]>
Commit | Line | Data |
---|---|---|
ec8f24b7 | 1 | # SPDX-License-Identifier: GPL-2.0-only |
59e0b520 CH |
2 | |
3 | menu "Memory Management options" | |
4 | ||
7b42f104 JW |
5 | # |
6 | # For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can | |
7 | # add proper SWAP support to them, in which case this can be remove. | |
8 | # | |
9 | config ARCH_NO_SWAP | |
10 | bool | |
11 | ||
b3fbd58f JW |
12 | config ZPOOL |
13 | bool | |
14 | ||
519bcb79 | 15 | menuconfig SWAP |
7b42f104 JW |
16 | bool "Support for paging of anonymous memory (swap)" |
17 | depends on MMU && BLOCK && !ARCH_NO_SWAP | |
18 | default y | |
19 | help | |
20 | This option allows you to choose whether you want to have support | |
21 | for so called swap devices or swap files in your kernel that are | |
22 | used to provide more virtual memory than the actual RAM present | |
23 | in your computer. If unsure say Y. | |
24 | ||
519bcb79 | 25 | config ZSWAP |
fcab9b44 | 26 | bool "Compressed cache for swap pages" |
b3fbd58f | 27 | depends on SWAP |
b3fbd58f | 28 | select CRYPTO |
519bcb79 JW |
29 | select ZPOOL |
30 | help | |
31 | A lightweight compressed cache for swap pages. It takes | |
32 | pages that are in the process of being swapped out and attempts to | |
33 | compress them into a dynamically allocated RAM-based memory pool. | |
34 | This can result in a significant I/O reduction on swap device and, | |
1a44131d | 35 | in the case where decompressing from RAM is faster than swap device |
519bcb79 JW |
36 | reads, can also improve workload performance. |
37 | ||
b3fbd58f JW |
38 | config ZSWAP_DEFAULT_ON |
39 | bool "Enable the compressed cache for swap pages by default" | |
40 | depends on ZSWAP | |
41 | help | |
42 | If selected, the compressed cache for swap pages will be enabled | |
43 | at boot, otherwise it will be disabled. | |
44 | ||
45 | The selection made here can be overridden by using the kernel | |
46 | command line 'zswap.enabled=' option. | |
47 | ||
b5ba474f NP |
48 | config ZSWAP_SHRINKER_DEFAULT_ON |
49 | bool "Shrink the zswap pool on memory pressure" | |
50 | depends on ZSWAP | |
51 | default n | |
52 | help | |
53 | If selected, the zswap shrinker will be enabled, and the pages | |
54 | stored in the zswap pool will become available for reclaim (i.e | |
55 | written back to the backing swap device) on memory pressure. | |
56 | ||
57 | This means that zswap writeback could happen even if the pool is | |
58 | not yet full, or the cgroup zswap limit has not been reached, | |
59 | reducing the chance that cold pages will reside in the zswap pool | |
60 | and consume memory indefinitely. | |
61 | ||
519bcb79 | 62 | choice |
b3fbd58f | 63 | prompt "Default compressor" |
519bcb79 JW |
64 | depends on ZSWAP |
65 | default ZSWAP_COMPRESSOR_DEFAULT_LZO | |
66 | help | |
67 | Selects the default compression algorithm for the compressed cache | |
68 | for swap pages. | |
69 | ||
70 | For an overview what kind of performance can be expected from | |
71 | a particular compression algorithm please refer to the benchmarks | |
72 | available at the following LWN page: | |
73 | https://lwn.net/Articles/751795/ | |
74 | ||
75 | If in doubt, select 'LZO'. | |
76 | ||
77 | The selection made here can be overridden by using the kernel | |
78 | command line 'zswap.compressor=' option. | |
79 | ||
80 | config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE | |
81 | bool "Deflate" | |
82 | select CRYPTO_DEFLATE | |
83 | help | |
84 | Use the Deflate algorithm as the default compression algorithm. | |
85 | ||
86 | config ZSWAP_COMPRESSOR_DEFAULT_LZO | |
87 | bool "LZO" | |
88 | select CRYPTO_LZO | |
89 | help | |
90 | Use the LZO algorithm as the default compression algorithm. | |
91 | ||
92 | config ZSWAP_COMPRESSOR_DEFAULT_842 | |
93 | bool "842" | |
94 | select CRYPTO_842 | |
95 | help | |
96 | Use the 842 algorithm as the default compression algorithm. | |
97 | ||
98 | config ZSWAP_COMPRESSOR_DEFAULT_LZ4 | |
99 | bool "LZ4" | |
100 | select CRYPTO_LZ4 | |
101 | help | |
102 | Use the LZ4 algorithm as the default compression algorithm. | |
103 | ||
104 | config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC | |
105 | bool "LZ4HC" | |
106 | select CRYPTO_LZ4HC | |
107 | help | |
108 | Use the LZ4HC algorithm as the default compression algorithm. | |
109 | ||
110 | config ZSWAP_COMPRESSOR_DEFAULT_ZSTD | |
111 | bool "zstd" | |
112 | select CRYPTO_ZSTD | |
113 | help | |
114 | Use the zstd algorithm as the default compression algorithm. | |
115 | endchoice | |
116 | ||
117 | config ZSWAP_COMPRESSOR_DEFAULT | |
118 | string | |
119 | depends on ZSWAP | |
120 | default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE | |
121 | default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO | |
122 | default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 | |
123 | default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 | |
124 | default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC | |
125 | default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD | |
126 | default "" | |
127 | ||
128 | choice | |
b3fbd58f | 129 | prompt "Default allocator" |
519bcb79 | 130 | depends on ZSWAP |
43d746dc | 131 | default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if HAVE_ZSMALLOC |
519bcb79 JW |
132 | default ZSWAP_ZPOOL_DEFAULT_ZBUD |
133 | help | |
134 | Selects the default allocator for the compressed cache for | |
135 | swap pages. | |
136 | The default is 'zbud' for compatibility, however please do | |
137 | read the description of each of the allocators below before | |
138 | making a right choice. | |
139 | ||
140 | The selection made here can be overridden by using the kernel | |
141 | command line 'zswap.zpool=' option. | |
142 | ||
143 | config ZSWAP_ZPOOL_DEFAULT_ZBUD | |
144 | bool "zbud" | |
145 | select ZBUD | |
146 | help | |
147 | Use the zbud allocator as the default allocator. | |
148 | ||
149 | config ZSWAP_ZPOOL_DEFAULT_Z3FOLD | |
150 | bool "z3fold" | |
151 | select Z3FOLD | |
152 | help | |
153 | Use the z3fold allocator as the default allocator. | |
154 | ||
155 | config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC | |
156 | bool "zsmalloc" | |
43d746dc | 157 | depends on HAVE_ZSMALLOC |
519bcb79 JW |
158 | select ZSMALLOC |
159 | help | |
160 | Use the zsmalloc allocator as the default allocator. | |
161 | endchoice | |
162 | ||
163 | config ZSWAP_ZPOOL_DEFAULT | |
164 | string | |
165 | depends on ZSWAP | |
166 | default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD | |
167 | default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD | |
168 | default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC | |
169 | default "" | |
170 | ||
519bcb79 | 171 | config ZBUD |
b3fbd58f JW |
172 | tristate "2:1 compression allocator (zbud)" |
173 | depends on ZSWAP | |
519bcb79 JW |
174 | help |
175 | A special purpose allocator for storing compressed pages. | |
