| 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: exoparg2 - AML execution - opcodes with 2 arguments * * Copyright (C) 2000 - 2025, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #include "acparser.h" #include "acinterp.h" #include "acevents.h" #include "amlcode.h" #define _COMPONENT ACPI_EXECUTER ACPI_MODULE_NAME("exoparg2") /*! * Naming convention for AML interpreter execution routines. * * The routines that begin execution of AML opcodes are named with a common * convention based upon the number of arguments, the number of target operands, * and whether or not a value is returned: * * AcpiExOpcode_xA_yT_zR * * Where: * * xA - ARGUMENTS: The number of arguments (input operands) that are * required for this opcode type (1 through 6 args). * yT - TARGETS: The number of targets (output operands) that are required * for this opcode type (0, 1, or 2 targets). * zR - RETURN VALUE: Indicates whether this opcode type returns a value * as the function return (0 or 1). * * The AcpiExOpcode* functions are called via the Dispatcher component with * fully resolved operands. !*/ /******************************************************************************* * * FUNCTION: acpi_ex_opcode_2A_0T_0R * * PARAMETERS: walk_state - Current walk state * * RETURN: Status * * DESCRIPTION: Execute opcode with two arguments, no target, and no return * value. * * ALLOCATION: Deletes both operands * ******************************************************************************/ acpi_status acpi_ex_opcode_2A_0T_0R(struct acpi_walk_state *walk_state) { union acpi_operand_object **operand = &walk_state->operands[0]; struct acpi_namespace_node *node; u32 value; acpi_status status = AE_OK; ACPI_FUNCTION_TRACE_STR(ex_opcode_2A_0T_0R, acpi_ps_get_opcode_name(walk_state->opcode)); /* Examine the opcode */ switch (walk_state->opcode) { case AML_NOTIFY_OP: /* Notify (notify_object, notify_value) */ /* The first operand is a namespace node */ node = (struct acpi_namespace_node *)operand[0]; /* Second value is the notify value */ value = (u32) operand[1]->integer.value; /* Are notifies allowed on this object? */ if (!acpi_ev_is_notify_object(node)) { ACPI_ERROR((AE_INFO, "Unexpected notify object type [%s]", acpi_ut_get_type_name(node->type))); status = AE_AML_OPERAND_TYPE; break; } /* * Dispatch the notify to the appropriate handler * NOTE: the request is queued for execution after this method * completes. The notify handlers are NOT invoked synchronously * from this thread -- because handlers may in turn run other * control methods. */ status = acpi_ev_queue_notify_request(node, value); break; default: ACPI_ERROR((AE_INFO, "Unknown AML opcode 0x%X", walk_state->opcode)); status = AE_AML_BAD_OPCODE; } return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ex_opcode_2A_2T_1R * * PARAMETERS: walk_state - Current walk state * * RETURN: Status * * DESCRIPTION: Execute a dyadic operator (2 operands) with 2 output targets * and one implicit return value. * ******************************************************************************/ acpi_status acpi_ex_opcode_2A_2T_1R(struct acpi_walk_state *walk_state) { union acpi_operand_object **operand = &walk_state->operands[0]; union acpi_operand_object *return_desc1 = NULL; union acpi_operand_object *return_desc2 = NULL; acpi_status status; ACPI_FUNCTION_TRACE_STR(ex_opcode_2A_2T_1R, acpi_ps_get_opcode_name(walk_state->opcode)); /* Execute the opcode */ switch (walk_state->opcode) { case AML_DIVIDE_OP: /* Divide (Dividend, Divisor, remainder_result quotient_result) */ return_desc1 = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER); if (!return_desc1) { status = AE_NO_MEMORY; goto cleanup; } return_desc2 = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER); if (!return_desc2) { status = AE_NO_MEMORY; goto cleanup; } /* Quotient to return_desc1, remainder to return_desc2 */ status = acpi_ut_divide(operand[0]->integer.value, operand[1]->integer.value, &return_desc1->integer.value, &return_desc2->integer.value); if (ACPI_FAILURE(status)) { goto cleanup; } break; default: ACPI_ERROR((AE_INFO, "Unknown AML opcode 0x%X", walk_state->opcode)); status = AE_AML_BAD_OPCODE; goto cleanup; } /* Store the results to the target reference operands */ status = acpi_ex_store(return_desc2, operand[2], walk_state); if (ACPI_FAILURE(status)) { goto cleanup; } status = acpi_ex_store(return_desc1, operand[3], walk_state); if (ACPI_FAILURE(status)) { goto cleanup; } cleanup: /* * Since the remainder is not returned indirectly, remove a reference to * it. Only the quotient is returned indirectly. */ acpi_ut_remove_reference(return_desc2); if (ACPI_FAILURE(status)) { /* Delete the return object */ acpi_ut_remove_reference(return_desc1); } /* Save return object (the remainder) on success */ else { walk_state->result_obj = return_desc1; } return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ex_opcode_2A_1T_1R * * PARAMETERS: walk_state - Current walk state * * RETURN: Status * * DESCRIPTION: Execute opcode with two arguments, one target, and a return * value. * ******************************************************************************/ acpi_status acpi_ex_opcode_2A_1T_1R(struct acpi_walk_state *walk_state) { union acpi_operand_object **operand = &walk_state->operands[0]; union acpi_operand_object *return_desc = NULL; u64 index; acpi_status status = AE_OK; acpi_size length = 0; ACPI_FUNCTION_TRACE_STR(ex_opcode_2A_1T_1R, acpi_ps_get_opcode_name(walk_state->opcode)); /* Execute the opcode */ if (walk_state->op_info->flags & AML_MATH) { /* All simple math opcodes (add, etc.) */ return_desc = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER); if (!return_desc) { status = AE_NO_MEMORY; goto cleanup; } return_desc->integer.value = acpi_ex_do_math_op(walk_state->opcode, operand[0]->integer.value, operand[1]->integer.value); goto store_result_to_target; } switch (walk_state->opcode) { case AML_MOD_OP: /* Mod (Dividend, Divisor, remainder_result (ACPI 2.0) */ return_desc = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER); if (!return_desc) { status = AE_NO_MEMORY; goto cleanup; } /* return_desc will contain the remainder */ status = acpi_ut_divide(operand[0]->integer.value, operand[1]->integer.value, NULL, &return_desc->integer.value); break; case AML_CONCATENATE_OP: /* Concatenate (Data1, Data2, Result) */ status = acpi_ex_do_concatenate(operand[0], operand[1], &return_desc, walk_state); break; case AML_TO_STRING_OP: /* to_string (Buffer, Length, Result) (ACPI 2.0) */ /* * Input object is guaranteed to be a buffer at this point (it may have * been converted.) Copy the raw buffer data to a new object of * type String. */ /* * Get the length of the new string. It is the smallest of: * 1) Length of the input buffer * 2) Max length as specified in the to_string operator * 3) Length of input buffer up to a zero byte (null terminator) * * NOTE: A length of zero is ok, and will create a zero-length, null * terminated string. */ while ((length < operand[0]->buffer.length) && /* Length of input buffer */ (length < operand[1]->integer.value) && /* Length operand */ (operand[0]->buffer.pointer[length])) { /* Null terminator */ length++; } /* Allocate a new string object */ return_desc = acpi_ut_create_string_object(length); if (!return_desc) { status = AE_NO_MEMORY; goto cleanup; } /* * Copy the raw buffer data with no transform. * (NULL terminated already) */ memcpy(return_desc->string.pointer, operand[0]->buffer.pointer, length); break; case AML_CONCATENATE_TEMPLATE_OP: /* concatenate_res_template (Buffer, Buffer, Result) (ACPI 2.0) */ status = acpi_ex_concat_template(operand[0], operand[1], &return_desc, walk_state); break; case AML_INDEX_OP: /* Index (Source Index Result) */ /* Create the internal return object */ return_desc = acpi_ut_create_internal_object(ACPI_TYPE_LOCAL_REFERENCE); if (!return_desc) { status = AE_NO_MEMORY; goto cleanup; } /* Initialize the Index reference object */ index = operand[1]->integer.value; return_desc->reference.value = (u32) index; return_desc->reference.class = ACPI_REFCLASS_INDEX; /* * At this point, the Source operand is a String, Buffer, or Package. * Verify that the index is within range. */ switch ((operand[0])->common.type) { case ACPI_TYPE_STRING: if (index >= operand[0]->string.length) { length = operand[0]->string.length; status = AE_AML_STRING_LIMIT; } return_desc->reference.target_type = ACPI_TYPE_BUFFER_FIELD; return_desc->reference.index_pointer = &(operand[0]->buffer.pointer[index]); break; case ACPI_TYPE_BUFFER: if (index >= operand[0]->buffer.length) { length = operand[0]->buffer.length; status = AE_AML_BUFFER_LIMIT; } return_desc->reference.target_type = ACPI_TYPE_BUFFER_FIELD; return_desc->reference.index_pointer = &(operand[0]->buffer.pointer[index]); break; case ACPI_TYPE_PACKAGE: if (index >= operand[0]->package.count) { length = operand[0]->package.count; status = AE_AML_PACKAGE_LIMIT; } return_desc->reference.target_type = ACPI_TYPE_PACKAGE; return_desc->reference.where = &operand[0]->package.elements[index]; break; default: ACPI_ERROR((AE_INFO, "Invalid object type: %X", (operand[0])->common.type)); status = AE_AML_INTERNAL; goto cleanup; } /* Failure means that the Index was beyond the end of the object */ if (ACPI_FAILURE(status)) { ACPI_BIOS_EXCEPTION((AE_INFO, status, "Index (0x%X%8.8X) is beyond end of object (length 0x%X)", ACPI_FORMAT_UINT64(index), (u32)length)); goto cleanup; } /* * Save the target object and add a reference to it for the life * of the index */ return_desc->reference.object = operand[0]; acpi_ut_add_reference(operand[0]); /* Store the reference to the Target */ status = acpi_ex_store(return_desc, operand[2], walk_state); /* Return the reference */ walk_state->result_obj = return_desc; goto cleanup; default: ACPI_ERROR((AE_INFO, "Unknown AML opcode 0x%X", walk_state->opcode)); status = AE_AML_BAD_OPCODE; break; } store_result_to_target: if (ACPI_SUCCESS(status)) { /* * Store the result of the operation (which is now in return_desc) into * the Target descriptor. */ status = acpi_ex_store(return_desc, operand[2], walk_state); if (ACPI_FAILURE(status)) { goto cleanup; } if (!walk_state->result_obj) { walk_state->result_obj = return_desc; } } cleanup: /* Delete return object on error */ if (ACPI_FAILURE(status)) { acpi_ut_remove_reference(return_desc); walk_state->result_obj = NULL; } return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ex_opcode_2A_0T_1R * * PARAMETERS: walk_state - Current walk state * * RETURN: Status * * DESCRIPTION: Execute opcode with 2 arguments, no target, and a return value * ******************************************************************************/ acpi_status acpi_ex_opcode_2A_0T_1R(struct acpi_walk_state *walk_state) { union acpi_operand_object **operand = &walk_state->operands[0]; union acpi_operand_object *return_desc = NULL; acpi_status status = AE_OK; u8 logical_result = FALSE; ACPI_FUNCTION_TRACE_STR(ex_opcode_2A_0T_1R, acpi_ps_get_opcode_name(walk_state->opcode)); /* Create the internal return object */ return_desc = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER); if (!return_desc) { status = AE_NO_MEMORY; goto cleanup; } /* Execute the Opcode */ if (walk_state->op_info->flags & AML_LOGICAL_NUMERIC) { /* logical_op (Operand0, Operand1) */ status = acpi_ex_do_logical_numeric_op(walk_state->opcode, operand[0]->integer. value, operand[1]->integer. value, &logical_result); goto store_logical_result; } else if (walk_state->op_info->flags & AML_LOGICAL) { /* logical_op (Operand0, Operand1) */ status = acpi_ex_do_logical_op(walk_state->opcode, operand[0], operand[1], &logical_result); goto store_logical_result; } switch (walk_state->opcode) { case AML_ACQUIRE_OP: /* Acquire (mutex_object, Timeout) */ status = acpi_ex_acquire_mutex(operand[1], operand[0], walk_state); if (status == AE_TIME) { logical_result = TRUE; /* TRUE = Acquire timed out */ status = AE_OK; } break; case AML_WAIT_OP: /* Wait (event_object, Timeout) */ status = acpi_ex_system_wait_event(operand[1], operand[0]); if (status == AE_TIME) { logical_result = TRUE; /* TRUE, Wait timed out */ status = AE_OK; } break; default: ACPI_ERROR((AE_INFO, "Unknown AML opcode 0x%X", walk_state->opcode)); status = AE_AML_BAD_OPCODE; goto cleanup; } store_logical_result: /* * Set return value to according to logical_result. logical TRUE (all ones) * Default is FALSE (zero) */ if (logical_result) { return_desc->integer.value = ACPI_UINT64_MAX; } cleanup: /* Delete return object on error */ if (ACPI_FAILURE(status)) { acpi_ut_remove_reference(return_desc); } /* Save return object on success */ else { walk_state->result_obj = return_desc; } return_ACPI_STATUS(status); } |
| 32 32 32 32 32 32 32 32 32 32 32 32 3 32 32 31 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Helper routines for building identity mapping page tables. This is * included by both the compressed kernel and the regular kernel. */ static void free_pte(struct x86_mapping_info *info, pmd_t *pmd) { pte_t *pte = pte_offset_kernel(pmd, 0); info->free_pgt_page(pte, info->context); } static void free_pmd(struct x86_mapping_info *info, pud_t *pud) { pmd_t *pmd = pmd_offset(pud, 0); int i; for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_present(pmd[i])) continue; if (pmd_leaf(pmd[i])) continue; free_pte(info, &pmd[i]); } info->free_pgt_page(pmd, info->context); } static void free_pud(struct x86_mapping_info *info, p4d_t *p4d) { pud_t *pud = pud_offset(p4d, 0); int i; for (i = 0; i < PTRS_PER_PUD; i++) { if (!pud_present(pud[i])) continue; if (pud_leaf(pud[i])) continue; free_pmd(info, &pud[i]); } info->free_pgt_page(pud, info->context); } static void free_p4d(struct x86_mapping_info *info, pgd_t *pgd) { p4d_t *p4d = p4d_offset(pgd, 0); int i; for (i = 0; i < PTRS_PER_P4D; i++) { if (!p4d_present(p4d[i])) continue; free_pud(info, &p4d[i]); } if (pgtable_l5_enabled()) info->free_pgt_page(p4d, info->context); } void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd) { int i; for (i = 0; i < PTRS_PER_PGD; i++) { if (!pgd_present(pgd[i])) continue; free_p4d(info, &pgd[i]); } info->free_pgt_page(pgd, info->context); } static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { addr &= PMD_MASK; for (; addr < end; addr += PMD_SIZE) { pmd_t *pmd = pmd_page + pmd_index(addr); if (pmd_present(*pmd)) continue; set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag)); } } static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, unsigned long addr, unsigned long end) { unsigned long next; for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; bool use_gbpage; next = pud_addr_end(addr, end); /* if this is already a gbpage, this portion is already mapped */ if (pud_leaf(*pud)) continue; /* Is using a gbpage allowed? */ use_gbpage = info->direct_gbpages; /* Don't use gbpage if it maps more than the requested region. */ /* at the begining: */ use_gbpage &= ((addr & ~PUD_MASK) == 0); /* ... or at the end: */ use_gbpage &= ((next & ~PUD_MASK) == 0); /* Never overwrite existing mappings */ use_gbpage &= !pud_present(*pud); if (use_gbpage) { pud_t pudval; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; } if (pud_present(*pud)) { pmd = pmd_offset(pud, 0); ident_pmd_init(info, pmd, addr, next); continue; } pmd = (pmd_t *)info->alloc_pgt_page(info->context); if (!pmd) return -ENOMEM; ident_pmd_init(info, pmd, addr, next); set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag)); } return 0; } static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, unsigned long addr, unsigned long end) { unsigned long next; int result; for (; addr < end; addr = next) { p4d_t *p4d = p4d_page + p4d_index(addr); pud_t *pud; next = p4d_addr_end(addr, end); if (p4d_present(*p4d)) { pud = pud_offset(p4d, 0); result = ident_pud_init(info, pud, addr, next); if (result) return result; continue; } pud = (pud_t *)info->alloc_pgt_page(info->context); if (!pud) return -ENOMEM; result = ident_pud_init(info, pud, addr, next); if (result) return result; set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW)); } return 0; } int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long pstart, unsigned long pend) { unsigned long addr = pstart + info->offset; unsigned long end = pend + info->offset; unsigned long next; int result; /* Set the default pagetable flags if not supplied */ if (!info->kernpg_flag) info->kernpg_flag = _KERNPG_TABLE; /* Filter out unsupported __PAGE_KERNEL_* bits: */ info->kernpg_flag &= __default_kernel_pte_mask; for (; addr < end; addr = next) { pgd_t *pgd = pgd_page + pgd_index(addr); p4d_t *p4d; next = pgd_addr_end(addr, end); if (pgd_present(*pgd)) { p4d = p4d_offset(pgd, 0); result = ident_p4d_init(info, p4d, addr, next); if (result) return result; continue; } p4d = (p4d_t *)info->alloc_pgt_page(info->context); if (!p4d) return -ENOMEM; result = ident_p4d_init(info, p4d, addr, next); if (result) return result; if (pgtable_l5_enabled()) { set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag | _PAGE_NOPTISHADOW)); } else { /* * With p4d folded, pgd is equal to p4d. * The pgd entry has to point to the pud page table in this case. */ pud_t *pud = pud_offset(p4d, 0); set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW)); } } return 0; } |
| 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | // SPDX-License-Identifier: GPL-2.0 /* * Media device request objects * * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved. * Copyright (C) 2018 Intel Corporation * Copyright (C) 2018 Google, Inc. * * Author: Hans Verkuil <hansverk@cisco.com> * Author: Sakari Ailus <sakari.ailus@linux.intel.com> */ #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/refcount.h> #include <media/media-device.h> #include <media/media-request.h> static const char * const request_state[] = { [MEDIA_REQUEST_STATE_IDLE] = "idle", [MEDIA_REQUEST_STATE_VALIDATING] = "validating", [MEDIA_REQUEST_STATE_QUEUED] = "queued", [MEDIA_REQUEST_STATE_COMPLETE] = "complete", [MEDIA_REQUEST_STATE_CLEANING] = "cleaning", [MEDIA_REQUEST_STATE_UPDATING] = "updating", }; static const char * media_request_state_str(enum media_request_state state) { BUILD_BUG_ON(ARRAY_SIZE(request_state) != NR_OF_MEDIA_REQUEST_STATE); if (WARN_ON(state >= ARRAY_SIZE(request_state))) return "invalid"; return request_state[state]; } static void media_request_clean(struct media_request *req) { struct media_request_object *obj, *obj_safe; /* Just a sanity check. No other code path is allowed to change this. */ WARN_ON(req->state != MEDIA_REQUEST_STATE_CLEANING); WARN_ON(req->updating_count); WARN_ON(req->access_count); list_for_each_entry_safe(obj, obj_safe, &req->objects, list) { media_request_object_unbind(obj); media_request_object_put(obj); } req->updating_count = 0; req->access_count = 0; WARN_ON(req->num_incomplete_objects); req->num_incomplete_objects = 0; wake_up_interruptible_all(&req->poll_wait); } static void media_request_release(struct kref *kref) { struct media_request *req = container_of(kref, struct media_request, kref); struct media_device *mdev = req->mdev; dev_dbg(mdev->dev, "request: release %s\n", req->debug_str); /* No other users, no need for a spinlock */ req->state = MEDIA_REQUEST_STATE_CLEANING; media_request_clean(req); if (mdev->ops->req_free) mdev->ops->req_free(req); else kfree(req); } void media_request_put(struct media_request *req) { kref_put(&req->kref, media_request_release); } EXPORT_SYMBOL_GPL(media_request_put); static int media_request_close(struct inode *inode, struct file *filp) { struct media_request *req = filp->private_data; media_request_put(req); return 0; } static __poll_t media_request_poll(struct file *filp, struct poll_table_struct *wait) { struct media_request *req = filp->private_data; unsigned long flags; __poll_t ret = 0; if (!(poll_requested_events(wait) & EPOLLPRI)) return 0; poll_wait(filp, &req->poll_wait, wait); spin_lock_irqsave(&req->lock, flags); if (req->state == MEDIA_REQUEST_STATE_COMPLETE) { ret = EPOLLPRI; goto unlock; } if (req->state != MEDIA_REQUEST_STATE_QUEUED) { ret = EPOLLERR; goto unlock; } unlock: spin_unlock_irqrestore(&req->lock, flags); return ret; } static long media_request_ioctl_queue(struct media_request *req) { struct media_device *mdev = req->mdev; enum media_request_state state; unsigned long flags; int ret; dev_dbg(mdev->dev, "request: queue %s\n", req->debug_str); /* * Ensure the request that is validated will be the one that gets queued * next by serialising the queueing process. This mutex is also used * to serialize with canceling a vb2 queue and with setting values such * as controls in a request. */ mutex_lock(&mdev->req_queue_mutex); media_request_get(req); spin_lock_irqsave(&req->lock, flags); if (req->state == MEDIA_REQUEST_STATE_IDLE) req->state = MEDIA_REQUEST_STATE_VALIDATING; state = req->state; spin_unlock_irqrestore(&req->lock, flags); if (state != MEDIA_REQUEST_STATE_VALIDATING) { dev_dbg(mdev->dev, "request: unable to queue %s, request in state %s\n", req->debug_str, media_request_state_str(state)); media_request_put(req); mutex_unlock(&mdev->req_queue_mutex); return -EBUSY; } ret = mdev->ops->req_validate(req); /* * If the req_validate was successful, then we mark the state as QUEUED * and call req_queue. The reason we set the state first is that this * allows req_queue to unbind or complete the queued objects in case * they are immediately 'consumed'. State changes from QUEUED to another * state can only happen if either the driver changes the state or if * the user cancels the vb2 queue. The driver can only change the state * after each object is queued through the req_queue op (and note that * that op cannot fail), so setting the state to QUEUED up front is * safe. * * The other reason for changing the state is if the vb2 queue is * canceled, and that uses the req_queue_mutex which is still locked * while req_queue is called, so that's safe as well. */ spin_lock_irqsave(&req->lock, flags); req->state = ret ? MEDIA_REQUEST_STATE_IDLE : MEDIA_REQUEST_STATE_QUEUED; spin_unlock_irqrestore(&req->lock, flags); if (!ret) mdev->ops->req_queue(req); mutex_unlock(&mdev->req_queue_mutex); if (ret) { dev_dbg(mdev->dev, "request: can't queue %s (%d)\n", req->debug_str, ret); media_request_put(req); } return ret; } static long media_request_ioctl_reinit(struct media_request *req) { struct media_device *mdev = req->mdev; unsigned long flags; spin_lock_irqsave(&req->lock, flags); if (req->state != MEDIA_REQUEST_STATE_IDLE && req->state != MEDIA_REQUEST_STATE_COMPLETE) { dev_dbg(mdev->dev, "request: %s not in idle or complete state, cannot reinit\n", req->debug_str); spin_unlock_irqrestore(&req->lock, flags); return -EBUSY; } if (req->access_count) { dev_dbg(mdev->dev, "request: %s is being accessed, cannot reinit\n", req->debug_str); spin_unlock_irqrestore(&req->lock, flags); return -EBUSY; } req->state = MEDIA_REQUEST_STATE_CLEANING; spin_unlock_irqrestore(&req->lock, flags); media_request_clean(req); spin_lock_irqsave(&req->lock, flags); req->state = MEDIA_REQUEST_STATE_IDLE; spin_unlock_irqrestore(&req->lock, flags); return 0; } static long media_request_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct media_request *req = filp->private_data; switch (cmd) { case MEDIA_REQUEST_IOC_QUEUE: return media_request_ioctl_queue(req); case MEDIA_REQUEST_IOC_REINIT: return media_request_ioctl_reinit(req); default: return -ENOIOCTLCMD; } } static const struct file_operations request_fops = { .owner = THIS_MODULE, .poll = media_request_poll, .unlocked_ioctl = media_request_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = media_request_ioctl, #endif /* CONFIG_COMPAT */ .release = media_request_close, }; struct media_request * media_request_get_by_fd(struct media_device *mdev, int request_fd) { struct media_request *req; if (!mdev || !mdev->ops || !mdev->ops->req_validate || !mdev->ops->req_queue) return ERR_PTR(-EBADR); CLASS(fd, f)(request_fd); if (fd_empty(f)) goto err; if (fd_file(f)->f_op != &request_fops) goto err; req = fd_file(f)->private_data; if (req->mdev != mdev) goto err; /* * Note: as long as someone has an open filehandle of the request, * the request can never be released. The fdget() above ensures that * even if userspace closes the request filehandle, the release() * fop won't be called, so the media_request_get() always succeeds * and there is no race condition where the request was released * before media_request_get() is called. */ media_request_get(req); return req; err: dev_dbg(mdev->dev, "cannot find request_fd %d\n", request_fd); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(media_request_get_by_fd); int media_request_alloc(struct media_device *mdev, int *alloc_fd) { struct media_request *req; struct file *filp; int fd; int ret; /* Either both are NULL or both are non-NULL */ if (WARN_ON(!mdev->ops->req_alloc ^ !mdev->ops->req_free)) return -ENOMEM; if (mdev->ops->req_alloc) req = mdev->ops->req_alloc(mdev); else req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { ret = fd; goto err_free_req; } filp = anon_inode_getfile("request", &request_fops, NULL, O_CLOEXEC); if (IS_ERR(filp)) { ret = PTR_ERR(filp); goto err_put_fd; } filp->private_data = req; req->mdev = mdev; req->state = MEDIA_REQUEST_STATE_IDLE; req->num_incomplete_objects = 0; kref_init(&req->kref); INIT_LIST_HEAD(&req->objects); spin_lock_init(&req->lock); init_waitqueue_head(&req->poll_wait); req->updating_count = 0; req->access_count = 0; *alloc_fd = fd; snprintf(req->debug_str, sizeof(req->debug_str), "%u:%d", atomic_inc_return(&mdev->request_id), fd); dev_dbg(mdev->dev, "request: allocated %s\n", req->debug_str); fd_install(fd, filp); return 0; err_put_fd: put_unused_fd(fd); err_free_req: if (mdev->ops->req_free) mdev->ops->req_free(req); else kfree(req); return ret; } static void media_request_object_release(struct kref *kref) { struct media_request_object *obj = container_of(kref, struct media_request_object, kref); struct media_request *req = obj->req; if (WARN_ON(req)) media_request_object_unbind(obj); obj->ops->release(obj); } struct media_request_object * media_request_object_find(struct media_request *req, const struct media_request_object_ops *ops, void *priv) { struct media_request_object *obj; struct media_request_object *found = NULL; unsigned long flags; if (WARN_ON(!ops || !priv)) return NULL; spin_lock_irqsave(&req->lock, flags); list_for_each_entry(obj, &req->objects, list) { if (obj->ops == ops && obj->priv == priv) { media_request_object_get(obj); found = obj; break; } } spin_unlock_irqrestore(&req->lock, flags); return found; } EXPORT_SYMBOL_GPL(media_request_object_find); void media_request_object_put(struct media_request_object *obj) { kref_put(&obj->kref, media_request_object_release); } EXPORT_SYMBOL_GPL(media_request_object_put); void media_request_object_init(struct media_request_object *obj) { obj->ops = NULL; obj->req = NULL; obj->priv = NULL; obj->completed = false; INIT_LIST_HEAD(&obj->list); kref_init(&obj->kref); } EXPORT_SYMBOL_GPL(media_request_object_init); int media_request_object_bind(struct media_request *req, const struct media_request_object_ops *ops, void *priv, bool is_buffer, struct media_request_object *obj) { unsigned long flags; int ret = -EBUSY; if (WARN_ON(!ops->release)) return -EBADR; spin_lock_irqsave(&req->lock, flags); if (WARN_ON(req->state != MEDIA_REQUEST_STATE_UPDATING && req->state != MEDIA_REQUEST_STATE_QUEUED)) goto unlock; obj->req = req; obj->ops = ops; obj->priv = priv; if (is_buffer) list_add_tail(&obj->list, &req->objects); else list_add(&obj->list, &req->objects); req->num_incomplete_objects++; ret = 0; unlock: spin_unlock_irqrestore(&req->lock, flags); return ret; } EXPORT_SYMBOL_GPL(media_request_object_bind); void media_request_object_unbind(struct media_request_object *obj) { struct media_request *req = obj->req; unsigned long flags; bool completed = false; if (WARN_ON(!req)) return; spin_lock_irqsave(&req->lock, flags); list_del(&obj->list); obj->req = NULL; if (req->state == MEDIA_REQUEST_STATE_COMPLETE) goto unlock; if (WARN_ON(req->state == MEDIA_REQUEST_STATE_VALIDATING)) goto unlock; if (req->state == MEDIA_REQUEST_STATE_CLEANING) { if (!obj->completed) req->num_incomplete_objects--; goto unlock; } if (WARN_ON(!req->num_incomplete_objects)) goto unlock; req->num_incomplete_objects--; if (req->state == MEDIA_REQUEST_STATE_QUEUED && !req->num_incomplete_objects) { req->state = MEDIA_REQUEST_STATE_COMPLETE; completed = true; wake_up_interruptible_all(&req->poll_wait); } unlock: spin_unlock_irqrestore(&req->lock, flags); if (obj->ops->unbind) obj->ops->unbind(obj); if (completed) media_request_put(req); } EXPORT_SYMBOL_GPL(media_request_object_unbind); void media_request_object_complete(struct media_request_object *obj) { struct media_request *req = obj->req; unsigned long flags; bool completed = false; spin_lock_irqsave(&req->lock, flags); if (obj->completed) goto unlock; obj->completed = true; if (WARN_ON(!req->num_incomplete_objects) || WARN_ON(req->state != MEDIA_REQUEST_STATE_QUEUED)) goto unlock; if (!--req->num_incomplete_objects) { req->state = MEDIA_REQUEST_STATE_COMPLETE; wake_up_interruptible_all(&req->poll_wait); completed = true; } unlock: spin_unlock_irqrestore(&req->lock, flags); if (completed) media_request_put(req); } EXPORT_SYMBOL_GPL(media_request_object_complete); |
| 3 3 2 3 3 3 3 3 3 2 3 3 3 2 2 2 3 1 1 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 6 6 4 5 4 5 5 3 3 3 3 3 2 633 633 633 633 1 1 633 633 633 633 1 24 22 3 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * 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. * * The IP fragmentation functionality. * * Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * Alan Cox : Split from ip.c , see ip_input.c for history. * David S. Miller : Begin massive cleanup... * Andi Kleen : Add sysctls. * xxxx : Overlapfrag bug. * Ultima : ip_expire() kernel panic. * Bill Hawes : Frag accounting and evictor fixes. * John McDonald : 0 length frag bug. * Alexey Kuznetsov: SMP races, threading, cleanup. * Patrick McHardy : LRU queue of frag heads for evictor. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/compiler.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/jiffies.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/netdevice.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/slab.h> #include <net/route.h> #include <net/dst.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_frag.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> #include <net/l3mdev.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c * as well. Or notify me, at least. --ANK */ static const char ip_frag_cache_name[] = "ip4-frags"; /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; unsigned int rid; struct inet_peer *peer; }; static u8 ip4_frag_ecn(u8 tos) { return 1 << (tos & INET_ECN_MASK); } static struct inet_frags ip4_frags; static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev, int *refs); static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); const struct frag_v4_compare_key *key = a; struct net *net = q->fqdir->net; struct inet_peer *p = NULL; q->key.v4 = *key; qp->ecn = 0; if (q->fqdir->max_dist) { rcu_read_lock(); p = inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif); if (p && !refcount_inc_not_zero(&p->refcnt)) p = NULL; rcu_read_unlock(); } qp->peer = p; } static void ip4_frag_free(struct inet_frag_queue *q) { struct ipq *qp; qp = container_of(q, struct ipq, q); if (qp->peer) inet_putpeer(qp->peer); } static bool frag_expire_skip_icmp(u32 user) { return user == IP_DEFRAG_AF_PACKET || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN, __IP_DEFRAG_CONNTRACK_IN_END) || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BRIDGE_IN); } /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ static void ip_expire(struct timer_list *t) { enum skb_drop_reason reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; struct inet_frag_queue *frag = timer_container_of(frag, t, timer); const struct iphdr *iph; struct sk_buff *head = NULL; struct net *net; struct ipq *qp; int refs = 1; qp = container_of(frag, struct ipq, q); net = qp->q.fqdir->net; rcu_read_lock(); /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(qp->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) goto out; qp->q.flags |= INET_FRAG_DROP; inet_frag_kill(&qp->q, &refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); if (!(qp->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&qp->q); if (!head) goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); reason = ip_route_input_noref(head, iph->daddr, iph->saddr, ip4h_dscp(iph), head->dev); if (reason) goto out; /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; if (frag_expire_skip_icmp(qp->q.key.v4.user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; spin_unlock(&qp->q.lock); icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); goto out_rcu_unlock; out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); kfree_skb_reason(head, reason); inet_frag_putn(&qp->q, refs); } /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user, int vif) { struct frag_v4_compare_key key = { .saddr = iph->saddr, .daddr = iph->daddr, .user = user, .vif = vif, .id = iph->id, .protocol = iph->protocol, }; struct inet_frag_queue *q; q = inet_frag_find(net->ipv4.fqdir, &key); if (!q) return NULL; return container_of(q, struct ipq, q); } /* Is the fragment too far ahead to be part of ipq? */ static int ip_frag_too_far(struct ipq *qp) { struct inet_peer *peer = qp->peer; unsigned int max = qp->q.fqdir->max_dist; unsigned int start, end; int rc; if (!peer || !max) return 0; start = qp->rid; end = atomic_inc_return(&peer->rid); qp->rid = end; rc = qp->q.fragments_tail && (end - start) > max; if (rc) __IP_INC_STATS(qp->q.fqdir->net, IPSTATS_MIB_REASMFAILS); return rc; } static int ip_frag_reinit(struct ipq *qp) { unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, SKB_DROP_REASON_FRAG_TOO_FAR); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; qp->iif = 0; qp->ecn = 0; return 0; } /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb, int *refs) { struct net *net = qp->q.fqdir->net; int ihl, end, flags, offset; struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; int err = -ENOENT; SKB_DR(reason); u8 ecn; /* If reassembly is already done, @skb must be a duplicate frag. */ if (qp->q.flags & INET_FRAG_COMPLETE) { SKB_DR_SET(reason, DUP_FRAG); goto err; } if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && unlikely(err = ip_frag_reinit(qp))) { inet_frag_kill(&qp->q, refs); goto err; } ecn = ip4_frag_ecn(ip_hdr(skb)->tos); offset = ntohs(ip_hdr(skb)->frag_off); flags = offset & ~IP_OFFSET; offset &= IP_OFFSET; offset <<= 3; /* offset is in 8-byte chunks */ ihl = ip_hdrlen(skb); /* Determine the position of this fragment. */ end = offset + skb->len - skb_network_offset(skb) - ihl; err = -EINVAL; /* Is this the final fragment? */ if ((flags & IP_MF) == 0) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { if (end&7) { end &= ~7; if (skb->ip_summed != CHECKSUM_UNNECESSARY) skb->ip_summed = CHECKSUM_NONE; } if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) goto discard_qp; qp->q.len = end; } } if (end == offset) goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev_tail = qp->q.fragments_tail; err = inet_frag_queue_insert(&qp->q, skb, offset, end); if (err) goto insert_error; if (dev) qp->iif = dev->ifindex; qp->q.stamp = skb->tstamp; qp->q.tstamp_type = skb->tstamp_type; qp->q.meat += skb->len; qp->ecn |= ecn; add_frag_mem_limit(qp->q.fqdir, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; fragsize = skb->len + ihl; if (fragsize > qp->q.max_size) qp->q.max_size = fragsize; if (ip_hdr(skb)->frag_off & htons(IP_DF) && fragsize > qp->max_df_size) qp->max_df_size = fragsize; if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev, refs); skb->_skb_refdst = orefdst; if (err) inet_frag_kill(&qp->q, refs); return err; } skb_dst_drop(skb); skb_orphan(skb); return -EINPROGRESS; insert_error: if (err == IPFRAG_DUP) { SKB_DR_SET(reason, DUP_FRAG); err = -EINVAL; goto err; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q, refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb_reason(skb, reason); return err; } static bool ip_frag_coalesce_ok(const struct ipq *qp) { return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; } /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev, int *refs) { struct net *net = qp->q.fqdir->net; struct iphdr *iph; void *reasm_data; int len, err; u8 ecn; inet_frag_kill(&qp->q, refs); ecn = ip_frag_ecn_table[qp->ecn]; if (unlikely(ecn == 0xff)) { err = -EINVAL; goto out_fail; } /* Make the one we just received the head. */ reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); if (!reasm_data) goto out_nomem; len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; inet_frag_reasm_finish(&qp->q, skb, reasm_data, ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; /* When we set IP_DF on a refragmented skb we must also force a * call to ip_fragment to avoid forwarding a DF-skb of size s while * original sender only sent fragments of size f (where f < s). * * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest * frag seen to avoid sending tiny DF-fragments in case skb was built * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; } ip_send_check(iph); __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; return 0; out_nomem: net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp); err = -ENOMEM; goto out_fail; out_oversize: net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr); out_fail: __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); return err; } /* Process an incoming IP datagram fragment. */ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; int vif = l3mdev_master_ifindex_rcu(dev); struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ rcu_read_lock(); qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret, refs = 0; spin_lock(&qp->q.lock); ret = ip_frag_queue(qp, skb, &refs); spin_unlock(&qp->q.lock); rcu_read_unlock(); inet_frag_putn(&qp->q, refs); return ret; } rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -ENOMEM; } EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct iphdr iph; int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; netoff = skb_network_offset(skb); if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { kfree_skb(skb); return NULL; } if (pskb_trim_rcsum(skb, netoff + len)) { kfree_skb(skb); return NULL; } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; skb_clear_hash(skb); } } return skb; } EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL static int dist_min; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ipfrag_max_dist", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &dist_min, }, }; /* secret interval has been deprecated */ static int ip4_frags_secret_interval_unused; static struct ctl_table ip4_frags_ctl_table[] = { { .procname = "ipfrag_secret_interval", .data = &ip4_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; static int __net_init ip4_frags_ns_ctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (!table) goto err_alloc; } table[0].data = &net->ipv4.fqdir->high_thresh; table[0].extra1 = &net->ipv4.fqdir->low_thresh; table[1].data = &net->ipv4.fqdir->low_thresh; table[1].extra2 = &net->ipv4.fqdir->high_thresh; table[2].data = &net->ipv4.fqdir->timeout; table[3].data = &net->ipv4.fqdir->max_dist; hdr = register_net_sysctl_sz(net, "net/ipv4", table, ARRAY_SIZE(ip4_frags_ns_ctl_table)); if (!hdr) goto err_reg; net->ipv4.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { const struct ctl_table *table; table = net->ipv4.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.frags_hdr); kfree(table); } static void __init ip4_frags_ctl_register(void) { register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table); } #else static int ip4_frags_ns_ctl_register(struct net *net) { return 0; } static void ip4_frags_ns_ctl_unregister(struct net *net) { } static void __init ip4_frags_ctl_register(void) { } #endif static int __net_init ipv4_frags_init_net(struct net *net) { int res; res = fqdir_init(&net->ipv4.fqdir, &ip4_frags, net); if (res < 0) return res; /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for * the real memory usage, by measuring both the size of frag * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) * and the SKB's truesize. * * A 64K fragment consumes 129736 bytes (44*2944)+200 * (1500 truesize == 2944, sizeof(struct ipq) == 200) * * We will commit 4MB at one time. Should we cross that limit * we will prune down to 3MB, making room for approx 8 big 64K * fragments 8x128k. */ net->ipv4.fqdir->high_thresh = 4 * 1024 * 1024; net->ipv4.fqdir->low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival * by TTL. */ net->ipv4.fqdir->timeout = IP_FRAG_TIME; net->ipv4.fqdir->max_dist = 64; res = ip4_frags_ns_ctl_register(net); if (res < 0) fqdir_exit(net->ipv4.fqdir); return res; } static void __net_exit ipv4_frags_pre_exit_net(struct net *net) { fqdir_pre_exit(net->ipv4.fqdir); } static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); fqdir_exit(net->ipv4.fqdir); } static struct pernet_operations ip4_frags_ops = { .init = ipv4_frags_init_net, .pre_exit = ipv4_frags_pre_exit_net, .exit = ipv4_frags_exit_net, }; static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v4, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v4_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params ip4_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .key_offset = offsetof(struct inet_frag_queue, key), .key_len = sizeof(struct frag_v4_compare_key), .hashfn = ip4_key_hashfn, .obj_hashfn = ip4_obj_hashfn, .obj_cmpfn = ip4_obj_cmpfn, .automatic_shrinking = true, }; void __init ipfrag_init(void) { ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.qsize = sizeof(struct ipq); ip4_frags.frag_expire = ip_expire; ip4_frags.frags_cache_name = ip_frag_cache_name; ip4_frags.rhash_params = ip4_rhash_params; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); ip4_frags_ctl_register(); register_pernet_subsys(&ip4_frags_ops); } |
| 14 14 14 14 5 12 12 12 4 6 2 4 4 4 3 3 3 2 2 2 2 14 10 14 14 17 17 17 16 13 7 17 6 1 6 5 4 2 2 2 4 2 2 2 1 1 5 4 3 3 3 1 2 2 2 2 2 2 2 3 3 3 3 2 15 16 16 7 5 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | // SPDX-License-Identifier: GPL-2.0-only /* * drivers/dma-buf/sync_file.c * * Copyright (C) 2012 Google, Inc. */ #include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> #include <linux/sync_file.h> #include <uapi/linux/sync_file.h> static const struct file_operations sync_file_fops; static struct sync_file *sync_file_alloc(void) { struct sync_file *sync_file; sync_file = kzalloc(sizeof(*sync_file), GFP_KERNEL); if (!sync_file) return NULL; sync_file->file = anon_inode_getfile("sync_file", &sync_file_fops, sync_file, 0); if (IS_ERR(sync_file->file)) goto err; init_waitqueue_head(&sync_file->wq); INIT_LIST_HEAD(&sync_file->cb.node); return sync_file; err: kfree(sync_file); return NULL; } static void fence_check_cb_func(struct dma_fence *f, struct dma_fence_cb *cb) { struct sync_file *sync_file; sync_file = container_of(cb, struct sync_file, cb); wake_up_all(&sync_file->wq); } /** * sync_file_create() - creates a sync file * @fence: fence to add to the sync_fence * * Creates a sync_file containg @fence. This function acquires and additional * reference of @fence for the newly-created &sync_file, if it succeeds. The * sync_file can be released with fput(sync_file->file). Returns the * sync_file or NULL in case of error. */ struct sync_file *sync_file_create(struct dma_fence *fence) { struct sync_file *sync_file; sync_file = sync_file_alloc(); if (!sync_file) return NULL; sync_file->fence = dma_fence_get(fence); return sync_file; } EXPORT_SYMBOL(sync_file_create); static struct sync_file *sync_file_fdget(int fd) { struct file *file = fget(fd); if (!file) return NULL; if (file->f_op != &sync_file_fops) goto err; return file->private_data; err: fput(file); return NULL; } /** * sync_file_get_fence - get the fence related to the sync_file fd * @fd: sync_file fd to get the fence from * * Ensures @fd references a valid sync_file and returns a fence that * represents all fence in the sync_file. On error NULL is returned. */ struct dma_fence *sync_file_get_fence(int fd) { struct sync_file *sync_file; struct dma_fence *fence; sync_file = sync_file_fdget(fd); if (!sync_file) return NULL; fence = dma_fence_get(sync_file->fence); fput(sync_file->file); return fence; } EXPORT_SYMBOL(sync_file_get_fence); /** * sync_file_get_name - get the name of the sync_file * @sync_file: sync_file to get the fence from * @buf: destination buffer to copy sync_file name into * @len: available size of destination buffer. * * Each sync_file may have a name assigned either by the user (when merging * sync_files together) or created from the fence it contains. In the latter * case construction of the name is deferred until use, and so requires * sync_file_get_name(). * * Returns: a string representing the name. */ char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) { if (sync_file->user_name[0]) { strscpy(buf, sync_file->user_name, len); } else { struct dma_fence *fence = sync_file->fence; snprintf(buf, len, "%s-%s%llu-%lld", fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), fence->context, fence->seqno); } return buf; } /** * sync_file_merge() - merge two sync_files * @name: name of new fence * @a: sync_file a * @b: sync_file b * * Creates a new sync_file which contains copies of all the fences in both * @a and @b. @a and @b remain valid, independent sync_file. Returns the * new merged sync_file or NULL in case of error. */ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { struct sync_file *sync_file; struct dma_fence *fence; sync_file = sync_file_alloc(); if (!sync_file) return NULL; fence = dma_fence_unwrap_merge(a->fence, b->fence); if (!fence) { fput(sync_file->file); return NULL; } sync_file->fence = fence; strscpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; } static int sync_file_release(struct inode *inode, struct file *file) { struct sync_file *sync_file = file->private_data; if (test_bit(POLL_ENABLED, &sync_file->flags)) dma_fence_remove_callback(sync_file->fence, &sync_file->cb); dma_fence_put(sync_file->fence); kfree(sync_file); return 0; } static __poll_t sync_file_poll(struct file *file, poll_table *wait) { struct sync_file *sync_file = file->private_data; poll_wait(file, &sync_file->wq, wait); if (list_empty(&sync_file->cb.node) && !test_and_set_bit(POLL_ENABLED, &sync_file->flags)) { if (dma_fence_add_callback(sync_file->fence, &sync_file->cb, fence_check_cb_func) < 0) wake_up_all(&sync_file->wq); } return dma_fence_is_signaled(sync_file->fence) ? EPOLLIN : 0; } static long sync_file_ioctl_merge(struct sync_file *sync_file, unsigned long arg) { int fd = get_unused_fd_flags(O_CLOEXEC); int err; struct sync_file *fence2, *fence3; struct sync_merge_data data; if (fd < 0) return fd; if (copy_from_user(&data, (void __user *)arg, sizeof(data))) { err = -EFAULT; goto err_put_fd; } if (data.flags || data.pad) { err = -EINVAL; goto err_put_fd; } fence2 = sync_file_fdget(data.fd2); if (!fence2) { err = -ENOENT; goto err_put_fd; } data.name[sizeof(data.name) - 1] = '\0'; fence3 = sync_file_merge(data.name, sync_file, fence2); if (!fence3) { err = -ENOMEM; goto err_put_fence2; } data.fence = fd; if (copy_to_user((void __user *)arg, &data, sizeof(data))) { err = -EFAULT; goto err_put_fence3; } fd_install(fd, fence3->file); fput(fence2->file); return 0; err_put_fence3: fput(fence3->file); err_put_fence2: fput(fence2->file); err_put_fd: put_unused_fd(fd); return err; } static int sync_fill_fence_info(struct dma_fence *fence, struct sync_fence_info *info) { strscpy(info->obj_name, fence->ops->get_timeline_name(fence), sizeof(info->obj_name)); strscpy(info->driver_name, fence->ops->get_driver_name(fence), sizeof(info->driver_name)); info->status = dma_fence_get_status(fence); info->timestamp_ns = dma_fence_is_signaled(fence) ? ktime_to_ns(dma_fence_timestamp(fence)) : ktime_set(0, 0); return info->status; } static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { struct sync_fence_info *fence_info = NULL; struct dma_fence_unwrap iter; struct sync_file_info info; unsigned int num_fences; struct dma_fence *fence; int ret; __u32 size; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; if (info.flags || info.pad) return -EINVAL; num_fences = 0; dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to * retrieve any sync_fence_info. If num_fences = 0 we skip filling * sync_fence_info and return the actual number of fences on * info->num_fences. */ if (!info.num_fences) { info.status = dma_fence_get_status(sync_file->fence); goto no_fences; } else { info.status = 1; } if (info.num_fences < num_fences) return -EINVAL; size = num_fences * sizeof(*fence_info); fence_info = kzalloc(size, GFP_KERNEL); if (!fence_info) return -ENOMEM; num_fences = 0; dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { int status; status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info, size)) { ret = -EFAULT; goto out; } no_fences: sync_file_get_name(sync_file, info.name, sizeof(info.name)); info.num_fences = num_fences; if (copy_to_user((void __user *)arg, &info, sizeof(info))) ret = -EFAULT; else ret = 0; out: kfree(fence_info); return ret; } static int sync_file_ioctl_set_deadline(struct sync_file *sync_file, unsigned long arg) { struct sync_set_deadline ts; if (copy_from_user(&ts, (void __user *)arg, sizeof(ts))) return -EFAULT; if (ts.pad) return -EINVAL; dma_fence_set_deadline(sync_file->fence, ns_to_ktime(ts.deadline_ns)); return 0; } static long sync_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct sync_file *sync_file = file->private_data; switch (cmd) { case SYNC_IOC_MERGE: return sync_file_ioctl_merge(sync_file, arg); case SYNC_IOC_FILE_INFO: return sync_file_ioctl_fence_info(sync_file, arg); case SYNC_IOC_SET_DEADLINE: return sync_file_ioctl_set_deadline(sync_file, arg); default: return -ENOTTY; } } static const struct file_operations sync_file_fops = { .release = sync_file_release, .poll = sync_file_poll, .unlocked_ioctl = sync_file_ioctl, .compat_ioctl = compat_ptr_ioctl, }; |
| 9 19 9 20 11 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * vivid-core.h - core datastructures * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #ifndef _VIVID_CORE_H_ #define _VIVID_CORE_H_ #include <linux/fb.h> #include <linux/workqueue.h> #include <media/cec.h> #include <media/videobuf2-v4l2.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> #include <media/v4l2-ctrls.h> #include <media/tpg/v4l2-tpg.h> #include "vivid-rds-gen.h" #include "vivid-vbi-gen.h" #define dprintk(dev, level, fmt, arg...) \ v4l2_dbg(level, vivid_debug, &dev->v4l2_dev, fmt, ## arg) /* The maximum number of inputs */ #define MAX_INPUTS 16 /* The maximum number of outputs */ #define MAX_OUTPUTS 16 /* The maximum number of video capture buffers */ #define MAX_VID_CAP_BUFFERS 64 /* The maximum up or down scaling factor is 4 */ #define MAX_ZOOM 4 /* The maximum image width/height are set to 4K DMT */ #define MAX_WIDTH 4096 #define MAX_HEIGHT 2160 /* The minimum image width/height */ #define MIN_WIDTH 16 #define MIN_HEIGHT MIN_WIDTH /* Pixel Array control divider */ #define PIXEL_ARRAY_DIV MIN_WIDTH /* The data_offset of plane 0 for the multiplanar formats */ #define PLANE0_DATA_OFFSET 128 /* The supported TV frequency range in MHz */ #define MIN_TV_FREQ (44U * 16U) #define MAX_TV_FREQ (958U * 16U) /* The number of samples returned in every SDR buffer */ #define SDR_CAP_SAMPLES_PER_BUF 0x4000 /* used by the threads to know when to resync internal counters */ #define JIFFIES_PER_DAY (3600U * 24U * HZ) #define JIFFIES_RESYNC (JIFFIES_PER_DAY * (0xf0000000U / JIFFIES_PER_DAY)) /* * Maximum number of HDMI inputs allowed by vivid, due to limitations * of the Physical Address in the EDID and used by CEC we stop at 15 * inputs and outputs. */ #define MAX_HDMI_INPUTS 15 #define MAX_HDMI_OUTPUTS 15 /* Maximum number of S-Video inputs allowed by vivid */ #define MAX_SVID_INPUTS 16 /* The maximum number of items in a menu control */ #define MAX_MENU_ITEMS BITS_PER_LONG_LONG /* Number of fixed menu items in the 'Connected To' menu controls */ #define FIXED_MENU_ITEMS 2 /* The maximum number of vivid devices */ #define VIVID_MAX_DEVS CONFIG_VIDEO_VIVID_MAX_DEVS extern const struct v4l2_rect vivid_min_rect; extern const struct v4l2_rect vivid_max_rect; extern unsigned vivid_debug; /* * NULL-terminated string array for the HDMI 'Connected To' menu controls * with the list of possible HDMI outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_hdmi_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all HDMI outputs that are in use */ extern u64 hdmi_to_output_menu_skip_mask; /* * Bitmask of which vivid instances need to update any connected * HDMI outputs. */ extern u64 hdmi_input_update_outputs_mask; /* * Spinlock for access to hdmi_to_output_menu_skip_mask and * hdmi_input_update_outputs_mask. */ extern spinlock_t hdmi_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the HDMI menu skip mask * changes. */ extern struct workqueue_struct *update_hdmi_ctrls_workqueue; /* * The HDMI menu control value (index in the menu list) maps to an HDMI * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_hdmi_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_hdmi_to_output_index[MAX_MENU_ITEMS]; /* * NULL-terminated string array for the S-Video 'Connected To' menu controls * with the list of possible S-Video outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_svid_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all S-Video outputs that are in use */ extern u64 svid_to_output_menu_skip_mask; /* Spinlock for access to svid_to_output_menu_skip_mask */ extern spinlock_t svid_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the S-Video menu skip mask * changes. */ extern struct workqueue_struct *update_svid_ctrls_workqueue; /* * The S-Video menu control value (index in the menu list) maps to an S-Video * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_svid_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_svid_to_output_index[MAX_MENU_ITEMS]; extern struct vivid_dev *vivid_devs[VIVID_MAX_DEVS]; extern unsigned int n_devs; struct vivid_fmt { u32 fourcc; /* v4l2 format id */ enum tgp_color_enc color_enc; bool can_do_overlay; u8 vdownsampling[TPG_MAX_PLANES]; u32 alpha_mask; u8 planes; u8 buffers; u32 data_offset[TPG_MAX_PLANES]; u32 bit_depth[TPG_MAX_PLANES]; }; extern struct vivid_fmt vivid_formats[]; /* buffer for one video frame */ struct vivid_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; enum vivid_input { WEBCAM, TV, SVID, HDMI, }; enum vivid_signal_mode { CURRENT_DV_TIMINGS, CURRENT_STD = CURRENT_DV_TIMINGS, NO_SIGNAL, NO_LOCK, OUT_OF_RANGE, SELECTED_DV_TIMINGS, SELECTED_STD = SELECTED_DV_TIMINGS, CYCLE_DV_TIMINGS, CYCLE_STD = CYCLE_DV_TIMINGS, CUSTOM_DV_TIMINGS, }; enum vivid_colorspace { VIVID_CS_170M, VIVID_CS_709, VIVID_CS_SRGB, VIVID_CS_OPRGB, VIVID_CS_2020, VIVID_CS_DCI_P3, VIVID_CS_240M, VIVID_CS_SYS_M, VIVID_CS_SYS_BG, }; #define VIVID_INVALID_SIGNAL(mode) \ ((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE) struct vivid_cec_xfer { struct cec_adapter *adap; u8 msg[CEC_MAX_MSG_SIZE]; u32 len; u32 sft; }; struct vivid_dev { u8 inst; struct v4l2_device v4l2_dev; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; struct media_pad vid_cap_pad; struct media_pad vid_out_pad; struct media_pad vbi_cap_pad; struct media_pad vbi_out_pad; struct media_pad sdr_cap_pad; struct media_pad meta_cap_pad; struct media_pad meta_out_pad; struct media_pad touch_cap_pad; #endif struct v4l2_ctrl_handler ctrl_hdl_user_gen; struct v4l2_ctrl_handler ctrl_hdl_user_vid; struct v4l2_ctrl_handler ctrl_hdl_user_aud; struct v4l2_ctrl_handler ctrl_hdl_streaming; struct v4l2_ctrl_handler ctrl_hdl_sdtv_cap; struct v4l2_ctrl_handler ctrl_hdl_loop_cap; struct v4l2_ctrl_handler ctrl_hdl_fb; struct video_device vid_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_cap; struct video_device vid_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_out; struct video_device vbi_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_cap; struct video_device vbi_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_out; struct video_device radio_rx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_rx; struct video_device radio_tx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_tx; struct video_device sdr_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_sdr_cap; struct video_device meta_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_cap; struct video_device meta_out_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_out; struct video_device touch_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_touch_cap; spinlock_t slock; struct mutex mutex; struct work_struct update_hdmi_ctrl_work; struct work_struct update_svid_ctrl_work; /* capabilities */ u32 vid_cap_caps; u32 vid_out_caps; u32 vbi_cap_caps; u32 vbi_out_caps; u32 sdr_cap_caps; u32 radio_rx_caps; u32 radio_tx_caps; u32 meta_cap_caps; u32 meta_out_caps; u32 touch_cap_caps; /* supported features */ bool multiplanar; u8 num_inputs; u8 num_hdmi_inputs; u8 num_svid_inputs; u8 input_type[MAX_INPUTS]; u8 input_name_counter[MAX_INPUTS]; u8 num_outputs; u8 num_hdmi_outputs; u8 output_type[MAX_OUTPUTS]; u8 output_name_counter[MAX_OUTPUTS]; bool has_audio_inputs; bool has_audio_outputs; bool has_vid_cap; bool has_vid_out; bool has_vbi_cap; bool has_raw_vbi_cap; bool has_sliced_vbi_cap; bool has_vbi_out; bool has_raw_vbi_out; bool has_sliced_vbi_out; bool has_radio_rx; bool has_radio_tx; bool has_sdr_cap; bool has_fb; bool has_meta_cap; bool has_meta_out; bool has_tv_tuner; bool has_touch_cap; /* Output index (0-MAX_OUTPUTS) to vivid instance of connected input */ struct vivid_dev *output_to_input_instance[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to input index (0-MAX_INPUTS) of connected input */ u8 output_to_input_index[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to HDMI or S-Video output index (0-MAX_HDMI/SVID_OUTPUTS) */ u8 output_to_iface_index[MAX_OUTPUTS]; /* ctrl_hdmi_to_output or ctrl_svid_to_output control value for each input */ s32 input_is_connected_to_output[MAX_INPUTS]; /* HDMI index (0-MAX_HDMI_OUTPUTS) to output index (0-MAX_OUTPUTS) */ u8 hdmi_index_to_output_index[MAX_HDMI_OUTPUTS]; /* HDMI index (0-MAX_HDMI_INPUTS) to input index (0-MAX_INPUTS) */ u8 hdmi_index_to_input_index[MAX_HDMI_INPUTS]; /* S-Video index (0-MAX_SVID_INPUTS) to input index (0-MAX_INPUTS) */ u8 svid_index_to_input_index[MAX_SVID_INPUTS]; /* controls */ struct v4l2_ctrl *brightness; struct v4l2_ctrl *contrast; struct v4l2_ctrl *saturation; struct v4l2_ctrl *hue; struct { /* autogain/gain cluster */ struct v4l2_ctrl *autogain; struct v4l2_ctrl *gain; }; struct v4l2_ctrl *volume; struct v4l2_ctrl *mute; struct v4l2_ctrl *alpha; struct v4l2_ctrl *button; struct v4l2_ctrl *boolean; struct v4l2_ctrl *int32; struct v4l2_ctrl *int64; struct v4l2_ctrl *menu; struct v4l2_ctrl *string; struct v4l2_ctrl *bitmask; struct v4l2_ctrl *int_menu; struct v4l2_ctrl *ro_int32; struct v4l2_ctrl *pixel_array; struct v4l2_ctrl *test_pattern; struct v4l2_ctrl *colorspace; struct v4l2_ctrl *rgb_range_cap; struct v4l2_ctrl *real_rgb_range_cap; struct { /* std_signal_mode/standard cluster */ struct v4l2_ctrl *ctrl_std_signal_mode; struct v4l2_ctrl *ctrl_standard; }; struct { /* dv_timings_signal_mode/timings cluster */ struct v4l2_ctrl *ctrl_dv_timings_signal_mode; struct v4l2_ctrl *ctrl_dv_timings; }; struct v4l2_ctrl *ctrl_has_crop_cap; struct v4l2_ctrl *ctrl_has_compose_cap; struct v4l2_ctrl *ctrl_has_scaler_cap; struct v4l2_ctrl *ctrl_has_crop_out; struct v4l2_ctrl *ctrl_has_compose_out; struct v4l2_ctrl *ctrl_has_scaler_out; struct v4l2_ctrl *ctrl_tx_mode; struct v4l2_ctrl *ctrl_tx_rgb_range; struct v4l2_ctrl *ctrl_tx_edid_present; struct v4l2_ctrl *ctrl_tx_hotplug; struct v4l2_ctrl *ctrl_tx_rxsense; struct v4l2_ctrl *ctrl_rx_power_present; struct v4l2_ctrl *radio_tx_rds_pi; struct v4l2_ctrl *radio_tx_rds_pty; struct v4l2_ctrl *radio_tx_rds_mono_stereo; struct v4l2_ctrl *radio_tx_rds_art_head; struct v4l2_ctrl *radio_tx_rds_compressed; struct v4l2_ctrl *radio_tx_rds_dyn_pty; struct v4l2_ctrl *radio_tx_rds_ta; struct v4l2_ctrl *radio_tx_rds_tp; struct v4l2_ctrl *radio_tx_rds_ms; struct v4l2_ctrl *radio_tx_rds_psname; struct v4l2_ctrl *radio_tx_rds_radiotext; struct v4l2_ctrl *radio_rx_rds_pty; struct v4l2_ctrl *radio_rx_rds_ta; struct v4l2_ctrl *radio_rx_rds_tp; struct v4l2_ctrl *radio_rx_rds_ms; struct v4l2_ctrl *radio_rx_rds_psname; struct v4l2_ctrl *radio_rx_rds_radiotext; struct v4l2_ctrl *ctrl_hdmi_to_output[MAX_HDMI_INPUTS]; char ctrl_hdmi_to_output_names[MAX_HDMI_INPUTS][32]; struct v4l2_ctrl *ctrl_svid_to_output[MAX_SVID_INPUTS]; char ctrl_svid_to_output_names[MAX_SVID_INPUTS][32]; unsigned input_brightness[MAX_INPUTS]; unsigned osd_mode; unsigned button_pressed; bool sensor_hflip; bool sensor_vflip; bool hflip; bool vflip; bool vbi_cap_interlaced; bool loop_video; bool reduced_fps; /* Framebuffer */ unsigned long video_pbase; void *video_vbase; u32 video_buffer_size; int display_width; int display_height; int display_byte_stride; int bits_per_pixel; int bytes_per_pixel; #ifdef CONFIG_VIDEO_VIVID_OSD struct fb_info fb_info; struct fb_var_screeninfo fb_defined; struct fb_fix_screeninfo fb_fix; #endif /* Error injection */ bool disconnect_error; bool queue_setup_error; bool buf_prepare_error; bool start_streaming_error; bool dqbuf_error; bool req_validate_error; bool seq_wrap; u64 time_wrap; u64 time_wrap_offset; unsigned perc_dropped_buffers; enum vivid_signal_mode std_signal_mode[MAX_INPUTS]; unsigned int query_std_last[MAX_INPUTS]; v4l2_std_id query_std[MAX_INPUTS]; enum tpg_video_aspect std_aspect_ratio[MAX_INPUTS]; enum vivid_signal_mode dv_timings_signal_mode[MAX_INPUTS]; char **query_dv_timings_qmenu; char *query_dv_timings_qmenu_strings; unsigned query_dv_timings_size; unsigned int query_dv_timings_last[MAX_INPUTS]; unsigned int query_dv_timings[MAX_INPUTS]; enum tpg_video_aspect dv_timings_aspect_ratio[MAX_INPUTS]; /* Input */ unsigned input; v4l2_std_id std_cap[MAX_INPUTS]; struct v4l2_dv_timings dv_timings_cap[MAX_INPUTS]; int dv_timings_cap_sel[MAX_INPUTS]; u32 service_set_cap; struct vivid_vbi_gen_data vbi_gen; u8 *edid; unsigned edid_blocks; unsigned edid_max_blocks; unsigned webcam_size_idx; unsigned webcam_ival_idx; unsigned tv_freq; unsigned tv_audmode; unsigned tv_field_cap; unsigned tv_audio_input; u32 power_present; /* Output */ unsigned output; v4l2_std_id std_out; struct v4l2_dv_timings dv_timings_out; u32 colorspace_out; u32 ycbcr_enc_out; u32 hsv_enc_out; u32 quantization_out; u32 xfer_func_out; u32 service_set_out; unsigned bytesperline_out[TPG_MAX_PLANES]; unsigned tv_field_out; unsigned tv_audio_output; bool vbi_out_have_wss; u8 vbi_out_wss[2]; bool vbi_out_have_cc[2]; u8 vbi_out_cc[2][2]; bool dvi_d_out; u8 *scaled_line; u8 *blended_line; unsigned cur_scaled_line; /* Output Overlay */ void *fb_vbase_out; bool overlay_out_enabled; int overlay_out_top, overlay_out_left; unsigned fbuf_out_flags; u32 chromakey_out; u8 global_alpha_out; /* video capture */ struct tpg_data tpg; unsigned ms_vid_cap; bool must_blank[MAX_VID_CAP_BUFFERS]; const struct vivid_fmt *fmt_cap; struct v4l2_fract timeperframe_vid_cap; enum v4l2_field field_cap; struct v4l2_rect src_rect; struct v4l2_rect fmt_cap_rect; struct v4l2_rect crop_cap; struct v4l2_rect compose_cap; struct v4l2_rect crop_bounds_cap; struct vb2_queue vb_vid_cap_q; struct list_head vid_cap_active; struct vb2_queue vb_vbi_cap_q; struct list_head vbi_cap_active; struct vb2_queue vb_meta_cap_q; struct list_head meta_cap_active; struct vb2_queue vb_touch_cap_q; struct list_head touch_cap_active; /* thread for generating video capture stream */ struct task_struct *kthread_vid_cap; unsigned long jiffies_vid_cap; u64 cap_stream_start; u64 cap_frame_period; u64 cap_frame_eof_offset; u32 cap_seq_offset; u32 cap_seq_count; bool cap_seq_resync; u32 vid_cap_seq_start; u32 vid_cap_seq_count; bool vid_cap_streaming; u32 vbi_cap_seq_start; u32 vbi_cap_seq_count; bool vbi_cap_streaming; u32 meta_cap_seq_start; u32 meta_cap_seq_count; bool meta_cap_streaming; /* Touch capture */ struct task_struct *kthread_touch_cap; unsigned long jiffies_touch_cap; u64 touch_cap_stream_start; u32 touch_cap_seq_offset; bool touch_cap_seq_resync; u32 touch_cap_seq_start; u32 touch_cap_seq_count; u32 touch_cap_with_seq_wrap_count; bool touch_cap_streaming; struct v4l2_fract timeperframe_tch_cap; struct v4l2_pix_format tch_format; int tch_pat_random; /* video output */ const struct vivid_fmt *fmt_out; struct v4l2_fract timeperframe_vid_out; enum v4l2_field field_out; struct v4l2_rect sink_rect; struct v4l2_rect fmt_out_rect; struct v4l2_rect crop_out; struct v4l2_rect compose_out; struct v4l2_rect compose_bounds_out; struct vb2_queue vb_vid_out_q; struct list_head vid_out_active; struct vb2_queue vb_vbi_out_q; struct list_head vbi_out_active; struct vb2_queue vb_meta_out_q; struct list_head meta_out_active; /* video loop precalculated rectangles */ /* * Intersection between what the output side composes and the capture side * crops. I.e., what actually needs to be copied from the output buffer to * the capture buffer. */ struct v4l2_rect loop_vid_copy; /* The part of the output buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_out; /* The part of the capture buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_cap; /* * The intersection of the framebuffer, the overlay output window and * loop_vid_copy. I.e., the part of the framebuffer that actually should be * blended with the compose_out rectangle. This uses the framebuffer origin. */ struct v4l2_rect loop_fb_copy; /* The same as loop_fb_copy but with compose_out origin. */ struct v4l2_rect loop_vid_overlay; /* * The part of the capture buffer that (after scaling) corresponds * to loop_vid_overlay. */ struct v4l2_rect loop_vid_overlay_cap; /* thread for generating video output stream */ struct task_struct *kthread_vid_out; unsigned long jiffies_vid_out; u32 out_seq_offset; u32 out_seq_count; bool out_seq_resync; u32 vid_out_seq_start; u32 vid_out_seq_count; bool vid_out_streaming; u32 vbi_out_seq_start; u32 vbi_out_seq_count; bool vbi_out_streaming; bool stream_sliced_vbi_out; u32 meta_out_seq_start; u32 meta_out_seq_count; bool meta_out_streaming; /* SDR capture */ struct vb2_queue vb_sdr_cap_q; struct list_head sdr_cap_active; u32 sdr_pixelformat; /* v4l2 format id */ unsigned sdr_buffersize; unsigned sdr_adc_freq; unsigned sdr_fm_freq; unsigned sdr_fm_deviation; int sdr_fixp_src_phase; int sdr_fixp_mod_phase; bool tstamp_src_is_soe; bool has_crop_cap; bool has_compose_cap; bool has_scaler_cap; bool has_crop_out; bool has_compose_out; bool has_scaler_out; /* thread for generating SDR stream */ struct task_struct *kthread_sdr_cap; unsigned long jiffies_sdr_cap; u32 sdr_cap_seq_offset; u32 sdr_cap_seq_start; u32 sdr_cap_seq_count; u32 sdr_cap_with_seq_wrap_count; bool sdr_cap_seq_resync; /* RDS generator */ struct vivid_rds_gen rds_gen; /* Radio receiver */ unsigned radio_rx_freq; unsigned radio_rx_audmode; int radio_rx_sig_qual; unsigned radio_rx_hw_seek_mode; bool radio_rx_hw_seek_prog_lim; bool radio_rx_rds_controls; bool radio_rx_rds_enabled; unsigned radio_rx_rds_use_alternates; unsigned radio_rx_rds_last_block; struct v4l2_fh *radio_rx_rds_owner; /* Radio transmitter */ unsigned radio_tx_freq; unsigned radio_tx_subchans; bool radio_tx_rds_controls; unsigned radio_tx_rds_last_block; struct v4l2_fh *radio_tx_rds_owner; /* Shared between radio receiver and transmitter */ bool radio_rds_loop; ktime_t radio_rds_init_time; /* CEC */ struct cec_adapter *cec_rx_adap; struct cec_adapter *cec_tx_adap[MAX_HDMI_OUTPUTS]; struct task_struct *kthread_cec; wait_queue_head_t kthread_waitq_cec; struct vivid_cec_xfer xfers[MAX_OUTPUTS]; spinlock_t cec_xfers_slock; /* read and write cec messages */ u32 cec_sft; /* bus signal free time, in bit periods */ u8 last_initiator; /* CEC OSD String */ char osd[14]; unsigned long osd_jiffies; bool meta_pts; bool meta_scr; }; static inline bool vivid_is_webcam(const struct vivid_dev *dev) { return dev->input_type[dev->input] == WEBCAM; } static inline bool vivid_is_tv_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == TV; } static inline bool vivid_is_svid_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == SVID; } static inline bool vivid_is_hdmi_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == HDMI; } static inline bool vivid_is_sdtv_cap(const struct vivid_dev *dev) { return vivid_is_tv_cap(dev) || vivid_is_svid_cap(dev); } static inline bool vivid_is_svid_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == SVID; } static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == HDMI; } #endif |
| 86 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * Copyright (C) 2014 Marvell International Ltd. * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> */ #ifndef __NET_NFC_H #define __NET_NFC_H #include <linux/nfc.h> #include <linux/device.h> #include <linux/skbuff.h> #define nfc_dbg(dev, fmt, ...) dev_dbg((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__) struct nfc_phy_ops { int (*write)(void *dev_id, struct sk_buff *skb); int (*enable)(void *dev_id); void (*disable)(void *dev_id); }; struct nfc_dev; /** * data_exchange_cb_t - Definition of nfc_data_exchange callback * * @context: nfc_data_exchange cb_context parameter * @skb: response data * @err: If an error has occurred during data exchange, it is the * error number. Zero means no error. * * When a rx or tx package is lost or corrupted or the target gets out * of the operating field, err is -EIO. */ typedef void (*data_exchange_cb_t)(void *context, struct sk_buff *skb, int err); typedef void (*se_io_cb_t)(void *context, u8 *apdu, size_t apdu_len, int err); struct nfc_target; struct nfc_ops { int (*dev_up)(struct nfc_dev *dev); int (*dev_down)(struct nfc_dev *dev); int (*start_poll)(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); void (*stop_poll)(struct nfc_dev *dev); int (*dep_link_up)(struct nfc_dev *dev, struct nfc_target *target, u8 comm_mode, u8 *gb, size_t gb_len); int (*dep_link_down)(struct nfc_dev *dev); int (*activate_target)(struct nfc_dev *dev, struct nfc_target *target, u32 protocol); void (*deactivate_target)(struct nfc_dev *dev, struct nfc_target *target, u8 mode); int (*im_transceive)(struct nfc_dev *dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context); int (*tm_send)(struct nfc_dev *dev, struct sk_buff *skb); int (*check_presence)(struct nfc_dev *dev, struct nfc_target *target); int (*fw_download)(struct nfc_dev *dev, const char *firmware_name); /* Secure Element API */ int (*discover_se)(struct nfc_dev *dev); int (*enable_se)(struct nfc_dev *dev, u32 se_idx); int (*disable_se)(struct nfc_dev *dev, u32 se_idx); int (*se_io) (struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context); }; #define NFC_TARGET_IDX_ANY -1 #define NFC_MAX_GT_LEN 48 #define NFC_ATR_RES_GT_OFFSET 15 #define NFC_ATR_REQ_GT_OFFSET 14 /** * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. * @ats_len: length of Answer To Select in bytes * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; u32 supported_protocols; u16 sens_res; u8 sel_res; u8 nfcid1_len; u8 nfcid1[NFC_NFCID1_MAXSIZE]; u8 nfcid2_len; u8 nfcid2[NFC_NFCID2_MAXSIZE]; u8 sensb_res_len; u8 sensb_res[NFC_SENSB_RES_MAXSIZE]; u8 sensf_res_len; u8 sensf_res[NFC_SENSF_RES_MAXSIZE]; u8 hci_reader_gate; u8 logical_idx; u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; u8 ats_len; u8 ats[NFC_ATS_MAXSIZE]; }; /** * nfc_se - A structure for NFC accessible secure elements. * * @idx: The secure element index. User space will enable or * disable a secure element by its index. * @type: The secure element type. It can be SE_UICC or * SE_EMBEDDED. * @state: The secure element state, either enabled or disabled. * */ struct nfc_se { struct list_head list; u32 idx; u16 type; u16 state; }; /** * nfc_evt_transaction - A struct for NFC secure element event transaction. * * @aid: The application identifier triggering the event * * @aid_len: The application identifier length [5:16] * * @params: The application parameters transmitted during the transaction * * @params_len: The applications parameters length [0:255] * */ #define NFC_MIN_AID_LENGTH 5 #define NFC_MAX_AID_LENGTH 16 #define NFC_MAX_PARAMS_LENGTH 255 #define NFC_EVT_TRANSACTION_AID_TAG 0x81 #define NFC_EVT_TRANSACTION_PARAMS_TAG 0x82 struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; u8 params[]; } __packed; struct nfc_genl_data { u32 poll_req_portid; struct mutex genl_data_mutex; }; struct nfc_vendor_cmd { __u32 vendor_id; __u32 subcmd; int (*doit)(struct nfc_dev *dev, void *data, size_t data_len); }; struct nfc_dev { int idx; u32 target_next_idx; struct nfc_target *targets; int n_targets; int targets_generation; struct device dev; bool dev_up; bool fw_download_in_progress; u8 rf_mode; bool polling; struct nfc_target *active_target; bool dep_link_up; struct nfc_genl_data genl_data; u32 supported_protocols; struct list_head secure_elements; int tx_headroom; int tx_tailroom; struct timer_list check_pres_timer; struct work_struct check_pres_work; bool shutting_down; struct rfkill *rfkill; const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern const struct class nfc_class; struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); /** * nfc_free_device - free nfc device * * @dev: The nfc device to free */ static inline void nfc_free_device(struct nfc_dev *dev) { put_device(&dev->dev); } int nfc_register_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** * nfc_set_parent_dev - set the parent device * * @nfc_dev: The nfc device whose parent is being set * @dev: The parent device */ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, struct device *dev) { nfc_dev->dev.parent = dev; } /** * nfc_set_drvdata - set driver specific data * * @dev: The nfc device * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } /** * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } /** * nfc_device_name - get the nfc device name * * @dev: The nfc device whose name to return */ static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, unsigned int *err); struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result); int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int ntargets); int nfc_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) return -EINVAL; dev->vendor_cmds = cmds; dev->n_vendor_cmds = n_cmds; return 0; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen); int nfc_vendor_cmd_reply(struct sk_buff *skb); /** * nfc_vendor_cmd_alloc_reply_skb - allocate vendor command reply * @dev: nfc device * @oui: vendor oui * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * a vendor command. Since it is intended for a reply, calling * it outside of a vendor command's doit() operation is invalid. * * The returned skb is pre-filled with some identifying data in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NFC_ATTR_VENDOR_DATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the vendor data attribute. * You must not modify the skb in any other way. * * When done, call nfc_vendor_cmd_reply() with the skb and return * its error code as the result of the doit() operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * nfc_vendor_cmd_alloc_reply_skb(struct nfc_dev *dev, u32 oui, u32 subcmd, int approxlen) { return __nfc_alloc_vendor_cmd_reply_skb(dev, NFC_ATTR_VENDOR_DATA, oui, subcmd, approxlen); } #endif /* __NET_NFC_H */ |
| 5 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: dsobject - Dispatcher object management routines * * Copyright (C) 2000 - 2025, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #include "acparser.h" #include "amlcode.h" #include "acdispat.h" #include "acnamesp.h" #include "acinterp.h" #define _COMPONENT ACPI_DISPATCHER ACPI_MODULE_NAME("dsobject") /******************************************************************************* * * FUNCTION: acpi_ds_build_internal_object * * PARAMETERS: walk_state - Current walk state * op - Parser object to be translated * obj_desc_ptr - Where the ACPI internal object is returned * * RETURN: Status * * DESCRIPTION: Translate a parser Op object to the equivalent namespace object * Simple objects are any objects other than a package object! * ******************************************************************************/ acpi_status acpi_ds_build_internal_object(struct acpi_walk_state *walk_state, union acpi_parse_object *op, union acpi_operand_object **obj_desc_ptr) { union acpi_operand_object *obj_desc; acpi_status status; ACPI_FUNCTION_TRACE(ds_build_internal_object); *obj_desc_ptr = NULL; if (op->common.aml_opcode == AML_INT_NAMEPATH_OP) { /* * This is a named object reference. If this name was * previously looked up in the namespace, it was stored in * this op. Otherwise, go ahead and look it up now */ if (!op->common.node) { /* Check if we are resolving a named reference within a package */ if ((op->common.parent->common.aml_opcode == AML_PACKAGE_OP) || (op->common.parent->common.aml_opcode == AML_VARIABLE_PACKAGE_OP)) { /* * We won't resolve package elements here, we will do this * after all ACPI tables are loaded into the namespace. This * behavior supports both forward references to named objects * and external references to objects in other tables. */ goto create_new_object; } else { status = acpi_ns_lookup(walk_state->scope_info, op->common.value.string, ACPI_TYPE_ANY, ACPI_IMODE_EXECUTE, ACPI_NS_SEARCH_PARENT | ACPI_NS_DONT_OPEN_SCOPE, NULL, ACPI_CAST_INDIRECT_PTR (struct acpi_namespace_node, &(op->common.node))); if (ACPI_FAILURE(status)) { ACPI_ERROR_NAMESPACE(walk_state-> scope_info, op->common.value. string, status); return_ACPI_STATUS(status); } } } } create_new_object: /* Create and init a new internal ACPI object */ obj_desc = acpi_ut_create_internal_object((acpi_ps_get_opcode_info (op->common.aml_opcode))-> object_type); if (!obj_desc) { return_ACPI_STATUS(AE_NO_MEMORY); } status = acpi_ds_init_object_from_op(walk_state, op, op->common.aml_opcode, &obj_desc); if (ACPI_FAILURE(status)) { acpi_ut_remove_reference(obj_desc); return_ACPI_STATUS(status); } /* * Handling for unresolved package reference elements. * These are elements that are namepaths. */ if ((op->common.parent->common.aml_opcode == AML_PACKAGE_OP) || (op->common.parent->common.aml_opcode == AML_VARIABLE_PACKAGE_OP)) { obj_desc->reference.resolved = TRUE; if ((op->common.aml_opcode == AML_INT_NAMEPATH_OP) && !obj_desc->reference.node) { /* * Name was unresolved above. * Get the prefix node for later lookup */ obj_desc->reference.node = walk_state->scope_info->scope.node; obj_desc->reference.aml = op->common.aml; obj_desc->reference.resolved = FALSE; } } *obj_desc_ptr = obj_desc; return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ds_build_internal_buffer_obj * * PARAMETERS: walk_state - Current walk state * op - Parser object to be translated * buffer_length - Length of the buffer * obj_desc_ptr - Where the ACPI internal object is returned * * RETURN: Status * * DESCRIPTION: Translate a parser Op package object to the equivalent * namespace object * ******************************************************************************/ acpi_status acpi_ds_build_internal_buffer_obj(struct acpi_walk_state *walk_state, union acpi_parse_object *op, u32 buffer_length, union acpi_operand_object **obj_desc_ptr) { union acpi_parse_object *arg; union acpi_operand_object *obj_desc; union acpi_parse_object *byte_list; u32 byte_list_length = 0; ACPI_FUNCTION_TRACE(ds_build_internal_buffer_obj); /* * If we are evaluating a Named buffer object "Name (xxxx, Buffer)". * The buffer object already exists (from the NS node), otherwise it must * be created. */ obj_desc = *obj_desc_ptr; if (!obj_desc) { /* Create a new buffer object */ obj_desc = acpi_ut_create_internal_object(ACPI_TYPE_BUFFER); *obj_desc_ptr = obj_desc; if (!obj_desc) { return_ACPI_STATUS(AE_NO_MEMORY); } } /* * Second arg is the buffer data (optional) byte_list can be either * individual bytes or a string initializer. In either case, a * byte_list appears in the AML. */ arg = op->common.value.arg; /* skip first arg */ byte_list = arg->named.next; if (byte_list) { if (byte_list->common.aml_opcode != AML_INT_BYTELIST_OP) { ACPI_ERROR((AE_INFO, "Expecting bytelist, found AML opcode 0x%X in op %p", byte_list->common.aml_opcode, byte_list)); acpi_ut_remove_reference(obj_desc); return (AE_TYPE); } byte_list_length = (u32) byte_list->common.value.integer; } /* * The buffer length (number of bytes) will be the larger of: * 1) The specified buffer length and * 2) The length of the initializer byte list */ obj_desc->buffer.length = buffer_length; if (byte_list_length > buffer_length) { obj_desc->buffer.length = byte_list_length; } /* Allocate the buffer */ if (obj_desc->buffer.length == 0) { obj_desc->buffer.pointer = NULL; ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Buffer defined with zero length in AML, creating\n")); } else { obj_desc->buffer.pointer = ACPI_ALLOCATE_ZEROED(obj_desc->buffer.length); if (!obj_desc->buffer.pointer) { acpi_ut_delete_object_desc(obj_desc); return_ACPI_STATUS(AE_NO_MEMORY); } /* Initialize buffer from the byte_list (if present) */ if (byte_list) { memcpy(obj_desc->buffer.pointer, byte_list->named.data, byte_list_length); } } obj_desc->buffer.flags |= AOPOBJ_DATA_VALID; op->common.node = ACPI_CAST_PTR(struct acpi_namespace_node, obj_desc); return_ACPI_STATUS(AE_OK); } /******************************************************************************* * * FUNCTION: acpi_ds_create_node * * PARAMETERS: walk_state - Current walk state * node - NS Node to be initialized * op - Parser object to be translated * * RETURN: Status * * DESCRIPTION: Create the object to be associated with a namespace node * ******************************************************************************/ acpi_status acpi_ds_create_node(struct acpi_walk_state *walk_state, struct acpi_namespace_node *node, union acpi_parse_object *op) { acpi_status status; union acpi_operand_object *obj_desc; ACPI_FUNCTION_TRACE_PTR(ds_create_node, op); /* * Because of the execution pass through the non-control-method * parts of the table, we can arrive here twice. Only init * the named object node the first time through */ if (acpi_ns_get_attached_object(node)) { return_ACPI_STATUS(AE_OK); } if (!op->common.value.arg) { /* No arguments, there is nothing to do */ return_ACPI_STATUS(AE_OK); } /* Build an internal object for the argument(s) */ status = acpi_ds_build_internal_object(walk_state, op->common.value.arg, &obj_desc); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } /* Re-type the object according to its argument */ node->type = obj_desc->common.type; /* Attach obj to node */ status = acpi_ns_attach_object(node, obj_desc, node->type); /* Remove local reference to the object */ acpi_ut_remove_reference(obj_desc); return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ds_init_object_from_op * * PARAMETERS: walk_state - Current walk state * op - Parser op used to init the internal object * opcode - AML opcode associated with the object * ret_obj_desc - Namespace object to be initialized * * RETURN: Status * * DESCRIPTION: Initialize a namespace object from a parser Op and its * associated arguments. The namespace object is a more compact * representation of the Op and its arguments. * ******************************************************************************/ acpi_status acpi_ds_init_object_from_op(struct acpi_walk_state *walk_state, union acpi_parse_object *op, u16 opcode, union acpi_operand_object **ret_obj_desc) { const struct acpi_opcode_info *op_info; union acpi_operand_object *obj_desc; acpi_status status = AE_OK; ACPI_FUNCTION_TRACE(ds_init_object_from_op); obj_desc = *ret_obj_desc; op_info = acpi_ps_get_opcode_info(opcode); if (op_info->class == AML_CLASS_UNKNOWN) { /* Unknown opcode */ return_ACPI_STATUS(AE_TYPE); } /* Perform per-object initialization */ switch (obj_desc->common.type) { case ACPI_TYPE_BUFFER: /* * Defer evaluation of Buffer term_arg operand */ obj_desc->buffer.node = ACPI_CAST_PTR(struct acpi_namespace_node, walk_state->operands[0]); obj_desc->buffer.aml_start = op->named.data; obj_desc->buffer.aml_length = op->named.length; break; case ACPI_TYPE_PACKAGE: /* * Defer evaluation of Package term_arg operand and all * package elements. (01/2017): We defer the element * resolution to allow forward references from the package * in order to provide compatibility with other ACPI * implementations. */ obj_desc->package.node = ACPI_CAST_PTR(struct acpi_namespace_node, walk_state->operands[0]); if (!op->named.data) { return_ACPI_STATUS(AE_OK); } obj_desc->package.aml_start = op->named.data; obj_desc->package.aml_length = op->named.length; break; case ACPI_TYPE_INTEGER: switch (op_info->type) { case AML_TYPE_CONSTANT: /* * Resolve AML Constants here - AND ONLY HERE! * All constants are integers. * We mark the integer with a flag that indicates that it started * life as a constant -- so that stores to constants will perform * as expected (noop). zero_op is used as a placeholder for optional * target operands. */ obj_desc->common.flags = AOPOBJ_AML_CONSTANT; switch (opcode) { case AML_ZERO_OP: obj_desc->integer.value = 0; break; case AML_ONE_OP: obj_desc->integer.value = 1; break; case AML_ONES_OP: obj_desc->integer.value = ACPI_UINT64_MAX; /* Truncate value if we are executing from a 32-bit ACPI table */ (void)acpi_ex_truncate_for32bit_table(obj_desc); break; case AML_REVISION_OP: obj_desc->integer.value = ACPI_CA_VERSION; break; default: ACPI_ERROR((AE_INFO, "Unknown constant opcode 0x%X", opcode)); status = AE_AML_OPERAND_TYPE; break; } break; case AML_TYPE_LITERAL: obj_desc->integer.value = op->common.value.integer; if (acpi_ex_truncate_for32bit_table(obj_desc)) { /* Warn if we found a 64-bit constant in a 32-bit table */ ACPI_WARNING((AE_INFO, "Truncated 64-bit constant found in 32-bit table: %8.8X%8.8X => %8.8X", ACPI_FORMAT_UINT64(op->common. value.integer), (u32)obj_desc->integer.value)); } break; default: ACPI_ERROR((AE_INFO, "Unknown Integer type 0x%X", op_info->type)); status = AE_AML_OPERAND_TYPE; break; } break; case ACPI_TYPE_STRING: obj_desc->string.pointer = op->common.value.string; obj_desc->string.length = (u32)strlen(op->common.value.string); /* * The string is contained in the ACPI table, don't ever try * to delete it */ obj_desc->common.flags |= AOPOBJ_STATIC_POINTER; break; case ACPI_TYPE_METHOD: break; case ACPI_TYPE_LOCAL_REFERENCE: switch (op_info->type) { case AML_TYPE_LOCAL_VARIABLE: /* Local ID (0-7) is (AML opcode - base AML_FIRST_LOCAL_OP) */ obj_desc->reference.value = ((u32)opcode) - AML_FIRST_LOCAL_OP; obj_desc->reference.class = ACPI_REFCLASS_LOCAL; status = acpi_ds_method_data_get_node(ACPI_REFCLASS_LOCAL, obj_desc->reference. value, walk_state, ACPI_CAST_INDIRECT_PTR (struct acpi_namespace_node, &obj_desc->reference. object)); break; case AML_TYPE_METHOD_ARGUMENT: /* Arg ID (0-6) is (AML opcode - base AML_FIRST_ARG_OP) */ obj_desc->reference.value = ((u32)opcode) - AML_FIRST_ARG_OP; obj_desc->reference.class = ACPI_REFCLASS_ARG; status = acpi_ds_method_data_get_node(ACPI_REFCLASS_ARG, obj_desc-> reference.value, walk_state, ACPI_CAST_INDIRECT_PTR (struct acpi_namespace_node, &obj_desc-> reference. object)); break; default: /* Object name or Debug object */ switch (op->common.aml_opcode) { case AML_INT_NAMEPATH_OP: /* Node was saved in Op */ obj_desc->reference.node = op->common.node; obj_desc->reference.class = ACPI_REFCLASS_NAME; if (op->common.node) { obj_desc->reference.object = op->common.node->object; } break; case AML_DEBUG_OP: obj_desc->reference.class = ACPI_REFCLASS_DEBUG; break; default: ACPI_ERROR((AE_INFO, "Unimplemented reference type for AML opcode: 0x%4.4X", opcode)); return_ACPI_STATUS(AE_AML_OPERAND_TYPE); } break; } break; default: ACPI_ERROR((AE_INFO, "Unimplemented data type: 0x%X", obj_desc->common.type)); status = AE_AML_OPERAND_TYPE; break; } return_ACPI_STATUS(status); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include "netlink.h" #include "common.h" #include "bitset.h" #include "../core/dev.h" #include "ts.h" struct tsconfig_req_info { struct ethnl_req_info base; }; struct tsconfig_reply_data { struct ethnl_reply_data base; struct hwtstamp_provider_desc hwprov_desc; struct { u32 tx_type; u32 rx_filter; u32 flags; } hwtst_config; }; #define TSCONFIG_REPDATA(__reply_base) \ container_of(__reply_base, struct tsconfig_reply_data, base) const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1] = { [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int tsconfig_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); struct hwtstamp_provider *hwprov = NULL; struct net_device *dev = reply_base->dev; struct kernel_hwtstamp_config cfg = {}; int ret; if (!dev->netdev_ops->ndo_hwtstamp_get) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev_get_hwtstamp_phylib(dev, &cfg); if (ret) goto out; data->hwtst_config.tx_type = BIT(cfg.tx_type); data->hwtst_config.rx_filter = BIT(cfg.rx_filter); data->hwtst_config.flags = cfg.flags; data->hwprov_desc.index = -1; hwprov = rtnl_dereference(dev->hwprov); if (hwprov) { data->hwprov_desc.index = hwprov->desc.index; data->hwprov_desc.qualifier = hwprov->desc.qualifier; } else { struct kernel_ethtool_ts_info ts_info = {}; ts_info.phc_index = -1; ret = __ethtool_get_ts_info(dev, &ts_info); if (ret) goto out; if (ts_info.phc_index == -1) return -ENODEV; data->hwprov_desc.index = ts_info.phc_index; data->hwprov_desc.qualifier = ts_info.phc_qualifier; } out: ethnl_ops_complete(dev); return ret; } static int tsconfig_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int len = 0; int ret; BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); if (data->hwtst_config.flags) { ret = ethnl_bitset32_size(&data->hwtst_config.flags, NULL, __HWTSTAMP_FLAG_CNT, ts_flags_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_HWTSTAMP_FLAGS */ } if (data->hwtst_config.tx_type) { ret = ethnl_bitset32_size(&data->hwtst_config.tx_type, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_TX_TYPES */ } if (data->hwtst_config.rx_filter) { ret = ethnl_bitset32_size(&data->hwtst_config.rx_filter, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_RX_FILTERS */ } if (data->hwprov_desc.index >= 0) /* _TSCONFIG_HWTSTAMP_PROVIDER */ len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); return len; } static int tsconfig_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int ret; if (data->hwtst_config.flags) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, &data->hwtst_config.flags, NULL, __HWTSTAMP_FLAG_CNT, ts_flags_names, compact); if (ret < 0) return ret; } if (data->hwtst_config.tx_type) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_TX_TYPES, &data->hwtst_config.tx_type, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; } if (data->hwtst_config.rx_filter) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_RX_FILTERS, &data->hwtst_config.rx_filter, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; } if (data->hwprov_desc.index >= 0) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, data->hwprov_desc.index) || nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, data->hwprov_desc.qualifier)) { nla_nest_cancel(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest); } return 0; } /* TSCONFIG_SET */ const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1] = { [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER] = NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_RX_FILTERS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_TX_TYPES] = { .type = NLA_NESTED }, }; static int tsconfig_send_reply(struct net_device *dev, struct genl_info *info) { struct tsconfig_reply_data *reply_data; struct tsconfig_req_info *req_info; struct sk_buff *rskb; void *reply_payload; int reply_len = 0; int ret; req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(sizeof(*reply_data), GFP_KERNEL); if (!reply_data) { kfree(req_info); return -ENOMEM; } ASSERT_RTNL(); reply_data->base.dev = dev; ret = tsconfig_prepare_data(&req_info->base, &reply_data->base, info); if (ret < 0) goto err_cleanup; ret = tsconfig_reply_size(&req_info->base, &reply_data->base); if (ret < 0) goto err_cleanup; reply_len = ret + ethnl_reply_header_size(); rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_TSCONFIG_SET_REPLY, ETHTOOL_A_TSCONFIG_HEADER, info, &reply_payload); if (!rskb) goto err_cleanup; ret = tsconfig_fill_reply(rskb, &req_info->base, &reply_data->base); if (ret < 0) goto err_cleanup; genlmsg_end(rskb, reply_payload); ret = genlmsg_reply(rskb, info); err_cleanup: kfree(reply_data); kfree(req_info); return ret; } static int ethnl_set_tsconfig_validate(struct ethnl_req_info *req_base, struct genl_info *info) { const struct net_device_ops *ops = req_base->dev->netdev_ops; if (!ops->ndo_hwtstamp_set || !ops->ndo_hwtstamp_get) return -EOPNOTSUPP; return 1; } static struct hwtstamp_provider * tsconfig_set_hwprov_from_desc(struct net_device *dev, struct genl_info *info, struct hwtstamp_provider_desc *hwprov_desc) { struct kernel_ethtool_ts_info ts_info; struct hwtstamp_provider *hwprov; struct nlattr **tb = info->attrs; struct phy_device *phy = NULL; enum hwtstamp_source source; int ret; ret = ethtool_net_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); if (!ret) { /* Found */ source = HWTSTAMP_SOURCE_NETDEV; } else { phy = ethtool_phy_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); if (IS_ERR(phy)) { if (PTR_ERR(phy) == -ENODEV) NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], "phc not in this net device topology"); return ERR_CAST(phy); } source = HWTSTAMP_SOURCE_PHYLIB; } hwprov = kzalloc(sizeof(*hwprov), GFP_KERNEL); if (!hwprov) return ERR_PTR(-ENOMEM); hwprov->desc.index = hwprov_desc->index; hwprov->desc.qualifier = hwprov_desc->qualifier; hwprov->source = source; hwprov->phydev = phy; return hwprov; } static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, struct genl_info *info) { struct kernel_hwtstamp_config hwtst_config = {0}; bool hwprov_mod = false, config_mod = false; struct hwtstamp_provider *hwprov = NULL; struct net_device *dev = req_base->dev; struct nlattr **tb = info->attrs; int ret; BUILD_BUG_ON(__HWTSTAMP_TX_CNT >= 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT >= 32); BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); if (!netif_device_present(dev)) return -ENODEV; if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER]) { struct hwtstamp_provider_desc __hwprov_desc = {.index = -1}; struct hwtstamp_provider *__hwprov; __hwprov = rtnl_dereference(dev->hwprov); if (__hwprov) { __hwprov_desc.index = __hwprov->desc.index; __hwprov_desc.qualifier = __hwprov->desc.qualifier; } ret = ts_parse_hwtst_provider(tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], &__hwprov_desc, info->extack, &hwprov_mod); if (ret < 0) return ret; if (hwprov_mod) { hwprov = tsconfig_set_hwprov_from_desc(dev, info, &__hwprov_desc); if (IS_ERR(hwprov)) return PTR_ERR(hwprov); } } /* Get current hwtstamp config if we are not changing the * hwtstamp source. It will be zeroed in the other case. */ if (!hwprov_mod) { ret = dev_get_hwtstamp_phylib(dev, &hwtst_config); if (ret < 0 && ret != -EOPNOTSUPP) goto err_free_hwprov; } /* Get the hwtstamp config from netlink */ if (tb[ETHTOOL_A_TSCONFIG_TX_TYPES]) { u32 req_tx_type; req_tx_type = BIT(hwtst_config.tx_type); ret = ethnl_update_bitset32(&req_tx_type, __HWTSTAMP_TX_CNT, tb[ETHTOOL_A_TSCONFIG_TX_TYPES], ts_tx_type_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; /* Select only one tx type at a time */ if (ffs(req_tx_type) != fls(req_tx_type)) { ret = -EINVAL; goto err_free_hwprov; } hwtst_config.tx_type = ffs(req_tx_type) - 1; } if (tb[ETHTOOL_A_TSCONFIG_RX_FILTERS]) { u32 req_rx_filter; req_rx_filter = BIT(hwtst_config.rx_filter); ret = ethnl_update_bitset32(&req_rx_filter, __HWTSTAMP_FILTER_CNT, tb[ETHTOOL_A_TSCONFIG_RX_FILTERS], ts_rx_filter_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; /* Select only one rx filter at a time */ if (ffs(req_rx_filter) != fls(req_rx_filter)) { ret = -EINVAL; goto err_free_hwprov; } hwtst_config.rx_filter = ffs(req_rx_filter) - 1; } if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS]) { ret = ethnl_update_bitset32(&hwtst_config.flags, __HWTSTAMP_FLAG_CNT, tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], ts_flags_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; } ret = net_hwtstamp_validate(&hwtst_config); if (ret) goto err_free_hwprov; if (hwprov_mod) { struct kernel_hwtstamp_config zero_config = {0}; struct hwtstamp_provider *__hwprov; /* Disable current time stamping if we try to enable * another one */ ret = dev_set_hwtstamp_phylib(dev, &zero_config, info->extack); if (ret < 0) goto err_free_hwprov; /* Change the selected hwtstamp source */ __hwprov = rcu_replace_pointer_rtnl(dev->hwprov, hwprov); if (__hwprov) kfree_rcu(__hwprov, rcu_head); } if (config_mod) { ret = dev_set_hwtstamp_phylib(dev, &hwtst_config, info->extack); if (ret < 0) return ret; } if (hwprov_mod || config_mod) { ret = tsconfig_send_reply(dev, info); if (ret && ret != -EOPNOTSUPP) { NL_SET_ERR_MSG(info->extack, "error while reading the new configuration set"); return ret; } } /* tsconfig has no notification */ return 0; err_free_hwprov: kfree(hwprov); return ret; } const struct ethnl_request_ops ethnl_tsconfig_request_ops = { .request_cmd = ETHTOOL_MSG_TSCONFIG_GET, .reply_cmd = ETHTOOL_MSG_TSCONFIG_GET_REPLY, .hdr_attr = ETHTOOL_A_TSCONFIG_HEADER, .req_info_size = sizeof(struct tsconfig_req_info), .reply_data_size = sizeof(struct tsconfig_reply_data), .prepare_data = tsconfig_prepare_data, .reply_size = tsconfig_reply_size, .fill_reply = tsconfig_fill_reply, .set_validate = ethnl_set_tsconfig_validate, .set = ethnl_set_tsconfig, }; |
