man2/madvise.2

   1 .\" Copyright (C) 2001 David Gómez <davidge@jazzfree.com>
   2 .\"
   3 .\" %%%LICENSE_START(VERBATIM)
   4 .\" Permission is granted to make and distribute verbatim copies of this
   5 .\" manual provided the copyright notice and this permission notice are
   6 .\" preserved on all copies.
   7 .\"
   8 .\" Permission is granted to copy and distribute modified versions of this
   9 .\" manual under the conditions for verbatim copying, provided that the
  10 .\" entire resulting derived work is distributed under the terms of a
  11 .\" permission notice identical to this one.
  12 .\"
  13 .\" Since the Linux kernel and libraries are constantly changing, this
  14 .\" manual page may be incorrect or out-of-date.  The author(s) assume no
  15 .\" responsibility for errors or omissions, or for damages resulting from
  16 .\" the use of the information contained herein.  The author(s) may not
  17 .\" have taken the same level of care in the production of this manual,
  18 .\" which is licensed free of charge, as they might when working
  19 .\" professionally.
  20 .\"
  21 .\" Formatted or processed versions of this manual, if unaccompanied by
  22 .\" the source, must acknowledge the copyright and authors of this work.
  23 .\" %%%LICENSE_END
  24 .\"
  25 .\" Based on comments from mm/filemap.c. Last modified on 10-06-2001
  26 .\" Modified, 25 Feb 2002, Michael Kerrisk, <mtk.manpages@gmail.com>
  27 .\"     Added notes on MADV_DONTNEED
  28 .\" 2010-06-19, mtk, Added documentation of MADV_MERGEABLE and
  29 .\"     MADV_UNMERGEABLE
  30 .\" 2010-06-15, Andi Kleen, Add documentation of MADV_HWPOISON.
  31 .\" 2010-06-19, Andi Kleen, Add documentation of MADV_SOFT_OFFLINE.
  32 .\" 2011-09-18, Doug Goldstein <cardoe@cardoe.com>
  33 .\"     Document MADV_HUGEPAGE and MADV_NOHUGEPAGE
  34 .\"
  35 .TH MADVISE 2 2021-03-22 "Linux" "Linux Programmer's Manual"
  36 .SH NAME
  37 madvise \- give advice about use of memory
  38 .SH SYNOPSIS
  39 .nf
  40 .B #include <sys/mman.h>
  41 .PP
  42 .BI "int madvise(void *" addr ", size_t " length ", int " advice );
  43 .fi
  44 .PP
  45 .RS -4
  46 Feature Test Macro Requirements for glibc (see
  47 .BR feature_test_macros (7)):
  48 .RE
  49 .PP
  50 .BR madvise ():
  51 .nf
  52     Since glibc 2.19:
  53         _DEFAULT_SOURCE
  54     Up to and including glibc 2.19:
  55         _BSD_SOURCE
  56 .fi
  57 .SH DESCRIPTION
  58 The
  59 .BR madvise ()
  60 system call is used to give advice or directions to the kernel
  61 about the address range beginning at address
  62 .I addr
  63 and with size
  64 .I length
  65 bytes.
  66 In most cases,
  67 the goal of such advice is to improve system or application performance.
  68 .PP
  69 Initially, the system call supported a set of "conventional"
  70 .I advice
  71 values, which are also available on several other implementations.
  72 (Note, though, that
  73 .BR madvise ()
  74 is not specified in POSIX.)
  75 Subsequently, a number of Linux-specific
  76 .IR advice
  77 values have been added.
  78 .\"
  79 .\" ======================================================================
  80 .\"
  81 .SS Conventional advice values
  82 The
  83 .I advice
  84 values listed below
  85 allow an application to tell the kernel how it expects to use
  86 some mapped or shared memory areas, so that the kernel can choose
  87 appropriate read-ahead and caching techniques.
  88 These
  89 .I advice
  90 values do not influence the semantics of the application
  91 (except in the case of
  92 .BR MADV_DONTNEED ),
  93 but may influence its performance.
  94 All of the
  95 .I advice
  96 values listed here have analogs in the POSIX-specified
  97 .BR posix_madvise (3)
  98 function, and the values have the same meanings, with the exception of
  99 .BR MADV_DONTNEED .