176 | It is designed to store up to two compressed pages per physical | |
177 | page. While this design limits storage density, it has simple and | |
178 | deterministic reclaim properties that make it preferable to a higher | |
179 | density approach when reclaim will be used. | |
180 | ||
181 | config Z3FOLD | |
b3fbd58f JW |
182 | tristate "3:1 compression allocator (z3fold)" |
183 | depends on ZSWAP | |
519bcb79 JW |
184 | help |
185 | A special purpose allocator for storing compressed pages. | |
186 | It is designed to store up to three compressed pages per physical | |
187 | page. It is a ZBUD derivative so the simplicity and determinism are | |
188 | still there. | |
189 | ||
43d746dc DH |
190 | config HAVE_ZSMALLOC |
191 | def_bool y | |
192 | depends on MMU | |
193 | depends on PAGE_SIZE_LESS_THAN_256KB # we want <= 64 KiB | |
194 | ||
519bcb79 | 195 | config ZSMALLOC |
b3fbd58f JW |
196 | tristate |
197 | prompt "N:1 compression allocator (zsmalloc)" if ZSWAP | |
43d746dc | 198 | depends on HAVE_ZSMALLOC |
519bcb79 JW |
199 | help |
200 | zsmalloc is a slab-based memory allocator designed to store | |
b3fbd58f JW |
201 | pages of various compression levels efficiently. It achieves |
202 | the highest storage density with the least amount of fragmentation. | |
519bcb79 JW |
203 | |
204 | config ZSMALLOC_STAT | |
205 | bool "Export zsmalloc statistics" | |
206 | depends on ZSMALLOC | |
207 | select DEBUG_FS | |
208 | help | |
209 | This option enables code in the zsmalloc to collect various | |
210 | statistics about what's happening in zsmalloc and exports that | |
211 | information to userspace via debugfs. | |
212 | If unsure, say N. | |
213 | ||
4ff93b29 SS |
214 | config ZSMALLOC_CHAIN_SIZE |
215 | int "Maximum number of physical pages per-zspage" | |
b46402fa | 216 | default 8 |
4ff93b29 SS |
217 | range 4 16 |
218 | depends on ZSMALLOC | |
219 | help | |
220 | This option sets the upper limit on the number of physical pages | |
221 | that a zmalloc page (zspage) can consist of. The optimal zspage | |
222 | chain size is calculated for each size class during the | |
223 | initialization of the pool. | |
224 | ||
225 | Changing this option can alter the characteristics of size classes, | |
226 | such as the number of pages per zspage and the number of objects | |
227 | per zspage. This can also result in different configurations of | |
228 | the pool, as zsmalloc merges size classes with similar | |
229 | characteristics. | |
230 | ||
231 | For more information, see zsmalloc documentation. | |
232 | ||
2a19be61 | 233 | menu "Slab allocator options" |
7b42f104 JW |
234 | |
235 | config SLUB | |
2a19be61 | 236 | def_bool y |
eb07c4f3 | 237 | |
e240e53a | 238 | config SLUB_TINY |
2a19be61 VB |
239 | bool "Configure for minimal memory footprint" |
240 | depends on EXPERT | |
e240e53a VB |
241 | select SLAB_MERGE_DEFAULT |
242 | help | |
2a19be61 | 243 | Configures the slab allocator in a way to achieve minimal memory |
e240e53a VB |
244 | footprint, sacrificing scalability, debugging and other features. |
245 | This is intended only for the smallest system that had used the | |
246 | SLOB allocator and is not recommended for systems with more than | |
247 | 16MB RAM. | |
248 | ||
249 | If unsure, say N. | |
250 | ||
7b42f104 JW |
251 | config SLAB_MERGE_DEFAULT |
252 | bool "Allow slab caches to be merged" | |
253 | default y | |
7b42f104 JW |
254 | help |
255 | For reduced kernel memory fragmentation, slab caches can be | |
256 | merged when they share the same size and other characteristics. | |
257 | This carries a risk of kernel heap overflows being able to | |
258 | overwrite objects from merged caches (and more easily control | |
259 | cache layout), which makes such heap attacks easier to exploit | |
260 | by attackers. By keeping caches unmerged, these kinds of exploits | |
261 | can usually only damage objects in the same cache. To disable | |
262 | merging at runtime, "slab_nomerge" can be passed on the kernel | |
263 | command line. | |
264 | ||
265 | config SLAB_FREELIST_RANDOM | |
266 | bool "Randomize slab freelist" | |
2a19be61 | 267 | depends on !SLUB_TINY |
7b42f104 JW |
268 | help |
269 | Randomizes the freelist order used on creating new pages. This | |
270 | security feature reduces the predictability of the kernel slab | |
271 | allocator against heap overflows. | |
272 | ||
273 | config SLAB_FREELIST_HARDENED | |
274 | bool "Harden slab freelist metadata" | |
2a19be61 | 275 | depends on !SLUB_TINY |
7b42f104 JW |
276 | help |
277 | Many kernel heap attacks try to target slab cache metadata and | |
278 | other infrastructure. This options makes minor performance | |
279 | sacrifices to harden the kernel slab allocator against common | |
2a19be61 | 280 | freelist exploit methods. |
7b42f104 | 281 | |
67f2df3b KC |
282 | config SLAB_BUCKETS |
283 | bool "Support allocation from separate kmalloc buckets" | |
284 | depends on !SLUB_TINY | |
285 | default SLAB_FREELIST_HARDENED | |
286 | help | |
287 | Kernel heap attacks frequently depend on being able to create | |
288 | specifically-sized allocations with user-controlled contents | |
289 | that will be allocated into the same kmalloc bucket as a | |
290 | target object. To avoid sharing these allocation buckets, | |
291 | provide an explicitly separated set of buckets to be used for | |
292 | user-controlled allocations. This may very slightly increase | |
293 | memory fragmentation, though in practice it's only a handful | |
294 | of extra pages since the bulk of user-controlled allocations | |
295 | are relatively long-lived. | |
296 | ||
297 | If unsure, say Y. | |
298 | ||
0710d012 VB |
299 | config SLUB_STATS |
300 | default n | |
2a19be61 VB |
301 | bool "Enable performance statistics" |
302 | depends on SYSFS && !SLUB_TINY | |
0710d012 | 303 | help |
2a19be61 | 304 | The statistics are useful to debug slab allocation behavior in |
0710d012 VB |
305 | order find ways to optimize the allocator. This should never be |
306 | enabled for production use since keeping statistics slows down | |
307 | the allocator by a few percentage points. The slabinfo command | |
308 | supports the determination of the most active slabs to figure | |
309 | out which slabs are relevant to a particular load. | |
310 | Try running: slabinfo -DA | |
311 | ||
519bcb79 JW |
312 | config SLUB_CPU_PARTIAL |
313 | default y | |
2a19be61 VB |
314 | depends on SMP && !SLUB_TINY |
315 | bool "Enable per cpu partial caches" | |
519bcb79 JW |
316 | help |
317 | Per cpu partial caches accelerate objects allocation and freeing | |
318 | that is local to a processor at the price of more indeterminism | |
319 | in the latency of the free. On overflow these caches will be cleared | |
320 | which requires the taking of locks that may cause latency spikes. | |
321 | Typically one would choose no for a realtime system. | |
322 | ||
3c615294 GR |
