, even when such special * page table entries are comprised of multiple ordinary page table entries. * * Will report 0 for pages which cannot be mapped into userspace, such as * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ static inline int folio_mapcount(const struct folio *folio) { int mapcount; if (likely(!folio_test_large(folio))) { mapcount = atomic_read(&folio->_mapcount) + 1; /* Handle page_has_type() pages */ if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) mapcount = 0; return mapcount; } return folio_large_mapcount(folio); } /** * folio_mapped - Is this folio mapped into userspace? * @folio: The folio. * * Return: True if any page in this folio is referenced by user page tables. */ static inline bool folio_mapped(const struct folio *folio) { return folio_mapcount(folio) >= 1; } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ static inline bool page_mapped(const struct page *page) { return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } static inline struct folio *virt_to_folio(const void *x) { struct page *page = virt_to_page(x); return page_folio(page); } void __folio_put(struct folio *folio); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return compound_order(page); } /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte, vma); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!folio_is_zone_device(folio)) return false; return __put_devmap_managed_folio_refs(folio, refs); } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) /** * folio_get - Increment the reference count on a folio. * @folio: The folio. * * Context: May be called in any context, as long as you know that * you have a refcount on the folio. If you do not already have one, * folio_try_get() may be the right interface for you to use. */ static inline void folio_get(struct folio *folio) { VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); folio_ref_inc(folio); } static inline void get_page(struct page *page) { folio_get(page_folio(page)); } static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } /** * folio_put - Decrement the reference count on a folio. * @folio: The folio. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put() unless you can be sure that it wasn't the * last reference. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) __folio_put(folio); } /** * folio_put_refs - Reduce the reference count on a folio. * @folio: The folio. * @refs: The amount to subtract from the folio's reference count. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put_refs() unless you can be sure that these weren't * the last references. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put_refs(struct folio *folio, int refs) { if (folio_ref_sub_and_test(folio, refs)) __folio_put(folio); } void folios_put_refs(struct folio_batch *folios, unsigned int *refs); /* * union release_pages_arg - an array of pages or folios * * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. * * The transparent union syntax for this kind of "any of these * argument types" is all kinds of ugly, so look away. */ typedef union { struct page **pages; struct folio **folios; struct encoded_page **encoded_pages; } release_pages_arg __attribute__ ((__transparent_union__)); void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need to * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folios_put(struct folio_batch *folios) { folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); /* * For some devmap managed pages we need to catch refcount transition * from 2 to 1: */ if (put_devmap_managed_folio_refs(folio, 1)) return; folio_put(folio); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() * provides safe operation for get_user_pages(), page_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { /* * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of * a file mapping. R/O MAP_PRIVATE mappings might still modify * underlying memory if ptrace is active, so this is only possible if * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif static inline int folio_nid(const struct folio *folio) { return page_to_nid(&folio->page); } #ifdef CONFIG_NUMA_BALANCING /* page access time bits needs to hold at least 4 seconds */ #define PAGE_ACCESS_TIME_MIN_BITS 12 #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS #define PAGE_ACCESS_TIME_BUCKETS \ (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) #else #define PAGE_ACCESS_TIME_BUCKETS 0 #endif #define PAGE_ACCESS_TIME_MASK \ (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int folio_last_cpupid(struct folio *folio) { return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int folio_last_cpupid(struct folio *folio) { return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; last_time = folio_xchg_last_cpupid(folio, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return folio_nid(folio); /* XXX */ } static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } static inline int folio_last_cpupid(struct folio *folio) { return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, KASAN_TAG_KERNEL); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } static inline struct zone *folio_zone(const struct folio *folio) { return page_zone(&folio->page); } static inline pg_data_t *folio_pgdat(const struct folio *folio) { return page_pgdat(&folio->page); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif /** * folio_pfn - Return the Page Frame Number of a folio. * @folio: The folio. * * A folio may contain multiple pages. The pages have consecutive * Page Frame Numbers. * * Return: The Page Frame Number of the first page in the folio. */ static inline unsigned long folio_pfn(struct folio *folio) { return page_to_pfn(&folio->page); } static inline struct folio *pfn_folio(unsigned long pfn) { return page_folio(pfn_to_page(pfn)); } /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. * * This function checks if a folio has been pinned via a call to * a function in the pin_user_pages() family. * * For small folios, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal folio references". * * False positives are OK, because: a) it's unlikely for a folio to * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * * For large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the page has been "dma-pinned". * False, if the page is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_test_large(folio)) return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then * folio_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the sign bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)folio_ref_count(folio)) >= GUP_PIN_COUNTING_BIAS; } static inline bool page_maybe_dma_pinned(struct page *page) { return folio_maybe_dma_pinned(page_folio(page)); } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return folio_maybe_dma_pinned(folio); } /** * is_zero_page - Query if a page is a zero page * @page: The page to query * * This returns true if @page is one of the permanent zero pages. */ static inline bool is_zero_page(const struct page *page) { return is_zero_pfn(page_to_pfn(page)); } /** * is_zero_folio - Query if a folio