| 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 | /* * Copyright © 2006 Keith Packard * Copyright © 2007-2008 Dave Airlie * Copyright © 2007-2008 Intel Corporation * Jesse Barnes <jesse.barnes@intel.com> * Copyright © 2014 Intel Corporation * Daniel Vetter <daniel.vetter@ffwll.ch> * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. */ #ifndef __DRM_MODES_H__ #define __DRM_MODES_H__ #include <linux/hdmi.h> #include <drm/drm_mode_object.h> #include <drm/drm_connector.h> struct videomode; /* * Note on terminology: here, for brevity and convenience, we refer to connector * control chips as 'CRTCs'. They can control any type of connector, VGA, LVDS, * DVI, etc. And 'screen' refers to the whole of the visible display, which * may span multiple monitors (and therefore multiple CRTC and connector * structures). */ /** * enum drm_mode_status - hardware support status of a mode * @MODE_OK: Mode OK * @MODE_HSYNC: hsync out of range * @MODE_VSYNC: vsync out of range * @MODE_H_ILLEGAL: mode has illegal horizontal timings * @MODE_V_ILLEGAL: mode has illegal vertical timings * @MODE_BAD_WIDTH: requires an unsupported linepitch * @MODE_NOMODE: no mode with a matching name * @MODE_NO_INTERLACE: interlaced mode not supported * @MODE_NO_DBLESCAN: doublescan mode not supported * @MODE_NO_VSCAN: multiscan mode not supported * @MODE_MEM: insufficient video memory * @MODE_VIRTUAL_X: mode width too large for specified virtual size * @MODE_VIRTUAL_Y: mode height too large for specified virtual size * @MODE_MEM_VIRT: insufficient video memory given virtual size * @MODE_NOCLOCK: no fixed clock available * @MODE_CLOCK_HIGH: clock required is too high * @MODE_CLOCK_LOW: clock required is too low * @MODE_CLOCK_RANGE: clock/mode isn't in a ClockRange * @MODE_BAD_HVALUE: horizontal timing was out of range * @MODE_BAD_VVALUE: vertical timing was out of range * @MODE_BAD_VSCAN: VScan value out of range * @MODE_HSYNC_NARROW: horizontal sync too narrow * @MODE_HSYNC_WIDE: horizontal sync too wide * @MODE_HBLANK_NARROW: horizontal blanking too narrow * @MODE_HBLANK_WIDE: horizontal blanking too wide * @MODE_VSYNC_NARROW: vertical sync too narrow * @MODE_VSYNC_WIDE: vertical sync too wide * @MODE_VBLANK_NARROW: vertical blanking too narrow * @MODE_VBLANK_WIDE: vertical blanking too wide * @MODE_PANEL: exceeds panel dimensions * @MODE_INTERLACE_WIDTH: width too large for interlaced mode * @MODE_ONE_WIDTH: only one width is supported * @MODE_ONE_HEIGHT: only one height is supported * @MODE_ONE_SIZE: only one resolution is supported * @MODE_NO_REDUCED: monitor doesn't accept reduced blanking * @MODE_NO_STEREO: stereo modes not supported * @MODE_NO_420: ycbcr 420 modes not supported * @MODE_STALE: mode has become stale * @MODE_BAD: unspecified reason * @MODE_ERROR: error condition * * This enum is used to filter out modes not supported by the driver/hardware * combination. */ enum drm_mode_status { MODE_OK = 0, MODE_HSYNC, MODE_VSYNC, MODE_H_ILLEGAL, MODE_V_ILLEGAL, MODE_BAD_WIDTH, MODE_NOMODE, MODE_NO_INTERLACE, MODE_NO_DBLESCAN, MODE_NO_VSCAN, MODE_MEM, MODE_VIRTUAL_X, MODE_VIRTUAL_Y, MODE_MEM_VIRT, MODE_NOCLOCK, MODE_CLOCK_HIGH, MODE_CLOCK_LOW, MODE_CLOCK_RANGE, MODE_BAD_HVALUE, MODE_BAD_VVALUE, MODE_BAD_VSCAN, MODE_HSYNC_NARROW, MODE_HSYNC_WIDE, MODE_HBLANK_NARROW, MODE_HBLANK_WIDE, MODE_VSYNC_NARROW, MODE_VSYNC_WIDE, MODE_VBLANK_NARROW, MODE_VBLANK_WIDE, MODE_PANEL, MODE_INTERLACE_WIDTH, MODE_ONE_WIDTH, MODE_ONE_HEIGHT, MODE_ONE_SIZE, MODE_NO_REDUCED, MODE_NO_STEREO, MODE_NO_420, MODE_STALE = -3, MODE_BAD = -2, MODE_ERROR = -1 }; #define DRM_MODE(nm, t, c, hd, hss, hse, ht, hsk, vd, vss, vse, vt, vs, f) \ .name = nm, .status = 0, .type = (t), .clock = (c), \ .hdisplay = (hd), .hsync_start = (hss), .hsync_end = (hse), \ .htotal = (ht), .hskew = (hsk), .vdisplay = (vd), \ .vsync_start = (vss), .vsync_end = (vse), .vtotal = (vt), \ .vscan = (vs), .flags = (f) /** * DRM_MODE_RES_MM - Calculates the display size from resolution and DPI * @res: The resolution in pixel * @dpi: The number of dots per inch */ #define DRM_MODE_RES_MM(res, dpi) \ (((res) * 254ul) / ((dpi) * 10ul)) #define __DRM_MODE_INIT(pix, hd, vd, hd_mm, vd_mm) \ .type = DRM_MODE_TYPE_DRIVER, .clock = (pix), \ .hdisplay = (hd), .hsync_start = (hd), .hsync_end = (hd), \ .htotal = (hd), .vdisplay = (vd), .vsync_start = (vd), \ .vsync_end = (vd), .vtotal = (vd), .width_mm = (hd_mm), \ .height_mm = (vd_mm) /** * DRM_MODE_INIT - Initialize display mode * @hz: Vertical refresh rate in Hertz * @hd: Horizontal resolution, width * @vd: Vertical resolution, height * @hd_mm: Display width in millimeters * @vd_mm: Display height in millimeters * * This macro initializes a &drm_display_mode that contains information about * refresh rate, resolution and physical size. */ #define DRM_MODE_INIT(hz, hd, vd, hd_mm, vd_mm) \ __DRM_MODE_INIT((hd) * (vd) * (hz) / 1000 /* kHz */, hd, vd, hd_mm, vd_mm) /** * DRM_SIMPLE_MODE - Simple display mode * @hd: Horizontal resolution, width * @vd: Vertical resolution, height * @hd_mm: Display width in millimeters * @vd_mm: Display height in millimeters * * This macro initializes a &drm_display_mode that only contains info about * resolution and physical size. */ #define DRM_SIMPLE_MODE(hd, vd, hd_mm, vd_mm) \ __DRM_MODE_INIT(1 /* pass validation */, hd, vd, hd_mm, vd_mm) #define CRTC_INTERLACE_HALVE_V (1 << 0) /* halve V values for interlacing */ #define CRTC_STEREO_DOUBLE (1 << 1) /* adjust timings for stereo modes */ #define CRTC_NO_DBLSCAN (1 << 2) /* don't adjust doublescan */ #define CRTC_NO_VSCAN (1 << 3) /* don't adjust doublescan */ #define CRTC_STEREO_DOUBLE_ONLY (CRTC_STEREO_DOUBLE | CRTC_NO_DBLSCAN | CRTC_NO_VSCAN) #define DRM_MODE_FLAG_3D_MAX DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF #define DRM_MODE_MATCH_TIMINGS (1 << 0) #define DRM_MODE_MATCH_CLOCK (1 << 1) #define DRM_MODE_MATCH_FLAGS (1 << 2) #define DRM_MODE_MATCH_3D_FLAGS (1 << 3) #define DRM_MODE_MATCH_ASPECT_RATIO (1 << 4) /** * struct drm_display_mode - DRM kernel-internal display mode structure * @hdisplay: horizontal display size * @hsync_start: horizontal sync start * @hsync_end: horizontal sync end * @htotal: horizontal total size * @hskew: horizontal skew?! * @vdisplay: vertical display size * @vsync_start: vertical sync start * @vsync_end: vertical sync end * @vtotal: vertical total size * @vscan: vertical scan?! * @crtc_hdisplay: hardware mode horizontal display size * @crtc_hblank_start: hardware mode horizontal blank start * @crtc_hblank_end: hardware mode horizontal blank end * @crtc_hsync_start: hardware mode horizontal sync start * @crtc_hsync_end: hardware mode horizontal sync end * @crtc_htotal: hardware mode horizontal total size * @crtc_hskew: hardware mode horizontal skew?! * @crtc_vdisplay: hardware mode vertical display size * @crtc_vblank_start: hardware mode vertical blank start * @crtc_vblank_end: hardware mode vertical blank end * @crtc_vsync_start: hardware mode vertical sync start * @crtc_vsync_end: hardware mode vertical sync end * @crtc_vtotal: hardware mode vertical total size * * This is the kernel API display mode information structure. For the * user-space version see struct drm_mode_modeinfo. * * The horizontal and vertical timings are defined per the following diagram. * * :: * * * Active Front Sync Back * Region Porch Porch * <-----------------------><----------------><-------------><--------------> * //////////////////////| * ////////////////////// | * ////////////////////// |.................. ................ * _______________ * <----- [hv]display -----> * <------------- [hv]sync_start ------------> * <--------------------- [hv]sync_end ---------------------> * <-------------------------------- [hv]total ----------------------------->* * * This structure contains two copies of timings. First are the plain timings, * which specify the logical mode, as it would be for a progressive 1:1 scanout * at the refresh rate userspace can observe through vblank timestamps. Then * there's the hardware timings, which are corrected for interlacing, * double-clocking and similar things. They are provided as a convenience, and * can be appropriately computed using drm_mode_set_crtcinfo(). * * For printing you can use %DRM_MODE_FMT and DRM_MODE_ARG(). */ struct drm_display_mode { /** * @clock: * * Pixel clock in kHz. */ int clock; /* in kHz */ u16 hdisplay; u16 hsync_start; u16 hsync_end; u16 htotal; u16 hskew; u16 vdisplay; u16 vsync_start; u16 vsync_end; u16 vtotal; u16 vscan; /** * @flags: * * Sync and timing flags: * * - DRM_MODE_FLAG_PHSYNC: horizontal sync is active high. * - DRM_MODE_FLAG_NHSYNC: horizontal sync is active low. * - DRM_MODE_FLAG_PVSYNC: vertical sync is active high. * - DRM_MODE_FLAG_NVSYNC: vertical sync is active low. * - DRM_MODE_FLAG_INTERLACE: mode is interlaced. * - DRM_MODE_FLAG_DBLSCAN: mode uses doublescan. * - DRM_MODE_FLAG_CSYNC: mode uses composite sync. * - DRM_MODE_FLAG_PCSYNC: composite sync is active high. * - DRM_MODE_FLAG_NCSYNC: composite sync is active low. * - DRM_MODE_FLAG_HSKEW: hskew provided (not used?). * - DRM_MODE_FLAG_BCAST: <deprecated> * - DRM_MODE_FLAG_PIXMUX: <deprecated> * - DRM_MODE_FLAG_DBLCLK: double-clocked mode. * - DRM_MODE_FLAG_CLKDIV2: half-clocked mode. * * Additionally there's flags to specify how 3D modes are packed: * * - DRM_MODE_FLAG_3D_NONE: normal, non-3D mode. * - DRM_MODE_FLAG_3D_FRAME_PACKING: 2 full frames for left and right. * - DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE: interleaved like fields. * - DRM_MODE_FLAG_3D_LINE_ALTERNATIVE: interleaved lines. * - DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL: side-by-side full frames. * - DRM_MODE_FLAG_3D_L_DEPTH: ? * - DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH: ? * - DRM_MODE_FLAG_3D_TOP_AND_BOTTOM: frame split into top and bottom * parts. * - DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF: frame split into left and * right parts. */ u32 flags; /** * @crtc_clock: * * Actual pixel or dot clock in the hardware. This differs from the * logical @clock when e.g. using interlacing, double-clocking, stereo * modes or other fancy stuff that changes the timings and signals * actually sent over the wire. * * This is again in kHz. * * Note that with digital outputs like HDMI or DP there's usually a * massive confusion between the dot clock and the signal clock at the * bit encoding level. Especially when a 8b/10b encoding is used and the * difference is exactly a factor of 10. */ int crtc_clock; u16 crtc_hdisplay; u16 crtc_hblank_start; u16 crtc_hblank_end; u16 crtc_hsync_start; u16 crtc_hsync_end; u16 crtc_htotal; u16 crtc_hskew; u16 crtc_vdisplay; u16 crtc_vblank_start; u16 crtc_vblank_end; u16 crtc_vsync_start; u16 crtc_vsync_end; u16 crtc_vtotal; /** * @width_mm: * * Addressable size of the output in mm, projectors should set this to * 0. */ u16 width_mm; /** * @height_mm: * * Addressable size of the output in mm, projectors should set this to * 0. */ u16 height_mm; /** * @type: * * A bitmask of flags, mostly about the source of a mode. Possible flags * are: * * - DRM_MODE_TYPE_PREFERRED: Preferred mode, usually the native * resolution of an LCD panel. There should only be one preferred * mode per connector at any given time. * - DRM_MODE_TYPE_DRIVER: Mode created by the driver, which is all of * them really. Drivers must set this bit for all modes they create * and expose to userspace. * - DRM_MODE_TYPE_USERDEF: Mode defined or selected via the kernel * command line. * * Plus a big list of flags which shouldn't be used at all, but are * still around since these flags are also used in the userspace ABI. * We no longer accept modes with these types though: * * - DRM_MODE_TYPE_BUILTIN: Meant for hard-coded modes, unused. * Use DRM_MODE_TYPE_DRIVER instead. * - DRM_MODE_TYPE_DEFAULT: Again a leftover, use * DRM_MODE_TYPE_PREFERRED instead. * - DRM_MODE_TYPE_CLOCK_C and DRM_MODE_TYPE_CRTC_C: Define leftovers * which are stuck around for hysterical raisins only. No one has an * idea what they were meant for. Don't use. */ u8 type; /** * @expose_to_userspace: * * Indicates whether the mode is to be exposed to the userspace. * This is to maintain a set of exposed modes while preparing * user-mode's list in drm_mode_getconnector ioctl. The purpose of * this only lies in the ioctl function, and is not to be used * outside the function. */ bool expose_to_userspace; /** * @head: * * struct list_head for mode lists. */ struct list_head head; /** * @name: * * Human-readable name of the mode, filled out with drm_mode_set_name(). */ char name[DRM_DISPLAY_MODE_LEN]; /** * @status: * * Status of the mode, used to filter out modes not supported by the * hardware. See enum &drm_mode_status. */ enum drm_mode_status status; /** * @picture_aspect_ratio: * * Field for setting the HDMI picture aspect ratio of a mode. */ enum hdmi_picture_aspect picture_aspect_ratio; }; /** * DRM_MODE_FMT - printf string for &struct drm_display_mode */ #define DRM_MODE_FMT "\"%s\": %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x" /** * DRM_MODE_ARG - printf arguments for &struct drm_display_mode * @m: display mode */ #define DRM_MODE_ARG(m) \ (m)->name, drm_mode_vrefresh(m), (m)->clock, \ (m)->hdisplay, (m)->hsync_start, (m)->hsync_end, (m)->htotal, \ (m)->vdisplay, (m)->vsync_start, (m)->vsync_end, (m)->vtotal, \ (m)->type, (m)->flags #define obj_to_mode(x) container_of(x, struct drm_display_mode, base) /** * drm_mode_is_stereo - check for stereo mode flags * @mode: drm_display_mode to check * * Returns: * True if the mode is one of the stereo modes (like side-by-side), false if * not. */ static inline bool drm_mode_is_stereo(const struct drm_display_mode *mode) { return mode->flags & DRM_MODE_FLAG_3D_MASK; } struct drm_connector; struct drm_cmdline_mode; struct drm_display_mode *drm_mode_create(struct drm_device *dev); void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode); void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out, const struct drm_display_mode *in); int drm_mode_convert_umode(struct drm_device *dev, struct drm_display_mode *out, const struct drm_mode_modeinfo *in); void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode); void drm_mode_debug_printmodeline(const struct drm_display_mode *mode); bool drm_mode_is_420_only(const struct drm_display_info *display, const struct drm_display_mode *mode); bool drm_mode_is_420_also(const struct drm_display_info *display, const struct drm_display_mode *mode); bool drm_mode_is_420(const struct drm_display_info *display, const struct drm_display_mode *mode); void drm_set_preferred_mode(struct drm_connector *connector, int hpref, int vpref); struct drm_display_mode *drm_analog_tv_mode(struct drm_device *dev, enum drm_connector_tv_mode mode, unsigned long pixel_clock_hz, unsigned int hdisplay, unsigned int vdisplay, bool interlace); static inline struct drm_display_mode *drm_mode_analog_ntsc_480i(struct drm_device *dev) { return drm_analog_tv_mode(dev, DRM_MODE_TV_MODE_NTSC, 13500000, 720, 480, true); } static inline struct drm_display_mode *drm_mode_analog_pal_576i(struct drm_device *dev) { return drm_analog_tv_mode(dev, DRM_MODE_TV_MODE_PAL, 13500000, 720, 576, true); } struct drm_display_mode *drm_cvt_mode(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh, bool reduced, bool interlaced, bool margins); struct drm_display_mode *drm_gtf_mode(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh, bool interlaced, int margins); struct drm_display_mode *drm_gtf_mode_complex(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh, bool interlaced, int margins, int GTF_M, int GTF_2C, int GTF_K, int GTF_2J); void drm_display_mode_from_videomode(const struct videomode *vm, struct drm_display_mode *dmode); void drm_display_mode_to_videomode(const struct drm_display_mode *dmode, struct videomode *vm); void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags); #if defined(CONFIG_OF) int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags, int index); int of_get_drm_panel_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags); #else static inline int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags, int index) { return -EINVAL; } static inline int of_get_drm_panel_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags) { return -EINVAL; } #endif void drm_mode_set_name(struct drm_display_mode *mode); int drm_mode_vrefresh(const struct drm_display_mode *mode); void drm_mode_get_hv_timing(const struct drm_display_mode *mode, int *hdisplay, int *vdisplay); void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags); void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src); void drm_mode_init(struct drm_display_mode *dst, const struct drm_display_mode *src); struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev, const struct drm_display_mode *mode); bool drm_mode_match(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2, unsigned int match_flags); bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2); bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2); bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2); /* for use by the crtc helper probe functions */ enum drm_mode_status drm_mode_validate_driver(struct drm_device *dev, const struct drm_display_mode *mode); enum drm_mode_status drm_mode_validate_size(const struct drm_display_mode *mode, int maxX, int maxY); enum drm_mode_status drm_mode_validate_ycbcr420(const struct drm_display_mode *mode, struct drm_connector *connector); void drm_mode_prune_invalid(struct drm_device *dev, struct list_head *mode_list, bool verbose); void drm_mode_sort(struct list_head *mode_list); void drm_connector_list_update(struct drm_connector *connector); /* parsing cmdline modes */ bool drm_mode_parse_command_line_for_connector(const char *mode_option, const struct drm_connector *connector, struct drm_cmdline_mode *mode); struct drm_display_mode * drm_mode_create_from_cmdline_mode(struct drm_device *dev, struct drm_cmdline_mode *cmd); #endif /* __DRM_MODES_H__ */ |
| 185 184 184 75 11 75 75 64 11 75 117 92 92 92 32 32 194 184 184 16 162 154 38 153 153 153 152 152 105 104 151 131 131 36 152 154 161 94 94 81 69 54 69 64 69 94 94 14 14 13 14 14 90 90 80 59 10 59 59 50 90 70 70 89 75 65 65 59 65 65 88 2 56 46 58 59 8 6 8 8 7 65 14 14 1 14 14 3 2 2 3 1 1 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * MIDI device handlers * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <sound/asoundef.h> #include "seq_oss_midi.h" #include "seq_oss_readq.h" #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <sound/seq_midi_event.h> #include "../seq_lock.h" #include <linux/init.h> #include <linux/slab.h> #include <linux/nospec.h> /* * constants */ #define SNDRV_SEQ_OSS_MAX_MIDI_NAME 30 /* * definition of midi device record */ struct seq_oss_midi { int seq_device; /* device number */ int client; /* sequencer client number */ int port; /* sequencer port number */ unsigned int flags; /* port capability */ int opened; /* flag for opening */ unsigned char name[SNDRV_SEQ_OSS_MAX_MIDI_NAME]; struct snd_midi_event *coder; /* MIDI event coder */ struct seq_oss_devinfo *devinfo; /* assigned OSSseq device */ snd_use_lock_t use_lock; struct mutex open_mutex; }; /* * midi device table */ static int max_midi_devs; static struct seq_oss_midi *midi_devs[SNDRV_SEQ_OSS_MAX_MIDI_DEVS]; static DEFINE_SPINLOCK(register_lock); /* * prototypes */ static struct seq_oss_midi *get_mdev(int dev); static struct seq_oss_midi *get_mididev(struct seq_oss_devinfo *dp, int dev); static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev); static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev); /* * look up the existing ports * this looks a very exhausting job. */ int snd_seq_oss_midi_lookup_ports(int client) { struct snd_seq_client_info *clinfo __free(kfree) = NULL; struct snd_seq_port_info *pinfo __free(kfree) = NULL; clinfo = kzalloc(sizeof(*clinfo), GFP_KERNEL); pinfo = kzalloc(sizeof(*pinfo), GFP_KERNEL); if (!clinfo || !pinfo) return -ENOMEM; clinfo->client = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT, clinfo) == 0) { if (clinfo->client == client) continue; /* ignore myself */ pinfo->addr.client = clinfo->client; pinfo->addr.port = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT, pinfo) == 0) snd_seq_oss_midi_check_new_port(pinfo); } return 0; } /* */ static struct seq_oss_midi * get_mdev(int dev) { struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); mdev = midi_devs[dev]; if (mdev) snd_use_lock_use(&mdev->use_lock); spin_unlock_irqrestore(®ister_lock, flags); return mdev; } /* * look for the identical slot */ static struct seq_oss_midi * find_slot(int client, int port) { int i; struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev && mdev->client == client && mdev->port == port) { /* found! */ snd_use_lock_use(&mdev->use_lock); spin_unlock_irqrestore(®ister_lock, flags); return mdev; } } spin_unlock_irqrestore(®ister_lock, flags); return NULL; } #define PERM_WRITE (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_SUBS_WRITE) #define PERM_READ (SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ) /* * register a new port if it doesn't exist yet */ int snd_seq_oss_midi_check_new_port(struct snd_seq_port_info *pinfo) { int i; struct seq_oss_midi *mdev; unsigned long flags; /* the port must include generic midi */ if (! (pinfo->type & SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC)) return 0; /* either read or write subscribable */ if ((pinfo->capability & PERM_WRITE) != PERM_WRITE && (pinfo->capability & PERM_READ) != PERM_READ) return 0; /* * look for the identical slot */ mdev = find_slot(pinfo->addr.client, pinfo->addr.port); if (mdev) { /* already exists */ snd_use_lock_free(&mdev->use_lock); return 0; } /* * allocate midi info record */ mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return -ENOMEM; /* copy the port information */ mdev->client = pinfo->addr.client; mdev->port = pinfo->addr.port; mdev->flags = pinfo->capability; mdev->opened = 0; snd_use_lock_init(&mdev->use_lock); mutex_init(&mdev->open_mutex); /* copy and truncate the name of synth device */ strscpy(mdev->name, pinfo->name, sizeof(mdev->name)); /* create MIDI coder */ if (snd_midi_event_new(MAX_MIDI_EVENT_BUF, &mdev->coder) < 0) { pr_err("ALSA: seq_oss: can't malloc midi coder\n"); kfree(mdev); return -ENOMEM; } /* OSS sequencer adds running status to all sequences */ snd_midi_event_no_status(mdev->coder, 1); /* * look for en empty slot */ spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { if (midi_devs[i] == NULL) break; } if (i >= max_midi_devs) { if (max_midi_devs >= SNDRV_SEQ_OSS_MAX_MIDI_DEVS) { spin_unlock_irqrestore(®ister_lock, flags); snd_midi_event_free(mdev->coder); kfree(mdev); return -ENOMEM; } max_midi_devs++; } mdev->seq_device = i; midi_devs[mdev->seq_device] = mdev; spin_unlock_irqrestore(®ister_lock, flags); return 0; } /* * release the midi device if it was registered */ int snd_seq_oss_midi_check_exit_port(int client, int port) { struct seq_oss_midi *mdev; unsigned long flags; int index; mdev = find_slot(client, port); if (mdev) { spin_lock_irqsave(®ister_lock, flags); midi_devs[mdev->seq_device] = NULL; spin_unlock_irqrestore(®ister_lock, flags); snd_use_lock_free(&mdev->use_lock); snd_use_lock_sync(&mdev->use_lock); snd_midi_event_free(mdev->coder); kfree(mdev); } spin_lock_irqsave(®ister_lock, flags); for (index = max_midi_devs - 1; index >= 0; index--) { if (midi_devs[index]) break; } max_midi_devs = index + 1; spin_unlock_irqrestore(®ister_lock, flags); return 0; } /* * release the midi device if it was registered */ void snd_seq_oss_midi_clear_all(void) { int i; struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev) { snd_midi_event_free(mdev->coder); kfree(mdev); midi_devs[i] = NULL; } } max_midi_devs = 0; spin_unlock_irqrestore(®ister_lock, flags); } /* * set up midi tables */ void snd_seq_oss_midi_setup(struct seq_oss_devinfo *dp) { spin_lock_irq(®ister_lock); dp->max_mididev = max_midi_devs; spin_unlock_irq(®ister_lock); } /* * clean up midi tables */ void snd_seq_oss_midi_cleanup(struct seq_oss_devinfo *dp) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_close(dp, i); dp->max_mididev = 0; } /* * open all midi devices. ignore errors. */ void snd_seq_oss_midi_open_all(struct seq_oss_devinfo *dp, int file_mode) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_open(dp, i, file_mode); } /* * get the midi device information */ static struct seq_oss_midi * get_mididev(struct seq_oss_devinfo *dp, int dev) { if (dev < 0 || dev >= dp->max_mididev) return NULL; dev = array_index_nospec(dev, dp->max_mididev); return get_mdev(dev); } /* * open the midi device if not opened yet */ int snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) { int perm; struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; int err; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; mutex_lock(&mdev->open_mutex); /* already used? */ if (mdev->opened && mdev->devinfo != dp) { err = -EBUSY; goto unlock; } perm = 0; if (is_write_mode(fmode)) perm |= PERM_WRITE; if (is_read_mode(fmode)) perm |= PERM_READ; perm &= mdev->flags; if (perm == 0) { err = -ENXIO; goto unlock; } /* already opened? */ if ((mdev->opened & perm) == perm) { err = 0; goto unlock; } perm &= ~mdev->opened; memset(&subs, 0, sizeof(subs)); if (perm & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_WRITE; } if (perm & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; subs.flags = SNDRV_SEQ_PORT_SUBS_TIMESTAMP; subs.queue = dp->queue; /* queue for timestamps */ if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_READ; } if (! mdev->opened) { err = -ENXIO; goto unlock; } mdev->devinfo = dp; err = 0; unlock: mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return err; } /* * close the midi device if already opened */ int snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; mutex_lock(&mdev->open_mutex); if (!mdev->opened || mdev->devinfo != dp) goto unlock; memset(&subs, 0, sizeof(subs)); if (mdev->opened & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } if (mdev->opened & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } mdev->opened = 0; mdev->devinfo = NULL; unlock: mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return 0; } /* * change seq capability flags to file mode flags */ int snd_seq_oss_midi_filemode(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; int mode; mdev = get_mididev(dp, dev); if (!mdev) return 0; mode = 0; if (mdev->opened & PERM_WRITE) mode |= SNDRV_SEQ_OSS_FILE_WRITE; if (mdev->opened & PERM_READ) mode |= SNDRV_SEQ_OSS_FILE_READ; snd_use_lock_free(&mdev->use_lock); return mode; } /* * reset the midi device and close it: * so far, only close the device. */ void snd_seq_oss_midi_reset(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return; if (! mdev->opened) { snd_use_lock_free(&mdev->use_lock); return; } if (mdev->opened & PERM_WRITE) { struct snd_seq_event ev; int c; memset(&ev, 0, sizeof(ev)); ev.dest.client = mdev->client; ev.dest.port = mdev->port; ev.queue = dp->queue; ev.source.port = dp->port; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) { ev.type = SNDRV_SEQ_EVENT_SENSING; snd_seq_oss_dispatch(dp, &ev, 0, 0); } for (c = 0; c < 16; c++) { ev.type = SNDRV_SEQ_EVENT_CONTROLLER; ev.data.control.channel = c; ev.data.control.param = MIDI_CTL_ALL_NOTES_OFF; snd_seq_oss_dispatch(dp, &ev, 0, 0); if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; snd_seq_oss_dispatch(dp, &ev, 0, 0); ev.type = SNDRV_SEQ_EVENT_PITCHBEND; ev.data.control.value = 0; snd_seq_oss_dispatch(dp, &ev, 0, 0); } } } // snd_seq_oss_midi_close(dp, dev); snd_use_lock_free(&mdev->use_lock); } /* * get client/port of the specified MIDI device */ void snd_seq_oss_midi_get_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_addr *addr) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return; addr->client = mdev->client; addr->port = mdev->port; snd_use_lock_free(&mdev->use_lock); } /* * input callback - this can be atomic */ int snd_seq_oss_midi_input(struct snd_seq_event *ev, int direct, void *private_data) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private_data; struct seq_oss_midi *mdev; int rc; if (dp->readq == NULL) return 0; mdev = find_slot(ev->source.client, ev->source.port); if (!mdev) return 0; if (! (mdev->opened & PERM_READ)) { snd_use_lock_free(&mdev->use_lock); return 0; } if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) rc = send_synth_event(dp, ev, mdev->seq_device); else rc = send_midi_event(dp, ev, mdev); snd_use_lock_free(&mdev->use_lock); return rc; } /* * convert ALSA sequencer event to OSS synth event */ static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev) { union evrec ossev; memset(&ossev, 0, sizeof(ossev)); switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: ossev.v.cmd = MIDI_NOTEON; break; case SNDRV_SEQ_EVENT_NOTEOFF: ossev.v.cmd = MIDI_NOTEOFF; break; case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.cmd = MIDI_KEY_PRESSURE; break; case SNDRV_SEQ_EVENT_CONTROLLER: ossev.l.cmd = MIDI_CTL_CHANGE; break; case SNDRV_SEQ_EVENT_PGMCHANGE: ossev.l.cmd = MIDI_PGM_CHANGE; break; case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.cmd = MIDI_CHN_PRESSURE; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.cmd = MIDI_PITCH_BEND; break; default: return 0; /* not supported */ } ossev.v.dev = dev; switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: case SNDRV_SEQ_EVENT_NOTEOFF: case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.code = EV_CHN_VOICE; ossev.v.note = ev->data.note.note; ossev.v.parm = ev->data.note.velocity; ossev.v.chn = ev->data.note.channel; break; case SNDRV_SEQ_EVENT_CONTROLLER: case SNDRV_SEQ_EVENT_PGMCHANGE: case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.code = EV_CHN_COMMON; ossev.l.p1 = ev->data.control.param; ossev.l.val = ev->data.control.value; ossev.l.chn = ev->data.control.channel; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.code = EV_CHN_COMMON; ossev.l.val = ev->data.control.value + 8192; ossev.l.chn = ev->data.control.channel; break; } snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); snd_seq_oss_readq_put_event(dp->readq, &ossev); return 0; } /* * decode event and send MIDI bytes to read queue */ static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev) { char msg[32]; int len; snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); if (!dp->timer->running) len = snd_seq_oss_timer_start(dp->timer); if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { snd_seq_oss_readq_sysex(dp->readq, mdev->seq_device, ev); snd_midi_event_reset_decode(mdev->coder); } else { len = snd_midi_event_decode(mdev->coder, msg, sizeof(msg), ev); if (len > 0) snd_seq_oss_readq_puts(dp->readq, mdev->seq_device, msg, len); } return 0; } /* * dump midi data * return 0 : enqueued * non-zero : invalid - ignored */ int snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, struct snd_seq_event *ev) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; if (snd_midi_event_encode_byte(mdev->coder, c, ev)) { snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port); snd_use_lock_free(&mdev->use_lock); return 0; } snd_use_lock_free(&mdev->use_lock); return -EINVAL; } /* * create OSS compatible midi_info record */ int snd_seq_oss_midi_make_info(struct seq_oss_devinfo *dp, int dev, struct midi_info *inf) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return -ENXIO; inf->device = dev; inf->dev_type = 0; /* FIXME: ?? */ inf->capabilities = 0; /* FIXME: ?? */ strscpy(inf->name, mdev->name, sizeof(inf->name)); snd_use_lock_free(&mdev->use_lock); return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ static char * capmode_str(int val) { val &= PERM_READ|PERM_WRITE; if (val == (PERM_READ|PERM_WRITE)) return "read/write"; else if (val == PERM_READ) return "read"; else if (val == PERM_WRITE) return "write"; else return "none"; } void snd_seq_oss_midi_info_read(struct snd_info_buffer *buf) { int i; struct seq_oss_midi *mdev; snd_iprintf(buf, "\nNumber of MIDI devices: %d\n", max_midi_devs); for (i = 0; i < max_midi_devs; i++) { snd_iprintf(buf, "\nmidi %d: ", i); mdev = get_mdev(i); if (mdev == NULL) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "[%s] ALSA port %d:%d\n", mdev->name, mdev->client, mdev->port); snd_iprintf(buf, " capability %s / opened %s\n", capmode_str(mdev->flags), capmode_str(mdev->opened)); snd_use_lock_free(&mdev->use_lock); } } #endif /* CONFIG_SND_PROC_FS */ |
| 34 34 34 632 633 632 632 632 616 14 4 4 4 4 4 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsverity.h> #include <keys/system_keyring.h> #include <uapi/linux/fsverity.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM static char *ima_appraise_cmdline_default __initdata; core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0); void __init ima_appraise_parse_cmdline(void) { const char *str = ima_appraise_cmdline_default; bool sb_state = arch_ima_get_secureboot(); int appraisal_state = ima_appraise; if (!str) return; if (strncmp(str, "off", 3) == 0) appraisal_state = 0; else if (strncmp(str, "log", 3) == 0) appraisal_state = IMA_APPRAISE_LOG; else if (strncmp(str, "fix", 3) == 0) appraisal_state = IMA_APPRAISE_FIX; else if (strncmp(str, "enforce", 7) == 0) appraisal_state = IMA_APPRAISE_ENFORCE; else pr_err("invalid \"%s\" appraise option", str); /* If appraisal state was changed, but secure boot is enabled, * keep its default */ if (sb_state) { if (!(appraisal_state & IMA_APPRAISE_ENFORCE)) pr_info("Secure boot enabled: ignoring ima_appraise=%s option", str); } else { ima_appraise = appraisal_state; } } #endif /* * is_ima_appraise_enabled - return appraise status * * Only return enabled, if not in ima_appraise="fix" or "log" modes. */ bool is_ima_appraise_enabled(void) { return ima_appraise & IMA_APPRAISE_ENFORCE; } /* * ima_must_appraise - set appraise flag * * Return 1 to appraise or hash */ int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { struct lsm_prop prop; if (!ima_appraise) return 0; security_current_getlsmprop_subj(&prop); return ima_match_policy(idmap, inode, current_cred(), &prop, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint) { int rc, offset; u8 algo = iint->ima_hash->algo; if (algo <= HASH_ALGO_SHA1) { offset = 1; iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST; } else { offset = 0; iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); return rc; } /* Return specific func appraised cached result */ enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return iint->ima_mmap_status; case BPRM_CHECK: return iint->ima_bprm_status; case CREDS_CHECK: return iint->ima_creds_status; case FILE_CHECK: case POST_SETATTR: return iint->ima_file_status; case MODULE_CHECK ... MAX_CHECK - 1: default: return iint->ima_read_status; } } static void ima_set_cache_status(struct ima_iint_cache *iint, enum ima_hooks func, enum integrity_status status) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->ima_mmap_status = status; break; case BPRM_CHECK: iint->ima_bprm_status = status; break; case CREDS_CHECK: iint->ima_creds_status = status; break; case FILE_CHECK: case POST_SETATTR: iint->ima_file_status = status; break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->ima_read_status = status; break; } } static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED); break; case BPRM_CHECK: iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED); break; case CREDS_CHECK: iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED); break; case FILE_CHECK: case POST_SETATTR: iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED); break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED); break; } } enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, int xattr_len) { struct signature_v2_hdr *sig; enum hash_algo ret; if (!xattr_value || xattr_len < 2) /* return default hash algo */ return ima_hash_algo; switch (xattr_value->type) { case IMA_VERITY_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 3 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; if (ret < HASH_ALGO__LAST) return ret; break; case IMA_XATTR_DIGEST: /* this is for backward compatibility */ if (xattr_len == 21) { unsigned int zero = 0; if (!memcmp(&xattr_value->data[16], &zero, 4)) return HASH_ALGO_MD5; else return HASH_ALGO_SHA1; } else if (xattr_len == 17) return HASH_ALGO_MD5; break; } /* return default hash algo */ return ima_hash_algo; } int ima_read_xattr(struct dentry *dentry, struct evm_ima_xattr_data **xattr_value, int xattr_len) { int ret; ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; } /* * calc_file_id_hash - calculate the hash of the ima_file_id struct data * @type: xattr type [enum evm_ima_xattr_type] * @algo: hash algorithm [enum hash_algo] * @digest: pointer to the digest to be hashed * @hash: (out) pointer to the hash * * IMA signature version 3 disambiguates the data that is signed by * indirectly signing the hash of the ima_file_id structure data. * * Signing the ima_file_id struct is currently only supported for * IMA_VERITY_DIGSIG type xattrs. * * Return 0 on success, error code otherwise. */ static int calc_file_id_hash(enum evm_ima_xattr_type type, enum hash_algo algo, const u8 *digest, struct ima_digest_data *hash) { struct ima_file_id file_id = { .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; if (type != IMA_VERITY_DIGSIG) return -EINVAL; memcpy(file_id.hash, digest, hash_digest_size[algo]); hash->algo = algo; hash->length = hash_digest_size[algo]; return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); } /* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { struct ima_max_digest_data hash; struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; fallthrough; case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) *cause = "verity-signature-required"; else *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } clear_bit(IMA_DIGSIG, &iint->atomic_flags); } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } if (xattr_len - sizeof(xattr_value->type) - hash_start >= iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 */ rc = memcmp(&xattr_value->data[hash_start], iint->ima_hash->digest, iint->ima_hash->length); else rc = -EINVAL; if (rc) { *cause = "invalid-hash"; *status = INTEGRITY_FAIL; break; } *status = INTEGRITY_PASS; break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; if ((iint->flags & mask) == mask) { *cause = "verity-signature-required"; *status = INTEGRITY_FAIL; break; } sig = (typeof(sig))xattr_value; if (sig->version >= 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { *status = INTEGRITY_UNKNOWN; break; } if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; case IMA_VERITY_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); if (iint->flags & IMA_DIGSIG_REQUIRED) { if (!(iint->flags & IMA_VERITY_REQUIRED)) { *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } } sig = (typeof(sig))xattr_value; if (sig->version != 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, iint->ima_hash->digest, container_of(&hash.hdr, struct ima_digest_data, hdr)); if (rc) { *cause = "sigv3-hashing-error"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, hash.digest, hash.hdr.length); if (rc) { *cause = "invalid-verity-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; break; } return rc; } /* * modsig_verify - verify modsig signature * * Verify whether the signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int modsig_verify(enum ima_hooks func, const struct modsig *modsig, enum integrity_status *status, const char **cause) { int rc; rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig); if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM, modsig); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } return rc; } /* * ima_check_blacklist - determine if the binary is blacklisted. * * Add the hash of the blacklisted binary to the measurement list, based * on policy. * * Returns -EPERM if the hash is blacklisted. */ int ima_check_blacklist(struct ima_iint_cache *iint, const struct modsig *modsig, int pcr) { enum hash_algo hash_algo; const u8 *digest = NULL; u32 digestsize = 0; int rc = 0; if (!(iint->flags & IMA_CHECK_BLACKLIST)) return 0; if (iint->flags & IMA_MODSIG_ALLOWED && modsig) { ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize); rc = is_binary_blacklisted(digest, digestsize); } else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash) rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); return rc; } static bool is_bprm_creds_for_exec(enum ima_hooks func, struct file *file) { struct linux_binprm *bprm; if (func == BPRM_CHECK) { bprm = container_of(&file, struct linux_binprm, file); return bprm->is_check; } return false; } /* * ima_appraise_measurement - appraise file measurement * * Call evm_verifyxattr() to verify the integrity of 'security.ima'. * Assuming success, compare the xattr hash with the collected measurement. * * Return 0 on success, error code otherwise */ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig) { static const char op[] = "appraise_data"; int audit_msgno = AUDIT_INTEGRITY_DATA; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len; bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig; /* If not appraising a modsig, we need an xattr. */ if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; /* * Unlike any of the other LSM hooks where the kernel enforces file * integrity, enforcing file integrity for the bprm_creds_for_exec() * LSM hook with the AT_EXECVE_CHECK flag is left up to the discretion * of the script interpreter(userspace). Differentiate kernel and * userspace enforced integrity audit messages. */ if (is_bprm_creds_for_exec(func, file)) audit_msgno = AUDIT_INTEGRITY_USERSPACE; /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) goto out; if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) cause = "verity-signature-required"; else cause = "IMA-signature-required"; } else { cause = "missing-hash"; } status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || (inode->i_size == 0))) status = INTEGRITY_PASS; goto out; } status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc < 0 ? 0 : rc); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: case INTEGRITY_UNKNOWN: break; case INTEGRITY_NOXATTRS: /* No EVM protected xattrs. */ /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; case INTEGRITY_FAIL_IMMUTABLE: set_bit(IMA_DIGSIG, &iint->atomic_flags); cause = "invalid-fail-immutable"; goto out; case INTEGRITY_FAIL: /* Invalid HMAC/signature. */ cause = "invalid-HMAC"; goto out; default: WARN_ONCE(true, "Unexpected integrity status %d\n", status); } if (xattr_value) rc = xattr_verify(func, iint, xattr_value, xattr_len, &status, &cause); /* * If we have a modsig and either no imasig or the imasig's key isn't * known, then try verifying the modsig. */ if (try_modsig && (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG || rc == -ENOKEY)) rc = modsig_verify(func, modsig, &status, &cause); out: /* * File signatures on some filesystems can not be properly verified. * When such filesystems are mounted by an untrusted mounter or on a * system not willing to accept such a risk, fail the file signature * verification. */ if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) || (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig && (!xattr_value || xattr_value->type != EVM_IMA_XATTR_DIGSIG)) { if (!ima_fix_xattr(dentry, iint)) status = INTEGRITY_PASS; } /* * Permit new files with file/EVM portable signatures, but * without data. */ if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE && test_bit(IMA_DIGSIG, &iint->atomic_flags)) { status = INTEGRITY_PASS; } integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); } ima_set_cache_status(iint, func, status); return status; } /* * ima_update_xattr - update 'security.ima' hash value */ void ima_update_xattr(struct ima_iint_cache *iint, struct file *file) { struct dentry *dentry = file_dentry(file); int rc = 0; /* do not collect and update hash for digital signatures */ if (test_bit(IMA_DIGSIG, &iint->atomic_flags)) return; if ((iint->ima_file_status != INTEGRITY_PASS) && !(iint->flags & IMA_HASH)) return; rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) return; inode_lock(file_inode(file)); ima_fix_xattr(dentry, iint); inode_unlock(file_inode(file)); } /** * ima_inode_post_setattr - reflect file metadata changes * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * Changes to a dentry's metadata might result in needing to appraise. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { struct inode *inode = d_backing_inode(dentry); struct ima_iint_cache *iint; int action; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode) || !(inode->i_opflags & IOP_XATTR)) return; action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = ima_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); if (!action) clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } } /* * ima_protect_xattr - protect 'security.ima' * * Ensure that not just anyone can modify or remove 'security.ima'. */ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 1; } return 0; } static void ima_reset_appraise_flags(struct inode *inode, int digsig) { struct ima_iint_cache *iint; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; iint->measured_pcrs = 0; set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags); if (digsig) set_bit(IMA_DIGSIG, &iint->atomic_flags); else clear_bit(IMA_DIGSIG, &iint->atomic_flags); } /** * validate_hash_algo() - Block setxattr with unsupported hash algorithms * @dentry: object of the setxattr() * @xattr_value: userland supplied xattr value * @xattr_value_len: length of xattr_value * * The xattr value is mapped to its hash algorithm, and this algorithm * must be built in the kernel for the setxattr to be allowed. * * Emit an audit message when the algorithm is invalid. * * Return: 0 on success, else an error. */ static int validate_hash_algo(struct dentry *dentry, const struct evm_ima_xattr_data *xattr_value, size_t xattr_value_len) { char *path = NULL, *pathbuf = NULL; enum hash_algo xattr_hash_algo; const char *errmsg = "unavailable-hash-algorithm"; unsigned int allowed_hashes; xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len); allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms); if (allowed_hashes) { /* success if the algorithm is allowed in the ima policy */ if (allowed_hashes & (1U << xattr_hash_algo)) return 0; /* * We use a different audit message when the hash algorithm * is denied by a policy rule, instead of not being built * in the kernel image */ errmsg = "denied-hash-algorithm"; } else { if (likely(xattr_hash_algo == ima_hash_algo)) return 0; /* allow any xattr using an algorithm built in the kernel */ if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0)) return 0; } pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); kfree(pathbuf); return -EACCES; } static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; int err; result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; err = validate_hash_algo(dentry, xvalue, xattr_value_len); if (err) return err; digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) ima_reset_appraise_flags(d_backing_inode(dentry), 0); return 0; } static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { int result; result = ima_protect_xattr(dentry, xattr_name, NULL, 0); if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), 0); if (result == 1) result = 0; } return result; } static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } static struct security_hook_list ima_appraise_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr), LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr), LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl), LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr), LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl), }; void __init init_ima_appraise_lsm(const struct lsm_id *lsmid) { security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks), lsmid); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Handshake request lifetime events * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2023, Oracle and/or its affiliates. */ #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <kunit/visibility.h> #include <uapi/linux/handshake.h> #include "handshake.h" #include <trace/events/handshake.h> /* * We need both a handshake_req -> sock mapping, and a sock -> * handshake_req mapping. Both are one-to-one. * * To avoid adding another pointer field to struct sock, net/handshake * maintains a hash table, indexed by the memory address of @sock, to * find the struct handshake_req outstanding for that socket. The * reverse direction uses a simple pointer field in the handshake_req * struct. */ static struct rhashtable handshake_rhashtbl ____cacheline_aligned_in_smp; static const struct rhashtable_params handshake_rhash_params = { .key_len = sizeof_field(struct handshake_req, hr_sk), .key_offset = offsetof(struct handshake_req, hr_sk), .head_offset = offsetof(struct handshake_req, hr_rhash), .automatic_shrinking = true, }; int handshake_req_hash_init(void) { return rhashtable_init(&handshake_rhashtbl, &handshake_rhash_params); } void handshake_req_hash_destroy(void) { rhashtable_destroy(&handshake_rhashtbl); } struct handshake_req *handshake_req_hash_lookup(struct sock *sk) { return rhashtable_lookup_fast(&handshake_rhashtbl, &sk, handshake_rhash_params); } EXPORT_SYMBOL_IF_KUNIT(handshake_req_hash_lookup); static bool handshake_req_hash_add(struct handshake_req *req) { int ret; ret = rhashtable_lookup_insert_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); return ret == 0; } static void handshake_req_destroy(struct handshake_req *req) { if (req->hr_proto->hp_destroy) req->hr_proto->hp_destroy(req); rhashtable_remove_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); kfree(req); } static void handshake_sk_destruct(struct sock *sk) { void (*sk_destruct)(struct sock *sk); struct handshake_req *req; req = handshake_req_hash_lookup(sk); if (!req) return; trace_handshake_destruct(sock_net(sk), req, sk); sk_destruct = req->hr_odestruct; handshake_req_destroy(req); if (sk_destruct) sk_destruct(sk); } /** * handshake_req_alloc - Allocate a handshake request * @proto: security protocol * @flags: memory allocation flags * * Returns an initialized handshake_req or NULL. */ struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto, gfp_t flags) { struct handshake_req *req; if (!proto) return NULL; if (proto->hp_handler_class <= HANDSHAKE_HANDLER_CLASS_NONE) return NULL; if (proto->hp_handler_class >= HANDSHAKE_HANDLER_CLASS_MAX) return NULL; if (!proto->hp_accept || !proto->hp_done) return NULL; req = kzalloc(struct_size(req, hr_priv, proto->hp_privsize), flags); if (!req) return NULL; INIT_LIST_HEAD(&req->hr_list); req->hr_proto = proto; return req; } EXPORT_SYMBOL(handshake_req_alloc); /** * handshake_req_private - Get per-handshake private data * @req: handshake arguments * */ void *handshake_req_private(struct handshake_req *req) { return (void *)&req->hr_priv; } EXPORT_SYMBOL(handshake_req_private); static bool __add_pending_locked(struct handshake_net *hn, struct handshake_req *req) { if (WARN_ON_ONCE(!list_empty(&req->hr_list))) return false; hn->hn_pending++; list_add_tail(&req->hr_list, &hn->hn_requests); return true; } static void __remove_pending_locked(struct handshake_net *hn, struct handshake_req *req) { hn->hn_pending--; list_del_init(&req->hr_list); } /* * Returns %true if the request was found on @net's pending list, * otherwise %false. * * If @req was on a pending list, it has not yet been accepted. */ static bool remove_pending(struct handshake_net *hn, struct handshake_req *req) { bool ret = false; spin_lock(&hn->hn_lock); if (!list_empty(&req->hr_list)) { __remove_pending_locked(hn, req); ret = true; } spin_unlock(&hn->hn_lock); return ret; } struct handshake_req *handshake_req_next(struct handshake_net *hn, int class) { struct handshake_req *req, *pos; req = NULL; spin_lock(&hn->hn_lock); list_for_each_entry(pos, &hn->hn_requests, hr_list) { if (pos->hr_proto->hp_handler_class != class) continue; __remove_pending_locked(hn, pos); req = pos; break; } spin_unlock(&hn->hn_lock); return req; } EXPORT_SYMBOL_IF_KUNIT(handshake_req_next); /** * handshake_req_submit - Submit a handshake request * @sock: open socket on which to perform the handshake * @req: handshake arguments * @flags: memory allocation flags * * Return values: * %0: Request queued * %-EINVAL: Invalid argument * %-EBUSY: A handshake is already under way for this socket * %-ESRCH: No handshake agent is available * %-EAGAIN: Too many pending handshake requests * %-ENOMEM: Failed to allocate memory * %-EMSGSIZE: Failed to construct notification message * %-EOPNOTSUPP: Handshake module not initialized * * A zero return value from handshake_req_submit() means that * exactly one subsequent completion callback is guaranteed. * * A negative return value from handshake_req_submit() means that * no completion callback will be done and that @req has been * destroyed. */ int handshake_req_submit(struct socket *sock, struct handshake_req *req, gfp_t flags) { struct handshake_net *hn; struct net *net; int ret; if (!sock || !req || !sock->file) { kfree(req); return -EINVAL; } req->hr_sk = sock->sk; if (!req->hr_sk) { kfree(req); return -EINVAL; } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); hn = handshake_pernet(net); if (!hn) goto out_err; ret = -EAGAIN; if (READ_ONCE(hn->hn_pending) >= hn->hn_pending_max) goto out_err; spin_lock(&hn->hn_lock); ret = -EOPNOTSUPP; if (test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags)) goto out_unlock; ret = -EBUSY; if (!handshake_req_hash_add(req)) goto out_unlock; if (!__add_pending_locked(hn, req)) goto out_unlock; spin_unlock(&hn->hn_lock); ret = handshake_genl_notify(net, req->hr_proto, flags); if (ret) { trace_handshake_notify_err(net, req, req->hr_sk, ret); if (remove_pending(hn, req)) goto out_err; } /* Prevent socket release while a handshake request is pending */ sock_hold(req->hr_sk); trace_handshake_submit(net, req, req->hr_sk); return 0; out_unlock: spin_unlock(&hn->hn_lock); out_err: trace_handshake_submit_err(net, req, req->hr_sk, ret); handshake_req_destroy(req); return ret; } EXPORT_SYMBOL(handshake_req_submit); void handshake_complete(struct handshake_req *req, unsigned int status, struct genl_info *info) { struct sock *sk = req->hr_sk; struct net *net = sock_net(sk); if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { trace_handshake_complete(net, req, sk, status); req->hr_proto->hp_done(req, status, info); /* Handshake request is no longer pending */ sock_put(sk); } } EXPORT_SYMBOL_IF_KUNIT(handshake_complete); /** * handshake_req_cancel - Cancel an in-progress handshake * @sk: socket on which there is an ongoing handshake * * Request cancellation races with request completion. To determine * who won, callers examine the return value from this function. * * Return values: * %true - Uncompleted handshake request was canceled * %false - Handshake request already completed or not found */ bool handshake_req_cancel(struct sock *sk) { struct handshake_req *req; struct handshake_net *hn; struct net *net; net = sock_net(sk); req = handshake_req_hash_lookup(sk); if (!req) { trace_handshake_cancel_none(net, req, sk); return false; } hn = handshake_pernet(net); if (hn && remove_pending(hn, req)) { /* Request hadn't been accepted */ goto out_true; } if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { /* Request already completed */ trace_handshake_cancel_busy(net, req, sk); return false; } out_true: trace_handshake_cancel(net, req, sk); /* Handshake request is no longer pending */ sock_put(sk); return true; } EXPORT_SYMBOL(handshake_req_cancel); |
| 197 197 197 197 197 197 197 849 849 849 849 849 849 28 28 28 28 28 28 28 28 28 28 4 15 4 4 4 4 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 | // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/bug.h> #include <net/page_pool/helpers.h> #include <net/hotdata.h> #include <net/netdev_lock.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #include <net/xdp_sock_drv.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_free(&mem_id_pool, xa->mem.id); kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; int type = mem->type; int id = mem->id; /* Reset mem info to defaults */ mem->id = 0; mem->type = 0; if (id == 0) return; if (type == MEM_TYPE_PAGE_POOL) { xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } xdp_unreg_mem_model(&xdp_rxq->mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (!__is_supported_mem_type(type)) return ERR_PTR(-EOPNOTSUPP); mem->type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ return NULL; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) return ERR_PTR(ret); } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return ERR_PTR(-ENOMEM); mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } mem->id = id; xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_free(&mem_id_pool, mem->id); mem->id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem); mutex_unlock(&mem_id_lock); return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return ERR_PTR(errno); } int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); return 0; } EXPORT_SYMBOL_GPL(xdp_reg_mem_model); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); if (type == MEM_TYPE_XSK_BUFF_POOL && allocator) xsk_pool_set_rxq_info(allocator, xdp_rxq); if (trace_mem_connect_enabled() && xdp_alloc) trace_mem_connect(xdp_alloc, xdp_rxq); return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /** * xdp_reg_page_pool - register &page_pool as a memory provider for XDP * @pool: &page_pool to register * * Can be used to register pools manually without connecting to any XDP RxQ * info, so that the XDP layer will be aware of them. Then, they can be * attached to an RxQ info manually via xdp_rxq_info_attach_page_pool(). * * Return: %0 on success, -errno on error. */ int xdp_reg_page_pool(struct page_pool *pool) { struct xdp_mem_info mem; return xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pool); } EXPORT_SYMBOL_GPL(xdp_reg_page_pool); /** * xdp_unreg_page_pool - unregister &page_pool from the memory providers list * @pool: &page_pool to unregister * * A shorthand for manual unregistering page pools. If the pool was previously * attached to an RxQ info, it must be detached first. */ void xdp_unreg_page_pool(const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_unreg_mem_model(&mem); } EXPORT_SYMBOL_GPL(xdp_unreg_page_pool); /** * xdp_rxq_info_attach_page_pool - attach registered pool to RxQ info * @xdp_rxq: XDP RxQ info to attach the pool to * @pool: pool to attach * * If the pool was registered manually, this function must be called instead * of xdp_rxq_info_reg_mem_model() to connect it to the RxQ info. */ void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_rxq_info_attach_mem_model(xdp_rxq, &mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_attach_page_pool); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, bool napi_direct, struct xdp_buff *xdp) { switch (mem_type) { case MEM_TYPE_PAGE_POOL: netmem = netmem_compound_head(netmem); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; /* No need to check netmem_is_pp() as mem->type knows this a * page_pool page */ page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, napi_direct); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(__netmem_address(netmem)); break; case MEM_TYPE_PAGE_ORDER0: put_page(__netmem_to_page(netmem)); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ xsk_buff_free(xdp); break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem_type); break; } } void xdp_return_frame(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, false, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, true, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); /* XDP bulk APIs introduce a defer/flush mechanism to return * pages belonging to the same xdp_mem_allocator object * (identified via the mem.id field) in bulk to optimize * I-cache and D-cache. * The bulk queue size is set to 16 to be aligned to how * XDP_REDIRECT bulking works. The bulk is flushed when * it is full or when mem.id changes. * xdp_frame_bulk is usually stored/allocated on the function * call-stack to avoid locking penalties. */ /* Must be called with rcu_read_lock held */ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq) { if (xdpf->mem_type != MEM_TYPE_PAGE_POOL) { xdp_return_frame(xdpf); return; } if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); if (unlikely(xdp_frame_has_frags(xdpf))) { struct skb_shared_info *sinfo; int i; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; bq->q[bq->count++] = skb_frag_netmem(frag); if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); } } bq->q[bq->count++] = virt_to_netmem(xdpf->data); } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); /** * xdp_return_frag -- free one XDP frag or decrement its refcount * @netmem: network memory reference to release * @xdp: &xdp_buff to release the frag for */ void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp) { __xdp_return(netmem, xdp->rxq->mem.type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frag); void xdp_return_buff(struct xdp_buff *xdp) { struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdp->rxq->mem.type, true, xdp); out: __xdp_return(virt_to_netmem(xdp->data), xdp->rxq->mem.type, true, xdp); } EXPORT_SYMBOL_GPL(xdp_return_buff); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); /* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */ void xdp_warn(const char *msg, const char *func, const int line) { WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); /** * xdp_build_skb_from_buff - create an skb from &xdp_buff * @xdp: &xdp_buff to convert to an skb * * Perform common operations to create a new skb to pass up the stack from * &xdp_buff: allocate an skb head from the NAPI percpu cache, initialize * skb data pointers and offsets, set the recycle bit if the buff is * PP-backed, Rx queue index, protocol and update frags info. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp) { const struct xdp_rxq_info *rxq = xdp->rxq; const struct skb_shared_info *sinfo; struct sk_buff *skb; u32 nr_frags = 0; int metalen; if (unlikely(xdp_buff_has_frags(xdp))) { sinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = sinfo->nr_frags; } skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); metalen = xdp->data - xdp->data_meta; if (metalen > 0) skb_metadata_set(skb, metalen); if (rxq->mem.type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(nr_frags)) { u32 tsize; tsize = sinfo->xdp_frags_truesize ? : nr_frags * xdp->frame_sz; xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, tsize, xdp_buff_is_frag_pfmemalloc(xdp)); } skb->protocol = eth_type_trans(skb, rxq->dev); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_buff); /** * xdp_copy_frags_from_zc - copy frags from XSk buff to skb * @skb: skb to copy frags to * @xdp: XSk &xdp_buff from which the frags will be copied * @pp: &page_pool backing page allocation, if available * * Copy all frags from XSk &xdp_buff to the skb to pass it up the stack. * Allocate a new buffer for each frag, copy it and attach to the skb. * * Return: true on success, false on netmem allocation fail. */ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb, const struct xdp_buff *xdp, struct page_pool *pp) { struct skb_shared_info *sinfo = skb_shinfo(skb); const struct skb_shared_info *xinfo; u32 nr_frags, tsize = 0; bool pfmemalloc = false; xinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = xinfo->nr_frags; for (u32 i = 0; i < nr_frags; i++) { const skb_frag_t *frag = &xinfo->frags[i]; u32 len = skb_frag_size(frag); u32 offset, truesize = len; struct page *page; page = page_pool_dev_alloc(pp, &offset, &truesize); if (unlikely(!page)) { sinfo->nr_frags = i; return false; } memcpy(page_address(page) + offset, skb_frag_address(frag), LARGEST_ALIGN(len)); __skb_fill_page_desc_noacc(sinfo, i, page, offset, len); tsize += truesize; pfmemalloc |= page_is_pfmemalloc(page); } xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size, tsize, pfmemalloc); return true; } /** * xdp_build_skb_from_zc - create an skb from XSk &xdp_buff * @xdp: source XSk buff * * Similar to xdp_build_skb_from_buff(), but for XSk frames. Allocate an skb * head, new buffer for the head, copy the data and initialize the skb fields. * If there are frags, allocate new buffers for them and copy. * Buffers are allocated from the system percpu pools to try recycling them. * If new skb was built successfully, @xdp is returned to XSk pool's freelist. * On error, it remains untouched and the caller must take care of this. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp) { const struct xdp_rxq_info *rxq = xdp->rxq; u32 len = xdp->data_end - xdp->data_meta; u32 truesize = xdp->frame_sz; struct sk_buff *skb = NULL; struct page_pool *pp; int metalen; void *data; if (!IS_ENABLED(CONFIG_PAGE_POOL)) return NULL; local_lock_nested_bh(&system_page_pool.bh_lock); pp = this_cpu_read(system_page_pool.pool); data = page_pool_dev_alloc_va(pp, &truesize); if (unlikely(!data)) goto out; skb = napi_build_skb(data, truesize); if (unlikely(!skb)) { page_pool_free_va(pp, data, true); goto out; } skb_mark_for_recycle(skb); skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); memcpy(__skb_put(skb, len), xdp->data_meta, LARGEST_ALIGN(len)); metalen = xdp->data - xdp->data_meta; if (metalen > 0) { skb_metadata_set(skb, metalen); __skb_pull(skb, metalen); } skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(xdp_buff_has_frags(xdp)) && unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) { napi_consume_skb(skb, true); skb = NULL; goto out; } xsk_buff_free(xdp); skb->protocol = eth_type_trans(skb, rxq->dev); out: local_unlock_nested_bh(&system_page_pool.bh_lock); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; u8 nr_frags; /* xdp frags frame */ if (unlikely(xdp_frame_has_frags(xdpf))) nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; /* Memory size backing xdp_frame data already have reserved * room for build_skb to place skb_shared_info in tailroom. */ frame_size = xdpf->frame_sz; hard_start = xdpf->data - headroom; skb = build_skb_around(skb, hard_start, frame_size); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); if (unlikely(xdp_frame_has_frags(xdpf))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, nr_frags * xdpf->frame_sz, xdp_frame_is_frag_pfmemalloc(xdpf)); /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) * - HW RX hash (skb_set_hash) * - RX ring dev queue index (skb_record_rx_queue) */ if (xdpf->mem_type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ xdp_scrub_frame(xdpf); return skb; } EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) { unsigned int headroom, totalsize; struct xdp_frame *nxdpf; struct page *page; void *addr; headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; if (unlikely(totalsize > PAGE_SIZE)) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); memcpy(addr, xdpf, totalsize); nxdpf = addr; nxdpf->data = addr + headroom; nxdpf->frame_sz = PAGE_SIZE; nxdpf->mem_type = MEM_TYPE_PAGE_ORDER0; return nxdpf; } __bpf_kfunc_start_defs(); /** * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp. * @ctx: XDP context pointer. * @timestamp: Return value pointer. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc * * ``-ENODATA`` : means no RX-timestamp available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. * @rss_type: Return value pointer for RSS type. * * The RSS hash type (@rss_type) specifies what portion of packet headers NIC * hardware used when calculating RSS hash value. The RSS type can be decoded * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag * @ctx: XDP context pointer. * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) * * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** * and should be used as follows: * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` * * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. * Driver is expected to provide those in **host byte order (usually LE)**, * so the bpf program should not perform byte conversion. * According to 802.1Q standard, *VLAN TCI (Tag control information)* * is a bit field that contains: * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, * *Drop eligible indicator (DEI)* - 1 bit, * *Priority code point (PCP)* - 3 bits. * For detailed meaning of DEI and PCP, please refer to other sources. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc * * ``-ENODATA`` : VLAN tag was not stripped or is not available */ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { return -EOPNOTSUPP; } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, .set = &xdp_metadata_kfunc_ids, }; BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted) #define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC u32 bpf_xdp_metadata_kfunc_id(int id) { /* xdp_metadata_kfunc_ids is sorted and can't be used */ return xdp_metadata_kfunc_ids_unsorted[id]; } bool bpf_dev_bound_kfunc_id(u32 btf_id) { return btf_id_set8_contains(&xdp_metadata_kfunc_ids, btf_id); } static int __init xdp_metadata_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); void xdp_set_features_flag_locked(struct net_device *dev, xdp_features_t val) { val &= NETDEV_XDP_ACT_MASK; if (dev->xdp_features == val) return; netdev_assert_locked_or_invisible(dev); dev->xdp_features = val; if (dev->reg_state == NETREG_REGISTERED) call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); } EXPORT_SYMBOL_GPL(xdp_set_features_flag_locked); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { netdev_lock(dev); xdp_set_features_flag_locked(dev, val); netdev_unlock(dev); } EXPORT_SYMBOL_GPL(xdp_set_features_flag); void xdp_features_set_redirect_target_locked(struct net_device *dev, bool support_sg) { xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); if (support_sg) val |= NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag_locked(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target_locked); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { netdev_lock(dev); xdp_features_set_redirect_target_locked(dev, support_sg); netdev_unlock(dev); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target_locked(struct net_device *dev) { xdp_features_t val = dev->xdp_features; val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); xdp_set_features_flag_locked(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target_locked); void xdp_features_clear_redirect_target(struct net_device *dev) { netdev_lock(dev); xdp_features_clear_redirect_target_locked(dev); netdev_unlock(dev); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); |
| 6639 581 6645 283 301 300 6557 272 270 271 269 270 270 271 271 269 269 4 271 269 271 270 232 271 232 232 270 270 270 271 271 270 271 270 1 583 231 232 1 1 1 231 231 232 232 232 229 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 18 2 2 2 2 2 2 2 2 2 2 2 2 12 12 12 12 12 4 3 3 3 3 1 1 3 3 41 40 39 38 39 40 19 19 5856 5851 582 583 583 583 16 583 317 583 583 16 583 582 583 581 583 582 583 301 301 572 576 572 575 574 6476 6476 6466 6468 6464 6476 | 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 | // 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; pr_info_once("blkio.%s is deprecated\n", cftype->name); 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), false); 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; } /* * Similar to blkg_conf_open_bdev, but additionally freezes the queue, * acquires q->elevator_lock, and ensures the correct locking order * between q->elevator_lock and q->rq_qos_mutex. * * This function returns negative error on failure. On success it returns * memflags which must be saved and later passed to blkg_conf_exit_frozen * for restoring the memalloc scope. */ unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx) { int ret; unsigned long memflags; if (ctx->bdev) return -EINVAL; ret = blkg_conf_open_bdev(ctx); if (ret < 0) return ret; /* * At this point, we haven’t started protecting anything related to QoS, * so we release q->rq_qos_mutex here, which was first acquired in blkg_ * conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing * the queue and acquiring q->elevator_lock to maintain the correct * locking order. */ mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue); mutex_lock(&ctx->bdev->bd_queue->elevator_lock); mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex); return memflags; } /** * 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); /* * Similar to blkg_conf_exit, but also unfreezes the queue and releases * q->elevator_lock. Should be used when blkg_conf_open_bdev_frozen * is used to open the bdev. */ void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags) { if (ctx->bdev) { struct request_queue *q = ctx->bdev->bd_queue; blkg_conf_exit(ctx); mutex_unlock(&q->elevator_lock); blk_mq_unfreeze_queue(q, memflags); } } 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, the subsystem 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, css_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); } class_dev_iter_exit(&iter); } 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 css_rstat_flush(&blkcg->css); 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 { struct blkcg *parent; if (!refcount_dec_and_test(&blkcg->online_pin)) break; parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); blkcg = parent; } 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; 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(); return 0; 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; unsigned int memflags; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) memflags = 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, memflags); 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; unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) memflags = 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, memflags); } 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; /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) return -EINVAL; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ 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"); ret = -ENOSPC; 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) { ret = -ENOMEM; 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 == pol->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_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); css_rstat_updated(&blkcg->css, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->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"); |
| 2 2 2 2 2 2 2 1 5 4 1 3 1 2 1 2 2 5 18 18 19 18 19 19 19 19 18 18 18 18 17 2 12 7 7 7 7 1 6 6 2 6 2 4 4 4 4 4 4 3 11 11 11 11 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 | /* * Copyright © 2008 Intel Corporation * Copyright © 2016 Collabora Ltd * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE 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. * * Based on code from the i915 driver. * Original author: Damien Lespiau <damien.lespiau@intel.com> * */ #include <linux/circ_buf.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/poll.h> #include <linux/uaccess.h> #include <drm/drm_crtc.h> #include <drm/drm_debugfs_crc.h> #include <drm/drm_drv.h> #include <drm/drm_print.h> #include "drm_internal.h" /** * DOC: CRC ABI * * DRM device drivers can provide to userspace CRC information of each frame as * it reached a given hardware component (a CRC sampling "source"). * * Userspace can control generation of CRCs in a given CRTC by writing to the * file dri/0/crtc-N/crc/control in debugfs, with N being the :ref:`index of * the CRTC<crtc_index>`. Accepted values are source names (which are * driver-specific) and the "auto" keyword, which will let the driver select a * default source of frame CRCs for this CRTC. * * Once frame CRC generation is enabled, userspace can capture them by reading * the dri/0/crtc-N/crc/data file. Each line in that file contains the frame * number in the first field and then a number of unsigned integer fields * containing the CRC data. Fields are separated by a single space and the number * of CRC fields is source-specific. * * Note that though in some cases the CRC is computed in a specified way and on * the frame contents as supplied by userspace (eDP 1.3), in general the CRC * computation is performed in an unspecified way and on frame contents that have * been already processed in also an unspecified way and thus userspace cannot * rely on being able to generate matching CRC values for the frame contents that * it submits. In this general case, the maximum userspace can do is to compare * the reported CRCs of frames that should have the same contents. * * On the driver side the implementation effort is minimal, drivers only need to * implement &drm_crtc_funcs.set_crc_source and &drm_crtc_funcs.verify_crc_source. * The debugfs files are automatically set up if those vfuncs are set. CRC samples * need to be captured in the driver by calling drm_crtc_add_crc_entry(). * Depending on the driver and HW requirements, &drm_crtc_funcs.set_crc_source * may result in a commit (even a full modeset). * * CRC results must be reliable across non-full-modeset atomic commits, so if a * commit via DRM_IOCTL_MODE_ATOMIC would disable or otherwise interfere with * CRC generation, then the driver must mark that commit as a full modeset * (drm_atomic_crtc_needs_modeset() should return true). As a result, to ensure * consistent results, generic userspace must re-setup CRC generation after a * legacy SETCRTC or an atomic commit with DRM_MODE_ATOMIC_ALLOW_MODESET. */ static int crc_control_show(struct seq_file *m, void *data) { struct drm_crtc *crtc = m->private; if (crtc->funcs->get_crc_sources) { size_t count; const char *const *sources = crtc->funcs->get_crc_sources(crtc, &count); size_t values_cnt; int i; if (count == 0 || !sources) goto out; for (i = 0; i < count; i++) if (!crtc->funcs->verify_crc_source(crtc, sources[i], &values_cnt)) { if (strcmp(sources[i], crtc->crc.source)) seq_printf(m, "%s\n", sources[i]); else seq_printf(m, "%s*\n", sources[i]); } } return 0; out: seq_printf(m, "%s*\n", crtc->crc.source); return 0; } static int crc_control_open(struct inode *inode, struct file *file) { struct drm_crtc *crtc = inode->i_private; return single_open(file, crc_control_show, crtc); } static ssize_t crc_control_write(struct file *file, const char __user *ubuf, size_t len, loff_t *offp) { struct seq_file *m = file->private_data; struct drm_crtc *crtc = m->private; struct drm_crtc_crc *crc = &crtc->crc; char *source; size_t values_cnt; int ret; if (len == 0) return 0; if (len > PAGE_SIZE - 1) { DRM_DEBUG_KMS("Expected < %lu bytes into crtc crc control\n", PAGE_SIZE); return -E2BIG; } source = memdup_user_nul(ubuf, len); if (IS_ERR(source)) return PTR_ERR(source); if (source[len - 1] == '\n') source[len - 1] = '\0'; ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt); if (ret) { kfree(source); return ret; } spin_lock_irq(&crc->lock); if (crc->opened) { spin_unlock_irq(&crc->lock); kfree(source); return -EBUSY; } kfree(crc->source); crc->source = source; spin_unlock_irq(&crc->lock); *offp += len; return len; } static const struct file_operations drm_crtc_crc_control_fops = { .owner = THIS_MODULE, .open = crc_control_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, .write = crc_control_write }; static int crtc_crc_data_count(struct drm_crtc_crc *crc) { assert_spin_locked(&crc->lock); return CIRC_CNT(crc->head, crc->tail, DRM_CRC_ENTRIES_NR); } static void crtc_crc_cleanup(struct drm_crtc_crc *crc) { kfree(crc->entries); crc->overflow = false; crc->entries = NULL; crc->head = 0; crc->tail = 0; crc->values_cnt = 0; crc->opened = false; } static int crtc_crc_open(struct inode *inode, struct file *filep) { struct drm_crtc *crtc = inode->i_private; struct drm_crtc_crc *crc = &crtc->crc; struct drm_crtc_crc_entry *entries = NULL; size_t values_cnt; int ret = 0; if (drm_drv_uses_atomic_modeset(crtc->dev)) { ret = drm_modeset_lock_single_interruptible(&crtc->mutex); if (ret) return ret; if (!crtc->state->active) ret = -EIO; drm_modeset_unlock(&crtc->mutex); if (ret) return ret; } ret = crtc->funcs->verify_crc_source(crtc, crc->source, &values_cnt); if (ret) return ret; if (WARN_ON(values_cnt > DRM_MAX_CRC_NR)) return -EINVAL; if (WARN_ON(values_cnt == 0)) return -EINVAL; entries = kcalloc(DRM_CRC_ENTRIES_NR, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; spin_lock_irq(&crc->lock); if (!crc->opened) { crc->opened = true; crc->entries = entries; crc->values_cnt = values_cnt; } else { ret = -EBUSY; } spin_unlock_irq(&crc->lock); if (ret) { kfree(entries); return ret; } ret = crtc->funcs->set_crc_source(crtc, crc->source); if (ret) goto err; return 0; err: spin_lock_irq(&crc->lock); crtc_crc_cleanup(crc); spin_unlock_irq(&crc->lock); return ret; } static int crtc_crc_release(struct inode *inode, struct file *filep) { struct drm_crtc *crtc = filep->f_inode->i_private; struct drm_crtc_crc *crc = &crtc->crc; /* terminate the infinite while loop if 'drm_dp_aux_crc_work' running */ spin_lock_irq(&crc->lock); crc->opened = false; spin_unlock_irq(&crc->lock); crtc->funcs->set_crc_source(crtc, NULL); spin_lock_irq(&crc->lock); crtc_crc_cleanup(crc); spin_unlock_irq(&crc->lock); return 0; } /* * 1 frame field of 10 chars plus a number of CRC fields of 10 chars each, space * separated, with a newline at the end and null-terminated. */ #define LINE_LEN(values_cnt) (10 + 11 * values_cnt + 1 + 1) #define MAX_LINE_LEN (LINE_LEN(DRM_MAX_CRC_NR)) static ssize_t crtc_crc_read(struct file *filep, char __user *user_buf, size_t count, loff_t *pos) { struct drm_crtc *crtc = filep->f_inode->i_private; struct drm_crtc_crc *crc = &crtc->crc; struct drm_crtc_crc_entry *entry; char buf[MAX_LINE_LEN]; int ret, i; spin_lock_irq(&crc->lock); if (!crc->source) { spin_unlock_irq(&crc->lock); return 0; } /* Nothing to read? */ while (crtc_crc_data_count(crc) == 0) { if (filep->f_flags & O_NONBLOCK) { spin_unlock_irq(&crc->lock); return -EAGAIN; } ret = wait_event_interruptible_lock_irq(crc->wq, crtc_crc_data_count(crc), crc->lock); if (ret) { spin_unlock_irq(&crc->lock); return ret; } } /* We know we have an entry to be read */ entry = &crc->entries[crc->tail]; if (count < LINE_LEN(crc->values_cnt)) { spin_unlock_irq(&crc->lock); return -EINVAL; } BUILD_BUG_ON_NOT_POWER_OF_2(DRM_CRC_ENTRIES_NR); crc->tail = (crc->tail + 1) & (DRM_CRC_ENTRIES_NR - 1); spin_unlock_irq(&crc->lock); if (entry->has_frame_counter) sprintf(buf, "0x%08x", entry->frame); else sprintf(buf, "XXXXXXXXXX"); for (i = 0; i < crc->values_cnt; i++) sprintf(buf + 10 + i * 11, " 0x%08x", entry->crcs[i]); sprintf(buf + 10 + crc->values_cnt * 11, "\n"); if (copy_to_user(user_buf, buf, LINE_LEN(crc->values_cnt))) return -EFAULT; return LINE_LEN(crc->values_cnt); } static __poll_t crtc_crc_poll(struct file *file, poll_table *wait) { struct drm_crtc *crtc = file->f_inode->i_private; struct drm_crtc_crc *crc = &crtc->crc; __poll_t ret = 0; poll_wait(file, &crc->wq, wait); spin_lock_irq(&crc->lock); if (crc->source && crtc_crc_data_count(crc)) ret |= EPOLLIN | EPOLLRDNORM; spin_unlock_irq(&crc->lock); return ret; } static const struct file_operations drm_crtc_crc_data_fops = { .owner = THIS_MODULE, .open = crtc_crc_open, .read = crtc_crc_read, .poll = crtc_crc_poll, .release = crtc_crc_release, }; void drm_debugfs_crtc_crc_add(struct drm_crtc *crtc) { struct dentry *crc_ent; if (!crtc->funcs->set_crc_source || !crtc->funcs->verify_crc_source) return; crc_ent = debugfs_create_dir("crc", crtc->debugfs_entry); debugfs_create_file("control", S_IRUGO | S_IWUSR, crc_ent, crtc, &drm_crtc_crc_control_fops); debugfs_create_file("data", S_IRUGO, crc_ent, crtc, &drm_crtc_crc_data_fops); } /** * drm_crtc_add_crc_entry - Add entry with CRC information for a frame * @crtc: CRTC to which the frame belongs * @has_frame: whether this entry has a frame number to go with * @frame: number of the frame these CRCs are about * @crcs: array of CRC values, with length matching #drm_crtc_crc.values_cnt * * For each frame, the driver polls the source of CRCs for new data and calls * this function to add them to the buffer from where userspace reads. */ int drm_crtc_add_crc_entry(struct drm_crtc *crtc, bool has_frame, uint32_t frame, uint32_t *crcs) { struct drm_crtc_crc *crc = &crtc->crc; struct drm_crtc_crc_entry *entry; int head, tail; unsigned long flags; spin_lock_irqsave(&crc->lock, flags); /* Caller may not have noticed yet that userspace has stopped reading */ if (!crc->entries) { spin_unlock_irqrestore(&crc->lock, flags); return -EINVAL; } head = crc->head; tail = crc->tail; if (CIRC_SPACE(head, tail, DRM_CRC_ENTRIES_NR) < 1) { bool was_overflow = crc->overflow; crc->overflow = true; spin_unlock_irqrestore(&crc->lock, flags); if (!was_overflow) DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n"); return -ENOBUFS; } entry = &crc->entries[head]; entry->frame = frame; entry->has_frame_counter = has_frame; memcpy(&entry->crcs, crcs, sizeof(*crcs) * crc->values_cnt); head = (head + 1) & (DRM_CRC_ENTRIES_NR - 1); crc->head = head; spin_unlock_irqrestore(&crc->lock, flags); wake_up_interruptible(&crc->wq); return 0; } EXPORT_SYMBOL_GPL(drm_crtc_add_crc_entry); |
| 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle firewalling core * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> * Bart De Schuymer <bdschuym@pandora.be> * * Lennert dedicates this file to Kerstin Wurdinger. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/in_route.h> #include <linux/inetdevice.h> #include <net/route.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { } static void fake_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { } static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; } static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { return NULL; } static unsigned int fake_mtu(const struct dst_entry *dst) { return dst->dev->mtu; } static struct dst_ops fake_dst_ops = { .family = AF_INET, .update_pmtu = fake_update_pmtu, .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, .mtu = fake_mtu, }; /* * Initialize bogus route table used to keep netfilter happy. * Currently, we fill in the PMTU entry because netfilter * refragmentation needs it, and the rt_flags entry because * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; dst_init_metrics(&rt->dst, br->metrics, false); dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } int __init br_nf_core_init(void) { return dst_entries_init(&fake_dst_ops); } void br_nf_core_fini(void) { dst_entries_destroy(&fake_dst_ops); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/bfs/inode.c * BFS superblock and inode operations. * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> * From fs/minix, Copyright (C) 1991, 1992 Linus Torvalds. * Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005. */ #include <linux/module.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/writeback.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/fs_context.h> #include "bfs.h" MODULE_AUTHOR("Tigran Aivazian <aivazian.tigran@gmail.com>"); MODULE_DESCRIPTION("SCO UnixWare BFS filesystem for Linux"); MODULE_LICENSE("GPL"); #undef DEBUG #ifdef DEBUG #define dprintf(x...) printf(x) #else #define dprintf(x...) #endif struct inode *bfs_iget(struct super_block *sb, unsigned long ino) { struct bfs_inode *di; struct inode *inode; struct buffer_head *bh; int block, off; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; if ((ino < BFS_ROOT_INO) || (ino > BFS_SB(inode->i_sb)->si_lasti)) { printf("Bad inode number %s:%08lx\n", inode->i_sb->s_id, ino); goto error; } block = (ino - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1; bh = sb_bread(inode->i_sb, block); if (!bh) { printf("Unable to read inode %s:%08lx\n", inode->i_sb->s_id, ino); goto error; } off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; di = (struct bfs_inode *)bh->b_data + off; inode->i_mode = 0x0000FFFF & le32_to_cpu(di->i_mode); if (le32_to_cpu(di->i_vtype) == BFS_VDIR) { inode->i_mode |= S_IFDIR; inode->i_op = &bfs_dir_inops; inode->i_fop = &bfs_dir_operations; } else if (le32_to_cpu(di->i_vtype) == BFS_VREG) { inode->i_mode |= S_IFREG; inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; } BFS_I(inode)->i_sblock = le32_to_cpu(di->i_sblock); BFS_I(inode)->i_eblock = le32_to_cpu(di->i_eblock); BFS_I(inode)->i_dsk_ino = le16_to_cpu(di->i_ino); i_uid_write(inode, le32_to_cpu(di->i_uid)); i_gid_write(inode, le32_to_cpu(di->i_gid)); set_nlink(inode, le32_to_cpu(di->i_nlink)); inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); inode_set_atime(inode, le32_to_cpu(di->i_atime), 0); inode_set_mtime(inode, le32_to_cpu(di->i_mtime), 0); inode_set_ctime(inode, le32_to_cpu(di->i_ctime), 0); brelse(bh); unlock_new_inode(inode); return inode; error: iget_failed(inode); return ERR_PTR(-EIO); } static struct bfs_inode *find_inode(struct super_block *sb, u16 ino, struct buffer_head **p) { if ((ino < BFS_ROOT_INO) || (ino > BFS_SB(sb)->si_lasti)) { printf("Bad inode number %s:%08x\n", sb->s_id, ino); return ERR_PTR(-EIO); } ino -= BFS_ROOT_INO; *p = sb_bread(sb, 1 + ino / BFS_INODES_PER_BLOCK); if (!*p) { printf("Unable to read inode %s:%08x\n", sb->s_id, ino); return ERR_PTR(-EIO); } return (struct bfs_inode *)(*p)->b_data + ino % BFS_INODES_PER_BLOCK; } static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct bfs_sb_info *info = BFS_SB(inode->i_sb); unsigned int ino = (u16)inode->i_ino; unsigned long i_sblock; struct bfs_inode *di; struct buffer_head *bh; int err = 0; dprintf("ino=%08x\n", ino); di = find_inode(inode->i_sb, ino, &bh); if (IS_ERR(di)) return PTR_ERR(di); mutex_lock(&info->bfs_lock); if (ino == BFS_ROOT_INO) di->i_vtype = cpu_to_le32(BFS_VDIR); else di->i_vtype = cpu_to_le32(BFS_VREG); di->i_ino = cpu_to_le16(ino); di->i_mode = cpu_to_le32(inode->i_mode); di->i_uid = cpu_to_le32(i_uid_read(inode)); di->i_gid = cpu_to_le32(i_gid_read(inode)); di->i_nlink = cpu_to_le32(inode->i_nlink); di->i_atime = cpu_to_le32(inode_get_atime_sec(inode)); di->i_mtime = cpu_to_le32(inode_get_mtime_sec(inode)); di->i_ctime = cpu_to_le32(inode_get_ctime_sec(inode)); i_sblock = BFS_I(inode)->i_sblock; di->i_sblock = cpu_to_le32(i_sblock); di->i_eblock = cpu_to_le32(BFS_I(inode)->i_eblock); di->i_eoffset = cpu_to_le32(i_sblock * BFS_BSIZE + inode->i_size - 1); mark_buffer_dirty(bh); if (wbc->sync_mode == WB_SYNC_ALL) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) err = -EIO; } brelse(bh); mutex_unlock(&info->bfs_lock); return err; } static void bfs_evict_inode(struct inode *inode) { unsigned long ino = inode->i_ino; struct bfs_inode *di; struct buffer_head *bh; struct super_block *s = inode->i_sb; struct bfs_sb_info *info = BFS_SB(s); struct bfs_inode_info *bi = BFS_I(inode); dprintf("ino=%08lx\n", ino); truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); if (inode->i_nlink) return; di = find_inode(s, inode->i_ino, &bh); if (IS_ERR(di)) return; mutex_lock(&info->bfs_lock); /* clear on-disk inode */ memset(di, 0, sizeof(struct bfs_inode)); mark_buffer_dirty(bh); brelse(bh); if (bi->i_dsk_ino) { if (bi->i_sblock) info->si_freeb += bi->i_eblock + 1 - bi->i_sblock; info->si_freei++; clear_bit(ino, info->si_imap); bfs_dump_imap("evict_inode", s); } /* * If this was the last file, make the previous block * "last block of the last file" even if there is no * real file there, saves us 1 gap. */ if (info->si_lf_eblk == bi->i_eblock) info->si_lf_eblk = bi->i_sblock - 1; mutex_unlock(&info->bfs_lock); } static void bfs_put_super(struct super_block *s) { struct bfs_sb_info *info = BFS_SB(s); if (!info) return; mutex_destroy(&info->bfs_lock); kfree(info); s->s_fs_info = NULL; } static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct bfs_sb_info *info = BFS_SB(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); buf->f_type = BFS_MAGIC; buf->f_bsize = s->s_blocksize; buf->f_blocks = info->si_blocks; buf->f_bfree = buf->f_bavail = info->si_freeb; buf->f_files = info->si_lasti + 1 - BFS_ROOT_INO; buf->f_ffree = info->si_freei; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = BFS_NAMELEN; return 0; } static struct kmem_cache *bfs_inode_cachep; static struct inode *bfs_alloc_inode(struct super_block *sb) { struct bfs_inode_info *bi; bi = alloc_inode_sb(sb, bfs_inode_cachep, GFP_KERNEL); if (!bi) return NULL; return &bi->vfs_inode; } static void bfs_free_inode(struct inode *inode) { kmem_cache_free(bfs_inode_cachep, BFS_I(inode)); } static void init_once(void *foo) { struct bfs_inode_info *bi = foo; inode_init_once(&bi->vfs_inode); } static int __init init_inodecache(void) { bfs_inode_cachep = kmem_cache_create("bfs_inode_cache", sizeof(struct bfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (bfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(bfs_inode_cachep); } static const struct super_operations bfs_sops = { .alloc_inode = bfs_alloc_inode, .free_inode = bfs_free_inode, .write_inode = bfs_write_inode, .evict_inode = bfs_evict_inode, .put_super = bfs_put_super, .statfs = bfs_statfs, }; void bfs_dump_imap(const char *prefix, struct super_block *s) { #ifdef DEBUG int i; char *tmpbuf = (char *)get_zeroed_page(GFP_KERNEL); if (!tmpbuf) return; for (i = BFS_SB(s)->si_lasti; i >= 0; i--) { if (i > PAGE_SIZE - 100) break; if (test_bit(i, BFS_SB(s)->si_imap)) strcat(tmpbuf, "1"); else strcat(tmpbuf, "0"); } printf("%s: lasti=%08lx <%s>\n", prefix, BFS_SB(s)->si_lasti, tmpbuf); free_page((unsigned long)tmpbuf); #endif } static int bfs_fill_super(struct super_block *s, struct fs_context *fc) { struct buffer_head *bh, *sbh; struct bfs_super_block *bfs_sb; struct inode *inode; unsigned i; struct bfs_sb_info *info; int ret = -EINVAL; unsigned long i_sblock, i_eblock, i_eoff, s_size; int silent = fc->sb_flags & SB_SILENT; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; mutex_init(&info->bfs_lock); s->s_fs_info = info; s->s_time_min = 0; s->s_time_max = U32_MAX; sb_set_blocksize(s, BFS_BSIZE); sbh = sb_bread(s, 0); if (!sbh) goto out; bfs_sb = (struct bfs_super_block *)sbh->b_data; if (le32_to_cpu(bfs_sb->s_magic) != BFS_MAGIC) { if (!silent) printf("No BFS filesystem on %s (magic=%08x)\n", s->s_id, le32_to_cpu(bfs_sb->s_magic)); goto out1; } if (BFS_UNCLEAN(bfs_sb, s) && !silent) printf("%s is unclean, continuing\n", s->s_id); s->s_magic = BFS_MAGIC; if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) || le32_to_cpu(bfs_sb->s_start) < sizeof(struct bfs_super_block) + sizeof(struct bfs_dirent)) { printf("Superblock is corrupted on %s\n", s->s_id); goto out1; } info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) / sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; if (info->si_lasti == BFS_MAX_LASTI) printf("NOTE: filesystem %s was created with 512 inodes, the real maximum is 511, mounting anyway\n", s->s_id); else if (info->si_lasti > BFS_MAX_LASTI) { printf("Impossible last inode number %lu > %d on %s\n", info->si_lasti, BFS_MAX_LASTI, s->s_id); goto out1; } for (i = 0; i < BFS_ROOT_INO; i++) set_bit(i, info->si_imap); s->s_op = &bfs_sops; inode = bfs_iget(s, BFS_ROOT_INO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto out1; } s->s_root = d_make_root(inode); if (!s->s_root) { ret = -ENOMEM; goto out1; } info->si_blocks = (le32_to_cpu(bfs_sb->s_end) + 1) >> BFS_BSIZE_BITS; info->si_freeb = (le32_to_cpu(bfs_sb->s_end) + 1 - le32_to_cpu(bfs_sb->s_start)) >> BFS_BSIZE_BITS; info->si_freei = 0; info->si_lf_eblk = 0; /* can we read the last block? */ bh = sb_bread(s, info->si_blocks - 1); if (!bh) { printf("Last block not available on %s: %lu\n", s->s_id, info->si_blocks - 1); ret = -EIO; goto out2; } brelse(bh); bh = NULL; for (i = BFS_ROOT_INO; i <= info->si_lasti; i++) { struct bfs_inode *di; int block = (i - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1; int off = (i - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; unsigned long eblock; if (!off) { brelse(bh); bh = sb_bread(s, block); } if (!bh) continue; di = (struct bfs_inode *)bh->b_data + off; /* test if filesystem is not corrupted */ i_eoff = le32_to_cpu(di->i_eoffset); i_sblock = le32_to_cpu(di->i_sblock); i_eblock = le32_to_cpu(di->i_eblock); s_size = le32_to_cpu(bfs_sb->s_end); if (i_sblock > info->si_blocks || i_eblock > info->si_blocks || i_sblock > i_eblock || (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { printf("Inode 0x%08x corrupted on %s\n", i, s->s_id); brelse(bh); ret = -EIO; goto out2; } if (!di->i_ino) { info->si_freei++; continue; } set_bit(i, info->si_imap); info->si_freeb -= BFS_FILEBLOCKS(di); eblock = le32_to_cpu(di->i_eblock); if (eblock > info->si_lf_eblk) info->si_lf_eblk = eblock; } brelse(bh); brelse(sbh); bfs_dump_imap("fill_super", s); return 0; out2: dput(s->s_root); s->s_root = NULL; out1: brelse(sbh); out: mutex_destroy(&info->bfs_lock); kfree(info); s->s_fs_info = NULL; return ret; } static int bfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, bfs_fill_super); } static const struct fs_context_operations bfs_context_ops = { .get_tree = bfs_get_tree, }; static int bfs_init_fs_context(struct fs_context *fc) { fc->ops = &bfs_context_ops; return 0; } static struct file_system_type bfs_fs_type = { .owner = THIS_MODULE, .name = "bfs", .init_fs_context = bfs_init_fs_context, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("bfs"); static int __init init_bfs_fs(void) { int err = init_inodecache(); if (err) goto out1; err = register_filesystem(&bfs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_bfs_fs(void) { unregister_filesystem(&bfs_fs_type); destroy_inodecache(); } module_init(init_bfs_fs) module_exit(exit_bfs_fs) |
| 49 49 186 186 186 218 218 74 217 218 218 218 218 36 37 188 186 10 186 187 188 186 186 156 188 151 151 151 151 77 61 61 90 5 4 69 49 50 50 50 52 30 50 50 50 50 7 7 7 7 7 69 69 69 69 69 69 69 52 52 69 49 69 20 20 20 20 20 194 193 194 16 16 195 49 49 194 138 138 94 108 194 216 196 196 192 165 216 218 218 218 74 74 216 217 217 20 20 198 195 195 216 216 216 218 13 33 33 33 33 33 33 33 15 33 33 33 33 33 17 21 33 33 33 33 33 33 33 33 33 33 17 33 33 33 33 17 33 33 33 33 33 6 56 6 6 56 60 60 59 59 58 59 59 5 56 40 59 59 59 56 59 59 74 33 33 72 33 33 60 59 59 1 151 100 151 151 151 77 77 77 151 151 151 151 151 100 151 151 151 77 77 77 151 151 149 149 148 9 9 9 149 149 149 9 151 151 100 151 151 151 149 148 9 148 64 64 21 21 21 184 182 183 183 182 109 26 109 109 26 25 25 151 151 151 151 149 77 149 74 155 155 155 155 155 74 64 21 74 74 74 74 155 155 71 155 155 77 155 153 155 155 155 155 10 10 10 10 10 10 10 10 203 202 202 37 37 37 37 36 37 37 37 37 37 37 37 37 37 36 37 37 46 46 45 46 46 46 46 44 37 37 25 25 1 37 36 37 37 37 37 37 37 36 1 36 36 37 37 44 44 31 33 46 10 46 46 47 48 48 48 48 15 15 46 46 40 4 4 46 4 46 12 46 46 46 46 46 46 46 46 46 46 46 46 46 46 10 10 48 48 48 4 4 4 4 4 4 4 4 4 4 4 4 169 170 168 169 61 170 170 170 169 20 20 20 20 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 151 1 1 1 151 151 169 169 170 169 170 56 56 56 56 56 56 56 56 48 48 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> * * Architecture independence: * Copyright (c) 2005, Bull S.A. * Written by Pierre Peiffer <pierre.peiffer@bull.net> */ /* * Extents support for EXT4 * * TODO: * - ext4*_error() should be used in some situations * - analyze all BUG()/BUG_ON(), use -EIO where appropriate * - smart tree reduction */ #include <linux/fs.h> #include <linux/time.h> #include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> #include <linux/iomap.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" #include <trace/events/ext4.h> /* * used by extent splitting. */ #define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \ due to ENOSPC */ #define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */ #define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */ #define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ #define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_inode_info *ei = EXT4_I(inode); __u32 csum; csum = ext4_chksum(ei->i_csum_seed, (__u8 *)eh, EXT4_EXTENT_TAIL_OFFSET(eh)); return cpu_to_le32(csum); } static int ext4_extent_block_csum_verify(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_feature_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); if (et->et_checksum != ext4_extent_block_csum(inode, eh)) return 0; return 1; } static void ext4_extent_block_csum_set(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_feature_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); et->et_checksum = ext4_extent_block_csum(inode, eh); } static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t split, int split_flag, int flags); static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; } static inline void ext4_ext_path_brelse(struct ext4_ext_path *path) { brelse(path->p_bh); path->p_bh = NULL; } static void ext4_ext_drop_refs(struct ext4_ext_path *path) { int depth, i; if (IS_ERR_OR_NULL(path)) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) ext4_ext_path_brelse(path); } void ext4_free_ext_path(struct ext4_ext_path *path) { if (IS_ERR_OR_NULL(path)) return; ext4_ext_drop_refs(path); kfree(path); } /* * Make sure 'handle' has at least 'check_cred' credits. If not, restart * transaction with 'restart_cred' credits. The function drops i_data_sem * when restarting transaction and gets it after transaction is restarted. * * The function returns 0 on success, 1 if transaction had to be restarted, * and < 0 in case of fatal error. */ int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred) { int ret; int dropped = 0; ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); if (dropped) down_write(&EXT4_I(inode)->i_data_sem); return ret; } /* * could return: * - EROFS * - ENOMEM */ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err = 0; if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, path->p_bh, EXT4_JTR_NONE); /* * The extent buffer's verified bit will be set again in * __ext4_ext_dirty(). We could leave an inconsistent * buffer if the extents updating procudure break off du * to some error happens, force to check it again. */ if (!err) clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ return err; } /* * could return: * - EROFS * - ENOMEM * - EIO */ static int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err; WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (path->p_bh) { ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); /* Extents updating done, re-set verified flag */ if (!err) set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); } return err; } #define ext4_ext_dirty(handle, inode, path) \ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { if (path) { int depth = path->p_depth; struct ext4_extent *ex; /* * Try to predict block placement assuming that we are * filling in a file which will eventually be * non-sparse --- i.e., in the case of libbfd writing * an ELF object sections out-of-order but in a way * the eventually results in a contiguous object or * executable file, or some database extending a table * space file. However, this is actually somewhat * non-ideal if we are writing a sparse file such as * qemu or KVM writing a raw image file that is going * to stay fairly sparse, since it will end up * fragmenting the file system's free space. Maybe we * should have some hueristics or some way to allow * userspace to pass a hint to file system, * especially if the latter case turns out to be * common. */ ex = path[depth].p_ext; if (ex) { ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex); ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block); if (block > ext_block) return ext_pblk + (block - ext_block); else return ext_pblk - (ext_block - block); } /* it looks like index is empty; * try to find starting block from index itself */ if (path[depth].p_bh) return path[depth].p_bh->b_blocknr; } /* OK. use inode's group */ return ext4_inode_to_goal_block(inode); } /* * Allocation for a meta data block */ static ext4_fsblk_t ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex, int *err, unsigned int flags) { ext4_fsblk_t goal, newblock; goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block)); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, err); return newblock; } static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 6) size = 6; #endif return size; } static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 5) size = 5; #endif return size; } static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 3) size = 3; #endif return size; } static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 4) size = 4; #endif return size; } static inline struct ext4_ext_path * ext4_force_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t lblk, int nofail) { int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext); int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO; if (nofail) flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; return ext4_split_extent_at(handle, inode, path, lblk, unwritten ? EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, flags); } static int ext4_ext_max_entries(struct inode *inode, int depth) { int max; if (depth == ext_depth(inode)) { if (depth == 0) max = ext4_ext_space_root(inode, 1); else max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) max = ext4_ext_space_block(inode, 1); else max = ext4_ext_space_block_idx(inode, 1); } return max; } static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); /* * We allow neither: * - zero length * - overflow/wrap-around */ if (lblock + len <= lblock) return 0; return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, ext4_lblk_t lblk, ext4_fsblk_t *pblk, int depth) { unsigned short entries; ext4_lblk_t lblock = 0; ext4_lblk_t cur = 0; if (eh->eh_entries == 0) return 1; entries = le16_to_cpu(eh->eh_entries); if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); /* * The logical block in the first entry should equal to * the number in the index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext->ee_block)) return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); if (lblock < cur) { *pblk = ext4_ext_pblock(ext); return 0; } cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); /* * The logical block in the first entry should equal to * the number in the parent index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext_idx->ei_block)) return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); if (lblock < cur) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; cur = lblock + 1; } } return 1; } static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { error_msg = "invalid magic"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) { error_msg = "unexpected eh_depth"; goto corrupted; } if (unlikely(eh->eh_max == 0)) { error_msg = "invalid eh_max"; goto corrupted; } max = ext4_ext_max_entries(inode, depth); if (unlikely(le16_to_cpu(eh->eh_max) > max)) { error_msg = "too large eh_max"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { error_msg = "invalid eh_entries"; goto corrupted; } if (unlikely((eh->eh_entries == 0) && (depth > 0))) { error_msg = "eh_entries is 0 but eh_depth is > 0"; goto corrupted; } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } if (unlikely(depth > 32)) { error_msg = "too large eh_depth"; goto corrupted; } /* Verify checksum on non-root extent tree nodes */ if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { error_msg = "extent tree corrupted"; err = -EFSBADCRC; goto corrupted; } return 0; corrupted: ext4_error_inode_err(inode, function, line, 0, -err, "pblk %llu bad header/extent: %s - magic %x, " "entries %u, max %u(%u), depth %u(%u)", (unsigned long long) pblk, error_msg, le16_to_cpu(eh->eh_magic), le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), max, le16_to_cpu(eh->eh_depth), depth); return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } static void ext4_cache_extents(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); ext4_lblk_t prev = 0; int i; for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { unsigned int status = EXTENT_STATUS_WRITTEN; ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); int len = ext4_ext_get_actual_len(ex); if (prev && (prev != lblk)) ext4_es_cache_extent(inode, prev, lblk - prev, ~0, EXTENT_STATUS_HOLE); if (ext4_ext_is_unwritten(ex)) status = EXTENT_STATUS_UNWRITTEN; ext4_es_cache_extent(inode, lblk, len, ext4_ext_pblock(ex), status); prev = lblk + len; } } static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_idx *idx, int depth, int flags) { struct buffer_head *bh; int err; gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; ext4_fsblk_t pblk; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; pblk = ext4_idx_pblock(idx); bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (!bh_uptodate_or_lock(bh)) { trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); err = ext4_read_bh(bh, 0, NULL, false); if (err < 0) goto errout; } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); ext4_cache_extents(inode, eh); } return bh; errout: put_bh(bh); return ERR_PTR(err); } #define read_extent_tree_block(inode, idx, depth, flags) \ __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* * This function is called to cache a file's extent information in the * extent status tree */ int ext4_ext_precache(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_ext_path *path = NULL; struct buffer_head *bh; int i = 0, depth, ret = 0; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return 0; /* not an extent-mapped inode */ ext4_check_map_extents_env(inode); down_read(&ei->i_data_sem); depth = ext_depth(inode); /* Don't cache anything if there are no external extent blocks */ if (!depth) { up_read(&ei->i_data_sem); return ret; } path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS); if (path == NULL) { up_read(&ei->i_data_sem); return -ENOMEM; } path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) goto out; path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr); while (i >= 0) { /* * If this is a leaf block or we've reached the end of * the index block, go up */ if ((i == depth) || path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { ext4_ext_path_brelse(path + i); i--; continue; } bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { ret = PTR_ERR(bh); break; } i++; path[i].p_bh = bh; path[i].p_hdr = ext_block_hdr(bh); path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr); } ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); ext4_free_ext_path(path); return ret; } #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { ext_debug(inode, " %d->%llu", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else ext_debug(inode, " []"); } ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) { int depth = ext_depth(inode); struct ext4_extent_header *eh; struct ext4_extent *ex; int i; if (IS_ERR_OR_NULL(path)) return; eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ext4_fsblk_t newblock, int level) { int depth = ext_depth(inode); struct ext4_extent *ex; if (depth != level) { struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { ext_debug(inode, "%d: move %d:%llu in new index %llu\n", level, le32_to_cpu(idx->ei_block), ext4_idx_pblock(idx), newblock); idx++; } return; } ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), newblock); ex++; } } #else #define ext4_ext_show_path(inode, path) #define ext4_ext_show_leaf(inode, path) #define ext4_ext_show_move(inode, path, newblock, level) #endif /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent_idx *r, *l, *m; ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), r, le32_to_cpu(r->ei_block)); if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; } path->p_idx = l - 1; ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { struct ext4_extent_idx *chix, *ix; int k; chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { if (k != 0 && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); printk(KERN_DEBUG "%u <= %u\n", le32_to_cpu(ix->ei_block), le32_to_cpu(ix[-1].ei_block)); } BUG_ON(k && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)); if (block < le32_to_cpu(ix->ei_block)) break; chix = ix; } BUG_ON(chix != path->p_idx); } #endif } /* * ext4_ext_binsearch: * binary search for closest extent of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent *r, *l, *m; if (eh->eh_entries == 0) { /* * this leaf is empty: * we get such a leaf in split/add case */ return; } ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), r, le32_to_cpu(r->ee_block)); if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; } path->p_ext = l - 1; ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { struct ext4_extent *chex, *ex; int k; chex = ex = EXT_FIRST_EXTENT(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { BUG_ON(k && le32_to_cpu(ex->ee_block) <= le32_to_cpu(ex[-1].ee_block)); if (block < le32_to_cpu(ex->ee_block)) break; chex = ex; } BUG_ON(chex != path->p_ext); } #endif } void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; eh = ext_inode_hdr(inode); eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); } struct ext4_ext_path * ext4_find_extent(struct inode *inode, ext4_lblk_t block, struct ext4_ext_path *path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; short int depth, i, ppos = 0; int ret; gfp_t gfp_flags = GFP_NOFS; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) { EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d", depth); ret = -EFSCORRUPTED; goto err; } if (path) { ext4_ext_drop_refs(path); if (depth > path[0].p_maxdepth) { kfree(path); path = NULL; } } if (!path) { /* account possible depth increase */ path = kcalloc(depth + 2, sizeof(struct ext4_ext_path), gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; } path[0].p_hdr = eh; path[0].p_bh = NULL; i = depth; if (!