323 | config RANDOM_KMALLOC_CACHES |
324 | default n | |
2a19be61 | 325 | depends on !SLUB_TINY |
3c615294 GR |
326 | bool "Randomize slab caches for normal kmalloc" |
327 | help | |
328 | A hardening feature that creates multiple copies of slab caches for | |
329 | normal kmalloc allocation and makes kmalloc randomly pick one based | |
330 | on code address, which makes the attackers more difficult to spray | |
331 | vulnerable memory objects on the heap for the purpose of exploiting | |
332 | memory vulnerabilities. | |
333 | ||
334 | Currently the number of copies is set to 16, a reasonably large value | |
335 | that effectively diverges the memory objects allocated for different | |
336 | subsystems or modules into different caches, at the expense of a | |
337 | limited degree of memory and CPU overhead that relates to hardware and | |
338 | system workload. | |
339 | ||
2a19be61 | 340 | endmenu # Slab allocator options |
519bcb79 | 341 | |
7b42f104 JW |
342 | config SHUFFLE_PAGE_ALLOCATOR |
343 | bool "Page allocator randomization" | |
344 | default SLAB_FREELIST_RANDOM && ACPI_NUMA | |
345 | help | |
346 | Randomization of the page allocator improves the average | |
347 | utilization of a direct-mapped memory-side-cache. See section | |
348 | 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI | |
349 | 6.2a specification for an example of how a platform advertises | |
350 | the presence of a memory-side-cache. There are also incidental | |
351 | security benefits as it reduces the predictability of page | |
352 | allocations to compliment SLAB_FREELIST_RANDOM, but the | |
5e0a760b | 353 | default granularity of shuffling on the MAX_PAGE_ORDER i.e, 10th |
23baf831 KS |
354 | order of pages is selected based on cache utilization benefits |
355 | on x86. | |
7b42f104 JW |
356 | |
357 | While the randomization improves cache utilization it may | |
358 | negatively impact workloads on platforms without a cache. For | |
b413f9cd MC |
359 | this reason, by default, the randomization is not enabled even |
360 | if SHUFFLE_PAGE_ALLOCATOR=y. The randomization may be force enabled | |
361 | with the 'page_alloc.shuffle' kernel command line parameter. | |
7b42f104 JW |
362 | |
363 | Say Y if unsure. | |
364 | ||
0710d012 VB |
365 | config COMPAT_BRK |
366 | bool "Disable heap randomization" | |
367 | default y | |
368 | help | |
369 | Randomizing heap placement makes heap exploits harder, but it | |
370 | also breaks ancient binaries (including anything libc5 based). | |
371 | This option changes the bootup default to heap randomization | |
372 | disabled, and can be overridden at runtime by setting | |
373 | /proc/sys/kernel/randomize_va_space to 2. | |
374 | ||
375 | On non-ancient distros (post-2000 ones) N is usually a safe choice. | |
376 | ||
377 | config MMAP_ALLOW_UNINITIALIZED | |
378 | bool "Allow mmapped anonymous memory to be uninitialized" | |
379 | depends on EXPERT && !MMU | |
380 | default n | |
381 | help | |
382 | Normally, and according to the Linux spec, anonymous memory obtained | |
383 | from mmap() has its contents cleared before it is passed to | |
384 | userspace. Enabling this config option allows you to request that | |
385 | mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus | |
386 | providing a huge performance boost. If this option is not enabled, | |
387 | then the flag will be ignored. | |
388 | ||
389 | This is taken advantage of by uClibc's malloc(), and also by | |
390 | ELF-FDPIC binfmt's brk and stack allocator. | |
391 | ||
392 | Because of the obvious security issues, this option should only be | |
393 | enabled on embedded devices where you control what is run in | |
394 | userspace. Since that isn't generally a problem on no-MMU systems, | |
395 | it is normally safe to say Y here. | |
396 | ||
397 | See Documentation/admin-guide/mm/nommu-mmap.rst for more information. | |
398 | ||
e1785e85 DH |
399 | config SELECT_MEMORY_MODEL |
400 | def_bool y | |
a8826eeb | 401 | depends on ARCH_SELECT_MEMORY_MODEL |
e1785e85 | 402 | |
3a9da765 DH |
403 | choice |
404 | prompt "Memory model" | |
e1785e85 | 405 | depends on SELECT_MEMORY_MODEL |
d41dee36 | 406 | default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT |
e1785e85 | 407 | default FLATMEM_MANUAL |
d66d109d MR |
408 | help |
409 | This option allows you to change some of the ways that | |
410 | Linux manages its memory internally. Most users will | |
411 | only have one option here selected by the architecture | |
412 | configuration. This is normal. | |
3a9da765 | 413 | |
e1785e85 | 414 | config FLATMEM_MANUAL |
3a9da765 | 415 | bool "Flat Memory" |
bb1c50d3 | 416 | depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE |
3a9da765 | 417 | help |
d66d109d MR |
418 | This option is best suited for non-NUMA systems with |
419 | flat address space. The FLATMEM is the most efficient | |
420 | system in terms of performance and resource consumption | |
421 | and it is the best option for smaller systems. | |
422 | ||
423 | For systems that have holes in their physical address | |
424 | spaces and for features like NUMA and memory hotplug, | |
dd33d29a | 425 | choose "Sparse Memory". |
d41dee36 AW |
426 | |
427 | If unsure, choose this option (Flat Memory) over any other. | |
3a9da765 | 428 | |
d41dee36 AW |
429 | config SPARSEMEM_MANUAL |
430 | bool "Sparse Memory" | |
431 | depends on ARCH_SPARSEMEM_ENABLE | |
432 | help | |
433 | This will be the only option for some systems, including | |
d66d109d | 434 | memory hot-plug systems. This is normal. |
d41dee36 | 435 | |
d66d109d MR |
436 | This option provides efficient support for systems with |
437 | holes is their physical address space and allows memory | |
438 | hot-plug and hot-remove. | |
d41dee36 | 439 | |
d66d109d | 440 | If unsure, choose "Flat Memory" over this option. |
d41dee36 | 441 | |
3a9da765 DH |
442 | endchoice |
443 | ||
d41dee36 AW |
444 | config SPARSEMEM |
445 | def_bool y | |
1a83e175 | 446 | depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL |
d41dee36 | 447 | |
e1785e85 DH |
448 | config FLATMEM |
449 | def_bool y | |
bb1c50d3 | 450 | depends on !SPARSEMEM || FLATMEM_MANUAL |
d41dee36 | 451 | |
3e347261 BP |
452 | # |
453 | # SPARSEMEM_EXTREME (which is the default) does some bootmem | |
c89ab04f | 454 | # allocations when sparse_init() is called. If this cannot |
3e347261 BP |
455 | # be done on your architecture, select this option. However, |
456 | # statically allocating the mem_section[] array can potentially | |
457 | # consume vast quantities of .bss, so be careful. | |
458 | # | |
459 | # This option will also potentially produce smaller runtime code | |
460 | # with gcc 3.4 and later. | |
461 | # | |
462 | config SPARSEMEM_STATIC | |
9ba16087 | 463 | bool |
3e347261 | 464 | |
802f192e | 465 | # |
44c09201 | 466 | # Architecture platforms which require a two level mem_section in SPARSEMEM |
802f192e BP |
