man2/madvise.2

   1 .\" Copyright (C) 2001 David Gómez <davidge@jazzfree.com>
   2 .\"
   3 .\" SPDX-License-Identifier: Linux-man-pages-copyleft
   4 .\"
   5 .\" Based on comments from mm/filemap.c. Last modified on 10-06-2001
   6 .\" Modified, 25 Feb 2002, Michael Kerrisk, <mtk.manpages@gmail.com>
   7 .\"     Added notes on MADV_DONTNEED
   8 .\" 2010-06-19, mtk, Added documentation of MADV_MERGEABLE and
   9 .\"     MADV_UNMERGEABLE
  10 .\" 2010-06-15, Andi Kleen, Add documentation of MADV_HWPOISON.
  11 .\" 2010-06-19, Andi Kleen, Add documentation of MADV_SOFT_OFFLINE.
  12 .\" 2011-09-18, Doug Goldstein <cardoe@cardoe.com>
  13 .\"     Document MADV_HUGEPAGE and MADV_NOHUGEPAGE
  14 .\"
  15 .TH MADVISE 2 (date) "Linux man-pages (unreleased)"
  16 .SH NAME
  17 madvise \- give advice about use of memory
  18 .SH LIBRARY
  19 Standard C library
  20 .RI ( libc ", " \-lc )
  21 .SH SYNOPSIS
  22 .nf
  23 .B #include <sys/mman.h>
  24 .PP
  25 .BI "int madvise(void *" addr ", size_t " length ", int " advice );
  26 .fi
  27 .PP
  28 .RS -4
  29 Feature Test Macro Requirements for glibc (see
  30 .BR feature_test_macros (7)):
  31 .RE
  32 .PP
  33 .BR madvise ():
  34 .nf
  35     Since glibc 2.19:
  36         _DEFAULT_SOURCE
  37     Up to and including glibc 2.19:
  38         _BSD_SOURCE
  39 .fi
  40 .SH DESCRIPTION
  41 The
  42 .BR madvise ()
  43 system call is used to give advice or directions to the kernel
  44 about the address range beginning at address
  45 .I addr
  46 and with size
  47 .IR length .
  48 .BR madvise ()
  49 only operates on whole pages, therefore
  50 .I addr
  51 must be page-aligned.
  52 The value of
  53 .I length
  54 is rounded up to a multiple of page size.
  55 In most cases,
  56 the goal of such advice is to improve system or application performance.
  57 .PP
  58 Initially, the system call supported a set of "conventional"
  59 .I advice
  60 values, which are also available on several other implementations.
  61 (Note, though, that
  62 .BR madvise ()
  63 is not specified in POSIX.)
  64 Subsequently, a number of Linux-specific
  65 .I advice
  66 values have been added.
  67 .\"
  68 .\" ======================================================================
  69 .\"
  70 .SS Conventional advice values
  71 The
  72 .I advice
  73 values listed below
  74 allow an application to tell the kernel how it expects to use
  75 some mapped or shared memory areas, so that the kernel can choose
  76 appropriate read-ahead and caching techniques.
  77 These
  78 .I advice
  79 values do not influence the semantics of the application
  80 (except in the case of
  81 .BR MADV_DONTNEED ),
  82 but may influence its performance.
  83 All of the
  84 .I advice
  85 values listed here have analogs in the POSIX-specified
  86 .BR posix_madvise (3)
  87 function, and the values have the same meanings, with the exception of
  88 .BR MADV_DONTNEED .
  89 .PP
  90 The advice is indicated in the
  91 .I advice
  92 argument, which is one of the following:
  93 .TP
  94 .B MADV_NORMAL
  95 No special treatment.
  96 This is the default.
  97 .TP
  98 .B MADV_RANDOM
  99 Expect page references in random order.
 100 (Hence, read ahead may be less useful than normally.)
 101 .TP
 102 .B MADV_SEQUENTIAL
 103 Expect page references in sequential order.
 104 (Hence, pages in the given range can be aggressively read ahead,
 105 and may be freed soon after they are accessed.)
 106 .TP
 107 .B MADV_WILLNEED
 108 Expect access in the near future.
 109 (Hence, it might be a good idea to read some pages ahead.)