(flags & EXT4_EX_NOCACHE) && depth == 0) ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; path[ppos].p_ext = NULL; bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; } eh = ext_block_hdr(bh); ppos++; path[ppos].p_bh = bh; path[ppos].p_hdr = eh; } path[ppos].p_depth = i; path[ppos].p_ext = NULL; path[ppos].p_idx = NULL; /* find extent */ ext4_ext_binsearch(inode, path + ppos, block); /* if not an empty leaf */ if (path[ppos].p_ext) path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); ext4_ext_show_path(inode, path); return path; err: ext4_free_ext_path(path); return ERR_PTR(ret); } /* * ext4_ext_insert_index: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, struct ext4_ext_path *curp, int logical, ext4_fsblk_t ptr) { struct ext4_extent_idx *ix; int len, err; err = ext4_ext_get_access(handle, inode, curp); if (err) return err; if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) { EXT4_ERROR_INODE(inode, "logical %d == ei_block %d!", logical, le32_to_cpu(curp->p_idx->ei_block)); return -EFSCORRUPTED; } if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) >= le16_to_cpu(curp->p_hdr->eh_max))) { EXT4_ERROR_INODE(inode, "eh_entries %d >= eh_max %d!", le16_to_cpu(curp->p_hdr->eh_entries), le16_to_cpu(curp->p_hdr->eh_max)); return -EFSCORRUPTED; } if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ ext_debug(inode, "insert new index %d after: %llu\n", logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ ext_debug(inode, "insert new index %d before: %llu\n", logical, ptr); ix = curp->p_idx; } if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); return -EFSCORRUPTED; } len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); return -EFSCORRUPTED; } err = ext4_ext_dirty(handle, inode, curp); ext4_std_error(inode->i_sb, err); return err; } /* * ext4_ext_split: * inserts new subtree into the path, using free index entry * at depth @at: * - allocates all needed blocks (new leaf and all intermediate index blocks) * - makes decision where to split * - moves remaining extents and index entries (right to the split point) * into the newly allocated blocks * - initializes subtree */ static int ext4_ext_split(handle_t *handle, struct inode *inode, unsigned int flags, struct ext4_ext_path *path, struct ext4_extent *newext, int at) { struct buffer_head *bh = NULL; int depth = ext_depth(inode); struct ext4_extent_header *neh; struct ext4_extent_idx *fidx; int i = at, k, m, a; ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ gfp_t gfp_flags = GFP_NOFS; int err = 0; size_t ext_size = 0; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ /* if current leaf will be split, then we should use * border from split point */ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!"); return -EFSCORRUPTED; } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } /* * If error occurs, then we break processing * and mark filesystem read-only. index won't * be inserted and tree will be in consistent * state. Next mount will repair buffers too. */ /* * Get array to track all allocated blocks. * We need this to handle errors and free blocks * upon them. */ ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); if (newblock == 0) goto cleanup; ablocks[a] = newblock; } /* initialize new leaf */ newblock = ablocks[--a]; if (unlikely(newblock == 0)) { EXT4_ERROR_INODE(inode, "newblock == 0!"); err = -EFSCORRUPTED; goto cleanup; } bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = 0; neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max)) { EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!", path[depth].p_hdr->eh_entries, path[depth].p_hdr->eh_max); err = -EFSCORRUPTED; goto cleanup; } /* start copy from next extent */ m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++; ext4_ext_show_move(inode, path, newblock, depth); if (m) { struct ext4_extent *ex; ex = EXT_FIRST_EXTENT(neh); memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old leaf */ if (m) { err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; le16_add_cpu(&path[depth].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto cleanup; } /* create intermediate indexes */ k = depth - at - 1; if (unlikely(k < 0)) { EXT4_ERROR_INODE(inode, "k %d < 0!", k); err = -EFSCORRUPTED; goto cleanup; } if (k) ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; while (k--) { oldblock = newblock; newblock = ablocks[--a]; bh = sb_getblk(inode->i_sb, newblock); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) != EXT_LAST_INDEX(path[i].p_hdr))) { EXT4_ERROR_INODE(inode, "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!", le32_to_cpu(path[i].p_ext->ee_block)); err = -EFSCORRUPTED; goto cleanup; } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { memmove(++fidx, path[i].p_idx, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old index */ if (m) { err = ext4_ext_get_access(handle, inode, path + i); if (err) goto cleanup; le16_add_cpu(&path[i].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + i); if (err) goto cleanup; } i--; } /* insert new index */ err = ext4_ext_insert_index(handle, inode, path + at, le32_to_cpu(border), newblock); cleanup: if (bh) { if (buffer_locked(bh)) unlock_buffer(bh); brelse(bh); } if (err) { /* free all allocated blocks in error case */ for (i = 0; i < depth; i++) { if (!ablocks[i]) continue; ext4_free_blocks(handle, inode, NULL, ablocks[i], 1, EXT4_FREE_BLOCKS_METADATA); } } kfree(ablocks); return err; } /* * ext4_ext_grow_indepth: * implements tree growing procedure: * - allocates new block * - moves top-level data (index block or leaf) into the new block * - initializes new top-level, creating index that points to the * just created block */ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, unsigned int flags) { struct ext4_extent_header *neh; struct buffer_head *bh; ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode))); if (goal > le32_to_cpu(es->s_first_data_block)) { flags |= EXT4_MB_HINT_TRY_GOAL; goal--; } else goal = ext4_inode_to_goal_block(inode); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, &err); if (newblock == 0) return err; bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) return -ENOMEM; lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) { unlock_buffer(bh); goto out; } ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); /* zero out unused area in the extent block */ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); set_buffer_verified(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto out; /* Update top-level index: num,max,pointer */ neh = ext_inode_hdr(inode); neh->eh_entries = cpu_to_le16(1); ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock); if (neh->eh_depth == 0) { /* Root extent block becomes index block */ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); return err; } /* * ext4_ext_create_new_leaf: * finds empty index and adds new leaf. * if no free index is found, then it requests in-depth growing. */ static struct ext4_ext_path * ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, unsigned int mb_flags, unsigned int gb_flags, struct ext4_ext_path *path, struct ext4_extent *newext) { struct ext4_ext_path *curp; int depth, i, err = 0; ext4_lblk_t ee_block = le32_to_cpu(newext->ee_block); repeat: i = depth = ext_depth(inode); /* walk up to the tree and look for free index entry */ curp = path + depth; while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) { i--; curp--; } /* we use already allocated block for index block, * so subsequent data blocks should be contiguous */ if (EXT_HAS_FREE_INDEX(curp)) { /* if we found index with free entry, then use that * entry: create all needed subtree and add new leaf */ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) goto errout; /* refill path */ path = ext4_find_extent(inode, ee_block, path, gb_flags); return path; } /* tree is full, time to grow in depth */ err = ext4_ext_grow_indepth(handle, inode, mb_flags); if (err) goto errout; /* refill path */ path = ext4_find_extent(inode, ee_block, path, gb_flags); if (IS_ERR(path)) return path; /* * only first (depth 0 -> 1) produces free space; * in all other cases we have to split the grown tree */ depth = ext_depth(inode); if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { /* now we need to split */ goto repeat; } return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * search the closest allocated block to the left for *logical * and returns it at @logical + it's physical address at @phys * if *logical is the smallest allocated block, the function * returns 0 at @phys * return value contains 0 (success) or error code */ static int ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth, ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!", *logical, le32_to_cpu(ex->ee_block)); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block), depth); return -EFSCORRUPTED; } } return 0; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; *phys = ext4_ext_pblock(ex) + ee_len - 1; return 0; } /* * Search the closest allocated block to the right for *logical * and returns it at @logical + it's physical address at @phys. * If not exists, return 0 and @phys is set to 0. We will return * 1 which means we found an allocated block and ret_ex is valid. * Or return a (< 0) error code. */ static int ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys, struct ext4_extent *ret_ex, int flags) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "first_extent(path[%d].p_hdr) != ex", depth); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix != EXT_FIRST_INDEX *logical %d!", *logical); return -EFSCORRUPTED; } } goto found_extent; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) { /* next allocated block in this leaf */ ex++; goto found_extent; } /* go up and search for index to the right */ while (--depth >= 0) { ix = path[depth].p_idx; if (ix != EXT_LAST_INDEX(path[depth].p_hdr)) goto got_index; } /* we've gone up to the root and found no index to the right */ return 0; got_index: /* we've found index to the right, let's * follow it and find the closest allocated * block to the right */ ix++; while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); put_bh(bh); } bh = read_extent_tree_block(inode, ix, path->p_depth - depth, flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ex = EXT_FIRST_EXTENT(eh); found_extent: *logical = le32_to_cpu(ex->ee_block); *phys = ext4_ext_pblock(ex); if (ret_ex) *ret_ex = *ex; if (bh) put_bh(bh); return 1; } /* * ext4_ext_next_allocated_block: * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. */ ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) return EXT_MAX_BLOCKS; while (depth >= 0) { struct ext4_ext_path *p = &path[depth]; if (depth == path->p_depth) { /* leaf */ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; /* zero-tree has no leaf blocks at all */ if (depth == 0) return EXT_MAX_BLOCKS; /* go to index block */ depth--; while (depth >= 0) { if (path[depth].p_idx != EXT_LAST_INDEX(path[depth].p_hdr)) return (ext4_lblk_t) le32_to_cpu(path[depth].p_idx[1].ei_block); depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_correct_indexes: * if leaf gets modified and modified extent is first in the leaf, * then we have to correct all indexes above. * TODO: do we need to correct tree in all cases? */ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { struct ext4_extent_header *eh; int depth = ext_depth(inode); struct ext4_extent *ex; __le32 border; int k, err = 0; eh = path[depth].p_hdr; ex = path[depth].p_ext; if (unlikely(ex == NULL || eh == NULL)) { EXT4_ERROR_INODE(inode, "ex %p == NULL or eh %p == NULL", ex, eh); return -EFSCORRUPTED; } if (depth == 0) { /* there is no tree at all */ return 0; } if (ex != EXT_FIRST_EXTENT(eh)) { /* we correct tree if first leaf got modified only */ return 0; } /* * TODO: we need correction if border is smaller than current one */ k = depth - 1; border = path[depth].p_ext->ee_block; err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; while (k--) { /* change all left-side indexes */ if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) goto clean; } return 0; clean: /* * The path[k].p_bh is either unmodified or with no verified bit * set (see ext4_ext_get_access()). So just clear the verified bit * of the successfully modified extents buffers, which will force * these extents to be checked to avoid using inconsistent data. */ while (++k < depth) clear_buffer_verified(path[k].p_bh); return err; } static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; ext1_ee_len = ext4_ext_get_actual_len(ex1); ext2_ee_len = ext4_ext_get_actual_len(ex2); if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; if (ext4_ext_is_unwritten(ex1) && ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) return 0; #endif if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2)) return 1; return 0; } /* * This function tries to merge the "ex" extent to the next extent in the tree. * It always tries to merge towards right. If you want to merge towards * left, pass "ex - 1" as argument instead of "ex". * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns * 1 if they got merged. */ static int ext4_ext_try_to_merge_right(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth, len; int merge_done = 0, unwritten; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; while (ex < EXT_LAST_EXTENT(eh)) { if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) break; /* merge with next extent! */ unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(ex + 1)); if (unwritten) ext4_ext_mark_unwritten(ex); if (ex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - ex - 1) * sizeof(struct ext4_extent); memmove(ex + 1, ex + 2, len); } le16_add_cpu(&eh->eh_entries, -1); merge_done = 1; WARN_ON(eh->eh_entries == 0); if (!eh->eh_entries) EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!"); } return merge_done; } /* * This function does a very simple check to see if we can collapse * an extent tree with a single extent tree leaf block into the inode. */ static void ext4_ext_try_to_merge_up(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { size_t s; unsigned max_root = ext4_ext_space_root(inode, 0); ext4_fsblk_t blk; if ((path[0].p_depth != 1) || (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) return; /* * We need to modify the block allocation bitmap and the block * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ if (ext4_journal_extend(handle, 2, ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* * Copy the extent data up to the inode */ blk = ext4_idx_pblock(path[0].p_idx); s = le16_to_cpu(path[1].p_hdr->eh_entries) * sizeof(struct ext4_extent_idx); s += sizeof(struct ext4_extent_header); path[1].p_maxdepth = path[0].p_maxdepth; memcpy(path[0].p_hdr, path[1].p_hdr, s); path[0].p_depth = 0; path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); path[0].p_hdr->eh_max = cpu_to_le16(max_root); ext4_ext_path_brelse(path + 1); ext4_free_blocks(handle, inode, NULL, blk, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* * This function tries to merge the @ex extent to neighbours in the tree, then * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; if (ex > EXT_FIRST_EXTENT(eh)) merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) (void) ext4_ext_try_to_merge_right(inode, path, ex); ext4_ext_try_to_merge_up(handle, inode, path); } /* * check if a portion of the "newext" extent overlaps with an * existing extent. * * If there is an overlap discovered, it updates the length of the newext * such that there will be no overlap, and then returns 1. * If there is no overlap found, it returns 0. */ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, struct inode *inode, struct ext4_extent *newext, struct ext4_ext_path *path) { ext4_lblk_t b1, b2; unsigned int depth, len1; unsigned int ret = 0; b1 = le32_to_cpu(newext->ee_block); len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path * is before the requested block(s) */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } /* check for overlap */ if (b1 + len1 > b2) { newext->ee_len = cpu_to_le16(b2 - b1); ret = 1; } out: return ret; } /* * ext4_ext_insert_extent: * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ struct ext4_ext_path * ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *newext, int gb_flags) { struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ int depth, len, err = 0; ext4_lblk_t next; int mb_flags = 0, unwritten; if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); err = -EFSCORRUPTED; goto errout; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; goto errout; } /* try to insert block into found extent and return */ if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) { /* * Try to see whether we should rather test the extent on * right from ex, or from the left of ex. This is because * ext4_find_extent() can return either extent on the * left, or on the right from the searched position. This * will make merging more effective. */ if (ex < EXT_LAST_EXTENT(eh) && (le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex) < le32_to_cpu(newext->ee_block))) { ex += 1; goto prepend; } else if ((ex > EXT_FIRST_EXTENT(eh)) && (le32_to_cpu(newext->ee_block) + ext4_ext_get_actual_len(newext) < le32_to_cpu(ex->ee_block))) ex -= 1; /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); nearex = ex; goto merge; } prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_block = newext->ee_block; ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); nearex = ex; goto merge; } } depth = ext_depth(inode); eh = path[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) goto has_space; /* probably next leaf has space for us? */ fex = EXT_LAST_EXTENT(eh); next = EXT_MAX_BLOCKS; if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { struct ext4_ext_path *npath; ext_debug(inode, "next leaf block - %u\n", next); npath = ext4_find_extent(inode, next, NULL, gb_flags); if (IS_ERR(npath)) { err = PTR_ERR(npath); goto errout; } BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); ext4_free_ext_path(path); path = npath; goto has_space; } ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_free_ext_path(npath); } /* * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) mb_flags |= EXT4_MB_USE_RESERVED; path = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, path, newext); if (IS_ERR(path)) return path; depth = ext_depth(inode); eh = path[depth].p_hdr; has_space: nearex = path[depth].p_ext; err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; if (!nearex) { /* there is no extent in this leaf, create first one */ ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext)); nearex = EXT_FIRST_EXTENT(eh); } else { if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); nearex++; } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), len, nearex, nearex + 1); memmove(nearex + 1, nearex, len * sizeof(struct ext4_extent)); } } le16_add_cpu(&eh->eh_entries, 1); path[depth].p_ext = nearex; nearex->ee_block = newext->ee_block; ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: /* try to merge extents */ if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, nearex); /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) goto errout; err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) goto errout; return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } static int ext4_fill_es_cache_info(struct inode *inode, ext4_lblk_t block, ext4_lblk_t num, struct fiemap_extent_info *fieinfo) { ext4_lblk_t next, end = block + num - 1; struct extent_status es; unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; unsigned int flags; int err; while (block <= end) { next = 0; flags = 0; if (!ext4_es_lookup_extent(inode, block, &next, &es)) break; if (ext4_es_is_unwritten(&es)) flags |= FIEMAP_EXTENT_UNWRITTEN; if (ext4_es_is_delayed(&es)) flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); if (ext4_es_is_hole(&es)) flags |= EXT4_FIEMAP_EXTENT_HOLE; if (next == 0) flags |= FIEMAP_EXTENT_LAST; if (flags & (FIEMAP_EXTENT_DELALLOC| EXT4_FIEMAP_EXTENT_HOLE)) es.es_pblk = 0; else es.es_pblk = ext4_es_pblock(&es); err = fiemap_fill_next_extent(fieinfo, (__u64)es.es_lblk << blksize_bits, (__u64)es.es_pblk << blksize_bits, (__u64)es.es_len << blksize_bits, flags); if (next == 0) break; block = next; if (err < 0) return err; if (err == 1) return 0; } return 0; } /* * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole * * Determine hole length (and start if easily possible) around given logical * block. We don't try too hard to find the beginning of the hole but @path * actually points to extent before @lblk, we provide it. * * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; ext4_lblk_t len; ex = path[depth].p_ext; if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ *lblk = 0; len = EXT_MAX_BLOCKS; } else if (*lblk < le32_to_cpu(ex->ee_block)) { len = le32_to_cpu(ex->ee_block) - *lblk; } else if (*lblk >= le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)) { ext4_lblk_t next; *lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); next = ext4_ext_next_allocated_block(path); BUG_ON(next == *lblk); len = next - *lblk; } else { BUG(); } return len; } /* * ext4_ext_rm_idx: * removes index from the index block. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, int depth) { int err; ext4_fsblk_t leaf; int k = depth - 1; /* free index block */ leaf = ext4_idx_pblock(path[k].p_idx); if (unlikely(path[k].p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr->eh_entries == 0", k); return -EFSCORRUPTED; } err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; if (path[k].p_idx != EXT_LAST_INDEX(path[k].p_hdr)) { int len = EXT_LAST_INDEX(path[k].p_hdr) - path[k].p_idx; len *= sizeof(struct ext4_extent_idx); memmove(path[k].p_idx, path[k].p_idx + 1, len); } le16_add_cpu(&path[k].p_hdr->eh_entries, -1); err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); while (--k >= 0) { if (path[k + 1].p_idx != EXT_FIRST_INDEX(path[k + 1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; path[k].p_idx->ei_block = path[k + 1].p_idx->ei_block; err = ext4_ext_dirty(handle, inode, path + k); if (err) goto clean; } return 0; clean: /* * The path[k].p_bh is either unmodified or with no verified bit * set (see ext4_ext_get_access()). So just clear the verified bit * of the successfully modified extents buffers, which will force * these extents to be checked to avoid using inconsistent data. */ while (++k < depth) clear_buffer_verified(path[k].p_bh); return err; } /* * ext4_ext_calc_credits_for_single_extent: * This routine returns max. credits that needed to insert an extent * to the extent tree. * When pass the actual path, the caller should calculate credits * under i_data_sem. */ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, struct ext4_ext_path *path) { if (path) { int depth = ext_depth(inode); int ret = 0; /* probably there is space in leaf? */ if (le16_to_cpu(path[depth].p_hdr->eh_entries) < le16_to_cpu(path[depth].p_hdr->eh_max)) { /* * There are some space in the leaf tree, no * need to account for leaf block credit * * bitmaps and block group descriptor blocks * and other metadata blocks still need to be * accounted. */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; } } return ext4_chunk_trans_blocks(inode, nrblocks); } /* * How many index/leaf blocks need to change/allocate to add @extents extents? * * If we add a single extent, then in the worse case, each tree level * index/leaf need to be changed in case of the tree split. * * If more extents are inserted, they could cause the whole tree split more * than once, but this is really rare. */ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; /* * Extent tree can change between the time we estimate credits and * the time we actually modify the tree. Assume the worst case. */ if (extents <= 1) index = (EXT4_MAX_EXTENT_DEPTH * 2) + extents; else index = (EXT4_MAX_EXTENT_DEPTH * 3) + DIV_ROUND_UP(extents, ext4_ext_space_block(inode, 0)); return index; } static inline int get_default_free_blocks_flags(struct inode *inode) { if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; return 0; } /* * ext4_rereserve_cluster - increment the reserved cluster count when * freeing a cluster with a pending reservation * * @inode - file containing the cluster * @lblk - logical block in cluster to be reserved * * Increments the reserved cluster count and adjusts quota in a bigalloc * file system when freeing a partial cluster containing at least one * delayed and unwritten block. A partial cluster meeting that * requirement will have a pending reservation. If so, the * RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to * defer reserved and allocated space accounting to a subsequent call * to this function. */ static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); dquot_reclaim_block(inode, EXT4_C2B(sbi, 1)); spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; percpu_counter_add(&sbi->s_dirtyclusters_counter, 1); spin_unlock(&ei->i_block_reservation_lock); percpu_counter_add(&sbi->s_freeclusters_counter, 1); ext4_remove_pending(inode, lblk); } static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, struct partial_cluster *partial, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t last_pblk, pblk; ext4_lblk_t num; int flags; /* only extent tail removal is allowed */ if (from < le32_to_cpu(ex->ee_block) || to != le32_to_cpu(ex->ee_block) + ee_len - 1) { ext4_error(sbi->s_sb, "strange request: removal(2) %u-%u from %u:%u", from, to, le32_to_cpu(ex->ee_block), ee_len); return 0; } #ifdef EXTENTS_STATS spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; if (ee_len < sbi->s_ext_min) sbi->s_ext_min = ee_len; if (ee_len > sbi->s_ext_max) sbi->s_ext_max = ee_len; if (ext_depth(inode) > sbi->s_depth_max) sbi->s_depth_max = ext_depth(inode); spin_unlock(&sbi->s_ext_stats_lock); #endif trace_ext4_remove_blocks(inode, ex, from, to, partial); /* * if we have a partial cluster, and it's different from the * cluster of the last block in the extent, we free it */ last_pblk = ext4_ext_pblock(ex) + ee_len - 1; if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, last_pblk)) { if (partial->state == tofree) { flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } num = le32_to_cpu(ex->ee_block) + ee_len - from; pblk = ext4_ext_pblock(ex) + ee_len - num; /* * We free the partial cluster at the end of the extent (if any), * unless the cluster is used by another extent (partial_cluster * state is nofree). If a partial cluster exists here, it must be * shared with the last block in the extent. */ flags = get_default_free_blocks_flags(inode); /* partial, left end cluster aligned, right end unaligned */ if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) && (EXT4_LBLK_CMASK(sbi, to) >= from) && (partial->state != nofree)) { if (ext4_is_pending(inode, to)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_PBLK_CMASK(sbi, last_pblk), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, to); partial->state = initial; flags = get_default_free_blocks_flags(inode); } flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we check to see if we * need to free it on a subsequent call to ext4_remove_blocks, * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; ext4_free_blocks(handle, inode, NULL, pblk, num, flags); /* reset the partial cluster if we've freed past it */ if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk)) partial->state = initial; /* * If we've freed the entire extent but the beginning is not left * cluster aligned and is not marked as ineligible for freeing we * record the partial cluster at the beginning of the extent. It * wasn't freed by the preceding ext4_free_blocks() call, and we * need to look farther to the left to determine if it's to be freed * (not shared with another extent). Else, reset the partial * cluster - we're either done freeing or the beginning of the * extent is left cluster aligned. */ if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) { if (partial->state == initial) { partial->pclu = EXT4_B2C(sbi, pblk); partial->lblk = from; partial->state = tofree; } } else { partial->state = initial; } return 0; } /* * ext4_ext_rm_leaf() Removes the extents associated with the * blocks appearing between "start" and "end". Both "start" * and "end" must appear in the same extent or EIO is returned. * * @handle: The journal handle * @inode: The files inode * @path: The path to the leaf * @partial_cluster: The cluster which we'll have to free if all extents * has been released from it. However, if this value is * negative, it's a cluster just to the right of the * punched region and it must not be freed. * @start: The first block to remove * @end: The last block to remove */ static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct partial_cluster *partial, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; ext4_lblk_t ex_ee_block; unsigned short ex_ee_len; unsigned unwritten = 0; struct ext4_extent *ex; ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* find where to start removing */ ex = path[depth].p_ext; if (!ex) ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_rm_leaf(inode, start, ex, partial); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { if (ext4_ext_is_unwritten(ex)) unwritten = 1; else unwritten = 0; ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; a = max(ex_ee_block, start); b = min(ex_ee_block + ex_ee_len - 1, end); ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { /* * We're going to skip this extent and move to another, * so note that its first cluster is in use to avoid * freeing it when removing blocks. Eventually, the * right edge of the truncated/punched region will * be just to the left. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex); partial->pclu = EXT4_B2C(sbi, pblk); partial->state = nofree; } ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); continue; } else if (b != ex_ee_block + ex_ee_len - 1) { EXT4_ERROR_INODE(inode, "can not handle truncate %u:%u " "on extent %u:%u", start, end, ex_ee_block, ex_ee_block + ex_ee_len - 1); err = -EFSCORRUPTED; goto out; } else if (a != ex_ee_block) { /* remove tail of the extent */ num = a - ex_ee_block; } else { /* remove whole extent: excellent! */ num = 0; } /* * 3 for leaf, sb, and inode plus 2 (bmap and group * descriptor) for each block group; assume two block * groups plus ex_ee_len/blocks_per_block_group for * the worst case */ credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb)); if (ex == EXT_FIRST_EXTENT(eh)) { correct_index = 1; credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); /* * We may end up freeing some index blocks and data from the * punched range. Note that partial clusters are accounted for * by ext4_free_data_revoke_credits(). */ revoke_credits = ext4_free_metadata_revoke_credits(inode->i_sb, ext_depth(inode)) + ext4_free_data_revoke_credits(inode, b - a + 1); err = ext4_datasem_ensure_credits(handle, inode, credits, credits, revoke_credits); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; err = ext4_remove_blocks(handle, inode, ex, partial, a, b); if (err) goto out; if (num == 0) /* this extent is removed; mark slot entirely unused */ ext4_ext_store_pblock(ex, 0); ex->ee_len = cpu_to_le16(num); /* * Do not mark unwritten if all the blocks in the * extent have been removed. */ if (unwritten && num) ext4_ext_mark_unwritten(ex); /* * If the extent was completely released, * we need to remove it from the leaf */ if (num == 0) { if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that * we dont have blank extents in the middle */ memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) * sizeof(struct ext4_extent)); /* Now get rid of the one at the end */ memset(EXT_LAST_EXTENT(eh), 0, sizeof(struct ext4_extent)); } le16_add_cpu(&eh->eh_entries, -1); } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) err = ext4_ext_correct_indexes(handle, inode, path); /* * If there's a partial cluster and at least one extent remains in * the leaf, free the partial cluster if it isn't shared with the * current extent. If it is shared with the current extent * we reset the partial cluster because we've reached the start of the * truncated/punched region and we're done removing blocks. */ if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) { pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; if (partial->pclu != EXT4_B2C(sbi, pblk)) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } /* if this leaf is free, then we should * remove it from index block above */ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) err = ext4_ext_rm_idx(handle, inode, path, depth); out: return err; } /* * ext4_ext_more_to_rm: * returns 1 if current index has to be freed (even partial) */ static int ext4_ext_more_to_rm(struct ext4_ext_path *path) { BUG_ON(path->p_idx == NULL); if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr)) return 0; /* * if truncate on deeper level happened, it wasn't partial, * so we have to consider current index for truncation */ if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block) return 0; return 1; } int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; int flags = EXT4_EX_NOCACHE | EXT4_EX_NOFAIL; partial.pclu = 0; partial.lblk = 0; partial.state = initial; ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, depth + 1, ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); again: trace_ext4_ext_remove_space(inode, start, end, depth); /* * Check if we are removing extents inside the extent tree. If that * is the case, we are going to punch a hole inside the extent tree * so we have to check whether we need to split the extent covering * the last block to remove so we can easily remove the part of it * in ext4_ext_rm_leaf(). */ if (end < EXT_MAX_BLOCKS - 1) { struct ext4_extent *ex; ext4_lblk_t ee_block, ex_end, lblk; ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ path = ext4_find_extent(inode, end, NULL, flags); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); } depth = ext_depth(inode); /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; if (!ex) { if (depth) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; } goto out; } ee_block = le32_to_cpu(ex->ee_block); ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1; /* * See if the last block is inside the extent, if so split * the extent at 'end' block so we can easily remove the * tail of the first part of the split extent in * ext4_ext_rm_leaf(). */ if (end >= ee_block && end < ex_end) { /* * If we're going to split the extent, note that * the cluster containing the block after 'end' is * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } /* * Split the extent in two so that 'end' is the last * block in the first new extent. Also we should not * fail removing space due to ENOSPC so try to use * reserved block if that happens. */ path = ext4_force_split_extent_at(handle, inode, path, end + 1, 1); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } } else if (sbi->s_cluster_ratio > 1 && end >= ex_end && partial.state == initial) { /* * If we're punching, there's an extent to the right. * If the partial cluster hasn't been set, set it to * that extent's first cluster and its state to nofree * so it won't be freed should it contain blocks to be * removed. If it's already set (tofree/nofree), we're * retrying and keep the original partial cluster info * so a cluster marked tofree as a result of earlier * extent removal is not lost. */ lblk = ex_end + 1; err = ext4_ext_search_right(inode, path, &lblk, &pblk, NULL, flags); if (err < 0) goto out; if (pblk) { partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } } } /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); if (path) { int k = i = depth; while (--k > 0) path[k].p_block = le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS | __GFP_NOFAIL); if (path == NULL) { ext4_journal_stop(handle); return -ENOMEM; } path[0].p_maxdepth = path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { err = -EFSCORRUPTED; goto out; } } err = 0; while (i >= 0 && err == 0) { if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ ext4_ext_path_brelse(path + i); i--; continue; } /* this is index block */ if (!path[i].p_hdr) { ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } if (!path[i].p_idx) { /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { /* we were already here, see at next index */ path[i].p_idx--; } ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); bh = read_extent_tree_block(inode, path[i].p_idx, depth - i - 1, flags); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); break; } /* Yield here to deal with large extent trees. * Should be a no-op if we did IO above. */ cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EFSCORRUPTED; break; } path[i + 1].p_bh = bh; /* save actual number of indexes since this * number is changed at the next iteration */ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries); i++; } else { /* we finished processing this index, go up */ if (path[i].p_hdr->eh_entries == 0 && i > 0) { /* index is empty, remove it; * handle must be already prepared by the * truncatei_leaf() */ err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ ext4_ext_path_brelse(path + i); i--; ext_debug(inode, "return to level %d\n", i); } } trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial, path->p_hdr->eh_entries); /* * if there's a partial cluster and we have removed the first extent * in the file, then we also free the partial cluster, if any */ if (partial.state == tofree && err == 0) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial.lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial.pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial.lblk); partial.state = initial; } /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* * truncate to zero freed all the tree, * so we need to correct eh_depth */ err = ext4_ext_get_access(handle, inode, path); if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } out: ext4_free_ext_path(path); path = NULL; if (err == -EAGAIN) goto again; ext4_journal_stop(handle); return err; } /* * called at mount time */ void ext4_ext_init(struct super_block *sb) { /* * possible initialization would be here */ if (ext4_has_feature_extents(sb)) { #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled" #ifdef AGGRESSIVE_TEST ", aggressive tests" #endif #ifdef CHECK_BINSEARCH ", check binsearch" #endif #ifdef EXTENTS_STATS ", stats" #endif "\n"); #endif #ifdef EXTENTS_STATS spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); EXT4_SB(sb)->s_ext_min = 1 << 30; EXT4_SB(sb)->s_ext_max = 0; #endif } } /* * called at umount time */ void ext4_ext_release(struct super_block *sb) { if (!ext4_has_feature_extents(sb)) return; #ifdef EXTENTS_STATS if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) { struct ext4_sb_info *sbi = EXT4_SB(sb); printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n", sbi->s_ext_blocks, sbi->s_ext_extents, sbi->s_ext_blocks / sbi->s_ext_extents); printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n", sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max); } #endif } static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) { ext4_lblk_t ee_block; ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); if (ee_len == 0) return; ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, EXTENT_STATUS_WRITTEN, false); } /* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, ee_len); } /* * ext4_split_extent_at() splits an extent at given block. * * @handle: the journal handle * @inode: the file inode * @path: the path to the extent * @split: the logical block where the extent is splitted. * @split_flags: indicates if the extent could be zeroout if split fails, and * the states(init or unwritten) of new extents. * @flags: flags used to insert new extent to extent tree. * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. * b> split is not needed, and just mark the extent. * * Return an extent path pointer on success, or an error pointer on failure. */ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t split, int split_flag, int flags) { ext4_fsblk_t newblock; ext4_lblk_t ee_block; struct ext4_extent *ex, newex, orig_ex, zero_ex; struct ext4_extent *ex2 = NULL; unsigned int ee_len, depth; int err = 0; BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); newblock = split - ee_block + ext4_ext_pblock(ex); BUG_ON(split < ee_block || split >= (ee_block + ee_len)); BUG_ON(!ext4_ext_is_unwritten(ex) && split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (split == ee_block) { /* * case b: block @split is the block that the extent begins with * then we just change the state of the extent, and splitting * is not needed. */ if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } /* case a */ memcpy(&orig_ex, ex, sizeof(orig_ex)); ex->ee_len = cpu_to_le16(split - ee_block); if (split_flag & EXT4_EXT_MARK_UNWRIT1) ext4_ext_mark_unwritten(ex); /* * path may lead to new leaf, not to original leaf any more * after ext4_ext_insert_extent() returns, */ err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto fix_extent_len; ex2 = &newex; ex2->ee_block = cpu_to_le32(split); ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block)); ext4_ext_store_pblock(ex2, newblock); if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex2); path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (!IS_ERR(path)) goto out; err = PTR_ERR(path); if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM) return path; /* * Get a new path to try to zeroout or fix the extent length. * Using EXT4_EX_NOFAIL guarantees that ext4_find_extent() * will not return -ENOMEM, otherwise -ENOMEM will cause a * retry in do_writepages(), and a WARN_ON may be triggered * in ext4_da_update_reserve_space() due to an incorrect * ee_len causing the i_reserved_data_blocks exception. */ path = ext4_find_extent(inode, ee_block, NULL, flags | EXT4_EX_NOFAIL); if (IS_ERR(path)) { EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %ld", split, PTR_ERR(path)); return path; } depth = ext_depth(inode); ex = path[depth].p_ext; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); zero_ex.ee_block = ex2->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex2)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex2)); } else { err = ext4_ext_zeroout(inode, ex); zero_ex.ee_block = ex->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); } } else { err = ext4_ext_zeroout(inode, &orig_ex); zero_ex.ee_block = orig_ex.ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(&orig_ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(&orig_ex)); } if (!err) { /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (!err) /* update extent status tree */ ext4_zeroout_es(inode, &zero_ex); /* If we failed at this point, we don't know in which * state the extent tree exactly is so don't try to fix * length of the original extent as it may do even more * damage. */ goto out; } } fix_extent_len: ex->ee_len = orig_ex.ee_len; /* * Ignore ext4_ext_dirty return value since we are already in error path * and err is a non-zero error code. */ ext4_ext_dirty(handle, inode, path + path->p_depth); out: if (err) { ext4_free_ext_path(path); path = ERR_PTR(err); } ext4_ext_show_leaf(inode, path); return path; } /* * ext4_split_extent() splits an extent and mark extent which is covered * by @map as split_flags indicates * * It may result in splitting the extent into multiple extents (up to three) * There are three possibilities: * a> There is no split required * b> Splits in two extents: Split is happening at either end of the extent * c> Splits in three extents: Somone is splitting in middle of the extent * */ static struct ext4_ext_path *ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_map_blocks *map, int split_flag, int flags, unsigned int *allocated) { ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len, depth; int unwritten; int split_flag1, flags1; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; if (unwritten) split_flag1 |= EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; if (split_flag & EXT4_EXT_DATA_VALID2) split_flag1 |= EXT4_EXT_DATA_VALID1; path = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, split_flag1, flags1); if (IS_ERR(path)) return path; /* * Update path is required because previous ext4_split_extent_at * may result in split of original leaf or extent zeroout. */ path = ext4_find_extent(inode, map->m_lblk, path, flags); if (IS_ERR(path)) return path; depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); ext4_free_ext_path(path); return ERR_PTR(-EFSCORRUPTED); } unwritten = ext4_ext_is_unwritten(ex); } if (map->m_lblk >= ee_block) { split_flag1 = split_flag & EXT4_EXT_DATA_VALID2; if (unwritten) { split_flag1 |= EXT4_EXT_MARK_UNWRIT1; split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT2); } path = ext4_split_extent_at(handle, inode, path, map->m_lblk, split_flag1, flags); if (IS_ERR(path)) return path; } if (allocated) { if (map->m_lblk + map->m_len > ee_block + ee_len) *allocated = ee_len - (map->m_lblk - ee_block); else *allocated = map->m_len; } ext4_ext_show_leaf(inode, path); return path; } /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an unwritten extent. It may result in splitting the unwritten * extent into multiple extents (up to three - one initialized and two * unwritten). * There are three possibilities: * a> There is no split required: Entire extent should be initialized * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * Pre-conditions: * - The extent pointed to by 'path' is unwritten. * - The extent pointed to by 'path' contains a superset * of the logical span [map->m_lblk, map->m_lblk + map->m_len). * * Post-conditions on success: * - the returned value is the number of blocks beyond map->l_lblk * that are allocated and initialized. * It is guaranteed to be >= map->m_len. */ static struct ext4_ext_path * ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex1, zero_ex2; struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; int err = 0; int split_flag = EXT4_EXT_DATA_VALID2; unsigned int max_zeroout = 0; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); zero_ex1.ee_len = 0; zero_ex2.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); /* Pre-conditions */ BUG_ON(!ext4_ext_is_unwritten(ex)); BUG_ON(!in_range(map->m_lblk, ee_block, ee_len)); /* * Attempt to transfer newly initialized blocks from the currently * unwritten extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly * memmove() calls. Transferring to the left is the common case in * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) * followed by append writes. * * Limitations of the current logic: * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ *allocated = 0; if ((map->m_lblk == ee_block) && /* See if we can merge left */ (map_len < ee_len) && /*L1*/ (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; unsigned int prev_len; abut_ex = ex - 1; prev_lblk = le32_to_cpu(abut_ex->ee_block); prev_len = ext4_ext_get_actual_len(abut_ex); prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of ex by 'map_len' blocks */ ex->ee_block = cpu_to_le32(ee_block + map_len); ext4_ext_store_pblock(ex, ee_pblk + map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ *allocated = map_len; } } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && (map_len < ee_len) && /*L1*/ ex < EXT_LAST_EXTENT(eh)) { /*L2*/ /* See if we can merge right */ ext4_lblk_t next_lblk; ext4_fsblk_t next_pblk, ee_pblk; unsigned int next_len; abut_ex = ex + 1; next_lblk = le32_to_cpu(abut_ex->ee_block); next_len = ext4_ext_get_actual_len(abut_ex); next_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((map->m_lblk + map_len) == next_lblk) && /*C2*/ ((ee_pblk + ee_len) == next_pblk) && /*C3*/ (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of abut_ex by 'map_len' blocks */ abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); ext4_ext_store_pblock(abut_ex, next_pblk - map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ *allocated = map_len; } } if (*allocated) { /* Mark the block containing both extents as dirty */ err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; if (err) goto errout; goto out; } else *allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; if (EXT4_EXT_MAY_ZEROOUT & split_flag) max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); /* * five cases: * 1. split the extent into three extents. * 2. split the extent into two extents, zeroout the head of the first * extent. * 3. split the extent into two extents, zeroout the tail of the second * extent. * 4. split the extent into two extents with out zeroout. * 5. no splitting needed, just possibly zeroout the head and / or the * tail of the extent. */ split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; if (max_zeroout && (*allocated > split_map.m_len)) { if (*allocated <= max_zeroout) { /* case 3 or 5 */ zero_ex1.ee_block = cpu_to_le32(split_map.m_lblk + split_map.m_len); zero_ex1.ee_len = cpu_to_le16(*allocated - split_map.m_len); ext4_ext_store_pblock(&zero_ex1, ext4_ext_pblock(ex) + split_map.m_lblk + split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) goto fallback; split_map.m_len = *allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < max_zeroout) { /* case 2 or 5 */ if (split_map.m_lblk != ee_block) { zero_ex2.ee_block = ex->ee_block; zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk - ee_block); ext4_ext_store_pblock(&zero_ex2, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) goto fallback; } split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; *allocated = map->m_len; } } fallback: path = ext4_split_extent(handle, inode, path, &split_map, split_flag, flags, NULL); if (IS_ERR(path)) return path; out: /* If we have gotten a failure, don't zero out status tree */ ext4_zeroout_es(inode, &zero_ex1); ext4_zeroout_es(inode, &zero_ex2); return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * This function is called by ext4_ext_map_blocks() from * ext4_get_blocks_dio_write() when DIO to write * to an unwritten extent. * * Writing to an unwritten extent may result in splitting the unwritten * extent into multiple initialized/unwritten extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be unwritten * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * This works the same way in the case of initialized -> unwritten conversion. * * One of more index blocks maybe needed if the extent tree grow after * the unwritten extent split. To prevent ENOSPC occur at the IO * complete, we need to split the unwritten extent before DIO submit * the IO. The unwritten extent called at this time will be split * into three unwritten extent(at most). After IO complete, the part * being filled will be convert to initialized by the end_io callback function * via ext4_convert_unwritten_extents(). * * The size of unwritten extent to be written is passed to the caller via the * allocated pointer. Return an extent path pointer on success, or an error * pointer on failure. */ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { ext4_lblk_t eof_block; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len; int split_flag = 0, depth; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); /* Convert to unwritten */ if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { split_flag |= EXT4_EXT_DATA_VALID1; /* Convert to initialized */ } else if (flags & EXT4_GET_BLOCKS_CONVERT) { split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2); } flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, path, map, split_flag, flags, allocated); } static struct ext4_ext_path * ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path) { struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); /* If extent is larger than requested it is a clear sign that we still * have some extent state machine issues left. So extent_split is still * required. * TODO: Once all related issues will be fixed this situation should be * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { #ifdef CONFIG_EXT4_DEBUG ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); #endif path = ext4_split_convert_extents(handle, inode, map, path, EXT4_GET_BLOCKS_CONVERT, NULL); if (IS_ERR(path)) return path; path = ext4_find_extent(inode, map->m_lblk, path, 0); if (IS_ERR(path)) return path; depth = ext_depth(inode); ex = path[depth].p_ext; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; /* first mark the extent as initialized */ ext4_ext_mark_initialized(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) goto errout; ext4_ext_show_leaf(inode, path); return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } static struct ext4_ext_path * convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, unsigned int *allocated) { struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; /* * Make sure that the extent is no bigger than we support with * unwritten extent */ if (map->m_len > EXT_UNWRITTEN_MAX_LEN) map->m_len = EXT_UNWRITTEN_MAX_LEN / 2; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); if (ee_block != map->m_lblk || ee_len > map->m_len) { path = ext4_split_convert_extents(handle, inode, map, path, EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, NULL); if (IS_ERR(path)) return path; path = ext4_find_extent(inode, map->m_lblk, path, 0); if (IS_ERR(path)) return path; depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); err = -EFSCORRUPTED; goto errout; } } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; /* first mark the extent as unwritten */ ext4_ext_mark_unwritten(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) goto errout; ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); map->m_flags |= EXT4_MAP_UNWRITTEN; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } static struct ext4_ext_path * ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated, ext4_fsblk_t newblock) { int err = 0; ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", (unsigned long long)map->m_lblk, map->m_len, flags, *allocated); ext4_ext_show_leaf(inode, path); /* * When writing into unwritten space, we should not fail to * allocate metadata blocks for the new extent block if needed. */ flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; trace_ext4_ext_handle_unwritten_extents(inode, map, flags, *allocated, newblock); /* get_block() before submitting IO, split the extent */ if (flags & EXT4_GET_BLOCKS_PRE_IO) { path = ext4_split_convert_extents(handle, inode, map, path, flags | EXT4_GET_BLOCKS_CONVERT, allocated); if (IS_ERR(path)) return path; /* * shouldn't get a 0 allocated when splitting an extent unless * m_len is 0 (bug) or extent has been corrupted */ if (unlikely(*allocated == 0)) { EXT4_ERROR_INODE(inode, "unexpected allocated == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto errout; } map->m_flags |= EXT4_MAP_UNWRITTEN; goto out; } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { path = ext4_convert_unwritten_extents_endio(handle, inode, map, path); if (IS_ERR(path)) return path; ext4_update_inode_fsync_trans(handle, inode, 1); goto map_out; } /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { map->m_flags |= EXT4_MAP_UNWRITTEN; goto map_out; } /* buffered READ or buffered write_begin() lookup */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * We have blocks reserved already. We * return allocated blocks so that delalloc * won't do block reservation for us. But * the buffer head will be unmapped so that * a read from the block returns 0s. */ map->m_flags |= EXT4_MAP_UNWRITTEN; goto out1; } /* * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. * For buffered writes, at writepage time, etc. Convert a * discovered unwritten extent to written. */ path = ext4_ext_convert_to_initialized(handle, inode, map, path, flags, allocated); if (IS_ERR(path)) return path; ext4_update_inode_fsync_trans(handle, inode, 1); /* * shouldn't get a 0 allocated when converting an unwritten extent * unless m_len is 0 (bug) or extent has been corrupted */ if (unlikely(*allocated == 0)) { EXT4_ERROR_INODE(inode, "unexpected allocated == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto errout; } out: map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; out1: map->m_pblk = newblock; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; ext4_ext_show_leaf(inode, path); return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation * * This function is called by ext4_ext_map_blocks() after we failed to * find blocks that were already in the inode's extent tree. Hence, * we know that the beginning of the requested region cannot overlap * the extent from the inode's extent tree. There are three cases we * want to catch. The first is this case: * * |--- cluster # N--| * |--- extent ---| |---- requested region ---| * |==========| * * The second case that we need to test for is this one: * * |--------- cluster # N ----------------| * |--- requested region --| |------- extent ----| * |=======================| * * The third case is when the requested region lies between two extents * within the same cluster: * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| * * In each of the above cases, we need to set the map->m_pblk and * map->m_len so it corresponds to the return the extent labelled as * "|====|" from cluster #N, since it is already in use for data in * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to * signal to ext4_ext_map_blocks() that map->m_pblk should be treated * as a new "allocated" block region. Otherwise, we will return 0 and * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len = ext4_ext_get_actual_len(ex); /* The extent passed in that we are trying to match */ ex_cluster_start = EXT4_B2C(sbi, ee_block); ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1); /* The requested region passed into ext4_map_blocks() */ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk); if ((rr_cluster_start == ex_cluster_end) || (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* * Check for and handle this case: * * |--------- cluster # N-------------| * |------- extent ----| * |--- requested region ---| * |===========| */ if (map->m_lblk < ee_block) map->m_len = min(map->m_len, ee_block - map->m_lblk); /* * Check for the case where there is already another allocated * block to the right of 'ex' but before the end of the cluster. * * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| */ if (map->m_lblk > ee_block) { ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } /* * Determine hole length around the given logical block, first try to * locate and expand the hole from the given @path, and then adjust it * if it's partially or completely converted to delayed extents, insert * it into the extent cache tree if it's indeed a hole, finally return * the length of the determined extent. */ static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t lblk) { ext4_lblk_t hole_start, len; struct extent_status es; hole_start = lblk; len = ext4_ext_find_hole(inode, path, &hole_start); again: ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, hole_start + len - 1, &es); if (!es.es_len) goto insert_hole; /* * There's a delalloc extent in the hole, handle it if the delalloc * extent is in front of, behind and straddle the queried range. */ if (lblk >= es.es_lblk + es.es_len) { /* * The delalloc extent is in front of the queried range, * find again from the queried start block. */ len -= lblk - hole_start; hole_start = lblk; goto again; } else if (in_range(lblk, es.es_lblk, es.es_len)) { /* * The delalloc extent containing lblk, it must have been * added after ext4_map_blocks() checked the extent status * tree so we are not holding i_rwsem and delalloc info is * only stabilized by i_data_sem we are going to release * soon. Don't modify the extent status tree and report * extent as a hole, just adjust the length to the delalloc * extent's after lblk. */ len = es.es_lblk + es.es_len - lblk; return len; } else { /* * The delalloc extent is partially or completely behind * the queried range, update hole length until the * beginning of the delalloc extent. */ len = min(es.es_lblk - hole_start, len); } insert_hole: /* Put just found gap into cache to speed up subsequent requests */ ext_debug(inode, " -> %u:%u\n", hole_start, len); ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE, false); /* Update hole_len to reflect hole size after lblk */ if (hole_start != lblk) len -= lblk - hole_start; return len; } /* * Block allocation/map/preallocation routine for extents based files * * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, flags is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) * * return > 0, number of blocks already mapped/allocated * if flags doesn't contain EXT4_GET_BLOCKS_CREATE and these are pre-allocated blocks * buffer head is unmapped * otherwise blocks are mapped * * return = 0, if plain look up failed (blocks have not been allocated) * buffer head is unmapped * * return < 0, error case. */ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent newex, *ex, ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0, pblk; int err = 0, depth; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ path = ext4_find_extent(inode, map->m_lblk, NULL, flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } depth = ext_depth(inode); /* * consistent leaf must not be empty; * this situation is possible, though, _during_ tree modification; * this is why assert can't be put in ext4_find_extent() */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address " "lblock: %lu, depth: %d pblock %lld", (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } ex = path[depth].p_ext; if (ex) { ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; /* * unwritten extents are treated as holes, except that * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); ext_debug(inode, "%u fit into %u:%d -> %llu\n", map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the * caller wants to convert it to unwritten. */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { path = convert_initialized_extent(handle, inode, map, path, &allocated); if (IS_ERR(path)) err = PTR_ERR(path); goto out; } else if (!ext4_ext_is_unwritten(ex)) { map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, path); goto out; } path = ext4_ext_handle_unwritten_extents( handle, inode, map, path, flags, &allocated, newblock); if (IS_ERR(path)) err = PTR_ERR(path); goto out; } } /* * requested block isn't allocated yet; * we couldn't try to create block if flags doesn't contain EXT4_GET_BLOCKS_CREATE */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { ext4_lblk_t len; len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, len); goto out; } /* * Okay, we need to do block allocation. */ newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned * by ext4_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* find neighbour allocated blocks */ ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) goto out; ar.lright = map->m_lblk; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2, flags); if (err < 0) goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && err && get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; err = 0; goto got_allocated_blocks; } /* * See if request is beyond maximum number of blocks we can have in * a single extent. For an initialized extent this limit is * EXT_INIT_MAX_LEN and for an unwritten extent this limit is * EXT_UNWRITTEN_MAX_LEN. */ if (map->m_len > EXT_INIT_MAX_LEN && !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_INIT_MAX_LEN; else if (map->m_len > EXT_UNWRITTEN_MAX_LEN && (flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_UNWRITTEN_MAX_LEN; /* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */ newex.ee_len = cpu_to_le16(map->m_len); err = ext4_ext_check_overlap(sbi, inode, &newex, path); if (err) allocated = ext4_ext_get_actual_len(&newex); else allocated = map->m_len; /* allocate new block */ ar.inode = inode; ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk); ar.logical = map->m_lblk; /* * We calculate the offset from the beginning of the cluster * for the logical block number, since when we allocate a * physical cluster, the physical block should start at the * same offset from the beginning of the cluster. This is * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; if (S_ISREG(inode->i_mode)) ar.flags = EXT4_MB_HINT_DATA; else /* disable in-core preallocation for non-regular files */ ar.flags = 0; if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE) ar.flags |= EXT4_MB_HINT_NOPREALLOC; if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ar.flags |= EXT4_MB_DELALLOC_RESERVED; if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ pblk = newblock + offset; ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (IS_ERR(path)) { err = PTR_ERR(path); if (allocated_clusters) { int fb_flags = 0; /* * free data blocks we just allocated. * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ ext4_discard_preallocations(inode); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, EXT4_C2B(sbi, allocated_clusters), fb_flags); } goto out; } /* * Cache the extent and update transaction to commit on fdatasync only * when it is _not_ an unwritten extent. */ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0) ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); map->m_pblk = pblk; map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); out: /* * We never use EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF with CREATE flag. * So we know that the depth used here is correct, since there was no * block allocation done if EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF is set. * If tomorrow we start using this QUERY flag with CREATE, then we will * need to re-calculate the depth as it might have changed due to block * allocation. */ if (flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) { WARN_ON_ONCE(flags & EXT4_GET_BLOCKS_CREATE); if (!err && ex && (ex == EXT_LAST_EXTENT(path[depth].p_hdr))) map->m_flags |= EXT4_MAP_QUERY_LAST_IN_LEAF; } ext4_free_ext_path(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); return err ? err : allocated; } int ext4_ext_truncate(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; int err = 0; /* * TODO: optimization is possible here. * Probably we need not scan at all, * because page truncation is enough. */ /* we have to know where to truncate from in crash case */ EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_mark_inode_dirty(handle, inode); if (err) return err; last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { memalloc_retry_wait(GFP_ATOMIC); goto retry_remove_space; } return err; } static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, ext4_lblk_t len, loff_t new_size, int flags) { struct inode *inode = file_inode(file); handle_t *handle; int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; unsigned int credits; loff_t epos, old_size = i_size_read(inode); BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)); map.m_lblk = offset; map.m_len = len; /* * Don't normalize the request if it can fit in one extent so * that it doesn't get unnecessarily split into multiple * extents. */ if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); retry: while (len) { /* * Recalculate credits when extent tree depth changes. */ if (depth != ext_depth(inode)) { credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); } handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { ext4_debug("inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); break; } /* * allow a full retry cycle for any remaining allocations */ retries = 0; map.m_lblk += ret; map.m_len = len = len - ret; epos = (loff_t)map.m_lblk << inode->i_blkbits; inode_set_ctime_current(inode); if (new_size) { if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) inode_set_mtime_to_ts(inode, inode_get_ctime(inode)); if (epos > old_size) { pagecache_isize_extended(inode, old_size, epos); ext4_zero_partial_blocks(handle, inode, old_size, epos - old_size); } } ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); ret3 = ext4_journal_stop(handle); ret2 = ret3 ? ret3 : ret2; if (unlikely(ret2)) break; } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return ret > 0 ? ret2 : ret; } static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); handle_t *handle = NULL; loff_t new_size = 0; loff_t end = offset + len; ext4_lblk_t start_lblk, end_lblk; unsigned int blocksize = i_blocksize(inode); unsigned int blkbits = inode->i_blkbits; int ret, flags, credits; trace_ext4_zero_range(inode, offset, len, mode); WARN_ON_ONCE(!inode_is_locked(inode)); /* Indirect files do not support unwritten extents */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EOPNOTSUPP; if (!(mode & FALLOC_FL_KEEP_SIZE) && (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { new_size = end; ret = inode_newsize_ok(inode, new_size); if (ret) return ret; } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; /* Preallocate the range including the unaligned edges */ if (!IS_ALIGNED(offset | end, blocksize)) { ext4_lblk_t alloc_lblk = offset >> blkbits; ext4_lblk_t len_lblk = EXT4_MAX_BLOCKS(len, offset, blkbits); ret = ext4_alloc_file_blocks(file, alloc_lblk, len_lblk, new_size, flags); if (ret) return ret; } ret = ext4_update_disksize_before_punch(inode, offset, len); if (ret) return ret; /* Now release the pages and zero block aligned part of pages */ ret = ext4_truncate_page_cache_block_range(inode, offset, end); if (ret) return ret; /* Zero range excluding the unaligned edges */ start_lblk = EXT4_B_TO_LBLK(inode, offset); end_lblk = end >> blkbits; if (end_lblk > start_lblk) { ext4_lblk_t zero_blks = end_lblk - start_lblk; flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); ret = ext4_alloc_file_blocks(file, start_lblk, zero_blks, new_size, flags); if (ret) return ret; } /* Finish zeroing out if it doesn't contain partial block */ if (IS_ALIGNED(offset | end, blocksize)) return ret; /* * In worst case we have to writeout two nonadjacent unwritten * blocks and update the inode */ credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1; if (ext4_should_journal_data(inode)) credits += 2; handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); return ret; } /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); if (ret) goto out_handle; if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } static long ext4_do_fallocate(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); loff_t end = offset + len; loff_t new_size = 0; ext4_lblk_t start_lblk, len_lblk; int ret; trace_ext4_fallocate_enter(inode, offset, len, mode); WARN_ON_ONCE(!inode_is_locked(inode)); start_lblk = offset >> inode->i_blkbits; len_lblk = EXT4_MAX_BLOCKS(len, offset, inode->i_blkbits); /* We only support preallocation for extent-based files only. */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { new_size = end; ret = inode_newsize_ok(inode, new_size); if (ret) goto out; } ret = ext4_alloc_file_blocks(file, start_lblk, len_lblk, new_size, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); if (ret) goto out; if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, EXT4_I(inode)->i_sync_tid); } out: trace_ext4_fallocate_exit(inode, offset, len_lblk, ret); return ret; } /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. * For block-mapped files, posix_fallocate should fall back to the method * of writing zeroes to the required new blocks (the same behavior which is * expected for file systems which do not support fallocate() system call). */ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; int ret; /* * Encrypted inodes can't handle collapse range or insert * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). */ if (IS_ENCRYPTED(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; inode_lock(inode); ret = ext4_convert_inline_data(inode); if (ret) goto out_inode_lock; /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out_inode_lock; if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ALLOCATE_RANGE) { ret = ext4_do_fallocate(file, offset, len, mode); goto out_inode_lock; } /* * Follow-up operations will drop page cache, hold invalidate lock * to prevent page faults from reinstantiating pages we have * released from page cache. */ filemap_invalidate_lock(mapping); ret = ext4_break_layouts(inode); if (ret) goto out_invalidate_lock; if (mode & FALLOC_FL_PUNCH_HOLE) ret = ext4_punch_hole(file, offset, len); else if (mode & FALLOC_FL_COLLAPSE_RANGE) ret = ext4_collapse_range(file, offset, len); else if (mode & FALLOC_FL_INSERT_RANGE) ret = ext4_insert_range(file, offset, len); else if (mode & FALLOC_FL_ZERO_RANGE) ret = ext4_zero_range(file, offset, len, mode); else ret = -EOPNOTSUPP; out_invalidate_lock: filemap_invalidate_unlock(mapping); out_inode_lock: inode_unlock(inode); return ret; } /* * This function converts a range of blocks to written extents. The caller of * this function will pass the start offset and the size. all unwritten extents * within this range will be converted to written extents. * * This function is called from the direct IO end io call back function for * atomic writes, to convert the unwritten extents after IO is completed. * * Note that the requirement for atomic writes is that all conversion should * happen atomically in a single fs journal transaction. We mainly only allocate * unwritten extents either on a hole on a pre-exiting unwritten extent range in * ext4_map_blocks_atomic_write(). The only case where we can have multiple * unwritten extents in a range [offset, offset+len) is when there is a split * unwritten extent between two leaf nodes which was cached in extent status * cache during ext4_iomap_alloc() time. That will allow * ext4_map_blocks_atomic_write() to return the unwritten extent range w/o going * into the slow path. That means we might need a loop for conversion of this * unwritten extent split across leaf block within a single journal transaction. * Split extents across leaf nodes is a rare case, but let's still handle that * to meet the requirements of multi-fsblock atomic writes. * * Returns 0 on success. */ int ext4_convert_unwritten_extents_atomic(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; int flags = EXT4_GET_BLOCKS_IO_CONVERT_EXT | EXT4_EX_NOCACHE; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * TODO: An optimization can be added later by having an extent * status flag e.g. EXTENT_STATUS_SPLIT_LEAF. If we query that * it can tell if the extent in the cache is a split extent. * But for now let's assume pextents as 2 always. */ credits = ext4_meta_trans_blocks(inode, max_blocks, 2); } if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); return ret; } } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); ret = ext4_map_blocks(handle, inode, &map, flags); if (ret != max_blocks) ext4_msg(inode->i_sb, KERN_INFO, "inode #%lu: block %u: len %u: " "split block mapping found for atomic write, " "ret = %d", inode->i_ino, map.m_lblk, map.m_len, ret); if (ret <= 0) break; } ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " "returned %d or %d", inode->i_ino, map.m_lblk, map.m_len, ret, ret2); return ret > 0 ? ret2 : ret; } /* * This function convert a range of blocks to written extents * The caller of this function will pass the start offset and the size. * all unwritten extents within this range will be converted to * written extents. * * This function is called from the direct IO end io call back * function, to convert the fallocated extents after IO is completed. * Returns 0 on success. */ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, max_blocks); } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } } /* * Do not cache any unrelated extents, as it does not hold the * i_rwsem or invalidate_lock, which could corrupt the extent * status tree. */ ret = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_IO_CONVERT_EXT | EXT4_EX_NOCACHE); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) break; } return ret > 0 ? ret2 : ret; } int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) { int ret = 0, err = 0; struct ext4_io_end_vec *io_end_vec; /* * This is somewhat ugly but the idea is clear: When transaction is * reserved, everything goes into it. Otherwise we rather start several * smaller transactions for conversion of each extent separately. */ if (handle) { handle = ext4_journal_start_reserved(handle, EXT4_HT_EXT_CONVERT); if (IS_ERR(handle)) return PTR_ERR(handle); } list_for_each_entry(io_end_vec, &io_end->list_vec, list) { ret = ext4_convert_unwritten_extents(handle, io_end->inode, io_end_vec->offset, io_end_vec->size); if (ret) break; } if (handle) err = ext4_journal_stop(handle); return ret < 0 ? ret : err; } static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct ext4_iloc iloc; int offset; /* offset of xattr in inode */ error = ext4_get_inode_loc(inode, &iloc); if (error) return error; physical = (__u64)iloc.bh->b_blocknr << blockbits; offset = EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; brelse(iloc.bh); iomap_type = IOMAP_INLINE; } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; iomap_type = IOMAP_MAPPED; } else { /* no in-inode or external block for xattr, so return -ENOENT */ error = -ENOENT; goto out; } iomap->addr = physical; iomap->offset = 0; iomap->length = length; iomap->type = iomap_type; iomap->flags = 0; out: return error; } static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int error; error = ext4_iomap_xattr_fiemap(inode, iomap); if (error == 0 && (offset >= iomap->length)) error = -ENOENT; return error; } static const struct iomap_ops ext4_iomap_xattr_ops = { .iomap_begin = ext4_iomap_xattr_begin, }; static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) { u64 maxbytes = ext4_get_maxbytes(inode); if (*len == 0) return -EINVAL; if (start > maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; return 0; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { int error = 0; inode_lock_shared(inode); if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) goto unlock; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } /* * For bitmap files the maximum size limit could be smaller than * s_maxbytes, so check len here manually instead of just relying on the * generic check. */ error = ext4_fiemap_check_ranges(inode, start, &len); if (error) goto unlock; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; error = iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_xattr_ops); } else { error = iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops); } unlock: inode_unlock_shared(inode); return error; } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { ext4_lblk_t start_blk, len_blks; __u64 last_blk; int error = 0; if (ext4_has_inline_data(inode)) { int has_inline; down_read(&EXT4_I(inode)->xattr_sem); has_inline = ext4_has_inline_data(inode); up_read(&EXT4_I(inode)->xattr_sem); if (has_inline) return 0; } if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { inode_lock_shared(inode); error = ext4_ext_precache(inode); inode_unlock_shared(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } error = fiemap_prep(inode, fieinfo, start, &len, 0); if (error) return error; error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; if (last_blk >= EXT_MAX_BLOCKS) last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* * Walk the extent tree gathering extent information * and pushing extents back to the user. */ return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); } /* * ext4_ext_shift_path_extents: * Shift the extents of a path structure lying between path[depth].p_ext * and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells * if it is right shift or left shift operation. */ static int ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, struct inode *inode, handle_t *handle, enum SHIFT_DIRECTION SHIFT) { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; bool update = false; int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { if (depth == path->p_depth) { ex_start = path[depth].p_ext; if (!ex_start) return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); /* leaf + sb + inode */ credits = 3; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { update = true; /* extent tree + sb + inode */ credits = depth + 2; } restart_credits = ext4_writepage_trans_blocks(inode); err = ext4_datasem_ensure_credits(handle, inode, credits, restart_credits, 0); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { le32_add_cpu(&ex_start->ee_block, -shift); /* Try to merge to the left. */ if ((ex_start > EXT_FIRST_EXTENT(path[depth].p_hdr)) && ext4_ext_try_to_merge_right(inode, path, ex_start - 1)) ex_last--; else ex_start++; } else { le32_add_cpu(&ex_last->ee_block, shift); ext4_ext_try_to_merge_right(inode, path, ex_last); ex_last--; } } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; if (--depth < 0 || !update) break; } /* Update index too */ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (SHIFT == SHIFT_LEFT) le32_add_cpu(&path[depth].p_idx->ei_block, -shift); else le32_add_cpu(&path[depth].p_idx->ei_block, shift); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; /* we are done if current index is not a starting index */ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr)) break; depth--; } out: return err; } /* * ext4_ext_shift_extents: * All the extents which lies in the range from @start to the last allocated * block for the @inode are shifted either towards left or right (depending * upon @SHIFT) by @shift blocks. * On success, 0 is returned, error otherwise. */ static int ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_lblk_t start, ext4_lblk_t shift, enum SHIFT_DIRECTION SHIFT) { struct ext4_ext_path *path; int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) goto out; stop = le32_to_cpu(extent->ee_block); /* * For left shifts, make sure the hole on the left is big enough to * accommodate the shift. For right shifts, make sure the last extent * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { path = ext4_find_extent(inode, start - 1, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (extent) { ex_start = le32_to_cpu(extent->ee_block); ex_end = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { ex_start = 0; ex_end = 0; } if ((start == ex_start && shift > ex_start) || (shift > start - ex_end)) { ret = -EINVAL; goto out; } } else { if (shift > EXT_MAX_BLOCKS - (stop + ext4_ext_get_actual_len(extent))) { ret = -EINVAL; goto out; } } /* * In case of left shift, iterator points to start and it is increased * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ again: ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; if (tmp != EXT_MAX_BLOCKS) *iterator = tmp; /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator * becomes NULL to indicate the end of the loop. */ while (iterator && start <= stop) { path = ext4_find_extent(inode, *iterator, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); return -EFSCORRUPTED; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { /* Hole, move to the next extent */ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) { path[depth].p_ext++; } else { *iterator = ext4_ext_next_allocated_block(path); continue; } } tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; else { extent = EXT_LAST_EXTENT(path[depth].p_hdr); while (le32_to_cpu(extent->ee_block) >= start) extent--; if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) break; extent++; iterator = NULL; } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); /* iterator can be NULL which means we should break */ if (ret == -EAGAIN) goto again; if (ret) break; } out: ext4_free_ext_path(path); return ret; } /* * ext4_collapse_range: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; loff_t end = offset + len; ext4_lblk_t start_lblk, end_lblk; handle_t *handle; unsigned int credits; loff_t start, new_size; int ret; trace_ext4_collapse_range(inode, offset, len); WARN_ON_ONCE(!inode_is_locked(inode)); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Collapse range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ if (end >= inode->i_size) return -EINVAL; /* * Write tail of the last page before removed range and data that * will be shifted since they will get removed from the page cache * below. We are also protected from pages becoming dirty by * i_rwsem and invalidate_lock. * Need to round down offset to be aligned with page size boundary * for page size > block size. */ start = round_down(offset, PAGE_SIZE); ret = filemap_write_and_wait_range(mapping, start, offset); if (!ret) ret = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (ret) return ret; truncate_pagecache(inode, start); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); start_lblk = offset >> inode->i_blkbits; end_lblk = (offset + len) >> inode->i_blkbits; ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); ret = ext4_ext_remove_space(inode, start_lblk, end_lblk - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_handle; } ext4_discard_preallocations(inode); ret = ext4_ext_shift_extents(inode, handle, end_lblk, end_lblk - start_lblk, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_handle; } new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; up_write(&EXT4_I(inode)->i_data_sem); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } /* * ext4_insert_range: * This function implements the FALLOC_FL_INSERT_RANGE flag of fallocate. * The data blocks starting from @offset to the EOF are shifted by @len * towards right to create a hole in the @inode. Inode size is increased * by len bytes. * Returns 0 on success, error otherwise. */ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; struct ext4_ext_path *path; struct ext4_extent *extent; ext4_lblk_t start_lblk, len_lblk, ee_start_lblk = 0; unsigned int credits, ee_len; int ret, depth, split_flag = 0; loff_t start; trace_ext4_insert_range(inode, offset, len); WARN_ON_ONCE(!inode_is_locked(inode)); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Insert range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; /* Offset must be less than i_size */ if (offset >= inode->i_size) return -EINVAL; /* Check whether the maximum file size would be exceeded */ if (len > inode->i_sb->s_maxbytes - inode->i_size) return -EFBIG; /* * Write out all dirty pages. Need to round down to align start offset * to page size boundary for page size > block size. */ start = round_down(offset, PAGE_SIZE); ret = filemap_write_and_wait_range(mapping, start, LLONG_MAX); if (ret) return ret; truncate_pagecache(inode, start); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_handle; start_lblk = offset >> inode->i_blkbits; len_lblk = len >> inode->i_blkbits; ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); path = ext4_find_extent(inode, start_lblk, NULL, 0); if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); ret = PTR_ERR(path); goto out_handle; } depth = ext_depth(inode); extent = path[depth].p_ext; if (extent) { ee_start_lblk = le32_to_cpu(extent->ee_block); ee_len = ext4_ext_get_actual_len(extent); /* * If start_lblk is not the starting block of extent, split * the extent @start_lblk */ if ((start_lblk > ee_start_lblk) && (start_lblk < (ee_start_lblk + ee_len))) { if (ext4_ext_is_unwritten(extent)) split_flag = EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; path = ext4_split_extent_at(handle, inode, path, start_lblk, split_flag, EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_METADATA_NOFAIL); } if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); ret = PTR_ERR(path); goto out_handle; } } ext4_free_ext_path(path); ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); /* * if start_lblk lies in a hole which is at start of file, use * ee_start_lblk to shift extents */ ret = ext4_ext_shift_extents(inode, handle, max(ee_start_lblk, start_lblk), len_lblk, SHIFT_RIGHT); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } /** * ext4_swap_extents() - Swap extents between two inodes * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode * @lblk2: Start block for second inode * @count: Number of blocks to swap * @unwritten: Mark second inode's extents as unwritten after swap * @erp: Pointer to save error value * * This helper routine does exactly what is promise "swap extents". All other * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: * i_rwsem is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes */ int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int unwritten, int *erp) { struct ext4_ext_path *path1 = NULL; struct ext4_ext_path *path2 = NULL; int replaced_count = 0; BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem)); BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem)); BUG_ON(!inode_is_locked(inode1)); BUG_ON(!inode_is_locked(inode2)); ext4_es_remove_extent(inode1, lblk1, count); ext4_es_remove_extent(inode2, lblk2, count); while (count) { struct ext4_extent *ex1, *ex2, tmp_ex; ext4_lblk_t e1_blk, e2_blk; int e1_len, e2_len, len; int split = 0; path1 = ext4_find_extent(inode1, lblk1, path1, EXT4_EX_NOCACHE); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } path2 = ext4_find_extent(inode2, lblk2, path2, EXT4_EX_NOCACHE); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto errout; e1_blk = le32_to_cpu(ex1->ee_block); e2_blk = le32_to_cpu(ex2->ee_block); e1_len = ext4_ext_get_actual_len(ex1); e2_len = ext4_ext_get_actual_len(ex2); /* Hole handling */ if (!in_range(lblk1, e1_blk, e1_len) || !in_range(lblk2, e2_blk, e2_len)) { ext4_lblk_t next1, next2; /* if hole after extent, then go to next extent */ next1 = ext4_ext_next_allocated_block(path1); next2 = ext4_ext_next_allocated_block(path2); /* If hole before extent, then shift to that extent */ if (e1_blk > lblk1) next1 = e1_blk; if (e2_blk > lblk2) next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) goto errout; /* Move to the rightest boundary */ len = next1 - lblk1; if (len < next2 - lblk2) len = next2 - lblk2; if (len > count) len = count; lblk1 += len; lblk2 += len; count -= len; continue; } /* Prepare left boundary */ if (e1_blk < lblk1) { split = 1; path1 = ext4_force_split_extent_at(handle, inode1, path1, lblk1, 0); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } } if (e2_blk < lblk2) { split = 1; path2 = ext4_force_split_extent_at(handle, inode2, path2, lblk2, 0); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) continue; /* Prepare right boundary */ len = count; if (len > e1_blk + e1_len - lblk1) len = e1_blk + e1_len - lblk1; if (len > e2_blk + e2_len - lblk2) len = e2_blk + e2_len - lblk2; if (len != e1_len) { split = 1; path1 = ext4_force_split_extent_at(handle, inode1, path1, lblk1 + len, 0); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } } if (len != e2_len) { split = 1; path2 = ext4_force_split_extent_at(handle, inode2, path2, lblk2 + len, 0); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) continue; BUG_ON(e2_len != e1_len); *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth); if (unlikely(*erp)) goto errout; *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto errout; /* Both extents are fully inside boundaries. Swap it now */ tmp_ex = *ex1; ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2)); ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex)); ex1->ee_len = cpu_to_le16(e2_len); ex2->ee_len = cpu_to_le16(e1_len); if (unwritten) ext4_ext_mark_unwritten(ex2); if (ext4_ext_is_unwritten(&tmp_ex)) ext4_ext_mark_unwritten(ex1); ext4_ext_try_to_merge(handle, inode2, path2, ex2); ext4_ext_try_to_merge(handle, inode1, path1, ex1); *erp = ext4_ext_dirty(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto errout; *erp = ext4_ext_dirty(handle, inode1, path1 + path1->p_depth); /* * Looks scarry ah..? second inode already points to new blocks, * and it was successfully dirtied. But luckily error may happen * only due to journal error, so full transaction will be * aborted anyway. */ if (unlikely(*erp)) goto errout; lblk1 += len; lblk2 += len; replaced_count += len; count -= len; } errout: ext4_free_ext_path(path1); ext4_free_ext_path(path2); return replaced_count; } /* * ext4_clu_mapped - determine whether any block in a logical cluster has * been mapped to a physical cluster * * @inode - file containing the logical cluster * @lclu - logical cluster of interest * * Returns 1 if any block in the logical cluster is mapped, signifying * that a physical cluster has been allocated for it. Otherwise, * returns 0. Can also return negative error codes. Derived from * ext4_ext_map_blocks(). */ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_ext_path *path; int depth, mapped = 0, err = 0; struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; /* * if data can be stored inline, the logical cluster isn't * mapped - no physical clusters have been allocated, and the * file has no extents */ if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || ext4_has_inline_data(inode)) return 0; /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); /* * A consistent leaf must not be empty. This situation is possible, * though, _during_ tree modification, and it's why an assert can't * be put in ext4_find_extent(). */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address - lblock: %lu, depth: %d, pblock: %lld", (unsigned long) EXT4_C2B(sbi, lclu), depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } extent = path[depth].p_ext; /* can't be mapped if the extent tree is empty */ if (extent == NULL) goto out; first_lblk = le32_to_cpu(extent->ee_block); first_lclu = EXT4_B2C(sbi, first_lblk); /* * Three possible outcomes at this point - found extent spanning * the target cluster, to the left of the target cluster, or to the * right of the target cluster. The first two cases are handled here. * The last case indicates the target cluster is not mapped. */ if (lclu >= first_lclu) { last_lclu = EXT4_B2C(sbi, first_lblk + ext4_ext_get_actual_len(extent) - 1); if (lclu <= last_lclu) { mapped = 1; } else { first_lblk = ext4_ext_next_allocated_block(path); first_lclu = EXT4_B2C(sbi, first_lblk); if (lclu == first_lclu) mapped = 1; } } out: ext4_free_ext_path(path); return err ? err : mapped; } /* * Updates physical block address and unwritten status of extent * starting at lblk start and of len. If such an extent doesn't exist, * this function splits the extent tree appropriately to create an * extent like this. This function is called in the fast commit * replay path. Returns 0 on success and error on failure. */ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk) { struct ext4_ext_path *path; struct ext4_extent *ex; int ret; path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ret = -EFSCORRUPTED; goto out; } if (le32_to_cpu(ex->ee_block) != start || ext4_ext_get_actual_len(ex) != len) { /* We need to split this extent to match our extent first */ down_write(&EXT4_I(inode)->i_data_sem); path = ext4_force_split_extent_at(NULL, inode, path, start, 1); up_write(&EXT4_I(inode)->i_data_sem); if (IS_ERR(path)) { ret = PTR_ERR(path); goto out; } path = ext4_find_extent(inode, start, path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; WARN_ON(le32_to_cpu(ex->ee_block) != start); if (ext4_ext_get_actual_len(ex) != len) { down_write(&EXT4_I(inode)->i_data_sem); path = ext4_force_split_extent_at(NULL, inode, path, start + len, 1); up_write(&EXT4_I(inode)->i_data_sem); if (IS_ERR(path)) { ret = PTR_ERR(path); goto out; } path = ext4_find_extent(inode, start, path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; } } if (unwritten) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); ext4_ext_store_pblock(ex, pblk); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); out: ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return ret; } /* Try to shrink the extent tree */ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t old_cur, cur = 0; while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) return; ex = path[path->p_depth].p_ext; if (!ex) { ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return; } old_cur = cur; cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); if (cur <= old_cur) cur = old_cur + 1; ext4_ext_try_to_merge(NULL, inode, path, ex); down_write(&EXT4_I(inode)->i_data_sem); ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); ext4_mark_inode_dirty(NULL, inode); ext4_free_ext_path(path); } } /* Check if *cur is a hole and if it is, skip it */ static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; map.m_lblk = *cur; map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; if (ret != 0) return 0; *cur = *cur + map.m_len; return 0; } /* Count number of blocks used by this inode and update i_blocks */ int ext4_ext_replay_set_iblocks(struct inode *inode) { struct ext4_ext_path *path = NULL, *path2 = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int numblks = 0, i, ret = 0; ext4_fsblk_t cmp1, cmp2; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) goto out; end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); /* Count the number of data blocks */ cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) numblks += ret; cur = cur + map.m_len; } /* * Count the number of extent tree blocks. We do it by looking up * two successive extents and determining the difference between * their paths. When path is different for 2 successive extents * we compare the blocks in the path at each level and increment * iblocks by total number of differences found. */ cur = 0; ret = skip_hole(inode, &cur); if (ret < 0) goto out; path = ext4_find_extent(inode, cur, path, 0); if (IS_ERR(path)) goto out; numblks += path->p_depth; while (cur < end) { path = ext4_find_extent(inode, cur, path, 0); if (IS_ERR(path)) break; ex = path[path->p_depth].p_ext; if (!ex) goto cleanup; cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); ret = skip_hole(inode, &cur); if (ret < 0) break; path2 = ext4_find_extent(inode, cur, path2, 0); if (IS_ERR(path2)) break; for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { cmp1 = cmp2 = 0; if (i <= path->p_depth) cmp1 = path[i].p_bh ? path[i].p_bh->b_blocknr : 0; if (i <= path2->p_depth) cmp2 = path2[i].p_bh ? path2[i].p_bh->b_blocknr : 0; if (cmp1 != cmp2 && cmp2 != 0) numblks++; } } out: inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9); ext4_mark_inode_dirty(NULL, inode); cleanup: ext4_free_ext_path(path); ext4_free_ext_path(path2); return 0; } int ext4_ext_clear_bb(struct inode *inode) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int j, ret = 0; struct ext4_map_blocks map; if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) return 0; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) goto out; end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, path, 0); if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, 0, path[j].p_block, 1, 1); } } else { path = NULL; } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } out: ext4_free_ext_path(path); return 0; } |
| 4 4 4 1 3 1 2 4 4 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * udp_diag.c Module for monitoring UDP transport protocols sockets. * * Authors: Pavel Emelyanov, <xemul@parallels.com> */ #include <linux/module.h> #include <linux/inet_diag.h> #include <linux/udp.h> #include <net/udp.h> #include <net/udplite.h> #include <linux/sock_diag.h> static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct sk_buff *in_skb = cb->skb; int err; struct sock *sk = NULL; struct sk_buff *rep; struct net *net = sock_net(in_skb->sk); rcu_read_lock(); if (req->sdiag_family == AF_INET) /* src and dst are swapped for historical reasons */ sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #endif if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); if (err) goto out; err = -ENOMEM; rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + inet_diag_msg_attrs_size() + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; err = inet_sk_diag_fill(sk, NULL, rep, cb, req, 0, netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); goto out; } err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) sock_put(sk); out_nosk: return err; } static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; struct nlattr *bc; cb_data = cb->data; bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct udp_hslot *hslot = &table->hash[slot]; struct sock *sk; num = 0; if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next; if (!(r->idiag_states & (1 << sk->sk_state))) goto next; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next; if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next; if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } next: num++; } spin_unlock_bh(&hslot->lock); } done: cb->args[0] = slot; cb->args[1] = num; } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r); } static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *info) { r->idiag_rqueue = udp_rqueue_get(sk); r->idiag_wqueue = sk_wmem_alloc_get(sk); } #ifdef CONFIG_INET_DIAG_DESTROY static int __udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req, struct udp_table *tbl) { struct net *net = sock_net(in_skb->sk); struct sock *sk; int err; rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = __udp4_lib_lookup(net, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = __udp4_lib_lookup(net, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); else sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); } #endif else { rcu_read_unlock(); return -EINVAL; } if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); if (!sk) return -ENOENT; if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_put(sk); return -ENOENT; } err = sock_diag_destroy(sk, ECONNABORTED); sock_put(sk); return err; } static int udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table); } static int udplite_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, &udplite_table); } #endif static const struct inet_diag_handler udp_diag_handler = { .owner = THIS_MODULE, .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udp_diag_destroy, #endif }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(&udplite_table, skb, cb, r); } static int udplite_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(&udplite_table, cb, req); } static const struct inet_diag_handler udplite_diag_handler = { .owner = THIS_MODULE, .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udplite_diag_destroy, #endif }; static int __init udp_diag_init(void) { int err; err = inet_diag_register(&udp_diag_handler); if (err) goto out; err = inet_diag_register(&udplite_diag_handler); if (err) goto out_lite; out: return err; out_lite: inet_diag_unregister(&udp_diag_handler); goto out; } static void __exit udp_diag_exit(void) { inet_diag_unregister(&udplite_diag_handler); inet_diag_unregister(&udp_diag_handler); } module_init(udp_diag_init); module_exit(udp_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */); |
| 2477 285 1639 2 912 25 2293 1736 914 1737 1736 876 898 2561 8130 1476 825 349 160 155 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Operations on the network namespace */ #ifndef __NET_NET_NAMESPACE_H #define __NET_NET_NAMESPACE_H #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/sysctl.h> #include <linux/uidgid.h> #include <net/flow.h> #include <net/netns/core.h> #include <net/netns/mib.h> #include <net/netns/unix.h> #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> #include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) #include <net/netns/flow_table.h> #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> #include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> #include <linux/notifier.h> #include <linux/xarray.h> struct user_namespace; struct proc_dir_entry; struct net_device; struct sock; struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; struct bpf_prog; #define NETDEV_HASHBITS 8 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { /* First cache line can be often dirtied. * Do not place here read-mostly fields. */ refcount_t passive; /* To decide when the network * namespace should be freed. */ spinlock_t rules_mod_lock; unsigned int dev_base_seq; /* protected by rtnl_mutex */ u32 ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit * methods on dead net ( * pernet_ops_rwsem read locked), * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ struct list_head ptype_all; struct list_head ptype_specific; #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; struct idr netns_ids; struct ns_common ns; struct ref_tracker_dir refcnt_tracker; struct ref_tracker_dir notrefcnt_tracker; /* tracker for objects not * refcounted against netns */ struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; #ifdef CONFIG_SYSCTL struct ctl_table_set sysctls; #endif struct sock *rtnl; /* rtnetlink socket */ struct sock *genl_sock; struct uevent_sock *uevent_sock; /* uevent socket */ struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; struct xarray dev_by_index; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; struct netns_core core; struct netns_mib mib; struct netns_packet packet; #if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; #endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct netns_ieee802154_lowpan ieee802154_lowpan; #endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif #if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) struct netns_nftables nft; #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) struct netns_ft ft; #endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic __rcu *gen; /* Used to store attached BPF programs */ struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif #if IS_ENABLED(CONFIG_MPLS) struct netns_mpls mpls; #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; #endif #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif #if IS_ENABLED(CONFIG_MCTP) struct netns_mctp mctp; #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif #ifdef CONFIG_DEBUG_NET_SMALL_RTNL /* Move to a better place when the config guard is removed. */ struct mutex rtnl_mutex; #endif } __randomize_layout; #include <linux/seq_file_net.h> /* Init's network namespace */ extern struct net init_net; #ifdef CONFIG_NET_NS struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); extern struct task_struct *cleanup_net_task; #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> static inline struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) return ERR_PTR(-EINVAL); return old_net; } static inline void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } static inline void net_ns_barrier(void) {} static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } static inline struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); #else #define ipx_register_sysctl() #define ipx_unregister_sysctl() #endif #ifdef CONFIG_NET_NS void __put_net(struct net *net); /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); return net; } static inline struct net *maybe_get_net(struct net *net) { /* Used when we know struct net exists but we * aren't guaranteed a previous reference count * exists. If the reference count is zero this * function fails and returns NULL. */ if (!refcount_inc_not_zero(&net->ns.count)) net = NULL; return net; } /* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) __put_net(net); } static inline int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } static inline int check_net(const struct net *net) { return refcount_read(&net->ns.count) != 0; } void net_drop_ns(void *); void net_passive_dec(struct net *net); #else static inline struct net *get_net(struct net *net) { return net; } static inline void put_net(struct net *net) { } static inline struct net *maybe_get_net(struct net *net) { return net; } static inline int net_eq(const struct net *net1, const struct net *net2) { return 1; } static inline int check_net(const struct net *net) { return 1; } #define net_drop_ns NULL static inline void net_passive_dec(struct net *net) { refcount_dec(&net->passive); } #endif static inline void net_passive_inc(struct net *net) { refcount_inc(&net->passive); } /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { return READ_ONCE(net->list.next); } static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, bool refcounted, gfp_t gfp) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_alloc(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker, gfp); #endif } static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, gfp_t gfp) { __netns_tracker_alloc(net, tracker, true, gfp); } static inline void __netns_tracker_free(struct net *net, netns_tracker *tracker, bool refcounted) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_free(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker); #endif } static inline struct net *get_net_track(struct net *net, netns_tracker *tracker, gfp_t gfp) { get_net(net); netns_tracker_alloc(net, tracker, gfp); return net; } static inline void put_net_track(struct net *net, netns_tracker *tracker) { __netns_tracker_free(net, tracker, true); put_net(net); } typedef struct { #ifdef CONFIG_NET_NS struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference_protected(pnet->net, true); #else return &init_net; #endif } static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); #else return &init_net; #endif } /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) #define for_each_net_continue_reverse(VAR) \ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit #define __net_initdata #define __net_initconst #else #define __net_init __init #define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(const struct net *net, struct net *peer); bool peernet_has_id(const struct net *net, struct net *peer); struct net *get_net_ns_by_id(const struct net *net, int id); struct pernet_operations { struct list_head list; /* * Below methods are called without any exclusive locks. * More than one net may be constructed and destructed * in parallel on several cpus. Every pernet_operations * have to keep in mind all other pernet_operations and * to introduce a locking, if they share common resources. * * The only time they are called with exclusive lock is * from register_pernet_subsys(), unregister_pernet_subsys() * register_pernet_device() and unregister_pernet_device(). * * Exit methods using blocking RCU primitives, such as * synchronize_rcu(), should be implemented via exit_batch. * Then, destruction of a group of net requires single * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. * * Note that a combination of pre_exit() and exit() can * be used, since a synchronize_rcu() is guaranteed between * the calls. */ int (*init)(struct net *net); void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); /* Following method is called with RTNL held. */ void (*exit_rtnl)(struct net *net, struct list_head *dev_kill_list); unsigned int * const id; const size_t size; }; /* * Use these carefully. If you implement a network device and it * needs per network namespace operations use device pernet operations, * otherwise use pernet subsys operations. * * Network interfaces need to be removed from a dying netns _before_ * subsys notifiers can be called, as most of the network code cleanup * (which is done from subsys notifiers) runs with the assumption that * dev_remove_pack has been called so no new packets will arrive during * and after the cleanup functions have been called. dev_remove_pack * is not per namespace so instead the guarantee of no more packets * arriving in a network namespace is provided by ensuring that all * network devices and all sockets have left the network namespace * before the cleanup methods are called. * * For the longest time the ipv4 icmp code was registered as a pernet * device which caused kernel oops, and panics during network * namespace cleanup. So please don't get this wrong. */ int register_pernet_subsys(struct pernet_operations *); void unregister_pernet_subsys(struct pernet_operations *); int register_pernet_device(struct pernet_operations *); void unregister_pernet_device(struct pernet_operations *); struct ctl_table; #define register_net_sysctl(net, path, table) \ register_net_sysctl_sz(net, path, table, ARRAY_SIZE(table)) #ifdef CONFIG_SYSCTL int net_sysctl_init(void); struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size); void unregister_net_sysctl_table(struct ctl_table_header *header); #else static inline int net_sysctl_init(void) { return 0; } static inline struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { return NULL; } static inline void unregister_net_sysctl_table(struct ctl_table_header *header) { } #endif static inline int rt_genid_ipv4(const struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #if IS_ENABLED(CONFIG_IPV6) static inline int rt_genid_ipv6(const struct net *net) { return atomic_read(&net->ipv6.fib6_sernum); } #endif static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); } extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { if (__fib6_flush_trees) __fib6_flush_trees(net); } #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * net_ieee802154_lowpan(struct net *net) { return &net->ieee802154_lowpan; } #endif /* For callers who don't really care about whether it's IPv4 or IPv6 */ static inline void rt_genid_bump_all(struct net *net) { rt_genid_bump_ipv4(net); rt_genid_bump_ipv6(net); } static inline int fnhe_genid(const struct net *net) { return atomic_read(&net->fnhe_genid); } static inline void fnhe_genid_bump(struct net *net) { atomic_inc(&net->fnhe_genid); } #ifdef CONFIG_NET void net_ns_init(void); #else static inline void net_ns_init(void) {} #endif #endif /* __NET_NET_NAMESPACE_H */ |