467 | # must select this option. This is usually for architecture platforms with |
468 | # an extremely sparse physical address space. | |
469 | # | |
3e347261 BP |
470 | config SPARSEMEM_EXTREME |
471 | def_bool y | |
472 | depends on SPARSEMEM && !SPARSEMEM_STATIC | |
4c21e2f2 | 473 | |
29c71111 | 474 | config SPARSEMEM_VMEMMAP_ENABLE |
9ba16087 | 475 | bool |
29c71111 AW |
476 | |
477 | config SPARSEMEM_VMEMMAP | |
a5ee6daa GL |
478 | bool "Sparse Memory virtual memmap" |
479 | depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE | |
480 | default y | |
481 | help | |
19fa40a0 KK |
482 | SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise |
483 | pfn_to_page and page_to_pfn operations. This is the most | |
484 | efficient option when sufficient kernel resources are available. | |
0b376f1e AK |
485 | # |
486 | # Select this config option from the architecture Kconfig, if it is preferred | |
487 | # to enable the feature of HugeTLB/dev_dax vmemmap optimization. | |
488 | # | |
0b6f1582 AK |
489 | config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP |
490 | bool | |
491 | ||
492 | config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP | |
0b376f1e | 493 | bool |
29c71111 | 494 | |
70210ed9 | 495 | config HAVE_MEMBLOCK_PHYS_MAP |
6341e62b | 496 | bool |
70210ed9 | 497 | |
25176ad0 | 498 | config HAVE_GUP_FAST |
050a9adc | 499 | depends on MMU |
6341e62b | 500 | bool |
2667f50e | 501 | |
52219aea DH |
502 | # Don't discard allocated memory used to track "memory" and "reserved" memblocks |
503 | # after early boot, so it can still be used to test for validity of memory. | |
504 | # Also, memblocks are updated with memory hot(un)plug. | |
350e88ba | 505 | config ARCH_KEEP_MEMBLOCK |
6341e62b | 506 | bool |
c378ddd5 | 507 | |
1e5d8e1e DW |
508 | # Keep arch NUMA mapping infrastructure post-init. |
509 | config NUMA_KEEP_MEMINFO | |
510 | bool | |
511 | ||
ee6f509c | 512 | config MEMORY_ISOLATION |
6341e62b | 513 | bool |
ee6f509c | 514 | |
a9e7b8d4 DH |
515 | # IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked |
516 | # IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via | |
517 | # /dev/mem. | |
518 | config EXCLUSIVE_SYSTEM_RAM | |
519 | def_bool y | |
520 | depends on !DEVMEM || STRICT_DEVMEM | |
521 | ||
46723bfa YI |
522 | # |
523 | # Only be set on architectures that have completely implemented memory hotplug | |
524 | # feature. If you are not sure, don't touch it. | |
525 | # | |
526 | config HAVE_BOOTMEM_INFO_NODE | |
527 | def_bool n | |
528 | ||
91024b3c AK |
529 | config ARCH_ENABLE_MEMORY_HOTPLUG |
530 | bool | |
531 | ||
519bcb79 JW |
532 | config ARCH_ENABLE_MEMORY_HOTREMOVE |
533 | bool | |
534 | ||
3947be19 | 535 | # eventually, we can have this option just 'select SPARSEMEM' |
519bcb79 JW |
536 | menuconfig MEMORY_HOTPLUG |
537 | bool "Memory hotplug" | |
b30c5927 | 538 | select MEMORY_ISOLATION |
71b6f2dd | 539 | depends on SPARSEMEM |
40b31360 | 540 | depends on ARCH_ENABLE_MEMORY_HOTPLUG |
7ec58a2b | 541 | depends on 64BIT |
1e5d8e1e | 542 | select NUMA_KEEP_MEMINFO if NUMA |
3947be19 | 543 | |
519bcb79 JW |
544 | if MEMORY_HOTPLUG |
545 | ||
8604d9e5 | 546 | config MEMORY_HOTPLUG_DEFAULT_ONLINE |
19fa40a0 KK |
547 | bool "Online the newly added memory blocks by default" |
548 | depends on MEMORY_HOTPLUG | |
549 | help | |
8604d9e5 VK |
550 | This option sets the default policy setting for memory hotplug |
551 | onlining policy (/sys/devices/system/memory/auto_online_blocks) which | |
552 | determines what happens to newly added memory regions. Policy setting | |
553 | can always be changed at runtime. | |
cb1aaebe | 554 | See Documentation/admin-guide/mm/memory-hotplug.rst for more information. |
8604d9e5 VK |
555 | |
556 | Say Y here if you want all hot-plugged memory blocks to appear in | |
557 | 'online' state by default. | |
558 | Say N here if you want the default policy to keep all hot-plugged | |
559 | memory blocks in 'offline' state. | |
560 | ||
0c0e6195 KH |
561 | config MEMORY_HOTREMOVE |
562 | bool "Allow for memory hot remove" | |
f7e3334a | 563 | select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) |
0c0e6195 KH |
564 | depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE |
565 | depends on MIGRATION | |
566 | ||
a08a2ae3 OS |
567 | config MHP_MEMMAP_ON_MEMORY |
568 | def_bool y | |
569 | depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP | |
570 | depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE | |
571 | ||
519bcb79 JW |
572 | endif # MEMORY_HOTPLUG |
573 | ||
04d5ea46 AK |
574 | config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE |
575 | bool | |
576 | ||
4c21e2f2 HD |
577 | # Heavily threaded applications may benefit from splitting the mm-wide |
578 | # page_table_lock, so that faults on different parts of the user address | |
579 | # space can be handled with less contention: split it at this NR_CPUS. | |
580 | # Default to 4 for wider testing, though 8 might be more appropriate. | |
581 | # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. | |
7b6ac9df | 582 | # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. |
60bccaa6 WD |
583 | # SPARC32 allocates multiple pte tables within a single page, and therefore |
584 | # a per-page lock leads to problems when multiple tables need to be locked | |
585 | # at the same time (e.g. copy_page_range()). | |
a70caa8b | 586 | # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. |
4c21e2f2 HD |
587 | # |
588 | config SPLIT_PTLOCK_CPUS | |
589 | int | |
9164550e | 590 | default "999999" if !MMU |
a70caa8b HD |
591 | default "999999" if ARM && !CPU_CACHE_VIPT |
592 | default "999999" if PARISC && !PA20 | |
60bccaa6 | 593 | default "999999" if SPARC32 |
4c21e2f2 | 594 | default "4" |
7cbe34cf | 595 | |
e009bb30 | 596 | config ARCH_ENABLE_SPLIT_PMD_PTLOCK |
6341e62b | 597 | bool |
e009bb30 | 598 | |
09316c09 KK |
599 | # |
600 | # support for memory balloon | |
601 | config MEMORY_BALLOON | |
6341e62b | 602 | bool |
09316c09 | 603 | |
18468d93 RA |
604 | # |
605 | # support for memory balloon compaction | |
606 | config BALLOON_COMPACTION | |
607 | bool "Allow for balloon memory compaction/migration" | |
cd14b018 | 608 | default y |
09316c09 | 609 | depends on COMPACTION && MEMORY_BALLOON |
18468d93 RA |
610 | help |
611 | Memory fragmentation introduced by ballooning might reduce | |
612 | significantly the number of 2MB contiguous memory blocks that can be | |
613 | used within a guest, thus imposing performance penalties associated | |
614 | with the reduced number of transparent huge pages that could be used | |
615 | by the guest workload. Allowing the compaction & migration for memory | |
616 | pages enlisted as being part of memory balloon devices avoids the | |
617 | scenario aforementioned and helps improving memory defragmentation. | |
618 | ||
e9e96b39 MG |
619 | # |
620 | # support for memory compaction | |
621 | config COMPACTION | |