is a zero page * @folio: The folio to query * * This returns true if @folio is one of the permanent zero pages. */ static inline bool is_zero_folio(const struct folio *folio) { return is_zero_page(&folio->page); } /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION static inline bool folio_is_longterm_pinnable(struct folio *folio) { #ifdef CONFIG_CMA int mt = folio_migratetype(folio); if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif /* The zero page can be "pinned" but gets special handling. */ if (is_zero_folio(folio)) return true; /* Coherent device memory must always allow eviction. */ if (folio_is_device_coherent(folio)) return false; /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); } #else static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /** * folio_nr_pages - The number of pages in the folio. * @folio: The folio. * * Return: A positive power of two. */ static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else return 1L << (folio->_flags_1 & 0xff); #endif } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) #else #define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES #endif /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ static inline unsigned long compound_nr(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 1; #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else return 1L << (folio->_flags_1 & 0xff); #endif } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { return folio_nr_pages((struct folio *)page); } /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * * If you have physically contiguous memory which may span more than * one folio (eg a &struct bio_vec), use this function to move from one * folio to the next. Do not use it if the memory is only virtually * contiguous as the folios are almost certainly not adjacent to each * other. This is the folio equivalent to writing ``page++``. * * Context: We assume that the folios are refcounted and/or locked at a * higher level and do not adjust the reference counts. * Return: The next struct folio. */ static inline struct folio *folio_next(struct folio *folio) { return (struct folio *)folio_page(folio, folio_nr_pages(folio)); } /** * folio_shift - The size of the memory described by this folio. * @folio: The folio. * * A folio represents a number of bytes which is a power-of-two in size. * This function tells you which power-of-two the folio is. See also * folio_size() and folio_order(). * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ static inline unsigned int folio_shift(struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } /** * folio_size - The number of bytes in a folio. * @folio: The folio. * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ static inline size_t folio_size(struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** * folio_likely_mapped_shared - Estimate if the folio is mapped into the page * tables of more than one MM * @folio: The folio. * * This function checks if the folio is currently mapped into more than one * MM ("mapped shared"), or if the folio is only mapped into a single MM * ("mapped exclusively"). * * As precise information is not easily available for all folios, this function * estimates the number of MMs ("sharers") that are currently mapping a folio * using the number of times the first page of the folio is currently mapped * into page tables. * * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, * the return value will be exactly correct, because they can only be mapped * at most once into an MM, and they cannot be partially mapped. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly * indicate "mapped exclusively" (false negative) when the folio is * only partially mapped into at least one MM. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. * #. For (small) KSM folios, the return value can wrongly indicate "mapped * shared" (false positive), when the folio is mapped multiple times into * the same MM. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). * * This function does not consider: * #. If the folio might get mapped in the (near) future (e.g., swapcache, * pagecache, temporary unmapping for migration). * #. If the folio is mapped differently (VM_PFNMAP). * #. If hugetlb page table sharing applies. Callers might want to check * hugetlb_pmd_shared(). * * Return: Whether the folio is estimated to be mapped into more than one MM. */ static inline bool folio_likely_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); /* Only partially-mappable folios require more care. */ if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; /* A single mapping implies "mapped exclusively". */ if (mapcount <= 1) return false; /* If any page is mapped more than once we treat it "mapped shared". */ if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) return true; /* Let's guess based on the first subpage. */ return atomic_read(&folio->_mapcount) > 0; } #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { int ret; long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) { ret = arch_make_page_accessible(folio_page(folio, i)); if (ret) break; } return ret; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif static inline void *folio_address(const struct folio *folio) { return page_address(&folio->page); } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)page->lru.next & BIT(1); } /* * Return true only if the folio has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool folio_is_pfmemalloc(const struct folio *folio) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)folio->lru.next & BIT(1); } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { page->lru.next = NULL; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely * drop the page in the mm, either by truncation or unmapping of the vma. By * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit_signals(struct task_struct *t); static inline int task_mm_cid(struct task_struct *t) { return t->mm_cid; } #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } static inline int task_mm_cid(struct task_struct *t) { /* * Use the processor id as a fall-back when the mm cid feature is * disabled. This provides functional per-cpu data structure accesses * in user-space, althrough it won't provide the memory usage benefits. */ return raw_smp_processor_id(); } #endif #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); static inline void zap_vma_pages(struct vm_area_struct *vma) { zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_pte(struct vm_area_struct *vma, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_folio(struct address_space *mapping, struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); /* * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, struct vm_area_struct **vmap) { struct page *page; struct vm_area_struct *vma; int got; if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) return ERR_PTR(-EINVAL); got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { put_page(page); return ERR_PTR(-EINVAL); } *vmap = vma; return page; } long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long sta |