| 13 13 13 13 13 13 6 6 14 14 13 14 14 7 6 7 21 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 | // SPDX-License-Identifier: GPL-2.0 /* * The Virtual DTV test driver serves as a reference DVB driver and helps * validate the existing APIs in the media subsystem. It can also aid * developers working on userspace applications. * * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' * and 'dvb_vidtv_demod'. * * Copyright (C) 2020 Daniel W. S. Almeida */ #include <linux/dev_printk.h> #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/time.h> #include <linux/types.h> #include <linux/workqueue.h> #include <media/dvbdev.h> #include <media/media-device.h> #include "vidtv_bridge.h" #include "vidtv_common.h" #include "vidtv_demod.h" #include "vidtv_mux.h" #include "vidtv_ts.h" #include "vidtv_tuner.h" #define MUX_BUF_MIN_SZ 90164 #define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) #define TUNER_DEFAULT_ADDR 0x68 #define DEMOD_DEFAULT_ADDR 0x60 #define VIDTV_DEFAULT_NETWORK_ID 0xff44 #define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org" #define VIDTV_DEFAULT_TS_ID 0x4081 /* * The LNBf fake parameters here are the ranges used by an * Universal (extended) European LNBf, which is likely the most common LNBf * found on Satellite digital TV system nowadays. */ #define LNB_CUT_FREQUENCY 11700000 /* high IF frequency */ #define LNB_LOW_FREQ 9750000 /* low IF frequency */ #define LNB_HIGH_FREQ 10600000 /* transition frequency */ static unsigned int drop_tslock_prob_on_low_snr; module_param(drop_tslock_prob_on_low_snr, uint, 0444); MODULE_PARM_DESC(drop_tslock_prob_on_low_snr, "Probability of losing the TS lock if the signal quality is bad"); static unsigned int recover_tslock_prob_on_good_snr; module_param(recover_tslock_prob_on_good_snr, uint, 0444); MODULE_PARM_DESC(recover_tslock_prob_on_good_snr, "Probability recovering the TS lock when the signal improves"); static unsigned int mock_power_up_delay_msec; module_param(mock_power_up_delay_msec, uint, 0444); MODULE_PARM_DESC(mock_power_up_delay_msec, "Simulate a power up delay"); static unsigned int mock_tune_delay_msec; module_param(mock_tune_delay_msec, uint, 0444); MODULE_PARM_DESC(mock_tune_delay_msec, "Simulate a tune delay"); static unsigned int vidtv_valid_dvb_t_freqs[NUM_VALID_TUNER_FREQS] = { 474000000 }; module_param_array(vidtv_valid_dvb_t_freqs, uint, NULL, 0444); MODULE_PARM_DESC(vidtv_valid_dvb_t_freqs, "Valid DVB-T frequencies to simulate, in Hz"); static unsigned int vidtv_valid_dvb_c_freqs[NUM_VALID_TUNER_FREQS] = { 474000000 }; module_param_array(vidtv_valid_dvb_c_freqs, uint, NULL, 0444); MODULE_PARM_DESC(vidtv_valid_dvb_c_freqs, "Valid DVB-C frequencies to simulate, in Hz"); static unsigned int vidtv_valid_dvb_s_freqs[NUM_VALID_TUNER_FREQS] = { 11362000 }; module_param_array(vidtv_valid_dvb_s_freqs, uint, NULL, 0444); MODULE_PARM_DESC(vidtv_valid_dvb_s_freqs, "Valid DVB-S/S2 frequencies to simulate at Ku-Band, in kHz"); static unsigned int max_frequency_shift_hz; module_param(max_frequency_shift_hz, uint, 0444); MODULE_PARM_DESC(max_frequency_shift_hz, "Maximum shift in HZ allowed when tuning in a channel"); DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nums); /* * Influences the signal acquisition time. See ISO/IEC 13818-1 : 2000. p. 113. */ static unsigned int si_period_msec = 40; module_param(si_period_msec, uint, 0444); MODULE_PARM_DESC(si_period_msec, "How often to send SI packets. Default: 40ms"); static unsigned int pcr_period_msec = 40; module_param(pcr_period_msec, uint, 0444); MODULE_PARM_DESC(pcr_period_msec, "How often to send PCR packets. Default: 40ms"); static unsigned int mux_rate_kbytes_sec = 4096; module_param(mux_rate_kbytes_sec, uint, 0444); MODULE_PARM_DESC(mux_rate_kbytes_sec, "Mux rate: will pad stream if below"); static unsigned int pcr_pid = 0x200; module_param(pcr_pid, uint, 0444); MODULE_PARM_DESC(pcr_pid, "PCR PID for all channels: defaults to 0x200"); static unsigned int mux_buf_sz_pkts; module_param(mux_buf_sz_pkts, uint, 0444); MODULE_PARM_DESC(mux_buf_sz_pkts, "Size for the internal mux buffer in multiples of 188 bytes"); static u32 vidtv_bridge_mux_buf_sz_for_mux_rate(void) { u32 max_elapsed_time_msecs = VIDTV_MAX_SLEEP_USECS / USEC_PER_MSEC; u32 mux_buf_sz = mux_buf_sz_pkts * TS_PACKET_LEN; u32 nbytes_expected; nbytes_expected = mux_rate_kbytes_sec; nbytes_expected *= max_elapsed_time_msecs; mux_buf_sz = roundup(nbytes_expected, TS_PACKET_LEN); mux_buf_sz += mux_buf_sz / 10; if (mux_buf_sz < MUX_BUF_MIN_SZ) mux_buf_sz = MUX_BUF_MIN_SZ; if (mux_buf_sz > MUX_BUF_MAX_SZ) mux_buf_sz = MUX_BUF_MAX_SZ; return mux_buf_sz; } static bool vidtv_bridge_check_demod_lock(struct vidtv_dvb *dvb, u32 n) { enum fe_status status; dvb->fe[n]->ops.read_status(dvb->fe[n], &status); return status == (FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK); } /* * called on a separate thread by the mux when new packets become available */ static void vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) { struct vidtv_dvb *dvb = priv; /* drop packets if we lose the lock */ if (vidtv_bridge_check_demod_lock(dvb, 0)) dvb_dmx_swfilter_packets(&dvb->demux, buf, npkts); } static int vidtv_start_streaming(struct vidtv_dvb *dvb) { struct vidtv_mux_init_args mux_args = { .mux_rate_kbytes_sec = mux_rate_kbytes_sec, .on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail, .pcr_period_usecs = pcr_period_msec * USEC_PER_MSEC, .si_period_usecs = si_period_msec * USEC_PER_MSEC, .pcr_pid = pcr_pid, .transport_stream_id = VIDTV_DEFAULT_TS_ID, .network_id = VIDTV_DEFAULT_NETWORK_ID, .network_name = VIDTV_DEFAULT_NETWORK_NAME, .priv = dvb, }; struct device *dev = &dvb->pdev->dev; u32 mux_buf_sz; if (dvb->streaming) { dev_warn_ratelimited(dev, "Already streaming. Skipping.\n"); return 0; } if (mux_buf_sz_pkts) mux_buf_sz = mux_buf_sz_pkts; else mux_buf_sz = vidtv_bridge_mux_buf_sz_for_mux_rate(); mux_args.mux_buf_sz = mux_buf_sz; dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args); if (!dvb->mux) return -ENOMEM; dvb->streaming = true; vidtv_mux_start_thread(dvb->mux); dev_dbg_ratelimited(dev, "Started streaming\n"); return 0; } static int vidtv_stop_streaming(struct vidtv_dvb *dvb) { struct device *dev = &dvb->pdev->dev; if (!dvb->streaming) { dev_warn_ratelimited(dev, "No streaming. Skipping.\n"); return 0; } dvb->streaming = false; vidtv_mux_stop_thread(dvb->mux); vidtv_mux_destroy(dvb->mux); dvb->mux = NULL; dev_dbg_ratelimited(dev, "Stopped streaming\n"); return 0; } static int vidtv_start_feed(struct dvb_demux_feed *feed) { struct dvb_demux *demux = feed->demux; struct vidtv_dvb *dvb = demux->priv; int ret; int rc; if (!demux->dmx.frontend) return -EINVAL; mutex_lock(&dvb->feed_lock); dvb->nfeeds++; rc = dvb->nfeeds; if (dvb->nfeeds == 1) { ret = vidtv_start_streaming(dvb); if (ret < 0) rc = ret; } mutex_unlock(&dvb->feed_lock); return rc; } static int vidtv_stop_feed(struct dvb_demux_feed *feed) { struct dvb_demux *demux = feed->demux; struct vidtv_dvb *dvb = demux->priv; int err = 0; mutex_lock(&dvb->feed_lock); dvb->nfeeds--; if (!dvb->nfeeds) err = vidtv_stop_streaming(dvb); mutex_unlock(&dvb->feed_lock); return err; } static struct dvb_frontend *vidtv_get_frontend_ptr(struct i2c_client *c) { struct vidtv_demod_state *state = i2c_get_clientdata(c); /* the demod will set this when its probe function runs */ return &state->frontend; } static int vidtv_master_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msgs[], int num) { /* * Right now, this virtual driver doesn't really send or receive * messages from I2C. A real driver will require an implementation * here. */ return 0; } static u32 vidtv_i2c_func(struct i2c_adapter *adapter) { return I2C_FUNC_I2C; } static const struct i2c_algorithm vidtv_i2c_algorithm = { .master_xfer = vidtv_master_xfer, .functionality = vidtv_i2c_func, }; static int vidtv_bridge_i2c_register_adap(struct vidtv_dvb *dvb) { struct i2c_adapter *i2c_adapter = &dvb->i2c_adapter; strscpy(i2c_adapter->name, "vidtv_i2c", sizeof(i2c_adapter->name)); i2c_adapter->owner = THIS_MODULE; i2c_adapter->algo = &vidtv_i2c_algorithm; i2c_adapter->algo_data = NULL; i2c_adapter->timeout = 500; i2c_adapter->retries = 3; i2c_adapter->dev.parent = &dvb->pdev->dev; i2c_set_adapdata(i2c_adapter, dvb); return i2c_add_adapter(&dvb->i2c_adapter); } static int vidtv_bridge_register_adap(struct vidtv_dvb *dvb) { int ret = 0; ret = dvb_register_adapter(&dvb->adapter, KBUILD_MODNAME, THIS_MODULE, &dvb->i2c_adapter.dev, adapter_nums); return ret; } static int vidtv_bridge_dmx_init(struct vidtv_dvb *dvb) { dvb->demux.dmx.capabilities = DMX_TS_FILTERING | DMX_SECTION_FILTERING; dvb->demux.priv = dvb; dvb->demux.filternum = 256; dvb->demux.feednum = 256; dvb->demux.start_feed = vidtv_start_feed; dvb->demux.stop_feed = vidtv_stop_feed; return dvb_dmx_init(&dvb->demux); } static int vidtv_bridge_dmxdev_init(struct vidtv_dvb *dvb) { dvb->dmx_dev.filternum = 256; dvb->dmx_dev.demux = &dvb->demux.dmx; dvb->dmx_dev.capabilities = 0; return dvb_dmxdev_init(&dvb->dmx_dev, &dvb->adapter); } static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n) { struct vidtv_demod_config cfg = { .drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr, .recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr, }; dvb->i2c_client_demod[n] = dvb_module_probe("dvb_vidtv_demod", NULL, &dvb->i2c_adapter, DEMOD_DEFAULT_ADDR, &cfg); /* driver will not work anyways so bail out */ if (!dvb->i2c_client_demod[n]) return -ENODEV; /* retrieve a ptr to the frontend state */ dvb->fe[n] = vidtv_get_frontend_ptr(dvb->i2c_client_demod[n]); return 0; } static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n) { struct vidtv_tuner_config cfg = { .fe = dvb->fe[n], .mock_power_up_delay_msec = mock_power_up_delay_msec, .mock_tune_delay_msec = mock_tune_delay_msec, }; u32 freq; int i; /* TODO: check if the frequencies are at a valid range */ memcpy(cfg.vidtv_valid_dvb_t_freqs, vidtv_valid_dvb_t_freqs, sizeof(vidtv_valid_dvb_t_freqs)); memcpy(cfg.vidtv_valid_dvb_c_freqs, vidtv_valid_dvb_c_freqs, sizeof(vidtv_valid_dvb_c_freqs)); /* * Convert Satellite frequencies from Ku-band in kHZ into S-band * frequencies in Hz. */ for (i = 0; i < ARRAY_SIZE(vidtv_valid_dvb_s_freqs); i++) { freq = vidtv_valid_dvb_s_freqs[i]; if (freq) { if (freq < LNB_CUT_FREQUENCY) freq = abs(freq - LNB_LOW_FREQ); else freq = abs(freq - LNB_HIGH_FREQ); } cfg.vidtv_valid_dvb_s_freqs[i] = freq; } cfg.max_frequency_shift_hz = max_frequency_shift_hz; dvb->i2c_client_tuner[n] = dvb_module_probe("dvb_vidtv_tuner", NULL, &dvb->i2c_adapter, TUNER_DEFAULT_ADDR, &cfg); return (dvb->i2c_client_tuner[n]) ? 0 : -ENODEV; } static int vidtv_bridge_dvb_init(struct vidtv_dvb *dvb) { int ret, i, j; ret = vidtv_bridge_i2c_register_adap(dvb); if (ret < 0) goto fail_i2c; ret = vidtv_bridge_register_adap(dvb); if (ret < 0) goto fail_adapter; dvb_register_media_controller(&dvb->adapter, &dvb->mdev); for (i = 0; i < NUM_FE; ++i) { ret = vidtv_bridge_probe_demod(dvb, i); if (ret < 0) goto fail_demod_probe; ret = vidtv_bridge_probe_tuner(dvb, i); if (ret < 0) goto fail_tuner_probe; ret = dvb_register_frontend(&dvb->adapter, dvb->fe[i]); if (ret < 0) goto fail_fe; } ret = vidtv_bridge_dmx_init(dvb); if (ret < 0) goto fail_dmx; ret = vidtv_bridge_dmxdev_init(dvb); if (ret < 0) goto fail_dmx_dev; for (j = 0; j < NUM_FE; ++j) { ret = dvb->demux.dmx.connect_frontend(&dvb->demux.dmx, &dvb->dmx_fe[j]); if (ret < 0) goto fail_dmx_conn; /* * The source of the demux is a frontend connected * to the demux. */ dvb->dmx_fe[j].source = DMX_FRONTEND_0; } return ret; fail_dmx_conn: for (j = j - 1; j >= 0; --j) dvb->demux.dmx.remove_frontend(&dvb->demux.dmx, &dvb->dmx_fe[j]); dvb_dmxdev_release(&dvb->dmx_dev); fail_dmx_dev: dvb_dmx_release(&dvb->demux); fail_dmx: fail_demod_probe: for (i = i - 1; i >= 0; --i) { dvb_unregister_frontend(dvb->fe[i]); fail_fe: dvb_module_release(dvb->i2c_client_tuner[i]); fail_tuner_probe: dvb_module_release(dvb->i2c_client_demod[i]); } fail_adapter: dvb_unregister_adapter(&dvb->adapter); fail_i2c: i2c_del_adapter(&dvb->i2c_adapter); return ret; } static int vidtv_bridge_probe(struct platform_device *pdev) { struct vidtv_dvb *dvb; int ret; dvb = kzalloc(sizeof(*dvb), GFP_KERNEL); if (!dvb) return -ENOMEM; dvb->pdev = pdev; #ifdef CONFIG_MEDIA_CONTROLLER_DVB dvb->mdev.dev = &pdev->dev; strscpy(dvb->mdev.model, "vidtv", sizeof(dvb->mdev.model)); strscpy(dvb->mdev.bus_info, "platform:vidtv", sizeof(dvb->mdev.bus_info)); media_device_init(&dvb->mdev); #endif ret = vidtv_bridge_dvb_init(dvb); if (ret < 0) goto err_dvb; mutex_init(&dvb->feed_lock); platform_set_drvdata(pdev, dvb); #ifdef CONFIG_MEDIA_CONTROLLER_DVB ret = media_device_register(&dvb->mdev); if (ret) { dev_err(dvb->mdev.dev, "media device register failed (err=%d)\n", ret); goto err_media_device_register; } #endif /* CONFIG_MEDIA_CONTROLLER_DVB */ dev_info(&pdev->dev, "Successfully initialized vidtv!\n"); return ret; #ifdef CONFIG_MEDIA_CONTROLLER_DVB err_media_device_register: media_device_cleanup(&dvb->mdev); #endif /* CONFIG_MEDIA_CONTROLLER_DVB */ err_dvb: kfree(dvb); return ret; } static void vidtv_bridge_remove(struct platform_device *pdev) { struct vidtv_dvb *dvb; u32 i; dvb = platform_get_drvdata(pdev); #ifdef CONFIG_MEDIA_CONTROLLER_DVB media_device_unregister(&dvb->mdev); media_device_cleanup(&dvb->mdev); #endif /* CONFIG_MEDIA_CONTROLLER_DVB */ mutex_destroy(&dvb->feed_lock); for (i = 0; i < NUM_FE; ++i) { dvb_unregister_frontend(dvb->fe[i]); dvb_module_release(dvb->i2c_client_tuner[i]); dvb_module_release(dvb->i2c_client_demod[i]); } dvb_dmxdev_release(&dvb->dmx_dev); dvb_dmx_release(&dvb->demux); dvb_unregister_adapter(&dvb->adapter); dev_info(&pdev->dev, "Successfully removed vidtv\n"); } static void vidtv_bridge_dev_release(struct device *dev) { struct vidtv_dvb *dvb; dvb = dev_get_drvdata(dev); kfree(dvb); } static struct platform_device vidtv_bridge_dev = { .name = VIDTV_PDEV_NAME, .dev.release = vidtv_bridge_dev_release, }; static struct platform_driver vidtv_bridge_driver = { .driver = { .name = VIDTV_PDEV_NAME, }, .probe = vidtv_bridge_probe, .remove = vidtv_bridge_remove, }; static void __exit vidtv_bridge_exit(void) { platform_driver_unregister(&vidtv_bridge_driver); platform_device_unregister(&vidtv_bridge_dev); } static int __init vidtv_bridge_init(void) { int ret; ret = platform_device_register(&vidtv_bridge_dev); if (ret) return ret; ret = platform_driver_register(&vidtv_bridge_driver); if (ret) platform_device_unregister(&vidtv_bridge_dev); return ret; } module_init(vidtv_bridge_init); module_exit(vidtv_bridge_exit); MODULE_DESCRIPTION("Virtual Digital TV Test Driver"); MODULE_AUTHOR("Daniel W. S. Almeida"); MODULE_LICENSE("GPL"); MODULE_ALIAS("vidtv"); MODULE_ALIAS("dvb_vidtv"); |
| 2 2 1 1 2 87 87 87 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC key management * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * RxRPC keys should have a description of describing their purpose: * "afs@CAMBRIDGE.REDHAT.COM> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/key-type.h> #include <linux/ctype.h> #include <linux/slab.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include <keys/user-type.h> #include "ar-internal.h" static int rxrpc_vet_description_s(const char *); static int rxrpc_preparse_s(struct key_preparsed_payload *); static void rxrpc_free_preparse_s(struct key_preparsed_payload *); static void rxrpc_destroy_s(struct key *); static void rxrpc_describe_s(const struct key *, struct seq_file *); /* * rxrpc server keys take "<serviceId>:<securityIndex>[:<sec-specific>]" as the * description and the key material as the payload. */ struct key_type key_type_rxrpc_s = { .name = "rxrpc_s", .flags = KEY_TYPE_NET_DOMAIN, .vet_description = rxrpc_vet_description_s, .preparse = rxrpc_preparse_s, .free_preparse = rxrpc_free_preparse_s, .instantiate = generic_key_instantiate, .destroy = rxrpc_destroy_s, .describe = rxrpc_describe_s, }; /* * Vet the description for an RxRPC server key. */ static int rxrpc_vet_description_s(const char *desc) { unsigned long service, sec_class; char *p; service = simple_strtoul(desc, &p, 10); if (*p != ':' || service > 65535) return -EINVAL; sec_class = simple_strtoul(p + 1, &p, 10); if ((*p && *p != ':') || sec_class < 1 || sec_class > 255) return -EINVAL; return 0; } /* * Preparse a server secret key. */ static int rxrpc_preparse_s(struct key_preparsed_payload *prep) { const struct rxrpc_security *sec; unsigned int service, sec_class; int n; _enter("%zu", prep->datalen); if (!prep->orig_description) return -EINVAL; if (sscanf(prep->orig_description, "%u:%u%n", &service, &sec_class, &n) != 2) return -EINVAL; sec = rxrpc_security_lookup(sec_class); if (!sec) return -ENOPKG; prep->payload.data[1] = (struct rxrpc_security *)sec; if (!sec->preparse_server_key) return -EINVAL; return sec->preparse_server_key(prep); } static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep) { const struct rxrpc_security *sec = prep->payload.data[1]; if (sec && sec->free_preparse_server_key) sec->free_preparse_server_key(prep); } static void rxrpc_destroy_s(struct key *key) { const struct rxrpc_security *sec = key->payload.data[1]; if (sec && sec->destroy_server_key) sec->destroy_server_key(key); } static void rxrpc_describe_s(const struct key *key, struct seq_file *m) { const struct rxrpc_security *sec = key->payload.data[1]; seq_puts(m, key->description); if (sec && sec->describe_server_key) sec->describe_server_key(key, m); } /* * grab the security keyring for a server socket */ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) { struct key *key; char *description; _enter(""); if (optlen <= 0 || optlen > PAGE_SIZE - 1) return -EINVAL; description = memdup_sockptr_nul(optval, optlen); if (IS_ERR(description)) return PTR_ERR(description); key = request_key(&key_type_keyring, description, NULL); if (IS_ERR(key)) { kfree(description); _leave(" = %ld", PTR_ERR(key)); return PTR_ERR(key); } rx->securities = key; kfree(description); _leave(" = 0 [key %x]", key->serial); return 0; } /** * rxrpc_sock_set_security_keyring - Set the security keyring for a kernel service * @sk: The socket to set the keyring on * @keyring: The keyring to set * * Set the server security keyring on an rxrpc socket. This is used to provide * the encryption keys for a kernel service. * * Return: %0 if successful and a negative error code otherwise. */ int rxrpc_sock_set_security_keyring(struct sock *sk, struct key *keyring) { struct rxrpc_sock *rx = rxrpc_sk(sk); int ret = 0; lock_sock(sk); if (rx->securities) ret = -EINVAL; else if (rx->sk.sk_state != RXRPC_UNBOUND) ret = -EISCONN; else rx->securities = key_get(keyring); release_sock(sk); return ret; } EXPORT_SYMBOL(rxrpc_sock_set_security_keyring); /** * rxrpc_sock_set_manage_response - Set the manage-response flag for a kernel service * @sk: The socket to set the keyring on * @set: True to set, false to clear the flag * * Set the flag on an rxrpc socket to say that the caller wants to manage the * RESPONSE packet and the user-defined data it may contain. Setting this * means that recvmsg() will return messages with RXRPC_CHALLENGED in the * control message buffer containing information about the challenge. * * The user should respond to the challenge by passing RXRPC_RESPOND or * RXRPC_RESPOND_ABORT control messages with sendmsg() to the same call. * Supplementary control messages, such as RXRPC_RESP_RXGK_APPDATA, may be * included to indicate the parts the user wants to supply. * * The server will be passed the response data with a RXRPC_RESPONDED control * message when it gets the first data from each call. * * Note that this is only honoured by security classes that need auxiliary data * (e.g. RxGK). Those that don't offer the facility (e.g. RxKAD) respond * without consulting userspace. * * Return: The previous setting. */ int rxrpc_sock_set_manage_response(struct sock *sk, bool set) { struct rxrpc_sock *rx = rxrpc_sk(sk); int ret; lock_sock(sk); ret = !!test_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); if (set) set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); else clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); release_sock(sk); return ret; } EXPORT_SYMBOL(rxrpc_sock_set_manage_response); |
| 736 206 736 228 206 27 754 753 754 261 738 752 725 205 268 221 305 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCATTERLIST_H #define _LINUX_SCATTERLIST_H #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/mm.h> #include <asm/io.h> struct scatterlist { unsigned long page_link; unsigned int offset; unsigned int length; dma_addr_t dma_address; #ifdef CONFIG_NEED_SG_DMA_LENGTH unsigned int dma_length; #endif #ifdef CONFIG_NEED_SG_DMA_FLAGS unsigned int dma_flags; #endif }; /* * These macros should be used after a dma_map_sg call has been done * to get bus addresses of each of the SG entries and their lengths. * You should only work with the number of sg entries dma_map_sg * returns, or alternatively stop on the first sg_dma_len(sg) which * is 0. */ #define sg_dma_address(sg) ((sg)->dma_address) #ifdef CONFIG_NEED_SG_DMA_LENGTH #define sg_dma_len(sg) ((sg)->dma_length) #else #define sg_dma_len(sg) ((sg)->length) #endif struct sg_table { struct scatterlist *sgl; /* the list */ unsigned int nents; /* number of mapped entries */ unsigned int orig_nents; /* original size of list */ }; struct sg_append_table { struct sg_table sgt; /* The scatter list table */ struct scatterlist *prv; /* last populated sge in the table */ unsigned int total_nents; /* Total entries in the table */ }; /* * Notes on SG table design. * * We use the unsigned long page_link field in the scatterlist struct to place * the page pointer AND encode information about the sg table as well. The two * lower bits are reserved for this information. * * If bit 0 is set, then the page_link contains a pointer to the next sg * table list. Otherwise the next entry is at sg + 1. * * If bit 1 is set, then this sg entry is the last element in a list. * * See sg_next(). * */ #define SG_CHAIN 0x01UL #define SG_END 0x02UL /* * We overload the LSB of the page pointer to indicate whether it's * a valid sg entry, or whether it points to the start of a new scatterlist. * Those low bits are there for everyone! (thanks mason :-) */ #define SG_PAGE_LINK_MASK (SG_CHAIN | SG_END) static inline unsigned int __sg_flags(struct scatterlist *sg) { return sg->page_link & SG_PAGE_LINK_MASK; } static inline struct scatterlist *sg_chain_ptr(struct scatterlist *sg) { return (struct scatterlist *)(sg->page_link & ~SG_PAGE_LINK_MASK); } static inline bool sg_is_chain(struct scatterlist *sg) { return __sg_flags(sg) & SG_CHAIN; } static inline bool sg_is_last(struct scatterlist *sg) { return __sg_flags(sg) & SG_END; } /** * sg_next - return the next scatterlist entry in a list * @sg: The current sg entry * * Description: * Usually the next entry will be @sg + 1, but if this sg element is part * of a chained scatterlist, it could jump to the start of a new * scatterlist array. * **/ static inline struct scatterlist *sg_next(struct scatterlist *sg) { if (sg_is_last(sg)) return NULL; sg++; if (unlikely(sg_is_chain(sg))) sg = sg_chain_ptr(sg); return sg; } /** * sg_assign_page - Assign a given page to an SG entry * @sg: SG entry * @page: The page * * Description: * Assign page to sg entry. Also see sg_set_page(), the most commonly used * variant. * **/ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) { unsigned long page_link = sg->page_link & (SG_CHAIN | SG_END); /* * In order for the low bit stealing approach to work, pages * must be aligned at a 32-bit boundary as a minimum. */ BUG_ON((unsigned long)page & SG_PAGE_LINK_MASK); #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif sg->page_link = page_link | (unsigned long) page; } /** * sg_set_page - Set sg entry to point at given page * @sg: SG entry * @page: The page * @len: Length of data * @offset: Offset into page * * Description: * Use this function to set an sg entry pointing at a page, never assign * the page directly. We encode sg table information in the lower bits * of the page pointer. See sg_page() for looking up the page belonging * to an sg entry. * **/ static inline void sg_set_page(struct scatterlist *sg, struct page *page, unsigned int len, unsigned int offset) { sg_assign_page(sg, page); sg->offset = offset; sg->length = len; } /** * sg_set_folio - Set sg entry to point at given folio * @sg: SG entry * @folio: The folio * @len: Length of data * @offset: Offset into folio * * Description: * Use this function to set an sg entry pointing at a folio, never assign * the folio directly. We encode sg table information in the lower bits * of the folio pointer. See sg_page() for looking up the page belonging * to an sg entry. * **/ static inline void sg_set_folio(struct scatterlist *sg, struct folio *folio, size_t len, size_t offset) { WARN_ON_ONCE(len > UINT_MAX); WARN_ON_ONCE(offset > UINT_MAX); sg_assign_page(sg, &folio->page); sg->offset = offset; sg->length = len; } static inline struct page *sg_page(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif return (struct page *)((sg)->page_link & ~SG_PAGE_LINK_MASK); } /** * sg_set_buf - Set sg entry to point at given data * @sg: SG entry * @buf: Data * @buflen: Data length * **/ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { #ifdef CONFIG_DEBUG_SG BUG_ON(!virt_addr_valid(buf)); #endif sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); } /* * Loop over each sg element, following the pointer to a new list if necessary */ #define for_each_sg(sglist, sg, nr, __i) \ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) /* * Loop over each sg element in the given sg_table object. */ #define for_each_sgtable_sg(sgt, sg, i) \ for_each_sg((sgt)->sgl, sg, (sgt)->orig_nents, i) /* * Loop over each sg element in the given *DMA mapped* sg_table object. * Please use sg_dma_address(sg) and sg_dma_len(sg) to extract DMA addresses * of the each element. */ #define for_each_sgtable_dma_sg(sgt, sg, i) \ for_each_sg((sgt)->sgl, sg, (sgt)->nents, i) static inline void __sg_chain(struct scatterlist *chain_sg, struct scatterlist *sgl) { /* * offset and length are unused for chain entry. Clear them. */ chain_sg->offset = 0; chain_sg->length = 0; /* * Set lowest bit to indicate a link pointer, and make sure to clear * the termination bit if it happens to be set. */ chain_sg->page_link = ((unsigned long) sgl | SG_CHAIN) & ~SG_END; } /** * sg_chain - Chain two sglists together * @prv: First scatterlist * @prv_nents: Number of entries in prv * @sgl: Second scatterlist * * Description: * Links @prv and @sgl together, to form a longer scatterlist. * **/ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, struct scatterlist *sgl) { __sg_chain(&prv[prv_nents - 1], sgl); } /** * sg_mark_end - Mark the end of the scatterlist * @sg: SG entryScatterlist * * Description: * Marks the passed in sg entry as the termination point for the sg * table. A call to sg_next() on this entry will return NULL. * **/ static inline void sg_mark_end(struct scatterlist *sg) { /* * Set termination bit, clear potential chain bit */ sg->page_link |= SG_END; sg->page_link &= ~SG_CHAIN; } /** * sg_unmark_end - Undo setting the end of the scatterlist * @sg: SG entryScatterlist * * Description: * Removes the termination marker from the given entry of the scatterlist. * **/ static inline void sg_unmark_end(struct scatterlist *sg) { sg->page_link &= ~SG_END; } /* * On 64-bit architectures there is a 4-byte padding in struct scatterlist * (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). Use this padding for DMA * flags bits to indicate when a specific dma address is a bus address or the * buffer may have been bounced via SWIOTLB. */ #ifdef CONFIG_NEED_SG_DMA_FLAGS #define SG_DMA_BUS_ADDRESS (1 << 0) #define SG_DMA_SWIOTLB (1 << 1) /** * sg_dma_is_bus_address - Return whether a given segment was marked * as a bus address * @sg: SG entry * * Description: * Returns true if sg_dma_mark_bus_address() has been called on * this segment. **/ static inline bool sg_dma_is_bus_address(struct scatterlist *sg) { return sg->dma_flags & SG_DMA_BUS_ADDRESS; } /** * sg_dma_mark_bus_address - Mark the scatterlist entry as a bus address * @sg: SG entry * * Description: * Marks the passed in sg entry to indicate that the dma_address is * a bus address and doesn't need to be unmapped. This should only be * used by dma_map_sg() implementations to mark bus addresses * so they can be properly cleaned up in dma_unmap_sg(). **/ static inline void sg_dma_mark_bus_address(struct scatterlist *sg) { sg->dma_flags |= SG_DMA_BUS_ADDRESS; } /** * sg_dma_unmark_bus_address - Unmark the scatterlist entry as a bus address * @sg: SG entry * * Description: * Clears the bus address mark. **/ static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) { sg->dma_flags &= ~SG_DMA_BUS_ADDRESS; } /** * sg_dma_is_swiotlb - Return whether the scatterlist was marked for SWIOTLB * bouncing * @sg: SG entry * * Description: * Returns true if the scatterlist was marked for SWIOTLB bouncing. Not all * elements may have been bounced, so the caller would have to check * individual SG entries with swiotlb_find_pool(). */ static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) { return sg->dma_flags & SG_DMA_SWIOTLB; } /** * sg_dma_mark_swiotlb - Mark the scatterlist for SWIOTLB bouncing * @sg: SG entry * * Description: * Marks a a scatterlist for SWIOTLB bounce. Not all SG entries may be * bounced. */ static inline void sg_dma_mark_swiotlb(struct scatterlist *sg) { sg->dma_flags |= SG_DMA_SWIOTLB; } #else static inline bool sg_dma_is_bus_address(struct scatterlist *sg) { return false; } static inline void sg_dma_mark_bus_address(struct scatterlist *sg) { } static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) { } static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) { return false; } static inline void sg_dma_mark_swiotlb(struct scatterlist *sg) { } #endif /* CONFIG_NEED_SG_DMA_FLAGS */ /** * sg_phys - Return physical address of an sg entry * @sg: SG entry * * Description: * This calls page_to_phys() on the page in this sg entry, and adds the * sg offset. The caller must know that it is legal to call page_to_phys() * on the sg page. * **/ static inline dma_addr_t sg_phys(struct scatterlist *sg) { return page_to_phys(sg_page(sg)) + sg->offset; } /** * sg_virt - Return virtual address of an sg entry * @sg: SG entry * * Description: * This calls page_address() on the page in this sg entry, and adds the * sg offset. The caller must know that the sg page has a valid virtual * mapping. * **/ static inline void *sg_virt(struct scatterlist *sg) { return page_address(sg_page(sg)) + sg->offset; } /** * sg_init_marker - Initialize markers in sg table * @sgl: The SG table * @nents: Number of entries in table * **/ static inline void sg_init_marker(struct scatterlist *sgl, unsigned int nents) { sg_mark_end(&sgl[nents - 1]); } int sg_nents(struct scatterlist *sg); int sg_nents_for_len(struct scatterlist *sg, u64 len); struct scatterlist *sg_last(struct scatterlist *s, unsigned int); void sg_init_table(struct scatterlist *, unsigned int); void sg_init_one(struct scatterlist *, const void *, unsigned int); int sg_split(struct scatterlist *in, const int in_mapped_nents, const off_t skip, const int nb_splits, const size_t *split_sizes, struct scatterlist **out, int *out_mapped_nents, gfp_t gfp_mask); typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); typedef void (sg_free_fn)(struct scatterlist *, unsigned int); void __sg_free_table(struct sg_table *, unsigned int, unsigned int, sg_free_fn *, unsigned int); void sg_free_table(struct sg_table *); void sg_free_append_table(struct sg_append_table *sgt); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); int sg_alloc_append_table_from_pages(struct sg_append_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, unsigned int left_pages, gfp_t gfp_mask); int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, gfp_t gfp_mask); /** * sg_alloc_table_from_pages - Allocate and initialize an sg table from * an array of pages * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous * ranges of the pages are squashed into a single scatterlist node. A user * may provide an offset at a start and a size of valid data in a buffer * specified by the page array. The returned sg table is released by * sg_free_table. * * Returns: * 0 on success, negative error on failure */ static inline int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, gfp_t gfp_mask) { return sg_alloc_table_from_pages_segment(sgt, pages, n_pages, offset, size, UINT_MAX, gfp_mask); } #ifdef CONFIG_SGL_ALLOC struct scatterlist *sgl_alloc_order(unsigned long long length, unsigned int order, bool chainable, gfp_t gfp, unsigned int *nent_p); struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp, unsigned int *nent_p); void sgl_free_n_order(struct scatterlist *sgl, int nents, int order); void sgl_free_order(struct scatterlist *sgl, int order); void sgl_free(struct scatterlist *sgl); #endif /* CONFIG_SGL_ALLOC */ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip, bool to_buffer); size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen); size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen); size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, size_t buflen, off_t skip); /* * Maximum number of entries that will be allocated in one piece, if * a list larger than this is required then chaining will be utilized. */ #define SG_MAX_SINGLE_ALLOC (PAGE_SIZE / sizeof(struct scatterlist)) /* * The maximum number of SG segments that we will put inside a * scatterlist (unless chaining is used). Should ideally fit inside a * single page, to avoid a higher order allocation. We could define this * to SG_MAX_SINGLE_ALLOC to pack correctly at the highest order. The * minimum value is 32 */ #define SG_CHUNK_SIZE 128 /* * Like SG_CHUNK_SIZE, but for archs that have sg chaining. This limit * is totally arbitrary, a setting of 2048 will get you at least 8mb ios. */ #ifdef CONFIG_ARCH_NO_SG_CHAIN #define SG_MAX_SEGMENTS SG_CHUNK_SIZE #else #define SG_MAX_SEGMENTS 2048 #endif #ifdef CONFIG_SG_POOL void sg_free_table_chained(struct sg_table *table, unsigned nents_first_chunk); int sg_alloc_table_chained(struct sg_table *table, int nents, struct scatterlist *first_chunk, unsigned nents_first_chunk); #endif /* * sg page iterator * * Iterates over sg entries page-by-page. On each successful iteration, you * can call sg_page_iter_page(@piter) to get the current page. * @piter->sg will point to the sg holding this page and @piter->sg_pgoffset to * the page's page offset within the sg. The iteration will stop either when a * maximum number of sg entries was reached or a terminating sg * (sg_last(sg) == true) was reached. */ struct sg_page_iter { struct scatterlist *sg; /* sg holding the page */ unsigned int sg_pgoffset; /* page offset within the sg */ /* these are internal states, keep away */ unsigned int __nents; /* remaining sg entries */ int __pg_advance; /* nr pages to advance at the * next step */ }; /* * sg page iterator for DMA addresses * * This is the same as sg_page_iter however you can call * sg_page_iter_dma_address(@dma_iter) to get the page's DMA * address. sg_page_iter_page() cannot be called on this iterator. */ struct sg_dma_page_iter { struct sg_page_iter base; }; bool __sg_page_iter_next(struct sg_page_iter *piter); bool __sg_page_iter_dma_next(struct sg_dma_page_iter *dma_iter); void __sg_page_iter_start(struct sg_page_iter *piter, struct scatterlist *sglist, unsigned int nents, unsigned long pgoffset); /** * sg_page_iter_page - get the current page held by the page iterator * @piter: page iterator holding the page */ static inline struct page *sg_page_iter_page(struct sg_page_iter *piter) { return nth_page(sg_page(piter->sg), piter->sg_pgoffset); } /** * sg_page_iter_dma_address - get the dma address of the current page held by * the page iterator. * @dma_iter: page iterator holding the page */ static inline dma_addr_t sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) { return sg_dma_address(dma_iter->base.sg) + (dma_iter->base.sg_pgoffset << PAGE_SHIFT); } /** * for_each_sg_page - iterate over the pages of the given sg list * @sglist: sglist to iterate over * @piter: page iterator to hold current page, sg, sg_pgoffset * @nents: maximum number of sg entries to iterate over * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_page() to get each page pointer. * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_page(sglist, piter, nents, pgoffset) \ for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \ __sg_page_iter_next(piter);) /** * for_each_sg_dma_page - iterate over the pages of the given sg list * @sglist: sglist to iterate over * @dma_iter: DMA page iterator to hold current page * @dma_nents: maximum number of sg entries to iterate over, this is the value * returned from dma_map_sg * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_dma_address() to get each page's DMA address. * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_dma_page(sglist, dma_iter, dma_nents, pgoffset) \ for (__sg_page_iter_start(&(dma_iter)->base, sglist, dma_nents, \ pgoffset); \ __sg_page_iter_dma_next(dma_iter);) /** * for_each_sgtable_page - iterate over all pages in the sg_table object * @sgt: sg_table object to iterate over * @piter: page iterator to hold current page * @pgoffset: starting page offset (in pages) * * Iterates over the all memory pages in the buffer described by * a scatterlist stored in the given sg_table object. * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit. */ #define for_each_sgtable_page(sgt, piter, pgoffset) \ for_each_sg_page((sgt)->sgl, piter, (sgt)->orig_nents, pgoffset) /** * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object * @sgt: sg_table object to iterate over * @dma_iter: DMA page iterator to hold current page * @pgoffset: starting page offset (in pages) * * Iterates over the all DMA mapped pages in the buffer described by * a scatterlist stored in the given sg_table object. * See also for_each_sg_dma_page(). In each loop it operates on PAGE_SIZE * unit. */ #define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset) \ for_each_sg_dma_page((sgt)->sgl, dma_iter, (sgt)->nents, pgoffset) /* * Mapping sg iterator * * Iterates over sg entries mapping page-by-page. On each successful * iteration, @miter->page points to the mapped page and * @miter->length bytes of data can be accessed at @miter->addr. As * long as an iteration is enclosed between start and stop, the user * is free to choose control structure and when to stop. * * @miter->consumed is set to @miter->length on each iteration. It * can be adjusted if the user can't consume all the bytes in one go. * Also, a stopped iteration can be resumed by calling next on it. * This is useful when iteration needs to release all resources and * continue later (e.g. at the next interrupt). */ #define SG_MITER_ATOMIC (1 << 0) /* use kmap_atomic */ #define SG_MITER_TO_SG (1 << 1) /* flush back to phys on unmap */ #define SG_MITER_FROM_SG (1 << 2) /* nop */ #define SG_MITER_LOCAL (1 << 3) /* use kmap_local */ struct sg_mapping_iter { /* the following three fields can be accessed directly */ struct page *page; /* currently mapped page */ void *addr; /* pointer to the mapped area */ size_t length; /* length of the mapped area */ size_t consumed; /* number of consumed bytes */ struct sg_page_iter piter; /* page iterator */ /* these are internal states, keep away */ unsigned int __offset; /* offset within page */ unsigned int __remaining; /* remaining bytes on page */ unsigned int __flags; }; void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, unsigned int nents, unsigned int flags); bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset); bool sg_miter_next(struct sg_mapping_iter *miter); void sg_miter_stop(struct sg_mapping_iter *miter); #endif /* _LINUX_SCATTERLIST_H */ |
| 111 111 111 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Do sleep inside a spin-lock * Copyright (c) 1999 by Takashi Iwai <tiwai@suse.de> */ #include <linux/export.h> #include <sound/core.h> #include "seq_lock.h" /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { if (warn_count-- == 0) pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); } } EXPORT_SYMBOL(snd_use_lock_sync_helper); |
| 1 3 2 1 3 6 6 6 6 927 926 882 880 923 924 57 56 55 56 56 7 490 7 7 7 7 881 879 878 880 880 881 879 164 164 164 164 560 560 559 560 558 557 159 159 159 159 295 295 290 264 291 196 194 195 196 195 74 194 167 196 536 537 536 537 536 532 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/stat.h> #include <linux/sysctl.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/hash.h> #include <linux/kmemleak.h> #include <linux/user_namespace.h> struct ucounts init_ucounts = { .ns = &init_user_ns, .uid = GLOBAL_ROOT_UID, .count = RCUREF_INIT(1), }; #define UCOUNTS_HASHTABLE_BITS 10 #define UCOUNTS_HASHTABLE_ENTRIES (1 << UCOUNTS_HASHTABLE_BITS) static struct hlist_nulls_head ucounts_hashtable[UCOUNTS_HASHTABLE_ENTRIES] = { [0 ... UCOUNTS_HASHTABLE_ENTRIES - 1] = HLIST_NULLS_HEAD_INIT(0) }; static DEFINE_SPINLOCK(ucounts_lock); #define ucounts_hashfn(ns, uid) \ hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \ UCOUNTS_HASHTABLE_BITS) #define ucounts_hashentry(ns, uid) \ (ucounts_hashtable + ucounts_hashfn(ns, uid)) #ifdef CONFIG_SYSCTL static struct ctl_table_set * set_lookup(struct ctl_table_root *root) { return ¤t_user_ns()->set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t_user_ns()->set == set; } static int set_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct user_namespace *user_ns = container_of(head->set, struct user_namespace, set); int mode; /* Allow users with CAP_SYS_RESOURCE unrestrained access */ if (ns_capable(user_ns, CAP_SYS_RESOURCE)) mode = (table->mode & S_IRWXU) >> 6; else /* Allow all others at most read-only access */ mode = table->mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = set_permissions, }; static long ue_zero = 0; static long ue_int_max = INT_MAX; #define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(long), \ .mode = 0644, \ .proc_handler = proc_doulongvec_minmax, \ .extra1 = &ue_zero, \ .extra2 = &ue_int_max, \ } static const struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), UCOUNT_ENTRY("max_pid_namespaces"), UCOUNT_ENTRY("max_uts_namespaces"), UCOUNT_ENTRY("max_ipc_namespaces"), UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), UCOUNT_ENTRY("max_time_namespaces"), #ifdef CONFIG_INOTIFY_USER UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), #endif #ifdef CONFIG_FANOTIFY UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif }; #endif /* CONFIG_SYSCTL */ bool setup_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS); setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < UCOUNT_COUNTS; i++) { tbl[i].data = &ns->ucount_max[i]; } ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl, ARRAY_SIZE(user_table)); } if (!ns->sysctls) { kfree(tbl); retire_sysctl_set(&ns->set); return false; } #endif return true; } void retire_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = ns->sysctls->ctl_table_arg; unregister_sysctl_table(ns->sysctls); retire_sysctl_set(&ns->set); kfree(tbl); #endif } static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_nulls_head *hashent) { struct ucounts *ucounts; struct hlist_nulls_node *pos; guard(rcu)(); hlist_nulls_for_each_entry_rcu(ucounts, pos, hashent, node) { if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) { if (rcuref_get(&ucounts->count)) return ucounts; } } return NULL; } static void hlist_add_ucounts(struct ucounts *ucounts) { struct hlist_nulls_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid); spin_lock_irq(&ucounts_lock); hlist_nulls_add_head_rcu(&ucounts->node, hashent); spin_unlock_irq(&ucounts_lock); } struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_nulls_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; ucounts = find_ucounts(ns, uid, hashent); if (ucounts) return ucounts; new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; new->ns = ns; new->uid = uid; rcuref_init(&new->count, 1); spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { spin_unlock_irq(&ucounts_lock); kfree(new); return ucounts; } hlist_nulls_add_head_rcu(&new->node, hashent); get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } void put_ucounts(struct ucounts *ucounts) { unsigned long flags; if (rcuref_put(&ucounts->count)) { spin_lock_irqsave(&ucounts_lock, flags); hlist_nulls_del_rcu(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); put_user_ns(ucounts->ns); kfree_rcu(ucounts, rcu); } } static inline bool atomic_long_inc_below(atomic_long_t *v, int u) { long c, old; c = atomic_long_read(v); for (;;) { if (unlikely(c >= u)) return false; old = atomic_long_cmpxchg(v, c, c+1); if (likely(old == c)) return true; c = old; } } struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type) { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; ucounts = alloc_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { long max; tns = iter->ns; max = READ_ONCE(tns->ucount_max[type]); if (!atomic_long_inc_below(&iter->ucount[type], max)) goto fail; } return ucounts; fail: bad = iter; for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) atomic_long_dec(&iter->ucount[type]); put_ucounts(ucounts); return NULL; } void dec_ucount(struct ucounts *ucounts, enum ucount_type type) { struct ucounts *iter; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_dec_if_positive(&iter->ucount[type]); WARN_ON_ONCE(dec < 0); } put_ucounts(ucounts); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long max = LONG_MAX; long ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(v, &iter->rlimit[type]); if (new < 0 || new > max) ret = LONG_MAX; else if (iter == ucounts) ret = new; max = get_userns_rlimit_max(iter->ns, type); } return ret; } bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long new = -1; /* Silence compiler warning */ for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_sub_return(v, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); if (iter == ucounts) new = dec; } return (new == 0); } static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, struct ucounts *last, enum rlimit_type type) { struct ucounts *iter, *next; for (iter = ucounts; iter != last; iter = next) { long dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); next = iter->ns->ucounts; if (dec == 0) put_ucounts(iter); } } void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) { do_dec_rlimit_put_ucounts(ucounts, NULL, type); } long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, bool override_rlimit) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; long max = LONG_MAX; long dec, ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) goto dec_unwind; if (iter == ucounts) ret = new; if (!override_rlimit) max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. */ if (new != 1) continue; if (!get_ucounts(iter)) goto dec_unwind; } return ret; dec_unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit) { struct ucounts *iter; long max = rlimit; if (rlimit > LONG_MAX) max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long val = get_rlimit_value(iter, type); if (val < 0 || val > max) return true; max = get_userns_rlimit_max(iter->ns, type); } return false; } static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL static struct ctl_table_header *user_header; static struct ctl_table empty[1]; /* * It is necessary to register the user directory in the * default set so that registrations in the child sets work * properly. */ user_header = register_sysctl_sz("user", empty, 0); kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif hlist_add_ucounts(&init_ucounts); inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1); return 0; } subsys_initcall(user_namespace_sysctl_init); |
| 2 2 4 4 2 1 1 1 1 12 12 12 12 12 1 11 11 11 11 11 11 11 11 11 11 11 12 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 13 13 5 4 4 4 13 4 6 6 2 6 12 12 12 1 12 12 12 12 12 12 12 12 12 1 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 27 1 26 25 27 27 27 27 27 12 2 2 2 2 68 68 68 68 68 68 152 152 151 152 152 60 54 151 151 149 146 146 146 68 68 60 60 60 60 68 68 68 68 152 152 152 152 151 151 152 152 152 12 85 12 142 141 23 12 12 17 17 145 69 70 62 61 56 54 60 54 68 69 70 68 68 70 151 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/usb/core/driver.c - most of the driver model stuff for usb * * (C) Copyright 2005 Greg Kroah-Hartman <gregkh@suse.de> * * based on drivers/usb/usb.c which had the following copyrights: * (C) Copyright Linus Torvalds 1999 * (C) Copyright Johannes Erdfelt 1999-2001 * (C) Copyright Andreas Gal 1999 * (C) Copyright Gregory P. Smith 1999 * (C) Copyright Deti Fliegl 1999 (new USB architecture) * (C) Copyright Randy Dunlap 2000 * (C) Copyright David Brownell 2000-2004 * (C) Copyright Yggdrasil Computing, Inc. 2000 * (usb_device_id matching changes by Adam J. Richter) * (C) Copyright Greg Kroah-Hartman 2002-2003 * * Released under the GPLv2 only. * * NOTE! This is not actually a driver at all, rather this is * just a collection of helper routines that implement the * matching, probing, releasing, suspending and resuming for * real drivers. * */ #include <linux/device.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/usb.h> #include <linux/usb/quirks.h> #include <linux/usb/hcd.h> #include "usb.h" /* * Adds a new dynamic USBdevice ID to this driver, * and cause the driver to probe for all devices again. */ ssize_t usb_store_new_id(struct usb_dynids *dynids, const struct usb_device_id *id_table, struct device_driver *driver, const char *buf, size_t count) { struct usb_dynid *dynid; u32 idVendor = 0; u32 idProduct = 0; unsigned int bInterfaceClass = 0; u32 refVendor, refProduct; int fields = 0; int retval = 0; fields = sscanf(buf, "%x %x %x %x %x", &idVendor, &idProduct, &bInterfaceClass, &refVendor, &refProduct); if (fields < 2) return -EINVAL; dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); if (!dynid) return -ENOMEM; INIT_LIST_HEAD(&dynid->node); dynid->id.idVendor = idVendor; dynid->id.idProduct = idProduct; dynid->id.match_flags = USB_DEVICE_ID_MATCH_DEVICE; if (fields > 2 && bInterfaceClass) { if (bInterfaceClass > 255) { retval = -EINVAL; goto fail; } dynid->id.bInterfaceClass = (u8)bInterfaceClass; dynid->id.match_flags |= USB_DEVICE_ID_MATCH_INT_CLASS; } if (fields > 4) { const struct usb_device_id *id = id_table; if (!id) { retval = -ENODEV; goto fail; } for (; id->match_flags; id++) if (id->idVendor == refVendor && id->idProduct == refProduct) break; if (id->match_flags) { dynid->id.driver_info = id->driver_info; } else { retval = -ENODEV; goto fail; } } mutex_lock(&usb_dynids_lock); list_add_tail(&dynid->node, &dynids->list); mutex_unlock(&usb_dynids_lock); retval = driver_attach(driver); if (retval) return retval; return count; fail: kfree(dynid); return retval; } EXPORT_SYMBOL_GPL(usb_store_new_id); ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf) { struct usb_dynid *dynid; size_t count = 0; guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &dynids->list, node) if (dynid->id.bInterfaceClass != 0) count += scnprintf(&buf[count], PAGE_SIZE - count, "%04x %04x %02x\n", dynid->id.idVendor, dynid->id.idProduct, dynid->id.bInterfaceClass); else count += scnprintf(&buf[count], PAGE_SIZE - count, "%04x %04x\n", dynid->id.idVendor, dynid->id.idProduct); return count; } EXPORT_SYMBOL_GPL(usb_show_dynids); static ssize_t new_id_show(struct device_driver *driver, char *buf) { struct usb_driver *usb_drv = to_usb_driver(driver); return usb_show_dynids(&usb_drv->dynids, buf); } static ssize_t new_id_store(struct device_driver *driver, const char *buf, size_t count) { struct usb_driver *usb_drv = to_usb_driver(driver); return usb_store_new_id(&usb_drv->dynids, usb_drv->id_table, driver, buf, count); } static DRIVER_ATTR_RW(new_id); /* * Remove a USB device ID from this driver */ static ssize_t remove_id_store(struct device_driver *driver, const char *buf, size_t count) { struct usb_dynid *dynid, *n; struct usb_driver *usb_driver = to_usb_driver(driver); u32 idVendor; u32 idProduct; int fields; fields = sscanf(buf, "%x %x", &idVendor, &idProduct); if (fields < 2) return -EINVAL; guard(mutex)(&usb_dynids_lock); list_for_each_entry_safe(dynid, n, &usb_driver->dynids.list, node) { struct usb_device_id *id = &dynid->id; if ((id->idVendor == idVendor) && (id->idProduct == idProduct)) { list_del(&dynid->node); kfree(dynid); break; } } return count; } static ssize_t remove_id_show(struct device_driver *driver, char *buf) { return new_id_show(driver, buf); } static DRIVER_ATTR_RW(remove_id); static int usb_create_newid_files(struct usb_driver *usb_drv) { int error = 0; if (usb_drv->no_dynamic_id) goto exit; if (usb_drv->probe != NULL) { error = driver_create_file(&usb_drv->driver, &driver_attr_new_id); if (error == 0) { error = driver_create_file(&usb_drv->driver, &driver_attr_remove_id); if (error) driver_remove_file(&usb_drv->driver, &driver_attr_new_id); } } exit: return error; } static void usb_remove_newid_files(struct usb_driver *usb_drv) { if (usb_drv->no_dynamic_id) return; if (usb_drv->probe != NULL) { driver_remove_file(&usb_drv->driver, &driver_attr_remove_id); driver_remove_file(&usb_drv->driver, &driver_attr_new_id); } } static void usb_free_dynids(struct usb_driver *usb_drv) { struct usb_dynid *dynid, *n; guard(mutex)(&usb_dynids_lock); list_for_each_entry_safe(dynid, n, &usb_drv->dynids.list, node) { list_del(&dynid->node); kfree(dynid); } } static const struct usb_device_id *usb_match_dynamic_id(struct usb_interface *intf, const struct usb_driver *drv) { struct usb_dynid *dynid; guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &drv->dynids.list, node) { if (usb_match_one_id(intf, &dynid->id)) { return &dynid->id; } } return NULL; } /* called from driver core with dev locked */ static int usb_probe_device(struct device *dev) { struct usb_device_driver *udriver = to_usb_device_driver(dev->driver); struct usb_device *udev = to_usb_device(dev); int error = 0; dev_dbg(dev, "%s\n", __func__); /* TODO: Add real matching code */ /* The device should always appear to be in use * unless the driver supports autosuspend. */ if (!udriver->supports_autosuspend) error = usb_autoresume_device(udev); if (error) return error; if (udriver->generic_subclass) error = usb_generic_driver_probe(udev); if (error) return error; /* Probe the USB device with the driver in hand, but only * defer to a generic driver in case the current USB * device driver has an id_table or a match function; i.e., * when the device driver was explicitly matched against * a device. * * If the device driver does not have either of these, * then we assume that it can bind to any device and is * not truly a more specialized/non-generic driver, so a * return value of -ENODEV should not force the device * to be handled by the generic USB driver, as there * can still be another, more specialized, device driver. * * This accommodates the usbip driver. * * TODO: What if, in the future, there are multiple * specialized USB device drivers for a particular device? * In such cases, there is a need to try all matching * specialised device drivers prior to setting the * use_generic_driver bit. */ if (udriver->probe) error = udriver->probe(udev); else if (!udriver->generic_subclass) error = -EINVAL; if (error == -ENODEV && udriver != &usb_generic_driver && (udriver->id_table || udriver->match)) { udev->use_generic_driver = 1; return -EPROBE_DEFER; } return error; } /* called from driver core with dev locked */ static int usb_unbind_device(struct device *dev) { struct usb_device *udev = to_usb_device(dev); struct usb_device_driver *udriver = to_usb_device_driver(dev->driver); if (udriver->disconnect) udriver->disconnect(udev); if (udriver->generic_subclass) usb_generic_driver_disconnect(udev); if (!udriver->supports_autosuspend) usb_autosuspend_device(udev); return 0; } /* called from driver core with dev locked */ static int usb_probe_interface(struct device *dev) { struct usb_driver *driver = to_usb_driver(dev->driver); struct usb_interface *intf = to_usb_interface(dev); struct usb_device *udev = interface_to_usbdev(intf); const struct usb_device_id *id; int error = -ENODEV; int lpm_disable_error = -ENODEV; dev_dbg(dev, "%s\n", __func__); intf->needs_binding = 0; if (usb_device_is_owned(udev)) return error; if (udev->authorized == 0) { dev_err(&intf->dev, "Device is not authorized for usage\n"); return error; } else if (intf->authorized == 0) { dev_err(&intf->dev, "Interface %d is not authorized for usage\n", intf->altsetting->desc.bInterfaceNumber); return error; } id = usb_match_dynamic_id(intf, driver); if (!id) id = usb_match_id(intf, driver->id_table); if (!id) return error; dev_dbg(dev, "%s - got id\n", __func__); error = usb_autoresume_device(udev); if (error) return error; intf->condition = USB_INTERFACE_BINDING; /* Probed interfaces are initially active. They are * runtime-PM-enabled only if the driver has autosuspend support. * They are sensitive to their children's power states. */ pm_runtime_set_active(dev); pm_suspend_ignore_children(dev, false); if (driver->supports_autosuspend) pm_runtime_enable(dev); /* If the new driver doesn't allow hub-initiated LPM, and we can't * disable hub-initiated LPM, then fail the probe. * * Otherwise, leaving LPM enabled should be harmless, because the * endpoint intervals should remain the same, and the U1/U2 timeouts * should remain the same. * * If we need to install alt setting 0 before probe, or another alt * setting during probe, that should also be fine. usb_set_interface() * will attempt to disable LPM, and fail if it can't disable it. */ if (driver->disable_hub_initiated_lpm) { lpm_disable_error = usb_unlocked_disable_lpm(udev); if (lpm_disable_error) { dev_err(&intf->dev, "%s Failed to disable LPM for driver %s\n", __func__, driver->name); error = lpm_disable_error; goto err; } } /* Carry out a deferred switch to altsetting 0 */ if (intf->needs_altsetting0) { error = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (error < 0) goto err; intf->needs_altsetting0 = 0; } error = driver->probe(intf, id); if (error) goto err; intf->condition = USB_INTERFACE_BOUND; /* If the LPM disable succeeded, balance the ref counts. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); usb_autosuspend_device(udev); return error; err: usb_set_intfdata(intf, NULL); intf->needs_remote_wakeup = 0; intf->condition = USB_INTERFACE_UNBOUND; /* If the LPM disable succeeded, balance the ref counts. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); /* Unbound interfaces are always runtime-PM-disabled and -suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); usb_autosuspend_device(udev); return error; } /* called from driver core with dev locked */ static int usb_unbind_interface(struct device *dev) { struct usb_driver *driver = to_usb_driver(dev->driver); struct usb_interface *intf = to_usb_interface(dev); struct usb_host_endpoint *ep, **eps = NULL; struct usb_device *udev; int i, j, error, r; int lpm_disable_error = -ENODEV; intf->condition = USB_INTERFACE_UNBINDING; /* Autoresume for set_interface call below */ udev = interface_to_usbdev(intf); error = usb_autoresume_device(udev); /* If hub-initiated LPM policy may change, attempt to disable LPM until * the driver is unbound. If LPM isn't disabled, that's fine because it * wouldn't be enabled unless all the bound interfaces supported * hub-initiated LPM. */ if (driver->disable_hub_initiated_lpm) lpm_disable_error = usb_unlocked_disable_lpm(udev); /* * Terminate all URBs for this interface unless the driver * supports "soft" unbinding and the device is still present. */ if (!driver->soft_unbind || udev->state == USB_STATE_NOTATTACHED) usb_disable_interface(udev, intf, false); driver->disconnect(intf); /* Free streams */ for (i = 0, j = 0; i < intf->cur_altsetting->desc.bNumEndpoints; i++) { ep = &intf->cur_altsetting->endpoint[i]; if (ep->streams == 0) continue; if (j == 0) { eps = kmalloc_array(USB_MAXENDPOINTS, sizeof(void *), GFP_KERNEL); if (!eps) break; } eps[j++] = ep; } if (j) { usb_free_streams(intf, eps, j, GFP_KERNEL); kfree(eps); } /* Reset other interface state. * We cannot do a Set-Interface if the device is suspended or * if it is prepared for a system sleep (since installing a new * altsetting means creating new endpoint device entries). * When either of these happens, defer the Set-Interface. */ if (intf->cur_altsetting->desc.bAlternateSetting == 0) { /* Already in altsetting 0 so skip Set-Interface. * Just re-enable it without affecting the endpoint toggles. */ usb_enable_interface(udev, intf, false); } else if (!error && !intf->dev.power.is_prepared) { r = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (r < 0) intf->needs_altsetting0 = 1; } else { intf->needs_altsetting0 = 1; } usb_set_intfdata(intf, NULL); intf->condition = USB_INTERFACE_UNBOUND; intf->needs_remote_wakeup = 0; /* Attempt to re-enable USB3 LPM, if the disable succeeded. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); /* Unbound interfaces are always runtime-PM-disabled and -suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); if (!error) usb_autosuspend_device(udev); return 0; } static void usb_shutdown_interface(struct device *dev) { struct usb_interface *intf = to_usb_interface(dev); struct usb_driver *driver; if (!dev->driver) return; driver = to_usb_driver(dev->driver); if (driver->shutdown) driver->shutdown(intf); } /** * usb_driver_claim_interface - bind a driver to an interface * @driver: the driver to be bound * @iface: the interface to which it will be bound; must be in the * usb device's active configuration * @data: driver data associated with that interface * * This is used by usb device drivers that need to claim more than one * interface on a device when probing (audio and acm are current examples). * No device driver should directly modify internal usb_interface or * usb_device structure members. * * Callers must own the device lock, so driver probe() entries don't need * extra locking, but other call contexts may need to explicitly claim that * lock. * * Return: 0 on success. */ int usb_driver_claim_interface(struct usb_driver *driver, struct usb_interface *iface, void *data) { struct device *dev; int retval = 0; if (!iface) return -ENODEV; dev = &iface->dev; if (dev->driver) return -EBUSY; /* reject claim if interface is not authorized */ if (!iface->authorized) return -ENODEV; dev->driver = &driver->driver; usb_set_intfdata(iface, data); iface->needs_binding = 0; iface->condition = USB_INTERFACE_BOUND; /* Claimed interfaces are initially inactive (suspended) and * runtime-PM-enabled, but only if the driver has autosuspend * support. Otherwise they are marked active, to prevent the * device from being autosuspended, but left disabled. In either * case they are sensitive to their children's power states. */ pm_suspend_ignore_children(dev, false); if (driver->supports_autosuspend) pm_runtime_enable(dev); else pm_runtime_set_active(dev); /* if interface was already added, bind now; else let * the future device_add() bind it, bypassing probe() */ if (device_is_registered(dev)) retval = device_bind_driver(dev); if (retval) { dev->driver = NULL; usb_set_intfdata(iface, NULL); iface->needs_remote_wakeup = 0; iface->condition = USB_INTERFACE_UNBOUND; /* * Unbound interfaces are always runtime-PM-disabled * and runtime-PM-suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); } return retval; } EXPORT_SYMBOL_GPL(usb_driver_claim_interface); /** * usb_driver_release_interface - unbind a driver from an interface * @driver: the driver to be unbound * @iface: the interface from which it will be unbound * * This can be used by drivers to release an interface without waiting * for their disconnect() methods to be called. In typical cases this * also causes the driver disconnect() method to be called. * * This call is synchronous, and may not be used in an interrupt context. * Callers must own the device lock, so driver disconnect() entries don't * need extra locking, but other call contexts may need to explicitly claim * that lock. */ void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface) { struct device *dev = &iface->dev; /* this should never happen, don't release something that's not ours */ if (!dev->driver || dev->driver != &driver->driver) return; /* don't release from within disconnect() */ if (iface->condition != USB_INTERFACE_BOUND) return; iface->condition = USB_INTERFACE_UNBINDING; /* Release via the driver core only if the interface * has already been registered */ if (device_is_registered(dev)) { device_release_driver(dev); } else { device_lock(dev); usb_unbind_interface(dev); dev->driver = NULL; device_unlock(dev); } } EXPORT_SYMBOL_GPL(usb_driver_release_interface); /* returns 0 if no match, 1 if match */ int usb_match_device(struct usb_device *dev, const struct usb_device_id *id) { if ((id->match_flags & USB_DEVICE_ID_MATCH_VENDOR) && id->idVendor != le16_to_cpu(dev->descriptor.idVendor)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_PRODUCT) && id->idProduct != le16_to_cpu(dev->descriptor.idProduct)) return 0; /* No need to test id->bcdDevice_lo != 0, since 0 is never greater than any unsigned number. */ if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_LO) && (id->bcdDevice_lo > le16_to_cpu(dev->descriptor.bcdDevice))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_HI) && (id->bcdDevice_hi < le16_to_cpu(dev->descriptor.bcdDevice))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_CLASS) && (id->bDeviceClass != dev->descriptor.bDeviceClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_SUBCLASS) && (id->bDeviceSubClass != dev->descriptor.bDeviceSubClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_PROTOCOL) && (id->bDeviceProtocol != dev->descriptor.bDeviceProtocol)) return 0; return 1; } /* returns 0 if no match, 1 if match */ int usb_match_one_id_intf(struct usb_device *dev, struct usb_host_interface *intf, const struct usb_device_id *id) { /* The interface class, subclass, protocol and number should never be * checked for a match if the device class is Vendor Specific, * unless the match record specifies the Vendor ID. */ if (dev->descriptor.bDeviceClass == USB_CLASS_VENDOR_SPEC && !(id->match_flags & USB_DEVICE_ID_MATCH_VENDOR) && (id->match_flags & (USB_DEVICE_ID_MATCH_INT_CLASS | USB_DEVICE_ID_MATCH_INT_SUBCLASS | USB_DEVICE_ID_MATCH_INT_PROTOCOL | USB_DEVICE_ID_MATCH_INT_NUMBER))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_CLASS) && (id->bInterfaceClass != intf->desc.bInterfaceClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_SUBCLASS) && (id->bInterfaceSubClass != intf->desc.bInterfaceSubClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_PROTOCOL) && (id->bInterfaceProtocol != intf->desc.bInterfaceProtocol)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER) && (id->bInterfaceNumber != intf->desc.bInterfaceNumber)) return 0; return 1; } /* returns 0 if no match, 1 if match */ int usb_match_one_id(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_host_interface *intf; struct usb_device *dev; /* proc_connectinfo in devio.c may call us with id == NULL. */ if (id == NULL) return 0; intf = interface->cur_altsetting; dev = interface_to_usbdev(interface); if (!usb_match_device(dev, id)) return 0; return usb_match_one_id_intf(dev, intf, id); } EXPORT_SYMBOL_GPL(usb_match_one_id); /** * usb_match_id - find first usb_device_id matching device or interface * @interface: the interface of interest * @id: array of usb_device_id structures, terminated by zero entry * * usb_match_id searches an array of usb_device_id's and returns * the first one matching the device or interface, or null. * This is used when binding (or rebinding) a driver to an interface. * Most USB device drivers will use this indirectly, through the usb core, * but some layered driver frameworks use it directly. * These device tables are exported with MODULE_DEVICE_TABLE, through * modutils, to support the driver loading functionality of USB hotplugging. * * Return: The first matching usb_device_id, or %NULL. * * What Matches: * * The "match_flags" element in a usb_device_id controls which * members are used. If the corresponding bit is set, the * value in the device_id must match its corresponding member * in the device or interface descriptor, or else the device_id * does not match. * * "driver_info" is normally used only by device drivers, * but you can create a wildcard "matches anything" usb_device_id * as a driver's "modules.usbmap" entry if you provide an id with * only a nonzero "driver_info" field. If you do this, the USB device * driver's probe() routine should use additional intelligence to * decide whether to bind to the specified interface. * * What Makes Good usb_device_id Tables: * * The match algorithm is very simple, so that intelligence in * driver selection must come from smart driver id records. * Unless you have good reasons to use another selection policy, * provide match elements only in related groups, and order match * specifiers from specific to general. Use the macros provided * for that purpose if you can. * * The most specific match specifiers use device descriptor * data. These are commonly used with product-specific matches; * the USB_DEVICE macro lets you provide vendor and product IDs, * and you can also match against ranges of product revisions. * These are widely used for devices with application or vendor * specific bDeviceClass values. * * Matches based on device class/subclass/protocol specifications * are slightly more general; use the USB_DEVICE_INFO macro, or * its siblings. These are used with single-function devices * where bDeviceClass doesn't specify that each interface has * its own class. * * Matches based on interface class/subclass/protocol are the * most general; they let drivers bind to any interface on a * multiple-function device. Use the USB_INTERFACE_INFO * macro, or its siblings, to match class-per-interface style * devices (as recorded in bInterfaceClass). * * Note that an entry created by USB_INTERFACE_INFO won't match * any interface if the device class is set to Vendor-Specific. * This is deliberate; according to the USB spec the meanings of * the interface class/subclass/protocol for these devices are also * vendor-specific, and hence matching against a standard product * class wouldn't work anyway. If you really want to use an * interface-based match for such a device, create a match record * that also specifies the vendor ID. (Unforunately there isn't a * standard macro for creating records like this.) * * Within those groups, remember that not all combinations are * meaningful. For example, don't give a product version range * without vendor and product IDs; or specify a protocol without * its associated class and subclass. */ const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id) { /* proc_connectinfo in devio.c may call us with id == NULL. */ if (id == NULL) return NULL; /* It is important to check that id->driver_info is nonzero, since an entry that is all zeroes except for a nonzero id->driver_info is the way to create an entry that indicates that the driver want to examine every device and interface. */ for (; id->idVendor || id->idProduct || id->bDeviceClass || id->bInterfaceClass || id->driver_info; id++) { if (usb_match_one_id(interface, id)) return id; } return NULL; } EXPORT_SYMBOL_GPL(usb_match_id); const struct usb_device_id *usb_device_match_id(struct usb_device *udev, const struct usb_device_id *id) { if (!id) return NULL; for (; id->idVendor || id->idProduct ; id++) { if (usb_match_device(udev, id)) return id; } return NULL; } EXPORT_SYMBOL_GPL(usb_device_match_id); bool usb_driver_applicable(struct usb_device *udev, const struct usb_device_driver *udrv) { if (udrv->id_table && udrv->match) return usb_device_match_id(udev, udrv->id_table) != NULL && udrv->match(udev); if (udrv->id_table) return usb_device_match_id(udev, udrv->id_table) != NULL; if (udrv->match) return udrv->match(udev); return false; } static int usb_device_match(struct device *dev, const struct device_driver *drv) { /* devices and interfaces are handled separately */ if (is_usb_device(dev)) { struct usb_device *udev; const struct usb_device_driver *udrv; /* interface drivers never match devices */ if (!is_usb_device_driver(drv)) return 0; udev = to_usb_device(dev); udrv = to_usb_device_driver(drv); /* If the device driver under consideration does not have a * id_table or a match function, then let the driver's probe * function decide. */ if (!udrv->id_table && !udrv->match) return 1; return usb_driver_applicable(udev, udrv); } else if (is_usb_interface(dev)) { struct usb_interface *intf; const struct usb_driver *usb_drv; const struct usb_device_id *id; /* device drivers never match interfaces */ if (is_usb_device_driver(drv)) return 0; intf = to_usb_interface(dev); usb_drv = to_usb_driver(drv); id = usb_match_id(intf, usb_drv->id_table); if (id) return 1; id = usb_match_dynamic_id(intf, usb_drv); if (id) return 1; } return 0; } static int usb_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct usb_device *usb_dev; if (is_usb_device(dev)) { usb_dev = to_usb_device(dev); } else if (is_usb_interface(dev)) { const struct usb_interface *intf = to_usb_interface(dev); usb_dev = interface_to_usbdev(intf); } else { return 0; } if (usb_dev->devnum < 0) { /* driver is often null here; dev_dbg() would oops */ pr_debug("usb %s: already deleted?\n", dev_name(dev)); return -ENODEV; } if (!usb_dev->bus) { pr_debug("usb %s: bus removed?\n", dev_name(dev)); return -ENODEV; } /* per-device configurations are common */ if (add_uevent_var(env, "PRODUCT=%x/%x/%x", le16_to_cpu(usb_dev->descriptor.idVendor), le16_to_cpu(usb_dev->descriptor.idProduct), le16_to_cpu(usb_dev->descriptor.bcdDevice))) return -ENOMEM; /* class-based driver binding models */ if (add_uevent_var(env, "TYPE=%d/%d/%d", usb_dev->descriptor.bDeviceClass, usb_dev->descriptor.bDeviceSubClass, usb_dev->descriptor.bDeviceProtocol)) return -ENOMEM; return 0; } static int __usb_bus_reprobe_drivers(struct device *dev, void *data) { struct usb_device_driver *new_udriver = data; struct usb_device *udev; int ret; /* Don't reprobe if current driver isn't usb_generic_driver */ if (dev->driver != &usb_generic_driver.driver) return 0; udev = to_usb_device(dev); if (!usb_driver_applicable(udev, new_udriver)) return 0; ret = device_reprobe(dev); if (ret && ret != -EPROBE_DEFER) dev_err(dev, "Failed to reprobe device (error %d)\n", ret); return 0; } bool is_usb_device_driver(const struct device_driver *drv) { return drv->probe == usb_probe_device; } /** * usb_register_device_driver - register a USB device (not interface) driver * @new_udriver: USB operations for the device driver * @owner: module owner of this driver. * * Registers a USB device driver with the USB core. The list of * unattached devices will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized devices. * * Return: A negative error code on failure and 0 on success. */ int usb_register_device_driver(struct usb_device_driver *new_udriver, struct module *owner) { int retval = 0; if (usb_disabled()) return -ENODEV; new_udriver->driver.name = new_udriver->name; new_udriver->driver.bus = &usb_bus_type; new_udriver->driver.probe = usb_probe_device; new_udriver->driver.remove = usb_unbind_device; new_udriver->driver.owner = owner; new_udriver->driver.dev_groups = new_udriver->dev_groups; retval = driver_register(&new_udriver->driver); if (!retval) { pr_info("%s: registered new device driver %s\n", usbcore_name, new_udriver->name); /* * Check whether any device could be better served with * this new driver */ bus_for_each_dev(&usb_bus_type, NULL, new_udriver, __usb_bus_reprobe_drivers); } else { pr_err("%s: error %d registering device driver %s\n", usbcore_name, retval, new_udriver->name); } return retval; } EXPORT_SYMBOL_GPL(usb_register_device_driver); /** * usb_deregister_device_driver - unregister a USB device (not interface) driver * @udriver: USB operations of the device driver to unregister * Context: must be able to sleep * * Unlinks the specified driver from the internal USB driver list. */ void usb_deregister_device_driver(struct usb_device_driver *udriver) { pr_info("%s: deregistering device driver %s\n", usbcore_name, udriver->name); driver_unregister(&udriver->driver); } EXPORT_SYMBOL_GPL(usb_deregister_device_driver); /** * usb_register_driver - register a USB interface driver * @new_driver: USB operations for the interface driver * @owner: module owner of this driver. * @mod_name: module name string * * Registers a USB interface driver with the USB core. The list of * unattached interfaces will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized interfaces. * * Return: A negative error code on failure and 0 on success. * * NOTE: if you want your driver to use the USB major number, you must call * usb_register_dev() to enable that functionality. This function no longer * takes care of that. */ int usb_register_driver(struct usb_driver *new_driver, struct module *owner, const char *mod_name) { int retval = 0; if (usb_disabled()) return -ENODEV; new_driver->driver.name = new_driver->name; new_driver->driver.bus = &usb_bus_type; new_driver->driver.probe = usb_probe_interface; new_driver->driver.remove = usb_unbind_interface; new_driver->driver.shutdown = usb_shutdown_interface; new_driver->driver.owner = owner; new_driver->driver.mod_name = mod_name; new_driver->driver.dev_groups = new_driver->dev_groups; INIT_LIST_HEAD(&new_driver->dynids.list); retval = driver_register(&new_driver->driver); if (retval) goto out; retval = usb_create_newid_files(new_driver); if (retval) goto out_newid; pr_info("%s: registered new interface driver %s\n", usbcore_name, new_driver->name); return 0; out_newid: driver_unregister(&new_driver->driver); out: pr_err("%s: error %d registering interface driver %s\n", usbcore_name, retval, new_driver->name); return retval; } EXPORT_SYMBOL_GPL(usb_register_driver); /** * usb_deregister - unregister a USB interface driver * @driver: USB operations of the interface driver to unregister * Context: must be able to sleep * * Unlinks the specified driver from the internal USB driver list. * * NOTE: If you called usb_register_dev(), you still need to call * usb_deregister_dev() to clean up your driver's allocated minor numbers, * this * call will no longer do it for you. */ void usb_deregister(struct usb_driver *driver) { pr_info("%s: deregistering interface driver %s\n", usbcore_name, driver->name); usb_remove_newid_files(driver); driver_unregister(&driver->driver); usb_free_dynids(driver); } EXPORT_SYMBOL_GPL(usb_deregister); /* Forced unbinding of a USB interface driver, either because * it doesn't support pre_reset/post_reset/reset_resume or * because it doesn't support suspend/resume. * * The caller must hold @intf's device's lock, but not @intf's lock. */ void usb_forced_unbind_intf(struct usb_interface *intf) { struct usb_driver *driver = to_usb_driver(intf->dev.driver); dev_dbg(&intf->dev, "forced unbind\n"); usb_driver_release_interface(driver, intf); /* Mark the interface for later rebinding */ intf->needs_binding = 1; } /* * Unbind drivers for @udev's marked interfaces. These interfaces have * the needs_binding flag set, for example by usb_resume_interface(). * * The caller must hold @udev's device lock. */ static void unbind_marked_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->dev.driver && intf->needs_binding) usb_forced_unbind_intf(intf); } } } /* Delayed forced unbinding of a USB interface driver and scan * for rebinding. * * The caller must hold @intf's device's lock, but not @intf's lock. * * Note: Rebinds will be skipped if a system sleep transition is in * progress and the PM "complete" callback hasn't occurred yet. */ static void usb_rebind_intf(struct usb_interface *intf) { int rc; /* Delayed unbind of an existing driver */ if (intf->dev.driver) usb_forced_unbind_intf(intf); /* Try to rebind the interface */ if (!intf->dev.power.is_prepared) { intf->needs_binding = 0; rc = device_attach(&intf->dev); if (rc < 0 && rc != -EPROBE_DEFER) dev_warn(&intf->dev, "rebind failed: %d\n", rc); } } /* * Rebind drivers to @udev's marked interfaces. These interfaces have * the needs_binding flag set. * * The caller must hold @udev's device lock. */ static void rebind_marked_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->needs_binding) usb_rebind_intf(intf); } } } /* * Unbind all of @udev's marked interfaces and then rebind all of them. * This ordering is necessary because some drivers claim several interfaces * when they are first probed. * * The caller must hold @udev's device lock. */ void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev) { unbind_marked_interfaces(udev); rebind_marked_interfaces(udev); } #ifdef CONFIG_PM /* Unbind drivers for @udev's interfaces that don't support suspend/resume * There is no check for reset_resume here because it can be determined * only during resume whether reset_resume is needed. * * The caller must hold @udev's device lock. */ static void unbind_no_pm_drivers_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; struct usb_driver *drv; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->dev.driver) { drv = to_usb_driver(intf->dev.driver); if (!drv->suspend || !drv->resume) usb_forced_unbind_intf(intf); } } } } static int usb_suspend_device(struct usb_device *udev, pm_message_t msg) { struct usb_device_driver *udriver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED || udev->state == USB_STATE_SUSPENDED) goto done; /* For devices that don't have a driver, we do a generic suspend. */ if (udev->dev.driver) udriver = to_usb_device_driver(udev->dev.driver); else { udev->do_remote_wakeup = 0; udriver = &usb_generic_driver; } if (udriver->suspend) status = udriver->suspend(udev, msg); if (status == 0 && udriver->generic_subclass) status = usb_generic_driver_suspend(udev, msg); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } static int usb_resume_device(struct usb_device *udev, pm_message_t msg) { struct usb_device_driver *udriver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED) goto done; /* Can't resume it if it doesn't have a driver. */ if (udev->dev.driver == NULL) { status = -ENOTCONN; goto done; } /* Non-root devices on a full/low-speed bus must wait for their * companion high-speed root hub, in case a handoff is needed. */ if (!PMSG_IS_AUTO(msg) && udev->parent && udev->bus->hs_companion) device_pm_wait_for_dev(&udev->dev, &udev->bus->hs_companion->root_hub->dev); if (udev->quirks & USB_QUIRK_RESET_RESUME) udev->reset_resume = 1; udriver = to_usb_device_driver(udev->dev.driver); if (udriver->generic_subclass) status = usb_generic_driver_resume(udev, msg); if (status == 0 && udriver->resume) status = udriver->resume(udev, msg); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } static int usb_suspend_interface(struct usb_device *udev, struct usb_interface *intf, pm_message_t msg) { struct usb_driver *driver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED || intf->condition == USB_INTERFACE_UNBOUND) goto done; driver = to_usb_driver(intf->dev.driver); /* at this time we know the driver supports suspend */ status = driver->suspend(intf, msg); if (status && !PMSG_IS_AUTO(msg)) dev_err(&intf->dev, "suspend error %d\n", status); done: dev_vdbg(&intf->dev, "%s: status %d\n", __func__, status); return status; } static int usb_resume_interface(struct usb_device *udev, struct usb_interface *intf, pm_message_t msg, int reset_resume) { struct usb_driver *driver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED) goto done; /* Don't let autoresume interfere with unbinding */ if (intf->condition == USB_INTERFACE_UNBINDING) goto done; /* Can't resume it if it doesn't have a driver. */ if (intf->condition == USB_INTERFACE_UNBOUND) { /* Carry out a deferred switch to altsetting 0 */ if (intf->needs_altsetting0 && !intf->dev.power.is_prepared) { usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); intf->needs_altsetting0 = 0; } goto done; } /* Don't resume if the interface is marked for rebinding */ if (intf->needs_binding) goto done; driver = to_usb_driver(intf->dev.driver); if (reset_resume) { if (driver->reset_resume) { status = driver->reset_resume(intf); if (status) dev_err(&intf->dev, "%s error %d\n", "reset_resume", status); } else { intf->needs_binding = 1; dev_dbg(&intf->dev, "no reset_resume for driver %s?\n", driver->name); } } else { status = driver->resume(intf); if (status) dev_err(&intf->dev, "resume error %d\n", status); } done: dev_vdbg(&intf->dev, "%s: status %d\n", __func__, status); /* Later we will unbind the driver and/or reprobe, if necessary */ return status; } /** * usb_suspend_both - suspend a USB device and its interfaces * @udev: the usb_device to suspend * @msg: Power Management message describing this state transition * * This is the central routine for suspending USB devices. It calls the * suspend methods for all the interface drivers in @udev and then calls * the suspend method for @udev itself. When the routine is called in * autosuspend, if an error occurs at any stage, all the interfaces * which were suspended are resumed so that they remain in the same * state as the device, but when called from system sleep, all error * from suspend methods of interfaces and the non-root-hub device itself * are simply ignored, so all suspended interfaces are only resumed * to the device's state when @udev is root-hub and its suspend method * returns failure. * * Autosuspend requests originating from a child device or an interface * driver may be made without the protection of @udev's device lock, but * all other suspend calls will hold the lock. Usbcore will insure that * method calls do not arrive during bind, unbind, or reset operations. * However drivers must be prepared to handle suspend calls arriving at * unpredictable times. * * This routine can run only in process context. * * Return: 0 if the suspend succeeded. */ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) { int status = 0; int i = 0, n = 0; struct usb_interface *intf; if (udev->state == USB_STATE_NOTATTACHED || udev->state == USB_STATE_SUSPENDED) goto done; /* Suspend all the interfaces and then udev itself */ if (udev->actconfig) { n = udev->actconfig->desc.bNumInterfaces; for (i = n - 1; i >= 0; --i) { intf = udev->actconfig->interface[i]; status = usb_suspend_interface(udev, intf, msg); /* Ignore errors during system sleep transitions */ if (!PMSG_IS_AUTO(msg)) status = 0; if (status != 0) break; } } if (status == 0) { status = usb_suspend_device(udev, msg); /* * Ignore errors from non-root-hub devices during * system sleep transitions. For the most part, * these devices should go to low power anyway when * the entire bus is suspended. */ if (udev->parent && !PMSG_IS_AUTO(msg)) status = 0; /* * If the device is inaccessible, don't try to resume * suspended interfaces and just return the error. */ if (status && status != -EBUSY) { int err; u16 devstat; err = usb_get_std_status(udev, USB_RECIP_DEVICE, 0, &devstat); if (err) { dev_err(&udev->dev, "Failed to suspend device, error %d\n", status); goto done; } } } /* If the suspend failed, resume interfaces that did get suspended */ if (status != 0) { if (udev->actconfig) { msg.event ^= (PM_EVENT_SUSPEND | PM_EVENT_RESUME); while (++i < n) { intf = udev->actconfig->interface[i]; usb_resume_interface(udev, intf, msg, 0); } } /* If the suspend succeeded then prevent any more URB submissions * and flush any outstanding URBs. */ } else { udev->can_submit = 0; for (i = 0; i < 16; ++i) { usb_hcd_flush_endpoint(udev, udev->ep_out[i]); usb_hcd_flush_endpoint(udev, udev->ep_in[i]); } } done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } /** * usb_resume_both - resume a USB device and its interfaces * @udev: the usb_device to resume * @msg: Power Management message describing this state transition * * This is the central routine for resuming USB devices. It calls the * resume method for @udev and then calls the resume methods for all * the interface drivers in @udev. * * Autoresume requests originating from a child device or an interface * driver may be made without the protection of @udev's device lock, but * all other resume calls will hold the lock. Usbcore will insure that * method calls do not arrive during bind, unbind, or reset operations. * However drivers must be prepared to handle resume calls arriving at * unpredictable times. * * This routine can run only in process context. * * Return: 0 on success. */ static int usb_resume_both(struct usb_device *udev, pm_message_t msg) { int status = 0; int i; struct usb_interface *intf; if (udev->state == USB_STATE_NOTATTACHED) { status = -ENODEV; goto done; } udev->can_submit = 1; /* Resume the device */ if (udev->state == USB_STATE_SUSPENDED || udev->reset_resume) status = usb_resume_device(udev, msg); /* Resume the interfaces */ if (status == 0 && udev->actconfig) { for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { intf = udev->actconfig->interface[i]; usb_resume_interface(udev, intf, msg, udev->reset_resume); } } usb_mark_last_busy(udev); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); if (!status) udev->reset_resume = 0; return status; } static void choose_wakeup(struct usb_device *udev, pm_message_t msg) { int w; /* * For FREEZE/QUIESCE, disable remote wakeups so no interrupts get * generated. */ if (msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_QUIESCE) { w = 0; } else { /* * Enable remote wakeup if it is allowed, even if no interface * drivers actually want it. */ w = device_may_wakeup(&udev->dev); } /* * If the device is autosuspended with the wrong wakeup setting, * autoresume now so the setting can be changed. */ if (udev->state == USB_STATE_SUSPENDED && w != udev->do_remote_wakeup) pm_runtime_resume(&udev->dev); udev->do_remote_wakeup = w; } /* The device lock is held by the PM core */ int usb_suspend(struct device *dev, pm_message_t msg) { struct usb_device *udev = to_usb_device(dev); int r; unbind_no_pm_drivers_interfaces(udev); /* From now on we are sure all drivers support suspend/resume * but not necessarily reset_resume() * so we may still need to unbind and rebind upon resume */ choose_wakeup(udev, msg); r = usb_suspend_both(udev, msg); if (r) return r; if (udev->quirks & USB_QUIRK_DISCONNECT_SUSPEND) usb_port_disable(udev); return 0; } /* The device lock is held by the PM core */ int usb_resume_complete(struct device *dev) { struct usb_device *udev = to_usb_device(dev); /* For PM complete calls, all we do is rebind interfaces * whose needs_binding flag is set */ if (udev->state != USB_STATE_NOTATTACHED) rebind_marked_interfaces(udev); return 0; } /* The device lock is held by the PM core */ int usb_resume(struct device *dev, pm_message_t msg) { struct usb_device *udev = to_usb_device(dev); int status; /* For all calls, take the device back to full power and * tell the PM core in case it was autosuspended previously. * Unbind the interfaces that will need rebinding later, * because they fail to support reset_resume. * (This can't be done in usb_resume_interface() * above because it doesn't own the right set of locks.) */ status = usb_resume_both(udev, msg); if (status == 0) { pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); unbind_marked_interfaces(udev); } /* Avoid PM error messages for devices disconnected while suspended * as we'll display regular disconnect messages just a bit later. */ if (status == -ENODEV || status == -ESHUTDOWN) status = 0; return status; } /** * usb_enable_autosuspend - allow a USB device to be autosuspended * @udev: the USB device which may be autosuspended * * This routine allows @udev to be autosuspended. An autosuspend won't * take place until the autosuspend_delay has elapsed and all the other * necessary conditions are satisfied. * * The caller must hold @udev's device lock. */ void usb_enable_autosuspend(struct usb_device *udev) { pm_runtime_allow(&udev->dev); } EXPORT_SYMBOL_GPL(usb_enable_autosuspend); /** * usb_disable_autosuspend - prevent a USB device from being autosuspended * @udev: the USB device which may not be autosuspended * * This routine prevents @udev from being autosuspended and wakes it up * if it is already autosuspended. * * The caller must hold @udev's device lock. */ void usb_disable_autosuspend(struct usb_device *udev) { pm_runtime_forbid(&udev->dev); } EXPORT_SYMBOL_GPL(usb_disable_autosuspend); /** * usb_autosuspend_device - delayed autosuspend of a USB device and its interfaces * @udev: the usb_device to autosuspend * * This routine should be called when a core subsystem is finished using * @udev and wants to allow it to autosuspend. Examples would be when * @udev's device file in usbfs is closed or after a configuration change. * * @udev's usage counter is decremented; if it drops to 0 and all the * interfaces are inactive then a delayed autosuspend will be attempted. * The attempt may fail (see autosuspend_check()). * * The caller must hold @udev's device lock. * * This routine can run only in process context. */ void usb_autosuspend_device(struct usb_device *udev) { int status; usb_mark_last_busy(udev); status = pm_runtime_put_sync_autosuspend(&udev->dev); dev_vdbg(&udev->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&udev->dev.power.usage_count), status); } /** * usb_autoresume_device - immediately autoresume a USB device and its interfaces * @udev: the usb_device to autoresume * * This routine should be called when a core subsystem wants to use @udev * and needs to guarantee that it is not suspended. No autosuspend will * occur until usb_autosuspend_device() is called. (Note that this will * not prevent suspend events originating in the PM core.) Examples would * be when @udev's device file in usbfs is opened or when a remote-wakeup * request is received. * * @udev's usage counter is incremented to prevent subsequent autosuspends. * However if the autoresume fails then the usage counter is re-decremented. * * The caller must hold @udev's device lock. * * This routine can run only in process context. * * Return: 0 on success. A negative error code otherwise. */ int usb_autoresume_device(struct usb_device *udev) { int status; status = pm_runtime_resume_and_get(&udev->dev); dev_vdbg(&udev->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&udev->dev.power.usage_count), status); if (status > 0) status = 0; return status; } /** * usb_autopm_put_interface - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine should be called by an interface driver when it is * finished using @intf and wants to allow it to autosuspend. A typical * example would be a character-device driver when its device file is * closed. * * The routine decrements @intf's usage counter. When the counter reaches * 0, a delayed autosuspend request for @intf's device is attempted. The * attempt may fail (see autosuspend_check()). * * This routine can run only in process context. */ void usb_autopm_put_interface(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); int status; usb_mark_last_busy(udev); status = pm_runtime_put_sync(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface); /** * usb_autopm_put_interface_async - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine does much the same thing as usb_autopm_put_interface(): * It decrements @intf's usage counter and schedules a delayed * autosuspend request if the counter is <= 0. The difference is that it * does not perform any synchronization; callers should hold a private * lock and handle all synchronization issues themselves. * * Typically a driver would call this routine during an URB's completion * handler, if no more URBs were pending. * * This routine can run in atomic context. */ void usb_autopm_put_interface_async(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); int status; usb_mark_last_busy(udev); status = pm_runtime_put(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_async); /** * usb_autopm_put_interface_no_suspend - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine decrements @intf's usage counter but does not carry out an * autosuspend. * * This routine can run in atomic context. */ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); pm_runtime_put_noidle(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); /** * usb_autopm_get_interface - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine should be called by an interface driver when it wants to * use @intf and needs to guarantee that it is not suspended. In addition, * the routine prevents @intf from being autosuspended subsequently. (Note * that this will not prevent suspend events originating in the PM core.) * This prevention will persist until usb_autopm_put_interface() is called * or @intf is unbound. A typical example would be a character-device * driver when its device file is opened. * * @intf's usage counter is incremented to prevent subsequent autosuspends. * However if the autoresume fails then the counter is re-decremented. * * This routine can run only in process context. * * Return: 0 on success. */ int usb_autopm_get_interface(struct usb_interface *intf) { int status; status = pm_runtime_resume_and_get(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); if (status > 0) status = 0; return status; } EXPORT_SYMBOL_GPL(usb_autopm_get_interface); /** * usb_autopm_get_interface_async - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine does much the same thing as * usb_autopm_get_interface(): It increments @intf's usage counter and * queues an autoresume request if the device is suspended. The * differences are that it does not perform any synchronization (callers * should hold a private lock and handle all synchronization issues * themselves), and it does not autoresume the device directly (it only * queues a request). After a successful call, the device may not yet be * resumed. * * This routine can run in atomic context. * * Return: 0 on success. A negative error code otherwise. */ int usb_autopm_get_interface_async(struct usb_interface *intf) { int status; status = pm_runtime_get(&intf->dev); if (status < 0 && status != -EINPROGRESS) pm_runtime_put_noidle(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); if (status > 0 || status == -EINPROGRESS) status = 0; return status; } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_async); /** * usb_autopm_get_interface_no_resume - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine increments @intf's usage counter but does not carry out an * autoresume. * * This routine can run in atomic context. */ void usb_autopm_get_interface_no_resume(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); pm_runtime_get_noresume(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume); /* Internal routine to check whether we may autosuspend a device. */ static int autosuspend_check(struct usb_device *udev) { int w, i; struct usb_interface *intf; if (udev->state == USB_STATE_NOTATTACHED) return -ENODEV; /* Fail if autosuspend is disabled, or any interfaces are in use, or * any interface drivers require remote wakeup but it isn't available. */ w = 0; if (udev->actconfig) { for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { intf = udev->actconfig->interface[i]; /* We don't need to check interfaces that are * disabled for runtime PM. Either they are unbound * or else their drivers don't support autosuspend * and so they are permanently active. */ if (intf->dev.power.disable_depth) continue; if (atomic_read(&intf->dev.power.usage_count) > 0) return -EBUSY; w |= intf->needs_remote_wakeup; /* Don't allow autosuspend if the device will need * a reset-resume and any of its interface drivers * doesn't include support or needs remote wakeup. */ if (udev->quirks & USB_QUIRK_RESET_RESUME) { struct usb_driver *driver; driver = to_usb_driver(intf->dev.driver); if (!driver->reset_resume || intf->needs_remote_wakeup) return -EOPNOTSUPP; } } } if (w && !device_can_wakeup(&udev->dev)) { dev_dbg(&udev->dev, "remote wakeup needed for autosuspend\n"); return -EOPNOTSUPP; } /* * If the device is a direct child of the root hub and the HCD * doesn't handle wakeup requests, don't allow autosuspend when * wakeup is needed. */ if (w && udev->parent == udev->bus->root_hub && bus_to_hcd(udev->bus)->cant_recv_wakeups) { dev_dbg(&udev->dev, "HCD doesn't handle wakeup requests\n"); return -EOPNOTSUPP; } udev->do_remote_wakeup = w; return 0; } int usb_runtime_suspend(struct device *dev) { struct usb_device *udev = to_usb_device(dev); int status; /* A USB device can be suspended if it passes the various autosuspend * checks. Runtime suspend for a USB device means suspending all the * interfaces and then the device itself. */ if (autosuspend_check(udev) != 0) return -EAGAIN; status = usb_suspend_both(udev, PMSG_AUTO_SUSPEND); /* Allow a retry if autosuspend failed temporarily */ if (status == -EAGAIN || status == -EBUSY) usb_mark_last_busy(udev); /* * The PM core reacts badly unless the return code is 0, * -EAGAIN, or -EBUSY, so always return -EBUSY on an error * (except for root hubs, because they don't suspend through * an upstream port like other USB devices). */ if (status != 0 && udev->parent) return -EBUSY; return status; } int usb_runtime_resume(struct device *dev) { struct usb_device *udev = to_usb_device(dev); int status; /* Runtime resume for a USB device means resuming both the device * and all its interfaces. */ status = usb_resume_both(udev, PMSG_AUTO_RESUME); return status; } int usb_runtime_idle(struct device *dev) { struct usb_device *udev = to_usb_device(dev); /* An idle USB device can be suspended if it passes the various * autosuspend checks. */ if (autosuspend_check(udev) == 0) pm_runtime_autosuspend(dev); /* Tell the core not to suspend it, though. */ return -EBUSY; } static int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) { struct usb_hcd *hcd = bus_to_hcd(udev->bus); int ret = -EPERM; if (hcd->driver->set_usb2_hw_lpm) { ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable); if (!ret) udev->usb2_hw_lpm_enabled = enable; } return ret; } int usb_enable_usb2_hardware_lpm(struct usb_device *udev) { if (!udev->usb2_hw_lpm_capable || !udev->usb2_hw_lpm_allowed || udev->usb2_hw_lpm_enabled) return 0; return usb_set_usb2_hardware_lpm(udev, 1); } int usb_disable_usb2_hardware_lpm(struct usb_device *udev) { if (!udev->usb2_hw_lpm_enabled) return 0; return usb_set_usb2_hardware_lpm(udev, 0); } #endif /* CONFIG_PM */ const struct bus_type usb_bus_type = { .name = "usb", .match = usb_device_match, .uevent = usb_uevent, .need_parent_lock = true, }; |