 100 .PP
 101 The advice is indicated in the
 102 .I advice
 103 argument, which is one of the following:
 104 .TP
 105 .B MADV_NORMAL
 106 No special treatment.
 107 This is the default.
 108 .TP
 109 .B MADV_RANDOM
 110 Expect page references in random order.
 111 (Hence, read ahead may be less useful than normally.)
 112 .TP
 113 .B MADV_SEQUENTIAL
 114 Expect page references in sequential order.
 115 (Hence, pages in the given range can be aggressively read ahead,
 116 and may be freed soon after they are accessed.)
 117 .TP
 118 .B MADV_WILLNEED
 119 Expect access in the near future.
 120 (Hence, it might be a good idea to read some pages ahead.)
 121 .TP
 122 .B MADV_DONTNEED
 123 Do not expect access in the near future.
 124 (For the time being, the application is finished with the given range,
 125 so the kernel can free resources associated with it.)
 126 .IP
 127 After a successful
 128 .B MADV_DONTNEED
 129 operation,
 130 the semantics of memory access in the specified region are changed:
 131 subsequent accesses of pages in the range will succeed, but will result
 132 in either repopulating the memory contents from the
 133 up-to-date contents of the underlying mapped file
 134 (for shared file mappings, shared anonymous mappings,
 135 and shmem-based techniques such as System V shared memory segments)
 136 or zero-fill-on-demand pages for anonymous private mappings.
 137 .IP
 138 Note that, when applied to shared mappings,
 139 .BR MADV_DONTNEED
 140 might not lead to immediate freeing of the pages in the range.
 141 The kernel is free to delay freeing the pages until an appropriate moment.
 142 The resident set size (RSS) of the calling process will be immediately
 143 reduced however.
 144 .IP
 145 .B MADV_DONTNEED
 146 cannot be applied to locked pages, Huge TLB pages, or
 147 .BR VM_PFNMAP
 148 pages.
 149 (Pages marked with the kernel-internal
 150 .B VM_PFNMAP
 151 .\" http://lwn.net/Articles/162860/
 152 flag are special memory areas that are not managed
 153 by the virtual memory subsystem.
 154 Such pages are typically created by device drivers that
 155 map the pages into user space.)
 156 .\"
 157 .\" ======================================================================
 158 .\"
 159 .SS Linux-specific advice values
 160 The following Linux-specific
 161 .I advice
 162 values have no counterparts in the POSIX-specified
 163 .BR posix_madvise (3),
 164 and may or may not have counterparts in the
 165 .BR madvise ()
 166 interface available on other implementations.
 167 Note that some of these operations change the semantics of memory accesses.
 168 .TP
 169 .BR MADV_REMOVE " (since Linux 2.6.16)"
 170 .\" commit f6b3ec238d12c8cc6cc71490c6e3127988460349
 171 Free up a given range of pages
 172 and its associated backing store.
 173 This is equivalent to punching a hole in the corresponding byte
 174 range of the backing store (see
 175 .BR fallocate (2)).
 176 Subsequent accesses in the specified address range will see
 177 bytes containing zero.
 178 .\" Databases want to use this feature to drop a section of their
 179 .\" bufferpool (shared memory segments) - without writing back to
 180 .\" disk/swap space.  This feature is also useful for supporting
 181 .\" hot-plug memory on UML.
 182 .IP
 183 The specified address range must be mapped shared and writable.
 184 This flag cannot be applied to locked pages, Huge TLB pages, or
 185 .BR VM_PFNMAP
 186 pages.
 187 .IP
 188 In the initial implementation, only
 189 .BR tmpfs (5)
 190 was supported
 191 .BR MADV_REMOVE ;
 192 but since Linux 3.5,
 193 .\" commit 3f31d07571eeea18a7d34db9af21d2285b807a17
 194 any filesystem which supports the
 195 .BR fallocate (2)
 196 .BR FALLOC_FL_PUNCH_HOLE
 197 mode also supports
 198 .BR MADV_REMOVE .
 199 Hugetlbfs fails with the error
 200 .BR EINVAL
 201 and other filesystems fail with the error
 202 .BR EOPNOTSUPP .
 203 .TP
 204 .BR MADV_DONTFORK " (since Linux 2.6.16)"
 205 .\" commit f822566165dd46ff5de9bf895cfa6c51f53bb0c4
 206 .\" See http://lwn.net/Articles/171941/
 207 Do not make the pages in this range available to the child after a
 208 .BR fork (2).