 110 .TP
 111 .B MADV_DONTNEED
 112 Do not expect access in the near future.
 113 (For the time being, the application is finished with the given range,
 114 so the kernel can free resources associated with it.)
 115 .IP
 116 After a successful
 117 .B MADV_DONTNEED
 118 operation,
 119 the semantics of memory access in the specified region are changed:
 120 subsequent accesses of pages in the range will succeed, but will result
 121 in either repopulating the memory contents from the
 122 up-to-date contents of the underlying mapped file
 123 (for shared file mappings, shared anonymous mappings,
 124 and shmem-based techniques such as System V shared memory segments)
 125 or zero-fill-on-demand pages for anonymous private mappings.
 126 .IP
 127 Note that, when applied to shared mappings,
 128 .B MADV_DONTNEED
 129 might not lead to immediate freeing of the pages in the range.
 130 The kernel is free to delay freeing the pages until an appropriate moment.
 131 The resident set size (RSS) of the calling process will be immediately
 132 reduced however.
 133 .IP
 134 .B MADV_DONTNEED
 135 cannot be applied to locked pages, or
 136 .B VM_PFNMAP
 137 pages.
 138 (Pages marked with the kernel-internal
 139 .B VM_PFNMAP
 140 .\" http://lwn.net/Articles/162860/
 141 flag are special memory areas that are not managed
 142 by the virtual memory subsystem.
 143 Such pages are typically created by device drivers that
 144 map the pages into user space.)
 145 .IP
 146 Support for Huge TLB pages was added in Linux v5.18.
 147 Addresses within a mapping backed by Huge TLB pages must be aligned
 148 to the underlying Huge TLB page size,
 149 and the range length is rounded up
 150 to a multiple of the underlying Huge TLB page size.
 151 .\"
 152 .\" ======================================================================
 153 .\"
 154 .SS Linux-specific advice values
 155 The following Linux-specific
 156 .I advice
 157 values have no counterparts in the POSIX-specified
 158 .BR posix_madvise (3),
 159 and may or may not have counterparts in the
 160 .BR madvise ()
 161 interface available on other implementations.
 162 Note that some of these operations change the semantics of memory accesses.
 163 .TP
 164 .BR MADV_REMOVE " (since Linux 2.6.16)"
 165 .\" commit f6b3ec238d12c8cc6cc71490c6e3127988460349
 166 Free up a given range of pages
 167 and its associated backing store.
 168 This is equivalent to punching a hole in the corresponding
 169 range of the backing store (see
 170 .BR fallocate (2)).
 171 Subsequent accesses in the specified address range will see
 172 data with a value of zero.
 173 .\" Databases want to use this feature to drop a section of their
 174 .\" bufferpool (shared memory segments) - without writing back to
 175 .\" disk/swap space.  This feature is also useful for supporting
 176 .\" hot-plug memory on UML.
 177 .IP
 178 The specified address range must be mapped shared and writable.
 179 This flag cannot be applied to locked pages, or
 180 .B VM_PFNMAP
 181 pages.
 182 .IP
 183 In the initial implementation, only
 184 .BR tmpfs (5)
 185 supported
 186 .BR MADV_REMOVE ;
 187 but since Linux 3.5,
 188 .\" commit 3f31d07571eeea18a7d34db9af21d2285b807a17
 189 any filesystem which supports the
 190 .BR fallocate (2)
 191 .B FALLOC_FL_PUNCH_HOLE
 192 mode also supports
 193 .BR MADV_REMOVE .
 194 Filesystems which do not support
 195 .B MADV_REMOVE
 196 fail with the error
 197 .BR EOPNOTSUPP .
 198 .IP
 199 Support for the Huge TLB filesystem was added in Linux v4.3.
 200 .TP
 201 .BR MADV_DONTFORK " (since Linux 2.6.16)"
 202 .\" commit f822566165dd46ff5de9bf895cfa6c51f53bb0c4
 203 .\" See http://lwn.net/Articles/171941/
 204 Do not make the pages in this range available to the child after a
 205 .BR fork (2).
 206 This is useful to prevent copy-on-write semantics from changing
 207 the physical location of a page if the parent writes to it after a
 208 .BR fork (2).
