Blame view
mm/memory_hotplug.c
48.4 KB
3947be196 [PATCH] memory ho... |
1 2 3 4 5 |
/* * linux/mm/memory_hotplug.c * * Copyright (C) */ |
3947be196 [PATCH] memory ho... |
6 7 8 9 10 |
#include <linux/stddef.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> |
3947be196 [PATCH] memory ho... |
11 |
#include <linux/compiler.h> |
b95f1b31b mm: Map most file... |
12 |
#include <linux/export.h> |
3947be196 [PATCH] memory ho... |
13 |
#include <linux/pagevec.h> |
2d1d43f6a [PATCH] call mm/p... |
14 |
#include <linux/writeback.h> |
3947be196 [PATCH] memory ho... |
15 16 17 18 19 20 21 |
#include <linux/slab.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/highmem.h> #include <linux/vmalloc.h> |
0a5470390 [PATCH] register ... |
22 |
#include <linux/ioport.h> |
0c0e61958 memory unplug: pa... |
23 24 25 |
#include <linux/delay.h> #include <linux/migrate.h> #include <linux/page-isolation.h> |
71088785c mm: cleanup to ma... |
26 |
#include <linux/pfn.h> |
6ad696d2c mm: allow memory ... |
27 |
#include <linux/suspend.h> |
6d9c285a6 mm: move inc_zone... |
28 |
#include <linux/mm_inline.h> |
d96ae5309 memory-hotplug: c... |
29 |
#include <linux/firmware-map.h> |
60a5a19e7 memory-hotplug: r... |
30 |
#include <linux/stop_machine.h> |
c8721bbbd mm: memory-hotplu... |
31 |
#include <linux/hugetlb.h> |
c5320926e mem-hotplug: intr... |
32 |
#include <linux/memblock.h> |
3947be196 [PATCH] memory ho... |
33 34 |
#include <asm/tlbflush.h> |
1e5ad9a3b mm/memory_hotplug... |
35 |
#include "internal.h" |
9d0ad8ca4 mm: extend memory... |
36 37 38 39 40 41 42 43 44 45 |
/* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be * changed by calling set_online_page_callback() for callback registration * and restore_online_page_callback() for generic callback restore. */ static void generic_online_page(struct page *page); static online_page_callback_t online_page_callback = generic_online_page; |
20d6c96b5 mem-hotplug: intr... |
46 47 48 49 50 |
DEFINE_MUTEX(mem_hotplug_mutex); void lock_memory_hotplug(void) { mutex_lock(&mem_hotplug_mutex); |
20d6c96b5 mem-hotplug: intr... |
51 52 53 54 |
} void unlock_memory_hotplug(void) { |
20d6c96b5 mem-hotplug: intr... |
55 56 |
mutex_unlock(&mem_hotplug_mutex); } |
45e0b78b0 [PATCH] hot-add-m... |
57 58 59 60 61 62 63 64 65 66 |
/* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) { struct resource *res; res = kzalloc(sizeof(struct resource), GFP_KERNEL); BUG_ON(!res); res->name = "System RAM"; res->start = start; res->end = start + size - 1; |
887c3cb18 Add IORESOUCE_BUS... |
67 |
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; |
45e0b78b0 [PATCH] hot-add-m... |
68 |
if (request_resource(&iomem_resource, res) < 0) { |
4996eed86 mm/memory_hotplug... |
69 70 |
pr_debug("System RAM resource %pR cannot be added ", res); |
45e0b78b0 [PATCH] hot-add-m... |
71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
kfree(res); res = NULL; } return res; } static void release_memory_resource(struct resource *res) { if (!res) return; release_resource(res); kfree(res); return; } |
53947027a [PATCH] hot-add-m... |
85 |
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE |
46723bfa5 memory-hotplug: i... |
86 87 |
void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) |
047532787 memory hotplug: r... |
88 |
{ |
5f24ce5fd thp: remove PG_buddy |
89 |
page->lru.next = (struct list_head *) type; |
047532787 memory hotplug: r... |
90 91 92 93 |
SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); } |
170a5a7eb mm: make __free_p... |
94 |
void put_page_bootmem(struct page *page) |
047532787 memory hotplug: r... |
95 |
{ |
5f24ce5fd thp: remove PG_buddy |
96 |