622 | bool "Allow for memory compaction" | |
cd14b018 | 623 | default y |
e9e96b39 | 624 | select MIGRATION |
33a93877 | 625 | depends on MMU |
e9e96b39 | 626 | help |
19fa40a0 KK |
627 | Compaction is the only memory management component to form |
628 | high order (larger physically contiguous) memory blocks | |
629 | reliably. The page allocator relies on compaction heavily and | |
630 | the lack of the feature can lead to unexpected OOM killer | |
631 | invocations for high order memory requests. You shouldn't | |
632 | disable this option unless there really is a strong reason for | |
633 | it and then we would be really interested to hear about that at | |
634 | [email protected]. | |
e9e96b39 | 635 | |
c7e0b3d0 TG |
636 | config COMPACT_UNEVICTABLE_DEFAULT |
637 | int | |
638 | depends on COMPACTION | |
639 | default 0 if PREEMPT_RT | |
640 | default 1 | |
641 | ||
36e66c55 AD |
642 | # |
643 | # support for free page reporting | |
644 | config PAGE_REPORTING | |
645 | bool "Free page reporting" | |
36e66c55 AD |
646 | help |
647 | Free page reporting allows for the incremental acquisition of | |
648 | free pages from the buddy allocator for the purpose of reporting | |
649 | those pages to another entity, such as a hypervisor, so that the | |
650 | memory can be freed within the host for other uses. | |
651 | ||
7cbe34cf CL |
652 | # |
653 | # support for page migration | |
654 | # | |
655 | config MIGRATION | |
b20a3503 | 656 | bool "Page migration" |
cd14b018 | 657 | default y |
de32a817 | 658 | depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU |
b20a3503 CL |
659 | help |
660 | Allows the migration of the physical location of pages of processes | |
e9e96b39 MG |
661 | while the virtual addresses are not changed. This is useful in |
662 | two situations. The first is on NUMA systems to put pages nearer | |
663 | to the processors accessing. The second is when allocating huge | |
664 | pages as migration can relocate pages to satisfy a huge page | |
665 | allocation instead of reclaiming. | |
6550e07f | 666 | |
76cbbead | 667 | config DEVICE_MIGRATION |
d90a25f8 | 668 | def_bool MIGRATION && ZONE_DEVICE |
76cbbead | 669 | |
c177c81e | 670 | config ARCH_ENABLE_HUGEPAGE_MIGRATION |
6341e62b | 671 | bool |
c177c81e | 672 | |
9c670ea3 NH |
673 | config ARCH_ENABLE_THP_MIGRATION |
674 | bool | |
675 | ||
4bfb68a0 AK |
676 | config HUGETLB_PAGE_SIZE_VARIABLE |
677 | def_bool n | |
678 | help | |
679 | Allows the pageblock_order value to be dynamic instead of just standard | |
680 | HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available | |
681 | on a platform. | |
682 | ||
5e0a760b KS |
683 | Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be |
684 | clamped down to MAX_PAGE_ORDER. | |
b3d40a2b | 685 | |
8df995f6 | 686 | config CONTIG_ALLOC |
19fa40a0 | 687 | def_bool (MEMORY_ISOLATION && COMPACTION) || CMA |
8df995f6 | 688 | |
52166607 YH |
689 | config PCP_BATCH_SCALE_MAX |
690 | int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" | |
691 | default 5 | |
692 | range 0 6 | |
693 | help | |
694 | In page allocator, PCP (Per-CPU pageset) is refilled and drained in | |
695 | batches. The batch number is scaled automatically to improve page | |
696 | allocation/free throughput. But too large scale factor may hurt | |
697 | latency. This option sets the upper limit of scale factor to limit | |
698 | the maximum latency. | |
699 | ||
600715dc | 700 | config PHYS_ADDR_T_64BIT |
d4a451d5 | 701 | def_bool 64BIT |
600715dc | 702 | |
2a7326b5 | 703 | config BOUNCE |
9ca24e2e VM |
704 | bool "Enable bounce buffers" |
705 | default y | |
ce288e05 | 706 | depends on BLOCK && MMU && HIGHMEM |
9ca24e2e | 707 | help |
ce288e05 CH |
708 | Enable bounce buffers for devices that cannot access the full range of |
709 | memory available to the CPU. Enabled by default when HIGHMEM is | |
710 | selected, but you may say n to override this. | |
2a7326b5 | 711 | |
cddb8a5c AA |
712 | config MMU_NOTIFIER |
713 | bool | |
99cb252f | 714 | select INTERVAL_TREE |
fc4d5c29 | 715 | |
f8af4da3 HD |
716 | config KSM |
717 | bool "Enable KSM for page merging" | |
718 | depends on MMU | |
59e1a2f4 | 719 | select XXHASH |
f8af4da3 HD |
720 | help |
721 | Enable Kernel Samepage Merging: KSM periodically scans those areas | |
722 | of an application's address space that an app has advised may be | |
723 | mergeable. When it finds pages of identical content, it replaces | |
d0f209f6 | 724 | the many instances by a single page with that content, so |
f8af4da3 HD |
725 | saving memory until one or another app needs to modify the content. |
726 | Recommended for use with KVM, or with other duplicative applications. | |
ee65728e | 727 | See Documentation/mm/ksm.rst for more information: KSM is inactive |
c73602ad HD |
728 | until a program has madvised that an area is MADV_MERGEABLE, and |
729 | root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). | |
f8af4da3 | 730 | |
e0a94c2a | 731 | config DEFAULT_MMAP_MIN_ADDR |
19fa40a0 | 732 | int "Low address space to protect from user allocation" |
6e141546 | 733 | depends on MMU |
19fa40a0 KK |
734 | default 4096 |
735 | help | |
e0a94c2a CL |
736 | This is the portion of low virtual memory which should be protected |
737 | from userspace allocation. Keeping a user from writing to low pages | |
738 | can help reduce the impact of kernel NULL pointer bugs. | |
739 | ||
34f7c528 | 740 | For most arm64, ppc64 and x86 users with lots of address space |
e0a94c2a CL |
741 | a value of 65536 is reasonable and should cause no problems. |
742 | On arm and other archs it should not be higher than 32768. | |
788084ab EP |
743 | Programs which use vm86 functionality or have some need to map |
744 | this low address space will need CAP_SYS_RAWIO or disable this | |
745 | protection by setting the value to 0. | |
e0a94c2a CL |
746 | |
747 | This value can be changed after boot using the | |
748 | /proc/sys/vm/mmap_min_addr tunable. | |
749 | ||
d949f36f LT |
750 | config ARCH_SUPPORTS_MEMORY_FAILURE |
751 | bool | |
e0a94c2a | 752 | |
6a46079c AK |
753 | config MEMORY_FAILURE |
754 | depends on MMU | |
d949f36f | 755 | depends on ARCH_SUPPORTS_MEMORY_FAILURE |
6a46079c | 756 | bool "Enable recovery from hardware memory errors" |
ee6f509c | 757 | select MEMORY_ISOLATION |
97f0b134 | 758 | select RAS |
6a46079c AK |
759 | help |
760 | Enables code to recover from some memory failures on systems | |
761 | with MCA recovery. This allows a system to continue running | |
762 | even when some of its memory has uncorrected errors. This requires | |
763 | special hardware support and typically ECC memory. | |
764 | ||
cae681fc | 765 | config HWPOISON_INJECT |
413f9efb | 766 | tristate "HWPoison pages injector" |
27df5068 | 767 | depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS |
478c5ffc | 768 | select PROC_PAGE_MONITOR |
cae681fc | 769 | |
fc4d5c29 DH |