 209 (Such page relocations cause problems for hardware that
 210 DMAs into the page.)
 211 .\" [PATCH] madvise MADV_DONTFORK/MADV_DOFORK
 212 .\" Currently, copy-on-write may change the physical address of
 213 .\" a page even if the user requested that the page is pinned in
 214 .\" memory (either by mlock or by get_user_pages).  This happens
 215 .\" if the process forks meanwhile, and the parent writes to that
 216 .\" page.  As a result, the page is orphaned: in case of
 217 .\" get_user_pages, the application will never see any data hardware
 218 .\" DMA's into this page after the COW.  In case of mlock'd memory,
 219 .\" the parent is not getting the realtime/security benefits of mlock.
 220 .\"
 221 .\" In particular, this affects the Infiniband modules which do DMA from
 222 .\" and into user pages all the time.
 223 .\"
 224 .\" This patch adds madvise options to control whether memory range is
 225 .\" inherited across fork. Useful e.g. for when hardware is doing DMA
 226 .\" from/into these pages.  Could also be useful to an application
 227 .\" wanting to speed up its forks by cutting large areas out of
 228 .\" consideration.
 229 .\"
 230 .\" SEE ALSO: http://lwn.net/Articles/171941/
 231 .\" "Tweaks to madvise() and posix_fadvise()", 14 Feb 2006
 232 .TP
 233 .BR MADV_DOFORK " (since Linux 2.6.16)"
 234 Undo the effect of
 235 .BR MADV_DONTFORK ,
 236 restoring the default behavior, whereby a mapping is inherited across
 237 .BR fork (2).
 238 .TP
 239 .BR MADV_HWPOISON " (since Linux 2.6.32)"
 240 .\" commit 9893e49d64a4874ea67849ee2cfbf3f3d6817573
 241 Poison the pages in the range specified by
 242 .I addr
 243 and
 244 .I length
 245 and handle subsequent references to those pages
 246 like a hardware memory corruption.
 247 This operation is available only for privileged
 248 .RB ( CAP_SYS_ADMIN )
 249 processes.
 250 This operation may result in the calling process receiving a
 251 .B SIGBUS
 252 and the page being unmapped.
 253 .IP
 254 This feature is intended for testing of memory error-handling code;
 255 it is available only if the kernel was configured with
 256 .BR CONFIG_MEMORY_FAILURE .
 257 .TP
 258 .BR MADV_MERGEABLE " (since Linux 2.6.32)"
 259 .\" commit f8af4da3b4c14e7267c4ffb952079af3912c51c5
 260 Enable Kernel Samepage Merging (KSM) for the pages in the range specified by
 261 .I addr
 262 and
 263 .IR length .
 264 The kernel regularly scans those areas of user memory that have
 265 been marked as mergeable,
 266 looking for pages with identical content.
 267 These are replaced by a single write-protected page (which is automatically
 268 copied if a process later wants to update the content of the page).
 269 KSM merges only private anonymous pages (see
 270 .BR mmap (2)).
 271 .IP
 272 The KSM feature is intended for applications that generate many
 273 instances of the same data (e.g., virtualization systems such as KVM).
 274 It can consume a lot of processing power; use with care.
 275 See the Linux kernel source file
 276 .I Documentation/admin\-guide/mm/ksm.rst
 277 for more details.
 278 .IP
 279 The
 280 .B MADV_MERGEABLE
 281 and
 282 .B MADV_UNMERGEABLE
 283 operations are available only if the kernel was configured with
 284 .BR CONFIG_KSM .
 285 .TP
 286 .BR MADV_UNMERGEABLE " (since Linux 2.6.32)"
 287 Undo the effect of an earlier
 288 .B MADV_MERGEABLE
 289 operation on the specified address range;
 290 KSM unmerges whatever pages it had merged in the address range specified by
 291 .I addr
 292 and
 293 .IR length .
 294 .TP
 295 .BR MADV_SOFT_OFFLINE " (since Linux 2.6.33)"
 296 .\" commit afcf938ee0aac4ef95b1a23bac704c6fbeb26de6
 297 Soft offline the pages in the range specified by
 298 .I addr
 299 and
 300 .IR length .
 301 The memory of each page in the specified range is preserved
 302 (i.e., when next accessed, the same content will be visible,
 303 but in a new physical page frame),
 304 and the original page is offlined
 305 (i.e., no longer used, and taken out of normal memory management).