| 1 1 1 1 1 1 1 1 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. * https://www.huawei.com/ * Copyright (C) 2021, Alibaba Cloud */ #include <linux/statfs.h> #include <linux/seq_file.h> #include <linux/crc32c.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/exportfs.h> #include <linux/backing-dev.h> #include "xattr.h" #define CREATE_TRACE_POINTS #include <trace/events/erofs.h> static struct kmem_cache *erofs_inode_cachep __read_mostly; void _erofs_printk(struct super_block *sb, const char *fmt, ...) { struct va_format vaf; va_list args; int level; va_start(args, fmt); level = printk_get_level(fmt); vaf.fmt = printk_skip_level(fmt); vaf.va = &args; if (sb) printk("%c%cerofs (device %s): %pV", KERN_SOH_ASCII, level, sb->s_id, &vaf); else printk("%c%cerofs: %pV", KERN_SOH_ASCII, level, &vaf); va_end(args); } static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata) { struct erofs_super_block *dsb = sbdata + EROFS_SUPER_OFFSET; u32 len = 1 << EROFS_SB(sb)->blkszbits, crc; if (len > EROFS_SUPER_OFFSET) len -= EROFS_SUPER_OFFSET; len -= offsetof(struct erofs_super_block, checksum) + sizeof(dsb->checksum); /* skip .magic(pre-verified) and .checksum(0) fields */ crc = crc32c(0x5045B54A, (&dsb->checksum) + 1, len); if (crc == le32_to_cpu(dsb->checksum)) return 0; erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected", crc, le32_to_cpu(dsb->checksum)); return -EBADMSG; } static void erofs_inode_init_once(void *ptr) { struct erofs_inode *vi = ptr; inode_init_once(&vi->vfs_inode); } static struct inode *erofs_alloc_inode(struct super_block *sb) { struct erofs_inode *vi = alloc_inode_sb(sb, erofs_inode_cachep, GFP_KERNEL); if (!vi) return NULL; /* zero out everything except vfs_inode */ memset(vi, 0, offsetof(struct erofs_inode, vfs_inode)); return &vi->vfs_inode; } static void erofs_free_inode(struct inode *inode) { struct erofs_inode *vi = EROFS_I(inode); if (inode->i_op == &erofs_fast_symlink_iops) kfree(inode->i_link); kfree(vi->xattr_shared_xattrs); kmem_cache_free(erofs_inode_cachep, vi); } /* read variable-sized metadata, offset will be aligned by 4-byte */ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; *offset = round_up(*offset, 4); ptr = erofs_bread(buf, *offset, true); if (IS_ERR(ptr)) return ptr; len = le16_to_cpu(*(__le16 *)ptr); if (!len) len = U16_MAX + 1; buffer = kmalloc(len, GFP_KERNEL); if (!buffer) return ERR_PTR(-ENOMEM); *offset += sizeof(__le16); *lengthp = len; for (i = 0; i < len; i += cnt) { cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset), len - i); ptr = erofs_bread(buf, *offset, true); if (IS_ERR(ptr)) { kfree(buffer); return ptr; } memcpy(buffer + i, ptr, cnt); *offset += cnt; } return buffer; } #ifndef CONFIG_EROFS_FS_ZIP static int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) { if (!dsb->u1.available_compr_algs) return 0; erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); return -EOPNOTSUPP; } #endif static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct erofs_device_info *dif, erofs_off_t *pos) { struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_fscache *fscache; struct erofs_deviceslot *dis; struct file *file; dis = erofs_read_metabuf(buf, sb, *pos, true); if (IS_ERR(dis)) return PTR_ERR(dis); if (!sbi->devs->flatdev && !dif->path) { if (!dis->tag[0]) { erofs_err(sb, "empty device tag @ pos %llu", *pos); return -EINVAL; } dif->path = kmemdup_nul(dis->tag, sizeof(dis->tag), GFP_KERNEL); if (!dif->path) return -ENOMEM; } if (erofs_is_fscache_mode(sb)) { fscache = erofs_fscache_register_cookie(sb, dif->path, 0); if (IS_ERR(fscache)) return PTR_ERR(fscache); dif->fscache = fscache; } else if (!sbi->devs->flatdev) { file = erofs_is_fileio_mode(sbi) ? filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) : bdev_file_open_by_path(dif->path, BLK_OPEN_READ, sb->s_type, NULL); if (IS_ERR(file)) { if (file == ERR_PTR(-ENOTBLK)) return -EINVAL; return PTR_ERR(file); } if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; } dif->file = file; } dif->blocks = le32_to_cpu(dis->blocks_lo); dif->uniaddr = le32_to_cpu(dis->uniaddr_lo); sbi->total_blocks += dif->blocks; *pos += EROFS_DEVT_SLOT_SIZE; return 0; } static int erofs_scan_devices(struct super_block *sb, struct erofs_super_block *dsb) { struct erofs_sb_info *sbi = EROFS_SB(sb); unsigned int ondisk_extradevs; erofs_off_t pos; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_device_info *dif; int id, err = 0; sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else ondisk_extradevs = le16_to_cpu(dsb->extra_devices); if (sbi->devs->extra_devices && ondisk_extradevs != sbi->devs->extra_devices) { erofs_err(sb, "extra devices don't match (ondisk %u, given %u)", ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } if (!ondisk_extradevs) return 0; if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1; pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE; down_read(&sbi->devs->rwsem); if (sbi->devs->extra_devices) { idr_for_each_entry(&sbi->devs->tree, dif, id) { err = erofs_init_device(&buf, sb, dif, &pos); if (err) break; } } else { for (id = 0; id < ondisk_extradevs; id++) { dif = kzalloc(sizeof(*dif), GFP_KERNEL); if (!dif) { err = -ENOMEM; break; } err = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); if (err < 0) { kfree(dif); break; } ++sbi->devs->extra_devices; err = erofs_init_device(&buf, sb, dif, &pos); if (err) break; } } up_read(&sbi->devs->rwsem); erofs_put_metabuf(&buf); return err; } static int erofs_read_superblock(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_super_block *dsb; void *data; int ret; data = erofs_read_metabuf(&buf, sb, 0, true); if (IS_ERR(data)) { erofs_err(sb, "cannot read erofs superblock"); return PTR_ERR(data); } dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET); ret = -EINVAL; if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) { erofs_err(sb, "cannot find valid erofs superblock"); goto out; } sbi->blkszbits = dsb->blkszbits; if (sbi->blkszbits < 9 || sbi->blkszbits > PAGE_SHIFT) { erofs_err(sb, "blkszbits %u isn't supported", sbi->blkszbits); goto out; } if (dsb->dirblkbits) { erofs_err(sb, "dirblkbits %u isn't supported", dsb->dirblkbits); goto out; } sbi->feature_compat = le32_to_cpu(dsb->feature_compat); if (erofs_sb_has_sb_chksum(sbi)) { ret = erofs_superblock_csum_verify(sb, data); if (ret) goto out; } ret = -EINVAL; sbi->feature_incompat = le32_to_cpu(dsb->feature_incompat); if (sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT) { erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel", sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT); goto out; } sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE; if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) { erofs_err(sb, "invalid sb_extslots %u (more than a fs block)", sbi->sb_size); goto out; } sbi->dif0.blocks = le32_to_cpu(dsb->blocks_lo); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); sbi->xattr_prefix_start = le32_to_cpu(dsb->xattr_prefix_start); sbi->xattr_prefix_count = dsb->xattr_prefix_count; sbi->xattr_filter_reserved = dsb->xattr_filter_reserved; #endif sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) { sbi->root_nid = le64_to_cpu(dsb->rootnid_8b); sbi->dif0.blocks = (sbi->dif0.blocks << 32) | le16_to_cpu(dsb->rb.blocks_hi); } else { sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b); } sbi->packed_nid = le64_to_cpu(dsb->packed_nid); sbi->inos = le64_to_cpu(dsb->inos); sbi->epoch = (s64)le64_to_cpu(dsb->epoch); sbi->fixed_nsec = le32_to_cpu(dsb->fixed_nsec); super_set_uuid(sb, (void *)dsb->uuid, sizeof(dsb->uuid)); /* parse on-disk compression configurations */ ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_48bit(sbi)) erofs_info(sb, "EXPERIMENTAL 48-bit layout support in use. Use at your own risk!"); if (erofs_is_fscache_mode(sb)) erofs_info(sb, "[deprecated] fscache-based on-demand read feature in use. Use at your own risk!"); out: erofs_put_metabuf(&buf); return ret; } static void erofs_default_options(struct erofs_sb_info *sbi) { #ifdef CONFIG_EROFS_FS_ZIP sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; sbi->opt.max_sync_decompress_pages = 3; sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; #endif #ifdef CONFIG_EROFS_FS_XATTR set_opt(&sbi->opt, XATTR_USER); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL set_opt(&sbi->opt, POSIX_ACL); #endif } enum { Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_fsoffset, }; static const struct constant_table erofs_param_cache_strategy[] = { {"disabled", EROFS_ZIP_CACHE_DISABLED}, {"readahead", EROFS_ZIP_CACHE_READAHEAD}, {"readaround", EROFS_ZIP_CACHE_READAROUND}, {} }; static const struct constant_table erofs_dax_param_enums[] = { {"always", EROFS_MOUNT_DAX_ALWAYS}, {"never", EROFS_MOUNT_DAX_NEVER}, {} }; static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_flag_no("user_xattr", Opt_user_xattr), fsparam_flag_no("acl", Opt_acl), fsparam_enum("cache_strategy", Opt_cache_strategy, erofs_param_cache_strategy), fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, erofs_dax_param_enums), fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), fsparam_flag_no("directio", Opt_directio), fsparam_u64("fsoffset", Opt_fsoffset), {} }; static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) { #ifdef CONFIG_FS_DAX struct erofs_sb_info *sbi = fc->s_fs_info; switch (mode) { case EROFS_MOUNT_DAX_ALWAYS: set_opt(&sbi->opt, DAX_ALWAYS); clear_opt(&sbi->opt, DAX_NEVER); return true; case EROFS_MOUNT_DAX_NEVER: set_opt(&sbi->opt, DAX_NEVER); clear_opt(&sbi->opt, DAX_ALWAYS); return true; default: DBG_BUGON(1); return false; } #else errorfc(fc, "dax options not supported"); return false; #endif } static int erofs_fc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct erofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; struct erofs_device_info *dif; int opt, ret; opt = fs_parse(fc, erofs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_user_xattr: #ifdef CONFIG_EROFS_FS_XATTR if (result.boolean) set_opt(&sbi->opt, XATTR_USER); else clear_opt(&sbi->opt, XATTR_USER); #else errorfc(fc, "{,no}user_xattr options not supported"); #endif break; case Opt_acl: #ifdef CONFIG_EROFS_FS_POSIX_ACL if (result.boolean) set_opt(&sbi->opt, POSIX_ACL); else clear_opt(&sbi->opt, POSIX_ACL); #else errorfc(fc, "{,no}acl options not supported"); #endif break; case Opt_cache_strategy: #ifdef CONFIG_EROFS_FS_ZIP sbi->opt.cache_strategy = result.uint_32; #else errorfc(fc, "compression not supported, cache_strategy ignored"); #endif break; case Opt_dax: if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS)) return -EINVAL; break; case Opt_dax_enum: if (!erofs_fc_set_dax_mode(fc, result.uint_32)) return -EINVAL; break; case Opt_device: dif = kzalloc(sizeof(*dif), GFP_KERNEL); if (!dif) return -ENOMEM; dif->path = kstrdup(param->string, GFP_KERNEL); if (!dif->path) { kfree(dif); return -ENOMEM; } down_write(&sbi->devs->rwsem); ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); up_write(&sbi->devs->rwsem); if (ret < 0) { kfree(dif->path); kfree(dif); return ret; } ++sbi->devs->extra_devices; break; #ifdef CONFIG_EROFS_FS_ONDEMAND case Opt_fsid: kfree(sbi->fsid); sbi->fsid = kstrdup(param->string, GFP_KERNEL); if (!sbi->fsid) return -ENOMEM; break; case Opt_domain_id: kfree(sbi->domain_id); sbi->domain_id = kstrdup(param->string, GFP_KERNEL); if (!sbi->domain_id) return -ENOMEM; break; #else case Opt_fsid: case Opt_domain_id: errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif case Opt_directio: #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (result.boolean) set_opt(&sbi->opt, DIRECT_IO); else clear_opt(&sbi->opt, DIRECT_IO); #else errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); #endif break; case Opt_fsoffset: sbi->dif0.fsoff = result.uint_64; break; } return 0; } static int erofs_encode_fh(struct inode *inode, u32 *fh, int *max_len, struct inode *parent) { erofs_nid_t nid = EROFS_I(inode)->nid; int len = parent ? 6 : 3; if (*max_len < len) { *max_len = len; return FILEID_INVALID; } fh[0] = (u32)(nid >> 32); fh[1] = (u32)(nid & 0xffffffff); fh[2] = inode->i_generation; if (parent) { nid = EROFS_I(parent)->nid; fh[3] = (u32)(nid >> 32); fh[4] = (u32)(nid & 0xffffffff); fh[5] = parent->i_generation; } *max_len = len; return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN; } static struct dentry *erofs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if ((fh_type != FILEID_INO64_GEN && fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3) return NULL; return d_obtain_alias(erofs_iget(sb, ((u64)fid->raw[0] << 32) | fid->raw[1])); } static struct dentry *erofs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6) return NULL; return d_obtain_alias(erofs_iget(sb, ((u64)fid->raw[3] << 32) | fid->raw[4])); } static struct dentry *erofs_get_parent(struct dentry *child) { erofs_nid_t nid; unsigned int d_type; int err; err = erofs_namei(d_inode(child), &dotdot_name, &nid, &d_type); if (err) return ERR_PTR(err); return d_obtain_alias(erofs_iget(child->d_sb, nid)); } static const struct export_operations erofs_export_ops = { .encode_fh = erofs_encode_fh, .fh_to_dentry = erofs_fh_to_dentry, .fh_to_parent = erofs_fh_to_parent, .get_parent = erofs_get_parent, }; static void erofs_set_sysfs_name(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); if (sbi->domain_id) super_set_sysfs_name_generic(sb, "%s,%s", sbi->domain_id, sbi->fsid); else if (sbi->fsid) super_set_sysfs_name_generic(sb, "%s", sbi->fsid); else if (erofs_is_fileio_mode(sbi)) super_set_sysfs_name_generic(sb, "%s", bdi_dev_name(sb->s_bdi)); else super_set_sysfs_name_id(sb); } static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct erofs_sb_info *sbi = EROFS_SB(sb); int err; sb->s_magic = EROFS_SUPER_MAGIC; sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_op = &erofs_sops; sbi->blkszbits = PAGE_SHIFT; if (!sb->s_bdev) { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; if (erofs_is_fscache_mode(sb)) { err = erofs_fscache_register_fs(sb); if (err) return err; } err = super_setup_bdi(sb); if (err) return err; } else { if (!sb_set_blocksize(sb, PAGE_SIZE)) { errorfc(fc, "failed to set initial blksize"); return -EINVAL; } sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); if (err) return err; if (sb->s_blocksize_bits != sbi->blkszbits) { if (erofs_is_fscache_mode(sb)) { errorfc(fc, "unsupported blksize for fscache mode"); return -EINVAL; } if (erofs_is_fileio_mode(sbi)) { sb->s_blocksize = 1 << sbi->blkszbits; sb->s_blocksize_bits = sbi->blkszbits; } else if (!sb_set_blocksize(sb, 1 << sbi->blkszbits)) { errorfc(fc, "failed to set erofs blksize"); return -EINVAL; } } if (sbi->dif0.fsoff) { if (sbi->dif0.fsoff & (sb->s_blocksize - 1)) return invalfc(fc, "fsoffset %llu is not aligned to block size %lu", sbi->dif0.fsoff, sb->s_blocksize); if (erofs_is_fscache_mode(sb)) return invalfc(fc, "cannot use fsoffset in fscache mode"); } if (test_opt(&sbi->opt, DAX_ALWAYS)) { if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { errorfc(fc, "unsupported blocksize for DAX"); clear_opt(&sbi->opt, DAX_ALWAYS); } } sb->s_time_gran = 1; sb->s_xattr = erofs_xattr_handlers; sb->s_export_op = &erofs_export_ops; if (test_opt(&sbi->opt, POSIX_ACL)) sb->s_flags |= SB_POSIXACL; else sb->s_flags &= ~SB_POSIXACL; err = z_erofs_init_super(sb); if (err) return err; if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) { inode = erofs_iget(sb, sbi->packed_nid); if (IS_ERR(inode)) return PTR_ERR(inode); sbi->packed_inode = inode; } inode = erofs_iget(sb, sbi->root_nid); if (IS_ERR(inode)) return PTR_ERR(inode); if (!S_ISDIR(inode->i_mode)) { erofs_err(sb, "rootino(nid %llu) is not a directory(i_mode %o)", sbi->root_nid, inode->i_mode); iput(inode); return -EINVAL; } sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; erofs_shrinker_register(sb); err = erofs_xattr_prefixes_init(sb); if (err) return err; erofs_set_sysfs_name(sb); err = erofs_register_sysfs(sb); if (err) return err; erofs_info(sb, "mounted with root inode @ nid %llu.", sbi->root_nid); return 0; } static int erofs_fc_get_tree(struct fs_context *fc) { struct erofs_sb_info *sbi = fc->s_fs_info; int ret; if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) return get_tree_nodev(fc, erofs_fc_fill_super); ret = get_tree_bdev_flags(fc, erofs_fc_fill_super, IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ? GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { struct file *file; if (!fc->source) return invalf(fc, "No source specified"); file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); if (IS_ERR(file)) return PTR_ERR(file); sbi->dif0.file = file; if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); } #endif return ret; } static int erofs_fc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_sb_info *new_sbi = fc->s_fs_info; DBG_BUGON(!sb_rdonly(sb)); if (new_sbi->fsid || new_sbi->domain_id) erofs_info(sb, "ignoring reconfiguration for fsid|domain_id."); if (test_opt(&new_sbi->opt, POSIX_ACL)) fc->sb_flags |= SB_POSIXACL; else fc->sb_flags &= ~SB_POSIXACL; sbi->opt = new_sbi->opt; fc->sb_flags |= SB_RDONLY; return 0; } static int erofs_release_device_info(int id, void *ptr, void *data) { struct erofs_device_info *dif = ptr; fs_put_dax(dif->dax_dev, NULL); if (dif->file) fput(dif->file); erofs_fscache_unregister_cookie(dif->fscache); dif->fscache = NULL; kfree(dif->path); kfree(dif); return 0; } static void erofs_free_dev_context(struct erofs_dev_context *devs) { if (!devs) return; idr_for_each(&devs->tree, &erofs_release_device_info, NULL); idr_destroy(&devs->tree); kfree(devs); } static void erofs_sb_free(struct erofs_sb_info *sbi) { erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); if (sbi->dif0.file) fput(sbi->dif0.file); kfree(sbi); } static void erofs_fc_free(struct fs_context *fc) { struct erofs_sb_info *sbi = fc->s_fs_info; if (sbi) /* free here if an error occurs before transferring to sb */ erofs_sb_free(sbi); } static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, .reconfigure = erofs_fc_reconfigure, .free = erofs_fc_free, }; static int erofs_init_fs_context(struct fs_context *fc) { struct erofs_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); if (!sbi->devs) { kfree(sbi); return -ENOMEM; } fc->s_fs_info = sbi; idr_init(&sbi->devs->tree); init_rwsem(&sbi->devs->rwsem); erofs_default_options(sbi); fc->ops = &erofs_context_ops; return 0; } static void erofs_drop_internal_inodes(struct erofs_sb_info *sbi) { iput(sbi->packed_inode); sbi->packed_inode = NULL; #ifdef CONFIG_EROFS_FS_ZIP iput(sbi->managed_cache); sbi->managed_cache = NULL; #endif } static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); erofs_drop_internal_inodes(sbi); fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); erofs_sb_free(sbi); sb->s_fs_info = NULL; } static void erofs_put_super(struct super_block *sb) { struct erofs_sb_info *const sbi = EROFS_SB(sb); erofs_unregister_sysfs(sb); erofs_shrinker_unregister(sb); erofs_xattr_prefixes_cleanup(sb); erofs_drop_internal_inodes(sbi); erofs_free_dev_context(sbi->devs); sbi->devs = NULL; erofs_fscache_unregister_fs(sb); } static struct file_system_type erofs_fs_type = { .owner = THIS_MODULE, .name = "erofs", .init_fs_context = erofs_init_fs_context, .kill_sb = erofs_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("erofs"); static int __init erofs_module_init(void) { int err; erofs_check_ondisk_layout_definitions(); erofs_inode_cachep = kmem_cache_create("erofs_inode", sizeof(struct erofs_inode), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, erofs_inode_init_once); if (!erofs_inode_cachep) return -ENOMEM; err = erofs_init_shrinker(); if (err) goto shrinker_err; err = z_erofs_init_subsystem(); if (err) goto zip_err; err = erofs_init_sysfs(); if (err) goto sysfs_err; err = register_filesystem(&erofs_fs_type); if (err) goto fs_err; return 0; fs_err: erofs_exit_sysfs(); sysfs_err: z_erofs_exit_subsystem(); zip_err: erofs_exit_shrinker(); shrinker_err: kmem_cache_destroy(erofs_inode_cachep); return err; } static void __exit erofs_module_exit(void) { unregister_filesystem(&erofs_fs_type); /* Ensure all RCU free inodes / pclusters are safe to be destroyed. */ rcu_barrier(); erofs_exit_sysfs(); z_erofs_exit_subsystem(); erofs_exit_shrinker(); kmem_cache_destroy(erofs_inode_cachep); } static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); buf->f_type = sb->s_magic; buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->total_blocks; buf->f_bfree = buf->f_bavail = 0; buf->f_files = ULLONG_MAX; buf->f_ffree = ULLONG_MAX - sbi->inos; buf->f_namelen = EROFS_NAME_LEN; if (uuid_is_null(&sb->s_uuid)) buf->f_fsid = u64_to_fsid(!sb->s_bdev ? 0 : huge_encode_dev(sb->s_bdev->bd_dev)); else buf->f_fsid = uuid_to_fsid(sb->s_uuid.b); return 0; } static int erofs_show_options(struct seq_file *seq, struct dentry *root) { struct erofs_sb_info *sbi = EROFS_SB(root->d_sb); struct erofs_mount_opts *opt = &sbi->opt; if (IS_ENABLED(CONFIG_EROFS_FS_XATTR)) seq_puts(seq, test_opt(opt, XATTR_USER) ? ",user_xattr" : ",nouser_xattr"); if (IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL)) seq_puts(seq, test_opt(opt, POSIX_ACL) ? ",acl" : ",noacl"); if (IS_ENABLED(CONFIG_EROFS_FS_ZIP)) seq_printf(seq, ",cache_strategy=%s", erofs_param_cache_strategy[opt->cache_strategy].name); if (test_opt(opt, DAX_ALWAYS)) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); if (sbi->domain_id) seq_printf(seq, ",domain_id=%s", sbi->domain_id); #endif if (sbi->dif0.fsoff) seq_printf(seq, ",fsoffset=%llu", sbi->dif0.fsoff); return 0; } const struct super_operations erofs_sops = { .put_super = erofs_put_super, .alloc_inode = erofs_alloc_inode, .free_inode = erofs_free_inode, .statfs = erofs_statfs, .show_options = erofs_show_options, }; module_init(erofs_module_init); module_exit(erofs_module_exit); MODULE_DESCRIPTION("Enhanced ROM File System"); MODULE_AUTHOR("Gao Xiang, Chao Yu, Miao Xie, CONSUMER BG, HUAWEI Inc."); MODULE_LICENSE("GPL"); |
| 40 6 6 6 6 6 6 6 6 5 4 35 1 1 1 1 1 1 1 1 1 1 1 40 40 40 33 40 40 40 39 1 38 38 38 38 3 35 35 35 35 35 35 35 35 35 2 2 43 1 42 43 40 40 40 40 40 35 35 2 35 35 35 35 2 2 2 6 2 2 2 2 2 2 165 165 24 15 15 15 3 2 3 24 48 46 3 43 9 35 2 35 2 2 5 4 4 5 5 4 3 15 15 14 8 6 8 11 10 9 9 9 9 1 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 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 | /* * An async IO implementation for Linux * Written by Benjamin LaHaise <bcrl@kvack.org> * * Implements an efficient asynchronous io interface. * * Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved. * Copyright 2018 Christoph Hellwig. * * See ../COPYING for licensing terms. */ #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/aio_abi.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/backing-dev.h> #include <linux/refcount.h> #include <linux/uio.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/aio.h> #include <linux/highmem.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/eventfd.h> #include <linux/blkdev.h> #include <linux/compat.h> #include <linux/migrate.h> #include <linux/ramfs.h> #include <linux/percpu-refcount.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include "internal.h" #define KIOCB_KEY 0 #define AIO_RING_MAGIC 0xa10a10a1 #define AIO_RING_COMPAT_FEATURES 1 #define AIO_RING_INCOMPAT_FEATURES 0 struct aio_ring { unsigned id; /* kernel internal index number */ unsigned nr; /* number of io_events */ unsigned head; /* Written to by userland or under ring_lock * mutex by aio_read_events_ring(). */ unsigned tail; unsigned magic; unsigned compat_features; unsigned incompat_features; unsigned header_length; /* size of aio_ring */ struct io_event io_events[]; }; /* 128 bytes + ring size */ /* * Plugging is meant to work with larger batches of IOs. If we don't * have more than the below, then don't bother setting up a plug. */ #define AIO_PLUG_THRESHOLD 2 #define AIO_RING_PAGES 8 struct kioctx_table { struct rcu_head rcu; unsigned nr; struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { unsigned reqs_available; }; struct ctx_rq_wait { struct completion comp; atomic_t count; }; struct kioctx { struct percpu_ref users; atomic_t dead; struct percpu_ref reqs; unsigned long user_id; struct kioctx_cpu __percpu *cpu; /* * For percpu reqs_available, number of slots we move to/from global * counter at a time: */ unsigned req_batch; /* * This is what userspace passed to io_setup(), it's not used for * anything but counting against the global max_reqs quota. * * The real limit is nr_events - 1, which will be larger (see * aio_setup_ring()) */ unsigned max_reqs; /* Size of ringbuffer, in units of struct io_event */ unsigned nr_events; unsigned long mmap_base; unsigned long mmap_size; struct folio **ring_folios; long nr_pages; struct rcu_work free_rwork; /* see free_ioctx() */ /* * signals when all in-flight requests are done */ struct ctx_rq_wait *rq_wait; struct { /* * This counts the number of available slots in the ringbuffer, * so we avoid overflowing it: it's decremented (if positive) * when allocating a kiocb and incremented when the resulting * io_event is pulled off the ringbuffer. * * We batch accesses to it with a percpu version. */ atomic_t reqs_available; } ____cacheline_aligned_in_smp; struct { spinlock_t ctx_lock; struct list_head active_reqs; /* used for cancellation */ } ____cacheline_aligned_in_smp; struct { struct mutex ring_lock; wait_queue_head_t wait; } ____cacheline_aligned_in_smp; struct { unsigned tail; unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; struct folio *internal_folios[AIO_RING_PAGES]; struct file *aio_ring_file; unsigned id; }; /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in <linux/fs.h> */ struct fsync_iocb { struct file *file; struct work_struct work; bool datasync; struct cred *creds; }; struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; bool cancelled; bool work_scheduled; bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can * access the file pointer through any of the sub-structs, * or directly as just 'ki_filp' in this struct. */ struct aio_kiocb { union { struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; }; struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ refcount_t ki_refcnt; /* * If the aio_resfd field of the userspace iocb is not zero, * this is the underlying eventfd context to deliver events to. */ struct eventfd_ctx *ki_eventfd; }; /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); static unsigned long aio_nr; /* current system wide number of aio requests */ static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ #ifdef CONFIG_SYSCTL static const struct ctl_table aio_sysctls[] = { { .procname = "aio-nr", .data = &aio_nr, .maxlen = sizeof(aio_nr), .mode = 0444, .proc_handler = proc_doulongvec_minmax, }, { .procname = "aio-max-nr", .data = &aio_max_nr, .maxlen = sizeof(aio_max_nr), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; static void __init aio_sysctl_init(void) { register_sysctl_init("fs", aio_sysctls); } #else #define aio_sysctl_init() do { } while (0) #endif static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct file *file; struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->i_private_data = ctx; inode->i_size = PAGE_SIZE * nr_pages; file = alloc_file_pseudo(inode, aio_mnt, "[aio]", O_RDWR, &aio_ring_fops); if (IS_ERR(file)) iput(inode); return file; } static int aio_init_fs_context(struct fs_context *fc) { if (!init_pseudo(fc, AIO_RING_MAGIC)) return -ENOMEM; fc->s_iflags |= SB_I_NOEXEC; return 0; } /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. */ static int __init aio_setup(void) { static struct file_system_type aio_fs = { .name = "aio", .init_fs_context = aio_init_fs_context, .kill_sb = kill_anon_super, }; aio_mnt = kern_mount(&aio_fs); if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); aio_sysctl_init(); return 0; } __initcall(aio_setup); static void put_aio_ring_file(struct kioctx *ctx) { struct file *aio_ring_file = ctx->aio_ring_file; struct address_space *i_mapping; if (aio_ring_file) { truncate_setsize(file_inode(aio_ring_file), 0); /* Prevent further access to the kioctx from migratepages */ i_mapping = aio_ring_file->f_mapping; spin_lock(&i_mapping->i_private_lock); i_mapping->i_private_data = NULL; ctx->aio_ring_file = NULL; spin_unlock(&i_mapping->i_private_lock); fput(aio_ring_file); } } static void aio_free_ring(struct kioctx *ctx) { int i; /* Disconnect the kiotx from the ring file. This prevents future * accesses to the kioctx from page migration. */ put_aio_ring_file(ctx); for (i = 0; i < ctx->nr_pages; i++) { struct folio *folio = ctx->ring_folios[i]; if (!folio) continue; pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, folio_ref_count(folio)); ctx->ring_folios[i] = NULL; folio_put(folio); } if (ctx->ring_folios && ctx->ring_folios != ctx->internal_folios) { kfree(ctx->ring_folios); ctx->ring_folios = NULL; } } static int aio_ring_mremap(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct mm_struct *mm = vma->vm_mm; struct kioctx_table *table; int i, res = -EINVAL; spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table) goto out_unlock; for (i = 0; i < table->nr; i++) { struct kioctx *ctx; ctx = rcu_dereference(table->table[i]); if (ctx && ctx->aio_ring_file == file) { if (!atomic_read(&ctx->dead)) { ctx->user_id = ctx->mmap_base = vma->vm_start; res = 0; } break; } } out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; } static const struct vm_operations_struct aio_ring_vm_ops = { .mremap = aio_ring_mremap, #if IS_ENABLED(CONFIG_MMU) .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, #endif }; static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) { vm_flags_set(vma, VM_DONTEXPAND); vma->vm_ops = &aio_ring_vm_ops; return 0; } static const struct file_operations aio_ring_fops = { .mmap = aio_ring_mmap, }; #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { struct kioctx *ctx; unsigned long flags; pgoff_t idx; int rc = 0; /* mapping->i_private_lock here protects against the kioctx teardown. */ spin_lock(&mapping->i_private_lock); ctx = mapping->i_private_data; if (!ctx) { rc = -EINVAL; goto out; } /* The ring_lock mutex. The prevents aio_read_events() from writing * to the ring's head, and prevents page migration from mucking in * a partially initialized kiotx. */ if (!mutex_trylock(&ctx->ring_lock)) { rc = -EAGAIN; goto out; } idx = src->index; if (idx < (pgoff_t)ctx->nr_pages) { /* Make sure the old folio hasn't already been changed */ if (ctx->ring_folios[idx] != src) rc = -EAGAIN; } else rc = -EINVAL; if (rc != 0) goto out_unlock; /* Writeback must be complete */ BUG_ON(folio_test_writeback(src)); folio_get(dst); rc = folio_migrate_mapping(mapping, dst, src, 1); if (rc != MIGRATEPAGE_SUCCESS) { folio_put(dst); goto out_unlock; } /* Take completion_lock to prevent other writes to the ring buffer * while the old folio is copied to the new. This prevents new * events from being lost. */ spin_lock_irqsave(&ctx->completion_lock, flags); folio_copy(dst, src); folio_migrate_flags(dst, src); BUG_ON(ctx->ring_folios[idx] != src); ctx->ring_folios[idx] = dst; spin_unlock_irqrestore(&ctx->completion_lock, flags); /* The old folio is no longer accessible. */ folio_put(src); out_unlock: mutex_unlock(&ctx->ring_lock); out: spin_unlock(&mapping->i_private_lock); return rc; } #else #define aio_migrate_folio NULL #endif static const struct address_space_operations aio_ctx_aops = { .dirty_folio = noop_dirty_folio, .migrate_folio = aio_migrate_folio, }; static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) { struct aio_ring *ring; struct mm_struct *mm = current->mm; unsigned long size, unused; int nr_pages; int i; struct file *file; /* Compensate for the ring buffer's head/tail overlap entry */ nr_events += 2; /* 1 is required, 2 for good luck */ size = sizeof(struct aio_ring); size += sizeof(struct io_event) * nr_events; nr_pages = PFN_UP(size); if (nr_pages < 0) return -EINVAL; file = aio_private_file(ctx, nr_pages); if (IS_ERR(file)) { ctx->aio_ring_file = NULL; return -ENOMEM; } ctx->aio_ring_file = file; nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); ctx->ring_folios = ctx->internal_folios; if (nr_pages > AIO_RING_PAGES) { ctx->ring_folios = kcalloc(nr_pages, sizeof(struct folio *), GFP_KERNEL); if (!ctx->ring_folios) { put_aio_ring_file(ctx); return -ENOMEM; } } for (i = 0; i < nr_pages; i++) { struct folio *folio; folio = __filemap_get_folio(file->f_mapping, i, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_USER | __GFP_ZERO); if (IS_ERR(folio)) break; pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, folio_ref_count(folio)); folio_end_read(folio, true); ctx->ring_folios[i] = folio; } ctx->nr_pages = i; if (unlikely(i != nr_pages)) { aio_free_ring(ctx); return -ENOMEM; } ctx->mmap_size = nr_pages * PAGE_SIZE; pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); if (mmap_write_lock_killable(mm)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -EINTR; } ctx->mmap_base = do_mmap(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, 0, 0, &unused, NULL); mmap_write_unlock(mm); if (IS_ERR((void *)ctx->mmap_base)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -ENOMEM; } pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ ring = folio_address(ctx->ring_folios[0]); ring->nr = nr_events; /* user copy */ ring->id = ~0U; ring->head = ring->tail = 0; ring->magic = AIO_RING_MAGIC; ring->compat_features = AIO_RING_COMPAT_FEATURES; ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); flush_dcache_folio(ctx->ring_folios[0]); return 0; } #define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event)) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { struct aio_kiocb *req; struct kioctx *ctx; unsigned long flags; /* * kiocb didn't come from aio or is neither a read nor a write, hence * ignore it. */ if (!(iocb->ki_flags & IOCB_AIO_RW)) return; req = container_of(iocb, struct aio_kiocb, rw); if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; ctx = req->ki_ctx; spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; spin_unlock_irqrestore(&ctx->ctx_lock, flags); } EXPORT_SYMBOL(kiocb_set_cancel_fn); /* * free_ioctx() should be RCU delayed to synchronize against the RCU * protected lookup_ioctx() and also needs process context to call * aio_free_ring(). Use rcu_work. */ static void free_ioctx(struct work_struct *work) { struct kioctx *ctx = container_of(to_rcu_work(work), struct kioctx, free_rwork); pr_debug("freeing %p\n", ctx); aio_free_ring(ctx); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); } static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); /* At this point we know that there are no any in-flight requests */ if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) complete(&ctx->rq_wait->comp); /* Synchronize against RCU protected table->table[] dereferences */ INIT_RCU_WORK(&ctx->free_rwork, free_ioctx); queue_rcu_work(system_wq, &ctx->free_rwork); } /* * When this function runs, the kioctx has been removed from the "hash table" * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ static void free_ioctx_users(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, users); struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, struct aio_kiocb, ki_list); req->ki_cancel(&req->rw); list_del_init(&req->ki_list); } spin_unlock_irq(&ctx->ctx_lock); percpu_ref_kill(&ctx->reqs); percpu_ref_put(&ctx->reqs); } static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) { unsigned i, new_nr; struct kioctx_table *table, *old; struct aio_ring *ring; spin_lock(&mm->ioctx_lock); table = rcu_dereference_raw(mm->ioctx_table); while (1) { if (table) for (i = 0; i < table->nr; i++) if (!rcu_access_pointer(table->table[i])) { ctx->id = i; rcu_assign_pointer(table->table[i], ctx); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, * we are protected from page migration * changes ring_folios by ->ring_lock. */ ring = folio_address(ctx->ring_folios[0]); ring->id = ctx->id; return 0; } new_nr = (table ? table->nr : 1) * 4; spin_unlock(&mm->ioctx_lock); table = kzalloc(struct_size(table, table, new_nr), GFP_KERNEL); if (!table) return -ENOMEM; table->nr = new_nr; spin_lock(&mm->ioctx_lock); old = rcu_dereference_raw(mm->ioctx_table); if (!old) { rcu_assign_pointer(mm->ioctx_table, table); } else if (table->nr > old->nr) { memcpy(table->table, old->table, old->nr * sizeof(struct kioctx *)); rcu_assign_pointer(mm->ioctx_table, table); kfree_rcu(old, rcu); } else { kfree(table); table = old; } } } static void aio_nr_sub(unsigned nr) { spin_lock(&aio_nr_lock); if (WARN_ON(aio_nr - nr > aio_nr)) aio_nr = 0; else aio_nr -= nr; spin_unlock(&aio_nr_lock); } /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. */ static struct kioctx *ioctx_alloc(unsigned nr_events) { struct mm_struct *mm = current->mm; struct kioctx *ctx; int err = -ENOMEM; /* * Store the original nr_events -- what userspace passed to io_setup(), * for counting against the global limit -- before it changes. */ unsigned int max_reqs = nr_events; /* * We keep track of the number of available ringbuffer slots, to prevent * overflow (reqs_available), and we also use percpu counters for this. * * So since up to half the slots might be on other cpu's percpu counters * and unavailable, double nr_events so userspace sees what they * expected: additionally, we move req_batch slots to/from percpu * counters at a time, so make sure that isn't 0: */ nr_events = max(nr_events, num_possible_cpus() * 4); nr_events *= 2; /* Prevent overflows */ if (nr_events > (0x10000000U / sizeof(struct io_event))) { pr_debug("ENOMEM: nr_events too high\n"); return ERR_PTR(-EINVAL); } if (!nr_events || (unsigned long)max_reqs > aio_max_nr) return ERR_PTR(-EAGAIN); ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); ctx->max_reqs = max_reqs; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); mutex_init(&ctx->ring_lock); /* Protect against page migration throughout kiotx setup by keeping * the ring_lock mutex held until setup is complete. */ mutex_lock(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL)) goto err; if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL)) goto err; ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) goto err; err = aio_setup_ring(ctx, nr_events); if (err < 0) goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4); if (ctx->req_batch < 1) ctx->req_batch = 1; /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); if (aio_nr + ctx->max_reqs > aio_max_nr || aio_nr + ctx->max_reqs < aio_nr) { spin_unlock(&aio_nr_lock); err = -EAGAIN; goto err_ctx; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */ err = ioctx_add_table(ctx, mm); if (err) goto err_cleanup; /* Release the ring_lock mutex now that all setup is complete. */ mutex_unlock(&ctx->ring_lock); pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: atomic_set(&ctx->dead, 1); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); } /* kill_ioctx * Cancels all outstanding aio requests on an aio context. Used * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, struct ctx_rq_wait *wait) { struct kioctx_table *table; spin_lock(&mm->ioctx_lock); if (atomic_xchg(&ctx->dead, 1)) { spin_unlock(&mm->ioctx_lock); return -EINVAL; } table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id])); RCU_INIT_POINTER(table->table[ctx->id], NULL); spin_unlock(&mm->ioctx_lock); /* free_ioctx_reqs() will do the necessary RCU synchronization */ wake_up_all(&ctx->wait); /* * It'd be more correct to do this in free_ioctx(), after all * the outstanding kiocbs have finished - but by then io_destroy * has already returned, so io_setup() could potentially return * -EAGAIN with no ioctxs actually in use (as far as userspace * could tell). */ aio_nr_sub(ctx->max_reqs); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); ctx->rq_wait = wait; percpu_ref_kill(&ctx->users); return 0; } /* * exit_aio: called when the last user of mm goes away. At this point, there is * no way for any new requests to be submited or any of the io_* syscalls to be * called on the context. * * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on * them. */ void exit_aio(struct mm_struct *mm) { struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table); struct ctx_rq_wait wait; int i, skipped; if (!table) return; atomic_set(&wait.count, table->nr); init_completion(&wait.comp); skipped = 0; for (i = 0; i < table->nr; ++i) { struct kioctx *ctx = rcu_dereference_protected(table->table[i], true); if (!ctx) { skipped++; continue; } /* * We don't need to bother with munmap() here - exit_mmap(mm) * is coming and it'll unmap everything. And we simply can't, * this is not necessarily our ->mm. * Since kill_ioctx() uses non-zero ->mmap_size as indicator * that it needs to unmap the area, just set it to 0. */ ctx->mmap_size = 0; kill_ioctx(mm, ctx, &wait); } if (!atomic_sub_and_test(skipped, &wait.count)) { /* Wait until all IO for the context are done. */ wait_for_completion(&wait.comp); } RCU_INIT_POINTER(mm->ioctx_table, NULL); kfree(table); } static void put_reqs_available(struct kioctx *ctx, unsigned nr) { struct kioctx_cpu *kcpu; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); kcpu->reqs_available += nr; while (kcpu->reqs_available >= ctx->req_batch * 2) { kcpu->reqs_available -= ctx->req_batch; atomic_add(ctx->req_batch, &ctx->reqs_available); } local_irq_restore(flags); } static bool __get_reqs_available(struct kioctx *ctx) { struct kioctx_cpu *kcpu; bool ret = false; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); if (!kcpu->reqs_available) { int avail = atomic_read(&ctx->reqs_available); do { if (avail < ctx->req_batch) goto out; } while (!atomic_try_cmpxchg(&ctx->reqs_available, &avail, avail - ctx->req_batch)); kcpu->reqs_available += ctx->req_batch; } ret = true; kcpu->reqs_available--; out: local_irq_restore(flags); return ret; } /* refill_reqs_available * Updates the reqs_available reference counts used for tracking the * number of free slots in the completion ring. This can be called * from aio_complete() (to optimistically update reqs_available) or * from aio_get_req() (the we're out of events case). It must be * called holding ctx->completion_lock. */ static void refill_reqs_available(struct kioctx *ctx, unsigned head, unsigned tail) { unsigned events_in_ring, completed; /* Clamp head since userland can write to it. */ head %= ctx->nr_events; if (head <= tail) events_in_ring = tail - head; else events_in_ring = ctx->nr_events - (head - tail); completed = ctx->completed_events; if (events_in_ring < completed) completed -= events_in_ring; else completed = 0; if (!completed) return; ctx->completed_events -= completed; put_reqs_available(ctx, completed); } /* user_refill_reqs_available * Called to refill reqs_available when aio_get_req() encounters an * out of space in the completion ring. */ static void user_refill_reqs_available(struct kioctx *ctx) { spin_lock_irq(&ctx->completion_lock); if (ctx->completed_events) { struct aio_ring *ring; unsigned head; /* Access of ring->head may race with aio_read_events_ring() * here, but that's okay since whether we read the old version * or the new version, and either will be valid. The important * part is that head cannot pass tail since we prevent * aio_complete() from updating tail by holding * ctx->completion_lock. Even if head is invalid, the check * against ctx->completed_events below will make sure we do the * safe/right thing. */ ring = folio_address(ctx->ring_folios[0]); head = ring->head; refill_reqs_available(ctx, head, ctx->tail); } spin_unlock_irq(&ctx->completion_lock); } static bool get_reqs_available(struct kioctx *ctx) { if (__get_reqs_available(ctx)) return true; user_refill_reqs_available(ctx); return __get_reqs_available(ctx); } /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. * * The refcount is initialized to 2 - one for the async op completion, * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { struct aio_kiocb *req; req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL); if (unlikely(!req)) return NULL; if (unlikely(!get_reqs_available(ctx))) { kmem_cache_free(kiocb_cachep, req); return NULL; } percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct aio_ring __user *ring = (void __user *)ctx_id; struct mm_struct *mm = current->mm; struct kioctx *ctx, *ret = NULL; struct kioctx_table *table; unsigned id; if (get_user(id, &ring->id)) return NULL; rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table || id >= table->nr) goto out; id = array_index_nospec(id, table->nr); ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { if (percpu_ref_tryget_live(&ctx->users)) ret = ctx; } out: rcu_read_unlock(); return ret; } static inline void iocb_destroy(struct aio_kiocb *iocb) { if (iocb->ki_eventfd) eventfd_ctx_put(iocb->ki_eventfd); if (iocb->ki_filp) fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } struct aio_waiter { struct wait_queue_entry w; size_t min_nr; }; /* aio_complete * Called when the io request on the given iocb is complete. */ static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; unsigned tail, pos, head, avail; unsigned long flags; /* * Add a completion event to the ring buffer. Must be done holding * ctx->completion_lock to prevent other code from messing with the tail * pointer since we might be called from irq context. */ spin_lock_irqsave(&ctx->completion_lock, flags); tail = ctx->tail; pos = tail + AIO_EVENTS_OFFSET; if (++tail >= ctx->nr_events) tail = 0; ev_page = folio_address(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; *event = iocb->ki_res; flush_dcache_folio(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, (void __user *)(unsigned long)iocb->ki_res.obj, iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again */ smp_wmb(); /* make event visible before updating tail */ ctx->tail = tail; ring = folio_address(ctx->ring_folios[0]); head = ring->head; ring->tail = tail; flush_dcache_folio(ctx->ring_folios[0]); ctx->completed_events++; if (ctx->completed_events > 1) refill_reqs_available(ctx, head, tail); avail = tail > head ? tail - head : tail + ctx->nr_events - head; spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); /* * Check if the user asked us to deliver the result through an * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd); /* * We have to order our ring_info tail store above and test * of the wait list below outside the wait lock. This is * like in wake_up_bit() where clearing a bit has to be * ordered with the unlocked test. */ smp_mb(); if (waitqueue_active(&ctx->wait)) { struct aio_waiter *curr, *next; unsigned long flags; spin_lock_irqsave(&ctx->wait.lock, flags); list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry) if (avail >= curr->min_nr) { wake_up_process(curr->w.private); list_del_init_careful(&curr->w.entry); } spin_unlock_irqrestore(&ctx->wait.lock, flags); } } static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_dec_and_test(&iocb->ki_refcnt)) { aio_complete(iocb); iocb_destroy(iocb); } } /* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of * events fetched */ static long aio_read_events_ring(struct kioctx *ctx, struct io_event __user *event, long nr) { struct aio_ring *ring; unsigned head, tail, pos; long ret = 0; int copy_ret; /* * The mutex can block and wake us up and that will cause * wait_event_interruptible_hrtimeout() to schedule without sleeping * and repeat. This should be rare enough that it doesn't cause * peformance issues. See the comment in read_events() for more detail. */ sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_folios here is protected by ctx->ring_lock. */ ring = folio_address(ctx->ring_folios[0]); head = ring->head; tail = ring->tail; /* * Ensure that once we've read the current tail pointer, that * we also see the events that were stored up to the tail. */ smp_rmb(); pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) goto out; head %= ctx->nr_events; tail %= ctx->nr_events; while (ret < nr) { long avail; struct io_event *ev; struct folio *folio; avail = (head <= tail ? tail : ctx->nr_events) - head; if (head == tail) break; pos = head + AIO_EVENTS_OFFSET; folio = ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]; pos %= AIO_EVENTS_PER_PAGE; avail = min(avail, nr - ret); avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos); ev = folio_address(folio); copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); if (unlikely(copy_ret)) { ret = -EFAULT; goto out; } ret += avail; head += avail; head %= ctx->nr_events; } ring = folio_address(ctx->ring_folios[0]); ring->head = head; flush_dcache_folio(ctx->ring_folios[0]); pr_debug("%li h%u t%u\n", ret, head, tail); out: mutex_unlock(&ctx->ring_lock); return ret; } static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, long *i) { long ret = aio_read_events_ring(ctx, event + *i, nr - *i); if (ret > 0) *i += ret; if (unlikely(atomic_read(&ctx->dead))) ret = -EINVAL; if (!*i) *i = ret; return ret < 0 || *i >= min_nr; } static long read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, ktime_t until) { struct hrtimer_sleeper t; struct aio_waiter w; long ret = 0, ret2 = 0; /* * Note that aio_read_events() is being called as the conditional - i.e. * we're calling it after prepare_to_wait() has set task state to * TASK_INTERRUPTIBLE. * * But aio_read_events() can block, and if it blocks it's going to flip * the task state back to TASK_RUNNING. * * This should be ok, provided it doesn't flip the state back to * TASK_RUNNING and return 0 too much - that causes us to spin. That * will only happen if the mutex_lock() call blocks, and we then find * the ringbuffer empty. So in practice we should be ok, but it's * something to be aware of when touching this code. */ aio_read_events(ctx, min_nr, nr, event, &ret); if (until == 0 || ret < 0 || ret >= min_nr) return ret; hrtimer_setup_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); if (until != KTIME_MAX) { hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns); hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL); } init_wait(&w.w); while (1) { unsigned long nr_got = ret; w.min_nr = min_nr - ret; ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE); if (!ret2 && !t.task) ret2 = -ETIME; if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2) break; if (nr_got == ret) schedule(); } finish_wait(&ctx->wait, &w.w); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); return ret; } /* sys_io_setup: * Create an aio_context capable of receiving at least nr_events. * ctxp must not point to an aio_context that already exists, and * must be initialized to 0 prior to the call. On successful * creation of the aio_context, *ctxp is filled in with the resulting * handle. May fail with -EINVAL if *ctxp is not initialized, * if the specified nr_events exceeds internal limits. May fail * with -EAGAIN if the specified nr_events exceeds the user's limit * of available events. May fail with -ENOMEM if insufficient kernel * resources are available. May fail with -EFAULT if an invalid * pointer is passed for ctxp. Will fail with -ENOSYS if not * implemented. */ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctxp); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctx32p); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { /* truncating is ok because it's a user address */ ret = put_user((u32)ioctx->user_id, ctx32p); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #endif /* sys_io_destroy: * Destroy the aio_context specified. May cancel any outstanding * AIOs and block on completion. Will fail with -ENOSYS if not * implemented. May fail with -EINVAL if the context pointed to * is invalid. */ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { struct ctx_rq_wait wait; int ret; init_completion(&wait.comp); atomic_set(&wait.count, 1); /* Pass requests_done to kill_ioctx() where it can be set * in a thread-safe way. If we try to set it here then we have * a race condition if two io_destroy() called simultaneously. */ ret = kill_ioctx(current->mm, ioctx, &wait); percpu_ref_put(&ioctx->users); /* Wait until all IO for the context are done. Otherwise kernel * keep using user-space buffers even if user thinks the context * is destroyed. */ if (!ret) wait_for_completion(&wait.comp); return ret; } pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } static void aio_remove_iocb(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; unsigned long flags; spin_lock_irqsave(&ctx->ctx_lock, flags); list_del(&iocb->ki_list); spin_unlock_irqrestore(&ctx->ctx_lock, flags); } static void aio_complete_rw(struct kiocb *kiocb, long res) { struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw); if (!list_empty_careful(&iocb->ki_list)) aio_remove_iocb(iocb); if (kiocb->ki_flags & IOCB_WRITE) { struct inode *inode = file_inode(kiocb->ki_filp); if (S_ISREG(inode->i_mode)) kiocb_end_write(kiocb); } iocb->ki_res.res = res; iocb->ki_res.res2 = 0; iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; req->ki_write_stream = 0; req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { /* * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then * aio_reqprio is interpreted as an I/O scheduling * class and priority. */ ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); return ret; } req->ki_ioprio = iocb->aio_reqprio; } else req->ki_ioprio = get_current_ioprio(); ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; } static ssize_t aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, bool vectored, bool compat, struct iov_iter *iter) { void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf; size_t len = iocb->aio_nbytes; if (!vectored) { ssize_t ret = import_ubuf(rw, buf, len, iter); *iovec = NULL; return ret; } return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat); } static inline void aio_rw_done(struct kiocb *req, ssize_t ret) { switch (ret) { case -EIOCBQUEUED: break; case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTARTNOHAND: case -ERESTART_RESTARTBLOCK: /* * There's no easy way to restart the syscall since other AIO's * may be already running. Just fail this IO with EINTR. */ ret = -EINTR; fallthrough; default: req->ki_complete(req, ret); } } static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; if (unlikely(!file->f_op->read_iter)) return -EINVAL; ret = aio_setup_rw(ITER_DEST, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, file->f_op->read_iter(req, &iter)); kfree(iovec); return ret; } static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(!file->f_op->write_iter)) return -EINVAL; ret = aio_setup_rw(ITER_SOURCE, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { if (S_ISREG(file_inode(file)->i_mode)) kiocb_start_write(req); req->ki_flags |= IOCB_WRITE; aio_rw_done(req, file->f_op->write_iter(req, &iter)); } kfree(iovec); return ret; } static void aio_fsync_work(struct work_struct *work) { struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); const struct cred *old_cred = override_creds(iocb->fsync.creds); iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); revert_creds(old_cred); put_cred(iocb->fsync.creds); iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, bool datasync) { if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)) return -EINVAL; if (unlikely(!req->file->f_op->fsync)) return -EINVAL; req->creds = prepare_creds(); if (!req->creds) return -ENOMEM; req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); schedule_work(&req->work); return 0; } static void aio_poll_put_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); iocb_put(iocb); } /* * Safely lock the waitqueue which the request is on, synchronizing with the * case where the ->poll() provider decides to free its waitqueue early. * * Returns true on success, meaning that req->head->lock was locked, req->wait * is on req->head, and an RCU read lock was taken. Returns false if the * request was already removed from its waitqueue (which might no longer exist). */ static bool poll_iocb_lock_wq(struct poll_iocb *req) { wait_queue_head_t *head; /* * While we hold the waitqueue lock and the waitqueue is nonempty, * wake_up_pollfree() will wait for us. However, taking the waitqueue * lock in the first place can race with the waitqueue being freed. * * We solve this as eventpoll does: by taking advantage of the fact that * all users of wake_up_pollfree() will RCU-delay the actual free. If * we enter rcu_read_lock() and see that the pointer to the queue is * non-NULL, we can then lock it without the memory being freed out from * under us, then check whether the request is still on the queue. * * Keep holding rcu_read_lock() as long as we hold the queue lock, in * case the caller deletes the entry from the queue, leaving it empty. * In that case, only RCU prevents the queue memory from being freed. */ rcu_read_lock(); head = smp_load_acquire(&req->head); if (head) { spin_lock(&head->lock); if (!list_empty(&req->wait.entry)) return true; spin_unlock(&head->lock); } rcu_read_unlock(); return false; } static void poll_iocb_unlock_wq(struct poll_iocb *req) { spin_unlock(&req->head->lock); rcu_read_unlock(); } static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); struct poll_table_struct pt = { ._key = req->events }; struct kioctx *ctx = iocb->ki_ctx; __poll_t mask = 0; if (!READ_ONCE(req->cancelled)) mask = vfs_poll(req->file, &pt) & req->events; /* * Note that ->ki_cancel callers also delete iocb from active_reqs after * calling ->ki_cancel. We need the ctx_lock roundtrip here to * synchronize with them. In the cancellation case the list_del_init * itself is not actually needed, but harmless so we keep it in to * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); if (poll_iocb_lock_wq(req)) { if (!mask && !READ_ONCE(req->cancelled)) { /* * The request isn't actually ready to be completed yet. * Reschedule completion if another wakeup came in. */ if (req->work_need_resched) { schedule_work(&req->work); req->work_need_resched = false; } else { req->work_scheduled = false; } poll_iocb_unlock_wq(req); spin_unlock_irq(&ctx->ctx_lock); return; } list_del_init(&req->wait.entry); poll_iocb_unlock_wq(req); } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); } /* assumes we are called with irqs disabled */ static int aio_poll_cancel(struct kiocb *iocb) { struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; if (poll_iocb_lock_wq(req)) { WRITE_ONCE(req->cancelled, true); if (!req->work_scheduled) { schedule_work(&aiocb->poll.work); req->work_scheduled = true; } poll_iocb_unlock_wq(req); } /* else, the request was force-cancelled by POLLFREE already */ return 0; } static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); unsigned long flags; /* for instances that support it check for an event match first: */ if (mask && !(mask & req->events)) return 0; /* * Complete the request inline if possible. This requires that three * conditions be met: * 1. An event mask must have been passed. If a plain wakeup was done * instead, then mask == 0 and we have to call vfs_poll() to get * the events, so inline completion isn't possible. * 2. The completion work must not have already been scheduled. * 3. ctx_lock must not be busy. We have to use trylock because we * already hold the waitqueue lock, so this inverts the normal * locking order. Use irqsave/irqrestore because not all * filesystems (e.g. fuse) call this function with IRQs disabled, * yet IRQs have to be disabled before ctx_lock is obtained. */ if (mask && !req->work_scheduled && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); if (iocb->ki_eventfd && !eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); } spin_unlock_irqrestore(&ctx->ctx_lock, flags); if (iocb) iocb_put(iocb); } else { /* * Schedule the completion work if needed. If it was already * scheduled, record that another wakeup came in. * * Don't remove the request from the waitqueue here, as it might * not actually be complete yet (we won't know until vfs_poll() * is called), and we must not miss any wakeups. POLLFREE is an * exception to this; see below. */ if (req->work_scheduled) { req->work_need_resched = true; } else { schedule_work(&req->work); req->work_scheduled = true; } /* * If the waitqueue is being freed early but we can't complete * the request inline, we have to tear down the request as best * we can. That means immediately removing the request from its * waitqueue and preventing all further accesses to the * waitqueue via the request. We also need to schedule the * completion work (done above). Also mark the request as * cancelled, to potentially skip an unneeded call to ->poll(). */ if (mask & POLLFREE) { WRITE_ONCE(req->cancelled, true); list_del_init(&req->wait.entry); /* * Careful: this *must* be the last step, since as soon * as req->head is NULL'ed out, the request can be * completed and freed, since aio_poll_complete_work() * will no longer need to take the waitqueue lock. */ smp_store_release(&req->head, NULL); } } return 1; } struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; bool queued; int error; }; static void aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); } static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ if ((u16)iocb->aio_buf != iocb->aio_buf) return -EINVAL; /* reject fields that are not defined for poll */ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags) return -EINVAL; INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; req->cancelled = false; req->work_scheduled = false; req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); if (likely(apt.queued)) { bool on_queue = poll_iocb_lock_wq(req); if (!on_queue || req->work_scheduled) { /* * aio_poll_wake() already either scheduled the async * completion work, or completed the request inline. */ if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); } else if (on_queue) { /* * Actually waiting for an event, so add the request to * active_reqs so that it can be cancelled if needed. */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } if (on_queue) poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; } spin_unlock_irq(&ctx->ctx_lock); if (mask) iocb_put(aiocb); return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, struct iocb __user *user_iocb, struct aio_kiocb *req, bool compat) { req->ki_filp = fget(iocb->aio_fildes); if (unlikely(!req->ki_filp)) return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ eventfd = eventfd_ctx_fdget(iocb->aio_resfd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); req->ki_eventfd = eventfd; } if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); return -EFAULT; } req->ki_res.obj = (u64)(unsigned long)user_iocb; req->ki_res.data = iocb->aio_data; req->ki_res.res = 0; req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); return -EINVAL; } } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { struct aio_kiocb *req; struct iocb iocb; int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; /* enforce forwards compatibility on users */ if (unlikely(iocb.aio_reserved2)) { pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } /* prevent overflows */ if (unlikely( (iocb.aio_buf != (unsigned long)iocb.aio_buf) || (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || ((ssize_t)iocb.aio_nbytes < 0) )) { pr_debug("EINVAL: overflow check\n"); return -EINVAL; } req = aio_get_req(ctx); if (unlikely(!req)) return -EAGAIN; err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); /* Done with the synchronous reference */ iocb_put(req); /* * If err is 0, we'd either done aio_complete() ourselves or have * arranged for that to be done asynchronously. Anything non-zero * means that we need to destroy req ourselves. */ if (unlikely(err)) { iocb_destroy(req); put_reqs_available(ctx, 1); } return err; } /* sys_io_submit: * Queue the nr iocbs pointed to by iocbpp for processing. Returns * the number of iocbs queued. May return -EINVAL if the aio_context * specified by ctx_id is invalid, if nr is < 0, if the iocb at * *iocbpp[0] is not properly initialized, if the operation specified * is invalid for the file descriptor in the iocb. May fail with * -EFAULT if any of the data structures point to invalid data. May * fail with -EBADF if the file descriptor specified in the first * iocb is invalid. May fail with -EAGAIN if insufficient resources * are available to queue any iocbs. Will return 0 if nr is 0. Will * fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, struct iocb __user * __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { struct iocb __user *user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, user_iocb, false); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, int, nr, compat_uptr_t __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { compat_uptr_t user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, compat_ptr(user_iocb), true); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #endif /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is * copied into the memory pointed to by result without being placed * into the completion queue and 0 is returned. May fail with * -EFAULT if any of the data structures pointed to are invalid. * May fail with -EINVAL if aio_context specified by ctx_id is * invalid. May fail with -EAGAIN if the iocb specified was not * cancelled. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { struct kioctx *ctx; struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; if (unlikely(key != KIOCB_KEY)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) return -EINVAL; spin_lock_irq(&ctx->ctx_lock); list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { if (kiocb->ki_res.obj == obj) { ret = kiocb->ki_cancel(&kiocb->rw); list_del_init(&kiocb->ki_list); break; } } spin_unlock_irq(&ctx->ctx_lock); if (!ret) { /* * The result argument is no longer used - the io_event is * always delivered via the ring buffer. -EINPROGRESS indicates * cancellation is progress: */ ret = -EINPROGRESS; } percpu_ref_put(&ctx->users); return ret; } static long do_io_getevents(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, struct timespec64 *ts) { ktime_t until = ts ? timespec64_to_ktime(*ts) : KTIME_MAX; struct kioctx *ioctx = lookup_ioctx(ctx_id); long ret = -EINVAL; if (likely(ioctx)) { if (likely(min_nr <= nr && min_nr >= 0)) ret = read_events(ioctx, min_nr, nr, events, until); percpu_ref_put(&ioctx->users); } return ret; } /* io_getevents: * Attempts to read at least min_nr events and up to nr events from * the completion queue for the aio_context specified by ctx_id. If * it succeeds, the number of read events is returned. May fail with * -EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is * out of range, if timeout is out of range. May fail with -EFAULT * if any of the memory specified is invalid. May return 0 or * < min_nr if the timeout specified by timeout has elapsed * before sufficient events are available, where timeout == NULL * specifies an infinite timeout. Note that the timeout pointed to by * timeout is relative. Will fail with -ENOSYS if not implemented. */ #ifdef CONFIG_64BIT SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout) { struct timespec64 ts; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif struct __aio_sigset { const sigset_t __user *sigmask; size_t sigsetsize; }; SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(io_pgetevents_time32, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, __s32, min_nr, __s32, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif #ifdef CONFIG_COMPAT struct __compat_aio_sigset { compat_uptr_t sigmask; compat_size_t sigsetsize; }; #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(io_pgetevents, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif |
| 6 6 6 6 3 3 2 3 3 1 1 1 5 6 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 | // SPDX-License-Identifier: MIT /* * Copyright © 2021 Intel Corporation */ #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/slab.h> #include <linux/string.h> #include "i915_driver.h" #include "i915_drv.h" #include "i915_mitigations.h" static unsigned long mitigations __read_mostly = ~0UL; enum { CLEAR_RESIDUALS = 0, }; static const char * const names[] = { [CLEAR_RESIDUALS] = "residuals", }; bool i915_mitigate_clear_residuals(void) { return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS); } static int mitigations_set(const char *val, const struct kernel_param *kp) { unsigned long new = ~0UL; char *str, *sep, *tok; bool first = true; int err = 0; BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations)); str = kstrdup(val, GFP_KERNEL); if (!str) return -ENOMEM; for (sep = str; (tok = strsep(&sep, ","));) { bool enable = true; int i; /* Be tolerant of leading/trailing whitespace */ tok = strim(tok); if (first) { first = false; if (!strcmp(tok, "auto")) continue; new = 0; if (!strcmp(tok, "off")) continue; } if (*tok == '!') { enable = !enable; tok++; } if (!strncmp(tok, "no", 2)) { enable = !enable; tok += 2; } if (*tok == '\0') continue; for (i = 0; i < ARRAY_SIZE(names); i++) { if (!strcmp(tok, names[i])) { if (enable) new |= BIT(i); else new &= ~BIT(i); break; } } if (i == ARRAY_SIZE(names)) { pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n", DRIVER_NAME, val, tok); err = -EINVAL; break; } } kfree(str); if (err) return err; WRITE_ONCE(mitigations, new); return 0; } static int mitigations_get(char *buffer, const struct kernel_param *kp) { unsigned long local = READ_ONCE(mitigations); int count, i; bool enable; if (!local) return scnprintf(buffer, PAGE_SIZE, "%s\n", "off"); if (local & BIT(BITS_PER_LONG - 1)) { count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto"); enable = false; } else { enable = true; count = 0; } for (i = 0; i < ARRAY_SIZE(names); i++) { if ((local & BIT(i)) != enable) continue; count += scnprintf(buffer + count, PAGE_SIZE - count, "%s%s,", enable ? "" : "!", names[i]); } buffer[count - 1] = '\n'; return count; } static const struct kernel_param_ops ops = { .set = mitigations_set, .get = mitigations_get, }; module_param_cb_unsafe(mitigations, &ops, NULL, 0600); MODULE_PARM_DESC(mitigations, "Selectively enable security mitigations for all Intel® GPUs in the system.\n" "\n" " auto -- enables all mitigations required for the platform [default]\n" " off -- disables all mitigations\n" "\n" "Individual mitigations can be enabled by passing a comma-separated string,\n" "e.g. mitigations=residuals to enable only clearing residuals or\n" "mitigations=auto,noresiduals to disable only the clear residual mitigation.\n" "Either '!' or 'no' may be used to switch from enabling the mitigation to\n" "disabling it.\n" "\n" "Active mitigations for Ivybridge, Baytrail, Haswell:\n" " residuals -- clear all thread-local registers between contexts" ); |
| 8 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> * * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT * funded by Astaro. */ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/netfilter/nf_nat.h> struct ip6table_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; static unsigned int ip6table_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv6_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, }; static const struct nf_hook_ops nf_nat_ipv6_ops[] = { { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; static int ip6t_nat_register_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net; struct nf_hook_ops *ops; struct xt_table *table; int i, ret; table = xt_find_table(net, NFPROTO_IPV6, "nat"); if (WARN_ON_ONCE(!table)) return -ENOENT; xt_nat_net = net_generic(net, ip6table_nat_net_id); ops = kmemdup(nf_nat_ipv6_ops, sizeof(nf_nat_ipv6_ops), GFP_KERNEL); if (!ops) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { ops[i].priv = table; ret = nf_nat_ipv6_register_fn(net, &ops[i]); if (ret) { while (i) nf_nat_ipv6_unregister_fn(net, &ops[--i]); kfree(ops); return ret; } } xt_nat_net->nf_nat_ops = ops; return 0; } static void ip6t_nat_unregister_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net = net_generic(net, ip6table_nat_net_id); struct nf_hook_ops *ops = xt_nat_net->nf_nat_ops; int i; if (!ops) return; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) nf_nat_ipv6_unregister_fn(net, &ops[i]); kfree(ops); } static int ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, NULL); if (ret < 0) { kfree(repl); return ret; } ret = ip6t_nat_register_lookups(net); if (ret < 0) ip6t_unregister_table_exit(net, "nat"); kfree(repl); return ret; } static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); } static void __net_exit ip6table_nat_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "nat"); } static struct pernet_operations ip6table_nat_net_ops = { .pre_exit = ip6table_nat_net_pre_exit, .exit = ip6table_nat_net_exit, .id = &ip6table_nat_net_id, .size = sizeof(struct ip6table_nat_pernet), }; static int __init ip6table_nat_init(void) { int ret; /* net->gen->ptr[ip6table_nat_net_id] must be allocated * before calling ip6t_nat_register_lookups(). */ ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; ret = xt_register_template(&nf_nat_ipv6_table, ip6table_nat_table_init); if (ret) unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { xt_unregister_template(&nf_nat_ipv6_table); unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); module_exit(ip6table_nat_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Ip6tables legacy nat table"); |
| 3 3 3 3 3 3 3 7 8 8 7 6 3 3 3 1 1 1 1 1 1 4 2 4 4 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 | #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/irq_work.h> #include <linux/slab.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/wait.h> #include <linux/poll.h> #include <linux/kmemleak.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #include <asm/rqspinlock.h> #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) /* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ #define RINGBUF_PGOFF \ (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) /* consumer page and producer page */ #define RINGBUF_POS_PAGES 2 #define RINGBUF_NR_META_PAGES (RINGBUF_PGOFF + RINGBUF_POS_PAGES) #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) struct bpf_ringbuf { wait_queue_head_t waitq; struct irq_work work; u64 mask; struct page **pages; int nr_pages; rqspinlock_t spinlock ____cacheline_aligned_in_smp; /* For user-space producer ring buffers, an atomic_t busy bit is used * to synchronize access to the ring buffers in the kernel, rather than * the spinlock that is used for kernel-producer ring buffers. This is * done because the ring buffer must hold a lock across a BPF program's * callback: * * __bpf_user_ringbuf_peek() // lock acquired * -> program callback_fn() * -> __bpf_user_ringbuf_sample_release() // lock released * * It is unsafe and incorrect to hold an IRQ spinlock across what could * be a long execution window, so we instead simply disallow concurrent * access to the ring buffer by kernel consumers, and return -EBUSY from * __bpf_user_ringbuf_peek() if the busy bit is held by another task. */ atomic_t busy ____cacheline_aligned_in_smp; /* Consumer and producer counters are put into separate pages to * allow each position to be mapped with different permissions. * This prevents a user-space application from modifying the * position and ruining in-kernel tracking. The permissions of the * pages depend on who is producing samples: user-space or the * kernel. Note that the pending counter is placed in the same * page as the producer, so that it shares the same cache line. * * Kernel-producer * --------------- * The producer position and data pages are mapped as r/o in * userspace. For this approach, bits in the header of samples are * used to signal to user-space, and to other producers, whether a * sample is currently being written. * * User-space producer * ------------------- * Only the page containing the consumer position is mapped r/o in * user-space. User-space producers also use bits of the header to * communicate to the kernel, but the kernel must carefully check and * validate each sample to ensure that they're correctly formatted, and * fully contained within the ring buffer. */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; struct bpf_ringbuf_map { struct bpf_map map; struct bpf_ringbuf *rb; }; /* 8-byte ring buffer record header structure */ struct bpf_ringbuf_hdr { u32 len; u32 pg_off; }; static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | __GFP_ZERO; int nr_meta_pages = RINGBUF_NR_META_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; struct page **pages, *page; struct bpf_ringbuf *rb; size_t array_size; int i; /* Each data page is mapped twice to allow "virtual" * continuous read of samples wrapping around the end of ring * buffer area: * ------------------------------------------------------ * | meta pages | real data pages | same data pages | * ------------------------------------------------------ * | | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 | * ------------------------------------------------------ * | | TA DA | TA DA | * ------------------------------------------------------ * ^^^^^^^ * | * Here, no need to worry about special handling of wrapped-around * data due to double-mapped data pages. This works both in kernel and * when mmap()'ed in user-space, simplifying both kernel and * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); pages = bpf_map_area_alloc(array_size, numa_node); if (!pages) return NULL; for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(numa_node, flags, 0); if (!page) { nr_pages = i; goto err_free_pages; } pages[i] = page; if (i >= nr_meta_pages) pages[nr_data_pages + i] = page; } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; rb->nr_pages = nr_pages; return rb; } err_free_pages: for (i = 0; i < nr_pages; i++) __free_page(pages[i]); bpf_map_area_free(pages); return NULL; } static void bpf_ringbuf_notify(struct irq_work *work) { struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work); wake_up_all(&rb->waitq); } /* Maximum size of ring buffer area is limited by 32-bit page offset within * record header, counted in pages. Reserve 8 bits for extensibility, and * take into account few extra pages for consumer/producer pages and * non-mmap()'able parts, the current maximum size would be: * * (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) * * This gives 64GB limit, which seems plenty for single ring buffer. Now * considering that the maximum value of data_sz is (4GB - 1), there * will be no overflow, so just note the size limit in the comments. */ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) { struct bpf_ringbuf *rb; rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) return NULL; raw_res_spin_lock_init(&rb->spinlock); atomic_set(&rb->busy, 0); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; rb->pending_pos = 0; return rb; } static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size || attr->value_size || !is_power_of_2(attr->max_entries) || !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE); if (!rb_map) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&rb_map->map, attr); rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); if (!rb_map->rb) { bpf_map_area_free(rb_map); return ERR_PTR(-ENOMEM); } return &rb_map->map; } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) { /* copy pages pointer and nr_pages to local variable, as we are going * to unmap rb itself with vunmap() below */ struct page **pages = rb->pages; int i, nr_pages = rb->nr_pages; vunmap(rb); for (i = 0; i < nr_pages; i++) __free_page(pages[i]); bpf_map_area_free(pages); } static void ringbuf_map_free(struct bpf_map *map) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); bpf_ringbuf_free(rb_map->rb); bpf_map_area_free(rb_map); } static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) { return ERR_PTR(-ENOTSUPP); } static long ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { return -ENOTSUPP; } static long ringbuf_map_delete_elem(struct bpf_map *map, void *key) { return -ENOTSUPP; } static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); if (vma->vm_flags & VM_WRITE) { /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); if (vma->vm_flags & VM_WRITE) { if (vma->vm_pgoff == 0) /* Disallow writable mappings to the consumer pointer, * and allow writable mappings to both the producer * position, and the ring buffer data itself. */ return -EPERM; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) { unsigned long cons_pos, prod_pos; cons_pos = smp_load_acquire(&rb->consumer_pos); prod_pos = smp_load_acquire(&rb->producer_pos); return prod_pos - cons_pos; } static u32 ringbuf_total_data_sz(const struct bpf_ringbuf *rb) { return rb->mask + 1; } static __poll_t ringbuf_map_poll_kern(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); poll_wait(filp, &rb_map->rb->waitq, pts); if (ringbuf_avail_data_sz(rb_map->rb)) return EPOLLIN | EPOLLRDNORM; return 0; } static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); poll_wait(filp, &rb_map->rb->waitq, pts); if (ringbuf_avail_data_sz(rb_map->rb) < ringbuf_total_data_sz(rb_map->rb)) return EPOLLOUT | EPOLLWRNORM; return 0; } static u64 ringbuf_map_mem_usage(const struct bpf_map *map) { struct bpf_ringbuf *rb; int nr_data_pages; int nr_meta_pages; u64 usage = sizeof(struct bpf_ringbuf_map); rb = container_of(map, struct bpf_ringbuf_map, map)->rb; usage += (u64)rb->nr_pages << PAGE_SHIFT; nr_meta_pages = RINGBUF_NR_META_PAGES; nr_data_pages = map->max_entries >> PAGE_SHIFT; usage += (nr_meta_pages + 2 * nr_data_pages) * sizeof(struct page *); return usage; } BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map) const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, .map_mmap = ringbuf_map_mmap_kern, .map_poll = ringbuf_map_poll_kern, .map_lookup_elem = ringbuf_map_lookup_elem, .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &ringbuf_map_btf_ids[0], }; BTF_ID_LIST_SINGLE(user_ringbuf_map_btf_ids, struct, bpf_ringbuf_map) const struct bpf_map_ops user_ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, .map_mmap = ringbuf_map_mmap_user, .map_poll = ringbuf_map_poll_user, .map_lookup_elem = ringbuf_map_lookup_elem, .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &user_ringbuf_map_btf_ids[0], }; /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, * calculate offset from record metadata to ring buffer in pages, rounded * down. This page offset is stored as part of record metadata and allows to * restore struct bpf_ringbuf * from record pointer. This page offset is * stored at offset 4 of record metadata header. */ static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb, struct bpf_ringbuf_hdr *hdr) { return ((void *)hdr - (void *)rb) >> PAGE_SHIFT; } /* Given pointer to ring buffer record header, restore pointer to struct * bpf_ringbuf itself by using page offset stored at offset 4 */ static struct bpf_ringbuf * bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) { unsigned long addr = (unsigned long)(void *)hdr; unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT; return (void*)((addr & PAGE_MASK) - off); } static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags; struct bpf_ringbuf_hdr *hdr; u32 len, pg_off, tmp_size, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); if (len > ringbuf_total_data_sz(rb)) return NULL; cons_pos = smp_load_acquire(&rb->consumer_pos); if (raw_res_spin_lock_irqsave(&rb->spinlock, flags)) return NULL; pend_pos = rb->pending_pos; prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; while (pend_pos < prod_pos) { hdr = (void *)rb->data + (pend_pos & rb->mask); hdr_len = READ_ONCE(hdr->len); if (hdr_len & BPF_RINGBUF_BUSY_BIT) break; tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); pend_pos += tmp_size; } rb->pending_pos = pend_pos; /* check for out of ringbuf space: * - by ensuring producer position doesn't advance more than * (ringbuf_size - 1) ahead * - by ensuring oldest not yet committed record until newest * record does not span more than (ringbuf_size - 1) */ if (new_prod_pos - cons_pos > rb->mask || new_prod_pos - pend_pos > rb->mask) { raw_res_spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } hdr = (void *)rb->data + (prod_pos & rb->mask); pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); hdr->len = size | BPF_RINGBUF_BUSY_BIT; hdr->pg_off = pg_off; /* pairs with consumer's smp_load_acquire() */ smp_store_release(&rb->producer_pos, new_prod_pos); raw_res_spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; if (unlikely(flags)) return 0; rb_map = container_of(map, struct bpf_ringbuf_map, map); return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size); } const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .func = bpf_ringbuf_reserve, .ret_type = RET_PTR_TO_RINGBUF_MEM_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) { unsigned long rec_pos, cons_pos; struct bpf_ringbuf_hdr *hdr; struct bpf_ringbuf *rb; u32 new_len; hdr = sample - BPF_RINGBUF_HDR_SZ; rb = bpf_ringbuf_restore_from_rec(hdr); new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT; if (discard) new_len |= BPF_RINGBUF_DISCARD_BIT; /* update record header with correct final size prefix */ xchg(&hdr->len, new_len); /* if consumer caught up and is waiting for our record, notify about * new data availability */ rec_pos = (void *)hdr - (void *)rb->data; cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) irq_work_queue(&rb->work); } BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, true /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; void *rec; if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP))) return -EINVAL; rb_map = container_of(map, struct bpf_ringbuf_map, map); rec = __bpf_ringbuf_reserve(rb_map->rb, size); if (!rec) return -EAGAIN; memcpy(rec, data, size); bpf_ringbuf_commit(rec, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) { struct bpf_ringbuf *rb; rb = container_of(map, struct bpf_ringbuf_map, map)->rb; switch (flags) { case BPF_RB_AVAIL_DATA: return ringbuf_avail_data_sz(rb); case BPF_RB_RING_SIZE: return ringbuf_total_data_sz(rb); case BPF_RB_CONS_POS: return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: return smp_load_acquire(&rb->producer_pos); default: return 0; } } const struct bpf_func_proto bpf_ringbuf_query_proto = { .func = bpf_ringbuf_query, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr) { struct bpf_ringbuf_map *rb_map; void *sample; int err; if (unlikely(flags)) { bpf_dynptr_set_null(ptr); return -EINVAL; } err = bpf_dynptr_check_size(size); if (err) { bpf_dynptr_set_null(ptr); return err; } rb_map = container_of(map, struct bpf_ringbuf_map, map); sample = __bpf_ringbuf_reserve(rb_map->rb, size); if (!sample) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); return 0; } const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { .func = bpf_ringbuf_reserve_dynptr, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) { if (!ptr->data) return 0; bpf_ringbuf_commit(ptr->data, flags, false /* discard */); bpf_dynptr_set_null(ptr); return 0; } const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { .func = bpf_ringbuf_submit_dynptr, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) { if (!ptr->data) return 0; bpf_ringbuf_commit(ptr->data, flags, true /* discard */); bpf_dynptr_set_null(ptr); return 0; } const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { .func = bpf_ringbuf_discard_dynptr, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *size) { int err; u32 hdr_len, sample_len, total_len, flags, *hdr; u64 cons_pos, prod_pos; /* Synchronizes with smp_store_release() in user-space producer. */ prod_pos = smp_load_acquire(&rb->producer_pos); if (prod_pos % 8) return -EINVAL; /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_sample_release() */ cons_pos = smp_load_acquire(&rb->consumer_pos); if (cons_pos >= prod_pos) return -ENODATA; hdr = (u32 *)((uintptr_t)rb->data + (uintptr_t)(cons_pos & rb->mask)); /* Synchronizes with smp_store_release() in user-space producer. */ hdr_len = smp_load_acquire(hdr); flags = hdr_len & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT); sample_len = hdr_len & ~flags; total_len = round_up(sample_len + BPF_RINGBUF_HDR_SZ, 8); /* The sample must fit within the region advertised by the producer position. */ if (total_len > prod_pos - cons_pos) return -EINVAL; /* The sample must fit within the data region of the ring buffer. */ if (total_len > ringbuf_total_data_sz(rb)) return -E2BIG; /* The sample must fit into a struct bpf_dynptr. */ err = bpf_dynptr_check_size(sample_len); if (err) return -E2BIG; if (flags & BPF_RINGBUF_DISCARD_BIT) { /* If the discard bit is set, the sample should be skipped. * * Update the consumer pos, and return -EAGAIN so the caller * knows to skip this sample and try to read the next one. */ smp_store_release(&rb->consumer_pos, cons_pos + total_len); return -EAGAIN; } if (flags & BPF_RINGBUF_BUSY_BIT) return -ENODATA; *sample = (void *)((uintptr_t)rb->data + (uintptr_t)((cons_pos + BPF_RINGBUF_HDR_SZ) & rb->mask)); *size = sample_len; return 0; } static void __bpf_user_ringbuf_sample_release(struct bpf_ringbuf *rb, size_t size, u64 flags) { u64 consumer_pos; u32 rounded_size = round_up(size + BPF_RINGBUF_HDR_SZ, 8); /* Using smp_load_acquire() is unnecessary here, as the busy-bit * prevents another task from writing to consumer_pos after it was read * by this task with smp_load_acquire() in __bpf_user_ringbuf_peek(). */ consumer_pos = rb->consumer_pos; /* Synchronizes with smp_load_acquire() in user-space producer. */ smp_store_release(&rb->consumer_pos, consumer_pos + rounded_size); } BPF_CALL_4(bpf_user_ringbuf_drain, struct bpf_map *, map, void *, callback_fn, void *, callback_ctx, u64, flags) { struct bpf_ringbuf *rb; long samples, discarded_samples = 0, ret = 0; bpf_callback_t callback = (bpf_callback_t)callback_fn; u64 wakeup_flags = BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP; int busy = 0; if (unlikely(flags & ~wakeup_flags)) return -EINVAL; rb = container_of(map, struct bpf_ringbuf_map, map)->rb; /* If another consumer is already consuming a sample, wait for them to finish. */ if (!atomic_try_cmpxchg(&rb->busy, &busy, 1)) return -EBUSY; for (samples = 0; samples < BPF_MAX_USER_RINGBUF_SAMPLES && ret == 0; samples++) { int err; u32 size; void *sample; struct bpf_dynptr_kern dynptr; err = __bpf_user_ringbuf_peek(rb, &sample, &size); if (err) { if (err == -ENODATA) { break; } else if (err == -EAGAIN) { discarded_samples++; continue; } else { ret = err; goto schedule_work_return; } } bpf_dynptr_init(&dynptr, sample, BPF_DYNPTR_TYPE_LOCAL, 0, size); ret = callback((uintptr_t)&dynptr, (uintptr_t)callback_ctx, 0, 0, 0); __bpf_user_ringbuf_sample_release(rb, size, flags); } ret = samples - discarded_samples; schedule_work_return: /* Prevent the clearing of the busy-bit from being reordered before the * storing of any rb consumer or producer positions. */ atomic_set_release(&rb->busy, 0); if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); else if (!(flags & BPF_RB_NO_WAKEUP) && samples > 0) irq_work_queue(&rb->work); return ret; } const struct bpf_func_proto bpf_user_ringbuf_drain_proto = { .func = bpf_user_ringbuf_drain, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; |
| 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/workqueue.h> #include <linux/can.h> #include <linux/can/can-ml.h> #include <linux/can/dev.h> #include <linux/can/skb.h> #include <linux/gpio/consumer.h> #include <linux/of.h> static void can_update_state_error_stats(struct net_device *dev, enum can_state new_state) { struct can_priv *priv = netdev_priv(dev); if (new_state <= priv->state) return; switch (new_state) { case CAN_STATE_ERROR_WARNING: priv->can_stats.error_warning++; break; case CAN_STATE_ERROR_PASSIVE: priv->can_stats.error_passive++; break; case CAN_STATE_BUS_OFF: priv->can_stats.bus_off++; break; default: break; } } static int can_tx_state_to_frame(struct net_device *dev, enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return CAN_ERR_CRTL_ACTIVE; case CAN_STATE_ERROR_WARNING: return CAN_ERR_CRTL_TX_WARNING; case CAN_STATE_ERROR_PASSIVE: return CAN_ERR_CRTL_TX_PASSIVE; default: return 0; } } static int can_rx_state_to_frame(struct net_device *dev, enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return CAN_ERR_CRTL_ACTIVE; case CAN_STATE_ERROR_WARNING: return CAN_ERR_CRTL_RX_WARNING; case CAN_STATE_ERROR_PASSIVE: return CAN_ERR_CRTL_RX_PASSIVE; default: return 0; } } const char *can_get_state_str(const enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return "Error Active"; case CAN_STATE_ERROR_WARNING: return "Error Warning"; case CAN_STATE_ERROR_PASSIVE: return "Error Passive"; case CAN_STATE_BUS_OFF: return "Bus Off"; case CAN_STATE_STOPPED: return "Stopped"; case CAN_STATE_SLEEPING: return "Sleeping"; default: return "<unknown>"; } } EXPORT_SYMBOL_GPL(can_get_state_str); static enum can_state can_state_err_to_state(u16 err) { if (err < CAN_ERROR_WARNING_THRESHOLD) return CAN_STATE_ERROR_ACTIVE; if (err < CAN_ERROR_PASSIVE_THRESHOLD) return CAN_STATE_ERROR_WARNING; if (err < CAN_BUS_OFF_THRESHOLD) return CAN_STATE_ERROR_PASSIVE; return CAN_STATE_BUS_OFF; } void can_state_get_by_berr_counter(const struct net_device *dev, const struct can_berr_counter *bec, enum can_state *tx_state, enum can_state *rx_state) { *tx_state = can_state_err_to_state(bec->txerr); *rx_state = can_state_err_to_state(bec->rxerr); } EXPORT_SYMBOL_GPL(can_state_get_by_berr_counter); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state) { struct can_priv *priv = netdev_priv(dev); enum can_state new_state = max(tx_state, rx_state); if (unlikely(new_state == priv->state)) { netdev_warn(dev, "%s: oops, state did not change", __func__); return; } netdev_dbg(dev, "Controller changed from %s State (%d) into %s State (%d).\n", can_get_state_str(priv->state), priv->state, can_get_state_str(new_state), new_state); can_update_state_error_stats(dev, new_state); priv->state = new_state; if (!cf) return; if (unlikely(new_state == CAN_STATE_BUS_OFF)) { cf->can_id |= CAN_ERR_BUSOFF; return; } cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= tx_state >= rx_state ? can_tx_state_to_frame(dev, tx_state) : 0; cf->data[1] |= tx_state <= rx_state ? can_rx_state_to_frame(dev, rx_state) : 0; } EXPORT_SYMBOL_GPL(can_change_state); /* CAN device restart for bus-off recovery */ static void can_restart(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); struct sk_buff *skb; struct can_frame *cf; int err; if (netif_carrier_ok(dev)) netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n"); /* No synchronization needed because the device is bus-off and * no messages can come in or go out. */ can_flush_echo_skb(dev); /* send restart message upstream */ skb = alloc_can_err_skb(dev, &cf); if (skb) { cf->can_id |= CAN_ERR_RESTARTED; netif_rx(skb); } /* Now restart the device */ netif_carrier_on(dev); err = priv->do_set_mode(dev, CAN_MODE_START); if (err) { netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err)); netif_carrier_off(dev); } else { netdev_dbg(dev, "Restarted\n"); priv->can_stats.restarts++; } } static void can_restart_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct can_priv *priv = container_of(dwork, struct can_priv, restart_work); can_restart(priv->dev); } int can_restart_now(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); /* A manual restart is only permitted if automatic restart is * disabled and the device is in the bus-off state */ if (priv->restart_ms) return -EINVAL; if (priv->state != CAN_STATE_BUS_OFF) return -EBUSY; cancel_delayed_work_sync(&priv->restart_work); can_restart(dev); return 0; } /* CAN bus-off * * This functions should be called when the device goes bus-off to * tell the netif layer that no more packets can be sent or received. * If enabled, a timer is started to trigger bus-off recovery. */ void can_bus_off(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); if (priv->restart_ms) netdev_info(dev, "bus-off, scheduling restart in %d ms\n", priv->restart_ms); else netdev_info(dev, "bus-off\n"); netif_carrier_off(dev); if (priv->restart_ms) schedule_delayed_work(&priv->restart_work, msecs_to_jiffies(priv->restart_ms)); } EXPORT_SYMBOL_GPL(can_bus_off); void can_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; dev->mtu = CAN_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; /* New-style flags. */ dev->flags = IFF_NOARP; dev->features = NETIF_F_HW_CSUM; } /* Allocate and setup space for the CAN network device */ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs) { struct can_ml_priv *can_ml; struct net_device *dev; struct can_priv *priv; int size; /* We put the driver's priv, the CAN mid layer priv and the * echo skb into the netdevice's priv. The memory layout for * the netdev_priv is like this: * * +-------------------------+ * | driver's priv | * +-------------------------+ * | struct can_ml_priv | * +-------------------------+ * | array of struct sk_buff | * +-------------------------+ */ size = ALIGN(sizeof_priv, NETDEV_ALIGN) + sizeof(struct can_ml_priv); if (echo_skb_max) size = ALIGN(size, sizeof(struct sk_buff *)) + echo_skb_max * sizeof(struct sk_buff *); dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup, txqs, rxqs); if (!dev) return NULL; priv = netdev_priv(dev); priv->dev = dev; can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; priv->echo_skb = (void *)priv + (size - echo_skb_max * sizeof(struct sk_buff *)); } priv->state = CAN_STATE_STOPPED; INIT_DELAYED_WORK(&priv->restart_work, can_restart_work); return dev; } EXPORT_SYMBOL_GPL(alloc_candev_mqs); /* Free space of the CAN network device */ void free_candev(struct net_device *dev) { free_netdev(dev); } EXPORT_SYMBOL_GPL(free_candev); /* changing MTU and control mode for CAN/CANFD devices */ int can_change_mtu(struct net_device *dev, int new_mtu) { struct can_priv *priv = netdev_priv(dev); u32 ctrlmode_static = can_get_static_ctrlmode(priv); /* Do not allow changing the MTU while running */ if (dev->flags & IFF_UP) return -EBUSY; /* allow change of MTU according to the CANFD ability of the device */ switch (new_mtu) { case CAN_MTU: /* 'CANFD-only' controllers can not switch to CAN_MTU */ if (ctrlmode_static & CAN_CTRLMODE_FD) return -EINVAL; priv->ctrlmode &= ~CAN_CTRLMODE_FD; break; case CANFD_MTU: /* check for potential CANFD ability */ if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) && !(ctrlmode_static & CAN_CTRLMODE_FD)) return -EINVAL; priv->ctrlmode |= CAN_CTRLMODE_FD; break; default: return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(can_change_mtu); /* generic implementation of netdev_ops::ndo_eth_ioctl for CAN devices * supporting hardware timestamps */ int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd) { struct hwtstamp_config hwts_cfg = { 0 }; switch (cmd) { case SIOCSHWTSTAMP: /* set */ if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg))) return -EFAULT; if (hwts_cfg.tx_type == HWTSTAMP_TX_ON && hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) return 0; return -ERANGE; case SIOCGHWTSTAMP: /* get */ hwts_cfg.tx_type = HWTSTAMP_TX_ON; hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL; if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg))) return -EFAULT; return 0; default: return -EOPNOTSUPP; } } EXPORT_SYMBOL(can_eth_ioctl_hwts); /* generic implementation of ethtool_ops::get_ts_info for CAN devices * supporting hardware timestamps */ int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, struct kernel_ethtool_ts_info *info) { info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_ON); info->rx_filters = BIT(HWTSTAMP_FILTER_ALL); return 0; } EXPORT_SYMBOL(can_ethtool_op_get_ts_info_hwts); /* Common open function when the device gets opened. * * This function should be called in the open function of the device * driver. */ int open_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); if (!priv->bittiming.bitrate) { netdev_err(dev, "bit-timing not yet defined\n"); return -EINVAL; } /* For CAN FD the data bitrate has to be >= the arbitration bitrate */ if ((priv->ctrlmode & CAN_CTRLMODE_FD) && (!priv->fd.data_bittiming.bitrate || priv->fd.data_bittiming.bitrate < priv->bittiming.bitrate)) { netdev_err(dev, "incorrect/missing data bit-timing\n"); return -EINVAL; } /* Switch carrier on if device was stopped while in bus-off state */ if (!netif_carrier_ok(dev)) netif_carrier_on(dev); return 0; } EXPORT_SYMBOL_GPL(open_candev); #ifdef CONFIG_OF /* Common function that can be used to understand the limitation of * a transceiver when it provides no means to determine these limitations * at runtime. */ void of_can_transceiver(struct net_device *dev) { struct device_node *dn; struct can_priv *priv = netdev_priv(dev); struct device_node *np = dev->dev.parent->of_node; int ret; dn = of_get_child_by_name(np, "can-transceiver"); if (!dn) return; ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max); of_node_put(dn); if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max)) netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n"); } EXPORT_SYMBOL_GPL(of_can_transceiver); #endif /* Common close function for cleanup before the device gets closed. * * This function should be called in the close function of the device * driver. */ void close_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); cancel_delayed_work_sync(&priv->restart_work); can_flush_echo_skb(dev); } EXPORT_SYMBOL_GPL(close_candev); static int can_set_termination(struct net_device *ndev, u16 term) { struct can_priv *priv = netdev_priv(ndev); int set; if (term == priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED]) set = 1; else set = 0; gpiod_set_value_cansleep(priv->termination_gpio, set); return 0; } static int can_get_termination(struct net_device *ndev) { struct can_priv *priv = netdev_priv(ndev); struct device *dev = ndev->dev.parent; struct gpio_desc *gpio; u32 term; int ret; /* Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. */ gpio = devm_gpiod_get_optional(dev, "termination", GPIOD_OUT_LOW); if (IS_ERR(gpio)) return dev_err_probe(dev, PTR_ERR(gpio), "Cannot get termination-gpios\n"); if (!gpio) return 0; ret = device_property_read_u32(dev, "termination-ohms", &term); if (ret) { netdev_err(ndev, "Cannot get termination-ohms: %pe\n", ERR_PTR(ret)); return ret; } if (term > U16_MAX) { netdev_err(ndev, "Invalid termination-ohms value (%u > %u)\n", term, U16_MAX); return -EINVAL; } priv->termination_const_cnt = ARRAY_SIZE(priv->termination_gpio_ohms); priv->termination_const = priv->termination_gpio_ohms; priv->termination_gpio = gpio; priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_DISABLED] = CAN_TERMINATION_DISABLED; priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED] = term; priv->do_set_termination = can_set_termination; return 0; } static bool can_bittiming_const_valid(const struct can_bittiming_const *btc) { if (!btc) return true; if (!btc->sjw_max) return false; return true; } /* Register the CAN network device */ int register_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); int err; /* Ensure termination_const, termination_const_cnt and * do_set_termination consistency. All must be either set or * unset. */ if ((!priv->termination_const != !priv->termination_const_cnt) || (!priv->termination_const != !priv->do_set_termination)) return -EINVAL; if (!priv->bitrate_const != !priv->bitrate_const_cnt) return -EINVAL; if (!priv->fd.data_bitrate_const != !priv->fd.data_bitrate_const_cnt) return -EINVAL; /* We only support either fixed bit rates or bit timing const. */ if ((priv->bitrate_const || priv->fd.data_bitrate_const) && (priv->bittiming_const || priv->fd.data_bittiming_const)) return -EINVAL; if (!can_bittiming_const_valid(priv->bittiming_const) || !can_bittiming_const_valid(priv->fd.data_bittiming_const)) return -EINVAL; if (!priv->termination_const) { err = can_get_termination(dev); if (err) return err; } dev->rtnl_link_ops = &can_link_ops; netif_carrier_off(dev); return register_netdev(dev); } EXPORT_SYMBOL_GPL(register_candev); /* Unregister the CAN network device */ void unregister_candev(struct net_device *dev) { unregister_netdev(dev); } EXPORT_SYMBOL_GPL(unregister_candev); /* Test if a network device is a candev based device * and return the can_priv* if so. */ struct can_priv *safe_candev_priv(struct net_device *dev) { if (dev->type != ARPHRD_CAN || dev->rtnl_link_ops != &can_link_ops) return NULL; return netdev_priv(dev); } EXPORT_SYMBOL_GPL(safe_candev_priv); static __init int can_dev_init(void) { int err; err = can_netlink_register(); if (!err) pr_info("CAN device driver interface\n"); return err; } module_init(can_dev_init); static __exit void can_dev_exit(void) { can_netlink_unregister(); } module_exit(can_dev_exit); MODULE_ALIAS_RTNL_LINK("can"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Root Complex Event Collector Support * * Authors: * Sean V Kelley <sean.v.kelley@intel.com> * Qiuxu Zhuo <qiuxu.zhuo@intel.com> * * Copyright (C) 2020 Intel Corp. */ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/pci_regs.h> #include "../pci.h" struct walk_rcec_data { struct pci_dev *rcec; int (*user_callback)(struct pci_dev *dev, void *data); void *user_data; }; static bool rcec_assoc_rciep(struct pci_dev *rcec, struct pci_dev *rciep) { unsigned long bitmap = rcec->rcec_ea->bitmap; unsigned int devn; /* An RCiEP found on a different bus in range */ if (rcec->bus->number != rciep->bus->number) return true; /* Same bus, so check bitmap */ for_each_set_bit(devn, &bitmap, 32) if (devn == PCI_SLOT(rciep->devfn)) return true; return false; } static int link_rcec_helper(struct pci_dev *dev, void *data) { struct walk_rcec_data *rcec_data = data; struct pci_dev *rcec = rcec_data->rcec; if ((pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) && rcec_assoc_rciep(rcec, dev)) { dev->rcec = rcec; pci_dbg(dev, "PME & error events signaled via %s\n", pci_name(rcec)); } return 0; } static int walk_rcec_helper(struct pci_dev *dev, void *data) { struct walk_rcec_data *rcec_data = data; struct pci_dev *rcec = rcec_data->rcec; if ((pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) && rcec_assoc_rciep(rcec, dev)) rcec_data->user_callback(dev, rcec_data->user_data); return 0; } static void walk_rcec(int (*cb)(struct pci_dev *dev, void *data), void *userdata) { struct walk_rcec_data *rcec_data = userdata; struct pci_dev *rcec = rcec_data->rcec; u8 nextbusn, lastbusn; struct pci_bus *bus; unsigned int bnr; if (!rcec->rcec_ea) return; /* Walk own bus for bitmap based association */ pci_walk_bus(rcec->bus, cb, rcec_data); nextbusn = rcec->rcec_ea->nextbusn; lastbusn = rcec->rcec_ea->lastbusn; /* All RCiEP devices are on the same bus as the RCEC */ if (nextbusn == 0xff && lastbusn == 0x00) return; for (bnr = nextbusn; bnr <= lastbusn; bnr++) { /* No association indicated (PCIe 5.0-1, 7.9.10.3) */ if (bnr == rcec->bus->number) continue; bus = pci_find_bus(pci_domain_nr(rcec->bus), bnr); if (!bus) continue; /* Find RCiEP devices on the given bus ranges */ pci_walk_bus(bus, cb, rcec_data); } } /** * pcie_link_rcec - Link RCiEP devices associated with RCEC. * @rcec: RCEC whose RCiEP devices should be linked. * * Link the given RCEC to each RCiEP device found. */ void pcie_link_rcec(struct pci_dev *rcec) { struct walk_rcec_data rcec_data; if (!rcec->rcec_ea) return; rcec_data.rcec = rcec; rcec_data.user_callback = NULL; rcec_data.user_data = NULL; walk_rcec(link_rcec_helper, &rcec_data); } /** * pcie_walk_rcec - Walk RCiEP devices associating with RCEC and call callback. * @rcec: RCEC whose RCiEP devices should be walked * @cb: Callback to be called for each RCiEP device found * @userdata: Arbitrary pointer to be passed to callback * * Walk the given RCEC. Call the callback on each RCiEP found. * * If @cb returns anything other than 0, break out. */ void pcie_walk_rcec(struct pci_dev *rcec, int (*cb)(struct pci_dev *, void *), void *userdata) { struct walk_rcec_data rcec_data; if (!rcec->rcec_ea) return; rcec_data.rcec = rcec; rcec_data.user_callback = cb; rcec_data.user_data = userdata; walk_rcec(walk_rcec_helper, &rcec_data); } void pci_rcec_init(struct pci_dev *dev) { struct rcec_ea *rcec_ea; u32 rcec, hdr, busn; u8 ver; /* Only for Root Complex Event Collectors */ if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_EC) return; rcec = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_RCEC); if (!rcec) return; rcec_ea = kzalloc(sizeof(*rcec_ea), GFP_KERNEL); if (!rcec_ea) return; pci_read_config_dword(dev, rcec + PCI_RCEC_RCIEP_BITMAP, &rcec_ea->bitmap); /* Check whether RCEC BUSN register is present */ pci_read_config_dword(dev, rcec, &hdr); ver = PCI_EXT_CAP_VER(hdr); if (ver >= PCI_RCEC_BUSN_REG_VER) { pci_read_config_dword(dev, rcec + PCI_RCEC_BUSN, &busn); rcec_ea->nextbusn = PCI_RCEC_BUSN_NEXT(busn); rcec_ea->lastbusn = PCI_RCEC_BUSN_LAST(busn); } else { /* Avoid later ver check by setting nextbusn */ rcec_ea->nextbusn = 0xff; rcec_ea->lastbusn = 0x00; } dev->rcec_ea = rcec_ea; } void pci_rcec_exit(struct pci_dev *dev) { kfree(dev->rcec_ea); dev->rcec_ea = NULL; } |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2010 Werner Fink, Jiri Slaby */ #include <linux/console.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/tty_driver.h> /* * This is handler for /proc/consoles */ static int show_console_dev(struct seq_file *m, void *v) { static const struct { short flag; char name; } con_flags[] = { { CON_ENABLED, 'E' }, { CON_CONSDEV, 'C' }, { CON_BOOT, 'B' }, { CON_NBCON, 'N' }, { CON_PRINTBUFFER, 'p' }, { CON_BRL, 'b' }, { CON_ANYTIME, 'a' }, }; char flags[ARRAY_SIZE(con_flags) + 1]; struct console *con = v; unsigned int a; dev_t dev = 0; if (con->device) { const struct tty_driver *driver; int index; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); driver = con->device(con, &index); console_unlock(); if (driver) { dev = MKDEV(driver->major, driver->minor_start); dev += index; } } for (a = 0; a < ARRAY_SIZE(con_flags); a++) flags[a] = (con->flags & con_flags[a].flag) ? con_flags[a].name : ' '; flags[a] = 0; seq_setwidth(m, 21 - 1); seq_printf(m, "%s%d", con->name, con->index); seq_pad(m, ' '); seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-', ((con->flags & CON_NBCON) || con->write) ? 'W' : '-', con->unblank ? 'U' : '-', flags); if (dev) seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev)); seq_putc(m, '\n'); return 0; } static void *c_start(struct seq_file *m, loff_t *pos) __acquires(&console_mutex) { struct console *con; loff_t off = 0; /* * Hold the console_list_lock to guarantee safe traversal of the * console list. SRCU cannot be used because there is no * place to store the SRCU cookie. */ console_list_lock(); for_each_console(con) if (off++ == *pos) break; return con; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) { struct console *con = v; ++*pos; return hlist_entry_safe(con->node.next, struct console, node); } static void c_stop(struct seq_file *m, void *v) __releases(&console_mutex) { console_list_unlock(); } static const struct seq_operations consoles_op = { .start = c_start, .next = c_next, .stop = c_stop, .show = show_console_dev }; static int __init proc_consoles_init(void) { proc_create_seq("consoles", 0, NULL, &consoles_op); return 0; } fs_initcall(proc_consoles_init); |