 209 This is useful to prevent copy-on-write semantics from changing
 210 the physical location of a page if the parent writes to it after a
 211 .BR fork (2).
 212 (Such page relocations cause problems for hardware that
 213 DMAs into the page.)
 214 .\" [PATCH] madvise MADV_DONTFORK/MADV_DOFORK
 215 .\" Currently, copy-on-write may change the physical address of
 216 .\" a page even if the user requested that the page is pinned in
 217 .\" memory (either by mlock or by get_user_pages).  This happens
 218 .\" if the process forks meanwhile, and the parent writes to that
 219 .\" page.  As a result, the page is orphaned: in case of
 220 .\" get_user_pages, the application will never see any data hardware
 221 .\" DMA's into this page after the COW.  In case of mlock'd memory,
 222 .\" the parent is not getting the realtime/security benefits of mlock.
 223 .\"
 224 .\" In particular, this affects the Infiniband modules which do DMA from
 225 .\" and into user pages all the time.
 226 .\"
 227 .\" This patch adds madvise options to control whether memory range is
 228 .\" inherited across fork. Useful e.g. for when hardware is doing DMA
 229 .\" from/into these pages.  Could also be useful to an application
 230 .\" wanting to speed up its forks by cutting large areas out of
 231 .\" consideration.
 232 .\"
 233 .\" SEE ALSO: http://lwn.net/Articles/171941/
 234 .\" "Tweaks to madvise() and posix_fadvise()", 14 Feb 2006
 235 .TP
 236 .BR MADV_DOFORK " (since Linux 2.6.16)"
 237 Undo the effect of
 238 .BR MADV_DONTFORK ,
 239 restoring the default behavior, whereby a mapping is inherited across
 240 .BR fork (2).
 241 .TP
 242 .BR MADV_HWPOISON " (since Linux 2.6.32)"
 243 .\" commit 9893e49d64a4874ea67849ee2cfbf3f3d6817573
 244 Poison the pages in the range specified by
 245 .I addr
 246 and
 247 .IR length
 248 and handle subsequent references to those pages
 249 like a hardware memory corruption.
 250 This operation is available only for privileged
 251 .RB ( CAP_SYS_ADMIN )
 252 processes.
 253 This operation may result in the calling process receiving a
 254 .B SIGBUS
 255 and the page being unmapped.
 256 .IP
 257 This feature is intended for testing of memory error-handling code;
 258 it is available only if the kernel was configured with
 259 .BR CONFIG_MEMORY_FAILURE .
 260 .TP
 261 .BR MADV_MERGEABLE " (since Linux 2.6.32)"
 262 .\" commit f8af4da3b4c14e7267c4ffb952079af3912c51c5
 263 Enable Kernel Samepage Merging (KSM) for the pages in the range specified by
 264 .I addr
 265 and
 266 .IR length .
 267 The kernel regularly scans those areas of user memory that have
 268 been marked as mergeable,
 269 looking for pages with identical content.
 270 These are replaced by a single write-protected page (which is automatically
 271 copied if a process later wants to update the content of the page).
 272 KSM merges only private anonymous pages (see
 273 .BR mmap (2)).
 274 .IP
 275 The KSM feature is intended for applications that generate many
 276 instances of the same data (e.g., virtualization systems such as KVM).
 277 It can consume a lot of processing power; use with care.
 278 See the Linux kernel source file
 279 .I Documentation/admin\-guide/mm/ksm.rst
 280 for more details.
 281 .IP
 282 The
 283 .BR MADV_MERGEABLE
 284 and
 285 .BR MADV_UNMERGEABLE
 286 operations are available only if the kernel was configured with
 287 .BR CONFIG_KSM .
 288 .TP
 289 .BR MADV_UNMERGEABLE " (since Linux 2.6.32)"
 290 Undo the effect of an earlier
 291 .BR MADV_MERGEABLE
 292 operation on the specified address range;
 293 KSM unmerges whatever pages it had merged in the address range specified by
 294 .IR addr
 295 and
 296 .IR length .
 297 .TP
 298 .BR MADV_SOFT_OFFLINE " (since Linux 2.6.33)"
 299 .\" commit afcf938ee0aac4ef95b1a23bac704c6fbeb26de6
 300 Soft offline the pages in the range specified by
 301 .I addr
 302 and
 303 .IR length .