 306 The effect of the
 307 .B MADV_SOFT_OFFLINE
 308 operation is invisible to (i.e., does not change the semantics of)
 309 the calling process.
 310 .IP
 311 This feature is intended for testing of memory error-handling code;
 312 it is available only if the kernel was configured with
 313 .BR CONFIG_MEMORY_FAILURE .
 314 .TP
 315 .BR MADV_HUGEPAGE " (since Linux 2.6.38)"
 316 .\" commit 0af4e98b6b095c74588af04872f83d333c958c32
 317 .\" http://lwn.net/Articles/358904/
 318 .\" https://lwn.net/Articles/423584/
 319 Enable Transparent Huge Pages (THP) for pages in the range specified by
 320 .I addr
 321 and
 322 .IR length .
 323 Currently, Transparent Huge Pages work only with private anonymous pages (see
 324 .BR mmap (2)).
 325 The kernel will regularly scan the areas marked as huge page candidates
 326 to replace them with huge pages.
 327 The kernel will also allocate huge pages directly when the region is
 328 naturally aligned to the huge page size (see
 329 .BR posix_memalign (2)).
 330 .IP
 331 This feature is primarily aimed at applications that use large mappings of
 332 data and access large regions of that memory at a time (e.g., virtualization
 333 systems such as QEMU).
 334 It can very easily waste memory (e.g., a 2\ MB mapping that only ever accesses
 335 1 byte will result in 2\ MB of wired memory instead of one 4\ KB page).
 336 See the Linux kernel source file
 337 .I Documentation/admin\-guide/mm/transhuge.rst
 338 for more details.
 339 .IP
 340 Most common kernels configurations provide
 341 .BR MADV_HUGEPAGE -style
 342 behavior by default, and thus
 343 .B MADV_HUGEPAGE
 344 is normally not necessary.
 345 It is mostly intended for embedded systems, where
 346 .BR MADV_HUGEPAGE -style
 347 behavior may not be enabled by default in the kernel.
 348 On such systems,
 349 this flag can be used in order to selectively enable THP.
 350 Whenever
 351 .B MADV_HUGEPAGE
 352 is used, it should always be in regions of memory with
 353 an access pattern that the developer knows in advance won't risk
 354 to increase the memory footprint of the application when transparent
 355 hugepages are enabled.
 356 .IP
 357 The
 358 .B MADV_HUGEPAGE
 359 and
 360 .B MADV_NOHUGEPAGE
 361 operations are available only if the kernel was configured with
 362 .BR CONFIG_TRANSPARENT_HUGEPAGE .
 363 .TP
 364 .BR MADV_NOHUGEPAGE " (since Linux 2.6.38)"
 365 Ensures that memory in the address range specified by
 366 .I addr
 367 and
 368 .I length
 369 will not be backed by transparent hugepages.
 370 .TP
 371 .BR MADV_DONTDUMP " (since Linux 3.4)"
 372 .\" commit 909af768e88867016f427264ae39d27a57b6a8ed
 373 .\" commit accb61fe7bb0f5c2a4102239e4981650f9048519
 374 Exclude from a core dump those pages in the range specified by
 375 .I addr
 376 and
 377 .IR length .
 378 This is useful in applications that have large areas of memory
 379 that are known not to be useful in a core dump.
 380 The effect of
 381 .B MADV_DONTDUMP
 382 takes precedence over the bit mask that is set via the
 383 .I /proc/[pid]/coredump_filter
 384 file (see
 385 .BR core (5)).
 386 .TP
 387 .BR MADV_DODUMP " (since Linux 3.4)"
 388 Undo the effect of an earlier
 389 .BR MADV_DONTDUMP .
 390 .TP
 391 .BR MADV_FREE " (since Linux 4.5)"
 392 The application no longer requires the pages in the range specified by
 393 .I addr
 394 and
 395 .IR len .
 396 The kernel can thus free these pages,
 397 but the freeing could be delayed until memory pressure occurs.
 398 For each of the pages that has been marked to be freed
 399 but has not yet been freed,
 400 the free operation will be canceled if the caller writes into the page.
 401 After a successful
 402 .B MADV_FREE
 403 operation, any stale data (i.e., dirty, unwritten pages) will be lost
 404 when the kernel frees the pages.
 405 However, subsequent writes to pages in the range will succeed
 406 and then kernel cannot free those dirtied pages,
 407 so that the caller can always see just written data.