| 45 1588 1555 1560 1554 1556 1559 1556 1556 10 10 10 7 7 7 629 629 629 16 16 1520 1105 335 521 523 520 521 8 522 512 8 522 522 6 6 6 6 2 6 6 6 508 508 507 509 502 378 509 507 507 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 | // SPDX-License-Identifier: GPL-2.0 /* * class.c - basic device class management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2003-2004 Greg Kroah-Hartman * Copyright (c) 2003-2004 IBM Corp. */ #include <linux/device/class.h> #include <linux/device.h> #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mutex.h> #include "base.h" /* /sys/class */ static struct kset *class_kset; #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) /** * class_to_subsys - Turn a struct class into a struct subsys_private * * @class: pointer to the struct bus_type to look up * * The driver core internals need to work on the subsys_private structure, not * the external struct class pointer. This function walks the list of * registered classes in the system and finds the matching one and returns the * internal struct subsys_private that relates to that class. * * Note, the reference count of the return value is INCREMENTED if it is not * NULL. A call to subsys_put() must be done when finished with the pointer in * order for it to be properly freed. */ struct subsys_private *class_to_subsys(const struct class *class) { struct subsys_private *sp = NULL; struct kobject *kobj; if (!class || !class_kset) return NULL; spin_lock(&class_kset->list_lock); if (list_empty(&class_kset->list)) goto done; list_for_each_entry(kobj, &class_kset->list, entry) { struct kset *kset = container_of(kobj, struct kset, kobj); sp = container_of_const(kset, struct subsys_private, subsys); if (sp->class == class) goto done; } sp = NULL; done: sp = subsys_get(sp); spin_unlock(&class_kset->list_lock); return sp; } static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->show) ret = class_attr->show(cp->class, class_attr, buf); return ret; } static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->store) ret = class_attr->store(cp->class, class_attr, buf, count); return ret; } static void class_release(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; pr_debug("class '%s': release.\n", class->name); if (class->class_release) class->class_release(class); else pr_debug("class '%s' does not have a release() function, " "be careful\n", class->name); lockdep_unregister_key(&cp->lock_key); kfree(cp); } static const struct kobj_ns_type_operations *class_child_ns_type(const struct kobject *kobj) { const struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; return class->ns_type; } static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; static const struct kobj_type class_ktype = { .sysfs_ops = &class_sysfs_ops, .release = class_release, .child_ns_type = class_child_ns_type, }; int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { struct subsys_private *sp = class_to_subsys(cls); int error; if (!sp) return -EINVAL; error = sysfs_create_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_create_file_ns); void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; sysfs_remove_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_remove_file_ns); static struct device *klist_class_to_dev(struct klist_node *n) { struct device_private *p = to_device_private_class(n); return p->device; } static void klist_class_dev_get(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); put_device(dev); } int class_register(const struct class *cls) { struct subsys_private *cp; struct lock_class_key *key; int error; pr_debug("device class '%s': registering\n", cls->name); if (cls->ns_type && !cls->namespace) { pr_err("%s: class '%s' does not have namespace\n", __func__, cls->name); return -EINVAL; } if (!cls->ns_type && cls->namespace) { pr_err("%s: class '%s' does not have ns_type\n", __func__, cls->name); return -EINVAL; } cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put); INIT_LIST_HEAD(&cp->interfaces); kset_init(&cp->glue_dirs); key = &cp->lock_key; lockdep_register_key(key); __mutex_init(&cp->mutex, "subsys mutex", key); error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name); if (error) goto err_out; cp->subsys.kobj.kset = class_kset; cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; error = kset_register(&cp->subsys); if (error) goto err_out; error = sysfs_create_groups(&cp->subsys.kobj, cls->class_groups); if (error) { kobject_del(&cp->subsys.kobj); kfree_const(cp->subsys.kobj.name); goto err_out; } return 0; err_out: lockdep_unregister_key(key); kfree(cp); return error; } EXPORT_SYMBOL_GPL(class_register); void class_unregister(const struct class *cls) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; pr_debug("device class '%s': unregistering\n", cls->name); sysfs_remove_groups(&sp->subsys.kobj, cls->class_groups); kset_unregister(&sp->subsys); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_unregister); static void class_create_release(const struct class *cls) { pr_debug("%s called for %s\n", __func__, cls->name); kfree(cls); } /** * class_create - create a struct class structure * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used * in calls to device_create(). * * Returns &struct class pointer on success, or ERR_PTR() on error. * * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ struct class *class_create(const char *name) { struct class *cls; int retval; cls = kzalloc(sizeof(*cls), GFP_KERNEL); if (!cls) { retval = -ENOMEM; goto error; } cls->name = name; cls->class_release = class_create_release; retval = class_register(cls); if (retval) goto error; return cls; error: kfree(cls); return ERR_PTR(retval); } EXPORT_SYMBOL_GPL(class_create); /** * class_destroy - destroys a struct class structure * @cls: pointer to the struct class that is to be destroyed * * Note, the pointer to be destroyed must have been created with a call * to class_create(). */ void class_destroy(const struct class *cls) { if (IS_ERR_OR_NULL(cls)) return; class_unregister(cls); } EXPORT_SYMBOL_GPL(class_destroy); /** * class_dev_iter_init - initialize class device iterator * @iter: class iterator to initialize * @class: the class we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize class iterator @iter such that it iterates over devices * of @class. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type) { struct subsys_private *sp = class_to_subsys(class); struct klist_node *start_knode = NULL; memset(iter, 0, sizeof(*iter)); if (!sp) { pr_crit("%s: class %p was not registered yet\n", __func__, class); return; } if (start) start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); /** * class_dev_iter_next - iterate to the next device * @iter: class iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into class code. */ struct device *class_dev_iter_next(struct class_dev_iter *iter) { struct klist_node *knode; struct device *dev; if (!iter->sp) return NULL; while (1) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } } EXPORT_SYMBOL_GPL(class_dev_iter_next); /** * class_dev_iter_exit - finish iteration * @iter: class iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); /** * class_for_each_device - device iterator * @class: the class we're iterating * @start: the device to start with in the list, if any. * @data: data for the callback * @fn: function to be called for each device * * Iterate over @class's list of devices, and call @fn for each, * passing it @data. If @start is set, the list iteration will start * there, otherwise if it is NULL, the iteration starts at the * beginning of the list. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * @fn is allowed to do anything including calling back into class * code. There's no locking restriction. */ int class_for_each_device(const struct class *class, const struct device *start, void *data, device_iter_t fn) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; int error = 0; if (!class) return -EINVAL; if (!sp) { WARN(1, "%s called for class '%s' before it was registered", __func__, class->name); return -EINVAL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { error = fn(dev, data); if (error) break; } class_dev_iter_exit(&iter); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_for_each_device); /** * class_find_device - device iterator for locating a particular device * @class: the class we're iterating * @start: Device to begin with * @data: data for the match function * @match: function to check device * * This is similar to the class_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. * * Note, you will need to drop the reference with put_device() after use. * * @match is allowed to do anything including calling back into class * code. There's no locking restriction. */ struct device *class_find_device(const struct class *class, const struct device *start, const void *data, device_match_t match) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; if (!class) return NULL; if (!sp) { WARN(1, "%s called for class '%s' before it was registered", __func__, class->name); return NULL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); break; } } class_dev_iter_exit(&iter); subsys_put(sp); return dev; } EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent; struct class_dev_iter iter; struct device *dev; if (!class_intf || !class_intf->class) return -ENODEV; parent = class_intf->class; sp = class_to_subsys(parent); if (!sp) return -EINVAL; /* * Reference in sp is now incremented and will be dropped when * the interface is removed in the call to class_interface_unregister() */ mutex_lock(&sp->mutex); list_add_tail(&class_intf->node, &sp->interfaces); if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->add_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); return 0; } EXPORT_SYMBOL_GPL(class_interface_register); void class_interface_unregister(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; if (!parent) return; sp = class_to_subsys(parent); if (!sp) return; mutex_lock(&sp->mutex); list_del_init(&class_intf->node); if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->remove_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); /* * Decrement the reference count twice, once for the class_to_subsys() * call in the start of this function, and the second one from the * reference increment in class_interface_register() */ subsys_put(sp); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_interface_unregister); ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, char *buf) { struct class_attribute_string *cs; cs = container_of(attr, struct class_attribute_string, attr); return sysfs_emit(buf, "%s\n", cs->str); } EXPORT_SYMBOL_GPL(show_class_attr_string); struct class_compat { struct kobject *kobj; }; /** * class_compat_register - register a compatibility class * @name: the name of the class * * Compatibility class are meant as a temporary user-space compatibility * workaround when converting a family of class devices to a bus devices. */ struct class_compat *class_compat_register(const char *name) { struct class_compat *cls; cls = kmalloc(sizeof(struct class_compat), GFP_KERNEL); if (!cls) return NULL; cls->kobj = kobject_create_and_add(name, &class_kset->kobj); if (!cls->kobj) { kfree(cls); return NULL; } return cls; } EXPORT_SYMBOL_GPL(class_compat_register); /** * class_compat_unregister - unregister a compatibility class * @cls: the class to unregister */ void class_compat_unregister(struct class_compat *cls) { kobject_put(cls->kobj); kfree(cls); } EXPORT_SYMBOL_GPL(class_compat_unregister); /** * class_compat_create_link - create a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device */ int class_compat_create_link(struct class_compat *cls, struct device *dev) { return sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_create_link); /** * class_compat_remove_link - remove a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device */ void class_compat_remove_link(struct class_compat *cls, struct device *dev) { sysfs_remove_link(cls->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_remove_link); /** * class_is_registered - determine if at this moment in time, a class is * registered in the driver core or not. * @class: the class to check * * Returns a boolean to state if the class is registered in the driver core * or not. Note that the value could switch right after this call is made, * so only use this in places where you "know" it is safe to do so (usually * to determine if the specific class has been registered yet or not). * * Be careful in using this. */ bool class_is_registered(const struct class *class) { struct subsys_private *sp = class_to_subsys(class); bool is_initialized = false; if (sp) { is_initialized = true; subsys_put(sp); } return is_initialized; } EXPORT_SYMBOL_GPL(class_is_registered); int __init classes_init(void) { class_kset = kset_create_and_add("class", NULL, NULL); if (!class_kset) return -ENOMEM; return 0; } |
| 622 622 2 2 2 2 2 2 2 2 2 697 751 666 751 751 751 751 48 48 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GRE_H #define __LINUX_GRE_H #include <linux/skbuff.h> #include <net/ip_tunnels.h> struct gre_base_hdr { __be16 flags; __be16 protocol; } __packed; struct gre_full_hdr { struct gre_base_hdr fixed_header; __be16 csum; __be16 reserved1; __be32 key; __be32 seq; } __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 #define GREPROTO_MAX 2 #define GRE_IP_PROTO_MAX 2 struct gre_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); }; int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); static inline bool netif_is_gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "gretap"); } static inline bool netif_is_ip6gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { IP_TUNNEL_DECLARE_FLAGS(res) = { }; __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); ip_tunnel_flags_copy(dst, res); } static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; __set_bit(IP_TUNNEL_KEY_BIT, cond); __set_bit(IP_TUNNEL_CSUM_BIT, cond); __set_bit(IP_TUNNEL_SEQ_BIT, cond); if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { *(__sum16 *)ptr = csum_fold(lco_csum(skb)); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } } } #endif |
| 158 1154 157 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> #include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_flow_table.h> struct nft_flow_offload { struct nft_flowtable *flowtable; }; static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) { if (dst_xfrm(dst)) return FLOW_OFFLOAD_XMIT_XFRM; return FLOW_OFFLOAD_XMIT_NEIGH; } static void nft_default_forward_path(struct nf_flow_route *route, struct dst_entry *dst_cache, enum ip_conntrack_dir dir) { route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; route->tuple[dir].dst = dst_cache; route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } static bool nft_is_valid_ether_device(const struct net_device *dev) { if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return false; return true; } static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, enum ip_conntrack_dir dir, u8 *ha, struct net_device_path_stack *stack) { const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; struct net_device *dev = dst_cache->dev; struct neighbour *n; u8 nud_state; if (!nft_is_valid_ether_device(dev)) goto out; n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; read_lock_bh(&n->lock); nud_state = n->nud_state; ether_addr_copy(ha, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; out: return dev_fill_forward_path(dev, ha, stack); } struct nft_forward_info { const struct net_device *indev; const struct net_device *outdev; const struct net_device *hw_outdev; struct id { __u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps; u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; enum flow_offload_xmit_type xmit_type; }; static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) { const struct net_device_path *path; int i; memcpy(info->h_dest, ha, ETH_ALEN); for (i = 0; i < stack->num_paths; i++) { path = &stack->path[i]; switch (path->type) { case DEV_PATH_ETHERNET: case DEV_PATH_DSA: case DEV_PATH_VLAN: case DEV_PATH_PPPOE: info->indev = path->dev; if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); if (path->type == DEV_PATH_ETHERNET) break; if (path->type == DEV_PATH_DSA) { i = stack->num_paths; break; } /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { info->indev = NULL; break; } if (!info->outdev) info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_UNTAG_HW: info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: info->num_encaps--; break; case DEV_PATH_BR_VLAN_KEEP: break; } info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; default: info->indev = NULL; break; } } if (!info->outdev) info->outdev = info->indev; info->hw_outdev = info->indev; if (nf_flowtable_hw_offload(flowtable) && nft_is_valid_ether_device(info->indev)) info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; } static bool nft_flowtable_find_dev(const struct net_device *dev, struct nft_flowtable *ft) { struct nft_hook *hook; bool found = false; list_for_each_entry_rcu(hook, &ft->hook_list, list) { if (!nft_hook_find_ops_rcu(hook, dev)) continue; found = true; break; } return found; } static void nft_dev_forward_path(struct nf_flow_route *route, const struct nf_conn *ct, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { const struct dst_entry *dst = route->tuple[dir].dst; struct net_device_path_stack stack; struct nft_forward_info info = {}; unsigned char ha[ETH_ALEN]; int i; if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; route->tuple[!dir].in.ifindex = info.indev->ifindex; for (i = 0; i < info.num_encaps; i++) { route->tuple[!dir].in.encap[i].id = info.encap[i].id; route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; } route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.outdev->ifindex; route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; route->tuple[dir].xmit_type = info.xmit_type; } } static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(pkt->skb))); fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } if (!dst_hold_safe(this_dst)) return -ENOENT; nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); if (!other_dst) { dst_release(this_dst); return -ENOENT; } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { nft_dev_forward_path(route, ct, dir, ft); nft_dev_forward_path(route, ct, !dir, ft); } return 0; } static bool nft_flow_offload_skip(struct sk_buff *skb, int family) { if (skb_sec_path(skb)) return true; if (family == NFPROTO_IPV4) { const struct ip_options *opt; opt = &(IPCB(skb)->opt); if (unlikely(opt->optlen)) return true; } return false; } static void flow_offload_ct_tcp(struct nf_conn *ct) { /* conntrack will not see all packets, disable tcp window validation. */ spin_lock_bh(&ct->lock); ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; spin_unlock_bh(&ct->lock); } static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; int ret; if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt))) goto out; ct = nf_ct_get(pkt->skb, &ctinfo); if (!ct) goto out; switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst || !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if (ct->status & IPS_NAT_MASK) goto out; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) goto out; break; } #endif default: goto out; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) goto out; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) goto out; dir = CTINFO2DIR(ctinfo); if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); if (!flow) goto err_flow_alloc; flow_offload_route_init(flow, &route); if (tcph) flow_offload_ct_tcp(ct); __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; return; err_flow_add: flow_offload_free(flow); err_flow_alloc: dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); out: regs->verdict.code = NFT_BREAK; } static int nft_flow_offload_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, hook_mask); } static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, }; static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_flow_offload *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_flowtable *flowtable; if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; flowtable = nft_flowtable_lookup(ctx->net, ctx->table, tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); if (!nft_use_inc(&flowtable->use)) return -EMFILE; priv->flowtable = flowtable; return nf_ct_netns_get(ctx->net, ctx->family); } static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); } static void nft_flow_offload_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_flow_offload *priv = nft_expr_priv(expr); nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, ctx->family); } static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_flow_offload_type; static const struct nft_expr_ops nft_flow_offload_ops = { .type = &nft_flow_offload_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, .activate = nft_flow_offload_activate, .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_DOWN) return NOTIFY_DONE; nf_flow_table_cleanup(dev); return NOTIFY_DONE; } static struct notifier_block flow_offload_netdev_notifier = { .notifier_call = flow_offload_netdev_event, }; static int __init nft_flow_offload_module_init(void) { int err; err = register_netdevice_notifier(&flow_offload_netdev_notifier); if (err) goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) goto register_expr; return 0; register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); err: return err; } static void __exit nft_flow_offload_module_exit(void) { nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); } module_init(nft_flow_offload_module_init); module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); MODULE_DESCRIPTION("nftables hardware flow offload module"); |
| 42 42 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 3774 332 332 329 41 329 328 329 329 41 327 265 329 184 184 184 184 184 158 155 171 171 16 16 16 170 105 170 184 4 185 145 39 29 39 37 37 36 36 37 78 25 54 3 215 218 13 266 266 260 266 117 261 294 267 265 267 293 267 264 265 109 266 103 266 261 266 145 145 144 276 55 10 95 95 95 95 2 93 69 25 79 89 79 15 15 15 4 11 1 11 218 203 218 218 218 218 218 218 215 86 86 86 86 86 86 14 11 8 8 8 7 6 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { struct file *file; const struct inode *inode; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; file = fd_file(f); if (!(file->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!file->f_mapping) return -EINVAL; if (!file->f_mapping->a_ops) return -EINVAL; inode = file_inode(file); if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; if (IS_ANON_FILE(inode)) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 48 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H #include <linux/smp_types.h> #include <linux/rcuwait.h> /* * An entry can be in one of four states: * * free NULL, 0 -> {claimed} : free to be used * claimed NULL, 3 -> {pending} : claimed to be enqueued * pending next, 3 -> {busy} : queued, pending callback * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ struct irq_work { struct __call_single_node node; void (*func)(struct irq_work *); struct rcuwait irqwait; }; #define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){ \ .node = { .u_flags = (_flags), }, \ .func = (_func), \ .irqwait = __RCUWAIT_INITIALIZER(irqwait), \ } #define IRQ_WORK_INIT(_func) __IRQ_WORK_INIT(_func, 0) #define IRQ_WORK_INIT_LAZY(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_LAZY) #define IRQ_WORK_INIT_HARD(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_HARD_IRQ) #define DEFINE_IRQ_WORK(name, _f) \ struct irq_work name = IRQ_WORK_INIT(_f) static inline void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { *work = IRQ_WORK_INIT(func); } static inline bool irq_work_is_pending(struct irq_work *work) { return atomic_read(&work->node.a_flags) & IRQ_WORK_PENDING; } static inline bool irq_work_is_busy(struct irq_work *work) { return atomic_read(&work->node.a_flags) & IRQ_WORK_BUSY; } static inline bool irq_work_is_hard(struct irq_work *work) { return atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ; } bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); void irq_work_tick(void); void irq_work_sync(struct irq_work *work); #ifdef CONFIG_IRQ_WORK #include <asm/irq_work.h> void irq_work_run(void); bool irq_work_needs_cpu(void); void irq_work_single(void *arg); void arch_irq_work_raise(void); #else static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } static inline void irq_work_single(void *arg) { } #endif #endif /* _LINUX_IRQ_WORK_H */ |
| 6 6 1 5 6 1 1 1 2 2 2 4 3 1 2 2 2 2 3 1 1 1 2 2 2 1 1 11 11 1 4 1 2 8 1 11 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 | // SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) /* Copyright(c) 2014 - 2020 Intel Corporation */ #include <crypto/algapi.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/bitops.h> #include <linux/pci.h> #include <linux/cdev.h> #include <linux/uaccess.h> #include "adf_accel_devices.h" #include "adf_common_drv.h" #include "adf_cfg.h" #include "adf_cfg_common.h" #include "adf_cfg_user.h" #define ADF_CFG_MAX_SECTION 512 #define ADF_CFG_MAX_KEY_VAL 256 #define DEVICE_NAME "qat_adf_ctl" static DEFINE_MUTEX(adf_ctl_lock); static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg); static const struct file_operations adf_ctl_ops = { .owner = THIS_MODULE, .unlocked_ioctl = adf_ctl_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static const struct class adf_ctl_class = { .name = DEVICE_NAME, }; struct adf_ctl_drv_info { unsigned int major; struct cdev drv_cdev; }; static struct adf_ctl_drv_info adf_ctl_drv; static void adf_chr_drv_destroy(void) { device_destroy(&adf_ctl_class, MKDEV(adf_ctl_drv.major, 0)); cdev_del(&adf_ctl_drv.drv_cdev); class_unregister(&adf_ctl_class); unregister_chrdev_region(MKDEV(adf_ctl_drv.major, 0), 1); } static int adf_chr_drv_create(void) { dev_t dev_id; struct device *drv_device; int ret; if (alloc_chrdev_region(&dev_id, 0, 1, DEVICE_NAME)) { pr_err("QAT: unable to allocate chrdev region\n"); return -EFAULT; } ret = class_register(&adf_ctl_class); if (ret) goto err_chrdev_unreg; adf_ctl_drv.major = MAJOR(dev_id); cdev_init(&adf_ctl_drv.drv_cdev, &adf_ctl_ops); if (cdev_add(&adf_ctl_drv.drv_cdev, dev_id, 1)) { pr_err("QAT: cdev add failed\n"); goto err_class_destr; } drv_device = device_create(&adf_ctl_class, NULL, MKDEV(adf_ctl_drv.major, 0), NULL, DEVICE_NAME); if (IS_ERR(drv_device)) { pr_err("QAT: failed to create device\n"); goto err_cdev_del; } return 0; err_cdev_del: cdev_del(&adf_ctl_drv.drv_cdev); err_class_destr: class_unregister(&adf_ctl_class); err_chrdev_unreg: unregister_chrdev_region(dev_id, 1); return -EFAULT; } static int adf_ctl_alloc_resources(struct adf_user_cfg_ctl_data **ctl_data, unsigned long arg) { struct adf_user_cfg_ctl_data *cfg_data; cfg_data = kzalloc(sizeof(*cfg_data), GFP_KERNEL); if (!cfg_data) return -ENOMEM; /* Initialize device id to NO DEVICE as 0 is a valid device id */ cfg_data->device_id = ADF_CFG_NO_DEVICE; if (copy_from_user(cfg_data, (void __user *)arg, sizeof(*cfg_data))) { pr_err("QAT: failed to copy from user cfg_data.\n"); kfree(cfg_data); return -EIO; } *ctl_data = cfg_data; return 0; } static int adf_add_key_value_data(struct adf_accel_dev *accel_dev, const char *section, const struct adf_user_cfg_key_val *key_val) { if (key_val->type == ADF_HEX) { long *ptr = (long *)key_val->val; long val = *ptr; if (adf_cfg_add_key_value_param(accel_dev, section, key_val->key, (void *)val, key_val->type)) { dev_err(&GET_DEV(accel_dev), "failed to add hex keyvalue.\n"); return -EFAULT; } } else { if (adf_cfg_add_key_value_param(accel_dev, section, key_val->key, key_val->val, key_val->type)) { dev_err(&GET_DEV(accel_dev), "failed to add keyvalue.\n"); return -EFAULT; } } return 0; } static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev, struct adf_user_cfg_ctl_data *ctl_data) { struct adf_user_cfg_key_val key_val; struct adf_user_cfg_key_val *params_head; struct adf_user_cfg_section section, *section_head; int i, j; section_head = ctl_data->config_section; for (i = 0; section_head && i < ADF_CFG_MAX_SECTION; i++) { if (copy_from_user(§ion, (void __user *)section_head, sizeof(*section_head))) { dev_err(&GET_DEV(accel_dev), "failed to copy section info\n"); goto out_err; } if (adf_cfg_section_add(accel_dev, section.name)) { dev_err(&GET_DEV(accel_dev), "failed to add section.\n"); goto out_err; } params_head = section.params; for (j = 0; params_head && j < ADF_CFG_MAX_KEY_VAL; j++) { if (copy_from_user(&key_val, (void __user *)params_head, sizeof(key_val))) { dev_err(&GET_DEV(accel_dev), "Failed to copy keyvalue.\n"); goto out_err; } if (adf_add_key_value_data(accel_dev, section.name, &key_val)) { goto out_err; } params_head = key_val.next; } section_head = section.next; } return 0; out_err: adf_cfg_del_all(accel_dev); return -EFAULT; } static int adf_ctl_ioctl_dev_config(struct file *fp, unsigned int cmd, unsigned long arg) { int ret; struct adf_user_cfg_ctl_data *ctl_data; struct adf_accel_dev *accel_dev; ret = adf_ctl_alloc_resources(&ctl_data, arg); if (ret) return ret; accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id); if (!accel_dev) { ret = -EFAULT; goto out; } if (adf_dev_started(accel_dev)) { ret = -EFAULT; goto out; } if (adf_copy_key_value_data(accel_dev, ctl_data)) { ret = -EFAULT; goto out; } set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status); out: kfree(ctl_data); return ret; } static int adf_ctl_is_device_in_use(int id) { struct adf_accel_dev *dev; list_for_each_entry(dev, adf_devmgr_get_head(), list) { if (id == dev->accel_id || id == ADF_CFG_ALL_DEVICES) { if (adf_devmgr_in_reset(dev) || adf_dev_in_use(dev)) { dev_info(&GET_DEV(dev), "device qat_dev%d is busy\n", dev->accel_id); return -EBUSY; } } } return 0; } static void adf_ctl_stop_devices(u32 id) { struct adf_accel_dev *accel_dev; list_for_each_entry(accel_dev, adf_devmgr_get_head(), list) { if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) { if (!adf_dev_started(accel_dev)) continue; /* First stop all VFs */ if (!accel_dev->is_vf) continue; adf_dev_down(accel_dev); } } list_for_each_entry(accel_dev, adf_devmgr_get_head(), list) { if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) { if (!adf_dev_started(accel_dev)) continue; adf_dev_down(accel_dev); } } } static int adf_ctl_ioctl_dev_stop(struct file *fp, unsigned int cmd, unsigned long arg) { int ret; struct adf_user_cfg_ctl_data *ctl_data; ret = adf_ctl_alloc_resources(&ctl_data, arg); if (ret) return ret; if (adf_devmgr_verify_id(ctl_data->device_id)) { pr_err("QAT: Device %d not found\n", ctl_data->device_id); ret = -ENODEV; goto out; } ret = adf_ctl_is_device_in_use(ctl_data->device_id); if (ret) goto out; if (ctl_data->device_id == ADF_CFG_ALL_DEVICES) pr_info("QAT: Stopping all acceleration devices.\n"); else pr_info("QAT: Stopping acceleration device qat_dev%d.\n", ctl_data->device_id); adf_ctl_stop_devices(ctl_data->device_id); out: kfree(ctl_data); return ret; } static int adf_ctl_ioctl_dev_start(struct file *fp, unsigned int cmd, unsigned long arg) { int ret; struct adf_user_cfg_ctl_data *ctl_data; struct adf_accel_dev *accel_dev; ret = adf_ctl_alloc_resources(&ctl_data, arg); if (ret) return ret; ret = -ENODEV; accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id); if (!accel_dev) goto out; dev_info(&GET_DEV(accel_dev), "Starting acceleration device qat_dev%d.\n", ctl_data->device_id); ret = adf_dev_up(accel_dev, false); if (ret) { dev_err(&GET_DEV(accel_dev), "Failed to start qat_dev%d\n", ctl_data->device_id); adf_dev_down(accel_dev); } out: kfree(ctl_data); return ret; } static int adf_ctl_ioctl_get_num_devices(struct file *fp, unsigned int cmd, unsigned long arg) { u32 num_devices = 0; adf_devmgr_get_num_dev(&num_devices); if (copy_to_user((void __user *)arg, &num_devices, sizeof(num_devices))) return -EFAULT; return 0; } static int adf_ctl_ioctl_get_status(struct file *fp, unsigned int cmd, unsigned long arg) { struct adf_hw_device_data *hw_data; struct adf_dev_status_info dev_info; struct adf_accel_dev *accel_dev; if (copy_from_user(&dev_info, (void __user *)arg, sizeof(struct adf_dev_status_info))) { pr_err("QAT: failed to copy from user.\n"); return -EFAULT; } accel_dev = adf_devmgr_get_dev_by_id(dev_info.accel_id); if (!accel_dev) return -ENODEV; hw_data = accel_dev->hw_device; dev_info.state = adf_dev_started(accel_dev) ? DEV_UP : DEV_DOWN; dev_info.num_ae = hw_data->get_num_aes(hw_data); dev_info.num_accel = hw_data->get_num_accels(hw_data); dev_info.num_logical_accel = hw_data->num_logical_accel; dev_info.banks_per_accel = hw_data->num_banks / hw_data->num_logical_accel; strscpy(dev_info.name, hw_data->dev_class->name, sizeof(dev_info.name)); dev_info.instance_id = hw_data->instance_id; dev_info.type = hw_data->dev_class->type; dev_info.bus = accel_to_pci_dev(accel_dev)->bus->number; dev_info.dev = PCI_SLOT(accel_to_pci_dev(accel_dev)->devfn); dev_info.fun = PCI_FUNC(accel_to_pci_dev(accel_dev)->devfn); if (copy_to_user((void __user *)arg, &dev_info, sizeof(struct adf_dev_status_info))) { dev_err(&GET_DEV(accel_dev), "failed to copy status.\n"); return -EFAULT; } return 0; } static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { int ret; if (mutex_lock_interruptible(&adf_ctl_lock)) return -EFAULT; switch (cmd) { case IOCTL_CONFIG_SYS_RESOURCE_PARAMETERS: ret = adf_ctl_ioctl_dev_config(fp, cmd, arg); break; case IOCTL_STOP_ACCEL_DEV: ret = adf_ctl_ioctl_dev_stop(fp, cmd, arg); break; case IOCTL_START_ACCEL_DEV: ret = adf_ctl_ioctl_dev_start(fp, cmd, arg); break; case IOCTL_GET_NUM_DEVICES: ret = adf_ctl_ioctl_get_num_devices(fp, cmd, arg); break; case IOCTL_STATUS_ACCEL_DEV: ret = adf_ctl_ioctl_get_status(fp, cmd, arg); break; default: pr_err_ratelimited("QAT: Invalid ioctl %d\n", cmd); ret = -EFAULT; break; } mutex_unlock(&adf_ctl_lock); return ret; } static int __init adf_register_ctl_device_driver(void) { if (adf_chr_drv_create()) goto err_chr_dev; if (adf_init_misc_wq()) goto err_misc_wq; if (adf_init_aer()) goto err_aer; if (adf_init_pf_wq()) goto err_pf_wq; if (adf_init_vf_wq()) goto err_vf_wq; if (qat_crypto_register()) goto err_crypto_register; if (qat_compression_register()) goto err_compression_register; return 0; err_compression_register: qat_crypto_unregister(); err_crypto_register: adf_exit_vf_wq(); err_vf_wq: adf_exit_pf_wq(); err_pf_wq: adf_exit_aer(); err_aer: adf_exit_misc_wq(); err_misc_wq: adf_chr_drv_destroy(); err_chr_dev: mutex_destroy(&adf_ctl_lock); return -EFAULT; } static void __exit adf_unregister_ctl_device_driver(void) { adf_chr_drv_destroy(); adf_exit_misc_wq(); adf_exit_aer(); adf_exit_vf_wq(); adf_exit_pf_wq(); qat_crypto_unregister(); qat_compression_unregister(); adf_clean_vf_map(false); mutex_destroy(&adf_ctl_lock); } module_init(adf_register_ctl_device_driver); module_exit(adf_unregister_ctl_device_driver); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel"); MODULE_DESCRIPTION("Intel(R) QuickAssist Technology"); MODULE_ALIAS_CRYPTO("intel_qat"); MODULE_VERSION(ADF_DRV_VERSION); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 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 | #ifndef _UAPI_LINUX_VIRTIO_RING_H #define _UAPI_LINUX_VIRTIO_RING_H /* An interface for efficient virtio implementation, currently for use by KVM, * but hopefully others soon. Do NOT change this since it will * break existing servers and clients. * * This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. * * 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 name of IBM nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * 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 IBM 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. * * Copyright Rusty Russell IBM Corporation 2007. */ #ifndef __KERNEL__ #include <stdint.h> #endif #include <linux/types.h> #include <linux/virtio_types.h> /* This marks a buffer as continuing via the next field. */ #define VRING_DESC_F_NEXT 1 /* This marks a buffer as write-only (otherwise read-only). */ #define VRING_DESC_F_WRITE 2 /* This means the buffer contains a list of buffer descriptors. */ #define VRING_DESC_F_INDIRECT 4 /* * Mark a descriptor as available or used in packed ring. * Notice: they are defined as shifts instead of shifted values. */ #define VRING_PACKED_DESC_F_AVAIL 7 #define VRING_PACKED_DESC_F_USED 15 /* The Host uses this in used->flags to advise the Guest: don't kick me when * you add a buffer. It's unreliable, so it's simply an optimization. Guest * will still kick if it's out of buffers. */ #define VRING_USED_F_NO_NOTIFY 1 /* The Guest uses this in avail->flags to advise the Host: don't interrupt me * when you consume a buffer. It's unreliable, so it's simply an * optimization. */ #define VRING_AVAIL_F_NO_INTERRUPT 1 /* Enable events in packed ring. */ #define VRING_PACKED_EVENT_FLAG_ENABLE 0x0 /* Disable events in packed ring. */ #define VRING_PACKED_EVENT_FLAG_DISABLE 0x1 /* * Enable events for a specific descriptor in packed ring. * (as specified by Descriptor Ring Change Event Offset/Wrap Counter). * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated. */ #define VRING_PACKED_EVENT_FLAG_DESC 0x2 /* * Wrap counter bit shift in event suppression structure * of packed ring. */ #define VRING_PACKED_EVENT_F_WRAP_CTR 15 /* We support indirect buffer descriptors */ #define VIRTIO_RING_F_INDIRECT_DESC 28 /* The Guest publishes the used index for which it expects an interrupt * at the end of the avail ring. Host should ignore the avail->flags field. */ /* The Host publishes the avail index for which it expects a kick * at the end of the used ring. Guest should ignore the used->flags field. */ #define VIRTIO_RING_F_EVENT_IDX 29 /* Alignment requirements for vring elements. * When using pre-virtio 1.0 layout, these fall out naturally. */ #define VRING_AVAIL_ALIGN_SIZE 2 #define VRING_USED_ALIGN_SIZE 4 #define VRING_DESC_ALIGN_SIZE 16 /** * struct vring_desc - Virtio ring descriptors, * 16 bytes long. These can chain together via @next. * * @addr: buffer address (guest-physical) * @len: buffer length * @flags: descriptor flags * @next: index of the next descriptor in the chain, * if the VRING_DESC_F_NEXT flag is set. We chain unused * descriptors via this, too. */ struct vring_desc { __virtio64 addr; __virtio32 len; __virtio16 flags; __virtio16 next; }; struct vring_avail { __virtio16 flags; __virtio16 idx; __virtio16 ring[]; }; /* u32 is used here for ids for padding reasons. */ struct vring_used_elem { /* Index of start of used descriptor chain. */ __virtio32 id; /* Total length of the descriptor chain which was used (written to) */ __virtio32 len; }; typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE))) vring_used_elem_t; struct vring_used { __virtio16 flags; __virtio16 idx; vring_used_elem_t ring[]; }; /* * The ring element addresses are passed between components with different * alignments assumptions. Thus, we might need to decrease the compiler-selected * alignment, and so must use a typedef to make sure the aligned attribute * actually takes hold: * * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes * * When used on a struct, or struct member, the aligned attribute can only * increase the alignment; in order to decrease it, the packed attribute must * be specified as well. When used as part of a typedef, the aligned attribute * can both increase and decrease alignment, and specifying the packed * attribute generates a warning. */ typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE))) vring_desc_t; typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE))) vring_avail_t; typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE))) vring_used_t; struct vring { unsigned int num; vring_desc_t *desc; vring_avail_t *avail; vring_used_t *used; }; #ifndef VIRTIO_RING_NO_LEGACY /* The standard layout for the ring is a continuous chunk of memory which looks * like this. We assume num is a power of 2. * * struct vring * { * // The actual descriptors (16 bytes each) * struct vring_desc desc[num]; * * // A ring of available descriptor heads with free-running index. * __virtio16 avail_flags; * __virtio16 avail_idx; * __virtio16 available[num]; * __virtio16 used_event_idx; * * // Padding to the next align boundary. * char pad[]; * * // A ring of used descriptor heads with free-running index. * __virtio16 used_flags; * __virtio16 used_idx; * struct vring_used_elem used[num]; * __virtio16 avail_event_idx; * }; */ /* We publish the used event index at the end of the available ring, and vice * versa. They are at the end for backwards compatibility. */ #define vring_used_event(vr) ((vr)->avail->ring[(vr)->num]) #define vring_avail_event(vr) (*(__virtio16 *)&(vr)->used->ring[(vr)->num]) static inline void vring_init(struct vring *vr, unsigned int num, void *p, unsigned long align) { vr->num = num; vr->desc = p; vr->avail = (struct vring_avail *)((char *)p + num * sizeof(struct vring_desc)); vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16) + align-1) & ~(align - 1)); } static inline unsigned vring_size(unsigned int num, unsigned long align) { return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num) + align - 1) & ~(align - 1)) + sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num; } #endif /* VIRTIO_RING_NO_LEGACY */ /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ /* Assuming a given event_idx value from the other side, if * we have just incremented index from old to new_idx, * should we trigger an event? */ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old) { /* Note: Xen has similar logic for notification hold-off * in include/xen/interface/io/ring.h with req_event and req_prod * corresponding to event_idx + 1 and new_idx respectively. * Note also that req_event and req_prod in Xen start at 1, * event indexes in virtio start at 0. */ return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old); } struct vring_packed_desc_event { /* Descriptor Ring Change Event Offset/Wrap Counter. */ __le16 off_wrap; /* Descriptor Ring Change Event Flags. */ __le16 flags; }; struct vring_packed_desc { /* Buffer Address. */ __le64 addr; /* Buffer Length. */ __le32 len; /* Buffer ID. */ __le16 id; /* The flags depending on descriptor type. */ __le16 flags; }; #endif /* _UAPI_LINUX_VIRTIO_RING_H */ |
| 528 317 527 527 527 527 527 528 527 528 528 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Provide a default dump_stack() function for architectures * which don't implement their own. */ #include <linux/kernel.h> #include <linux/buildid.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/smp.h> #include <linux/atomic.h> #include <linux/kexec.h> #include <linux/utsname.h> #include <linux/stop_machine.h> static char dump_stack_arch_desc_str[128]; /** * dump_stack_set_arch_desc - set arch-specific str to show with task dumps * @fmt: printf-style format string * @...: arguments for the format string * * The configured string will be printed right after utsname during task * dumps. Usually used to add arch-specific system identifiers. If an * arch wants to make use of such an ID string, it should initialize this * as soon as possible during boot. */ void __init dump_stack_set_arch_desc(const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(dump_stack_arch_desc_str, sizeof(dump_stack_arch_desc_str), fmt, args); va_end(args); } #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) #define BUILD_ID_FMT " %20phN" #define BUILD_ID_VAL vmlinux_build_id #else #define BUILD_ID_FMT "%s" #define BUILD_ID_VAL "" #endif /** * dump_stack_print_info - print generic debug info for dump_stack() * @log_lvl: log level * * Arch-specific dump_stack() implementations can use this function to * print out the same debug information as the generic dump_stack(). */ void dump_stack_print_info(const char *log_lvl) { printk("%sCPU: %d UID: %u PID: %d Comm: %.20s %s%s %s %.*s %s " BUILD_ID_FMT "\n", log_lvl, raw_smp_processor_id(), __kuid_val(current_real_cred()->euid), current->pid, current->comm, kexec_crash_loaded() ? "Kdump: loaded " : "", print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version, preempt_model_str(), BUILD_ID_VAL); if (get_taint()) printk("%s%s\n", log_lvl, print_tainted_verbose()); if (dump_stack_arch_desc_str[0] != '\0') printk("%sHardware name: %s\n", log_lvl, dump_stack_arch_desc_str); print_worker_info(log_lvl, current); print_stop_info(log_lvl, current); print_scx_info(log_lvl, current); } /** * show_regs_print_info - print generic debug info for show_regs() * @log_lvl: log level * * show_regs() implementations can use this function to print out generic * debug information. */ void show_regs_print_info(const char *log_lvl) { dump_stack_print_info(log_lvl); } static void __dump_stack(const char *log_lvl) { dump_stack_print_info(log_lvl); show_stack(NULL, NULL, log_lvl); } /** * dump_stack_lvl - dump the current task information and its stack trace * @log_lvl: log level * * Architectures can override this implementation by implementing its own. */ asmlinkage __visible void dump_stack_lvl(const char *log_lvl) { bool in_panic = this_cpu_in_panic(); unsigned long flags; /* * Permit this cpu to perform nested stack dumps while serialising * against other CPUs, unless this CPU is in panic. * * When in panic, non-panic CPUs are not permitted to store new * printk messages so there is no need to synchronize the output. * This avoids potential deadlock in panic() if another CPU is * holding and unable to release the printk_cpu_sync. */ if (!in_panic) printk_cpu_sync_get_irqsave(flags); __dump_stack(log_lvl); if (!in_panic) printk_cpu_sync_put_irqrestore(flags); } EXPORT_SYMBOL(dump_stack_lvl); asmlinkage __visible void dump_stack(void) { dump_stack_lvl(KERN_DEFAULT); } EXPORT_SYMBOL(dump_stack); |
| 49 48 48 48 49 28 25 28 8 5 3 2 1 3 2 1 8 1 1 1 1 24 24 16 24 23 1 1 24 24 24 1 24 24 24 1 23 24 24 13 7 9 5 4 3 3 1 2 3 4 1 3 2 1 1 1 2 4 3 15 4 1 1 7 7 6 5 7 2 1 1 1 1 3 3 2 1 1 34 32 4 2 4 1 2 4 7 7 3 3 3 15 34 40 40 38 35 2 1 2 1 1 41 15 14 7 6 5 3 6 5 1 4 3 2 1 2 3 14 15 41 24 24 24 28 28 25 28 19 27 2 2 2 2 2 2 2 2 2 2 1 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/in.h> #include <linux/ipv6.h> #include <linux/poll.h> #include <net/sock.h> #include "rds.h" /* this is just used for stats gathering :/ */ static DEFINE_SPINLOCK(rds_sock_lock); static unsigned long rds_sock_count; static LIST_HEAD(rds_sock_list); DECLARE_WAIT_QUEUE_HEAD(rds_poll_waitq); /* * This is called as the final descriptor referencing this socket is closed. * We have to unbind the socket so that another socket can be bound to the * address it was using. * * We have to be careful about racing with the incoming path. sock_orphan() * sets SOCK_DEAD and we use that as an indicator to the rx path that new * messages shouldn't be queued. */ static int rds_release(struct socket *sock) { struct sock *sk = sock->sk; struct rds_sock *rs; if (!sk) goto out; rs = rds_sk_to_rs(sk); sock_orphan(sk); /* Note - rds_clear_recv_queue grabs rs_recv_lock, so * that ensures the recv path has completed messing * with the socket. */ rds_clear_recv_queue(rs); rds_cong_remove_socket(rs); rds_remove_bound(rs); rds_send_drop_to(rs, NULL); rds_rdma_drop_keys(rs); rds_notify_queue_get(rs, NULL); rds_notify_msg_zcopy_purge(&rs->rs_zcookie_queue); spin_lock_bh(&rds_sock_lock); list_del_init(&rs->rs_item); rds_sock_count--; spin_unlock_bh(&rds_sock_lock); rds_trans_put(rs->rs_transport); sock->sk = NULL; sock_put(sk); out: return 0; } /* * Careful not to race with rds_release -> sock_orphan which clears sk_sleep. * _bh() isn't OK here, we're called from interrupt handlers. It's probably OK * to wake the waitqueue after sk_sleep is clear as we hold a sock ref, but * this seems more conservative. * NB - normally, one would use sk_callback_lock for this, but we can * get here from interrupts, whereas the network code grabs sk_callback_lock * with _lock_bh only - so relying on sk_callback_lock introduces livelocks. */ void rds_wake_sk_sleep(struct rds_sock *rs) { unsigned long flags; read_lock_irqsave(&rs->rs_recv_lock, flags); __rds_wake_sk_sleep(rds_rs_to_sk(rs)); read_unlock_irqrestore(&rs->rs_recv_lock, flags); } static int rds_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); struct sockaddr_in6 *sin6; struct sockaddr_in *sin; int uaddr_len; /* racey, don't care */ if (peer) { if (ipv6_addr_any(&rs->rs_conn_addr)) return -ENOTCONN; if (ipv6_addr_v4mapped(&rs->rs_conn_addr)) { sin = (struct sockaddr_in *)uaddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); sin->sin_family = AF_INET; sin->sin_port = rs->rs_conn_port; sin->sin_addr.s_addr = rs->rs_conn_addr_v4; uaddr_len = sizeof(*sin); } else { sin6 = (struct sockaddr_in6 *)uaddr; sin6->sin6_family = AF_INET6; sin6->sin6_port = rs->rs_conn_port; sin6->sin6_addr = rs->rs_conn_addr; sin6->sin6_flowinfo = 0; /* scope_id is the same as in the bound address. */ sin6->sin6_scope_id = rs->rs_bound_scope_id; uaddr_len = sizeof(*sin6); } } else { /* If socket is not yet bound and the socket is connected, * set the return address family to be the same as the * connected address, but with 0 address value. If it is not * connected, set the family to be AF_UNSPEC (value 0) and * the address size to be that of an IPv4 address. */ if (ipv6_addr_any(&rs->rs_bound_addr)) { if (ipv6_addr_any(&rs->rs_conn_addr)) { sin = (struct sockaddr_in *)uaddr; memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_UNSPEC; return sizeof(*sin); } #if IS_ENABLED(CONFIG_IPV6) if (!(ipv6_addr_type(&rs->rs_conn_addr) & IPV6_ADDR_MAPPED)) { sin6 = (struct sockaddr_in6 *)uaddr; memset(sin6, 0, sizeof(*sin6)); sin6->sin6_family = AF_INET6; return sizeof(*sin6); } #endif sin = (struct sockaddr_in *)uaddr; memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; return sizeof(*sin); } if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) { sin = (struct sockaddr_in *)uaddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); sin->sin_family = AF_INET; sin->sin_port = rs->rs_bound_port; sin->sin_addr.s_addr = rs->rs_bound_addr_v4; uaddr_len = sizeof(*sin); } else { sin6 = (struct sockaddr_in6 *)uaddr; sin6->sin6_family = AF_INET6; sin6->sin6_port = rs->rs_bound_port; sin6->sin6_addr = rs->rs_bound_addr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = rs->rs_bound_scope_id; uaddr_len = sizeof(*sin6); } } return uaddr_len; } /* * RDS' poll is without a doubt the least intuitive part of the interface, * as EPOLLIN and EPOLLOUT do not behave entirely as you would expect from * a network protocol. * * EPOLLIN is asserted if * - there is data on the receive queue. * - to signal that a previously congested destination may have become * uncongested * - A notification has been queued to the socket (this can be a congestion * update, or a RDMA completion, or a MSG_ZEROCOPY completion). * * EPOLLOUT is asserted if there is room on the send queue. This does not mean * however, that the next sendmsg() call will succeed. If the application tries * to send to a congested destination, the system call may still fail (and * return ENOBUFS). */ static __poll_t rds_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); __poll_t mask = 0; unsigned long flags; poll_wait(file, sk_sleep(sk), wait); if (rs->rs_seen_congestion) poll_wait(file, &rds_poll_waitq, wait); read_lock_irqsave(&rs->rs_recv_lock, flags); if (!rs->rs_cong_monitor) { /* When a congestion map was updated, we signal EPOLLIN for * "historical" reasons. Applications can also poll for * WRBAND instead. */ if (rds_cong_updated_since(&rs->rs_cong_track)) mask |= (EPOLLIN | EPOLLRDNORM | EPOLLWRBAND); } else { spin_lock(&rs->rs_lock); if (rs->rs_cong_notify) mask |= (EPOLLIN | EPOLLRDNORM); spin_unlock(&rs->rs_lock); } if (!list_empty(&rs->rs_recv_queue) || !list_empty(&rs->rs_notify_queue) || !list_empty(&rs->rs_zcookie_queue.zcookie_head)) mask |= (EPOLLIN | EPOLLRDNORM); if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) mask |= (EPOLLOUT | EPOLLWRNORM); if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; read_unlock_irqrestore(&rs->rs_recv_lock, flags); /* clear state any time we wake a seen-congested socket */ if (mask) rs->rs_seen_congestion = 0; return mask; } static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); rds_tos_t utos, tos = 0; switch (cmd) { case SIOCRDSSETTOS: if (get_user(utos, (rds_tos_t __user *)arg)) return -EFAULT; if (rs->rs_transport && rs->rs_transport->get_tos_map) tos = rs->rs_transport->get_tos_map(utos); else return -ENOIOCTLCMD; spin_lock_bh(&rds_sock_lock); if (rs->rs_tos || rs->rs_conn) { spin_unlock_bh(&rds_sock_lock); return -EINVAL; } rs->rs_tos = tos; spin_unlock_bh(&rds_sock_lock); break; case SIOCRDSGETTOS: spin_lock_bh(&rds_sock_lock); tos = rs->rs_tos; spin_unlock_bh(&rds_sock_lock); if (put_user(tos, (rds_tos_t __user *)arg)) return -EFAULT; break; default: return -ENOIOCTLCMD; } return 0; } static int rds_cancel_sent_to(struct rds_sock *rs, sockptr_t optval, int len) { struct sockaddr_in6 sin6; struct sockaddr_in sin; int ret = 0; /* racing with another thread binding seems ok here */ if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } if (len < sizeof(struct sockaddr_in)) { ret = -EINVAL; goto out; } else if (len < sizeof(struct sockaddr_in6)) { /* Assume IPv4 */ if (copy_from_sockptr(&sin, optval, sizeof(struct sockaddr_in))) { ret = -EFAULT; goto out; } ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr); sin6.sin6_port = sin.sin_port; } else { if (copy_from_sockptr(&sin6, optval, sizeof(struct sockaddr_in6))) { ret = -EFAULT; goto out; } } rds_send_drop_to(rs, &sin6); out: return ret; } static int rds_set_bool_option(unsigned char *optvar, sockptr_t optval, int optlen) { int value; if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&value, optval, sizeof(int))) return -EFAULT; *optvar = !!value; return 0; } static int rds_cong_monitor(struct rds_sock *rs, sockptr_t optval, int optlen) { int ret; ret = rds_set_bool_option(&rs->rs_cong_monitor, optval, optlen); if (ret == 0) { if (rs->rs_cong_monitor) { rds_cong_add_socket(rs); } else { rds_cong_remove_socket(rs); rs->rs_cong_mask = 0; rs->rs_cong_notify = 0; } } return ret; } static int rds_set_transport(struct rds_sock *rs, sockptr_t optval, int optlen) { int t_type; if (rs->rs_transport) return -EOPNOTSUPP; /* previously attached to transport */ if (optlen != sizeof(int)) return -EINVAL; if (copy_from_sockptr(&t_type, optval, sizeof(t_type))) return -EFAULT; if (t_type < 0 || t_type >= RDS_TRANS_COUNT) return -EINVAL; rs->rs_transport = rds_trans_get(t_type); return rs->rs_transport ? 0 : -ENOPROTOOPT; } static int rds_enable_recvtstamp(struct sock *sk, sockptr_t optval, int optlen, int optname) { int val, valbool; if (optlen != sizeof(int)) return -EFAULT; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; valbool = val ? 1 : 0; if (optname == SO_TIMESTAMP_NEW) sock_set_flag(sk, SOCK_TSTAMP_NEW); if (valbool) sock_set_flag(sk, SOCK_RCVTSTAMP); else sock_reset_flag(sk, SOCK_RCVTSTAMP); return 0; } static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_rx_trace_so trace; int i; if (optlen != sizeof(struct rds_rx_trace_so)) return -EFAULT; if (copy_from_sockptr(&trace, optval, sizeof(trace))) return -EFAULT; if (trace.rx_traces > RDS_MSG_RX_DGRAM_TRACE_MAX) return -EFAULT; rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } rs->rs_rx_trace[i] = trace.rx_trace_pos[i]; } return 0; } static int rds_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret; if (level != SOL_RDS) { ret = -ENOPROTOOPT; goto out; } switch (optname) { case RDS_CANCEL_SENT_TO: ret = rds_cancel_sent_to(rs, optval, optlen); break; case RDS_GET_MR: ret = rds_get_mr(rs, optval, optlen); break; case RDS_GET_MR_FOR_DEST: ret = rds_get_mr_for_dest(rs, optval, optlen); break; case RDS_FREE_MR: ret = rds_free_mr(rs, optval, optlen); break; case RDS_RECVERR: ret = rds_set_bool_option(&rs->rs_recverr, optval, optlen); break; case RDS_CONG_MONITOR: ret = rds_cong_monitor(rs, optval, optlen); break; case SO_RDS_TRANSPORT: lock_sock(sock->sk); ret = rds_set_transport(rs, optval, optlen); release_sock(sock->sk); break; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: lock_sock(sock->sk); ret = rds_enable_recvtstamp(sock->sk, optval, optlen, optname); release_sock(sock->sk); break; case SO_RDS_MSG_RXPATH_LATENCY: ret = rds_recv_track_latency(rs, optval, optlen); break; default: ret = -ENOPROTOOPT; } out: return ret; } static int rds_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret = -ENOPROTOOPT, len; int trans; if (level != SOL_RDS) goto out; if (get_user(len, optlen)) { ret = -EFAULT; goto out; } switch (optname) { case RDS_INFO_FIRST ... RDS_INFO_LAST: ret = rds_info_getsockopt(sock, optname, optval, optlen); break; case RDS_RECVERR: if (len < sizeof(int)) ret = -EINVAL; else if (put_user(rs->rs_recverr, (int __user *) optval) || put_user(sizeof(int), optlen)) ret = -EFAULT; else ret = 0; break; case SO_RDS_TRANSPORT: if (len < sizeof(int)) { ret = -EINVAL; break; } trans = (rs->rs_transport ? rs->rs_transport->t_type : RDS_TRANS_NONE); /* unbound */ if (put_user(trans, (int __user *)optval) || put_user(sizeof(int), optlen)) ret = -EFAULT; else ret = 0; break; default: break; } out: return ret; } static int rds_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_in *sin; struct rds_sock *rs = rds_sk_to_rs(sk); int ret = 0; if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; lock_sock(sk); switch (uaddr->sa_family) { case AF_INET: sin = (struct sockaddr_in *)uaddr; if (addr_len < sizeof(struct sockaddr_in)) { ret = -EINVAL; break; } if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) { ret = -EDESTADDRREQ; break; } if (ipv4_is_multicast(sin->sin_addr.s_addr) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) { ret = -EINVAL; break; } ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &rs->rs_conn_addr); rs->rs_conn_port = sin->sin_port; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct sockaddr_in6 *sin6; int addr_type; sin6 = (struct sockaddr_in6 *)uaddr; if (addr_len < sizeof(struct sockaddr_in6)) { ret = -EINVAL; break; } addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) { ret = -EPROTOTYPE; break; } /* It is a mapped address. Need to do some sanity * checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) { ret = -EPROTOTYPE; break; } } if (addr_type & IPV6_ADDR_LINKLOCAL) { /* If socket is arleady bound to a link local address, * the peer address must be on the same link. */ if (sin6->sin6_scope_id == 0 || (!ipv6_addr_any(&rs->rs_bound_addr) && rs->rs_bound_scope_id && sin6->sin6_scope_id != rs->rs_bound_scope_id)) { ret = -EINVAL; break; } /* Remember the connected address scope ID. It will * be checked against the binding local address when * the socket is bound. */ rs->rs_bound_scope_id = sin6->sin6_scope_id; } rs->rs_conn_addr = sin6->sin6_addr; rs->rs_conn_port = sin6->sin6_port; break; } #endif default: ret = -EAFNOSUPPORT; break; } release_sock(sk); return ret; } static struct proto rds_proto = { .name = "RDS", .owner = THIS_MODULE, .obj_size = sizeof(struct rds_sock), }; static const struct proto_ops rds_proto_ops = { .family = AF_RDS, .owner = THIS_MODULE, .release = rds_release, .bind = rds_bind, .connect = rds_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = rds_getname, .poll = rds_poll, .ioctl = rds_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = rds_setsockopt, .getsockopt = rds_getsockopt, .sendmsg = rds_sendmsg, .recvmsg = rds_recvmsg, .mmap = sock_no_mmap, }; static void rds_sock_destruct(struct sock *sk) { struct rds_sock *rs = rds_sk_to_rs(sk); WARN_ON((&rs->rs_item != rs->rs_item.next || &rs->rs_item != rs->rs_item.prev)); } static int __rds_create(struct socket *sock, struct sock *sk, int protocol) { struct rds_sock *rs; sock_init_data(sock, sk); sock->ops = &rds_proto_ops; sk->sk_protocol = protocol; sk->sk_destruct = rds_sock_destruct; rs = rds_sk_to_rs(sk); spin_lock_init(&rs->rs_lock); rwlock_init(&rs->rs_recv_lock); INIT_LIST_HEAD(&rs->rs_send_queue); INIT_LIST_HEAD(&rs->rs_recv_queue); INIT_LIST_HEAD(&rs->rs_notify_queue); INIT_LIST_HEAD(&rs->rs_cong_list); rds_message_zcopy_queue_init(&rs->rs_zcookie_queue); spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; rs->rs_tos = 0; rs->rs_conn = NULL; spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); rds_sock_count++; spin_unlock_bh(&rds_sock_lock); return 0; } static int rds_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; if (sock->type != SOCK_SEQPACKET || protocol) return -ESOCKTNOSUPPORT; sk = sk_alloc(net, AF_RDS, GFP_KERNEL, &rds_proto, kern); if (!sk) return -ENOMEM; return __rds_create(sock, sk, protocol); } void rds_sock_addref(struct rds_sock *rs) { sock_hold(rds_rs_to_sk(rs)); } void rds_sock_put(struct rds_sock *rs) { sock_put(rds_rs_to_sk(rs)); } static const struct net_proto_family rds_family_ops = { .family = AF_RDS, .create = rds_create, .owner = THIS_MODULE, }; static void rds_sock_inc_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_sock *rs; struct rds_incoming *inc; unsigned int total = 0; len /= sizeof(struct rds_info_message); spin_lock_bh(&rds_sock_lock); list_for_each_entry(rs, &rds_sock_list, rs_item) { /* This option only supports IPv4 sockets. */ if (!ipv6_addr_v4mapped(&rs->rs_bound_addr)) continue; read_lock(&rs->rs_recv_lock); /* XXX too lazy to maintain counts.. */ list_for_each_entry(inc, &rs->rs_recv_queue, i_item) { total++; if (total <= len) rds_inc_info_copy(inc, iter, inc->i_saddr.s6_addr32[3], rs->rs_bound_addr_v4, 1); } read_unlock(&rs->rs_recv_lock); } spin_unlock_bh(&rds_sock_lock); lens->nr = total; lens->each = sizeof(struct rds_info_message); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_sock_inc_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_incoming *inc; unsigned int total = 0; struct rds_sock *rs; len /= sizeof(struct rds6_info_message); spin_lock_bh(&rds_sock_lock); list_for_each_entry(rs, &rds_sock_list, rs_item) { read_lock(&rs->rs_recv_lock); list_for_each_entry(inc, &rs->rs_recv_queue, i_item) { total++; if (total <= len) rds6_inc_info_copy(inc, iter, &inc->i_saddr, &rs->rs_bound_addr, 1); } read_unlock(&rs->rs_recv_lock); } spin_unlock_bh(&rds_sock_lock); lens->nr = total; lens->each = sizeof(struct rds6_info_message); } #endif static void rds_sock_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_info_socket sinfo; unsigned int cnt = 0; struct rds_sock *rs; len /= sizeof(struct rds_info_socket); spin_lock_bh(&rds_sock_lock); if (len < rds_sock_count) { cnt = rds_sock_count; goto out; } list_for_each_entry(rs, &rds_sock_list, rs_item) { /* This option only supports IPv4 sockets. */ if (!ipv6_addr_v4mapped(&rs->rs_bound_addr)) continue; sinfo.sndbuf = rds_sk_sndbuf(rs); sinfo.rcvbuf = rds_sk_rcvbuf(rs); sinfo.bound_addr = rs->rs_bound_addr_v4; sinfo.connected_addr = rs->rs_conn_addr_v4; sinfo.bound_port = rs->rs_bound_port; sinfo.connected_port = rs->rs_conn_port; sinfo.inum = sock_i_ino(rds_rs_to_sk(rs)); rds_info_copy(iter, &sinfo, sizeof(sinfo)); cnt++; } out: lens->nr = cnt; lens->each = sizeof(struct rds_info_socket); spin_unlock_bh(&rds_sock_lock); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_sock_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds6_info_socket sinfo6; struct rds_sock *rs; len /= sizeof(struct rds6_info_socket); spin_lock_bh(&rds_sock_lock); if (len < rds_sock_count) goto out; list_for_each_entry(rs, &rds_sock_list, rs_item) { sinfo6.sndbuf = rds_sk_sndbuf(rs); sinfo6.rcvbuf = rds_sk_rcvbuf(rs); sinfo6.bound_addr = rs->rs_bound_addr; sinfo6.connected_addr = rs->rs_conn_addr; sinfo6.bound_port = rs->rs_bound_port; sinfo6.connected_port = rs->rs_conn_port; sinfo6.inum = sock_i_ino(rds_rs_to_sk(rs)); rds_info_copy(iter, &sinfo6, sizeof(sinfo6)); } out: lens->nr = rds_sock_count; lens->each = sizeof(struct rds6_info_socket); spin_unlock_bh(&rds_sock_lock); } #endif static void rds_exit(void) { sock_unregister(rds_family_ops.family); proto_unregister(&rds_proto); rds_conn_exit(); rds_cong_exit(); rds_sysctl_exit(); rds_threads_exit(); rds_stats_exit(); rds_page_exit(); rds_bind_lock_destroy(); rds_info_deregister_func(RDS_INFO_SOCKETS, rds_sock_info); rds_info_deregister_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_SOCKETS, rds6_sock_info); rds_info_deregister_func(RDS6_INFO_RECV_MESSAGES, rds6_sock_inc_info); #endif } module_exit(rds_exit); u32 rds_gen_num; static int __init rds_init(void) { int ret; net_get_random_once(&rds_gen_num, sizeof(rds_gen_num)); ret = rds_bind_lock_init(); if (ret) goto out; ret = rds_conn_init(); if (ret) goto out_bind; ret = rds_threads_init(); if (ret) goto out_conn; ret = rds_sysctl_init(); if (ret) goto out_threads; ret = rds_stats_init(); if (ret) goto out_sysctl; ret = proto_register(&rds_proto, 1); if (ret) goto out_stats; ret = sock_register(&rds_family_ops); if (ret) goto out_proto; rds_info_register_func(RDS_INFO_SOCKETS, rds_sock_info); rds_info_register_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_SOCKETS, rds6_sock_info); rds_info_register_func(RDS6_INFO_RECV_MESSAGES, rds6_sock_inc_info); #endif goto out; out_proto: proto_unregister(&rds_proto); out_stats: rds_stats_exit(); out_sysctl: rds_sysctl_exit(); out_threads: rds_threads_exit(); out_conn: rds_conn_exit(); rds_cong_exit(); rds_page_exit(); out_bind: rds_bind_lock_destroy(); out: return ret; } module_init(rds_init); #define DRV_VERSION "4.0" #define DRV_RELDATE "Feb 12, 2009" MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>"); MODULE_DESCRIPTION("RDS: Reliable Datagram Sockets" " v" DRV_VERSION " (" DRV_RELDATE ")"); MODULE_VERSION(DRV_VERSION); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS_NETPROTO(PF_RDS); |
| 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/signalfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> #include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD /* * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) wake_up(&tsk->sighand->signalfd_wqh); } extern void signalfd_cleanup(struct sighand_struct *sighand); #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } static inline void signalfd_cleanup(struct sighand_struct *sighand) { } #endif /* CONFIG_SIGNALFD */ #endif /* _LINUX_SIGNALFD_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2021 Intel Corporation */ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include "hci_codec.h" static int hci_codec_list_add(struct list_head *list, struct hci_op_read_local_codec_caps *sent, struct hci_rp_read_local_codec_caps *rp, void *caps, __u32 len) { struct codec_list *entry; entry = kzalloc(sizeof(*entry) + len, GFP_KERNEL); if (!entry) return -ENOMEM; entry->id = sent->id; if (sent->id == 0xFF) { entry->cid = __le16_to_cpu(sent->cid); entry->vid = __le16_to_cpu(sent->vid); } entry->transport = sent->transport; entry->len = len; entry->num_caps = 0; if (rp) { entry->num_caps = rp->num_caps; memcpy(entry->caps, caps, len); } list_add(&entry->list, list); return 0; } void hci_codec_list_clear(struct list_head *codec_list) { struct codec_list *c, *n; list_for_each_entry_safe(c, n, codec_list, list) { list_del(&c->list); kfree(c); } } static void hci_read_codec_capabilities(struct hci_dev *hdev, __u8 transport, struct hci_op_read_local_codec_caps *cmd) { __u8 i; for (i = 0; i < TRANSPORT_TYPE_MAX; i++) { if (transport & BIT(i)) { struct hci_rp_read_local_codec_caps *rp; struct hci_codec_caps *caps; struct sk_buff *skb; __u8 j; __u32 len; cmd->transport = i; /* If Read_Codec_Capabilities command is not supported * then just add codec to the list without caps */ if (!(hdev->commands[45] & 0x08)) { hci_dev_lock(hdev); hci_codec_list_add(&hdev->local_codecs, cmd, NULL, NULL, 0); hci_dev_unlock(hdev); continue; } skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODEC_CAPS, sizeof(*cmd), cmd, 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read codec capabilities (%ld)", PTR_ERR(skb)); continue; } if (skb->len < sizeof(*rp)) goto error; rp = (void *)skb->data; if (rp->status) goto error; if (!rp->num_caps) { len = 0; /* this codec doesn't have capabilities */ goto skip_caps_parse; } skb_pull(skb, sizeof(*rp)); for (j = 0, len = 0; j < rp->num_caps; j++) { caps = (void *)skb->data; if (skb->len < sizeof(*caps)) goto error; if (skb->len < caps->len) goto error; len += sizeof(caps->len) + caps->len; skb_pull(skb, sizeof(caps->len) + caps->len); } skip_caps_parse: hci_dev_lock(hdev); hci_codec_list_add(&hdev->local_codecs, cmd, rp, (__u8 *)rp + sizeof(*rp), len); hci_dev_unlock(hdev); error: kfree_skb(skb); } } } void hci_read_supported_codecs(struct hci_dev *hdev) { struct sk_buff *skb; struct hci_rp_read_local_supported_codecs *rp; struct hci_std_codecs *std_codecs; struct hci_vnd_codecs *vnd_codecs; struct hci_op_read_local_codec_caps caps; __u8 i; skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", PTR_ERR(skb)); return; } if (skb->len < sizeof(*rp)) goto error; rp = (void *)skb->data; if (rp->status) goto error; skb_pull(skb, sizeof(rp->status)); std_codecs = (void *)skb->data; /* validate codecs length before accessing */ if (skb->len < flex_array_size(std_codecs, codec, std_codecs->num) + sizeof(std_codecs->num)) goto error; /* enumerate codec capabilities of standard codecs */ memset(&caps, 0, sizeof(caps)); for (i = 0; i < std_codecs->num; i++) { caps.id = std_codecs->codec[i]; caps.direction = 0x00; hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } skb_pull(skb, flex_array_size(std_codecs, codec, std_codecs->num) + sizeof(std_codecs->num)); vnd_codecs = (void *)skb->data; /* validate vendor codecs length before accessing */ if (skb->len < flex_array_size(vnd_codecs, codec, vnd_codecs->num) + sizeof(vnd_codecs->num)) goto error; /* enumerate vendor codec capabilities */ for (i = 0; i < vnd_codecs->num; i++) { caps.id = 0xFF; caps.cid = vnd_codecs->codec[i].cid; caps.vid = vnd_codecs->codec[i].vid; caps.direction = 0x00; hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } error: kfree_skb(skb); } void hci_read_supported_codecs_v2(struct hci_dev *hdev) { struct sk_buff *skb; struct hci_rp_read_local_supported_codecs_v2 *rp; struct hci_std_codecs_v2 *std_codecs; struct hci_vnd_codecs_v2 *vnd_codecs; struct hci_op_read_local_codec_caps caps; __u8 i; skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS_V2, 0, NULL, 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", PTR_ERR(skb)); return; } if (skb->len < sizeof(*rp)) goto error; rp = (void *)skb->data; if (rp->status) goto error; skb_pull(skb, sizeof(rp->status)); std_codecs = (void *)skb->data; /* check for payload data length before accessing */ if (skb->len < flex_array_size(std_codecs, codec, std_codecs->num) + sizeof(std_codecs->num)) goto error; memset(&caps, 0, sizeof(caps)); for (i = 0; i < std_codecs->num; i++) { caps.id = std_codecs->codec[i].id; hci_read_codec_capabilities(hdev, std_codecs->codec[i].transport, &caps); } skb_pull(skb, flex_array_size(std_codecs, codec, std_codecs->num) + sizeof(std_codecs->num)); vnd_codecs = (void *)skb->data; /* check for payload data length before accessing */ if (skb->len < flex_array_size(vnd_codecs, codec, vnd_codecs->num) + sizeof(vnd_codecs->num)) goto error; for (i = 0; i < vnd_codecs->num; i++) { caps.id = 0xFF; caps.cid = vnd_codecs->codec[i].cid; caps.vid = vnd_codecs->codec[i].vid; hci_read_codec_capabilities(hdev, vnd_codecs->codec[i].transport, &caps); } error: kfree_skb(skb); } |
| 92 92 92 92 92 92 92 92 83 83 83 83 83 83 571 570 572 571 571 571 566 567 567 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __FIRMWARE_SYSFS_H #define __FIRMWARE_SYSFS_H #include <linux/device.h> #include "firmware.h" MODULE_IMPORT_NS("FIRMWARE_LOADER_PRIVATE"); extern struct firmware_fallback_config fw_fallback_config; extern struct device_attribute dev_attr_loading; #ifdef CONFIG_FW_LOADER_USER_HELPER /** * struct firmware_fallback_config - firmware fallback configuration settings * * Helps describe and fine tune the fallback mechanism. * * @force_sysfs_fallback: force the sysfs fallback mechanism to be used * as if one had enabled CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y. * Useful to help debug a CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y * functionality on a kernel where that config entry has been disabled. * @ignore_sysfs_fallback: force to disable the sysfs fallback mechanism. * This emulates the behaviour as if we had set the kernel * config CONFIG_FW_LOADER_USER_HELPER=n. * @old_timeout: for internal use * @loading_timeout: the timeout to wait for the fallback mechanism before * giving up, in seconds. */ struct firmware_fallback_config { unsigned int force_sysfs_fallback; unsigned int ignore_sysfs_fallback; int old_timeout; int loading_timeout; }; /* These getters are vetted to use int properly */ static inline int __firmware_loading_timeout(void) { return fw_fallback_config.loading_timeout; } /* These setters are vetted to use int properly */ static inline void __fw_fallback_set_timeout(int timeout) { fw_fallback_config.loading_timeout = timeout; } #endif #ifdef CONFIG_FW_LOADER_SYSFS int register_sysfs_loader(void); void unregister_sysfs_loader(void); #if defined(CONFIG_FW_LOADER_USER_HELPER) && defined(CONFIG_SYSCTL) int register_firmware_config_sysctl(void); void unregister_firmware_config_sysctl(void); #else static inline int register_firmware_config_sysctl(void) { return 0; } static inline void unregister_firmware_config_sysctl(void) { } #endif /* CONFIG_FW_LOADER_USER_HELPER && CONFIG_SYSCTL */ #else /* CONFIG_FW_LOADER_SYSFS */ static inline int register_sysfs_loader(void) { return 0; } static inline void unregister_sysfs_loader(void) { } #endif /* CONFIG_FW_LOADER_SYSFS */ struct fw_sysfs { bool nowait; struct device dev; struct fw_priv *fw_priv; struct firmware *fw; void *fw_upload_priv; }; #define to_fw_sysfs(__dev) container_of_const(__dev, struct fw_sysfs, dev) void __fw_load_abort(struct fw_priv *fw_priv); static inline void fw_load_abort(struct fw_sysfs *fw_sysfs) { struct fw_priv *fw_priv = fw_sysfs->fw_priv; __fw_load_abort(fw_priv); } struct fw_sysfs * fw_create_instance(struct firmware *firmware, const char *fw_name, struct device *device, u32 opt_flags); #ifdef CONFIG_FW_UPLOAD extern struct device_attribute dev_attr_status; extern struct device_attribute dev_attr_error; extern struct device_attribute dev_attr_cancel; extern struct device_attribute dev_attr_remaining_size; int fw_upload_start(struct fw_sysfs *fw_sysfs); void fw_upload_free(struct fw_sysfs *fw_sysfs); umode_t fw_upload_is_visible(struct kobject *kobj, struct attribute *attr, int n); #else static inline int fw_upload_start(struct fw_sysfs *fw_sysfs) { return 0; } static inline void fw_upload_free(struct fw_sysfs *fw_sysfs) { } #endif #endif /* __FIRMWARE_SYSFS_H */ |
| 4 8 3 3 3 40 3 3 3 10 9 9 8 8 8 8 7 6 6 6 6 2 2 1 2 2 5 5 5 5 5 1 4 5 5 4 1 1 1 1 1 4 4 1 3 2 2 7 6 2 5 5 1 1 2 2 1 195 195 195 195 195 195 195 5 2 3 1 3 3 2 1 190 190 4 190 188 186 1 186 3 183 183 174 174 114 174 174 174 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/nospec.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/pcm.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include "pcm_local.h" MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Abramo Bagnara <abramo@alsa-project.org>"); MODULE_DESCRIPTION("Midlevel PCM code for ALSA."); MODULE_LICENSE("GPL"); static LIST_HEAD(snd_pcm_devices); static DEFINE_MUTEX(register_mutex); #if IS_ENABLED(CONFIG_SND_PCM_OSS) static LIST_HEAD(snd_pcm_notify_list); #endif static int snd_pcm_free(struct snd_pcm *pcm); static int snd_pcm_dev_free(struct snd_device *device); static int snd_pcm_dev_register(struct snd_device *device); static int snd_pcm_dev_disconnect(struct snd_device *device); static struct snd_pcm *snd_pcm_get(struct snd_card *card, int device) { struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == card && pcm->device == device) return pcm; } return NULL; } static int snd_pcm_next(struct snd_card *card, int device) { struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == card && pcm->device > device) return pcm->device; else if (pcm->card->number > card->number) return -1; } return -1; } static int snd_pcm_add(struct snd_pcm *newpcm) { struct snd_pcm *pcm; if (newpcm->internal) return 0; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == newpcm->card && pcm->device == newpcm->device) return -EBUSY; if (pcm->card->number > newpcm->card->number || (pcm->card == newpcm->card && pcm->device > newpcm->device)) { list_add(&newpcm->list, pcm->list.prev); return 0; } } list_add_tail(&newpcm->list, &snd_pcm_devices); return 0; } static int snd_pcm_control_ioctl(struct snd_card *card, struct snd_ctl_file *control, unsigned int cmd, unsigned long arg) { switch (cmd) { case SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE: { int device; if (get_user(device, (int __user *)arg)) return -EFAULT; scoped_guard(mutex, ®ister_mutex) device = snd_pcm_next(card, device); if (put_user(device, (int __user *)arg)) return -EFAULT; return 0; } case SNDRV_CTL_IOCTL_PCM_INFO: { struct snd_pcm_info __user *info; unsigned int device, subdevice; int stream; struct snd_pcm *pcm; struct snd_pcm_str *pstr; struct snd_pcm_substream *substream; info = (struct snd_pcm_info __user *)arg; if (get_user(device, &info->device)) return -EFAULT; if (get_user(stream, &info->stream)) return -EFAULT; if (stream < 0 || stream > 1) return -EINVAL; stream = array_index_nospec(stream, 2); if (get_user(subdevice, &info->subdevice)) return -EFAULT; guard(mutex)(®ister_mutex); pcm = snd_pcm_get(card, device); if (pcm == NULL) return -ENXIO; pstr = &pcm->streams[stream]; if (pstr->substream_count == 0) return -ENOENT; if (subdevice >= pstr->substream_count) return -ENXIO; for (substream = pstr->substream; substream; substream = substream->next) if (substream->number == (int)subdevice) break; if (substream == NULL) return -ENXIO; guard(mutex)(&pcm->open_mutex); return snd_pcm_info_user(substream, info); } case SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE: { int val; if (get_user(val, (int __user *)arg)) return -EFAULT; control->preferred_subdevice[SND_CTL_SUBDEV_PCM] = val; return 0; } } return -ENOIOCTLCMD; } #define FORMAT(v) [SNDRV_PCM_FORMAT_##v] = #v static const char * const snd_pcm_format_names[] = { FORMAT(S8), FORMAT(U8), FORMAT(S16_LE), FORMAT(S16_BE), FORMAT(U16_LE), FORMAT(U16_BE), FORMAT(S24_LE), FORMAT(S24_BE), FORMAT(U24_LE), FORMAT(U24_BE), FORMAT(S32_LE), FORMAT(S32_BE), FORMAT(U32_LE), FORMAT(U32_BE), FORMAT(FLOAT_LE), FORMAT(FLOAT_BE), FORMAT(FLOAT64_LE), FORMAT(FLOAT64_BE), FORMAT(IEC958_SUBFRAME_LE), FORMAT(IEC958_SUBFRAME_BE), FORMAT(MU_LAW), FORMAT(A_LAW), FORMAT(IMA_ADPCM), FORMAT(MPEG), FORMAT(GSM), FORMAT(SPECIAL), FORMAT(S24_3LE), FORMAT(S24_3BE), FORMAT(U24_3LE), FORMAT(U24_3BE), FORMAT(S20_3LE), FORMAT(S20_3BE), FORMAT(U20_3LE), FORMAT(U20_3BE), FORMAT(S18_3LE), FORMAT(S18_3BE), FORMAT(U18_3LE), FORMAT(U18_3BE), FORMAT(G723_24), FORMAT(G723_24_1B), FORMAT(G723_40), FORMAT(G723_40_1B), FORMAT(DSD_U8), FORMAT(DSD_U16_LE), FORMAT(DSD_U32_LE), FORMAT(DSD_U16_BE), FORMAT(DSD_U32_BE), FORMAT(S20_LE), FORMAT(S20_BE), FORMAT(U20_LE), FORMAT(U20_BE), }; /** * snd_pcm_format_name - Return a name string for the given PCM format * @format: PCM format * * Return: the format name string */ const char *snd_pcm_format_name(snd_pcm_format_t format) { unsigned int format_num = (__force unsigned int)format; if (format_num >= ARRAY_SIZE(snd_pcm_format_names) || !snd_pcm_format_names[format_num]) return "Unknown"; return snd_pcm_format_names[format_num]; } EXPORT_SYMBOL_GPL(snd_pcm_format_name); #ifdef CONFIG_SND_VERBOSE_PROCFS #define STATE(v) [SNDRV_PCM_STATE_##v] = #v #define STREAM(v) [SNDRV_PCM_STREAM_##v] = #v #define READY(v) [SNDRV_PCM_READY_##v] = #v #define XRUN(v) [SNDRV_PCM_XRUN_##v] = #v #define SILENCE(v) [SNDRV_PCM_SILENCE_##v] = #v #define TSTAMP(v) [SNDRV_PCM_TSTAMP_##v] = #v #define ACCESS(v) [SNDRV_PCM_ACCESS_##v] = #v #define START(v) [SNDRV_PCM_START_##v] = #v #define SUBFORMAT(v) [SNDRV_PCM_SUBFORMAT_##v] = #v static const char * const snd_pcm_stream_names[] = { STREAM(PLAYBACK), STREAM(CAPTURE), }; static const char * const snd_pcm_state_names[] = { STATE(OPEN), STATE(SETUP), STATE(PREPARED), STATE(RUNNING), STATE(XRUN), STATE(DRAINING), STATE(PAUSED), STATE(SUSPENDED), STATE(DISCONNECTED), }; static const char * const snd_pcm_access_names[] = { ACCESS(MMAP_INTERLEAVED), ACCESS(MMAP_NONINTERLEAVED), ACCESS(MMAP_COMPLEX), ACCESS(RW_INTERLEAVED), ACCESS(RW_NONINTERLEAVED), }; static const char * const snd_pcm_subformat_names[] = { SUBFORMAT(STD), SUBFORMAT(MSBITS_MAX), SUBFORMAT(MSBITS_20), SUBFORMAT(MSBITS_24), }; static const char * const snd_pcm_tstamp_mode_names[] = { TSTAMP(NONE), TSTAMP(ENABLE), }; static const char *snd_pcm_stream_name(int stream) { return snd_pcm_stream_names[stream]; } static const char *snd_pcm_access_name(snd_pcm_access_t access) { return snd_pcm_access_names[(__force int)access]; } static const char *snd_pcm_subformat_name(snd_pcm_subformat_t subformat) { return snd_pcm_subformat_names[(__force int)subformat]; } static const char *snd_pcm_tstamp_mode_name(int mode) { return snd_pcm_tstamp_mode_names[mode]; } static const char *snd_pcm_state_name(snd_pcm_state_t state) { return snd_pcm_state_names[(__force int)state]; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) #include <linux/soundcard.h> static const char *snd_pcm_oss_format_name(int format) { switch (format) { case AFMT_MU_LAW: return "MU_LAW"; case AFMT_A_LAW: return "A_LAW"; case AFMT_IMA_ADPCM: return "IMA_ADPCM"; case AFMT_U8: return "U8"; case AFMT_S16_LE: return "S16_LE"; case AFMT_S16_BE: return "S16_BE"; case AFMT_S8: return "S8"; case AFMT_U16_LE: return "U16_LE"; case AFMT_U16_BE: return "U16_BE"; case AFMT_MPEG: return "MPEG"; default: return "unknown"; } } #endif static void snd_pcm_proc_info_read(struct snd_pcm_substream *substream, struct snd_info_buffer *buffer) { struct snd_pcm_info *info __free(kfree) = NULL; int err; if (! substream) return; info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return; err = snd_pcm_info(substream, info); if (err < 0) { snd_iprintf(buffer, "error %d\n", err); return; } snd_iprintf(buffer, "card: %d\n", info->card); snd_iprintf(buffer, "device: %d\n", info->device); snd_iprintf(buffer, "subdevice: %d\n", info->subdevice); snd_iprintf(buffer, "stream: %s\n", snd_pcm_stream_name(info->stream)); snd_iprintf(buffer, "id: %s\n", info->id); snd_iprintf(buffer, "name: %s\n", info->name); snd_iprintf(buffer, "subname: %s\n", info->subname); snd_iprintf(buffer, "class: %d\n", info->dev_class); snd_iprintf(buffer, "subclass: %d\n", info->dev_subclass); snd_iprintf(buffer, "subdevices_count: %d\n", info->subdevices_count); snd_iprintf(buffer, "subdevices_avail: %d\n", info->subdevices_avail); } static void snd_pcm_stream_proc_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_pcm_proc_info_read(((struct snd_pcm_str *)entry->private_data)->substream, buffer); } static void snd_pcm_substream_proc_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_pcm_proc_info_read(entry->private_data, buffer); } static void snd_pcm_substream_proc_hw_params_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } if (runtime->state == SNDRV_PCM_STATE_OPEN) { snd_iprintf(buffer, "no setup\n"); return; } snd_iprintf(buffer, "access: %s\n", snd_pcm_access_name(runtime->access)); snd_iprintf(buffer, "format: %s\n", snd_pcm_format_name(runtime->format)); snd_iprintf(buffer, "subformat: %s\n", snd_pcm_subformat_name(runtime->subformat)); snd_iprintf(buffer, "channels: %u\n", runtime->channels); snd_iprintf(buffer, "rate: %u (%u/%u)\n", runtime->rate, runtime->rate_num, runtime->rate_den); snd_iprintf(buffer, "period_size: %lu\n", runtime->period_size); snd_iprintf(buffer, "buffer_size: %lu\n", runtime->buffer_size); #if IS_ENABLED(CONFIG_SND_PCM_OSS) if (substream->oss.oss) { snd_iprintf(buffer, "OSS format: %s\n", snd_pcm_oss_format_name(runtime->oss.format)); snd_iprintf(buffer, "OSS channels: %u\n", runtime->oss.channels); snd_iprintf(buffer, "OSS rate: %u\n", runtime->oss.rate); snd_iprintf(buffer, "OSS period bytes: %lu\n", (unsigned long)runtime->oss.period_bytes); snd_iprintf(buffer, "OSS periods: %u\n", runtime->oss.periods); snd_iprintf(buffer, "OSS period frames: %lu\n", (unsigned long)runtime->oss.period_frames); } #endif } static void snd_pcm_substream_proc_sw_params_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } if (runtime->state == SNDRV_PCM_STATE_OPEN) { snd_iprintf(buffer, "no setup\n"); return; } snd_iprintf(buffer, "tstamp_mode: %s\n", snd_pcm_tstamp_mode_name(runtime->tstamp_mode)); snd_iprintf(buffer, "period_step: %u\n", runtime->period_step); snd_iprintf(buffer, "avail_min: %lu\n", runtime->control->avail_min); snd_iprintf(buffer, "start_threshold: %lu\n", runtime->start_threshold); snd_iprintf(buffer, "stop_threshold: %lu\n", runtime->stop_threshold); snd_iprintf(buffer, "silence_threshold: %lu\n", runtime->silence_threshold); snd_iprintf(buffer, "silence_size: %lu\n", runtime->silence_size); snd_iprintf(buffer, "boundary: %lu\n", runtime->boundary); } static void snd_pcm_substream_proc_status_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; struct snd_pcm_status64 status; int err; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } memset(&status, 0, sizeof(status)); err = snd_pcm_status64(substream, &status); if (err < 0) { snd_iprintf(buffer, "error %d\n", err); return; } snd_iprintf(buffer, "state: %s\n", snd_pcm_state_name(status.state)); snd_iprintf(buffer, "owner_pid : %d\n", pid_vnr(substream->pid)); snd_iprintf(buffer, "trigger_time: %lld.%09lld\n", status.trigger_tstamp_sec, status.trigger_tstamp_nsec); snd_iprintf(buffer, "tstamp : %lld.%09lld\n", status.tstamp_sec, status.tstamp_nsec); snd_iprintf(buffer, "delay : %ld\n", status.delay); snd_iprintf(buffer, "avail : %ld\n", status.avail); snd_iprintf(buffer, "avail_max : %ld\n", status.avail_max); snd_iprintf(buffer, "-----\n"); snd_iprintf(buffer, "hw_ptr : %ld\n", runtime->status->hw_ptr); snd_iprintf(buffer, "appl_ptr : %ld\n", runtime->control->appl_ptr); #ifdef CONFIG_SND_PCM_XRUN_DEBUG snd_iprintf(buffer, "xrun_counter: %d\n", substream->xrun_counter); #endif } #ifdef CONFIG_SND_PCM_XRUN_DEBUG static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; snd_pcm_stop_xrun(substream); } static void snd_pcm_xrun_debug_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_str *pstr = entry->private_data; snd_iprintf(buffer, "%d\n", pstr->xrun_debug); } static void snd_pcm_xrun_debug_write(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_str *pstr = entry->private_data; char line[64]; if (!snd_info_get_line(buffer, line, sizeof(line))) pstr->xrun_debug = simple_strtoul(line, NULL, 10); } #endif static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) { struct snd_pcm *pcm = pstr->pcm; struct snd_info_entry *entry; char name[16]; sprintf(name, "pcm%i%c", pcm->device, pstr->stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c'); entry = snd_info_create_card_entry(pcm->card, name, pcm->card->proc_root); if (!entry) return -ENOMEM; entry->mode = S_IFDIR | 0555; pstr->proc_root = entry; entry = snd_info_create_card_entry(pcm->card, "info", pstr->proc_root); if (entry) snd_info_set_text_ops(entry, pstr, snd_pcm_stream_proc_info_read); #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = snd_info_create_card_entry(pcm->card, "xrun_debug", pstr->proc_root); if (entry) { snd_info_set_text_ops(entry, pstr, snd_pcm_xrun_debug_read); entry->c.text.write = snd_pcm_xrun_debug_write; entry->mode |= 0200; } #endif return 0; } static int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { snd_info_free_entry(pstr->proc_root); pstr->proc_root = NULL; return 0; } static struct snd_info_entry * create_substream_info_entry(struct snd_pcm_substream *substream, const char *name, void (*read)(struct snd_info_entry *, struct snd_info_buffer *)) { struct snd_info_entry *entry; entry = snd_info_create_card_entry(substream->pcm->card, name, substream->proc_root); if (entry) snd_info_set_text_ops(entry, substream, read); return entry; } static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) { struct snd_info_entry *entry; struct snd_card *card; char name[16]; card = substream->pcm->card; sprintf(name, "sub%i", substream->number); entry = snd_info_create_card_entry(card, name, substream->pstr->proc_root); if (!entry) return -ENOMEM; entry->mode = S_IFDIR | 0555; substream->proc_root = entry; create_substream_info_entry(substream, "info", snd_pcm_substream_proc_info_read); create_substream_info_entry(substream, "hw_params", snd_pcm_substream_proc_hw_params_read); create_substream_info_entry(substream, "sw_params", snd_pcm_substream_proc_sw_params_read); create_substream_info_entry(substream, "status", snd_pcm_substream_proc_status_read); #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = create_substream_info_entry(substream, "xrun_injection", NULL); if (entry) { entry->c.text.write = snd_pcm_xrun_injection_write; entry->mode = S_IFREG | 0200; } #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ return 0; } #else /* !CONFIG_SND_VERBOSE_PROCFS */ static inline int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) { return 0; } #endif /* CONFIG_SND_VERBOSE_PROCFS */ static const struct attribute_group *pcm_dev_attr_groups[]; /* * PM callbacks: we need to deal only with suspend here, as the resume is * triggered either from user-space or the driver's resume callback */ static int do_pcm_suspend(struct device *dev) { struct snd_pcm_str *pstr = dev_get_drvdata(dev); if (!pstr->pcm->no_device_suspend) snd_pcm_suspend_all(pstr->pcm); return 0; } static const struct dev_pm_ops pcm_dev_pm_ops = { SYSTEM_SLEEP_PM_OPS(do_pcm_suspend, NULL) }; /* device type for PCM -- basically only for passing PM callbacks */ static const struct device_type pcm_dev_type = { .name = "pcm", .pm = &pcm_dev_pm_ops, }; /** * snd_pcm_new_stream - create a new PCM stream * @pcm: the pcm instance * @stream: the stream direction, SNDRV_PCM_STREAM_XXX * @substream_count: the number of substreams * * Creates a new stream for the pcm. * The corresponding stream on the pcm must have been empty before * calling this, i.e. zero must be given to the argument of * snd_pcm_new(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count) { int idx, err; struct snd_pcm_str *pstr = &pcm->streams[stream]; struct snd_pcm_substream *substream, *prev; #if IS_ENABLED(CONFIG_SND_PCM_OSS) mutex_init(&pstr->oss.setup_mutex); #endif pstr->stream = stream; pstr->pcm = pcm; pstr->substream_count = substream_count; if (!substream_count) return 0; err = snd_device_alloc(&pstr->dev, pcm->card); if (err < 0) return err; dev_set_name(pstr->dev, "pcmC%iD%i%c", pcm->card->number, pcm->device, stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c'); pstr->dev->groups = pcm_dev_attr_groups; pstr->dev->type = &pcm_dev_type; dev_set_drvdata(pstr->dev, pstr); if (!pcm->internal) { err = snd_pcm_stream_proc_init(pstr); if (err < 0) { pcm_err(pcm, "Error in snd_pcm_stream_proc_init\n"); return err; } } prev = NULL; for (idx = 0, prev = NULL; idx < substream_count; idx++) { substream = kzalloc(sizeof(*substream), GFP_KERNEL); if (!substream) return -ENOMEM; substream->pcm = pcm; substream->pstr = pstr; substream->number = idx; substream->stream = stream; sprintf(substream->name, "subdevice #%i", idx); substream->buffer_bytes_max = UINT_MAX; if (prev == NULL) pstr->substream = substream; else prev->next = substream; if (!pcm->internal) { err = snd_pcm_substream_proc_init(substream); if (err < 0) { pcm_err(pcm, "Error in snd_pcm_stream_proc_init\n"); if (prev == NULL) pstr->substream = NULL; else prev->next = NULL; kfree(substream); return err; } } substream->group = &substream->self_group; snd_pcm_group_init(&substream->self_group); list_add_tail(&substream->link_list, &substream->self_group.substreams); atomic_set(&substream->mmap_count, 0); prev = substream; } return 0; } EXPORT_SYMBOL(snd_pcm_new_stream); static int _snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, bool internal, struct snd_pcm **rpcm) { struct snd_pcm *pcm; int err; static const struct snd_device_ops ops = { .dev_free = snd_pcm_dev_free, .dev_register = snd_pcm_dev_register, .dev_disconnect = snd_pcm_dev_disconnect, }; static const struct snd_device_ops internal_ops = { .dev_free = snd_pcm_dev_free, }; if (snd_BUG_ON(!card)) return -ENXIO; if (rpcm) *rpcm = NULL; pcm = kzalloc(sizeof(*pcm), GFP_KERNEL); if (!pcm) return -ENOMEM; pcm->card = card; pcm->device = device; pcm->internal = internal; mutex_init(&pcm->open_mutex); init_waitqueue_head(&pcm->open_wait); INIT_LIST_HEAD(&pcm->list); if (id) strscpy(pcm->id, id, sizeof(pcm->id)); err = snd_pcm_new_stream(pcm, SNDRV_PCM_STREAM_PLAYBACK, playback_count); if (err < 0) goto free_pcm; err = snd_pcm_new_stream(pcm, SNDRV_PCM_STREAM_CAPTURE, capture_count); if (err < 0) goto free_pcm; err = snd_device_new(card, SNDRV_DEV_PCM, pcm, internal ? &internal_ops : &ops); if (err < 0) goto free_pcm; if (rpcm) *rpcm = pcm; return 0; free_pcm: snd_pcm_free(pcm); return err; } /** * snd_pcm_new - create a new PCM instance * @card: the card instance * @id: the id string * @device: the device index (zero based) * @playback_count: the number of substreams for playback * @capture_count: the number of substreams for capture * @rpcm: the pointer to store the new pcm instance * * Creates a new PCM instance. * * The pcm operators have to be set afterwards to the new instance * via snd_pcm_set_ops(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm) { return _snd_pcm_new(card, id, device, playback_count, capture_count, false, rpcm); } EXPORT_SYMBOL(snd_pcm_new); /** * snd_pcm_new_internal - create a new internal PCM instance * @card: the card instance * @id: the id string * @device: the device index (zero based - shared with normal PCMs) * @playback_count: the number of substreams for playback * @capture_count: the number of substreams for capture * @rpcm: the pointer to store the new pcm instance * * Creates a new internal PCM instance with no userspace device or procfs * entries. This is used by ASoC Back End PCMs in order to create a PCM that * will only be used internally by kernel drivers. i.e. it cannot be opened * by userspace. It provides existing ASoC components drivers with a substream * and access to any private data. * * The pcm operators have to be set afterwards to the new instance * via snd_pcm_set_ops(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new_internal(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm) { return _snd_pcm_new(card, id, device, playback_count, capture_count, true, rpcm); } EXPORT_SYMBOL(snd_pcm_new_internal); static void free_chmap(struct snd_pcm_str *pstr) { if (pstr->chmap_kctl) { struct snd_card *card = pstr->pcm->card; snd_ctl_remove(card, pstr->chmap_kctl); pstr->chmap_kctl = NULL; } } static void snd_pcm_free_stream(struct snd_pcm_str * pstr) { struct snd_pcm_substream *substream, *substream_next; #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss_setup *setup, *setupn; #endif /* free all proc files under the stream */ snd_pcm_stream_proc_done(pstr); substream = pstr->substream; while (substream) { substream_next = substream->next; snd_pcm_timer_done(substream); kfree(substream); substream = substream_next; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) for (setup = pstr->oss.setup_list; setup; setup = setupn) { setupn = setup->next; kfree(setup->task_name); kfree(setup); } #endif free_chmap(pstr); if (pstr->substream_count) put_device(pstr->dev); } #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define pcm_call_notify(pcm, call) \ do { \ struct snd_pcm_notify *_notify; \ list_for_each_entry(_notify, &snd_pcm_notify_list, list) \ _notify->call(pcm); \ } while (0) #else #define pcm_call_notify(pcm, call) do {} while (0) #endif static int snd_pcm_free(struct snd_pcm *pcm) { if (!pcm) return 0; if (!pcm->internal) pcm_call_notify(pcm, n_unregister); if (pcm->private_free) pcm->private_free(pcm); snd_pcm_lib_preallocate_free_for_all(pcm); snd_pcm_free_stream(&pcm->streams[SNDRV_PCM_STREAM_PLAYBACK]); snd_pcm_free_stream(&pcm->streams[SNDRV_PCM_STREAM_CAPTURE]); kfree(pcm); return 0; } static int snd_pcm_dev_free(struct snd_device *device) { struct snd_pcm *pcm = device->device_data; return snd_pcm_free(pcm); } int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream) { struct snd_pcm_str * pstr; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; struct snd_card *card; int prefer_subdevice; size_t size; if (snd_BUG_ON(!pcm || !rsubstream)) return -ENXIO; if (snd_BUG_ON(stream != SNDRV_PCM_STREAM_PLAYBACK && stream != SNDRV_PCM_STREAM_CAPTURE)) return -EINVAL; *rsubstream = NULL; pstr = &pcm->streams[stream]; if (pstr->substream == NULL || pstr->substream_count == 0) return -ENODEV; card = pcm->card; prefer_subdevice = snd_ctl_get_preferred_subdevice(card, SND_CTL_SUBDEV_PCM); if (pcm->info_flags & SNDRV_PCM_INFO_HALF_DUPLEX) { int opposite = !stream; for (substream = pcm->streams[opposite].substream; substream; substream = substream->next) { if (SUBSTREAM_BUSY(substream)) return -EAGAIN; } } if (file->f_flags & O_APPEND) { if (prefer_subdevice < 0) { if (pstr->substream_count > 1) return -EINVAL; /* must be unique */ substream = pstr->substream; } else { for (substream = pstr->substream; substream; substream = substream->next) if (substream->number == prefer_subdevice) break; } if (! substream) return -ENODEV; if (! SUBSTREAM_BUSY(substream)) return -EBADFD; substream->ref_count++; *rsubstream = substream; return 0; } for (substream = pstr->substream; substream; substream = substream->next) { if (!SUBSTREAM_BUSY(substream) && (prefer_subdevice == -1 || substream->number == prefer_subdevice)) break; } if (substream == NULL) return -EAGAIN; runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); if (runtime == NULL) return -ENOMEM; size = PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status)); runtime->status = alloc_pages_exact(size, GFP_KERNEL); if (runtime->status == NULL) { kfree(runtime); return -ENOMEM; } memset(runtime->status, 0, size); size = PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control)); runtime->control = alloc_pages_exact(size, GFP_KERNEL); if (runtime->control == NULL) { free_pages_exact(runtime->status, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status))); kfree(runtime); return -ENOMEM; } memset(runtime->control, 0, size); init_waitqueue_head(&runtime->sleep); init_waitqueue_head(&runtime->tsleep); __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_OPEN); mutex_init(&runtime->buffer_mutex); atomic_set(&runtime->buffer_accessing, 0); substream->runtime = runtime; substream->private_data = pcm->private_data; substream->ref_count = 1; substream->f_flags = file->f_flags; substream->pid = get_pid(task_pid(current)); pstr->substream_opened++; *rsubstream = substream; #ifdef CONFIG_SND_PCM_XRUN_DEBUG substream->xrun_counter = 0; #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ return 0; } void snd_pcm_detach_substream(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime; if (PCM_RUNTIME_CHECK(substream)) return; runtime = substream->runtime; if (runtime->private_free != NULL) runtime->private_free(runtime); free_pages_exact(runtime->status, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status))); free_pages_exact(runtime->control, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control))); kfree(runtime->hw_constraints.rules); /* Avoid concurrent access to runtime via PCM timer interface */ if (substream->timer) { scoped_guard(spinlock_irq, &substream->timer->lock) substream->runtime = NULL; } else { substream->runtime = NULL; } mutex_destroy(&runtime->buffer_mutex); snd_fasync_free(runtime->fasync); kfree(runtime); put_pid(substream->pid); substream->pid = NULL; substream->pstr->substream_opened--; } static ssize_t pcm_class_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_pcm_str *pstr = dev_get_drvdata(dev); struct snd_pcm *pcm = pstr->pcm; const char *str; static const char *strs[SNDRV_PCM_CLASS_LAST + 1] = { [SNDRV_PCM_CLASS_GENERIC] = "generic", [SNDRV_PCM_CLASS_MULTI] = "multi", [SNDRV_PCM_CLASS_MODEM] = "modem", [SNDRV_PCM_CLASS_DIGITIZER] = "digitizer", }; if (pcm->dev_class > SNDRV_PCM_CLASS_LAST) str = "none"; else str = strs[pcm->dev_class]; return sysfs_emit(buf, "%s\n", str); } static DEVICE_ATTR_RO(pcm_class); static struct attribute *pcm_dev_attrs[] = { &dev_attr_pcm_class.attr, NULL }; static const struct attribute_group pcm_dev_attr_group = { .attrs = pcm_dev_attrs, }; static const struct attribute_group *pcm_dev_attr_groups[] = { &pcm_dev_attr_group, NULL }; static int snd_pcm_dev_register(struct snd_device *device) { int cidx, err; struct snd_pcm_substream *substream; struct snd_pcm *pcm; if (snd_BUG_ON(!device || !device->device_data)) return -ENXIO; pcm = device->device_data; guard(mutex)(®ister_mutex); err = snd_pcm_add(pcm); if (err) return err; for (cidx = 0; cidx < 2; cidx++) { int devtype = -1; if (pcm->streams[cidx].substream == NULL) continue; switch (cidx) { case SNDRV_PCM_STREAM_PLAYBACK: devtype = SNDRV_DEVICE_TYPE_PCM_PLAYBACK; break; case SNDRV_PCM_STREAM_CAPTURE: devtype = SNDRV_DEVICE_TYPE_PCM_CAPTURE; break; } /* register pcm */ err = snd_register_device(devtype, pcm->card, pcm->device, &snd_pcm_f_ops[cidx], pcm, pcm->streams[cidx].dev); if (err < 0) { list_del_init(&pcm->list); return err; } for (substream = pcm->streams[cidx].substream; substream; substream = substream->next) snd_pcm_timer_init(substream); } pcm_call_notify(pcm, n_register); return err; } static int snd_pcm_dev_disconnect(struct snd_device *device) { struct snd_pcm *pcm = device->device_data; struct snd_pcm_substream *substream; int cidx; guard(mutex)(®ister_mutex); guard(mutex)(&pcm->open_mutex); wake_up(&pcm->open_wait); list_del_init(&pcm->list); for_each_pcm_substream(pcm, cidx, substream) { snd_pcm_stream_lock_irq(substream); if (substream->runtime) { if (snd_pcm_running(substream)) snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED); /* to be sure, set the state unconditionally */ __snd_pcm_set_state(substream->runtime, SNDRV_PCM_STATE_DISCONNECTED); wake_up(&substream->runtime->sleep); wake_up(&substream->runtime->tsleep); } snd_pcm_stream_unlock_irq(substream); } for_each_pcm_substream(pcm, cidx, substream) snd_pcm_sync_stop(substream, false); pcm_call_notify(pcm, n_disconnect); for (cidx = 0; cidx < 2; cidx++) { if (pcm->streams[cidx].dev) snd_unregister_device(pcm->streams[cidx].dev); free_chmap(&pcm->streams[cidx]); } return 0; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) /** * snd_pcm_notify - Add/remove the notify list * @notify: PCM notify list * @nfree: 0 = register, 1 = unregister * * This adds the given notifier to the global list so that the callback is * called for each registered PCM devices. This exists only for PCM OSS * emulation, so far. * * Return: zero if successful, or a negative error code */ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree) { struct snd_pcm *pcm; if (snd_BUG_ON(!notify || !notify->n_register || !notify->n_unregister || !notify->n_disconnect)) return -EINVAL; guard(mutex)(®ister_mutex); if (nfree) { list_del(¬ify->list); list_for_each_entry(pcm, &snd_pcm_devices, list) notify->n_unregister(pcm); } else { list_add_tail(¬ify->list, &snd_pcm_notify_list); list_for_each_entry(pcm, &snd_pcm_devices, list) notify->n_register(pcm); } return 0; } EXPORT_SYMBOL(snd_pcm_notify); #endif /* CONFIG_SND_PCM_OSS */ #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_pcm_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm *pcm; guard(mutex)(®ister_mutex); list_for_each_entry(pcm, &snd_pcm_devices, list) { snd_iprintf(buffer, "%02i-%02i: %s : %s", pcm->card->number, pcm->device, pcm->id, pcm->name); if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) snd_iprintf(buffer, " : playback %i", pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream_count); if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) snd_iprintf(buffer, " : capture %i", pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream_count); snd_iprintf(buffer, "\n"); } } static struct snd_info_entry *snd_pcm_proc_entry; static void snd_pcm_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "pcm", NULL); if (entry) { snd_info_set_text_ops(entry, NULL, snd_pcm_proc_read); if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_pcm_proc_entry = entry; } static void snd_pcm_proc_done(void) { snd_info_free_entry(snd_pcm_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_pcm_proc_init() #define snd_pcm_proc_done() #endif /* CONFIG_SND_PROC_FS */ /* * ENTRY functions */ static int __init alsa_pcm_init(void) { snd_ctl_register_ioctl(snd_pcm_control_ioctl); snd_ctl_register_ioctl_compat(snd_pcm_control_ioctl); snd_pcm_proc_init(); return 0; } static void __exit alsa_pcm_exit(void) { snd_ctl_unregister_ioctl(snd_pcm_control_ioctl); snd_ctl_unregister_ioctl_compat(snd_pcm_control_ioctl); snd_pcm_proc_done(); } module_init(alsa_pcm_init) module_exit(alsa_pcm_exit) |