 304 The memory of each page in the specified range is preserved
 305 (i.e., when next accessed, the same content will be visible,
 306 but in a new physical page frame),
 307 and the original page is offlined
 308 (i.e., no longer used, and taken out of normal memory management).
 309 The effect of the
 310 .B MADV_SOFT_OFFLINE
 311 operation is invisible to (i.e., does not change the semantics of)
 312 the calling process.
 313 .IP
 314 This feature is intended for testing of memory error-handling code;
 315 it is available only if the kernel was configured with
 316 .BR CONFIG_MEMORY_FAILURE .
 317 .TP
 318 .BR MADV_HUGEPAGE " (since Linux 2.6.38)"
 319 .\" commit 0af4e98b6b095c74588af04872f83d333c958c32
 320 .\" http://lwn.net/Articles/358904/
 321 .\" https://lwn.net/Articles/423584/
 322 Enable Transparent Huge Pages (THP) for pages in the range specified by
 323 .I addr
 324 and
 325 .IR length .
 326 Currently, Transparent Huge Pages work only with private anonymous pages (see
 327 .BR mmap (2)).
 328 The kernel will regularly scan the areas marked as huge page candidates
 329 to replace them with huge pages.
 330 The kernel will also allocate huge pages directly when the region is
 331 naturally aligned to the huge page size (see
 332 .BR posix_memalign (2)).
 333 .IP
 334 This feature is primarily aimed at applications that use large mappings of
 335 data and access large regions of that memory at a time (e.g., virtualization
 336 systems such as QEMU).
 337 It can very easily waste memory (e.g., a 2\ MB mapping that only ever accesses
 338 1 byte will result in 2\ MB of wired memory instead of one 4\ KB page).
 339 See the Linux kernel source file
 340 .I Documentation/admin\-guide/mm/transhuge.rst
 341 for more details.
 342 .IP
 343 Most common kernels configurations provide
 344 .BR MADV_HUGEPAGE -style
 345 behavior by default, and thus
 346 .BR MADV_HUGEPAGE
 347 is normally not necessary.
 348 It is mostly intended for embedded systems, where
 349 .BR MADV_HUGEPAGE -style
 350 behavior may not be enabled by default in the kernel.
 351 On such systems,
 352 this flag can be used in order to selectively enable THP.
 353 Whenever
 354 .BR MADV_HUGEPAGE
 355 is used, it should always be in regions of memory with
 356 an access pattern that the developer knows in advance won't risk
 357 to increase the memory footprint of the application when transparent
 358 hugepages are enabled.
 359 .IP
 360 The
 361 .BR MADV_HUGEPAGE
 362 and
 363 .BR MADV_NOHUGEPAGE
 364 operations are available only if the kernel was configured with
 365 .BR CONFIG_TRANSPARENT_HUGEPAGE .
 366 .TP
 367 .BR MADV_NOHUGEPAGE " (since Linux 2.6.38)"
 368 Ensures that memory in the address range specified by
 369 .IR addr
 370 and
 371 .IR length
 372 will not be backed by transparent hugepages.
 373 .TP
 374 .BR MADV_DONTDUMP " (since Linux 3.4)"
 375 .\" commit 909af768e88867016f427264ae39d27a57b6a8ed
 376 .\" commit accb61fe7bb0f5c2a4102239e4981650f9048519
 377 Exclude from a core dump those pages in the range specified by
 378 .I addr
 379 and
 380 .IR length .
 381 This is useful in applications that have large areas of memory
 382 that are known not to be useful in a core dump.
 383 The effect of
 384 .BR MADV_DONTDUMP
 385 takes precedence over the bit mask that is set via the
 386 .I /proc/[pid]/coredump_filter
 387 file (see
 388 .BR core (5)).
 389 .TP
 390 .BR MADV_DODUMP " (since Linux 3.4)"
 391 Undo the effect of an earlier
 392 .BR MADV_DONTDUMP .
 393 .TP
 394 .BR MADV_FREE " (since Linux 4.5)"
 395 The application no longer requires the pages in the range specified by
 396 .IR addr
 397 and
 398 .IR len .
 399 The kernel can thus free these pages,
 400 but the freeing could be delayed until memory pressure occurs.