 408 If there is no subsequent write,
 409 the kernel can free the pages at any time.
 410 Once pages in the range have been freed, the caller will
 411 see zero-fill-on-demand pages upon subsequent page references.
 412 .IP
 413 The
 414 .B MADV_FREE
 415 operation
 416 can be applied only to private anonymous pages (see
 417 .BR mmap (2)).
 418 In Linux before version 4.12,
 419 .\" commit 93e06c7a645343d222c9a838834a51042eebbbf7
 420 when freeing pages on a swapless system,
 421 the pages in the given range are freed instantly,
 422 regardless of memory pressure.
 423 .TP
 424 .BR MADV_WIPEONFORK " (since Linux 4.14)"
 425 .\" commit d2cd9ede6e193dd7d88b6d27399e96229a551b19
 426 Present the child process with zero-filled memory in this range after a
 427 .BR fork (2).
 428 This is useful in forking servers in order to ensure
 429 that sensitive per-process data
 430 (for example, PRNG seeds, cryptographic secrets, and so on)
 431 is not handed to child processes.
 432 .IP
 433 The
 434 .B MADV_WIPEONFORK
 435 operation can be applied only to private anonymous pages (see
 436 .BR mmap (2)).
 437 .IP
 438 Within the child created by
 439 .BR fork (2),
 440 the
 441 .B MADV_WIPEONFORK
 442 setting remains in place on the specified address range.
 443 This setting is cleared during
 444 .BR execve (2).
 445 .TP
 446 .BR MADV_KEEPONFORK " (since Linux 4.14)"
 447 .\" commit d2cd9ede6e193dd7d88b6d27399e96229a551b19
 448 Undo the effect of an earlier
 449 .BR MADV_WIPEONFORK .
 450 .TP
 451 .BR MADV_COLD " (since Linux 5.4)"
 452 .\" commit 9c276cc65a58faf98be8e56962745ec99ab87636
 453 Deactivate a given range of pages.
 454 This will make the pages a more probable
 455 reclaim target should there be a memory pressure.
 456 This is a nondestructive operation.
 457 The advice might be ignored for some pages in the range when it is not
 458 applicable.
 459 .TP
 460 .BR MADV_PAGEOUT " (since Linux 5.4)"
 461 .\" commit 1a4e58cce84ee88129d5d49c064bd2852b481357
 462 Reclaim a given range of pages.
 463 This is done to free up memory occupied by these pages.
 464 If a page is anonymous, it will be swapped out.
 465 If a page is file-backed and dirty, it will be written back to the backing
 466 storage.
 467 The advice might be ignored for some pages in the range when it is not
 468 applicable.
 469 .TP
 470 .BR MADV_POPULATE_READ " (since Linux 5.14)"
 471 "Populate (prefault) page tables readable,
 472 faulting in all pages in the range just as if manually reading from each page;
 473 however,
 474 avoid the actual memory access that would have been performed after handling
 475 the fault.
 476 .IP
 477 In contrast to
 478 .BR MAP_POPULATE ,
 479 .B MADV_POPULATE_READ
 480 does not hide errors,
 481 can be applied to (parts of) existing mappings and will always populate
 482 (prefault) page tables readable.
 483 One example use case is prefaulting a file mapping,
 484 reading all file content from disk;
 485 however,
 486 pages won't be dirtied and consequently won't have to be written back to disk
 487 when evicting the pages from memory.
 488 .IP
 489 Depending on the underlying mapping,
 490 map the shared zeropage,
 491 preallocate memory or read the underlying file;
 492 files with holes might or might not preallocate blocks.
 493 If populating fails,
 494 a
 495 .B SIGBUS
 496 signal is not generated; instead, an error is returned.
 497 .IP
 498 If
 499 .B MADV_POPULATE_READ
 500 succeeds,
 501 all page tables have been populated (prefaulted) readable once.
 502 If
 503 .B MADV_POPULATE_READ
 504 fails,
 505 some page tables might have been populated.
 506 .IP
 507 .B MADV_POPULATE_READ
 508 cannot be applied to mappings without read permissions
 509 and special mappings,
 510 for example,
 511 mappings marked with kernel-internal flags such as
 512 .B VM_PFNMAP
 513 or
 514 .BR VM_IO ,
 515 or secret memory regions created using
 516 .BR memfd_secret(2) .