770 | config NOMMU_INITIAL_TRIM_EXCESS |
771 | int "Turn on mmap() excess space trimming before booting" | |
772 | depends on !MMU | |
773 | default 1 | |
774 | help | |
775 | The NOMMU mmap() frequently needs to allocate large contiguous chunks | |
776 | of memory on which to store mappings, but it can only ask the system | |
777 | allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently | |
778 | more than it requires. To deal with this, mmap() is able to trim off | |
779 | the excess and return it to the allocator. | |
780 | ||
781 | If trimming is enabled, the excess is trimmed off and returned to the | |
782 | system allocator, which can cause extra fragmentation, particularly | |
783 | if there are a lot of transient processes. | |
784 | ||
785 | If trimming is disabled, the excess is kept, but not used, which for | |
786 | long-term mappings means that the space is wasted. | |
787 | ||
788 | Trimming can be dynamically controlled through a sysctl option | |
789 | (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of | |
790 | excess pages there must be before trimming should occur, or zero if | |
791 | no trimming is to occur. | |
792 | ||
793 | This option specifies the initial value of this option. The default | |
794 | of 1 says that all excess pages should be trimmed. | |
795 | ||
dd19d293 | 796 | See Documentation/admin-guide/mm/nommu-mmap.rst for more information. |
bbddff05 | 797 | |
519bcb79 JW |
798 | config ARCH_WANT_GENERAL_HUGETLB |
799 | bool | |
800 | ||
801 | config ARCH_WANTS_THP_SWAP | |
802 | def_bool n | |
803 | ||
804 | menuconfig TRANSPARENT_HUGEPAGE | |
13ece886 | 805 | bool "Transparent Hugepage Support" |
554b0f3c | 806 | depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT |
5d689240 | 807 | select COMPACTION |
3a08cd52 | 808 | select XARRAY_MULTI |
4c76d9d1 AA |
809 | help |
810 | Transparent Hugepages allows the kernel to use huge pages and | |
811 | huge tlb transparently to the applications whenever possible. | |
812 | This feature can improve computing performance to certain | |
813 | applications by speeding up page faults during memory | |
814 | allocation, by reducing the number of tlb misses and by speeding | |
815 | up the pagetable walking. | |
816 | ||
817 | If memory constrained on embedded, you may want to say N. | |
818 | ||
519bcb79 JW |
819 | if TRANSPARENT_HUGEPAGE |
820 | ||
13ece886 AA |
821 | choice |
822 | prompt "Transparent Hugepage Support sysfs defaults" | |
823 | depends on TRANSPARENT_HUGEPAGE | |
824 | default TRANSPARENT_HUGEPAGE_ALWAYS | |
825 | help | |
826 | Selects the sysfs defaults for Transparent Hugepage Support. | |
827 | ||
828 | config TRANSPARENT_HUGEPAGE_ALWAYS | |
829 | bool "always" | |
830 | help | |
831 | Enabling Transparent Hugepage always, can increase the | |
832 | memory footprint of applications without a guaranteed | |
833 | benefit but it will work automatically for all applications. | |
834 | ||
835 | config TRANSPARENT_HUGEPAGE_MADVISE | |
836 | bool "madvise" | |
837 | help | |
838 | Enabling Transparent Hugepage madvise, will only provide a | |
839 | performance improvement benefit to the applications using | |
840 | madvise(MADV_HUGEPAGE) but it won't risk to increase the | |
841 | memory footprint of applications without a guaranteed | |
842 | benefit. | |
683ec99f DM |
843 | |
844 | config TRANSPARENT_HUGEPAGE_NEVER | |
845 | bool "never" | |
846 | help | |
847 | Disable Transparent Hugepage by default. It can still be | |
848 | enabled at runtime via sysfs. | |
13ece886 AA |
849 | endchoice |
850 | ||
38d8b4e6 YH |
851 | config THP_SWAP |
852 | def_bool y | |
dad6a5eb | 853 | depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT |
38d8b4e6 YH |
854 | help |
855 | Swap transparent huge pages in one piece, without splitting. | |
14fef284 YH |
856 | XXX: For now, swap cluster backing transparent huge page |
857 | will be split after swapout. | |
38d8b4e6 YH |
858 | |
859 | For selection by architectures with reasonable THP sizes. | |
860 | ||
519bcb79 JW |
861 | config READ_ONLY_THP_FOR_FS |
862 | bool "Read-only THP for filesystems (EXPERIMENTAL)" | |
863 | depends on TRANSPARENT_HUGEPAGE && SHMEM | |
864 | ||
865 | help | |
866 | Allow khugepaged to put read-only file-backed pages in THP. | |
867 | ||
868 | This is marked experimental because it is a new feature. Write | |
869 | support of file THPs will be developed in the next few release | |
870 | cycles. | |
871 | ||
872 | endif # TRANSPARENT_HUGEPAGE | |
873 | ||
ac3830c3 PX |
874 | # |
875 | # The architecture supports pgtable leaves that is larger than PAGE_SIZE | |
876 | # | |
877 | config PGTABLE_HAS_HUGE_LEAVES | |
878 | def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE | |
879 | ||
bbddff05 TH |
880 | # |
881 | # UP and nommu archs use km based percpu allocator | |
882 | # | |
883 | config NEED_PER_CPU_KM | |
3583521a | 884 | depends on !SMP || !MMU |
bbddff05 TH |
885 | bool |
886 | default y | |
077b1f83 | 887 | |
7ecd19cf KW |
888 | config NEED_PER_CPU_EMBED_FIRST_CHUNK |
889 | bool | |
890 | ||
891 | config NEED_PER_CPU_PAGE_FIRST_CHUNK | |
892 | bool | |
893 | ||
894 | config USE_PERCPU_NUMA_NODE_ID | |
895 | bool | |
896 | ||
897 | config HAVE_SETUP_PER_CPU_AREA | |
898 | bool | |
899 | ||
f825c736 AK |
900 | config CMA |
901 | bool "Contiguous Memory Allocator" | |
aca52c39 | 902 | depends on MMU |
f825c736 AK |
903 | select MIGRATION |
904 | select MEMORY_ISOLATION | |
905 | help | |
906 | This enables the Contiguous Memory Allocator which allows other | |
907 | subsystems to allocate big physically-contiguous blocks of memory. | |
908 | CMA reserves a region of memory and allows only movable pages to | |
909 | be allocated from it. This way, the kernel can use the memory for | |
910 | pagecache and when a subsystem requests for contiguous area, the | |
911 | allocated pages are migrated away to serve the contiguous request. | |
912 | ||
913 | If unsure, say "n". | |
914 | ||
28b24c1f SL |
915 | config CMA_DEBUGFS |
916 | bool "CMA debugfs interface" | |
917 | depends on CMA && DEBUG_FS | |
918 | help | |
919 | Turns on the DebugFS interface for CMA. | |
920 | ||
43ca106f MK |
921 | config CMA_SYSFS |
922 | bool "CMA information through sysfs interface" | |
923 | depends on CMA && SYSFS | |
924 | help | |
925 | This option exposes some sysfs attributes to get information | |
926 | from CMA. | |
927 | ||
a254129e JK |
928 | config CMA_AREAS |
929 | int "Maximum count of the CMA areas" | |
930 | depends on CMA | |
73307523 AK |
931 | default 20 if NUMA |
932 | default 8 | |
a254129e JK |
933 | help |
934 | CMA allows to create CMA areas for particular purpose, mainly, | |
935 | used as device private area. This parameter sets the maximum | |
936 | number of CMA area in the system. | |
937 | ||
73307523 | 938 | If unsure, leave the default value "8" in UMA and "20" in NUMA. |
a254129e | 939 | |
af8d417a DS |