 401 For each of the pages that has been marked to be freed
 402 but has not yet been freed,
 403 the free operation will be canceled if the caller writes into the page.
 404 After a successful
 405 .B MADV_FREE
 406 operation, any stale data (i.e., dirty, unwritten pages) will be lost
 407 when the kernel frees the pages.
 408 However, subsequent writes to pages in the range will succeed
 409 and then kernel cannot free those dirtied pages,
 410 so that the caller can always see just written data.
 411 If there is no subsequent write,
 412 the kernel can free the pages at any time.
 413 Once pages in the range have been freed, the caller will
 414 see zero-fill-on-demand pages upon subsequent page references.
 415 .IP
 416 The
 417 .B MADV_FREE
 418 operation
 419 can be applied only to private anonymous pages (see
 420 .BR mmap (2)).
 421 In Linux before version 4.12,
 422 .\" commit 93e06c7a645343d222c9a838834a51042eebbbf7
 423 when freeing pages on a swapless system,
 424 the pages in the given range are freed instantly,
 425 regardless of memory pressure.
 426 .TP
 427 .BR MADV_WIPEONFORK " (since Linux 4.14)"
 428 .\" commit d2cd9ede6e193dd7d88b6d27399e96229a551b19
 429 Present the child process with zero-filled memory in this range after a
 430 .BR fork (2).
 431 This is useful in forking servers in order to ensure
 432 that sensitive per-process data
 433 (for example, PRNG seeds, cryptographic secrets, and so on)
 434 is not handed to child processes.
 435 .IP
 436 The
 437 .B MADV_WIPEONFORK
 438 operation can be applied only to private anonymous pages (see
 439 .BR mmap (2)).
 440 .IP
 441 Within the child created by
 442 .BR fork (2),
 443 the
 444 .B MADV_WIPEONFORK
 445 setting remains in place on the specified address range.
 446 This setting is cleared during
 447 .BR execve (2).
 448 .TP
 449 .BR MADV_KEEPONFORK " (since Linux 4.14)"
 450 .\" commit d2cd9ede6e193dd7d88b6d27399e96229a551b19
 451 Undo the effect of an earlier
 452 .BR MADV_WIPEONFORK .
 453 .TP
 454 .BR MADV_COLD " (since Linux 5.4)"
 455 .\" commit 9c276cc65a58faf98be8e56962745ec99ab87636
 456 Deactivate a given range of pages.
 457 This will make the pages a more probable
 458 reclaim target should there be a memory pressure.
 459 This is a nondestructive operation.
 460 The advice might be ignored for some pages in the range when it is not
 461 applicable.
 462 .TP
 463 .BR MADV_PAGEOUT " (since Linux 5.4)"
 464 .\" commit 1a4e58cce84ee88129d5d49c064bd2852b481357
 465 Reclaim a given range of pages.
 466 This is done to free up memory occupied by these pages.
 467 If a page is anonymous, it will be swapped out.
 468 If a page is file-backed and dirty, it will be written back to the backing
 469 storage.
 470 The advice might be ignored for some pages in the range when it is not
 471 applicable.
 472 .TP
 473 .BR MADV_POPULATE_READ " (since Linux 5.14)"
 474 "Populate (prefault) page tables readable,
 475 faulting in all pages in the range just as if manually reading from each page;
 476 however,
 477 avoid the actual memory access that would have been performed after handling
 478 the fault.
 479 .IP
 480 In contrast to
 481 .BR MAP_POPULATE ,
 482 .B MADV_POPULATE_READ
 483 does not hide errors,
 484 can be applied to (parts of) existing mappings and will always populate
 485 (prefault) page tables readable.
 486 One example use case is prefaulting a file mapping,
 487 reading all file content from disk;
 488 however,
 489 pages won't be dirtied and consequently won't have to be written back to disk
 490 when evicting the pages from memory.
 491 .IP
 492 Depending on the underlying mapping,
 493 map the shared zeropage,
 494 preallocate memory or read the underlying file;
 495 files with holes might or might not preallocate blocks.
 496 If populating fails,
 497 a
 498 .B SIGBUS
 499 signal is not generated; instead, an error is returned.
 500 .IP
 501 If
 502 .B MADV_POPULATE_READ
 503 succeeds,
 504 all page tables have been populated (prefaulted) readable once.
 505 If
 506 .B MADV_POPULATE_READ
 507 fails,
 508 some page tables might have been populated.