 517 .IP
 518 Note that with
 519 .BR MADV_POPULATE_READ ,
 520 the process can be killed at any moment when the system runs out of memory.
 521 .TP
 522 .BR MADV_POPULATE_WRITE " (since Linux 5.14)"
 523 Populate (prefault) page tables writable,
 524 faulting in all pages in the range just as if manually writing to each
 525 each page;
 526 however,
 527 avoid the actual memory access that would have been performed after handling
 528 the fault.
 529 .IP
 530 In contrast to
 531 .BR MAP_POPULATE ,
 532 MADV_POPULATE_WRITE does not hide errors,
 533 can be applied to (parts of) existing mappings and will always populate
 534 (prefault) page tables writable.
 535 One example use case is preallocating memory,
 536 breaking any CoW (Copy on Write).
 537 .IP
 538 Depending on the underlying mapping,
 539 preallocate memory or read the underlying file;
 540 files with holes will preallocate blocks.
 541 If populating fails,
 542 a
 543 .B SIGBUS
 544 signal is not generated; instead, an error is returned.
 545 .IP
 546 If
 547 .B MADV_POPULATE_WRITE
 548 succeeds,
 549 all page tables have been populated (prefaulted) writable once.
 550 If
 551 .B MADV_POPULATE_WRITE
 552 fails,
 553 some page tables might have been populated.
 554 .IP
 555 .B MADV_POPULATE_WRITE
 556 cannot be applied to mappings without write permissions
 557 and special mappings,
 558 for example,
 559 mappings marked with kernel-internal flags such as
 560 .B VM_PFNMAP
 561 or
 562 .BR VM_IO ,
 563 or secret memory regions created using
 564 .BR memfd_secret(2) .
 565 .IP
 566 Note that with
 567 .BR MADV_POPULATE_WRITE ,
 568 the process can be killed at any moment when the system runs out of memory.
 569 .SH RETURN VALUE
 570 On success,
 571 .BR madvise ()
 572 returns zero.
 573 On error, it returns \-1 and
 574 .I errno
 575 is set to indicate the error.
 576 .SH ERRORS
 577 .TP
 578 .B EACCES
 579 .I advice
 580 is
 581 .BR MADV_REMOVE ,
 582 but the specified address range is not a shared writable mapping.
 583 .TP
 584 .B EAGAIN
 585 A kernel resource was temporarily unavailable.
 586 .TP
 587 .B EBADF
 588 The map exists, but the area maps something that isn't a file.
 589 .TP
 590 .B EFAULT
 591 .I advice
 592 is
 593 .B MADV_POPULATE_READ
 594 or
 595 .BR MADV_POPULATE_WRITE ,
 596 and populating (prefaulting) page tables failed because a
 597 .B SIGBUS
 598 would have been generated on actual memory access and the reason is not a
 599 HW poisoned page
 600 (HW poisoned pages can,
 601 for example,
 602 be created using the
 603 .B MADV_HWPOISON
 604 flag described elsewhere in this page).
 605 .TP
 606 .B EINVAL
 607 .I addr
 608 is not page-aligned or
 609 .I length
 610 is negative.
 611 .\" .I length
 612 .\" is zero,
 613 .TP
 614 .B EINVAL
 615 .I advice
 616 is not a valid.
 617 .TP
 618 .B EINVAL
 619 .I advice
 620 is
 621 .B MADV_COLD
 622 or
 623 .B MADV_PAGEOUT
 624 and the specified address range includes locked, Huge TLB pages, or
 625 .B VM_PFNMAP
 626 pages.
 627 .TP
 628 .B EINVAL
 629 .I advice
 630 is
 631 .B MADV_DONTNEED
 632 or
 633 .B MADV_REMOVE
 634 and the specified address range includes locked, Huge TLB pages, or
 635 .B VM_PFNMAP
 636 pages.
 637 .TP
 638 .B EINVAL
 639 .I advice
 640 is
 641 .B MADV_MERGEABLE
 642 or
 643 .BR MADV_UNMERGEABLE ,
 644 but the kernel was not configured with
 645 .BR CONFIG_KSM .