940 | config MEM_SOFT_DIRTY |
941 | bool "Track memory changes" | |
942 | depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS | |
943 | select PROC_PAGE_MONITOR | |
4e2e2770 | 944 | help |
af8d417a DS |
945 | This option enables memory changes tracking by introducing a |
946 | soft-dirty bit on pte-s. This bit it set when someone writes | |
947 | into a page just as regular dirty bit, but unlike the latter | |
948 | it can be cleared by hands. | |
949 | ||
1ad1335d | 950 | See Documentation/admin-guide/mm/soft-dirty.rst for more details. |
4e2e2770 | 951 | |
9e5c33d7 MS |
952 | config GENERIC_EARLY_IOREMAP |
953 | bool | |
042d27ac | 954 | |
22ee3ea5 HD |
955 | config STACK_MAX_DEFAULT_SIZE_MB |
956 | int "Default maximum user stack size for 32-bit processes (MB)" | |
957 | default 100 | |
042d27ac HD |
958 | range 8 2048 |
959 | depends on STACK_GROWSUP && (!64BIT || COMPAT) | |
960 | help | |
961 | This is the maximum stack size in Megabytes in the VM layout of 32-bit | |
962 | user processes when the stack grows upwards (currently only on parisc | |
22ee3ea5 | 963 | arch) when the RLIMIT_STACK hard limit is unlimited. |
042d27ac | 964 | |
22ee3ea5 | 965 | A sane initial value is 100 MB. |
3a80a7fa | 966 | |
3a80a7fa | 967 | config DEFERRED_STRUCT_PAGE_INIT |
1ce22103 | 968 | bool "Defer initialisation of struct pages to kthreads" |
d39f8fb4 | 969 | depends on SPARSEMEM |
ab1e8d89 | 970 | depends on !NEED_PER_CPU_KM |
889c695d | 971 | depends on 64BIT |
854fa98d | 972 | depends on !KMSAN |
e4443149 | 973 | select PADATA |
3a80a7fa MG |
974 | help |
975 | Ordinarily all struct pages are initialised during early boot in a | |
976 | single thread. On very large machines this can take a considerable | |
977 | amount of time. If this option is set, large machines will bring up | |
e4443149 DJ |
978 | a subset of memmap at boot and then initialise the rest in parallel. |
979 | This has a potential performance impact on tasks running early in the | |
1ce22103 VB |
980 | lifetime of the system until these kthreads finish the |
981 | initialisation. | |
033fbae9 | 982 | |
1c676e0d SP |
983 | config PAGE_IDLE_FLAG |
984 | bool | |
985 | select PAGE_EXTENSION if !64BIT | |
986 | help | |
987 | This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed | |
988 | bit writers can set the state of the bit in the flags so that PTE | |
989 | Accessed bit readers may avoid disturbance. | |
990 | ||
33c3fc71 VD |
991 | config IDLE_PAGE_TRACKING |
992 | bool "Enable idle page tracking" | |
993 | depends on SYSFS && MMU | |
1c676e0d | 994 | select PAGE_IDLE_FLAG |
33c3fc71 VD |
995 | help |
996 | This feature allows to estimate the amount of user pages that have | |
997 | not been touched during a given period of time. This information can | |
998 | be useful to tune memory cgroup limits and/or for job placement | |
999 | within a compute cluster. | |
1000 | ||
1ad1335d MR |
1001 | See Documentation/admin-guide/mm/idle_page_tracking.rst for |
1002 | more details. | |
33c3fc71 | 1003 | |
8690bbcf MD |
1004 | # Architectures which implement cpu_dcache_is_aliasing() to query |
1005 | # whether the data caches are aliased (VIVT or VIPT with dcache | |
1006 | # aliasing) need to select this. | |
1007 | config ARCH_HAS_CPU_CACHE_ALIASING | |
1008 | bool | |
1009 | ||
c2280be8 AK |
1010 | config ARCH_HAS_CACHE_LINE_SIZE |
1011 | bool | |
1012 | ||
2792d84e KC |
1013 | config ARCH_HAS_CURRENT_STACK_POINTER |
1014 | bool | |
1015 | help | |
1016 | In support of HARDENED_USERCOPY performing stack variable lifetime | |
1017 | checking, an architecture-agnostic way to find the stack pointer | |
1018 | is needed. Once an architecture defines an unsigned long global | |
1019 | register alias named "current_stack_pointer", this config can be | |
1020 | selected. | |
1021 | ||
17596731 | 1022 | config ARCH_HAS_PTE_DEVMAP |
65f7d049 OH |
1023 | bool |
1024 | ||
63703f37 KW |
1025 | config ARCH_HAS_ZONE_DMA_SET |
1026 | bool | |
1027 | ||
1028 | config ZONE_DMA | |
1029 | bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET | |
1030 | default y if ARM64 || X86 | |
1031 | ||
1032 | config ZONE_DMA32 | |
1033 | bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET | |
1034 | depends on !X86_32 | |
1035 | default y if ARM64 | |
1036 | ||
033fbae9 | 1037 | config ZONE_DEVICE |
5042db43 | 1038 | bool "Device memory (pmem, HMM, etc...) hotplug support" |
033fbae9 DW |
1039 | depends on MEMORY_HOTPLUG |
1040 | depends on MEMORY_HOTREMOVE | |
99490f16 | 1041 | depends on SPARSEMEM_VMEMMAP |
17596731 | 1042 | depends on ARCH_HAS_PTE_DEVMAP |
3a08cd52 | 1043 | select XARRAY_MULTI |
033fbae9 DW |
1044 | |
1045 | help | |
1046 | Device memory hotplug support allows for establishing pmem, | |
1047 | or other device driver discovered memory regions, in the | |
1048 | memmap. This allows pfn_to_page() lookups of otherwise | |
1049 | "device-physical" addresses which is needed for using a DAX | |
1050 | mapping in an O_DIRECT operation, among other things. | |
1051 | ||
1052 | If FS_DAX is enabled, then say Y. | |
06a660ad | 1053 | |
9c240a7b CH |
1054 | # |
1055 | # Helpers to mirror range of the CPU page tables of a process into device page | |
1056 | # tables. | |
1057 | # | |
c0b12405 | 1058 | config HMM_MIRROR |
9c240a7b | 1059 | bool |
f442c283 | 1060 | depends on MMU |
c0b12405 | 1061 | |
14b80582 DW |
1062 | config GET_FREE_REGION |
1063 | depends on SPARSEMEM | |
1064 | bool | |
1065 | ||
5042db43 JG |
1066 | config DEVICE_PRIVATE |
1067 | bool "Unaddressable device memory (GPU memory, ...)" | |
7328d9cc | 1068 | depends on ZONE_DEVICE |
14b80582 | 1069 | select GET_FREE_REGION |
5042db43 JG |
1070 | |
1071 | help | |
1072 | Allows creation of struct pages to represent unaddressable device | |
1073 | memory; i.e., memory that is only accessible from the device (or | |
1074 | group of devices). You likely also want to select HMM_MIRROR. | |
1075 | ||
3e9a9e25 CH |
1076 | config VMAP_PFN |
1077 | bool | |
1078 | ||
63c17fb8 DH |
1079 | config ARCH_USES_HIGH_VMA_FLAGS |
1080 | bool | |
66d37570 DH |
1081 | config ARCH_HAS_PKEYS |
1082 | bool | |
30a5b536 | 1083 | |
b0284cd2 CM |
1084 | config ARCH_USES_PG_ARCH_X |
1085 | bool | |
1086 | help | |
1087 | Enable the definition of PG_arch_x page flags with x > 1. Only | |
1088 | suitable for 64-bit architectures with CONFIG_FLATMEM or | |
1089 | CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be | |
1090 | enough room for additional bits in page->flags. | |
1091 | ||
0710d012 VB |
1092 | config VM_EVENT_COUNTERS |
1093 | default y | |
1094 | bool "Enable VM event counters for /proc/vmstat" if EXPERT | |
1095 | help | |
1096 | VM event counters are needed for event counts to be shown. | |
1097 | This option allows the disabling of the VM event counters | |
1098 | on EXPERT systems. /proc/vmstat will only show page counts | |
1099 | if VM event counters are disabled. | |
1100 | ||