| 6 10 2 5 153 169 15 13 3 13 168 12 5 5 10 10 7 7 157 7 6 6 4 7 3 2 1 5 2 4 3 159 6 1 1 1 4 1 3 4 2 171 3 3 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) { switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: return protocol == cpu_to_be16(ETH_P_IP); case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: return false; } } static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { if (skb->protocol) return 0; switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: skb->protocol = cpu_to_be16(ETH_P_IPV6); break; default: return -EINVAL; } return 0; } static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; case VIRTIO_NET_HDR_GSO_UDP_L4: gso_type = SKB_GSO_UDP_L4; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; default: return -EINVAL; } if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) gso_type |= SKB_GSO_TCP_ECN; if (hdr->gso_size == 0) return -EINVAL; } skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); if (!pskb_may_pull(skb, needed)) return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; if (skb_transport_offset(skb) < nh_min_len) return -EINVAL; nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { struct flow_keys_basic keys; if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); if (!protocol) virtio_net_hdr_set_proto(skb, hdr); else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; else skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { skb->protocol = htons(ETH_P_IPV6); goto retry; } return -EINVAL; } p_off = keys.control.thoff + thlen; if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); switch (gso_type & ~SKB_GSO_TCP_ECN) { case SKB_GSO_UDP: /* UFO may not include transport header in gso_size. */ nh_off -= thlen; break; case SKB_GSO_UDP_L4: if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; if (skb->csum_offset != offsetof(struct udphdr, check)) return -EINVAL; if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) return -EINVAL; if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; case SKB_GSO_TCPV4: case SKB_GSO_TCPV6: if (skb->ip_summed == CHECKSUM_PARTIAL && skb->csum_offset != offsetof(struct tcphdr, check)) return -EINVAL; break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) return -EINVAL; /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } } return 0; } static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, bool has_data_valid, int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); /* This is a hint as to how much should be linear. */ hdr->hdr_len = __cpu_to_virtio16(little_endian, skb_headlen(skb)); hdr->gso_size = __cpu_to_virtio16(little_endian, sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (sinfo->gso_type & SKB_GSO_UDP_L4) hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; hdr->csum_start = __cpu_to_virtio16(little_endian, skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; } #endif /* _LINUX_VIRTIO_NET_H */ |
| 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/nfs_fs.h * * Copyright (C) 1992 Rick Sladkey * * OS-specific nfs filesystem definitions and declarations */ #ifndef _LINUX_NFS_FS_H #define _LINUX_NFS_FS_H #include <uapi/linux/nfs_fs.h> /* * Enable dprintk() debugging support for nfs client. */ #ifdef CONFIG_NFS_DEBUG # define NFS_DEBUG #endif #include <linux/in.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/rwsem.h> #include <linux/wait.h> #include <linux/sunrpc/debug.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/clnt.h> #ifdef CONFIG_NFS_FSCACHE #include <linux/netfs.h> #endif #include <linux/nfs.h> #include <linux/nfs2.h> #include <linux/nfs3.h> #include <linux/nfs4.h> #include <linux/nfs_xdr.h> #include <linux/nfs_fs_sb.h> #include <linux/mempool.h> /* * These are the default for number of transports to different server IPs */ #define NFS_MAX_TRANSPORTS 16 /* * Size of the NFS directory verifier */ #define NFS_DIR_VERIFIER_SIZE 2 /* * NFSv3/v4 Access mode cache entry */ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; kuid_t fsuid; kgid_t fsgid; struct group_info *group_info; u64 timestamp; __u32 mask; struct rcu_head rcu_head; }; struct nfs_lock_context { refcount_t count; struct list_head list; struct nfs_open_context *open_context; fl_owner_t lockowner; atomic_t io_count; struct rcu_head rcu_head; }; struct nfs_file_localio { struct nfsd_file __rcu *ro_file; struct nfsd_file __rcu *rw_file; struct list_head list; void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */ }; static inline void nfs_localio_file_init(struct nfs_file_localio *nfl) { #if IS_ENABLED(CONFIG_NFS_LOCALIO) nfl->ro_file = NULL; nfl->rw_file = NULL; INIT_LIST_HEAD(&nfl->list); nfl->nfs_uuid = NULL; #endif } struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; int error; unsigned long flags; #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) struct nfs4_threshold *mdsthreshold; struct list_head list; struct rcu_head rcu_head; struct nfs_file_localio nfl; }; struct nfs_open_dir_context { struct list_head list; atomic_t cache_hits; atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; bool force_clear; bool eof; struct rcu_head rcu_head; }; /* * NFSv4 delegation */ struct nfs_delegation; struct posix_acl; struct nfs4_xattr_cache; /* * nfs fs inode data in memory */ struct nfs_inode { /* * The 64bit 'inode number' */ __u64 fileid; /* * NFS file handle */ struct nfs_fh fh; /* * Various flags */ unsigned long flags; /* atomic bit ops */ unsigned long cache_validity; /* bit mask */ /* * read_cache_jiffies is when we started read-caching this inode. * attrtimeo is for how long the cached information is assumed * to be valid. A successful attribute revalidation doubles * attrtimeo (up to acregmax/acdirmax), a failure resets it to * acregmin/acdirmin. * * We need to revalidate the cached attrs for this inode if * * jiffies - read_cache_jiffies >= attrtimeo * * Please note the comparison is greater than or equal * so that zero timeout values can be specified. */ unsigned long read_cache_jiffies; unsigned long attrtimeo; unsigned long attrtimeo_timestamp; unsigned long attr_gencount; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; union { /* Directory */ struct { /* "Generation counter" for the attribute cache. * This is bumped whenever we update the metadata * on the server. */ unsigned long cache_change_attribute; /* * This is the cookie verifier used for NFSv3 readdir * operations */ __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; /* Readers: in-flight sillydelete RPC calls */ /* Writers: rmdir */ struct rw_semaphore rmdir_sem; }; /* Regular file */ struct { atomic_long_t nrequests; atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; }; }; /* Open contexts for shared mmap writes */ struct list_head open_files; /* Keep track of out-of-order replies. * The ooo array contains start/end pairs of * numbers from the changeid sequence when * the inode's iversion has been updated. * It also contains end/start pair (i.e. reverse order) * of sections of the changeid sequence that have * been seen in replies from the server. * Normally these should match and when both * A:B and B:A are found in ooo, they are both removed. * And if a reply with A:B causes an iversion update * of A:B, then neither are added. * When a reply has pre_change that doesn't match * iversion, then the changeid pair and any consequent * change in iversion ARE added. Later replies * might fill in the gaps, or possibly a gap is caused * by a change from another client. * When a file or directory is opened, if the ooo table * is not empty, then we assume the gaps were due to * another client and we invalidate the cached data. * * We can only track a limited number of concurrent gaps. * Currently that limit is 16. * We allocate the table on demand. If there is insufficient * memory, then we probably cannot cache the file anyway * so there is no loss. */ struct { int cnt; struct { u64 start, end; } gap[16]; } *ooo; #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ struct list_head open_states; struct nfs_delegation __rcu *delegation; struct rw_semaphore rwsem; /* pNFS layout information */ struct pnfs_layout_hdr *layout; #endif /* CONFIG_NFS_V4*/ /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif union { struct inode vfs_inode; #ifdef CONFIG_NFS_FSCACHE struct netfs_inode netfs; /* netfs context and VFS inode */ #endif }; }; struct nfs4_copy_state { struct list_head copies; struct list_head src_copies; nfs4_stateid stateid; struct completion completion; uint64_t count; struct nfs_writeverf verf; int error; int flags; struct nfs4_state *parent_src_state; struct nfs4_state *parent_dst_state; }; /* * Access bit flags */ #define NFS_ACCESS_READ 0x0001 #define NFS_ACCESS_LOOKUP 0x0002 #define NFS_ACCESS_MODIFY 0x0004 #define NFS_ACCESS_EXTEND 0x0008 #define NFS_ACCESS_DELETE 0x0010 #define NFS_ACCESS_EXECUTE 0x0020 #define NFS_ACCESS_XAREAD 0x0040 #define NFS_ACCESS_XAWRITE 0x0080 #define NFS_ACCESS_XALIST 0x0100 /* * Cache validity bit flags */ #define NFS_INO_INVALID_DATA BIT(1) /* cached data is invalid */ #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ #define NFS_INO_INVALID_CTIME BIT(9) /* cached ctime is invalid */ #define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ #define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ #define NFS_INO_DATA_INVAL_DEFER \ BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ #define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */ #define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ | NFS_INO_INVALID_MTIME \ | NFS_INO_INVALID_SIZE \ | NFS_INO_INVALID_NLINK \ | NFS_INO_INVALID_MODE \ | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* * Bit offsets in flags field */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ #define NFS_INO_ODIRECT (12) /* I/O setting is O_DIRECT */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { return container_of(inode, struct nfs_inode, vfs_inode); } static inline struct nfs_server *NFS_SB(const struct super_block *s) { return (struct nfs_server *)(s->s_fs_info); } static inline struct nfs_fh *NFS_FH(const struct inode *inode) { return &NFS_I(inode)->fh; } static inline struct nfs_server *NFS_SERVER(const struct inode *inode) { return NFS_SB(inode->i_sb); } static inline struct rpc_clnt *NFS_CLIENT(const struct inode *inode) { return NFS_SERVER(inode)->client; } static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode) { return NFS_SERVER(inode)->nfs_client->rpc_ops; } static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); return S_ISDIR(inode->i_mode) ? nfss->acdirmin : nfss->acregmin; } static inline unsigned NFS_MAXATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); return S_ISDIR(inode->i_mode) ? nfss->acdirmax : nfss->acregmax; } static inline int NFS_STALE(const struct inode *inode) { return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; } static inline void set_nfs_fileid(struct inode *inode, __u64 fileid) { NFS_I(inode)->fileid = fileid; } static inline void nfs_mark_for_revalidate(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } /** * nfs_save_change_attribute - Returns the inode attribute change cookie * @dir - pointer to parent directory inode * The "cache change attribute" is updated when we need to revalidate * our dentry cache after a directory was seen to change on the server. */ static inline unsigned long nfs_save_change_attribute(struct inode *dir) { return NFS_I(dir)->cache_change_attribute; } /* * linux/fs/nfs/inode.c */ extern int nfs_sync_mapping(struct address_space *mapping); extern void nfs_zap_mapping(struct inode *inode, struct address_space *mapping); extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct mnt_idmap *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp); extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); extern void nfs_file_clear_open_context(struct file *flip); extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx); extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); extern u64 nfs_compat_user_ino64(u64 fileid); extern void nfs_fattr_init(struct nfs_fattr *fattr); extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); static inline void nfs4_label_free(struct nfs4_label *label) { #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (label) { kfree(label->label); kfree(label); } #endif } static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { if (fattr) nfs4_label_free(fattr->label); kfree(fattr); } extern struct nfs_fh *nfs_alloc_fhandle(void); static inline void nfs_free_fhandle(const struct nfs_fh *fh) { kfree(fh); } #ifdef NFS_DEBUG extern u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh); static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh) { return _nfs_display_fhandle_hash(fh); } extern void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption); #define nfs_display_fhandle(fh, caption) \ do { \ if (unlikely(nfs_debug & NFSDBG_FACILITY)) \ _nfs_display_fhandle(fh, caption); \ } while (0) #else static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh) { return 0; } static inline void nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { } #endif /* * linux/fs/nfs/nfsroot.c */ extern int nfs_root_data(char **root_device, char **root_data); /*__init*/ /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern __be32 root_nfs_parse_addr(char *name); /*__init*/ /* * linux/fs/nfs/file.c */ extern const struct file_operations nfs_file_operations; #if IS_ENABLED(CONFIG_NFS_V4) extern const struct file_operations nfs4_file_operations; #endif /* CONFIG_NFS_V4 */ extern const struct address_space_operations nfs_file_aops; extern const struct address_space_operations nfs_dir_aops; static inline struct nfs_open_context *nfs_file_open_context(struct file *filp) { return filp->private_data; } static inline const struct cred *nfs_file_cred(struct file *file) { if (file != NULL) { struct nfs_open_context *ctx = nfs_file_open_context(file); if (ctx) return ctx->cred; } return NULL; } /* * linux/fs/nfs/direct.c */ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c */ extern const struct file_operations nfs_dir_operations; extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); #if IS_ENABLED(CONFIG_NFS_V4) extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block); extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, struct file *file, unsigned int open_flags, umode_t mode); /* * linux/fs/nfs/symlink.c */ extern const struct inode_operations nfs_symlink_inode_operations; /* * linux/fs/nfs/sysctl.c */ #ifdef CONFIG_SYSCTL extern int nfs_register_sysctl(void); extern void nfs_unregister_sysctl(void); #else #define nfs_register_sysctl() 0 #define nfs_unregister_sysctl() do { } while(0) #endif /* * linux/fs/nfs/namespace.c */ extern const struct inode_operations nfs_mountpoint_inode_operations; extern const struct inode_operations nfs_referral_inode_operations; extern int nfs_mountpoint_expiry_timeout; extern void nfs_release_automount_timer(void); /* * linux/fs/nfs/unlink.c */ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); /* * linux/fs/nfs/write.c */ extern int nfs_congestion_kb; extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct folio *folio); extern int nfs_update_folio(struct file *file, struct folio *folio, unsigned int offset, unsigned int count); /* * Try to write back everything synchronously (but check the * return value!) */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; return false; } /* * linux/fs/nfs/read.c */ int nfs_read_folio(struct file *, struct folio *); void nfs_readahead(struct readahead_control *); /* * inline functions */ static inline loff_t nfs_size_to_loff_t(__u64 size) { return min_t(u64, size, OFFSET_MAX); } static inline ino_t nfs_fileid_to_ino_t(u64 fileid) { ino_t ino = (ino_t) fileid; if (sizeof(ino_t) < sizeof(u64)) ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8; return ino; } static inline void nfs_ooo_clear(struct nfs_inode *nfsi) { nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; kfree(nfsi->ooo); nfsi->ooo = NULL; } static inline bool nfs_ooo_test(struct nfs_inode *nfsi) { return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || (nfsi->ooo && nfsi->ooo->cnt > 0); } #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. * If it is opened *before* we decide to unlink, we will silly-rename * instead. If it is opened *after*, then we need to create or will fail. * If we allow the two to race, we could end up with a file that is open * but deleted on the server resulting in ESTALE. * So use ->d_fsdata to record when the unlink is happening * and block dentry revalidation while it is set. */ #define NFS_FSDATA_BLOCKED ((void*)1) # undef ifdebug # ifdef NFS_DEBUG # define ifdebug(fac) if (unlikely(nfs_debug & NFSDBG_##fac)) # define NFS_IFDEBUG(x) x # else # define ifdebug(fac) if (0) # define NFS_IFDEBUG(x) # endif #endif |
| 238 16 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (c) 2001-2002 by David Brownell */ #ifndef __USB_CORE_HCD_H #define __USB_CORE_HCD_H #ifdef __KERNEL__ #include <linux/rwsem.h> #include <linux/interrupt.h> #include <linux/idr.h> #define MAX_TOPO_LEVEL 6 /* This file contains declarations of usbcore internals that are mostly * used or exposed by Host Controller Drivers. */ /* * USB Packet IDs (PIDs) */ #define USB_PID_EXT 0xf0 /* USB 2.0 LPM ECN */ #define USB_PID_OUT 0xe1 #define USB_PID_ACK 0xd2 #define USB_PID_DATA0 0xc3 #define USB_PID_PING 0xb4 /* USB 2.0 */ #define USB_PID_SOF 0xa5 #define USB_PID_NYET 0x96 /* USB 2.0 */ #define USB_PID_DATA2 0x87 /* USB 2.0 */ #define USB_PID_SPLIT 0x78 /* USB 2.0 */ #define USB_PID_IN 0x69 #define USB_PID_NAK 0x5a #define USB_PID_DATA1 0x4b #define USB_PID_PREAMBLE 0x3c /* Token mode */ #define USB_PID_ERR 0x3c /* USB 2.0: handshake mode */ #define USB_PID_SETUP 0x2d #define USB_PID_STALL 0x1e #define USB_PID_MDATA 0x0f /* USB 2.0 */ /*-------------------------------------------------------------------------*/ /* * USB Host Controller Driver (usb_hcd) framework * * Since "struct usb_bus" is so thin, you can't share much code in it. * This framework is a layer over that, and should be more shareable. */ /*-------------------------------------------------------------------------*/ struct giveback_urb_bh { bool running; bool high_prio; spinlock_t lock; struct list_head head; struct work_struct bh; struct usb_host_endpoint *completing_ep; }; enum usb_dev_authorize_policy { USB_DEVICE_AUTHORIZE_NONE = 0, USB_DEVICE_AUTHORIZE_ALL = 1, USB_DEVICE_AUTHORIZE_INTERNAL = 2, }; struct usb_hcd { /* * housekeeping */ struct usb_bus self; /* hcd is-a bus */ struct kref kref; /* reference counter */ const char *product_desc; /* product/vendor string */ int speed; /* Speed for this roothub. * May be different from * hcd->driver->flags & HCD_MASK */ char irq_descr[24]; /* driver + bus # */ struct timer_list rh_timer; /* drives root-hub polling */ struct urb *status_urb; /* the current status urb */ #ifdef CONFIG_PM struct work_struct wakeup_work; /* for remote wakeup */ #endif struct work_struct died_work; /* for when the device dies */ /* * hardware info/state */ const struct hc_driver *driver; /* hw-specific hooks */ /* * OTG and some Host controllers need software interaction with phys; * other external phys should be software-transparent */ struct usb_phy *usb_phy; struct usb_phy_roothub *phy_roothub; /* Flags that need to be manipulated atomically because they can * change while the host controller is running. Always use * set_bit() or clear_bit() to change their values. */ unsigned long flags; #define HCD_FLAG_HW_ACCESSIBLE 0 /* at full power */ #define HCD_FLAG_POLL_RH 2 /* poll for rh status? */ #define HCD_FLAG_POLL_PENDING 3 /* status has changed? */ #define HCD_FLAG_WAKEUP_PENDING 4 /* root hub is resuming? */ #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ #define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). */ #define HCD_HW_ACCESSIBLE(hcd) ((hcd)->flags & (1U << HCD_FLAG_HW_ACCESSIBLE)) #define HCD_POLL_RH(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_RH)) #define HCD_POLL_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_PENDING)) #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) #define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default * or they require explicit user space authorization; this bit is * settable through /sys/class/usb_host/X/interface_authorized_default */ #define HCD_INTF_AUTHORIZED(hcd) \ ((hcd)->flags & (1U << HCD_FLAG_INTF_AUTHORIZED)) /* * Specifies if devices are authorized by default * or they require explicit user space authorization; this bit is * settable through /sys/class/usb_host/X/authorized_default */ enum usb_dev_authorize_policy dev_policy; /* Flags that get set only during HCD registration or removal. */ unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ unsigned msix_enabled:1; /* driver has MSI-X enabled? */ unsigned msi_enabled:1; /* driver has MSI enabled? */ /* * do not manage the PHY state in the HCD core, instead let the driver * handle this (for example if the PHY can only be turned on after a * specific event) */ unsigned skip_phy_initialization:1; /* The next flag is a stopgap, to be removed when all the HCDs * support the new root-hub polling mechanism. */ unsigned uses_new_polling:1; unsigned has_tt:1; /* Integrated TT in root hub */ unsigned amd_resume_bug:1; /* AMD remote wakeup quirk */ unsigned can_do_streams:1; /* HC supports streams */ unsigned tpl_support:1; /* OTG & EH TPL support */ unsigned cant_recv_wakeups:1; /* wakeup requests from downstream aren't received */ unsigned int irq; /* irq allocated */ void __iomem *regs; /* device memory/io */ resource_size_t rsrc_start; /* memory/io resource start */ resource_size_t rsrc_len; /* memory/io resource length */ unsigned power_budget; /* in mA, 0 = no limit */ struct giveback_urb_bh high_prio_bh; struct giveback_urb_bh low_prio_bh; /* bandwidth_mutex should be taken before adding or removing * any new bus bandwidth constraints: * 1. Before adding a configuration for a new device. * 2. Before removing the configuration to put the device into * the addressed state. * 3. Before selecting a different configuration. * 4. Before selecting an alternate interface setting. * * bandwidth_mutex should be dropped after a successful control message * to the device, or resetting the bandwidth after a failed attempt. */ struct mutex *address0_mutex; struct mutex *bandwidth_mutex; struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; #define HCD_BUFFER_POOLS 4 struct dma_pool *pool[HCD_BUFFER_POOLS]; int state; # define __ACTIVE 0x01 # define __SUSPEND 0x04 # define __TRANSIENT 0x80 # define HC_STATE_HALT 0 # define HC_STATE_RUNNING (__ACTIVE) # define HC_STATE_QUIESCING (__SUSPEND|__TRANSIENT|__ACTIVE) # define HC_STATE_RESUMING (__SUSPEND|__TRANSIENT) # define HC_STATE_SUSPENDED (__SUSPEND) #define HC_IS_RUNNING(state) ((state) & __ACTIVE) #define HC_IS_SUSPENDED(state) ((state) & __SUSPEND) /* memory pool for HCs having local memory, or %NULL */ struct gen_pool *localmem_pool; /* more shared queuing code would be good; it should support * smarter scheduling, handle transaction translators, etc; * input size of periodic table to an interrupt scheduler. * (ohci 32, uhci 1024, ehci 256/512/1024). */ /* The HC driver's private data is stored at the end of * this structure. */ unsigned long hcd_priv[] __attribute__ ((aligned(sizeof(s64)))); }; /* 2.4 does this a bit differently ... */ static inline struct usb_bus *hcd_to_bus(struct usb_hcd *hcd) { return &hcd->self; } static inline struct usb_hcd *bus_to_hcd(struct usb_bus *bus) { return container_of(bus, struct usb_hcd, self); } /*-------------------------------------------------------------------------*/ struct hc_driver { const char *description; /* "ehci-hcd" etc */ const char *product_desc; /* product/vendor string */ size_t hcd_priv_size; /* size of private data */ /* irq handler */ irqreturn_t (*irq) (struct usb_hcd *hcd); int flags; #define HCD_MEMORY 0x0001 /* HC regs use memory (else I/O) */ #define HCD_DMA 0x0002 /* HC uses DMA */ #define HCD_SHARED 0x0004 /* Two (or more) usb_hcds share HW */ #define HCD_USB11 0x0010 /* USB 1.1 */ #define HCD_USB2 0x0020 /* USB 2.0 */ #define HCD_USB3 0x0040 /* USB 3.0 */ #define HCD_USB31 0x0050 /* USB 3.1 */ #define HCD_USB32 0x0060 /* USB 3.2 */ #define HCD_MASK 0x0070 #define HCD_BH 0x0100 /* URB complete in BH context */ /* called to init HCD and root hub */ int (*reset) (struct usb_hcd *hcd); int (*start) (struct usb_hcd *hcd); /* NOTE: these suspend/resume calls relate to the HC as * a whole, not just the root hub; they're for PCI bus glue. */ /* called after suspending the hub, before entering D3 etc */ int (*pci_suspend)(struct usb_hcd *hcd, bool do_wakeup); /* called after entering D0 (etc), before resuming the hub */ int (*pci_resume)(struct usb_hcd *hcd, pm_message_t state); /* called just before hibernate final D3 state, allows host to poweroff parts */ int (*pci_poweroff_late)(struct usb_hcd *hcd, bool do_wakeup); /* cleanly make HCD stop writing memory and doing I/O */ void (*stop) (struct usb_hcd *hcd); /* shutdown HCD */ void (*shutdown) (struct usb_hcd *hcd); /* return current frame number */ int (*get_frame_number) (struct usb_hcd *hcd); /* manage i/o requests, device state */ int (*urb_enqueue)(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags); int (*urb_dequeue)(struct usb_hcd *hcd, struct urb *urb, int status); /* * (optional) these hooks allow an HCD to override the default DMA * mapping and unmapping routines. In general, they shouldn't be * necessary unless the host controller has special DMA requirements, * such as alignment constraints. If these are not specified, the * general usb_hcd_(un)?map_urb_for_dma functions will be used instead * (and it may be a good idea to call these functions in your HCD * implementation) */ int (*map_urb_for_dma)(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags); void (*unmap_urb_for_dma)(struct usb_hcd *hcd, struct urb *urb); /* hw synch, freeing endpoint resources that urb_dequeue can't */ void (*endpoint_disable)(struct usb_hcd *hcd, struct usb_host_endpoint *ep); /* (optional) reset any endpoint state such as sequence number and current window */ void (*endpoint_reset)(struct usb_hcd *hcd, struct usb_host_endpoint *ep); /* root hub support */ int (*hub_status_data) (struct usb_hcd *hcd, char *buf); int (*hub_control) (struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex, char *buf, u16 wLength); int (*bus_suspend)(struct usb_hcd *); int (*bus_resume)(struct usb_hcd *); int (*start_port_reset)(struct usb_hcd *, unsigned port_num); unsigned long (*get_resuming_ports)(struct usb_hcd *); /* force handover of high-speed port to full-speed companion */ void (*relinquish_port)(struct usb_hcd *, int); /* has a port been handed over to a companion? */ int (*port_handed_over)(struct usb_hcd *, int); /* CLEAR_TT_BUFFER completion callback */ void (*clear_tt_buffer_complete)(struct usb_hcd *, struct usb_host_endpoint *); /* xHCI specific functions */ /* Called by usb_alloc_dev to alloc HC device structures */ int (*alloc_dev)(struct usb_hcd *, struct usb_device *); /* Called by usb_disconnect to free HC device structures */ void (*free_dev)(struct usb_hcd *, struct usb_device *); /* Change a group of bulk endpoints to support multiple stream IDs */ int (*alloc_streams)(struct usb_hcd *hcd, struct usb_device *udev, struct usb_host_endpoint **eps, unsigned int num_eps, unsigned int num_streams, gfp_t mem_flags); /* Reverts a group of bulk endpoints back to not using stream IDs. * Can fail if we run out of memory. */ int (*free_streams)(struct usb_hcd *hcd, struct usb_device *udev, struct usb_host_endpoint **eps, unsigned int num_eps, gfp_t mem_flags); /* Bandwidth computation functions */ /* Note that add_endpoint() can only be called once per endpoint before * check_bandwidth() or reset_bandwidth() must be called. * drop_endpoint() can only be called once per endpoint also. * A call to xhci_drop_endpoint() followed by a call to * xhci_add_endpoint() will add the endpoint to the schedule with * possibly new parameters denoted by a different endpoint descriptor * in usb_host_endpoint. A call to xhci_add_endpoint() followed by a * call to xhci_drop_endpoint() is not allowed. */ /* Allocate endpoint resources and add them to a new schedule */ int (*add_endpoint)(struct usb_hcd *, struct usb_device *, struct usb_host_endpoint *); /* Drop an endpoint from a new schedule */ int (*drop_endpoint)(struct usb_hcd *, struct usb_device *, struct usb_host_endpoint *); /* Check that a new hardware configuration, set using * endpoint_enable and endpoint_disable, does not exceed bus * bandwidth. This must be called before any set configuration * or set interface requests are sent to the device. */ int (*check_bandwidth)(struct usb_hcd *, struct usb_device *); /* Reset the device schedule to the last known good schedule, * which was set from a previous successful call to * check_bandwidth(). This reverts any add_endpoint() and * drop_endpoint() calls since that last successful call. * Used for when a check_bandwidth() call fails due to resource * or bandwidth constraints. */ void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *); /* Set the hardware-chosen device address */ int (*address_device)(struct usb_hcd *, struct usb_device *udev, unsigned int timeout_ms); /* prepares the hardware to send commands to the device */ int (*enable_device)(struct usb_hcd *, struct usb_device *udev); /* Notifies the HCD after a hub descriptor is fetched. * Will block. */ int (*update_hub_device)(struct usb_hcd *, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags); int (*reset_device)(struct usb_hcd *, struct usb_device *); /* Notifies the HCD after a device is connected and its * address is set */ int (*update_device)(struct usb_hcd *, struct usb_device *); int (*set_usb2_hw_lpm)(struct usb_hcd *, struct usb_device *, int); /* USB 3.0 Link Power Management */ /* Returns the USB3 hub-encoded value for the U1/U2 timeout. */ int (*enable_usb3_lpm_timeout)(struct usb_hcd *, struct usb_device *, enum usb3_link_state state); /* The xHCI host controller can still fail the command to * disable the LPM timeouts, so this can return an error code. */ int (*disable_usb3_lpm_timeout)(struct usb_hcd *, struct usb_device *, enum usb3_link_state state); int (*find_raw_port_number)(struct usb_hcd *, int); /* Call for power on/off the port if necessary */ int (*port_power)(struct usb_hcd *hcd, int portnum, bool enable); /* Call for SINGLE_STEP_SET_FEATURE Test for USB2 EH certification */ #define EHSET_TEST_SINGLE_STEP_SET_FEATURE 0x06 int (*submit_single_step_set_feature)(struct usb_hcd *, struct urb *, int); }; static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) { return hcd->driver->flags & HCD_BH; } static inline bool hcd_periodic_completion_in_progress(struct usb_hcd *hcd, struct usb_host_endpoint *ep) { return hcd->high_prio_bh.completing_ep == ep; } static inline bool hcd_uses_dma(struct usb_hcd *hcd) { return IS_ENABLED(CONFIG_HAS_DMA) && (hcd->driver->flags & HCD_DMA); } extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb, int status); extern void usb_hcd_unlink_urb_from_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_submit_urb(struct urb *urb, gfp_t mem_flags); extern int usb_hcd_unlink_urb(struct urb *urb, int status); extern void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status); extern int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags); extern void usb_hcd_unmap_urb_setup_for_dma(struct usb_hcd *, struct urb *); extern void usb_hcd_unmap_urb_for_dma(struct usb_hcd *, struct urb *); extern void usb_hcd_flush_endpoint(struct usb_device *udev, struct usb_host_endpoint *ep); extern void usb_hcd_disable_endpoint(struct usb_device *udev, struct usb_host_endpoint *ep); extern void usb_hcd_reset_endpoint(struct usb_device *udev, struct usb_host_endpoint *ep); extern void usb_hcd_synchronize_unlinks(struct usb_device *udev); extern int usb_hcd_alloc_bandwidth(struct usb_device *udev, struct usb_host_config *new_config, struct usb_host_interface *old_alt, struct usb_host_interface *new_alt); extern int usb_hcd_get_frame_number(struct usb_device *udev); struct usb_hcd *__usb_create_hcd(const struct hc_driver *driver, struct device *sysdev, struct device *dev, const char *bus_name, struct usb_hcd *primary_hcd); extern struct usb_hcd *usb_create_hcd(const struct hc_driver *driver, struct device *dev, const char *bus_name); extern struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver, struct device *dev, const char *bus_name, struct usb_hcd *shared_hcd); extern struct usb_hcd *usb_get_hcd(struct usb_hcd *hcd); extern void usb_put_hcd(struct usb_hcd *hcd); extern int usb_hcd_is_primary_hcd(struct usb_hcd *hcd); extern int usb_add_hcd(struct usb_hcd *hcd, unsigned int irqnum, unsigned long irqflags); extern void usb_remove_hcd(struct usb_hcd *hcd); extern int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1); int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr, dma_addr_t dma, size_t size); struct platform_device; extern void usb_hcd_platform_shutdown(struct platform_device *dev); #ifdef CONFIG_USB_HCD_TEST_MODE extern int ehset_single_step_set_feature(struct usb_hcd *hcd, int port); #else static inline int ehset_single_step_set_feature(struct usb_hcd *hcd, int port) { return 0; } #endif /* CONFIG_USB_HCD_TEST_MODE */ #ifdef CONFIG_USB_PCI struct pci_dev; struct pci_device_id; extern int usb_hcd_pci_probe(struct pci_dev *dev, const struct hc_driver *driver); extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); #ifdef CONFIG_USB_PCI_AMD extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); static inline bool usb_hcd_amd_resume_bug(struct pci_dev *dev, const struct hc_driver *driver) { if (!usb_hcd_amd_remote_wakeup_quirk(dev)) return false; if (driver->flags & (HCD_USB11 | HCD_USB3)) return true; return false; } #else /* CONFIG_USB_PCI_AMD */ static inline bool usb_hcd_amd_resume_bug(struct pci_dev *dev, const struct hc_driver *driver) { return false; } #endif extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ void usb_init_pool_max(void); int hcd_buffer_create(struct usb_hcd *hcd); void hcd_buffer_destroy(struct usb_hcd *hcd); void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, gfp_t mem_flags, dma_addr_t *dma); void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, size_t size, gfp_t mem_flags, dma_addr_t *dma); void hcd_buffer_free_pages(struct usb_hcd *hcd, size_t size, void *addr, dma_addr_t dma); /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); extern void usb_hc_died(struct usb_hcd *hcd); extern void usb_hcd_poll_rh_status(struct usb_hcd *hcd); extern void usb_wakeup_notification(struct usb_device *hdev, unsigned int portnum); extern void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum); extern void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum); /* The D0/D1 toggle bits ... USE WITH CAUTION (they're almost hcd-internal) */ #define usb_gettoggle(dev, ep, out) (((dev)->toggle[out] >> (ep)) & 1) #define usb_dotoggle(dev, ep, out) ((dev)->toggle[out] ^= (1 << (ep))) #define usb_settoggle(dev, ep, out, bit) \ ((dev)->toggle[out] = ((dev)->toggle[out] & ~(1 << (ep))) | \ ((bit) << (ep))) /* -------------------------------------------------------------------------- */ /* Enumeration is only for the hub driver, or HCD virtual root hubs */ extern struct usb_device *usb_alloc_dev(struct usb_device *parent, struct usb_bus *, unsigned port); extern int usb_new_device(struct usb_device *dev); extern void usb_disconnect(struct usb_device **); extern int usb_get_configuration(struct usb_device *dev); extern void usb_destroy_configuration(struct usb_device *dev); /*-------------------------------------------------------------------------*/ /* * HCD Root Hub support */ #include <linux/usb/ch11.h> /* * As of USB 2.0, full/low speed devices are segregated into trees. * One type grows from USB 1.1 host controllers (OHCI, UHCI etc). * The other type grows from high speed hubs when they connect to * full/low speed devices using "Transaction Translators" (TTs). * * TTs should only be known to the hub driver, and high speed bus * drivers (only EHCI for now). They affect periodic scheduling and * sometimes control/bulk error recovery. */ struct usb_device; struct usb_tt { struct usb_device *hub; /* upstream highspeed hub */ int multi; /* true means one TT per port */ unsigned think_time; /* think time in ns */ void *hcpriv; /* HCD private data */ /* for control/bulk error recovery (CLEAR_TT_BUFFER) */ spinlock_t lock; struct list_head clear_list; /* of usb_tt_clear */ struct work_struct clear_work; }; struct usb_tt_clear { struct list_head clear_list; unsigned tt; u16 devinfo; struct usb_hcd *hcd; struct usb_host_endpoint *ep; }; extern int usb_hub_clear_tt_buffer(struct urb *urb); extern void usb_ep0_reinit(struct usb_device *); /* (shifted) direction/type/recipient from the USB 2.0 spec, table 9.2 */ #define DeviceRequest \ ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_DEVICE)<<8) #define DeviceOutRequest \ ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_DEVICE)<<8) #define InterfaceRequest \ ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) #define EndpointRequest \ ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) #define EndpointOutRequest \ ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) /* class requests from the USB 2.0 hub spec, table 11-15 */ #define HUB_CLASS_REQ(dir, type, request) ((((dir) | (type)) << 8) | (request)) /* GetBusState and SetHubDescriptor are optional, omitted */ #define ClearHubFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, USB_REQ_CLEAR_FEATURE) #define ClearPortFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, USB_REQ_CLEAR_FEATURE) #define GetHubDescriptor HUB_CLASS_REQ(USB_DIR_IN, USB_RT_HUB, USB_REQ_GET_DESCRIPTOR) #define GetHubStatus HUB_CLASS_REQ(USB_DIR_IN, USB_RT_HUB, USB_REQ_GET_STATUS) #define GetPortStatus HUB_CLASS_REQ(USB_DIR_IN, USB_RT_PORT, USB_REQ_GET_STATUS) #define SetHubFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, USB_REQ_SET_FEATURE) #define SetPortFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, USB_REQ_SET_FEATURE) #define ClearTTBuffer HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, HUB_CLEAR_TT_BUFFER) #define ResetTT HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, HUB_RESET_TT) #define GetTTState HUB_CLASS_REQ(USB_DIR_IN, USB_RT_PORT, HUB_GET_TT_STATE) #define StopTT HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, HUB_STOP_TT) /*-------------------------------------------------------------------------*/ /* class requests from USB 3.1 hub spec, table 10-7 */ #define SetHubDepth HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, HUB_SET_DEPTH) #define GetPortErrorCount HUB_CLASS_REQ(USB_DIR_IN, USB_RT_PORT, HUB_GET_PORT_ERR_COUNT) /* * Generic bandwidth allocation constants/support */ #define FRAME_TIME_USECS 1000L #define BitTime(bytecount) (7 * 8 * bytecount / 6) /* with integer truncation */ /* Trying not to use worst-case bit-stuffing * of (7/6 * 8 * bytecount) = 9.33 * bytecount */ /* bytecount = data payload byte count */ #define NS_TO_US(ns) DIV_ROUND_UP(ns, 1000L) /* convert nanoseconds to microseconds, rounding up */ /* * Full/low speed bandwidth allocation constants/support. */ #define BW_HOST_DELAY 1000L /* nanoseconds */ #define BW_HUB_LS_SETUP 333L /* nanoseconds */ /* 4 full-speed bit times (est.) */ #define FRAME_TIME_BITS 12000L /* frame = 1 millisecond */ #define FRAME_TIME_MAX_BITS_ALLOC (90L * FRAME_TIME_BITS / 100L) #define FRAME_TIME_MAX_USECS_ALLOC (90L * FRAME_TIME_USECS / 100L) /* * Ceiling [nano/micro]seconds (typical) for that many bytes at high speed * ISO is a bit less, no ACK ... from USB 2.0 spec, 5.11.3 (and needed * to preallocate bandwidth) */ #define USB2_HOST_DELAY 5 /* nsec, guess */ #define HS_NSECS(bytes) (((55 * 8 * 2083) \ + (2083UL * (3 + BitTime(bytes))))/1000 \ + USB2_HOST_DELAY) #define HS_NSECS_ISO(bytes) (((38 * 8 * 2083) \ + (2083UL * (3 + BitTime(bytes))))/1000 \ + USB2_HOST_DELAY) #define HS_USECS(bytes) NS_TO_US(HS_NSECS(bytes)) #define HS_USECS_ISO(bytes) NS_TO_US(HS_NSECS_ISO(bytes)) extern long usb_calc_bus_time(int speed, int is_input, int isoc, int bytecount); /*-------------------------------------------------------------------------*/ extern void usb_set_device_state(struct usb_device *udev, enum usb_device_state new_state); /*-------------------------------------------------------------------------*/ /* exported only within usbcore */ extern struct idr usb_bus_idr; extern struct mutex usb_bus_idr_lock; extern wait_queue_head_t usb_kill_urb_queue; #define usb_endpoint_out(ep_dir) (!((ep_dir) & USB_DIR_IN)) #ifdef CONFIG_PM extern unsigned usb_wakeup_enabled_descendants(struct usb_device *udev); extern void usb_root_hub_lost_power(struct usb_device *rhdev); extern int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg); extern int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg); extern void usb_hcd_resume_root_hub(struct usb_hcd *hcd); #else static inline unsigned usb_wakeup_enabled_descendants(struct usb_device *udev) { return 0; } static inline void usb_hcd_resume_root_hub(struct usb_hcd *hcd) { return; } #endif /* CONFIG_PM */ /*-------------------------------------------------------------------------*/ #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE) struct usb_mon_operations { void (*urb_submit)(struct usb_bus *bus, struct urb *urb); void (*urb_submit_error)(struct usb_bus *bus, struct urb *urb, int err); void (*urb_complete)(struct usb_bus *bus, struct urb *urb, int status); /* void (*urb_unlink)(struct usb_bus *bus, struct urb *urb); */ }; extern const struct usb_mon_operations *mon_ops; static inline void usbmon_urb_submit(struct usb_bus *bus, struct urb *urb) { if (bus->monitored) (*mon_ops->urb_submit)(bus, urb); } static inline void usbmon_urb_submit_error(struct usb_bus *bus, struct urb *urb, int error) { if (bus->monitored) (*mon_ops->urb_submit_error)(bus, urb, error); } static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb, int status) { if (bus->monitored) (*mon_ops->urb_complete)(bus, urb, status); } int usb_mon_register(const struct usb_mon_operations *ops); void usb_mon_deregister(void); #else static inline void usbmon_urb_submit(struct usb_bus *bus, struct urb *urb) {} static inline void usbmon_urb_submit_error(struct usb_bus *bus, struct urb *urb, int error) {} static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb, int status) {} #endif /* CONFIG_USB_MON || CONFIG_USB_MON_MODULE */ /*-------------------------------------------------------------------------*/ /* random stuff */ /* This rwsem is for use only by the hub driver and ehci-hcd. * Nobody else should touch it. */ extern struct rw_semaphore ehci_cf_port_reset_rwsem; /* Keep track of which host controller drivers are loaded */ #define USB_UHCI_LOADED 0 #define USB_OHCI_LOADED 1 #define USB_EHCI_LOADED 2 extern unsigned long usb_hcds_loaded; #endif /* __KERNEL__ */ #endif /* __USB_CORE_HCD_H */ |
| 3 16 16 16 16 14 14 3 3 3 17 16 16 16 14 3 9 9 9 9 9 9 13 13 13 13 13 13 13 13 13 14 14 14 17 17 14 14 13 13 17 3 7 7 2 2 2 2 2 18 17 17 17 17 17 17 17 17 17 17 17 13 11 11 18 6 6 1 6 6 17 4 2 2 2 2 2 2 2 4 3 6 14 6 6 6 6 6 1 6 6 6 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 | /* * Public API and common code for kernel->userspace relay file support. * * See Documentation/filesystems/relay.rst for an overview. * * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com) * * Moved to kernel/relay.c by Paul Mundt, 2006. * November 2006 - CPU hotplug support by Mathieu Desnoyers * (mathieu.desnoyers@polymtl.ca) * * This file is released under the GPL. */ #include <linux/errno.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/string.h> #include <linux/relay.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/cpu.h> #include <linux/splice.h> /* list of open channels, for cpu hotplug */ static DEFINE_MUTEX(relay_channels_mutex); static LIST_HEAD(relay_channels); /* * fault() vm_op implementation for relay file mapping. */ static vm_fault_t relay_buf_fault(struct vm_fault *vmf) { struct page *page; struct rchan_buf *buf = vmf->vma->vm_private_data; pgoff_t pgoff = vmf->pgoff; if (!buf) return VM_FAULT_OOM; page = vmalloc_to_page(buf->start + (pgoff << PAGE_SHIFT)); if (!page) return VM_FAULT_SIGBUS; get_page(page); vmf->page = page; return 0; } /* * vm_ops for relay file mappings. */ static const struct vm_operations_struct relay_file_mmap_ops = { .fault = relay_buf_fault, }; /* * allocate an array of pointers of struct page */ static struct page **relay_alloc_page_array(unsigned int n_pages) { return kvcalloc(n_pages, sizeof(struct page *), GFP_KERNEL); } /* * free an array of pointers of struct page */ static void relay_free_page_array(struct page **array) { kvfree(array); } /** * relay_mmap_buf: - mmap channel buffer to process address space * @buf: relay channel buffer * @vma: vm_area_struct describing memory to be mapped * * Returns 0 if ok, negative on error * * Caller should already have grabbed mmap_lock. */ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) { unsigned long length = vma->vm_end - vma->vm_start; if (!buf) return -EBADF; if (length != (unsigned long)buf->chan->alloc_size) return -EINVAL; vma->vm_ops = &relay_file_mmap_ops; vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = buf; return 0; } /** * relay_alloc_buf - allocate a channel buffer * @buf: the buffer struct * @size: total size of the buffer * * Returns a pointer to the resulting buffer, %NULL if unsuccessful. The * passed in size will get page aligned, if it isn't already. */ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size) { void *mem; unsigned int i, j, n_pages; *size = PAGE_ALIGN(*size); n_pages = *size >> PAGE_SHIFT; buf->page_array = relay_alloc_page_array(n_pages); if (!buf->page_array) return NULL; for (i = 0; i < n_pages; i++) { buf->page_array[i] = alloc_page(GFP_KERNEL); if (unlikely(!buf->page_array[i])) goto depopulate; set_page_private(buf->page_array[i], (unsigned long)buf); } mem = vmap(buf->page_array, n_pages, VM_MAP, PAGE_KERNEL); if (!mem) goto depopulate; memset(mem, 0, *size); buf->page_count = n_pages; return mem; depopulate: for (j = 0; j < i; j++) __free_page(buf->page_array[j]); relay_free_page_array(buf->page_array); return NULL; } /** * relay_create_buf - allocate and initialize a channel buffer * @chan: the relay channel * * Returns channel buffer if successful, %NULL otherwise. */ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; buf->start = relay_alloc_buf(buf, &chan->alloc_size); if (!buf->start) goto free_buf; buf->chan = chan; kref_get(&buf->chan->kref); return buf; free_buf: kfree(buf->padding); kfree(buf); return NULL; } /** * relay_destroy_channel - free the channel struct * @kref: target kernel reference that contains the relay channel * * Should only be called from kref_put(). */ static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); free_percpu(chan->buf); kfree(chan); } /** * relay_destroy_buf - destroy an rchan_buf struct and associated buffer * @buf: the buffer struct */ static void relay_destroy_buf(struct rchan_buf *buf) { struct rchan *chan = buf->chan; unsigned int i; if (likely(buf->start)) { vunmap(buf->start); for (i = 0; i < buf->page_count; i++) __free_page(buf->page_array[i]); relay_free_page_array(buf->page_array); } *per_cpu_ptr(chan->buf, buf->cpu) = NULL; kfree(buf->padding); kfree(buf); kref_put(&chan->kref, relay_destroy_channel); } /** * relay_remove_buf - remove a channel buffer * @kref: target kernel reference that contains the relay buffer * * Removes the file from the filesystem, which also frees the * rchan_buf_struct and the channel buffer. Should only be called from * kref_put(). */ static void relay_remove_buf(struct kref *kref) { struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref); relay_destroy_buf(buf); } /** * relay_buf_empty - boolean, is the channel buffer empty? * @buf: channel buffer * * Returns 1 if the buffer is empty, 0 otherwise. */ static int relay_buf_empty(struct rchan_buf *buf) { return (buf->subbufs_produced - buf->subbufs_consumed) ? 0 : 1; } /** * relay_buf_full - boolean, is the channel buffer full? * @buf: channel buffer * * Returns 1 if the buffer is full, 0 otherwise. */ int relay_buf_full(struct rchan_buf *buf) { size_t ready = buf->subbufs_produced - buf->subbufs_consumed; return (ready >= buf->chan->n_subbufs) ? 1 : 0; } EXPORT_SYMBOL_GPL(relay_buf_full); /* * High-level relay kernel API and associated functions. */ static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding) { if (!buf->chan->cb->subbuf_start) return !relay_buf_full(buf); return buf->chan->cb->subbuf_start(buf, subbuf, prev_subbuf, prev_padding); } /** * wakeup_readers - wake up readers waiting on a channel * @work: contains the channel buffer * * This is the function used to defer reader waking */ static void wakeup_readers(struct irq_work *work) { struct rchan_buf *buf; buf = container_of(work, struct rchan_buf, wakeup_work); wake_up_interruptible(&buf->read_wait); } /** * __relay_reset - reset a channel buffer * @buf: the channel buffer * @init: 1 if this is a first-time initialization * * See relay_reset() for description of effect. */ static void __relay_reset(struct rchan_buf *buf, unsigned int init) { size_t i; if (init) { init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); init_irq_work(&buf->wakeup_work, wakeup_readers); } else { irq_work_sync(&buf->wakeup_work); } buf->subbufs_produced = 0; buf->subbufs_consumed = 0; buf->bytes_consumed = 0; buf->finalized = 0; buf->data = buf->start; buf->offset = 0; for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; relay_subbuf_start(buf, buf->data, NULL, 0); } /** * relay_reset - reset the channel * @chan: the channel * * This has the effect of erasing all data from all channel buffers * and restarting the channel in its initial state. The buffers * are not freed, so any mappings are still in effect. * * NOTE. Care should be taken that the channel isn't actually * being used by anything when this call is made. */ void relay_reset(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) { __relay_reset(buf, 0); return; } mutex_lock(&relay_channels_mutex); for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) __relay_reset(buf, 0); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_reset); static inline void relay_set_buf_dentry(struct rchan_buf *buf, struct dentry *dentry) { buf->dentry = dentry; d_inode(buf->dentry)->i_size = buf->early_bytes; } static struct dentry *relay_create_buf_file(struct rchan *chan, struct rchan_buf *buf, unsigned int cpu) { struct dentry *dentry; char *tmpname; tmpname = kasprintf(GFP_KERNEL, "%s%d", chan->base_filename, cpu); if (!tmpname) return NULL; /* Create file in fs */ dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); if (IS_ERR(dentry)) dentry = NULL; kfree(tmpname); return dentry; } /* * relay_open_buf - create a new relay channel buffer * * used by relay_open() and CPU hotplug. */ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) { struct rchan_buf *buf; struct dentry *dentry; if (chan->is_global) return *per_cpu_ptr(chan->buf, 0); buf = relay_create_buf(chan); if (!buf) return NULL; if (chan->has_base_filename) { dentry = relay_create_buf_file(chan, buf, cpu); if (!dentry) goto free_buf; relay_set_buf_dentry(buf, dentry); } else { /* Only retrieve global info, nothing more, nothing less */ dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); if (IS_ERR_OR_NULL(dentry)) goto free_buf; } buf->cpu = cpu; __relay_reset(buf, 1); if(chan->is_global) { *per_cpu_ptr(chan->buf, 0) = buf; buf->cpu = 0; } return buf; free_buf: relay_destroy_buf(buf); return NULL; } /** * relay_close_buf - close a channel buffer * @buf: channel buffer * * Marks the buffer finalized and restores the default callbacks. * The channel buffer and channel buffer data structure are then freed * automatically when the last reference is given up. */ static void relay_close_buf(struct rchan_buf *buf) { buf->finalized = 1; irq_work_sync(&buf->wakeup_work); buf->chan->cb->remove_buf_file(buf->dentry); kref_put(&buf->kref, relay_remove_buf); } int relay_prepare_cpu(unsigned int cpu) { struct rchan *chan; struct rchan_buf *buf; mutex_lock(&relay_channels_mutex); list_for_each_entry(chan, &relay_channels, list) { if (*per_cpu_ptr(chan->buf, cpu)) continue; buf = relay_open_buf(chan, cpu); if (!buf) { pr_err("relay: cpu %d buffer creation failed\n", cpu); mutex_unlock(&relay_channels_mutex); return -ENOMEM; } *per_cpu_ptr(chan->buf, cpu) = buf; } mutex_unlock(&relay_channels_mutex); return 0; } /** * relay_open - create a new relay channel * @base_filename: base name of files to create * @parent: dentry of parent directory, %NULL for root directory or buffer * @subbuf_size: size of sub-buffers * @n_subbufs: number of sub-buffers * @cb: client callback functions * @private_data: user-defined data * * Returns channel pointer if successful, %NULL otherwise. * * Creates a channel buffer for each cpu using the sizes and * attributes specified. The created channel buffer files * will be named base_filename0...base_filenameN-1. File * permissions will be %S_IRUSR. */ struct rchan *relay_open(const char *base_filename, struct dentry *parent, size_t subbuf_size, size_t n_subbufs, const struct rchan_callbacks *cb, void *private_data) { unsigned int i; struct rchan *chan; struct rchan_buf *buf; if (!(subbuf_size && n_subbufs)) return NULL; if (subbuf_size > UINT_MAX / n_subbufs) return NULL; if (!cb || !cb->create_buf_file || !cb->remove_buf_file) return NULL; chan = kzalloc(sizeof(struct rchan), GFP_KERNEL); if (!chan) return NULL; chan->buf = alloc_percpu(struct rchan_buf *); if (!chan->buf) { kfree(chan); return NULL; } chan->version = RELAYFS_CHANNEL_VERSION; chan->n_subbufs = n_subbufs; chan->subbuf_size = subbuf_size; chan->alloc_size = PAGE_ALIGN(subbuf_size * n_subbufs); chan->parent = parent; chan->private_data = private_data; if (base_filename) { chan->has_base_filename = 1; strscpy(chan->base_filename, base_filename, NAME_MAX); } chan->cb = cb; kref_init(&chan->kref); mutex_lock(&relay_channels_mutex); for_each_online_cpu(i) { buf = relay_open_buf(chan, i); if (!buf) goto free_bufs; *per_cpu_ptr(chan->buf, i) = buf; } list_add(&chan->list, &relay_channels); mutex_unlock(&relay_channels_mutex); return chan; free_bufs: for_each_possible_cpu(i) { if ((buf = *per_cpu_ptr(chan->buf, i))) relay_close_buf(buf); } kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); return NULL; } EXPORT_SYMBOL_GPL(relay_open); struct rchan_percpu_buf_dispatcher { struct rchan_buf *buf; struct dentry *dentry; }; /** * relay_switch_subbuf - switch to a new sub-buffer * @buf: channel buffer * @length: size of current event * * Returns either the length passed in or 0 if full. * * Performs sub-buffer-switch tasks such as invoking callbacks, * updating padding counts, waking up readers, etc. */ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) { void *old, *new; size_t old_subbuf, new_subbuf; if (unlikely(length > buf->chan->subbuf_size)) goto toobig; if (buf->offset != buf->chan->subbuf_size + 1) { buf->prev_padding = buf->chan->subbuf_size - buf->offset; old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; buf->padding[old_subbuf] = buf->prev_padding; buf->subbufs_produced++; if (buf->dentry) d_inode(buf->dentry)->i_size += buf->chan->subbuf_size - buf->padding[old_subbuf]; else buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; smp_mb(); if (waitqueue_active(&buf->read_wait)) { /* * Calling wake_up_interruptible() from here * will deadlock if we happen to be logging * from the scheduler (trying to re-grab * rq->lock), so defer it. */ irq_work_queue(&buf->wakeup_work); } } old = buf->data; new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; new = buf->start + new_subbuf * buf->chan->subbuf_size; buf->offset = 0; if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) { buf->offset = buf->chan->subbuf_size + 1; return 0; } buf->data = new; buf->padding[new_subbuf] = 0; if (unlikely(length + buf->offset > buf->chan->subbuf_size)) goto toobig; return length; toobig: buf->chan->last_toobig = length; return 0; } EXPORT_SYMBOL_GPL(relay_switch_subbuf); /** * relay_subbufs_consumed - update the buffer's sub-buffers-consumed count * @chan: the channel * @cpu: the cpu associated with the channel buffer to update * @subbufs_consumed: number of sub-buffers to add to current buf's count * * Adds to the channel buffer's consumed sub-buffer count. * subbufs_consumed should be the number of sub-buffers newly consumed, * not the total consumed. * * NOTE. Kernel clients don't need to call this function if the channel * mode is 'overwrite'. */ void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t subbufs_consumed) { struct rchan_buf *buf; if (!chan || cpu >= NR_CPUS) return; buf = *per_cpu_ptr(chan->buf, cpu); if (!buf || subbufs_consumed > chan->n_subbufs) return; if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed) buf->subbufs_consumed = buf->subbufs_produced; else buf->subbufs_consumed += subbufs_consumed; } EXPORT_SYMBOL_GPL(relay_subbufs_consumed); /** * relay_close - close the channel * @chan: the channel * * Closes all channel buffers and frees the channel. */ void relay_close(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; mutex_lock(&relay_channels_mutex); if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) relay_close_buf(buf); else for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) relay_close_buf(buf); if (chan->last_toobig) printk(KERN_WARNING "relay: one or more items not logged " "[item size (%zd) > sub-buffer size (%zd)]\n", chan->last_toobig, chan->subbuf_size); list_del(&chan->list); kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_close); /** * relay_flush - close the channel * @chan: the channel * * Flushes all channel buffers, i.e. forces buffer switch. */ void relay_flush(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) { relay_switch_subbuf(buf, 0); return; } mutex_lock(&relay_channels_mutex); for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) relay_switch_subbuf(buf, 0); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_flush); /** * relay_file_open - open file op for relay files * @inode: the inode * @filp: the file * * Increments the channel buffer refcount. */ static int relay_file_open(struct inode *inode, struct file *filp) { struct rchan_buf *buf = inode->i_private; kref_get(&buf->kref); filp->private_data = buf; return nonseekable_open(inode, filp); } /** * relay_file_mmap - mmap file op for relay files * @filp: the file * @vma: the vma describing what to map * * Calls upon relay_mmap_buf() to map the file into user space. */ static int relay_file_mmap(struct file *filp, struct vm_area_struct *vma) { struct rchan_buf *buf = filp->private_data; return relay_mmap_buf(buf, vma); } /** * relay_file_poll - poll file op for relay files * @filp: the file * @wait: poll table * * Poll implemention. */ static __poll_t relay_file_poll(struct file *filp, poll_table *wait) { __poll_t mask = 0; struct rchan_buf *buf = filp->private_data; if (buf->finalized) return EPOLLERR; if (filp->f_mode & FMODE_READ) { poll_wait(filp, &buf->read_wait, wait); if (!relay_buf_empty(buf)) mask |= EPOLLIN | EPOLLRDNORM; } return mask; } /** * relay_file_release - release file op for relay files * @inode: the inode * @filp: the file * * Decrements the channel refcount, as the filesystem is * no longer using it. */ static int relay_file_release(struct inode *inode, struct file *filp) { struct rchan_buf *buf = filp->private_data; kref_put(&buf->kref, relay_remove_buf); return 0; } /* * relay_file_read_consume - update the consumed count for the buffer */ static void relay_file_read_consume(struct rchan_buf *buf, size_t read_pos, size_t bytes_consumed) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t read_subbuf; if (buf->subbufs_produced == buf->subbufs_consumed && buf->offset == buf->bytes_consumed) return; if (buf->bytes_consumed + bytes_consumed > subbuf_size) { relay_subbufs_consumed(buf->chan, buf->cpu, 1); buf->bytes_consumed = 0; } buf->bytes_consumed += bytes_consumed; if (!read_pos) read_subbuf = buf->subbufs_consumed % n_subbufs; else read_subbuf = read_pos / buf->chan->subbuf_size; if (buf->bytes_consumed + buf->padding[read_subbuf] == subbuf_size) { if ((read_subbuf == buf->subbufs_produced % n_subbufs) && (buf->offset == subbuf_size)) return; relay_subbufs_consumed(buf->chan, buf->cpu, 1); buf->bytes_consumed = 0; } } /* * relay_file_read_avail - boolean, are there unconsumed bytes available? */ static int relay_file_read_avail(struct rchan_buf *buf) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t produced = buf->subbufs_produced; size_t consumed; relay_file_read_consume(buf, 0, 0); consumed = buf->subbufs_consumed; if (unlikely(buf->offset > subbuf_size)) { if (produced == consumed) return 0; return 1; } if (unlikely(produced - consumed >= n_subbufs)) { consumed = produced - n_subbufs + 1; buf->subbufs_consumed = consumed; buf->bytes_consumed = 0; } produced = (produced % n_subbufs) * subbuf_size + buf->offset; consumed = (consumed % n_subbufs) * subbuf_size + buf->bytes_consumed; if (consumed > produced) produced += n_subbufs * subbuf_size; if (consumed == produced) { if (buf->offset == subbuf_size && buf->subbufs_produced > buf->subbufs_consumed) return 1; return 0; } return 1; } /** * relay_file_read_subbuf_avail - return bytes available in sub-buffer * @read_pos: file read position * @buf: relay channel buffer */ static size_t relay_file_read_subbuf_avail(size_t read_pos, struct rchan_buf *buf) { size_t padding, avail = 0; size_t read_subbuf, read_offset, write_subbuf, write_offset; size_t subbuf_size = buf->chan->subbuf_size; write_subbuf = (buf->data - buf->start) / subbuf_size; write_offset = buf->offset > subbuf_size ? subbuf_size : buf->offset; read_subbuf = read_pos / subbuf_size; read_offset = read_pos % subbuf_size; padding = buf->padding[read_subbuf]; if (read_subbuf == write_subbuf) { if (read_offset + padding < write_offset) avail = write_offset - (read_offset + padding); } else avail = (subbuf_size - padding) - read_offset; return avail; } /** * relay_file_read_start_pos - find the first available byte to read * @buf: relay channel buffer * * If the read_pos is in the middle of padding, return the * position of the first actually available byte, otherwise * return the original value. */ static size_t relay_file_read_start_pos(struct rchan_buf *buf) { size_t read_subbuf, padding, padding_start, padding_end; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) % (n_subbufs * subbuf_size); read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; padding_start = (read_subbuf + 1) * subbuf_size - padding; padding_end = (read_subbuf + 1) * subbuf_size; if (read_pos >= padding_start && read_pos < padding_end) { read_subbuf = (read_subbuf + 1) % n_subbufs; read_pos = read_subbuf * subbuf_size; } return read_pos; } /** * relay_file_read_end_pos - return the new read position * @read_pos: file read position * @buf: relay channel buffer * @count: number of bytes to be read */ static size_t relay_file_read_end_pos(struct rchan_buf *buf, size_t read_pos, size_t count) { size_t read_subbuf, padding, end_pos; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; if (read_pos % subbuf_size + count + padding == subbuf_size) end_pos = (read_subbuf + 1) * subbuf_size; else end_pos = read_pos + count; if (end_pos >= subbuf_size * n_subbufs) end_pos = 0; return end_pos; } static ssize_t relay_file_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct rchan_buf *buf = filp->private_data; size_t read_start, avail; size_t written = 0; int ret; if (!count) return 0; inode_lock(file_inode(filp)); do { void *from; if (!relay_file_read_avail(buf)) break; read_start = relay_file_read_start_pos(buf); avail = relay_file_read_subbuf_avail(read_start, buf); if (!avail) break; avail = min(count, avail); from = buf->start + read_start; ret = avail; if (copy_to_user(buffer, from, avail)) break; buffer += ret; written += ret; count -= ret; relay_file_read_consume(buf, read_start, ret); *ppos = relay_file_read_end_pos(buf, read_start, ret); } while (count); inode_unlock(file_inode(filp)); return written; } const struct file_operations relay_file_operations = { .open = relay_file_open, .poll = relay_file_poll, .mmap = relay_file_mmap, .read = relay_file_read, .release = relay_file_release, }; EXPORT_SYMBOL_GPL(relay_file_operations); |
| 2 6 4 17 18 18 4 3 1 1 23 23 23 19 18 18 18 18 18 18 18 6 6 2 1 1 1 1 1 4 18 18 18 23 4 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/fdtable.h> #include <linux/string.h> #include <linux/random.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/cache.h> #include <linux/bug.h> #include <linux/err.h> #include <linux/kcmp.h> #include <linux/capability.h> #include <linux/list.h> #include <linux/eventpoll.h> #include <linux/file.h> #include <asm/unistd.h> /* * We don't expose the real in-memory order of objects for security reasons. * But still the comparison results should be suitable for sorting. So we * obfuscate kernel pointers values and compare the production instead. * * The obfuscation is done in two steps. First we xor the kernel pointer with * a random value, which puts pointer into a new position in a reordered space. * Secondly we multiply the xor production with a large odd random number to * permute its bits even more (the odd multiplier guarantees that the product * is unique ever after the high bits are truncated, since any odd number is * relative prime to 2^n). * * Note also that the obfuscation itself is invisible to userspace and if needed * it can be changed to an alternate scheme. */ static unsigned long cookies[KCMP_TYPES][2] __read_mostly; static long kptr_obfuscate(long v, int type) { return (v ^ cookies[type][0]) * cookies[type][1]; } /* * 0 - equal, i.e. v1 = v2 * 1 - less than, i.e. v1 < v2 * 2 - greater than, i.e. v1 > v2 * 3 - not equal but ordering unavailable (reserved for future) */ static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) { long t1, t2; t1 = kptr_obfuscate((long)v1, type); t2 = kptr_obfuscate((long)v2, type); return (t1 < t2) | ((t1 > t2) << 1); } /* The caller must have pinned the task */ static struct file * get_file_raw_ptr(struct task_struct *task, unsigned int idx) { struct file *file; file = fget_task(task, idx); if (file) fput(file); return file; } static void kcmp_unlock(struct rw_semaphore *l1, struct rw_semaphore *l2) { if (likely(l2 != l1)) up_read(l2); up_read(l1); } static int kcmp_lock(struct rw_semaphore *l1, struct rw_semaphore *l2) { int err; if (l2 > l1) swap(l1, l2); err = down_read_killable(l1); if (!err && likely(l1 != l2)) { err = down_read_killable_nested(l2, SINGLE_DEPTH_NESTING); if (err) up_read(l1); } return err; } #ifdef CONFIG_EPOLL static int kcmp_epoll_target(struct task_struct *task1, struct task_struct *task2, unsigned long idx1, struct kcmp_epoll_slot __user *uslot) { struct file *filp, *filp_epoll, *filp_tgt; struct kcmp_epoll_slot slot; if (copy_from_user(&slot, uslot, sizeof(slot))) return -EFAULT; filp = get_file_raw_ptr(task1, idx1); if (!filp) return -EBADF; filp_epoll = fget_task(task2, slot.efd); if (!filp_epoll) return -EBADF; filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); return kcmp_ptr(filp, filp_tgt, KCMP_FILE); } #else static int kcmp_epoll_target(struct task_struct *task1, struct task_struct *task2, unsigned long idx1, struct kcmp_epoll_slot __user *uslot) { return -EOPNOTSUPP; } #endif SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2) { struct task_struct *task1, *task2; int ret; rcu_read_lock(); /* * Tasks are looked up in caller's PID namespace only. */ task1 = find_task_by_vpid(pid1); task2 = find_task_by_vpid(pid2); if (unlikely(!task1 || !task2)) goto err_no_task; get_task_struct(task1); get_task_struct(task2); rcu_read_unlock(); /* * One should have enough rights to inspect task details. */ ret = kcmp_lock(&task1->signal->exec_update_lock, &task2->signal->exec_update_lock); if (ret) goto err; if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) { ret = -EPERM; goto err_unlock; } switch (type) { case KCMP_FILE: { struct file *filp1, *filp2; filp1 = get_file_raw_ptr(task1, idx1); filp2 = get_file_raw_ptr(task2, idx2); if (filp1 && filp2) ret = kcmp_ptr(filp1, filp2, KCMP_FILE); else ret = -EBADF; break; } case KCMP_VM: ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM); break; case KCMP_FILES: ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES); break; case KCMP_FS: ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS); break; case KCMP_SIGHAND: ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND); break; case KCMP_IO: ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO); break; case KCMP_SYSVSEM: #ifdef CONFIG_SYSVIPC ret = kcmp_ptr(task1->sysvsem.undo_list, task2->sysvsem.undo_list, KCMP_SYSVSEM); #else ret = -EOPNOTSUPP; #endif break; case KCMP_EPOLL_TFD: ret = kcmp_epoll_target(task1, task2, idx1, (void *)idx2); break; default: ret = -EINVAL; break; } err_unlock: kcmp_unlock(&task1->signal->exec_update_lock, &task2->signal->exec_update_lock); err: put_task_struct(task1); put_task_struct(task2); return ret; err_no_task: rcu_read_unlock(); return -ESRCH; } static __init int kcmp_cookies_init(void) { int i; get_random_bytes(cookies, sizeof(cookies)); for (i = 0; i < KCMP_TYPES; i++) cookies[i][1] |= (~(~0UL >> 1) | 1); return 0; } arch_initcall(kcmp_cookies_init); |
| 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 | /* * driver.c - driver support * * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * Shaohua Li <shaohua.li@intel.com> * Adam Belay <abelay@novell.com> * * This code is licenced under the GPL. */ #include <linux/mutex.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/cpuidle.h> #include <linux/cpumask.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/math64.h> #include "cpuidle.h" DEFINE_SPINLOCK(cpuidle_driver_lock); #ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS static DEFINE_PER_CPU(struct cpuidle_driver *, cpuidle_drivers); /** * __cpuidle_get_cpu_driver - return the cpuidle driver tied to a CPU. * @cpu: the CPU handled by the driver * * Returns a pointer to struct cpuidle_driver or NULL if no driver has been * registered for @cpu. */ static struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) { return per_cpu(cpuidle_drivers, cpu); } /** * __cpuidle_unset_driver - unset per CPU driver variables. * @drv: a valid pointer to a struct cpuidle_driver * * For each CPU in the driver's CPU mask, unset the registered driver per CPU * variable. If @drv is different from the registered driver, the corresponding * variable is not cleared. */ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) { int cpu; for_each_cpu(cpu, drv->cpumask) { if (drv != __cpuidle_get_cpu_driver(cpu)) continue; per_cpu(cpuidle_drivers, cpu) = NULL; } } /** * __cpuidle_set_driver - set per CPU driver variables for the given driver. * @drv: a valid pointer to a struct cpuidle_driver * * Returns 0 on success, -EBUSY if any CPU in the cpumask have a driver * different from drv already. */ static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) { int cpu; for_each_cpu(cpu, drv->cpumask) { struct cpuidle_driver *old_drv; old_drv = __cpuidle_get_cpu_driver(cpu); if (old_drv && old_drv != drv) return -EBUSY; } for_each_cpu(cpu, drv->cpumask) per_cpu(cpuidle_drivers, cpu) = drv; return 0; } #else static struct cpuidle_driver *cpuidle_curr_driver; /** * __cpuidle_get_cpu_driver - return the global cpuidle driver pointer. * @cpu: ignored without the multiple driver support * * Return a pointer to a struct cpuidle_driver object or NULL if no driver was * previously registered. */ static inline struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) { return cpuidle_curr_driver; } /** * __cpuidle_set_driver - assign the global cpuidle driver variable. * @drv: pointer to a struct cpuidle_driver object * * Returns 0 on success, -EBUSY if the driver is already registered. */ static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) { if (cpuidle_curr_driver) return -EBUSY; cpuidle_curr_driver = drv; return 0; } /** * __cpuidle_unset_driver - unset the global cpuidle driver variable. * @drv: a pointer to a struct cpuidle_driver * * Reset the global cpuidle variable to NULL. If @drv does not match the * registered driver, do nothing. */ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) { if (drv == cpuidle_curr_driver) cpuidle_curr_driver = NULL; } #endif /** * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer on a cpu * @arg: a void pointer used to match the SMP cross call API * * If @arg is NULL broadcast is disabled otherwise enabled * * This function is executed per CPU by an SMP cross call. It's not * supposed to be called directly. */ static void cpuidle_setup_broadcast_timer(void *arg) { if (arg) tick_broadcast_enable(); else tick_broadcast_disable(); } /** * __cpuidle_driver_init - initialize the driver's internal data * @drv: a valid pointer to a struct cpuidle_driver */ static void __cpuidle_driver_init(struct cpuidle_driver *drv) { int i; /* * Use all possible CPUs as the default, because if the kernel boots * with some CPUs offline and then we online one of them, the CPU * notifier has to know which driver to assign. */ if (!drv->cpumask) drv->cpumask = (struct cpumask *)cpu_possible_mask; for (i = 0; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; /* * Look for the timer stop flag in the different states and if * it is found, indicate that the broadcast timer has to be set * up. */ if (s->flags & CPUIDLE_FLAG_TIMER_STOP) drv->bctimer = 1; /* * The core will use the target residency and exit latency * values in nanoseconds, but allow drivers to provide them in * microseconds too. */ if (s->target_residency > 0) s->target_residency_ns = s->target_residency * NSEC_PER_USEC; else if (s->target_residency_ns < 0) s->target_residency_ns = 0; else s->target_residency = div_u64(s->target_residency_ns, NSEC_PER_USEC); if (s->exit_latency > 0) s->exit_latency_ns = mul_u32_u32(s->exit_latency, NSEC_PER_USEC); else if (s->exit_latency_ns < 0) s->exit_latency_ns = 0; else s->exit_latency = div_u64(s->exit_latency_ns, NSEC_PER_USEC); } } /** * __cpuidle_register_driver: register the driver * @drv: a valid pointer to a struct cpuidle_driver * * Do some sanity checks, initialize the driver, assign the driver to the * global cpuidle driver variable(s) and set up the broadcast timer if the * cpuidle driver has some states that shut down the local timer. * * Returns 0 on success, a negative error code otherwise: * * -EINVAL if the driver pointer is NULL or no idle states are available * * -ENODEV if the cpuidle framework is disabled * * -EBUSY if the driver is already assigned to the global variable(s) */ static int __cpuidle_register_driver(struct cpuidle_driver *drv) { int ret; if (!drv || !drv->state_count) return -EINVAL; ret = cpuidle_coupled_state_verify(drv); if (ret) return ret; if (cpuidle_disabled()) return -ENODEV; __cpuidle_driver_init(drv); ret = __cpuidle_set_driver(drv); if (ret) return ret; if (drv->bctimer) on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, (void *)1, 1); return 0; } /** * __cpuidle_unregister_driver - unregister the driver * @drv: a valid pointer to a struct cpuidle_driver * * Check if the driver is no longer in use, reset the global cpuidle driver * variable(s) and disable the timer broadcast notification mechanism if it was * in use. * */ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv) { if (drv->bctimer) { drv->bctimer = 0; on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, NULL, 1); } __cpuidle_unset_driver(drv); } /** * cpuidle_register_driver - registers a driver * @drv: a pointer to a valid struct cpuidle_driver * * Register the driver under a lock to prevent concurrent attempts to * [un]register the driver from occurring at the same time. * * Returns 0 on success, a negative error code (returned by * __cpuidle_register_driver()) otherwise. */ int cpuidle_register_driver(struct cpuidle_driver *drv) { struct cpuidle_governor *gov; int ret; spin_lock(&cpuidle_driver_lock); ret = __cpuidle_register_driver(drv); spin_unlock(&cpuidle_driver_lock); if (!ret && !strlen(param_governor) && drv->governor && (cpuidle_get_driver() == drv)) { mutex_lock(&cpuidle_lock); gov = cpuidle_find_governor(drv->governor); if (gov) { cpuidle_prev_governor = cpuidle_curr_governor; if (cpuidle_switch_governor(gov) < 0) cpuidle_prev_governor = NULL; } mutex_unlock(&cpuidle_lock); } return ret; } EXPORT_SYMBOL_GPL(cpuidle_register_driver); /** * cpuidle_unregister_driver - unregisters a driver * @drv: a pointer to a valid struct cpuidle_driver * * Unregisters the cpuidle driver under a lock to prevent concurrent attempts * to [un]register the driver from occurring at the same time. @drv has to * match the currently registered driver. */ void cpuidle_unregister_driver(struct cpuidle_driver *drv) { bool enabled = (cpuidle_get_driver() == drv); spin_lock(&cpuidle_driver_lock); __cpuidle_unregister_driver(drv); spin_unlock(&cpuidle_driver_lock); if (!enabled) return; mutex_lock(&cpuidle_lock); if (cpuidle_prev_governor) { if (!cpuidle_switch_governor(cpuidle_prev_governor)) cpuidle_prev_governor = NULL; } mutex_unlock(&cpuidle_lock); } EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); /** * cpuidle_get_driver - return the driver tied to the current CPU. * * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered. */ struct cpuidle_driver *cpuidle_get_driver(void) { struct cpuidle_driver *drv; int cpu; cpu = get_cpu(); drv = __cpuidle_get_cpu_driver(cpu); put_cpu(); return drv; } EXPORT_SYMBOL_GPL(cpuidle_get_driver); /** * cpuidle_get_cpu_driver - return the driver registered for a CPU. * @dev: a valid pointer to a struct cpuidle_device * * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered * for the CPU associated with @dev. */ struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev) { if (!dev) return NULL; return __cpuidle_get_cpu_driver(dev->cpu); } EXPORT_SYMBOL_GPL(cpuidle_get_cpu_driver); /** * cpuidle_driver_state_disabled - Disable or enable an idle state * @drv: cpuidle driver owning the state * @idx: State index * @disable: Whether or not to disable the state */ void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, bool disable) { unsigned int cpu; mutex_lock(&cpuidle_lock); spin_lock(&cpuidle_driver_lock); if (!drv->cpumask) { drv->states[idx].flags |= CPUIDLE_FLAG_UNUSABLE; goto unlock; } for_each_cpu(cpu, drv->cpumask) { struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); if (!dev) continue; if (disable) dev->states_usage[idx].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; else dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER; } unlock: spin_unlock(&cpuidle_driver_lock); mutex_unlock(&cpuidle_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H /* * Determines how hard direct compaction should try to succeed. * Lower value means higher priority, analogically to reclaim priority. */ enum compact_priority { COMPACT_PRIO_SYNC_FULL, MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL, COMPACT_PRIO_SYNC_LIGHT, MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, COMPACT_PRIO_ASYNC, INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC }; /* Return values for compact_zone() and try_to_compact_pages() */ /* When adding new states, please adjust include/trace/events/compaction.h */ enum compact_result { /* For more detailed tracepoint output - internal to compaction */ COMPACT_NOT_SUITABLE_ZONE, /* * compaction didn't start as it was not possible or direct reclaim * was more suitable */ COMPACT_SKIPPED, /* compaction didn't start as it was deferred due to past failures */ COMPACT_DEFERRED, /* For more detailed tracepoint output - internal to compaction */ COMPACT_NO_SUITABLE_PAGE, /* compaction should continue to another pageblock */ COMPACT_CONTINUE, /* * The full zone was compacted scanned but wasn't successful to compact * suitable pages. */ COMPACT_COMPLETE, /* * direct compaction has scanned part of the zone but wasn't successful * to compact suitable pages. */ COMPACT_PARTIAL_SKIPPED, /* compaction terminated prematurely due to lock contentions */ COMPACT_CONTENDED, /* * direct compaction terminated after concluding that the allocation * should now succeed */ COMPACT_SUCCESS, }; struct alloc_context; /* in mm/internal.h */ /* * Number of free order-0 pages that should be available above given watermark * to make sure compaction has reasonable chance of not running out of free * pages that it needs to isolate as migration target during its work. */ static inline unsigned long compact_gap(unsigned int order) { /* * Although all the isolations for migration are temporary, compaction * free scanner may have up to 1 << order pages on its list and then * try to split an (order - 1) free page. At that point, a gap of * 1 << order might not be enough, so it's safer to require twice that * amount. Note that the number of pages on the list is also * effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum * that the migrate scanner can have isolated on migrate list, and free * scanner is only invoked when the number of isolated free pages is * lower than that. But it's not worth to complicate the formula here * as a bigger gap for higher orders than strictly necessary can also * improve chances of compaction success. */ return 2UL << order; } static inline int current_is_kcompactd(void) { return current->flags & PF_KCOMPACTD; } #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern bool compaction_suitable(struct zone *zone, int order, unsigned long watermark, int highest_zoneidx); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); extern void __meminit kcompactd_run(int nid); extern void __meminit kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else static inline void reset_isolation_suitable(pg_data_t *pgdat) { } static inline bool compaction_suitable(struct zone *zone, int order, unsigned long watermark, int highest_zoneidx) { return false; } static inline void kcompactd_run(int nid) { } static inline void kcompactd_stop(int nid) { } static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) { } #endif /* CONFIG_COMPACTION */ struct node; #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) extern int compaction_register_node(struct node *node); extern void compaction_unregister_node(struct node *node); #else static inline int compaction_register_node(struct node *node) { return 0; } static inline void compaction_unregister_node(struct node *node) { } #endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */ #endif /* _LINUX_COMPACTION_H */ |
| 2930 2923 2927 2926 2770 295 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef MM_SLAB_H #define MM_SLAB_H #include <linux/reciprocal_div.h> #include <linux/list_lru.h> #include <linux/local_lock.h> #include <linux/random.h> #include <linux/kobject.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <linux/kfence.h> #include <linux/kasan.h> /* * Internal slab definitions */ #ifdef CONFIG_64BIT # ifdef system_has_cmpxchg128 # define system_has_freelist_aba() system_has_cmpxchg128() # define try_cmpxchg_freelist try_cmpxchg128 # endif #define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg128 typedef u128 freelist_full_t; #else /* CONFIG_64BIT */ # ifdef system_has_cmpxchg64 # define system_has_freelist_aba() system_has_cmpxchg64() # define try_cmpxchg_freelist try_cmpxchg64 # endif #define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg64 typedef u64 freelist_full_t; #endif /* CONFIG_64BIT */ #if defined(system_has_freelist_aba) && !defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) #undef system_has_freelist_aba #endif /* * Freelist pointer and counter to cmpxchg together, avoids the typical ABA * problems with cmpxchg of just a pointer. */ typedef union { struct { void *freelist; unsigned long counter; }; freelist_full_t full; } freelist_aba_t; /* Reuses the bits in struct page */ struct slab { unsigned long __page_flags; struct kmem_cache *slab_cache; union { struct { union { struct list_head slab_list; #ifdef CONFIG_SLUB_CPU_PARTIAL struct { struct slab *next; int slabs; /* Nr of slabs left */ }; #endif }; /* Double-word boundary */ union { struct { void *freelist; /* first free object */ union { unsigned long counters; struct { unsigned inuse:16; unsigned objects:15; /* * If slab debugging is enabled then the * frozen bit can be reused to indicate * that the slab was corrupted */ unsigned frozen:1; }; }; }; #ifdef system_has_freelist_aba freelist_aba_t freelist_counter; #endif }; }; struct rcu_head rcu_head; }; unsigned int __page_type; atomic_t __page_refcount; #ifdef CONFIG_SLAB_OBJ_EXT unsigned long obj_exts; #endif }; #define SLAB_MATCH(pg, sl) \ static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl)) SLAB_MATCH(flags, __page_flags); SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */ SLAB_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG SLAB_MATCH(memcg_data, obj_exts); #elif defined(CONFIG_SLAB_OBJ_EXT) SLAB_MATCH(_unused_slab_obj_exts, obj_exts); #endif #undef SLAB_MATCH static_assert(sizeof(struct slab) <= sizeof(struct page)); #if defined(system_has_freelist_aba) static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t))); #endif /** * folio_slab - Converts from folio to slab. * @folio: The folio. * * Currently struct slab is a different representation of a folio where * folio_test_slab() is true. * * Return: The slab which contains this folio. */ #define folio_slab(folio) (_Generic((folio), \ const struct folio *: (const struct slab *)(folio), \ struct folio *: (struct slab *)(folio))) /** * slab_folio - The folio allocated for a slab * @s: The slab. * * Slabs are allocated as folios that contain the individual objects and are * using some fields in the first struct page of the folio - those fields are * now accessed by struct slab. It is occasionally necessary to convert back to * a folio in order to communicate with the rest of the mm. Please use this * helper function instead of casting yourself, as the implementation may change * in the future. */ #define slab_folio(s) (_Generic((s), \ const struct slab *: (const struct folio *)s, \ struct slab *: (struct folio *)s)) /** * page_slab - Converts from first struct page to slab. * @p: The first (either head of compound or single) page of slab. * * A temporary wrapper to convert struct page to struct slab in situations where * we know the page is the compound head, or single order-0 page. * * Long-term ideally everything would work with struct slab directly or go * through folio to struct slab. * * Return: The slab which contains this page */ #define page_slab(p) (_Generic((p), \ const struct page *: (const struct slab *)(p), \ struct page *: (struct slab *)(p))) /** * slab_page - The first struct page allocated for a slab * @s: The slab. * * A convenience wrapper for converting slab to the first struct page of the * underlying folio, to communicate with code not yet converted to folio or * struct slab. */ #define slab_page(s) folio_page(slab_folio(s), 0) /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. */ static inline bool slab_test_pfmemalloc(const struct slab *slab) { return folio_test_active(slab_folio(slab)); } static inline void slab_set_pfmemalloc(struct slab *slab) { folio_set_active(slab_folio(slab)); } static inline void slab_clear_pfmemalloc(struct slab *slab) { folio_clear_active(slab_folio(slab)); } static inline void __slab_clear_pfmemalloc(struct slab *slab) { __folio_clear_active(slab_folio(slab)); } static inline void *slab_address(const struct slab *slab) { return folio_address(slab_folio(slab)); } static inline int slab_nid(const struct slab *slab) { return folio_nid(slab_folio(slab)); } static inline pg_data_t *slab_pgdat(const struct slab *slab) { return folio_pgdat(slab_folio(slab)); } static inline struct slab *virt_to_slab(const void *addr) { struct folio *folio = virt_to_folio(addr); if (!folio_test_slab(folio)) return NULL; return folio_slab(folio); } static inline int slab_order(const struct slab *slab) { return folio_order(slab_folio(slab)); } static inline size_t slab_size(const struct slab *slab) { return PAGE_SIZE << slab_order(slab); } #ifdef CONFIG_SLUB_CPU_PARTIAL #define slub_percpu_partial(c) ((c)->partial) #define slub_set_percpu_partial(c, p) \ ({ \ slub_percpu_partial(c) = (p)->next; \ }) #define slub_percpu_partial_read_once(c) READ_ONCE(slub_percpu_partial(c)) #else #define slub_percpu_partial(c) NULL #define slub_set_percpu_partial(c, p) #define slub_percpu_partial_read_once(c) NULL #endif // CONFIG_SLUB_CPU_PARTIAL /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the * given order would contain. */ struct kmem_cache_order_objects { unsigned int x; }; /* * Slab cache management. */ struct kmem_cache { #ifndef CONFIG_SLUB_TINY struct kmem_cache_cpu __percpu *cpu_slab; #endif /* Used for retrieving partial slabs, etc. */ slab_flags_t flags; unsigned long min_partial; unsigned int size; /* Object size including metadata */ unsigned int object_size; /* Object size without metadata */ struct reciprocal_value reciprocal_size; unsigned int offset; /* Free pointer offset */ #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; /* Number of per cpu partial slabs to keep around */ unsigned int cpu_partial_slabs; #endif struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ void (*ctor)(void *object); /* Object constructor */ unsigned int inuse; /* Offset to metadata */ unsigned int align; /* Alignment */ unsigned int red_left_pad; /* Left redzone padding size */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ #endif #ifdef CONFIG_SLAB_FREELIST_HARDENED unsigned long random; #endif #ifdef CONFIG_NUMA /* * Defragmentation by allocating from a remote node. */ unsigned int remote_node_defrag_ratio; #endif #ifdef CONFIG_SLAB_FREELIST_RANDOM unsigned int *random_seq; #endif #ifdef CONFIG_KASAN_GENERIC struct kasan_cache kasan_info; #endif #ifdef CONFIG_HARDENED_USERCOPY unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ #endif struct kmem_cache_node *node[MAX_NUMNODES]; }; #if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY) #define SLAB_SUPPORTS_SYSFS 1 void sysfs_slab_unlink(struct kmem_cache *s); void sysfs_slab_release(struct kmem_cache *s); #else static inline void sysfs_slab_unlink(struct kmem_cache *s) { } static inline void sysfs_slab_release(struct kmem_cache *s) { } #endif void *fixup_red_left(struct kmem_cache *s, void *p); static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { void *object = x - (x - slab_address(slab)) % cache->size; void *last_object = slab_address(slab) + (slab->objects - 1) * cache->size; void *result = (unlikely(object > last_object)) ? last_object : object; result = fixup_red_left(cache, result); return result; } /* Determine object index from a given position */ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, void *addr, void *obj) { return reciprocal_divide(kasan_reset_tag(obj) - addr, cache->reciprocal_size); } static inline unsigned int obj_to_index(const struct kmem_cache *cache, const struct slab *slab, void *obj) { if (is_kfence_address(obj)) return 0; return __obj_to_index(cache, slab_address(slab), obj); } static inline int objs_per_slab(const struct kmem_cache *cache, const struct slab *slab) { return slab->objects; } /* * State of the slab allocator. * * This is used to describe the states of the allocator during bootup. * Allocators use this to gradually bootstrap themselves. Most allocators * have the problem that the structures used for managing slab caches are * allocated from slab caches themselves. */ enum slab_state { DOWN, /* No slab functionality yet */ PARTIAL, /* SLUB: kmem_cache_node available */ UP, /* Slab caches usable but not all extras yet */ FULL /* Everything is working */ }; extern enum slab_state slab_state; /* The slab cache mutex protects the management structures during changes */ extern struct mutex slab_mutex; /* The list of all slab caches on the system */ extern struct list_head slab_caches; /* The slab cache that manages slab cache information */ extern struct kmem_cache *kmem_cache; /* A table of kmalloc cache names and sizes */ extern const struct kmalloc_info_struct { const char *name[NR_KMALLOC_TYPES]; unsigned int size; } kmalloc_info[]; /* Kmalloc array related functions */ void setup_kmalloc_cache_index_table(void); void create_kmalloc_caches(void); extern u8 kmalloc_size_index[24]; static inline unsigned int size_index_elem(unsigned int bytes) { return (bytes - 1) / 8; } /* * Find the kmem_cache structure that serves a given size of * allocation * * This assumes size is larger than zero and not larger than * KMALLOC_MAX_CACHE_SIZE and the caller must check that. */ static inline struct kmem_cache * kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, unsigned long caller) { unsigned int index; if (!b) b = &kmalloc_caches[kmalloc_type(flags, caller)]; if (size <= 192) index = kmalloc_size_index[size_index_elem(size)]; else index = fls(size - 1); return (*b)[index]; } gfp_t kmalloc_fix_flags(gfp_t flags); /* Functions provided by the slab allocators */ int do_kmem_cache_create(struct kmem_cache *s, const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags); void __init kmem_cache_init(void); extern void create_boot_cache(struct kmem_cache *, const char *name, unsigned int size, slab_flags_t flags, unsigned int useroffset, unsigned int usersize); int slab_unmergeable(struct kmem_cache *s); struct kmem_cache *find_mergeable(unsigned size, unsigned align, slab_flags_t flags, const char *name, void (*ctor)(void *)); struct kmem_cache * __kmem_cache_alias(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); slab_flags_t kmem_cache_flags(slab_flags_t flags, const char *name); static inline bool is_kmalloc_cache(struct kmem_cache *s) { return (s->flags & SLAB_KMALLOC); } static inline bool is_kmalloc_normal(struct kmem_cache *s) { if (!is_kmalloc_cache(s)) return false; return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); } #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ SLAB_CACHE_DMA32 | SLAB_PANIC | \ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS | \ SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ SLAB_TEMPORARY | SLAB_ACCOUNT | \ SLAB_NO_USER_FLAGS | SLAB_KMALLOC | SLAB_NO_MERGE) #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ SLAB_TRACE | SLAB_CONSISTENCY_CHECKS) #define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS) bool __kmem_cache_empty(struct kmem_cache *); int __kmem_cache_shutdown(struct kmem_cache *); void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *); void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; struct file; struct slabinfo { unsigned long active_objs; unsigned long num_objs; unsigned long active_slabs; unsigned long num_slabs; unsigned long shared_avail; unsigned int limit; unsigned int batchcount; unsigned int shared; unsigned int objects_per_slab; unsigned int cache_order; }; void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo); #ifdef CONFIG_SLUB_DEBUG #ifdef CONFIG_SLUB_DEBUG_ON DECLARE_STATIC_KEY_TRUE(slub_debug_enabled); #else DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); long validate_slab_cache(struct kmem_cache *s); static inline bool __slub_debug_enabled(void) { return static_branch_unlikely(&slub_debug_enabled); } #else static inline void print_tracking(struct kmem_cache *s, void *object) { } static inline bool __slub_debug_enabled(void) { return false; } #endif /* * Returns true if any of the specified slab_debug flags is enabled for the * cache. Use only for flags parsed by setup_slub_debug() as it also enables * the static key. */ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags) { if (IS_ENABLED(CONFIG_SLUB_DEBUG)) VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); if (__slub_debug_enabled()) return s->flags & flags; return false; } #if IS_ENABLED(CONFIG_SLUB_DEBUG) && IS_ENABLED(CONFIG_KUNIT) bool slab_in_kunit_test(void); #else static inline bool slab_in_kunit_test(void) { return false; } #endif #ifdef CONFIG_SLAB_OBJ_EXT /* * slab_obj_exts - get the pointer to the slab object extension vector * associated with a slab. * @slab: a pointer to the slab struct * * Returns a pointer to the object extension vector associated with the slab, * or NULL if no such vector has been associated yet. */ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { unsigned long obj_exts = READ_ONCE(slab->obj_exts); #ifdef CONFIG_MEMCG VM_BUG_ON_PAGE(obj_exts && !(obj_exts & MEMCG_DATA_OBJEXTS), slab_page(slab)); VM_BUG_ON_PAGE(obj_exts & MEMCG_DATA_KMEM, slab_page(slab)); #endif return (struct slabobj_ext *)(obj_exts & ~OBJEXTS_FLAGS_MASK); } int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, bool new_slab); #else /* CONFIG_SLAB_OBJ_EXT */ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { return NULL; } #endif /* CONFIG_SLAB_OBJ_EXT */ static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s) { return (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B; } #ifdef CONFIG_MEMCG bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, gfp_t flags, size_t size, void **p); void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, int objects, struct slabobj_ext *obj_exts); #endif void kvfree_rcu_cb(struct rcu_head *head); size_t __ksize(const void *objp); static inline size_t slab_ksize(const struct kmem_cache *s) { #ifdef CONFIG_SLUB_DEBUG /* * Debugging requires use of the padding between object * and whatever may come after it. */ if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) return s->object_size; #endif if (s->flags & SLAB_KASAN) return s->object_size; /* * If we have the need to store the freelist pointer * back there or track user information then we can * only use the space before that information. */ if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) return s->inuse; /* * Else we can use all the padding etc for the allocation */ return s->size; } #ifdef CONFIG_SLUB_DEBUG void dump_unreclaimable_slab(void); #else static inline void dump_unreclaimable_slab(void) { } #endif void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr); #ifdef CONFIG_SLAB_FREELIST_RANDOM int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, gfp_t gfp); void cache_random_seq_destroy(struct kmem_cache *cachep); #else static inline int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, gfp_t gfp) { return 0; } static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } #endif /* CONFIG_SLAB_FREELIST_RANDOM */ static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) { if (c->ctor) return false; if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) return flags & __GFP_ZERO; return true; } return flags & __GFP_ZERO; } static inline bool slab_want_init_on_free(struct kmem_cache *c) { if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free)) return !(c->ctor || (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))); return false; } #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) void debugfs_slab_release(struct kmem_cache *); #else static inline void debugfs_slab_release(struct kmem_cache *s) { } #endif #ifdef CONFIG_PRINTK #define KS_ADDRS_COUNT 16 struct kmem_obj_info { void *kp_ptr; struct slab *kp_slab; void *kp_objp; unsigned long kp_data_offset; struct kmem_cache *kp_slab_cache; void *kp_ret; void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif void __check_heap_object(const void *ptr, unsigned long n, const struct slab *slab, bool to_user); static inline bool slub_debug_orig_size(struct kmem_cache *s) { return (kmem_cache_debug_flags(s, SLAB_STORE_USER) && (s->flags & SLAB_KMALLOC)); } #ifdef CONFIG_SLUB_DEBUG void skip_orig_size_check(struct kmem_cache *s, const void *object); #endif #endif /* MM_SLAB_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017 Google, Inc. */ #ifndef _LINUX_BINDER_ALLOC_H #define _LINUX_BINDER_ALLOC_H #include <linux/rbtree.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/rtmutex.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/list_lru.h> #include <uapi/linux/android/binder.h> extern struct list_lru binder_freelist; struct binder_transaction; /** * struct binder_buffer - buffer used for binder transactions * @entry: entry alloc->buffers * @rb_node: node for allocated_buffers/free_buffers rb trees * @free: %true if buffer is free * @clear_on_free: %true if buffer must be zeroed after use * @allow_user_free: %true if user is allowed to free buffer * @async_transaction: %true if buffer is in use for an async txn * @oneway_spam_suspect: %true if total async allocate size just exceed * spamming detect threshold * @debug_id: unique ID for debugging * @transaction: pointer to associated struct binder_transaction * @target_node: struct binder_node associated with this buffer * @data_size: size of @transaction data * @offsets_size: size of array of offsets * @extra_buffers_size: size of space for other objects (like sg lists) * @user_data: user pointer to base of buffer space * @pid: pid to attribute the buffer to (caller) * * Bookkeeping structure for binder transaction buffers */ struct binder_buffer { struct list_head entry; /* free and allocated entries by address */ struct rb_node rb_node; /* free entry by size or allocated entry */ /* by address */ unsigned free:1; unsigned clear_on_free:1; unsigned allow_user_free:1; unsigned async_transaction:1; unsigned oneway_spam_suspect:1; unsigned debug_id:27; struct binder_transaction *transaction; struct binder_node *target_node; size_t data_size; size_t offsets_size; size_t extra_buffers_size; unsigned long user_data; int pid; }; /** * struct binder_shrinker_mdata - binder metadata used to reclaim pages * @lru: LRU entry in binder_freelist * @alloc: binder_alloc owning the page to reclaim * @page_index: offset in @alloc->pages[] into the page to reclaim */ struct binder_shrinker_mdata { struct list_head lru; struct binder_alloc *alloc; unsigned long page_index; }; static inline struct list_head *page_to_lru(struct page *p) { struct binder_shrinker_mdata *mdata; mdata = (struct binder_shrinker_mdata *)page_private(p); return &mdata->lru; } /** * struct binder_alloc - per-binder proc state for binder allocator * @mutex: protects binder_alloc fields * @mm: copy of task->mm (invariant after open) * @vm_start: base of per-proc address space mapped via mmap * @buffers: list of all buffers for this proc * @free_buffers: rb tree of buffers available for allocation * sorted by size * @allocated_buffers: rb tree of allocated buffers sorted by address * @free_async_space: VA space available for async buffers. This is * initialized at mmap time to 1/2 the full VA space * @pages: array of struct page * * @buffer_size: size of address space specified via mmap * @pid: pid for associated binder_proc (invariant after init) * @pages_high: high watermark of offset in @pages * @mapped: whether the vm area is mapped, each binder instance is * allowed a single mapping throughout its lifetime * @oneway_spam_detected: %true if oneway spam detection fired, clear that * flag once the async buffer has returned to a healthy state * * Bookkeeping structure for per-proc address space management for binder * buffers. It is normally initialized during binder_init() and binder_mmap() * calls. The address space is used for both user-visible buffers and for * struct binder_buffer objects used to track the user buffers */ struct binder_alloc { struct mutex mutex; struct mm_struct *mm; unsigned long vm_start; struct list_head buffers; struct rb_root free_buffers; struct rb_root allocated_buffers; size_t free_async_space; struct page **pages; size_t buffer_size; int pid; size_t pages_high; bool mapped; bool oneway_spam_detected; }; #ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST void binder_selftest_alloc(struct binder_alloc *alloc); #else static inline void binder_selftest_alloc(struct binder_alloc *alloc) {} #endif enum lru_status binder_alloc_free_page(struct list_head *item, struct list_lru_one *lru, void *cb_arg); struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, size_t data_size, size_t offsets_size, size_t extra_buffers_size, int is_async); void binder_alloc_init(struct binder_alloc *alloc); int binder_alloc_shrinker_init(void); void binder_alloc_shrinker_exit(void); void binder_alloc_vma_close(struct binder_alloc *alloc); struct binder_buffer * binder_alloc_prepare_to_free(struct binder_alloc *alloc, unsigned long user_ptr); void binder_alloc_free_buf(struct binder_alloc *alloc, struct binder_buffer *buffer); int binder_alloc_mmap_handler(struct binder_alloc *alloc, struct vm_area_struct *vma); void binder_alloc_deferred_release(struct binder_alloc *alloc); int binder_alloc_get_allocated_count(struct binder_alloc *alloc); void binder_alloc_print_allocated(struct seq_file *m, struct binder_alloc *alloc); void binder_alloc_print_pages(struct seq_file *m, struct binder_alloc *alloc); /** * binder_alloc_get_free_async_space() - get free space available for async * @alloc: binder_alloc for this proc * * Return: the bytes remaining in the address-space for async transactions */ static inline size_t binder_alloc_get_free_async_space(struct binder_alloc *alloc) { size_t free_async_space; mutex_lock(&alloc->mutex); free_async_space = alloc->free_async_space; mutex_unlock(&alloc->mutex); return free_async_space; } unsigned long binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc, struct binder_buffer *buffer, binder_size_t buffer_offset, const void __user *from, size_t bytes); int binder_alloc_copy_to_buffer(struct binder_alloc *alloc, struct binder_buffer *buffer, binder_size_t buffer_offset, void *src, size_t bytes); int binder_alloc_copy_from_buffer(struct binder_alloc *alloc, void *dest, struct binder_buffer *buffer, binder_size_t buffer_offset, size_t bytes); #endif /* _LINUX_BINDER_ALLOC_H */ |