 509 .IP
 510 .B MADV_POPULATE_READ
 511 cannot be applied to mappings without read permissions
 512 and special mappings,
 513 for example,
 514 mappings marked with kernel-internal flags such as
 515 .B VM_PFNMAP
 516 or
 517 .BR VM_IO ,
 518 or secret memory regions created using
 519 .BR memfd_secret(2) .
 520 .IP
 521 Note that with
 522 .BR MADV_POPULATE_READ ,
 523 the process can be killed at any moment when the system runs out of memory.
 524 .TP
 525 .BR MADV_POPULATE_WRITE " (since Linux 5.14)"
 526 Populate (prefault) page tables writable,
 527 faulting in all pages in the range just as if manually writing to each
 528 each page;
 529 however,
 530 avoid the actual memory access that would have been performed after handling
 531 the fault.
 532 .IP
 533 In contrast to
 534 .BR MAP_POPULATE ,
 535 MADV_POPULATE_WRITE does not hide errors,
 536 can be applied to (parts of) existing mappings and will always populate
 537 (prefault) page tables writable.
 538 One example use case is preallocating memory,
 539 breaking any CoW (Copy on Write).
 540 .IP
 541 Depending on the underlying mapping,
 542 preallocate memory or read the underlying file;
 543 files with holes will preallocate blocks.
 544 If populating fails,
 545 a
 546 .B SIGBUS
 547 signal is not generated; instead, an error is returned.
 548 .IP
 549 If
 550 .B MADV_POPULATE_WRITE
 551 succeeds,
 552 all page tables have been populated (prefaulted) writable once.
 553 If
 554 .B MADV_POPULATE_WRITE
 555 fails,
 556 some page tables might have been populated.
 557 .IP
 558 .B MADV_POPULATE_WRITE
 559 cannot be applied to mappings without write permissions
 560 and special mappings,
 561 for example,
 562 mappings marked with kernel-internal flags such as
 563 .B VM_PFNMAP
 564 or
 565 .BR VM_IO ,
 566 or secret memory regions created using
 567 .BR memfd_secret(2) .
 568 .IP
 569 Note that with
 570 .BR MADV_POPULATE_WRITE ,
 571 the process can be killed at any moment when the system runs out of memory.
 572 .SH RETURN VALUE
 573 On success,
 574 .BR madvise ()
 575 returns zero.
 576 On error, it returns \-1 and
 577 .I errno
 578 is set to indicate the error.
 579 .SH ERRORS
 580 .TP
 581 .B EACCES
 582 .I advice
 583 is
 584 .BR MADV_REMOVE ,
 585 but the specified address range is not a shared writable mapping.
 586 .TP
 587 .B EAGAIN
 588 A kernel resource was temporarily unavailable.
 589 .TP
 590 .B EBADF
 591 The map exists, but the area maps something that isn't a file.
 592 .TP
 593 .B EFAULT
 594 .I advice
 595 is
 596 .B MADV_POPULATE_READ
 597 or
 598 .BR MADV_POPULATE_WRITE ,
 599 and populating (prefaulting) page tables failed because a
 600 .B SIGBUS
 601 would have been generated on actual memory access and the reason is not a
 602 HW poisoned page
 603 (HW poisoned pages can,
 604 for example,
 605 be created using the
 606 .B MADV_HWPOISON
 607 flag described elsewhere in this page).
 608 .TP
 609 .B EINVAL
 610 .I addr
 611 is not page-aligned or
 612 .I length
 613 is negative.
 614 .\" .I length
 615 .\" is zero,
 616 .TP
 617 .B EINVAL
 618 .I advice
 619 is not a valid.
 620 .TP
 621 .B EINVAL
 622 .I advice
 623 is
 624 .B MADV_DONTNEED
 625 or
 626 .BR MADV_REMOVE
 627 and the specified address range includes locked, Huge TLB pages, or
 628 .B VM_PFNMAP
 629 pages.
 630 .TP
 631 .B EINVAL
 632 .I advice
 633 is
 634 .BR MADV_MERGEABLE
 635 or
 636 .BR MADV_UNMERGEABLE ,
 637 but the kernel was not configured with
 638 .BR CONFIG_KSM .