30a5b536 DZ |
1101 | config PERCPU_STATS |
1102 | bool "Collect percpu memory statistics" | |
30a5b536 DZ |
1103 | help |
1104 | This feature collects and exposes statistics via debugfs. The | |
1105 | information includes global and per chunk statistics, which can | |
1106 | be used to help understand percpu memory usage. | |
64c349f4 | 1107 | |
9c84f229 JH |
1108 | config GUP_TEST |
1109 | bool "Enable infrastructure for get_user_pages()-related unit tests" | |
d0de8241 | 1110 | depends on DEBUG_FS |
64c349f4 | 1111 | help |
9c84f229 JH |
1112 | Provides /sys/kernel/debug/gup_test, which in turn provides a way |
1113 | to make ioctl calls that can launch kernel-based unit tests for | |
1114 | the get_user_pages*() and pin_user_pages*() family of API calls. | |
64c349f4 | 1115 | |
9c84f229 JH |
1116 | These tests include benchmark testing of the _fast variants of |
1117 | get_user_pages*() and pin_user_pages*(), as well as smoke tests of | |
1118 | the non-_fast variants. | |
1119 | ||
f4f9bda4 JH |
1120 | There is also a sub-test that allows running dump_page() on any |
1121 | of up to eight pages (selected by command line args) within the | |
1122 | range of user-space addresses. These pages are either pinned via | |
1123 | pin_user_pages*(), or pinned via get_user_pages*(), as specified | |
1124 | by other command line arguments. | |
1125 | ||
baa489fa | 1126 | See tools/testing/selftests/mm/gup_test.c |
3010a5ea | 1127 | |
d0de8241 BS |
1128 | comment "GUP_TEST needs to have DEBUG_FS enabled" |
1129 | depends on !GUP_TEST && !DEBUG_FS | |
3010a5ea | 1130 | |
6ca297d4 | 1131 | config GUP_GET_PXX_LOW_HIGH |
39656e83 CH |
1132 | bool |
1133 | ||
def85743 KB |
1134 | config DMAPOOL_TEST |
1135 | tristate "Enable a module to run time tests on dma_pool" | |
1136 | depends on HAS_DMA | |
1137 | help | |
1138 | Provides a test module that will allocate and free many blocks of | |
1139 | various sizes and report how long it takes. This is intended to | |
1140 | provide a consistent way to measure how changes to the | |
1141 | dma_pool_alloc/free routines affect performance. | |
1142 | ||
3010a5ea LD |
1143 | config ARCH_HAS_PTE_SPECIAL |
1144 | bool | |
59e0b520 | 1145 | |
c5acad84 TH |
1146 | config MAPPING_DIRTY_HELPERS |
1147 | bool | |
1148 | ||
298fa1ad TG |
1149 | config KMAP_LOCAL |
1150 | bool | |
1151 | ||
825c43f5 AB |
1152 | config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY |
1153 | bool | |
1154 | ||
1fbaf8fc CH |
1155 | # struct io_mapping based helper. Selected by drivers that need them |
1156 | config IO_MAPPING | |
1157 | bool | |
1507f512 | 1158 | |
626e98cb TW |
1159 | config MEMFD_CREATE |
1160 | bool "Enable memfd_create() system call" if EXPERT | |
1161 | ||
1507f512 | 1162 | config SECRETMEM |
74947724 LB |
1163 | default y |
1164 | bool "Enable memfd_secret() system call" if EXPERT | |
1165 | depends on ARCH_HAS_SET_DIRECT_MAP | |
1166 | help | |
1167 | Enable the memfd_secret() system call with the ability to create | |
1168 | memory areas visible only in the context of the owning process and | |
1169 | not mapped to other processes and other kernel page tables. | |
1507f512 | 1170 | |
9a10064f CC |
1171 | config ANON_VMA_NAME |
1172 | bool "Anonymous VMA name support" | |
1173 | depends on PROC_FS && ADVISE_SYSCALLS && MMU | |
1174 | ||
1175 | help | |
1176 | Allow naming anonymous virtual memory areas. | |
1177 | ||
1178 | This feature allows assigning names to virtual memory areas. Assigned | |
1179 | names can be later retrieved from /proc/pid/maps and /proc/pid/smaps | |
1180 | and help identifying individual anonymous memory areas. | |
1181 | Assigning a name to anonymous virtual memory area might prevent that | |
1182 | area from being merged with adjacent virtual memory areas due to the | |
1183 | difference in their name. | |
1184 | ||
430529b5 PX |
1185 | config HAVE_ARCH_USERFAULTFD_WP |
1186 | bool | |
1187 | help | |
1188 | Arch has userfaultfd write protection support | |
1189 | ||
1190 | config HAVE_ARCH_USERFAULTFD_MINOR | |
1191 | bool | |
1192 | help | |
1193 | Arch has userfaultfd minor fault support | |
1194 | ||
97219cc3 PX |
1195 | menuconfig USERFAULTFD |
1196 | bool "Enable userfaultfd() system call" | |
1197 | depends on MMU | |
1198 | help | |
1199 | Enable the userfaultfd() system call that allows to intercept and | |
1200 | handle page faults in userland. | |
1201 | ||
1202 | if USERFAULTFD | |
1db9dbc2 | 1203 | config PTE_MARKER_UFFD_WP |
81e0f15f PX |
1204 | bool "Userfaultfd write protection support for shmem/hugetlbfs" |
1205 | default y | |
1206 | depends on HAVE_ARCH_USERFAULTFD_WP | |
1db9dbc2 PX |
1207 | |
1208 | help | |
1209 | Allows to create marker PTEs for userfaultfd write protection | |
1210 | purposes. It is required to enable userfaultfd write protection on | |
1211 | file-backed memory types like shmem and hugetlbfs. | |
97219cc3 | 1212 | endif # USERFAULTFD |
1db9dbc2 | 1213 | |
ac35a490 | 1214 | # multi-gen LRU { |
ec1c86b2 YZ |
1215 | config LRU_GEN |
1216 | bool "Multi-Gen LRU" | |
1217 | depends on MMU | |
1218 | # make sure folio->flags has enough spare bits | |
1219 | depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP | |
1220 | help | |
07017acb YZ |
1221 | A high performance LRU implementation to overcommit memory. See |
1222 | Documentation/admin-guide/mm/multigen_lru.rst for details. | |
ec1c86b2 | 1223 | |
354ed597 YZ |
1224 | config LRU_GEN_ENABLED |
1225 | bool "Enable by default" | |
1226 | depends on LRU_GEN | |
1227 | help | |
1228 | This option enables the multi-gen LRU by default. | |
1229 | ||
ac35a490 YZ |
1230 | config LRU_GEN_STATS |
1231 | bool "Full stats for debugging" | |
1232 | depends on LRU_GEN | |
1233 | help | |
1234 | Do not enable this option unless you plan to look at historical stats | |
1235 | from evicted generations for debugging purpose. | |
1236 | ||
1237 | This option has a per-memcg and per-node memory overhead. | |
61dd3f24 KH |
1238 | |
1239 | config LRU_GEN_WALKS_MMU | |
1240 | def_bool y | |
1241 | depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG | |
ac35a490 YZ |
1242 | # } |
1243 | ||
0b6cc04f SB |
1244 | config ARCH_SUPPORTS_PER_VMA_LOCK |
1245 | def_bool n | |
1246 | ||
1247 | config PER_VMA_LOCK | |
1248 | def_bool y | |
1249 | depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP | |
1250 | help | |
1251 | Allow per-vma locking during page fault handling. | |
1252 | ||
1253 | This feature allows locking each virtual memory area separately when | |
1254 | handling page faults instead of taking mmap_lock. | |
1255 | ||
c2508ec5 LT |
1256 | config LOCK_MM_AND_FIND_VMA |
1257 | bool | |
1258 | depends on !STACK_GROWSUP | |
1259 | ||
8f23f5db JG |
1260 | config IOMMU_MM_DATA |
1261 | bool | |
1262 | ||
12af2b83 MRI |
1263 | config EXECMEM |
1264 | bool | |
1265 | ||
2224d848 SP |
1266 | source "mm/damon/Kconfig" |
1267 | ||
59e0b520 | 1268 | endmenu |