| 5 5 5 2 2 2 2 2 2 2 1 1 1 1 1 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | // SPDX-License-Identifier: GPL-2.0 /* * Handle caching attributes in page tables (PAT) * * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * Suresh B Siddha <suresh.b.siddha@intel.com> * * Interval tree used to store the PAT memory type reservations. */ #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/interval_tree_generic.h> #include <linux/sched.h> #include <linux/gfp.h> #include <linux/pgtable.h> #include <asm/memtype.h> #include "memtype.h" /* * The memtype tree keeps track of memory type for specific * physical memory areas. Without proper tracking, conflicting memory * types in different mappings can cause CPU cache corruption. * * The tree is an interval tree (augmented rbtree) which tree is ordered * by the starting address. The tree can contain multiple entries for * different regions which overlap. All the aliases have the same * cache attributes of course, as enforced by the PAT logic. * * memtype_lock protects the rbtree. */ static inline u64 interval_start(struct memtype *entry) { return entry->start; } static inline u64 interval_end(struct memtype *entry) { return entry->end - 1; } INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end, interval_start, interval_end, static, interval) static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED; static int memtype_check_conflict(u64 start, u64 end, enum page_cache_mode reqtype, enum page_cache_mode *newtype) { struct memtype *entry_match; enum page_cache_mode found_type = reqtype; entry_match = interval_iter_first(&memtype_rbroot, start, end-1); if (entry_match == NULL) goto success; if (entry_match->type != found_type && newtype == NULL) goto failure; dprintk("Overlap at 0x%Lx-0x%Lx\n", entry_match->start, entry_match->end); found_type = entry_match->type; entry_match = interval_iter_next(entry_match, start, end-1); while (entry_match) { if (entry_match->type != found_type) goto failure; entry_match = interval_iter_next(entry_match, start, end-1); } success: if (newtype) *newtype = found_type; return 0; failure: pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", current->comm, current->pid, start, end, cattr_name(found_type), cattr_name(entry_match->type)); return -EBUSY; } int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_type) { int err = 0; err = memtype_check_conflict(entry_new->start, entry_new->end, entry_new->type, ret_type); if (err) return err; if (ret_type) entry_new->type = *ret_type; interval_insert(entry_new, &memtype_rbroot); return 0; } struct memtype *memtype_erase(u64 start, u64 end) { struct memtype *entry = interval_iter_first(&memtype_rbroot, start, end - 1); while (entry && entry->start < end) { if (entry->start == start && entry->end == end) { interval_remove(entry, &memtype_rbroot); return entry; } entry = interval_iter_next(entry, start, end - 1); } return ERR_PTR(-EINVAL); } struct memtype *memtype_lookup(u64 addr) { return interval_iter_first(&memtype_rbroot, addr, addr + PAGE_SIZE-1); } /* * Debugging helper, copy the Nth entry of the tree into a * a copy for printout. This allows us to print out the tree * via debugfs, without holding the memtype_lock too long: */ #ifdef CONFIG_DEBUG_FS int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos) { struct memtype *entry_match; int i = 1; entry_match = interval_iter_first(&memtype_rbroot, 0, ULONG_MAX); while (entry_match && pos != i) { entry_match = interval_iter_next(entry_match, 0, ULONG_MAX); i++; } if (entry_match) { /* pos == i */ *entry_out = *entry_match; return 0; } else { return 1; } } #endif |
| 4249 4248 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM workqueue #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WORKQUEUE_H #include <linux/tracepoint.h> #include <linux/workqueue.h> struct pool_workqueue; /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a * delayed work is actually queued on a workqueue (ie: once the delay * has been reached). */ TRACE_EVENT(workqueue_queue_work, TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) __field( int, req_cpu ) __field( int, cpu ) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __assign_str(workqueue); __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); /** * workqueue_activate_work - called when a work gets activated * @work: pointer to struct work_struct * * This event occurs when a queued work is put on the active queue, * which happens immediately after queueing unless @max_active limit * is reached. */ TRACE_EVENT(workqueue_activate_work, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p function=%ps ", __entry->work, __entry->function) ); /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_end, TP_PROTO(struct work_struct *work, work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); #endif /* _TRACE_WORKQUEUE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/truncate.h * * Common inline functions needed for truncate support */ /* * Truncate blocks that were not used by write. We have to truncate the * pagecache as well so that corresponding buffers get properly unmapped. */ static inline void ext4_truncate_failed_write(struct inode *inode) { struct address_space *mapping = inode->i_mapping; /* * We don't need to call ext4_break_layouts() because the blocks we * are truncating were never visible to userspace. */ filemap_invalidate_lock(mapping); truncate_inode_pages(mapping, inode->i_size); ext4_truncate(inode); filemap_invalidate_unlock(mapping); } /* * Work out how many blocks we need to proceed with the next chunk of a * truncate transaction. */ static inline unsigned long ext4_blocks_for_truncate(struct inode *inode) { ext4_lblk_t needed; needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); /* Give ourselves just enough room to cope with inodes in which * i_blocks is corrupt: we've seen disk corruptions in the past * which resulted in random data in an inode which looked enough * like a regular file for ext4 to try to delete it. Things * will go a bit crazy if that happens, but at least we should * try not to panic the whole kernel. */ if (needed < 2) needed = 2; /* But we need to bound the transaction so we don't overflow the * journal. */ if (needed > EXT4_MAX_TRANS_DATA) needed = EXT4_MAX_TRANS_DATA; return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; } |
| 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: hwvalid - I/O request validation * * Copyright (C) 2000 - 2025, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #define _COMPONENT ACPI_HARDWARE ACPI_MODULE_NAME("hwvalid") /* Local prototypes */ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width); /* * Protected I/O ports. Some ports are always illegal, and some are * conditionally illegal. This table must remain ordered by port address. * * The table is used to implement the Microsoft port access rules that * first appeared in Windows XP. Some ports are always illegal, and some * ports are only illegal if the BIOS calls _OSI with nothing newer than * the specific _OSI strings. * * This provides ACPICA with the desired port protections and * Microsoft compatibility. * * Description of port entries: * DMA: DMA controller * PIC0: Programmable Interrupt Controller (8259A) * PIT1: System Timer 1 * PIT2: System Timer 2 failsafe * RTC: Real-time clock * CMOS: Extended CMOS * DMA1: DMA 1 page registers * DMA1L: DMA 1 Ch 0 low page * DMA2: DMA 2 page registers * DMA2L: DMA 2 low page refresh * ARBC: Arbitration control * SETUP: Reserved system board setup * POS: POS channel select * PIC1: Cascaded PIC * IDMA: ISA DMA * ELCR: PIC edge/level registers * PCI: PCI configuration space */ static const struct acpi_port_info acpi_protected_ports[] = { {"DMA", 0x0000, 0x000F, ACPI_OSI_WIN_XP}, {"PIC0", 0x0020, 0x0021, ACPI_ALWAYS_ILLEGAL}, {"PIT1", 0x0040, 0x0043, ACPI_OSI_WIN_XP}, {"PIT2", 0x0048, 0x004B, ACPI_OSI_WIN_XP}, {"RTC", 0x0070, 0x0071, ACPI_OSI_WIN_XP}, {"CMOS", 0x0074, 0x0076, ACPI_OSI_WIN_XP}, {"DMA1", 0x0081, 0x0083, ACPI_OSI_WIN_XP}, {"DMA1L", 0x0087, 0x0087, ACPI_OSI_WIN_XP}, {"DMA2", 0x0089, 0x008B, ACPI_OSI_WIN_XP}, {"DMA2L", 0x008F, 0x008F, ACPI_OSI_WIN_XP}, {"ARBC", 0x0090, 0x0091, ACPI_OSI_WIN_XP}, {"SETUP", 0x0093, 0x0094, ACPI_OSI_WIN_XP}, {"POS", 0x0096, 0x0097, ACPI_OSI_WIN_XP}, {"PIC1", 0x00A0, 0x00A1, ACPI_ALWAYS_ILLEGAL}, {"IDMA", 0x00C0, 0x00DF, ACPI_OSI_WIN_XP}, {"ELCR", 0x04D0, 0x04D1, ACPI_ALWAYS_ILLEGAL}, {"PCI", 0x0CF8, 0x0CFF, ACPI_OSI_WIN_XP} }; #define ACPI_PORT_INFO_ENTRIES ACPI_ARRAY_LENGTH (acpi_protected_ports) /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_request * * PARAMETERS: Address Address of I/O port/register * bit_width Number of bits (8,16,32) * * RETURN: Status * * DESCRIPTION: Validates an I/O request (address/length). Certain ports are * always illegal and some ports are only illegal depending on * the requests the BIOS AML code makes to the predefined * _OSI method. * ******************************************************************************/ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) { u32 i; u32 byte_width; acpi_io_address last_address; const struct acpi_port_info *port_info; ACPI_FUNCTION_TRACE(hw_validate_io_request); /* Supported widths are 8/16/32 */ if ((bit_width != 8) && (bit_width != 16) && (bit_width != 32)) { ACPI_ERROR((AE_INFO, "Bad BitWidth parameter: %8.8X", bit_width)); return_ACPI_STATUS(AE_BAD_PARAMETER); } port_info = acpi_protected_ports; byte_width = ACPI_DIV_8(bit_width); last_address = address + byte_width - 1; ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X", ACPI_FORMAT_UINT64(address), ACPI_FORMAT_UINT64(last_address), byte_width)); /* Maximum 16-bit address in I/O space */ if (last_address > ACPI_UINT16_MAX) { ACPI_ERROR((AE_INFO, "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X", ACPI_FORMAT_UINT64(address), byte_width)); return_ACPI_STATUS(AE_LIMIT); } /* Exit if requested address is not within the protected port table */ if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) { return_ACPI_STATUS(AE_OK); } /* Check request against the list of protected I/O ports */ for (i = 0; i < ACPI_PORT_INFO_ENTRIES; i++, port_info++) { /* * Check if the requested address range will write to a reserved * port. There are four cases to consider: * * 1) Address range is contained completely in the port address range * 2) Address range overlaps port range at the port range start * 3) Address range overlaps port range at the port range end * 4) Address range completely encompasses the port range */ if ((address <= port_info->end) && (last_address >= port_info->start)) { /* Port illegality may depend on the _OSI calls made by the BIOS */ if (port_info->osi_dependency == ACPI_ALWAYS_ILLEGAL || acpi_gbl_osi_data == port_info->osi_dependency) { ACPI_DEBUG_PRINT((ACPI_DB_VALUES, "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)\n", ACPI_FORMAT_UINT64(address), byte_width, port_info->name, port_info->start, port_info->end)); return_ACPI_STATUS(AE_AML_ILLEGAL_ADDRESS); } } /* Finished if address range ends before the end of this port */ if (last_address <= port_info->end) { break; } } return_ACPI_STATUS(AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_read_port * * PARAMETERS: Address Address of I/O port/register to read * Value Where value (data) is returned * Width Number of bits * * RETURN: Status and value read from port * * DESCRIPTION: Read data from an I/O port or register. This is a front-end * to acpi_os_read_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_read_port(acpi_io_address address, u32 *value, u32 width) { acpi_status status; u32 one_byte; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_read_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0, *value = 0; i < width; i += 8) { /* Validate and read one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_read_port(address, &one_byte, 8); if (ACPI_FAILURE(status)) { return (status); } *value |= (one_byte << i); } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_write_port * * PARAMETERS: Address Address of I/O port/register to write * Value Value to write * Width Number of bits * * RETURN: Status * * DESCRIPTION: Write data to an I/O port or register. This is a front-end * to acpi_os_write_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_write_port(acpi_io_address address, u32 value, u32 width) { acpi_status status; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_write_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0; i < width; i += 8) { /* Validate and write one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_write_port(address, (value >> i) & 0xFF, 8); if (ACPI_FAILURE(status)) { return (status); } } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_block * * PARAMETERS: Address Address of I/O port/register blobk * bit_width Number of bits (8,16,32) in each register * count Number of registers in the block * * RETURN: Status * * DESCRIPTION: Validates a block of I/O ports/registers. * ******************************************************************************/ acpi_status acpi_hw_validate_io_block(u64 address, u32 bit_width, u32 count) { acpi_status status; while (count--) { status = acpi_hw_validate_io_request((acpi_io_address)address, bit_width); if (ACPI_FAILURE(status)) return_ACPI_STATUS(status); address += ACPI_DIV_8(bit_width); } return_ACPI_STATUS(AE_OK); } |
| 2 2 2 2 2 1 1 1 2 42 42 42 42 42 42 42 42 42 42 42 42 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 IBM Corporation * * Author: Cedric Le Goater <clg@fr.ibm.com> */ #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/sysctl.h> #include <linux/stat.h> #include <linux/capability.h> #include <linux/slab.h> #include <linux/cred.h> static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; static const struct ctl_table mq_sysctls[] = { { .procname = "queues_max", .data = &init_ipc_ns.mq_queues_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "msg_max", .data = &init_ipc_ns.mq_msg_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_max_limit_min, .extra2 = &msg_max_limit_max, }, { .procname = "msgsize_max", .data = &init_ipc_ns.mq_msgsize_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, { .procname = "msg_default", .data = &init_ipc_ns.mq_msg_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_max_limit_min, .extra2 = &msg_max_limit_max, }, { .procname = "msgsize_default", .data = &init_ipc_ns.mq_msgsize_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, }; static struct ctl_table_set *set_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->ipc_ns->mq_set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->ipc_ns->mq_set == set; } static void mq_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct ipc_namespace *ns = container_of(head->set, struct ipc_namespace, mq_set); kuid_t ns_root_uid = make_kuid(ns->user_ns, 0); kgid_t ns_root_gid = make_kgid(ns->user_ns, 0); *uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID; *gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID; } static int mq_permissions(struct ctl_table_header *head, const struct ctl_table *table) { int mode = table->mode; kuid_t ns_root_uid; kgid_t ns_root_gid; mq_set_ownership(head, &ns_root_uid, &ns_root_gid); if (uid_eq(current_euid(), ns_root_uid)) mode >>= 6; else if (in_egroup_p(ns_root_gid)) mode >>= 3; mode &= 7; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = mq_permissions, .set_ownership = mq_set_ownership, }; bool setup_mq_sysctls(struct ipc_namespace *ns) { struct ctl_table *tbl; setup_sysctl_set(&ns->mq_set, &set_root, set_is_seen); tbl = kmemdup(mq_sysctls, sizeof(mq_sysctls), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < ARRAY_SIZE(mq_sysctls); i++) { if (tbl[i].data == &init_ipc_ns.mq_queues_max) tbl[i].data = &ns->mq_queues_max; else if (tbl[i].data == &init_ipc_ns.mq_msg_max) tbl[i].data = &ns->mq_msg_max; else if (tbl[i].data == &init_ipc_ns.mq_msgsize_max) tbl[i].data = &ns->mq_msgsize_max; else if (tbl[i].data == &init_ipc_ns.mq_msg_default) tbl[i].data = &ns->mq_msg_default; else if (tbl[i].data == &init_ipc_ns.mq_msgsize_default) tbl[i].data = &ns->mq_msgsize_default; else tbl[i].data = NULL; } ns->mq_sysctls = __register_sysctl_table(&ns->mq_set, "fs/mqueue", tbl, ARRAY_SIZE(mq_sysctls)); } if (!ns->mq_sysctls) { kfree(tbl); retire_sysctl_set(&ns->mq_set); return false; } return true; } void retire_mq_sysctls(struct ipc_namespace *ns) { const struct ctl_table *tbl; tbl = ns->mq_sysctls->ctl_table_arg; unregister_sysctl_table(ns->mq_sysctls); retire_sysctl_set(&ns->mq_set); kfree(tbl); } |
| 5 5 3 2 5 3 3 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 | // SPDX-License-Identifier: GPL-2.0-only /* * ati_remote2 - ATI/Philips USB RF remote driver * * Copyright (C) 2005-2008 Ville Syrjala <syrjala@sci.fi> * Copyright (C) 2007-2008 Peter Stokes <linux@dadeos.co.uk> */ #include <linux/usb/input.h> #include <linux/slab.h> #include <linux/module.h> #define DRIVER_DESC "ATI/Philips USB RF remote driver" MODULE_DESCRIPTION(DRIVER_DESC); MODULE_AUTHOR("Ville Syrjala <syrjala@sci.fi>"); MODULE_LICENSE("GPL"); /* * ATI Remote Wonder II Channel Configuration * * The remote control can be assigned one of sixteen "channels" in order to facilitate * the use of multiple remote controls within range of each other. * A remote's "channel" may be altered by pressing and holding the "PC" button for * approximately 3 seconds, after which the button will slowly flash the count of the * currently configured "channel", using the numeric keypad enter a number between 1 and * 16 and then press the "PC" button again, the button will slowly flash the count of the * newly configured "channel". */ enum { ATI_REMOTE2_MAX_CHANNEL_MASK = 0xFFFF, ATI_REMOTE2_MAX_MODE_MASK = 0x1F, }; static int ati_remote2_set_mask(const char *val, const struct kernel_param *kp, unsigned int max) { unsigned int mask; int ret; if (!val) return -EINVAL; ret = kstrtouint(val, 0, &mask); if (ret) return ret; if (mask & ~max) return -EINVAL; *(unsigned int *)kp->arg = mask; return 0; } static int ati_remote2_set_channel_mask(const char *val, const struct kernel_param *kp) { pr_debug("%s()\n", __func__); return ati_remote2_set_mask(val, kp, ATI_REMOTE2_MAX_CHANNEL_MASK); } static int ati_remote2_get_channel_mask(char *buffer, const struct kernel_param *kp) { pr_debug("%s()\n", __func__); return sprintf(buffer, "0x%04x\n", *(unsigned int *)kp->arg); } static int ati_remote2_set_mode_mask(const char *val, const struct kernel_param *kp) { pr_debug("%s()\n", __func__); return ati_remote2_set_mask(val, kp, ATI_REMOTE2_MAX_MODE_MASK); } static int ati_remote2_get_mode_mask(char *buffer, const struct kernel_param *kp) { pr_debug("%s()\n", __func__); return sprintf(buffer, "0x%02x\n", *(unsigned int *)kp->arg); } static unsigned int channel_mask = ATI_REMOTE2_MAX_CHANNEL_MASK; #define param_check_channel_mask(name, p) __param_check(name, p, unsigned int) static const struct kernel_param_ops param_ops_channel_mask = { .set = ati_remote2_set_channel_mask, .get = ati_remote2_get_channel_mask, }; module_param(channel_mask, channel_mask, 0644); MODULE_PARM_DESC(channel_mask, "Bitmask of channels to accept <15:Channel16>...<1:Channel2><0:Channel1>"); static unsigned int mode_mask = ATI_REMOTE2_MAX_MODE_MASK; #define param_check_mode_mask(name, p) __param_check(name, p, unsigned int) static const struct kernel_param_ops param_ops_mode_mask = { .set = ati_remote2_set_mode_mask, .get = ati_remote2_get_mode_mask, }; module_param(mode_mask, mode_mask, 0644); MODULE_PARM_DESC(mode_mask, "Bitmask of modes to accept <4:PC><3:AUX4><2:AUX3><1:AUX2><0:AUX1>"); static const struct usb_device_id ati_remote2_id_table[] = { { USB_DEVICE(0x0471, 0x0602) }, /* ATI Remote Wonder II */ { } }; MODULE_DEVICE_TABLE(usb, ati_remote2_id_table); static DEFINE_MUTEX(ati_remote2_mutex); enum { ATI_REMOTE2_OPENED = 0x1, ATI_REMOTE2_SUSPENDED = 0x2, }; enum { ATI_REMOTE2_AUX1, ATI_REMOTE2_AUX2, ATI_REMOTE2_AUX3, ATI_REMOTE2_AUX4, ATI_REMOTE2_PC, ATI_REMOTE2_MODES, }; static const struct { u8 hw_code; u16 keycode; } ati_remote2_key_table[] = { { 0x00, KEY_0 }, { 0x01, KEY_1 }, { 0x02, KEY_2 }, { 0x03, KEY_3 }, { 0x04, KEY_4 }, { 0x05, KEY_5 }, { 0x06, KEY_6 }, { 0x07, KEY_7 }, { 0x08, KEY_8 }, { 0x09, KEY_9 }, { 0x0c, KEY_POWER }, { 0x0d, KEY_MUTE }, { 0x10, KEY_VOLUMEUP }, { 0x11, KEY_VOLUMEDOWN }, { 0x20, KEY_CHANNELUP }, { 0x21, KEY_CHANNELDOWN }, { 0x28, KEY_FORWARD }, { 0x29, KEY_REWIND }, { 0x2c, KEY_PLAY }, { 0x30, KEY_PAUSE }, { 0x31, KEY_STOP }, { 0x37, KEY_RECORD }, { 0x38, KEY_DVD }, { 0x39, KEY_TV }, { 0x3f, KEY_PROG1 }, /* AUX1-AUX4 and PC */ { 0x54, KEY_MENU }, { 0x58, KEY_UP }, { 0x59, KEY_DOWN }, { 0x5a, KEY_LEFT }, { 0x5b, KEY_RIGHT }, { 0x5c, KEY_OK }, { 0x78, KEY_A }, { 0x79, KEY_B }, { 0x7a, KEY_C }, { 0x7b, KEY_D }, { 0x7c, KEY_E }, { 0x7d, KEY_F }, { 0x82, KEY_ENTER }, { 0x8e, KEY_VENDOR }, { 0x96, KEY_COFFEE }, { 0xa9, BTN_LEFT }, { 0xaa, BTN_RIGHT }, { 0xbe, KEY_QUESTION }, { 0xd0, KEY_EDIT }, { 0xd5, KEY_FRONT }, { 0xf9, KEY_INFO }, }; struct ati_remote2 { struct input_dev *idev; struct usb_device *udev; struct usb_interface *intf[2]; struct usb_endpoint_descriptor *ep[2]; struct urb *urb[2]; void *buf[2]; dma_addr_t buf_dma[2]; unsigned long jiffies; int mode; char name[64]; char phys[64]; /* Each mode (AUX1-AUX4 and PC) can have an independent keymap. */ u16 keycode[ATI_REMOTE2_MODES][ARRAY_SIZE(ati_remote2_key_table)]; unsigned int flags; unsigned int channel_mask; unsigned int mode_mask; }; static struct usb_driver ati_remote2_driver; static int ati_remote2_submit_urbs(struct ati_remote2 *ar2) { int r; r = usb_submit_urb(ar2->urb[0], GFP_KERNEL); if (r) { dev_err(&ar2->intf[0]->dev, "%s(): usb_submit_urb() = %d\n", __func__, r); return r; } r = usb_submit_urb(ar2->urb[1], GFP_KERNEL); if (r) { usb_kill_urb(ar2->urb[0]); dev_err(&ar2->intf[1]->dev, "%s(): usb_submit_urb() = %d\n", __func__, r); return r; } return 0; } static void ati_remote2_kill_urbs(struct ati_remote2 *ar2) { usb_kill_urb(ar2->urb[1]); usb_kill_urb(ar2->urb[0]); } static int ati_remote2_open(struct input_dev *idev) { struct ati_remote2 *ar2 = input_get_drvdata(idev); int r; dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); r = usb_autopm_get_interface(ar2->intf[0]); if (r) { dev_err(&ar2->intf[0]->dev, "%s(): usb_autopm_get_interface() = %d\n", __func__, r); return r; } scoped_guard(mutex, &ati_remote2_mutex) { if (!(ar2->flags & ATI_REMOTE2_SUSPENDED)) { r = ati_remote2_submit_urbs(ar2); if (r) break; } ar2->flags |= ATI_REMOTE2_OPENED; } usb_autopm_put_interface(ar2->intf[0]); return r; } static void ati_remote2_close(struct input_dev *idev) { struct ati_remote2 *ar2 = input_get_drvdata(idev); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); guard(mutex)(&ati_remote2_mutex); if (!(ar2->flags & ATI_REMOTE2_SUSPENDED)) ati_remote2_kill_urbs(ar2); ar2->flags &= ~ATI_REMOTE2_OPENED; } static void ati_remote2_input_mouse(struct ati_remote2 *ar2) { struct input_dev *idev = ar2->idev; u8 *data = ar2->buf[0]; int channel, mode; channel = data[0] >> 4; if (!((1 << channel) & ar2->channel_mask)) return; mode = data[0] & 0x0F; if (mode > ATI_REMOTE2_PC) { dev_err(&ar2->intf[0]->dev, "Unknown mode byte (%02x %02x %02x %02x)\n", data[3], data[2], data[1], data[0]); return; } if (!((1 << mode) & ar2->mode_mask)) return; input_event(idev, EV_REL, REL_X, (s8) data[1]); input_event(idev, EV_REL, REL_Y, (s8) data[2]); input_sync(idev); } static int ati_remote2_lookup(unsigned int hw_code) { int i; for (i = 0; i < ARRAY_SIZE(ati_remote2_key_table); i++) if (ati_remote2_key_table[i].hw_code == hw_code) return i; return -1; } static void ati_remote2_input_key(struct ati_remote2 *ar2) { struct input_dev *idev = ar2->idev; u8 *data = ar2->buf[1]; int channel, mode, hw_code, index; channel = data[0] >> 4; if (!((1 << channel) & ar2->channel_mask)) return; mode = data[0] & 0x0F; if (mode > ATI_REMOTE2_PC) { dev_err(&ar2->intf[1]->dev, "Unknown mode byte (%02x %02x %02x %02x)\n", data[3], data[2], data[1], data[0]); return; } hw_code = data[2]; if (hw_code == 0x3f) { /* * For some incomprehensible reason the mouse pad generates * events which look identical to the events from the last * pressed mode key. Naturally we don't want to generate key * events for the mouse pad so we filter out any subsequent * events from the same mode key. */ if (ar2->mode == mode) return; if (data[1] == 0) ar2->mode = mode; } if (!((1 << mode) & ar2->mode_mask)) return; index = ati_remote2_lookup(hw_code); if (index < 0) { dev_err(&ar2->intf[1]->dev, "Unknown code byte (%02x %02x %02x %02x)\n", data[3], data[2], data[1], data[0]); return; } switch (data[1]) { case 0: /* release */ break; case 1: /* press */ ar2->jiffies = jiffies + msecs_to_jiffies(idev->rep[REP_DELAY]); break; case 2: /* repeat */ /* No repeat for mouse buttons. */ if (ar2->keycode[mode][index] == BTN_LEFT || ar2->keycode[mode][index] == BTN_RIGHT) return; if (!time_after_eq(jiffies, ar2->jiffies)) return; ar2->jiffies = jiffies + msecs_to_jiffies(idev->rep[REP_PERIOD]); break; default: dev_err(&ar2->intf[1]->dev, "Unknown state byte (%02x %02x %02x %02x)\n", data[3], data[2], data[1], data[0]); return; } input_event(idev, EV_KEY, ar2->keycode[mode][index], data[1]); input_sync(idev); } static void ati_remote2_complete_mouse(struct urb *urb) { struct ati_remote2 *ar2 = urb->context; int r; switch (urb->status) { case 0: usb_mark_last_busy(ar2->udev); ati_remote2_input_mouse(ar2); break; case -ENOENT: case -EILSEQ: case -ECONNRESET: case -ESHUTDOWN: dev_dbg(&ar2->intf[0]->dev, "%s(): urb status = %d\n", __func__, urb->status); return; default: usb_mark_last_busy(ar2->udev); dev_err(&ar2->intf[0]->dev, "%s(): urb status = %d\n", __func__, urb->status); } r = usb_submit_urb(urb, GFP_ATOMIC); if (r) dev_err(&ar2->intf[0]->dev, "%s(): usb_submit_urb() = %d\n", __func__, r); } static void ati_remote2_complete_key(struct urb *urb) { struct ati_remote2 *ar2 = urb->context; int r; switch (urb->status) { case 0: usb_mark_last_busy(ar2->udev); ati_remote2_input_key(ar2); break; case -ENOENT: case -EILSEQ: case -ECONNRESET: case -ESHUTDOWN: dev_dbg(&ar2->intf[1]->dev, "%s(): urb status = %d\n", __func__, urb->status); return; default: usb_mark_last_busy(ar2->udev); dev_err(&ar2->intf[1]->dev, "%s(): urb status = %d\n", __func__, urb->status); } r = usb_submit_urb(urb, GFP_ATOMIC); if (r) dev_err(&ar2->intf[1]->dev, "%s(): usb_submit_urb() = %d\n", __func__, r); } static int ati_remote2_getkeycode(struct input_dev *idev, struct input_keymap_entry *ke) { struct ati_remote2 *ar2 = input_get_drvdata(idev); unsigned int mode; int offset; unsigned int index; unsigned int scancode; if (ke->flags & INPUT_KEYMAP_BY_INDEX) { index = ke->index; if (index >= ATI_REMOTE2_MODES * ARRAY_SIZE(ati_remote2_key_table)) return -EINVAL; mode = ke->index / ARRAY_SIZE(ati_remote2_key_table); offset = ke->index % ARRAY_SIZE(ati_remote2_key_table); scancode = (mode << 8) + ati_remote2_key_table[offset].hw_code; } else { if (input_scancode_to_scalar(ke, &scancode)) return -EINVAL; mode = scancode >> 8; if (mode > ATI_REMOTE2_PC) return -EINVAL; offset = ati_remote2_lookup(scancode & 0xff); if (offset < 0) return -EINVAL; index = mode * ARRAY_SIZE(ati_remote2_key_table) + offset; } ke->keycode = ar2->keycode[mode][offset]; ke->len = sizeof(scancode); memcpy(&ke->scancode, &scancode, sizeof(scancode)); ke->index = index; return 0; } static int ati_remote2_setkeycode(struct input_dev *idev, const struct input_keymap_entry *ke, unsigned int *old_keycode) { struct ati_remote2 *ar2 = input_get_drvdata(idev); unsigned int mode; int offset; unsigned int index; unsigned int scancode; if (ke->flags & INPUT_KEYMAP_BY_INDEX) { if (ke->index >= ATI_REMOTE2_MODES * ARRAY_SIZE(ati_remote2_key_table)) return -EINVAL; mode = ke->index / ARRAY_SIZE(ati_remote2_key_table); offset = ke->index % ARRAY_SIZE(ati_remote2_key_table); } else { if (input_scancode_to_scalar(ke, &scancode)) return -EINVAL; mode = scancode >> 8; if (mode > ATI_REMOTE2_PC) return -EINVAL; offset = ati_remote2_lookup(scancode & 0xff); if (offset < 0) return -EINVAL; } *old_keycode = ar2->keycode[mode][offset]; ar2->keycode[mode][offset] = ke->keycode; __set_bit(ke->keycode, idev->keybit); for (mode = 0; mode < ATI_REMOTE2_MODES; mode++) { for (index = 0; index < ARRAY_SIZE(ati_remote2_key_table); index++) { if (ar2->keycode[mode][index] == *old_keycode) return 0; } } __clear_bit(*old_keycode, idev->keybit); return 0; } static int ati_remote2_input_init(struct ati_remote2 *ar2) { struct input_dev *idev; int index, mode, retval; idev = input_allocate_device(); if (!idev) return -ENOMEM; ar2->idev = idev; input_set_drvdata(idev, ar2); idev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP) | BIT_MASK(EV_REL); idev->keybit[BIT_WORD(BTN_MOUSE)] = BIT_MASK(BTN_LEFT) | BIT_MASK(BTN_RIGHT); idev->relbit[0] = BIT_MASK(REL_X) | BIT_MASK(REL_Y); for (mode = 0; mode < ATI_REMOTE2_MODES; mode++) { for (index = 0; index < ARRAY_SIZE(ati_remote2_key_table); index++) { ar2->keycode[mode][index] = ati_remote2_key_table[index].keycode; __set_bit(ar2->keycode[mode][index], idev->keybit); } } /* AUX1-AUX4 and PC generate the same scancode. */ index = ati_remote2_lookup(0x3f); ar2->keycode[ATI_REMOTE2_AUX1][index] = KEY_PROG1; ar2->keycode[ATI_REMOTE2_AUX2][index] = KEY_PROG2; ar2->keycode[ATI_REMOTE2_AUX3][index] = KEY_PROG3; ar2->keycode[ATI_REMOTE2_AUX4][index] = KEY_PROG4; ar2->keycode[ATI_REMOTE2_PC][index] = KEY_PC; __set_bit(KEY_PROG1, idev->keybit); __set_bit(KEY_PROG2, idev->keybit); __set_bit(KEY_PROG3, idev->keybit); __set_bit(KEY_PROG4, idev->keybit); __set_bit(KEY_PC, idev->keybit); idev->rep[REP_DELAY] = 250; idev->rep[REP_PERIOD] = 33; idev->open = ati_remote2_open; idev->close = ati_remote2_close; idev->getkeycode = ati_remote2_getkeycode; idev->setkeycode = ati_remote2_setkeycode; idev->name = ar2->name; idev->phys = ar2->phys; usb_to_input_id(ar2->udev, &idev->id); idev->dev.parent = &ar2->udev->dev; retval = input_register_device(idev); if (retval) input_free_device(idev); return retval; } static int ati_remote2_urb_init(struct ati_remote2 *ar2) { struct usb_device *udev = ar2->udev; int i, pipe, maxp; for (i = 0; i < 2; i++) { ar2->buf[i] = usb_alloc_coherent(udev, 4, GFP_KERNEL, &ar2->buf_dma[i]); if (!ar2->buf[i]) return -ENOMEM; ar2->urb[i] = usb_alloc_urb(0, GFP_KERNEL); if (!ar2->urb[i]) return -ENOMEM; pipe = usb_rcvintpipe(udev, ar2->ep[i]->bEndpointAddress); maxp = usb_maxpacket(udev, pipe); maxp = maxp > 4 ? 4 : maxp; usb_fill_int_urb(ar2->urb[i], udev, pipe, ar2->buf[i], maxp, i ? ati_remote2_complete_key : ati_remote2_complete_mouse, ar2, ar2->ep[i]->bInterval); ar2->urb[i]->transfer_dma = ar2->buf_dma[i]; ar2->urb[i]->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; } return 0; } static void ati_remote2_urb_cleanup(struct ati_remote2 *ar2) { int i; for (i = 0; i < 2; i++) { usb_free_urb(ar2->urb[i]); usb_free_coherent(ar2->udev, 4, ar2->buf[i], ar2->buf_dma[i]); } } static int ati_remote2_setup(struct ati_remote2 *ar2, unsigned int ch_mask) { int r, i, channel; /* * Configure receiver to only accept input from remote "channel" * channel == 0 -> Accept input from any remote channel * channel == 1 -> Only accept input from remote channel 1 * channel == 2 -> Only accept input from remote channel 2 * ... * channel == 16 -> Only accept input from remote channel 16 */ channel = 0; for (i = 0; i < 16; i++) { if ((1 << i) & ch_mask) { if (!(~(1 << i) & ch_mask)) channel = i + 1; break; } } r = usb_control_msg(ar2->udev, usb_sndctrlpipe(ar2->udev, 0), 0x20, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, channel, 0x0, NULL, 0, USB_CTRL_SET_TIMEOUT); if (r) { dev_err(&ar2->udev->dev, "%s - failed to set channel due to error: %d\n", __func__, r); return r; } return 0; } static ssize_t ati_remote2_show_channel_mask(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_device *udev = to_usb_device(dev); struct usb_interface *intf = usb_ifnum_to_if(udev, 0); struct ati_remote2 *ar2 = usb_get_intfdata(intf); return sprintf(buf, "0x%04x\n", ar2->channel_mask); } static ssize_t ati_remote2_store_channel_mask(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct usb_device *udev = to_usb_device(dev); struct usb_interface *intf = usb_ifnum_to_if(udev, 0); struct ati_remote2 *ar2 = usb_get_intfdata(intf); unsigned int mask; int r; r = kstrtouint(buf, 0, &mask); if (r) return r; if (mask & ~ATI_REMOTE2_MAX_CHANNEL_MASK) return -EINVAL; r = usb_autopm_get_interface(ar2->intf[0]); if (r) { dev_err(&ar2->intf[0]->dev, "%s(): usb_autopm_get_interface() = %d\n", __func__, r); return r; } scoped_guard(mutex, &ati_remote2_mutex) { if (mask != ar2->channel_mask) { r = ati_remote2_setup(ar2, mask); if (!r) ar2->channel_mask = mask; } } usb_autopm_put_interface(ar2->intf[0]); return r ? r : count; } static ssize_t ati_remote2_show_mode_mask(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_device *udev = to_usb_device(dev); struct usb_interface *intf = usb_ifnum_to_if(udev, 0); struct ati_remote2 *ar2 = usb_get_intfdata(intf); return sprintf(buf, "0x%02x\n", ar2->mode_mask); } static ssize_t ati_remote2_store_mode_mask(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct usb_device *udev = to_usb_device(dev); struct usb_interface *intf = usb_ifnum_to_if(udev, 0); struct ati_remote2 *ar2 = usb_get_intfdata(intf); unsigned int mask; int err; err = kstrtouint(buf, 0, &mask); if (err) return err; if (mask & ~ATI_REMOTE2_MAX_MODE_MASK) return -EINVAL; ar2->mode_mask = mask; return count; } static DEVICE_ATTR(channel_mask, 0644, ati_remote2_show_channel_mask, ati_remote2_store_channel_mask); static DEVICE_ATTR(mode_mask, 0644, ati_remote2_show_mode_mask, ati_remote2_store_mode_mask); static struct attribute *ati_remote2_attrs[] = { &dev_attr_channel_mask.attr, &dev_attr_mode_mask.attr, NULL, }; ATTRIBUTE_GROUPS(ati_remote2); static int ati_remote2_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(interface); struct usb_host_interface *alt = interface->cur_altsetting; struct ati_remote2 *ar2; int r; if (alt->desc.bInterfaceNumber) return -ENODEV; ar2 = kzalloc(sizeof (struct ati_remote2), GFP_KERNEL); if (!ar2) return -ENOMEM; ar2->udev = udev; /* Sanity check, first interface must have an endpoint */ if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) { dev_err(&interface->dev, "%s(): interface 0 must have an endpoint\n", __func__); r = -ENODEV; goto fail1; } ar2->intf[0] = interface; ar2->ep[0] = &alt->endpoint[0].desc; /* Sanity check, the device must have two interfaces */ ar2->intf[1] = usb_ifnum_to_if(udev, 1); if ((udev->actconfig->desc.bNumInterfaces < 2) || !ar2->intf[1]) { dev_err(&interface->dev, "%s(): need 2 interfaces, found %d\n", __func__, udev->actconfig->desc.bNumInterfaces); r = -ENODEV; goto fail1; } r = usb_driver_claim_interface(&ati_remote2_driver, ar2->intf[1], ar2); if (r) goto fail1; /* Sanity check, second interface must have an endpoint */ alt = ar2->intf[1]->cur_altsetting; if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) { dev_err(&interface->dev, "%s(): interface 1 must have an endpoint\n", __func__); r = -ENODEV; goto fail2; } ar2->ep[1] = &alt->endpoint[0].desc; r = ati_remote2_urb_init(ar2); if (r) goto fail3; ar2->channel_mask = channel_mask; ar2->mode_mask = mode_mask; r = ati_remote2_setup(ar2, ar2->channel_mask); if (r) goto fail3; usb_make_path(udev, ar2->phys, sizeof(ar2->phys)); strlcat(ar2->phys, "/input0", sizeof(ar2->phys)); strlcat(ar2->name, "ATI Remote Wonder II", sizeof(ar2->name)); r = ati_remote2_input_init(ar2); if (r) goto fail3; usb_set_intfdata(interface, ar2); interface->needs_remote_wakeup = 1; return 0; fail3: ati_remote2_urb_cleanup(ar2); fail2: usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]); fail1: kfree(ar2); return r; } static void ati_remote2_disconnect(struct usb_interface *interface) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; if (alt->desc.bInterfaceNumber) return; ar2 = usb_get_intfdata(interface); usb_set_intfdata(interface, NULL); input_unregister_device(ar2->idev); ati_remote2_urb_cleanup(ar2); usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]); kfree(ar2); } static int ati_remote2_suspend(struct usb_interface *interface, pm_message_t message) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; if (alt->desc.bInterfaceNumber) return 0; ar2 = usb_get_intfdata(interface); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); guard(mutex)(&ati_remote2_mutex); if (ar2->flags & ATI_REMOTE2_OPENED) ati_remote2_kill_urbs(ar2); ar2->flags |= ATI_REMOTE2_SUSPENDED; return 0; } static int ati_remote2_resume(struct usb_interface *interface) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; int r = 0; if (alt->desc.bInterfaceNumber) return 0; ar2 = usb_get_intfdata(interface); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); guard(mutex)(&ati_remote2_mutex); if (ar2->flags & ATI_REMOTE2_OPENED) r = ati_remote2_submit_urbs(ar2); if (!r) ar2->flags &= ~ATI_REMOTE2_SUSPENDED; return r; } static int ati_remote2_reset_resume(struct usb_interface *interface) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; int r = 0; if (alt->desc.bInterfaceNumber) return 0; ar2 = usb_get_intfdata(interface); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); guard(mutex)(&ati_remote2_mutex); r = ati_remote2_setup(ar2, ar2->channel_mask); if (r) return r; if (ar2->flags & ATI_REMOTE2_OPENED) r = ati_remote2_submit_urbs(ar2); if (!r) ar2->flags &= ~ATI_REMOTE2_SUSPENDED; return r; } static int ati_remote2_pre_reset(struct usb_interface *interface) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; if (alt->desc.bInterfaceNumber) return 0; ar2 = usb_get_intfdata(interface); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); mutex_lock(&ati_remote2_mutex); if (ar2->flags == ATI_REMOTE2_OPENED) ati_remote2_kill_urbs(ar2); return 0; } static int ati_remote2_post_reset(struct usb_interface *interface) { struct ati_remote2 *ar2; struct usb_host_interface *alt = interface->cur_altsetting; int r = 0; if (alt->desc.bInterfaceNumber) return 0; ar2 = usb_get_intfdata(interface); dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); if (ar2->flags == ATI_REMOTE2_OPENED) r = ati_remote2_submit_urbs(ar2); mutex_unlock(&ati_remote2_mutex); return r; } static struct usb_driver ati_remote2_driver = { .name = "ati_remote2", .probe = ati_remote2_probe, .disconnect = ati_remote2_disconnect, .dev_groups = ati_remote2_groups, .id_table = ati_remote2_id_table, .suspend = ati_remote2_suspend, .resume = ati_remote2_resume, .reset_resume = ati_remote2_reset_resume, .pre_reset = ati_remote2_pre_reset, .post_reset = ati_remote2_post_reset, .supports_autosuspend = 1, }; module_usb_driver(ati_remote2_driver); |
| 430 5 427 9 431 415 412 9 1 8 8 410 94 94 94 4 94 94 94 93 93 94 94 4 94 94 94 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/termios.h> #include <linux/tty.h> #include <linux/export.h> #include "tty.h" /* * Routine which returns the baud rate of the tty * * Note that the baud_table needs to be kept in sync with the * include/asm/termbits.h file. */ static const speed_t baud_table[] = { 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, 9600, 19200, 38400, 57600, 115200, 230400, 460800, #ifdef __sparc__ 76800, 153600, 307200, 614400, 921600, 500000, 576000, 1000000, 1152000, 1500000, 2000000 #else 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000, 2500000, 3000000, 3500000, 4000000 #endif }; static const tcflag_t baud_bits[] = { B0, B50, B75, B110, B134, B150, B200, B300, B600, B1200, B1800, B2400, B4800, B9600, B19200, B38400, B57600, B115200, B230400, B460800, #ifdef __sparc__ B76800, B153600, B307200, B614400, B921600, B500000, B576000, B1000000, B1152000, B1500000, B2000000 #else B500000, B576000, B921600, B1000000, B1152000, B1500000, B2000000, B2500000, B3000000, B3500000, B4000000 #endif }; static int n_baud_table = ARRAY_SIZE(baud_table); /** * tty_termios_baud_rate * @termios: termios structure * * Convert termios baud rate data into a speed. This should be called * with the termios lock held if this termios is a terminal termios * structure. Device drivers can call this function but should use * ->c_[io]speed directly as they are updated. * * Locking: none */ speed_t tty_termios_baud_rate(const struct ktermios *termios) { unsigned int cbaud; cbaud = termios->c_cflag & CBAUD; /* Magic token for arbitrary speed via c_ispeed/c_ospeed */ if (cbaud == BOTHER) return termios->c_ospeed; if (cbaud & CBAUDEX) { cbaud &= ~CBAUDEX; cbaud += 15; } return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); /** * tty_termios_input_baud_rate * @termios: termios structure * * Convert termios baud rate data into a speed. This should be called * with the termios lock held if this termios is a terminal termios * structure. Device drivers can call this function but should use * ->c_[io]speed directly as they are updated. * * Locking: none */ speed_t tty_termios_input_baud_rate(const struct ktermios *termios) { unsigned int cbaud = (termios->c_cflag >> IBSHIFT) & CBAUD; if (cbaud == B0) return tty_termios_baud_rate(termios); /* Magic token for arbitrary speed via c_ispeed */ if (cbaud == BOTHER) return termios->c_ispeed; if (cbaud & CBAUDEX) { cbaud &= ~CBAUDEX; cbaud += 15; } return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_input_baud_rate); /** * tty_termios_encode_baud_rate * @termios: ktermios structure holding user requested state * @ibaud: input speed * @obaud: output speed * * Encode the speeds set into the passed termios structure. This is * used as a library helper for drivers so that they can report back * the actual speed selected when it differs from the speed requested * * For maximal back compatibility with legacy SYS5/POSIX *nix behaviour * we need to carefully set the bits when the user does not get the * desired speed. We allow small margins and preserve as much of possible * of the input intent to keep compatibility. * * Locking: Caller should hold termios lock. This is already held * when calling this function from the driver termios handler. * * The ifdefs deal with platforms whose owners have yet to update them * and will all go away once this is done. */ void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud) { int i = 0; int ifound = -1, ofound = -1; int iclose = ibaud/50, oclose = obaud/50; int ibinput = 0; if (obaud == 0) /* CD dropped */ ibaud = 0; /* Clear ibaud to be sure */ termios->c_ispeed = ibaud; termios->c_ospeed = obaud; if (((termios->c_cflag >> IBSHIFT) & CBAUD) != B0) ibinput = 1; /* An input speed was specified */ /* If the user asked for a precise weird speed give a precise weird * answer. If they asked for a Bfoo speed they may have problems * digesting non-exact replies so fuzz a bit. */ if ((termios->c_cflag & CBAUD) == BOTHER) { oclose = 0; if (!ibinput) iclose = 0; } if (((termios->c_cflag >> IBSHIFT) & CBAUD) == BOTHER) iclose = 0; termios->c_cflag &= ~CBAUD; termios->c_cflag &= ~(CBAUD << IBSHIFT); /* * Our goal is to find a close match to the standard baud rate * returned. Walk the baud rate table and if we get a very close * match then report back the speed as a POSIX Bxxxx value by * preference */ do { if (obaud - oclose <= baud_table[i] && obaud + oclose >= baud_table[i]) { termios->c_cflag |= baud_bits[i]; ofound = i; } if (ibaud - iclose <= baud_table[i] && ibaud + iclose >= baud_table[i]) { /* For the case input == output don't set IBAUD bits * if the user didn't do so. */ if (ofound == i && !ibinput) { ifound = i; } else { ifound = i; termios->c_cflag |= (baud_bits[i] << IBSHIFT); } } } while (++i < n_baud_table); /* If we found no match then use BOTHER. */ if (ofound == -1) termios->c_cflag |= BOTHER; /* Set exact input bits only if the input and output differ or the * user already did. */ if (ifound == -1 && (ibaud != obaud || ibinput)) termios->c_cflag |= (BOTHER << IBSHIFT); } EXPORT_SYMBOL_GPL(tty_termios_encode_baud_rate); /** * tty_encode_baud_rate - set baud rate of the tty * @tty: terminal device * @ibaud: input baud rate * @obaud: output baud rate * * Update the current termios data for the tty with the new speed * settings. The caller must hold the termios_rwsem for the tty in * question. */ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, speed_t obaud) { tty_termios_encode_baud_rate(&tty->termios, ibaud, obaud); } EXPORT_SYMBOL_GPL(tty_encode_baud_rate); |
| 807 810 810 810 798 808 799 810 810 809 47 11 60 11 47 1154 1154 714 89 89 19 8 60 810 188 128 129 128 129 129 129 129 187 95 174 | 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 | /* * Copyright (c) 2015, Mellanox Technologies 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 "core_priv.h" #include <linux/in.h> #include <linux/in6.h> /* For in6_dev_get/in6_dev_put */ #include <net/addrconf.h> #include <net/bonding.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> static struct workqueue_struct *gid_cache_wq; enum gid_op_type { GID_DEL = 0, GID_ADD }; struct update_gid_event_work { struct work_struct work; union ib_gid gid; struct ib_gid_attr gid_attr; enum gid_op_type gid_op; }; #define ROCE_NETDEV_CALLBACK_SZ 3 struct netdev_event_work_cmd { roce_netdev_callback cb; roce_netdev_filter filter; struct net_device *ndev; struct net_device *filter_ndev; }; struct netdev_event_work { struct work_struct work; struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ]; }; static const struct { bool (*is_supported)(const struct ib_device *device, u32 port_num); enum ib_gid_type gid_type; } PORT_CAP_TO_GID_TYPE[] = { {rdma_protocol_roce_eth_encap, IB_GID_TYPE_ROCE}, {rdma_protocol_roce_udp_encap, IB_GID_TYPE_ROCE_UDP_ENCAP}, }; #define CAP_TO_GID_TABLE_SIZE ARRAY_SIZE(PORT_CAP_TO_GID_TYPE) unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port) { int i; unsigned int ret_flags = 0; if (!rdma_protocol_roce(ib_dev, port)) return 1UL << IB_GID_TYPE_IB; for (i = 0; i < CAP_TO_GID_TABLE_SIZE; i++) if (PORT_CAP_TO_GID_TYPE[i].is_supported(ib_dev, port)) ret_flags |= 1UL << PORT_CAP_TO_GID_TYPE[i].gid_type; return ret_flags; } EXPORT_SYMBOL(roce_gid_type_mask_support); static void update_gid(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *gid_attr) { int i; unsigned long gid_type_mask = roce_gid_type_mask_support(ib_dev, port); for (i = 0; i < IB_GID_TYPE_SIZE; i++) { if ((1UL << i) & gid_type_mask) { gid_attr->gid_type = i; switch (gid_op) { case GID_ADD: ib_cache_gid_add(ib_dev, port, gid, gid_attr); break; case GID_DEL: ib_cache_gid_del(ib_dev, port, gid, gid_attr); break; } } } } enum bonding_slave_state { BONDING_SLAVE_STATE_ACTIVE = 1UL << 0, BONDING_SLAVE_STATE_INACTIVE = 1UL << 1, /* No primary slave or the device isn't a slave in bonding */ BONDING_SLAVE_STATE_NA = 1UL << 2, }; static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_device *dev, struct net_device *upper) { if (upper && netif_is_bond_master(upper)) { struct net_device *pdev = bond_option_active_slave_get_rcu(netdev_priv(upper)); if (pdev) return dev == pdev ? BONDING_SLAVE_STATE_ACTIVE : BONDING_SLAVE_STATE_INACTIVE; } return BONDING_SLAVE_STATE_NA; } #define REQUIRED_BOND_STATES (BONDING_SLAVE_STATE_ACTIVE | \ BONDING_SLAVE_STATE_NA) static bool is_eth_port_of_netdev_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *real_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); real_dev = rdma_vlan_dev_real_dev(cookie); if (!real_dev) real_dev = cookie; res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) && (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) & REQUIRED_BOND_STATES)) || real_dev == rdma_ndev); rcu_read_unlock(); return res; } static bool is_eth_port_inactive_slave_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu(rdma_ndev); res = is_eth_active_slave_of_bonding_rcu(rdma_ndev, master_dev) == BONDING_SLAVE_STATE_INACTIVE; rcu_read_unlock(); return res; } /** * is_ndev_for_default_gid_filter - Check if a given netdevice * can be considered for default GIDs or not. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: rdma netdevice pointer * @cookie: Netdevice to consider to form a default GID * * is_ndev_for_default_gid_filter() returns true if a given netdevice can be * considered for deriving default RoCE GID, returns false otherwise. */ static bool is_ndev_for_default_gid_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool res; if (!rdma_ndev) return false; rcu_read_lock(); /* * When rdma netdevice is used in bonding, bonding master netdevice * should be considered for default GIDs. Therefore, ignore slave rdma * netdevices when bonding is considered. * Additionally when event(cookie) netdevice is bond master device, * make sure that it the upper netdevice of rdma netdevice. */ res = ((cookie_ndev == rdma_ndev && !netif_is_bond_slave(rdma_ndev)) || (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev))); rcu_read_unlock(); return res; } static bool pass_all_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { return true; } static bool upper_device_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { bool res; if (!rdma_ndev) return false; if (rdma_ndev == cookie) return true; rcu_read_lock(); res = rdma_is_upper_dev_rcu(rdma_ndev, cookie); rcu_read_unlock(); return res; } /** * is_upper_ndev_bond_master_filter - Check if a given netdevice * is bond master device of netdevice of the RDMA device of port. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: Pointer to rdma netdevice * @cookie: Netdevice to consider to form a default GID * * is_upper_ndev_bond_master_filter() returns true if a cookie_netdev * is bond master device and rdma_ndev is its lower netdevice. It might * not have been established as slave device yet. */ static bool is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool match = false; if (!rdma_ndev) return false; rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) match = true; rcu_read_unlock(); return match; } static void update_gid_ip(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, struct net_device *ndev, struct sockaddr *addr) { union ib_gid gid; struct ib_gid_attr gid_attr; rdma_ip2gid(addr, &gid); memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; update_gid(gid_op, ib_dev, port, &gid, &gid_attr); } static void bond_delete_netdev_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, struct net_device *event_ndev) { struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev); unsigned long gid_type_mask; if (!rdma_ndev) return; if (!real_dev) real_dev = event_ndev; rcu_read_lock(); if (((rdma_ndev != event_ndev && !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) || is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) == BONDING_SLAVE_STATE_INACTIVE)) { rcu_read_unlock(); return; } rcu_read_unlock(); gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { const struct in_ifaddr *ifa; struct in_device *in_dev; struct sin_list { struct list_head list; struct sockaddr_in ip; }; struct sin_list *sin_iter; struct sin_list *sin_temp; LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; rcu_read_lock(); in_dev = __in_dev_get_rcu(ndev); if (!in_dev) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->ip.sin_family = AF_INET; entry->ip.sin_addr.s_addr = ifa->ifa_address; list_add_tail(&entry->list, &sin_list); } rcu_read_unlock(); list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { update_gid_ip(GID_ADD, ib_dev, port, ndev, (struct sockaddr *)&sin_iter->ip); list_del(&sin_iter->list); kfree(sin_iter); } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct inet6_ifaddr *ifp; struct inet6_dev *in6_dev; struct sin6_list { struct list_head list; struct sockaddr_in6 sin6; }; struct sin6_list *sin6_iter; struct sin6_list *sin6_temp; struct ib_gid_attr gid_attr = {.ndev = ndev}; LIST_HEAD(sin6_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; in6_dev = in6_dev_get(ndev); if (!in6_dev) return; read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { struct sin6_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->sin6.sin6_family = AF_INET6; entry->sin6.sin6_addr = ifp->addr; list_add_tail(&entry->list, &sin6_list); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); list_for_each_entry_safe(sin6_iter, sin6_temp, &sin6_list, list) { union ib_gid gid; rdma_ip2gid((struct sockaddr *)&sin6_iter->sin6, &gid); update_gid(GID_ADD, ib_dev, port, &gid, &gid_attr); list_del(&sin6_iter->list); kfree(sin6_iter); } } static void _add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { enum_netdev_ipv4_ips(ib_dev, port, ndev); if (IS_ENABLED(CONFIG_IPV6)) enum_netdev_ipv6_ips(ib_dev, port, ndev); } static void add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { _add_netdev_ips(ib_dev, port, cookie); } static void del_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie); } /** * del_default_gids - Delete default GIDs of the event/cookie netdevice * @ib_dev: RDMA device pointer * @port: Port of the RDMA device whose GID table to consider * @rdma_ndev: Unused rdma netdevice * @cookie: Pointer to event netdevice * * del_default_gids() deletes the default GIDs of the event/cookie netdevice. */ static void del_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, cookie_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void add_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *event_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, event_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_SET); } static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net *net; struct net_device *ndev; /* Lock the rtnl to make sure the netdevs does not move under * our feet */ rtnl_lock(); down_read(&net_rwsem); for_each_net(net) for_each_netdev(net, ndev) { /* * Filter and add default GIDs of the primary netdevice * when not in bonding mode, or add default GIDs * of bond master device, when in bonding mode. */ if (is_ndev_for_default_gid_filter(ib_dev, port, rdma_ndev, ndev)) add_default_gids(ib_dev, port, rdma_ndev, ndev); if (is_eth_port_of_netdev_filter(ib_dev, port, rdma_ndev, ndev)) _add_netdev_ips(ib_dev, port, ndev); } up_read(&net_rwsem); rtnl_unlock(); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @ib_dev: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ib_dev) { ib_enum_roce_netdev(ib_dev, pass_all_filter, NULL, enum_all_gids_of_dev_cb, NULL); } EXPORT_SYMBOL(rdma_roce_rescan_device); /** * rdma_roce_rescan_port - Rescan all of the network devices in the system * and add their gids if relevant to the port of the RoCE device. * * @ib_dev: IB device * @port: Port number */ void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port) { struct net_device *ndev = NULL; if (rdma_protocol_roce(ib_dev, port)) { ndev = ib_device_get_netdev(ib_dev, port); if (!ndev) return; enum_all_gids_of_dev_cb(ib_dev, port, ndev, ndev); dev_put(ndev); } } EXPORT_SYMBOL(rdma_roce_rescan_port); static void callback_for_addr_gid_device_scan(struct ib_device *device, u32 port, struct net_device *rdma_ndev, void *cookie) { struct update_gid_event_work *parsed = cookie; return update_gid(parsed->gid_op, device, port, &parsed->gid, &parsed->gid_attr); } struct upper_list { struct list_head list; struct net_device *upper; }; static int netdev_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; list_add_tail(&entry->list, upper_list); dev_hold(upper); entry->upper = upper; return 0; } static void handle_netdev_upper(struct ib_device *ib_dev, u32 port, void *cookie, void (*handle_netdev)(struct ib_device *ib_dev, u32 port, struct net_device *ndev)) { struct net_device *ndev = cookie; struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); priv.data = &upper_list; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); list_for_each_entry_safe(upper_iter, upper_temp, &upper_list, list) { handle_netdev(ib_dev, port, upper_iter->upper); dev_put(upper_iter->upper); list_del(&upper_iter->list); kfree(upper_iter); } } void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, ndev); } EXPORT_SYMBOL(roce_del_all_netdev_gids); static void del_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, roce_del_all_netdev_gids); } static void add_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _add_netdev_ips); } static void del_netdev_default_ips_join(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_ndev; rcu_read_lock(); master_ndev = netdev_master_upper_dev_get_rcu(rdma_ndev); dev_hold(master_ndev); rcu_read_unlock(); if (master_ndev) { bond_delete_netdev_default_gids(ib_dev, port, rdma_ndev, master_ndev); dev_put(master_ndev); } } /* The following functions operate on all IB devices. netdevice_event and * addr_event execute ib_enum_all_roce_netdevs through a work. * ib_enum_all_roce_netdevs iterates through all IB devices. */ static void netdevice_event_work_handler(struct work_struct *_work) { struct netdev_event_work *work = container_of(_work, struct netdev_event_work, work); unsigned int i; for (i = 0; i < ARRAY_SIZE(work->cmds) && work->cmds[i].cb; i++) { ib_enum_all_roce_netdevs(work->cmds[i].filter, work->cmds[i].filter_ndev, work->cmds[i].cb, work->cmds[i].ndev); dev_put(work->cmds[i].ndev); dev_put(work->cmds[i].filter_ndev); } kfree(work); } static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, struct net_device *ndev) { unsigned int i; struct netdev_event_work *ndev_work = kmalloc(sizeof(*ndev_work), GFP_KERNEL); if (!ndev_work) return NOTIFY_DONE; memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds)); for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) { if (!ndev_work->cmds[i].ndev) ndev_work->cmds[i].ndev = ndev; if (!ndev_work->cmds[i].filter_ndev) ndev_work->cmds[i].filter_ndev = ndev; dev_hold(ndev_work->cmds[i].ndev); dev_hold(ndev_work->cmds[i].filter_ndev); } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } static const struct netdev_event_work_cmd add_cmd = { .cb = add_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd add_cmd_upper_ips = { .cb = add_netdev_upper_ips, .filter = is_eth_port_of_netdev_filter }; static void ndev_event_unlink(struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd upper_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter }; cmds[0] = upper_ips_del_cmd; cmds[0].ndev = changeupper_info->upper_dev; cmds[1] = add_cmd; } static const struct netdev_event_work_cmd bonding_default_add_cmd = { .cb = add_default_gids, .filter = is_upper_ndev_bond_master_filter }; static void ndev_event_link(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd bonding_default_del_cmd = { .cb = del_default_gids, .filter = is_upper_ndev_bond_master_filter }; /* * When a lower netdev is linked to its upper bonding * netdev, delete lower slave netdev's default GIDs. */ cmds[0] = bonding_default_del_cmd; cmds[0].ndev = event_ndev; cmds[0].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device default GIDs */ cmds[1] = bonding_default_add_cmd; cmds[1].ndev = changeupper_info->upper_dev; cmds[1].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device IP based GIDs */ cmds[2] = add_cmd_upper_ips; cmds[2].ndev = changeupper_info->upper_dev; cmds[2].filter_ndev = changeupper_info->upper_dev; } static void netdevice_event_changeupper(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { if (changeupper_info->linking) ndev_event_link(event_ndev, changeupper_info, cmds); else ndev_event_unlink(changeupper_info, cmds); } static const struct netdev_event_work_cmd add_default_gid_cmd = { .cb = add_default_gids, .filter = is_ndev_for_default_gid_filter, }; static int netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { static const struct netdev_event_work_cmd del_cmd = { .cb = del_netdev_ips, .filter = pass_all_filter}; static const struct netdev_event_work_cmd bonding_default_del_cmd_join = { .cb = del_netdev_default_ips_join, .filter = is_eth_port_inactive_slave_filter }; static const struct netdev_event_work_cmd netdev_del_cmd = { .cb = del_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd bonding_event_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter}; struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ] = { {NULL} }; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_UP: cmds[0] = bonding_default_del_cmd_join; cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; break; case NETDEV_UNREGISTER: if (ndev->reg_state < NETREG_UNREGISTERED) cmds[0] = del_cmd; else return NOTIFY_DONE; break; case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; if (ndev->reg_state == NETREG_REGISTERED) { cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; } break; case NETDEV_CHANGEUPPER: netdevice_event_changeupper(ndev, container_of(ptr, struct netdev_notifier_changeupper_info, info), cmds); break; case NETDEV_BONDING_FAILOVER: cmds[0] = bonding_event_ips_del_cmd; /* Add default GIDs of the bond device */ cmds[1] = bonding_default_add_cmd; /* Add IP based GIDs of the bond device */ cmds[2] = add_cmd_upper_ips; break; default: return NOTIFY_DONE; } return netdevice_queue_work(cmds, ndev); } static void update_gid_event_work_handler(struct work_struct *_work) { struct update_gid_event_work *work = container_of(_work, struct update_gid_event_work, work); ib_enum_all_roce_netdevs(is_eth_port_of_netdev_filter, work->gid_attr.ndev, callback_for_addr_gid_device_scan, work); dev_put(work->gid_attr.ndev); kfree(work); } static int addr_event(struct notifier_block *this, unsigned long event, struct sockaddr *sa, struct net_device *ndev) { struct update_gid_event_work *work; enum gid_op_type gid_op; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_UP: gid_op = GID_ADD; break; case NETDEV_DOWN: gid_op = GID_DEL; break; default: return NOTIFY_DONE; } work = kmalloc(sizeof(*work), GFP_ATOMIC); if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, update_gid_event_work_handler); rdma_ip2gid(sa, &work->gid); work->gid_op = gid_op; memset(&work->gid_attr, 0, sizeof(work->gid_attr)); dev_hold(ndev); work->gid_attr.ndev = ndev; queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } static int inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in in; struct net_device *ndev; struct in_ifaddr *ifa = ptr; in.sin_family = AF_INET; in.sin_addr.s_addr = ifa->ifa_address; ndev = ifa->ifa_dev->dev; return addr_event(this, event, (struct sockaddr *)&in, ndev); } static int inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in6 in6; struct net_device *ndev; struct inet6_ifaddr *ifa6 = ptr; in6.sin6_family = AF_INET6; in6.sin6_addr = ifa6->addr; ndev = ifa6->idev->dev; return addr_event(this, event, (struct sockaddr *)&in6, ndev); } static struct notifier_block nb_netdevice = { .notifier_call = netdevice_event }; static struct notifier_block nb_inetaddr = { .notifier_call = inetaddr_event }; static struct notifier_block nb_inet6addr = { .notifier_call = inet6addr_event }; int __init roce_gid_mgmt_init(void) { gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); if (!gid_cache_wq) return -ENOMEM; register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); /* We relay on the netdevice notifier to enumerate all * existing devices in the system. Register to this notifier * last to make sure we will not miss any IP add/del * callbacks. */ register_netdevice_notifier(&nb_netdevice); return 0; } void __exit roce_gid_mgmt_cleanup(void) { if (IS_ENABLED(CONFIG_IPV6)) unregister_inet6addr_notifier(&nb_inet6addr); unregister_inetaddr_notifier(&nb_inetaddr); unregister_netdevice_notifier(&nb_netdevice); /* Ensure all gid deletion tasks complete before we go down, * to avoid any reference to free'd memory. By the time * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ destroy_workqueue(gid_cache_wq); } |
| 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET An implementation of the SOCKET network access protocol. * This is the master header file for the Linux NET layer, * or, in plain English: the networking handling part of the * kernel. * * Version: @(#)net.h 1.0.3 05/25/93 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_NET_H #define _LINUX_NET_H #include <linux/stringify.h> #include <linux/random.h> #include <linux/wait.h> #include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> struct poll_table_struct; struct pipe_inode_info; struct inode; struct file; struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. * Eventually all flags will be in sk->sk_wq->flags. */ enum socket_flags { SOCKWQ_ASYNC_NOSPACE, SOCKWQ_ASYNC_WAITDATA, SOCK_NOSPACE, SOCK_SUPPORT_ZC, SOCK_CUSTOM_SOCKOPT, }; #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types * @SOCK_STREAM: stream (connection) socket * @SOCK_DGRAM: datagram (conn.less) socket * @SOCK_RAW: raw socket * @SOCK_RDM: reliably-delivered message * @SOCK_SEQPACKET: sequential packet socket * @SOCK_DCCP: Datagram Congestion Control Protocol socket * @SOCK_PACKET: linux specific way of getting packets at the dev level. * For writing rarp and other similar things on the user level. * * When adding some new socket type please * grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS * overrides this enum for binary compat reasons. */ enum sock_type { SOCK_STREAM = 1, SOCK_DGRAM = 2, SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, SOCK_DCCP = 6, SOCK_PACKET = 10, }; #endif /* ARCH_HAS_SOCKET_TYPES */ #define SOCK_MAX (SOCK_PACKET + 1) /* Mask which covers at least up to SOCK_MASK-1. The * remaining bits are used as flags. */ #define SOCK_TYPE_MASK 0xf /* Flags for socket, socketpair, accept4 */ #define SOCK_CLOEXEC O_CLOEXEC #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #define SOCK_COREDUMP O_NOCTTY /** * enum sock_shutdown_cmd - Shutdown types * @SHUT_RD: shutdown receptions * @SHUT_WR: shutdown transmissions * @SHUT_RDWR: shutdown receptions/transmissions */ enum sock_shutdown_cmd { SHUT_RD, SHUT_WR, SHUT_RDWR, }; struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation * @wq: wait queue for several uses */ struct socket { socket_state state; short type; unsigned long flags; struct file *file; struct sock *sk; const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; struct vm_area_struct; struct page; struct sockaddr; struct msghdr; struct module; struct sk_buff; struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); struct proto_ops { int family; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, struct sockaddr *myaddr, int sockaddr_len); int (*connect) (struct socket *sock, struct sockaddr *vaddr, int sockaddr_len, int flags); int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #endif int (*gettstamp) (struct socket *sock, void __user *userstamp, bool timeval, bool time32); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); /* Notes for implementing recvmsg: * =============================== * msg->msg_namelen should get updated by the recvmsg handlers * iff msg_name != NULL. It is by default 0 to prevent * returning uninitialized memory to user space. The recvfrom * handlers can assume that msg.msg_name is either NULL or has * a minimum size of sizeof(struct sockaddr_storage). */ int (*recvmsg) (struct socket *sock, struct msghdr *m, size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); /* The following functions are called internally by kernel with * sock lock already held. */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); /* This is different from read_sock(), it reads an entire skb at a time. */ int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); int (*set_rcvlowat)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ type dst = ({ __sockaddr_check_size(sizeof(*dst)); (type) src; }) struct net_proto_family { int family; int (*create)(struct net *net, struct socket *sock, int protocol, int kern); struct module *owner; }; struct iovec; struct kvec; enum { SOCK_WAKE_IO, SOCK_WAKE_WAITD, SOCK_WAKE_SPACE, SOCK_WAKE_URG, }; int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); struct socket *sockfd_lookup(int fd, int *err); struct socket *sock_from_file(struct file *file); #define sockfd_put(sock) fput(sock->file) int net_ratelimit(void); #define net_ratelimited_function(function, ...) \ do { \ if (net_ratelimit()) \ function(__VA_ARGS__); \ } while (0) #define net_emerg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_emerg, fmt, ##__VA_ARGS__) #define net_alert_ratelimited(fmt, ...) \ net_ratelimited_function(pr_alert, fmt, ##__VA_ARGS__) #define net_crit_ratelimited(fmt, ...) \ net_ratelimited_function(pr_crit, fmt, ##__VA_ARGS__) #define net_err_ratelimited(fmt, ...) \ net_ratelimited_function(pr_err, fmt, ##__VA_ARGS__) #define net_notice_ratelimited(fmt, ...) \ net_ratelimited_function(pr_notice, fmt, ##__VA_ARGS__) #define net_warn_ratelimited(fmt, ...) \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define net_dbg_ratelimited(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ net_ratelimit()) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else #define net_dbg_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) /* * E.g. XFS meta- & log-data is in slab pages, or bcache meta * data pages, or other high order pages allocated by * __get_free_pages() without __GFP_COMP, which have a page_count * of 0 and/or have PageSlab() set. We cannot use send_page for * those, as that does get_page(); put_page(); and would cause * either a VM_BUG directly, or __page_cache_release a page that * would actually still be referenced by someone, leading to some * obscure delayed Oops somewhere else. */ static inline bool sendpage_ok(struct page *page) { return !PageSlab(page) && page_count(page) >= 1; } /* * Check sendpage_ok on contiguous pages. */ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) { struct page *p = page + (offset >> PAGE_SHIFT); size_t count = 0; while (count < len) { if (!sendpage_ok(p)) return false; p++; count += PAGE_SIZE; } return true; } int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen); int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); /* Routine returns the IP overhead imposed by a (caller-protected) socket. */ u32 kernel_sock_ip_overhead(struct sock *sk); #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ "-type-" __stringify(type)) #define MODULE_ALIAS_NET_PF_PROTO_NAME(pf, proto, name) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ name) #endif /* _LINUX_NET_H */ |
| 8 8 6 8 8 14 13 14 8 6 6 6 6 6 8 6 8 8 446 63 12 12 12 4 4 12 4 12 12 1 1 446 446 446 446 372 446 446 138 63 446 446 2 446 446 436 446 446 491 491 491 240 491 73 490 491 491 422 422 422 422 239 186 162 162 238 232 34 239 491 60 44 20 59 59 44 217 317 4 2 4 4 8 8 8 6 6 6 5 6 6 478 186 466 169 33 33 21 287 287 478 478 477 478 478 477 478 478 478 478 478 34 34 8 478 8 8 1 8 478 8 478 478 373 373 373 373 58 58 373 58 58 58 58 58 58 58 58 372 478 58 478 463 121 463 122 463 463 14 12 9 475 472 456 43 43 447 447 447 447 5 446 63 446 436 421 421 421 421 447 20 19 447 14 14 14 439 447 446 42 447 300 300 69 5 69 69 69 69 118 177 177 287 287 286 287 120 287 287 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 828 829 830 830 828 829 6 8 7 7 7 7 7 7 7 7 7 5 7 8 8 6 6 6 6 6 6 6 6 6 6 6 3 3 3 6 6 6 6 6 6 6 6 6 6 6 5 6 6 6 6 6 6 469 279 113 113 113 279 279 488 304 470 470 470 470 470 6 6 470 470 5 6 3 6 6 8 6 5 6 6 6 6 6 6 6 3 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 2 6 10 10 100 100 100 2 6 6 6 6 6 10 10 5 5 5 5 5 5 5 5 4 5 2 66 9 5 5 5 5 58 58 58 58 58 58 58 58 58 161 2 2 2 2 2 2 2 2 2 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 6 6 5 5 5 5 1 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 1 1 1 1 1 1 1 1 5 5 5 5 5 4 5 5 5 5 5 5 5 5 2 2 2 2 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 4 4 5 5 5 4 5 5 5 1 1 1 1 1 1 1 5 4 5 5 5 5 5 5 5 5 5 1 1 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 12 12 11 11 12 12 11 11 12 12 6 6 6 6 6 6 6 6 6 6 1 6 5 6 6 5 6 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 4 5 4 4 4 4 2 2 2 4 4 4 4 2 2 2 2 2 4 4 2 5 5 5 5 5 5 5 5 5 5 5 4 2 2 2 2 1 2 2 3 6 6 6 6 6 6 6 6 5 5 5 6 6 5 5 6 5 5 6 6 6 5 6 6 6 6 6 6 6 6 3 6 6 6 6 6 6 5 6 6 6 6 6 6 6 6 6 6 6 6 6 6 1 6 6 6 6 1 6 6 6 6 6 6 6 6 6 6 6 6 6 4 4 4 2 2 4 3 6 6 6 6 6 6 2 6 5 6 6 6 6 6 6 6 6 6 6 6 6 5 2 2 6 4 6 6 6 6 2 2 6 2 6 6 6 5 6 8 4 4 4 4 4 4 4 4 4 4 4 4 4 5 5 4 4 4 4 4 4 4 4 4 1 2 1 2 5 5 5 5 5 5 6 6 6 6 4 5 5 4 1 3 5 35 34 35 35 35 35 35 32 35 35 35 35 35 34 34 35 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 35 35 35 35 35 35 35 33 2 35 35 35 35 35 35 2 35 8 8 2 6 6 6 6 3 3 3 6 8 38 2 2 2 2 2 2 2 2 8 6 6 6 6 6 6 6 6 6 5 4 3 6 8 6 3 8 8 8 8 8 8 8 8 8 8 8 8 7 8 7 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 2 8 8 7 8 8 8 8 8 8 8 5 5 5 8 8 8 8 8 8 8 7 7 7 7 7 7 7 7 7 7 7 7 8 8 8 8 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; #ifdef CONFIG_MEMCG /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ int *proactive_swappiness; #endif /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Not allow cache_trim_mode to be turned on as part of reclaim? */ unsigned int no_cache_trim_mode:1; /* Has cache_trim_mode failed at least once? */ unsigned int cache_trim_mode_failed:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; /* Shared cgroup tree walk failed, rescan the whole tree */ unsigned int memcg_full_walk:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { if (sc->proactive && sc->proactive_swappiness) return *sc->proactive_swappiness; return mem_cgroup_swappiness(memcg); } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { return READ_ONCE(vm_swappiness); } #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to * and including the specified highidx * @zone: The current zone in the iterator * @pgdat: The pgdat which node_zones are being iterated * @idx: The index variable * @highidx: The index of the highest zone to return * * This macro iterates through all managed zones up to and including the specified highidx. * The zone iterator enters an invalid state after macro call and must be reinitialized * before it can be used again. */ #define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx) \ for ((idx) = 0, (zone) = (pgdat)->node_zones; \ (idx) <= (highidx); \ (idx)++, (zone)++) \ if (!managed_zone(zone)) \ continue; \ else static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc, struct mem_cgroup *memcg) { int demotion_nid; if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; demotion_nid = next_demotion_node(nid); if (demotion_nid == NUMA_NO_NODE) return false; /* If demotion node isn't in the cgroup's mems_allowed, fall back */ return mem_cgroup_node_allowed(memcg, demotion_nid); } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc, memcg); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); /* * If there are no reclaimable file-backed or anonymous pages, * ensure zones with sufficient free pages are not skipped. * This prevents zones like DMA32 from being ignored in reclaim * scenarios where they can still help alleviate memory pressure. */ if (nr == 0) nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; struct zone *zone; for_each_managed_zone_pgdat(zone, lruvec_pgdat(lruvec), zid, zone_idx) { if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } #define CHECK_RECLAIMER_OFFSET(type) \ do { \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGDEMOTE_##type - PGDEMOTE_KSWAPD); \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGSCAN_##type - PGSCAN_KSWAPD); \ } while (0) static int reclaimer_offset(struct scan_control *sc) { CHECK_RECLAIMER_OFFSET(DIRECT); CHECK_RECLAIMER_OFFSET(KHUGEPAGED); CHECK_RECLAIMER_OFFSET(PROACTIVE); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; if (sc->proactive) return PGSTEAL_PROACTIVE - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; struct zone *zone; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for_each_managed_zone_pgdat(zone, pgdat, i, MAX_NR_ZONES - 1) { reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { int (*writeout)(struct folio *, struct writeback_control *); /* * We no longer attempt to writeback filesystem folios here, other * than tmpfs/shmem. That's taken care of in page-writeback. * If we find a dirty filesystem folio at the end of the LRU list, * typically that means the filesystem is saturating the storage * with contiguous writes and telling it to write a folio here * would only make the situation worse by injecting an element * of random access. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (shmem_mapping(mapping)) writeout = shmem_writeout; else if (folio_test_anon(folio)) writeout = swap_writeout; else return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; /* * The large shmem folio can be split if CONFIG_THP_SWAP is * not enabled or contiguous swap entries are failed to * allocate. */ if (shmem_mapping(mapping) && folio_test_large(folio)) wbc.list = folio_list; folio_set_reclaim(folio); res = writeout(folio, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __delete_from_swap_cache(folio, swap, shadow); memcg1_swapout(folio, swap); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; #ifdef CONFIG_LRU_GEN /* * Only used on a mapped folio in the eviction (rmap walk) path, where promotion * needs to be done by taking the folio off the LRU list and then adding it back * with PG_active set. In contrast, the aging (page table walk) path uses * folio_update_gen(). */ static bool lru_gen_set_refs(struct folio *folio) { /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return false; } set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset)); return true; } #else static bool lru_gen_set_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* * There are two cases to consider. * 1) Rmap lock contention: rotate. * 2) Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (lru_gen_enabled()) { if (!referenced_ptes) return FOLIOREF_RECLAIM; return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP; } referenced_folio = folio_test_clear_referenced(folio); if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } struct folio *alloc_migrate_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask, .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_migrate_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references, struct mem_cgroup *memcg) { struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc, memcg); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; if (folio_contain_hwpoisoned_page(folio)) { unmap_poisoned_folio(folio, folio_pfn(folio), false); folio_unlock(folio); folio_put(folio); continue; } VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs), or the folio belongs to a mapping where * waiting on writeback during reclaim may lead to a deadlock. * In this case mark the folio for immediate reclaim and * continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { mapping = folio_mapping(folio); /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask) || (mapping && mapping_writeback_may_deadlock_on_reclaim(mapping))) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, 1, NULL)) goto activate_locked; /* * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ if (data_race(!list_empty(&folio->_deferred_list) && folio_test_partially_mapped(folio)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) { int __maybe_unused order = folio_order(folio); if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages >= HPAGE_PMD_NR) { count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } #endif count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) goto activate_locked_split; } /* * Normally the folio will be dirtied in unmap because its * pte should be dirty. A special case is MADV_FREE page. The * page's pte could have dirty bit cleared but the folio's * SwapBacked flag is still set because clearing the dirty bit * and SwapBacked flag has no lock protected. For such folio, * unmap will not set dirty bit for it, so folio reclaim will * not write the folio out. This can cause data corruption when * the folio is swapped in later. Always setting the dirty flag * for the folio solves the problem. */ folio_mark_dirty(folio); } } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; /* * Without TTU_SYNC, try_to_unmap will only begin to * hold PTL from the first present PTE within a large * folio. Some initial PTEs might be skipped due to * races with parallel PTE writes in which PTEs can be * cleared temporarily before being written new present * values. This will lead to a large folio is still * mapped while some subpages have been partially * unmapped after try_to_unmap; TTU_SYNC helps * try_to_unmap acquire PTL from the first PTE, * eliminating the influence of temporary PTE values. */ if (folio_test_large(folio)) flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug, folio_list)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: /* * If shmem folio is split when writeback to swap, * the tail pages will make their own pass through * this function and be accounted then. */ if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } goto activate_locked; case PAGE_SUCCESS: if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); } continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_demoted = demote_folio_list(&demote_folios, pgdat); nr_reclaimed += nr_demoted; stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true, NULL); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0, total_scan = 0, scan = 0; unsigned long nr_pages; unsigned long max_nr_skipped = 0; LIST_HEAD(folios_skipped); while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; /* Using max_nr_skipped to prevent hard LOCKUP*/ if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED && (folio_zonenum(folio) > sc->reclaim_idx)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; max_nr_skipped++; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static bool too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return false; if (!writeback_throttling_sane(sc)) return false; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; struct folio_batch free_folios; folio_batch_init(&free_folios); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } if (free_folios.nr) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false, lruvec_memcg(lruvec)); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); __count_vm_events(PGDEACTIVATE, nr_deactivate); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); if (nr_rotated) lru_note_cost(lruvec, file, 0, nr_rotated); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true, NULL); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat); return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats in rate-limited way as we don't need * most accurate stats here. We may switch to regular stats flushing * in the future once it is cheap enough. */ mem_cgroup_flush_stats_ratelimited(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) && !sc->no_cache_trim_mode) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; struct zone *zone; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for_each_managed_zone_pgdat(zone, pgdat, z, MAX_NR_ZONES - 1) { total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } static inline void calculate_pressure_balance(struct scan_control *sc, int swappiness, u64 *fraction, u64 *denominator) { unsigned long anon_cost, file_cost, total_cost; unsigned long ap, fp; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[WORKINGSET_ANON] = ap; fraction[WORKINGSET_FILE] = fp; *denominator = ap + fp; } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* Proactive reclaim initiated by userspace for anonymous memory only */ if (swappiness == SWAPPINESS_ANON_ONLY) { WARN_ON_ONCE(!sc->proactive); scan_balance = SCAN_ANON; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now to make sure * a streaming file access pattern doesn't cause swapping. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; calculate_pressure_balance(sc, swappiness, fraction, &denominator); out: for_each_evictable_lru(lru) { bool file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct lruvec *lruvec, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(lruvec_pgdat(lruvec)->node_id, sc, lruvec_memcg(lruvec)); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } /* Get the min/max evictable type based on swappiness */ #define min_type(swappiness) (!(swappiness)) #define max_type(swappiness) ((swappiness) < SWAPPINESS_ANON_ONLY) #define evictable_min_seq(min_seq, swappiness) \ min((min_seq)[min_type(swappiness)], (min_seq)[max_type(swappiness)]) #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define for_each_evictable_type(type, swappiness) \ for ((type) = min_type(swappiness); (type) <= max_type(swappiness); (type)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc, memcg) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { int type; for (type = 0; type < ANON_AND_FILE; type++) { int n = get_nr_gens(lruvec, type); if (n < MIN_NR_GENS || n > MAX_NR_GENS) return false; } return true; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lruvec *lruvec = walk->lruvec; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); hist = lru_hist_from_seq(walk->seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(walk->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq); if (walk->seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < seq); if (seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { int i; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->gain = gain; pos->refaulted = pos->total = 0; for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) { pos->refaulted += lrugen->avg_refaulted[type][i] + atomic_long_read(&lrugen->refaulted[hist][type][i]); pos->total += lrugen->avg_total[type][i] + lrugen->protected[hist][type][i] + atomic_long_read(&lrugen->evicted[hist][type][i]); } } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + lrugen->protected[hist][type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); WRITE_ONCE(lrugen->protected[hist][type][tier], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return -1; } do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) return -1; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lruvec *lruvec = walk->lruvec; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->swappiness; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->swappiness; if (walk->swappiness > MAX_SWAPPINESS) return true; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct folio *folio = pfn_folio(pfn); if (folio_lru_gen(folio) < 0) return NULL; if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg(folio) != memcg) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio, int new_gen, bool dirty) { int old_gen; if (!folio) return; if (dirty && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } else if (lru_gen_set_refs(folio)) { old_gen = folio_lru_gen(folio); if (old_gen >= 0 && old_gen != new_gen) folio_activate(folio); } } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; bool dirty; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); pmd_t pmdval; pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return true; } if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { pte_unmap_unlock(pte, ptl); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(args->vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; walk->mm_stats[MM_LEAF_YOUNG]++; } walk_update_folio(walk, last, gen, dirty); last = NULL; if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; bool dirty; pmd_t *pmd; spinlock_t *ptl; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; if (!pmd_present(pmd[i])) goto next; if (!pmd_trans_huge(pmd[i])) { if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); if (pfn == -1) goto next; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) goto next; if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pmd_dirty(pmd[i])) dirty = true; walk->mm_stats[MM_LEAF_YOUNG]++; next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; if (pfn != -1) walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct lruvec *lruvec = walk->lruvec; walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->seq != max_seq) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); /* For file type, skip the check if swappiness is anon only */ if (type && (swappiness == SWAPPINESS_ANON_ONLY)) goto done; /* For anon type, skip the check if swappiness is zero (file only) */ if (!type && !swappiness) goto done; /* prevent cold/hot inversion if the type is evictable */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int tier = lru_tier_from_refs(refs, workingset); int delta = folio_nr_pages(folio); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness) { int gen, type, zone; bool success = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for_each_evictable_type(type, swappiness) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_folio */ if (swappiness && swappiness <= MAX_SWAPPINESS) { unsigned long seq = lrugen->max_seq - MIN_NR_GENS; if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq) min_seq[LRU_GEN_ANON] = seq; else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq) min_seq[LRU_GEN_FILE] = seq; } for_each_evictable_type(type, swappiness) { if (min_seq[type] <= lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = seq == lrugen->max_seq; if (!success) goto unlock; for (type = 0; type < ANON_AND_FILE; type++) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; if (inc_min_seq(lruvec, type, swappiness)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, seq, swappiness); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk->lruvec = lruvec; walk->seq = seq; walk->swappiness = swappiness; walk->force_scan = force_scan; do { success = iterate_mm_list(walk, &mm); if (mm) walk_mm(mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, seq, swappiness); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); /* * The estimation is based on LRU pages only, so cap it to prevent * overshoots of shrinker objects by large margins. */ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; int swappiness = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; int swappiness = get_swappiness(lruvec, sc); struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness)); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); mem_cgroup_calculate_protection(NULL, memcg); if (!reclaimable) reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; bool dirty; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; struct folio *last = NULL; int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (!ptep_clear_young_notify(vma, addr, pte)) return false; if (spin_is_contended(pvmw->ptl)) return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start == PAGE_SIZE) return true; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; } walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); return true; } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; bool dirty, writeback; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); int tier = lru_tier_from_refs(refs, workingset); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) { gen = folio_inc_gen(lruvec, folio, false); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } return true; } /* ineligible */ if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } dirty = folio_test_dirty(folio); writeback = folio_test_writeback(folio); if (type == LRU_GEN_FILE && dirty) { sc->nr.file_taken += delta; if (!writeback) sc->nr.unqueued_dirty += delta; } /* waiting for writeback */ if (writeback || (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swap constrained */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } count_memcg_events(memcg, item, isolated); count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); if (type == LRU_GEN_FILE) sc->nr.file_taken += isolated; /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (2:3). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 2, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 3, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness) { struct ctrl_pos sp, pv; if (swappiness <= MIN_SWAPPINESS + 1) return LRU_GEN_FILE; if (swappiness >= MAX_SWAPPINESS) return LRU_GEN_ANON; /* * Compare the sum of all tiers of anon with that of file to determine * which type to scan. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv); return positive_ctrl_err(&sp, &pv); } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type = get_type_to_scan(lruvec, swappiness); for_each_evictable_type(i, swappiness) { int scanned; int tier = get_tier_idx(lruvec, type); *type_scanned = type; scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) return scanned; type = !type; } return 0; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false, memcg); sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { DEFINE_MIN_SEQ(lruvec); if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) && !folio_test_dirty(folio) && !folio_test_writeback(folio)) { list_move(&folio->lru, &clean); continue; } /* don't add rejected folios to the oldest generation */ if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type]) set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active)); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) { walk->lruvec = lruvec; reset_batch_size(walk); } __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, int swappiness, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long size = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); *nr_to_scan = 0; /* have to run aging, since eviction is not possible anymore */ if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq) return true; for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } *nr_to_scan = size; /* better to run aging even though eviction is still possible */ return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { bool success; unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) return nr_to_scan; /* try to get away with not aging at the default priority */ if (!success || sc->priority == DEF_PRIORITY) return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* * If too many file cache in the coldest generation can't be evicted * due to being dirty, wake up the flusher. */ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: if (sc->nr_reclaimed > reclaimed) pgdat->kswapd_failures = 0; } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); n[2] = READ_ONCE(lrugen->protected[hist][type][tier]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2); else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { DEFINE_MAX_SEQ(lruvec); if (seq > max_seq) return -EINVAL; return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < evictable_min_seq(min_seq, swappiness)) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); else if (swappiness > SWAPPINESS_ANON_ONLY) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd, swap_string[5]; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %4s %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, swap_string, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } if (n == 4) { swappiness = -1; } else if (!strcmp("max", swap_string)) { /* set by userspace for anonymous memory only */ swappiness = SWAPPINESS_ANON_ONLY; } else { err = kstrtouint(swap_string, 0, &swappiness); if (err) break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec, sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; struct zone *zone; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for_each_managed_zone_pgdat(zone, pgdat, z, sc->reclaim_idx) { unsigned long watermark = min_wmark_pages(zone); /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, watermark, sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, watermark, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, }; struct mem_cgroup_reclaim_cookie *partial = &reclaim; struct mem_cgroup *memcg; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree, using an iterator state that * persists across invocations. This strikes a balance between * fairness and allocation latency. * * For kswapd, reliable forward progress is more important * than a quick return to idle. Always do full walks. */ if (current_is_kswapd() || sc->memcg_full_walk) partial = NULL; memcg = mem_cgroup_iter(target_memcg, NULL, partial); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(target_memcg, memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(target_memcg, memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); /* If partial walks are allowed, bail once goal is reached */ if (partial && sc->nr_reclaimed >= sc->nr_to_reclaim) { mem_cgroup_iter_break(target_memcg, memcg); break; } } while ((memcg = mem_cgroup_iter(target_memcg, memcg, partial))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { memset(&sc->nr, 0, sizeof(sc->nr)); lru_gen_shrink_node(pgdat, sc); return; } target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, nr_node_reclaimed); if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; else if (sc->cache_trim_mode) sc->cache_trim_mode_failed = 1; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; if (!gfp_compaction_allowed(sc->gfp_mask)) return false; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return true; /* * Direct reclaim usually targets the min watermark, but compaction * takes time to run and there are potentially other callers using the * pages just freed. So target a higher buffer to give compaction a * reasonable chance of completing and allocating the pages. * * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone); if (compaction_suitable(zone, sc->order, watermark, sc->reclaim_idx)) return true; return false; } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree to meet the reclaim goal while * keeping latency low. Since the iterator state is shared * among all direct reclaim invocations (to retain fairness * among cgroups), though, high concurrency can result in * individual threads not seeing enough cgroups to make * meaningful forward progress. Avoid false OOMs in this case. */ if (!sc->memcg_full_walk) { sc->priority = initial_priority; sc->memcg_full_walk = 1; goto retry; } /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for_each_managed_zone_pgdat(zone, pgdat, i, ZONE_NORMAL) { if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state_snapshot(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .proactive_swappiness = swappiness, .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!can_age_anon_pages(lruvec, sc)) return; if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { enum zone_stat_item item; unsigned long free_pages; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = promo_wmark_pages(zone); else mark = high_wmark_pages(zone); /* * In defrag_mode, watermarks must be met in whole * blocks to avoid polluting allocator fallbacks. * * However, kswapd usually cannot accomplish this on * its own and needs kcompactd support. Once it's * reclaimed a compaction gap, and kswapd_shrink_node * has dropped order, simply ensure there are enough * base pages for compaction, wake kcompactd & sleep. */ if (defrag_mode && order) item = NR_FREE_PAGES_BLOCKS; else item = NR_FREE_PAGES; /* * When there is a high number of CPUs in the system, * the cumulative error from the vmstat per-cpu cache * can blur the line between the watermarks. In that * case, be safe and get an accurate snapshot. * * TODO: NR_FREE_PAGES_BLOCKS moves in steps of * pageblock_nr_pages, while the vmstat pcp threshold * is limited to 125. On many configurations that * counter won't actually be per-cpu cached. But keep * things simple for now; revisit when somebody cares. */ free_pages = zone_page_state(zone, item); if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark) free_pages = zone_page_state_snapshot(zone, item); if (__zone_watermark_ok(zone, order, mark, highest_zoneidx, 0, free_pages)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_NODE_CONGESTED, &lruvec->flags); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; unsigned long nr_reclaimed = sc->nr_reclaimed; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for_each_managed_zone_pgdat(zone, pgdat, z, sc->reclaim_idx) { sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; /* account for progress from mm_account_reclaimed_pages() */ return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; bool was_frozen; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = kthread_freezable_should_stop(&was_frozen); __fs_reclaim_acquire(_THIS_IP_); if (was_frozen || ret) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); /* * Restart only if it went through the priority loop all the way, * but cache_trim_mode didn't work. */ if (!sc.nr_reclaimed && sc.priority < 1 && !sc.no_cache_trim_mode && sc.cache_trim_mode_failed) { sc.no_cache_trim_mode = 1; goto restart; } if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool was_frozen; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); if (kthread_freezable_should_stop(&was_frozen)) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (was_frozen) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void __meminit kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; } else { wake_up_process(pgdat->kswapd); } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static const struct ctl_table vmscan_sysctl_table[] = { { .procname = "swappiness", .data = &vm_swappiness, .maxlen = sizeof(vm_swappiness), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_NUMA { .procname = "zone_reclaim_mode", .data = &node_reclaim_mode, .maxlen = sizeof(node_reclaim_mode), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, } #endif }; static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); register_sysctl_init("vm", vmscan_sysctl_table); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit_lock(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (ret) count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS); else count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 16 16 1 16 15 15 15 15 16 22 22 20 21 4 2 2 4 3 9 5 5 9 8 6 9 8 4 4 3 7 7 7 7 2 21 21 26 27 26 24 3 2 1 3 2 9 8 2 10 9 8 10 13 10 3 2 12 12 12 12 1 27 14 9 15 15 15 9 4 8 6 12 4 12 4 11 14 15 1 15 5 5 5 2 3 2 4 4 1 1 5 48 47 47 83 47 1 47 33 29 33 33 33 29 19 17 32 28 21 17 32 18 10 2 30 32 32 32 33 1 33 13 12 12 8 7 4 11 11 11 13 1 13 45 38 47 47 47 47 12 7 2 23 5 41 28 30 42 6 40 42 42 35 23 41 39 41 38 41 41 41 45 1 47 7 5 5 2 24 17 25 25 25 25 6 6 1 10 5 17 13 12 20 7 16 20 20 14 20 17 20 16 20 25 2 25 5 5 5 5 14 1 13 13 10 9 10 9 5 14 9 14 14 1 12 12 9 8 10 8 4 14 8 14 54 8 5 3 2 2 2 5 1 1 1 4 10 9 6 10 10 9 9 9 7 8 3 5 8 8 2 1 6 7 2 9 9 10 13 13 10 3 1 1 11 13 10 3 6 6 5 3 3 1 1 4 6 3 1 1 1 1 1 1 3 2 3 3 3 3 4 4 3 4 2 6 6 5 6 3 17 14 11 10 4 12 7 2 8 8 1 7 4 16 4 3 3 2 3 2 1 9 3 3 1 1 1 2 1 10 9 1 1 9 10 10 1 9 2 9 7 7 7 3 2 1 7 3 11 11 7 10 10 1 9 8 7 7 5 7 7 7 9 9 9 7 8 5 10 6 6 2 5 6 2 6 5 3 2 1 36 35 36 36 34 33 33 34 33 32 29 36 6 2 4 3 2 4 3 2 4 56 53 56 45 6 47 44 6 38 4 37 35 35 2 1 1 3 7 2 6 4 4 2 2 17 28 16 35 35 3 1 1 1 2 1 1 1 4 22 18 21 1 18 4 1 17 19 19 19 17 10 3 12 10 8 8 6 5 4 2 5 3 2 2 1 374 374 376 2 1 3 1 2 1 1 1 1 1 1 1 13 2 2 1 2 1 2 2 1 1 7 6 2 1 3 1 2 1 1 3 2 1 56 4 4 3 2 3 1 2 1 2 1 5 5 5 1 5 7 6 14 13 3 2 2 1 1 1 2 2 1 18 88 12 3 22 3 2 31 30 29 18 30 1 1 2 1 2 1 2 1 5 4 1 6 7 4 3 4 5 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h |