 639 .TP
 640 .B EINVAL
 641 .I advice
 642 is
 643 .BR MADV_FREE
 644 or
 645 .BR MADV_WIPEONFORK
 646 but the specified address range includes file, Huge TLB,
 647 .BR MAP_SHARED ,
 648 or
 649 .BR VM_PFNMAP
 650 ranges.
 651 .TP
 652 .B EINVAL
 653 .I advice
 654 is
 655 .B MADV_POPULATE_READ
 656 or
 657 .BR MADV_POPULATE_WRITE ,
 658 but the specified address range includes ranges with insufficient permissions
 659 or special mappings,
 660 for example,
 661 mappings marked with kernel-internal flags such a
 662 .B VM_IO
 663 or
 664 .BR VM_PFNMAP ,
 665 or secret memory regions created using
 666 .BR memfd_secret(2) .
 667 .TP
 668 .B EIO
 669 (for
 670 .BR MADV_WILLNEED )
 671 Paging in this area would exceed the process's
 672 maximum resident set size.
 673 .TP
 674 .B ENOMEM
 675 (for
 676 .BR MADV_WILLNEED )
 677 Not enough memory: paging in failed.
 678 .TP
 679 .B ENOMEM
 680 Addresses in the specified range are not currently
 681 mapped, or are outside the address space of the process.
 682 .TP
 683 .B ENOMEM
 684 .I advice
 685 is
 686 .B MADV_POPULATE_READ
 687 or
 688 .BR MADV_POPULATE_WRITE ,
 689 and populating (prefaulting) page tables failed because there was not enough
 690 memory.
 691 .TP
 692 .B EPERM
 693 .I advice
 694 is
 695 .BR MADV_HWPOISON ,
 696 but the caller does not have the
 697 .B CAP_SYS_ADMIN
 698 capability.
 699 .TP
 700 .B EHWPOISON
 701 .I advice
 702 is
 703 .B MADV_POPULATE_READ
 704 or
 705 .BR MADV_POPULATE_WRITE ,
 706 and populating (prefaulting) page tables failed because a HW poisoned page
 707 (HW poisoned pages can,
 708 for example,
 709 be created using the
 710 .B MADV_HWPOISON
 711 flag described elsewhere in this page)
 712 was encountered.
 713 .SH VERSIONS
 714 Since Linux 3.18,
 715 .\" commit d3ac21cacc24790eb45d735769f35753f5b56ceb
 716 support for this system call is optional,
 717 depending on the setting of the
 718 .B CONFIG_ADVISE_SYSCALLS
 719 configuration option.
 720 .SH CONFORMING TO
 721 .BR madvise ()
 722 is not specified by any standards.
 723 Versions of this system call, implementing a wide variety of
 724 .I advice
 725 values, exist on many other implementations.
 726 Other implementations typically implement at least the flags listed
 727 above under
 728 .IR "Conventional advice flags" ,
 729 albeit with some variation in semantics.
 730 .PP
 731 POSIX.1-2001 describes
 732 .BR posix_madvise (3)
 733 with constants
 734 .BR POSIX_MADV_NORMAL ,
 735 .BR POSIX_MADV_RANDOM ,
 736 .BR POSIX_MADV_SEQUENTIAL ,
 737 .BR POSIX_MADV_WILLNEED ,
 738 and
 739 .BR POSIX_MADV_DONTNEED ,
 740 and so on, with behavior close to the similarly named flags listed above.
 741 .SH NOTES
 742 .SS Linux notes
 743 The Linux implementation requires that the address
 744 .I addr
 745 be page-aligned, and allows
 746 .I length
 747 to be zero.
 748 If there are some parts of the specified address range
 749 that are not mapped, the Linux version of
 750 .BR madvise ()
 751 ignores them and applies the call to the rest (but returns
 752 .B ENOMEM
 753 from the system call, as it should).
 754 .\" .SH HISTORY
 755 .\" The
 756 .\" .BR madvise ()
 757 .\" function first appeared in 4.4BSD.
 758 .SH SEE ALSO
 759 .BR getrlimit (2),
 760 .BR memfd_secret(2),
 761 .BR mincore (2),
 762 .BR mmap (2),
 763 .BR mprotect (2),
 764 .BR msync (2),
 765 .BR munmap (2),
 766 .BR prctl (2),
 767 .BR process_madvise (2),
 768 .BR posix_madvise (3),
 769 .BR core (5)