 646 .TP
 647 .B EINVAL
 648 .I advice
 649 is
 650 .B MADV_FREE
 651 or
 652 .B MADV_WIPEONFORK
 653 but the specified address range includes file, Huge TLB,
 654 .BR MAP_SHARED ,
 655 or
 656 .B VM_PFNMAP
 657 ranges.
 658 .TP
 659 .B EINVAL
 660 .I advice
 661 is
 662 .B MADV_POPULATE_READ
 663 or
 664 .BR MADV_POPULATE_WRITE ,
 665 but the specified address range includes ranges with insufficient permissions
 666 or special mappings,
 667 for example,
 668 mappings marked with kernel-internal flags such a
 669 .B VM_IO
 670 or
 671 .BR VM_PFNMAP ,
 672 or secret memory regions created using
 673 .BR memfd_secret(2) .
 674 .TP
 675 .B EIO
 676 (for
 677 .BR MADV_WILLNEED )
 678 Paging in this area would exceed the process's
 679 maximum resident set size.
 680 .TP
 681 .B ENOMEM
 682 (for
 683 .BR MADV_WILLNEED )
 684 Not enough memory: paging in failed.
 685 .TP
 686 .B ENOMEM
 687 Addresses in the specified range are not currently
 688 mapped, or are outside the address space of the process.
 689 .TP
 690 .B ENOMEM
 691 .I advice
 692 is
 693 .B MADV_POPULATE_READ
 694 or
 695 .BR MADV_POPULATE_WRITE ,
 696 and populating (prefaulting) page tables failed because there was not enough
 697 memory.
 698 .TP
 699 .B EPERM
 700 .I advice
 701 is
 702 .BR MADV_HWPOISON ,
 703 but the caller does not have the
 704 .B CAP_SYS_ADMIN
 705 capability.
 706 .TP
 707 .B EHWPOISON
 708 .I advice
 709 is
 710 .B MADV_POPULATE_READ
 711 or
 712 .BR MADV_POPULATE_WRITE ,
 713 and populating (prefaulting) page tables failed because a HW poisoned page
 714 (HW poisoned pages can,
 715 for example,
 716 be created using the
 717 .B MADV_HWPOISON
 718 flag described elsewhere in this page)
 719 was encountered.
 720 .SH VERSIONS
 721 Since Linux 3.18,
 722 .\" commit d3ac21cacc24790eb45d735769f35753f5b56ceb
 723 support for this system call is optional,
 724 depending on the setting of the
 725 .B CONFIG_ADVISE_SYSCALLS
 726 configuration option.
 727 .SH STANDARDS
 728 .BR madvise ()
 729 is not specified by any standards.
 730 Versions of this system call, implementing a wide variety of
 731 .I advice
 732 values, exist on many other implementations.
 733 Other implementations typically implement at least the flags listed
 734 above under
 735 .IR "Conventional advice flags" ,
 736 albeit with some variation in semantics.
 737 .PP
 738 POSIX.1-2001 describes
 739 .BR posix_madvise (3)
 740 with constants
 741 .BR POSIX_MADV_NORMAL ,
 742 .BR POSIX_MADV_RANDOM ,
 743 .BR POSIX_MADV_SEQUENTIAL ,
 744 .BR POSIX_MADV_WILLNEED ,
 745 and
 746 .BR POSIX_MADV_DONTNEED ,
 747 and so on, with behavior close to the similarly named flags listed above.
 748 .SH NOTES
 749 .SS Linux notes
 750 The Linux implementation requires that the address
 751 .I addr
 752 be page-aligned, and allows
 753 .I length
 754 to be zero.
 755 If there are some parts of the specified address range
 756 that are not mapped, the Linux version of
 757 .BR madvise ()
 758 ignores them and applies the call to the rest (but returns
 759 .B ENOMEM
 760 from the system call, as it should).
 761 .\" .SH HISTORY
 762 .\" The
 763 .\" .BR madvise ()
 764 .\" function first appeared in 4.4BSD.
 765 .SH SEE ALSO
 766 .BR getrlimit (2),
 767 .BR memfd_secret (2),
 768 .BR mincore (2),
 769 .BR mmap (2),
 770 .BR mprotect (2),
 771 .BR msync (2),
 772 .BR munmap (2),
 773 .BR prctl (2),
 774 .BR process_madvise (2),
 775 .BR posix_madvise (3),
 776 .BR core (5)