unsigned long type; |
047532787 memory hotplug: r... |
97 |
|
5f24ce5fd thp: remove PG_buddy |
98 99 100 |
type = (unsigned long) page->lru.next; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); |
047532787 memory hotplug: r... |
101 102 103 104 |
if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); |
5f24ce5fd thp: remove PG_buddy |
105 |
INIT_LIST_HEAD(&page->lru); |
170a5a7eb mm: make __free_p... |
106 |
free_reserved_page(page); |
047532787 memory hotplug: r... |
107 |
} |
047532787 memory hotplug: r... |
108 |
} |
46723bfa5 memory-hotplug: i... |
109 110 |
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE #ifndef CONFIG_SPARSEMEM_VMEMMAP |
d92bc3185 mm: make register... |
111 |
static void register_page_bootmem_info_section(unsigned long start_pfn) |
047532787 memory hotplug: r... |
112 113 114 115 |
{ unsigned long *usemap, mapsize, section_nr, i; struct mem_section *ms; struct page *page, *memmap; |
047532787 memory hotplug: r... |
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
section_nr = pfn_to_section_nr(start_pfn); ms = __nr_to_section(section_nr); /* Get section's memmap address */ memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); /* * Get page for the memmap's phys address * XXX: need more consideration for sparse_vmemmap... */ page = virt_to_page(memmap); mapsize = sizeof(struct page) * PAGES_PER_SECTION; mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; /* remember memmap's page */ for (i = 0; i < mapsize; i++, page++) get_page_bootmem(section_nr, page, SECTION_INFO); usemap = __nr_to_section(section_nr)->pageblock_flags; page = virt_to_page(usemap); mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT; for (i = 0; i < mapsize; i++, page++) |
af370fb8c memory hotplug: s... |
140 |
get_page_bootmem(section_nr, page, MIX_SECTION_INFO); |
047532787 memory hotplug: r... |
141 142 |
} |
46723bfa5 memory-hotplug: i... |
143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
#else /* CONFIG_SPARSEMEM_VMEMMAP */ static void register_page_bootmem_info_section(unsigned long start_pfn) { unsigned long *usemap, mapsize, section_nr, i; struct mem_section *ms; struct page *page, *memmap; if (!pfn_valid(start_pfn)) return; section_nr = pfn_to_section_nr(start_pfn); ms = __nr_to_section(section_nr); memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); usemap = __nr_to_section(section_nr)->pageblock_flags; page = virt_to_page(usemap); mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT; for (i = 0; i < mapsize; i++, page++) get_page_bootmem(section_nr, page, MIX_SECTION_INFO); } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ |
047532787 memory hotplug: r... |
169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
void register_page_bootmem_info_node(struct pglist_data *pgdat) { unsigned long i, pfn, end_pfn, nr_pages; int node = pgdat->node_id; struct page *page; struct zone *zone; nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; page = virt_to_page(pgdat); for (i = 0; i < nr_pages; i++, page++) get_page_bootmem(node, page, NODE_INFO); zone = &pgdat->node_zones[0]; for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) { |
139c2d75b mm: use zone_is_i... |
185 |
if (zone_is_initialized(zone)) { |
047532787 memory hotplug: r... |
186 187 188 189 190 191 192 193 194 195 196 |
nr_pages = zone->wait_table_hash_nr_entries * sizeof(wait_queue_head_t); nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT; page = virt_to_page(zone->wait_table); for (i = 0; i < nr_pages; i++, page++) get_page_bootmem(node, page, NODE_INFO); } } pfn = pgdat->node_start_pfn; |
c1f194952 mm/memory_hotplug... |
197 |
end_pfn = pgdat_end_pfn(pgdat); |
047532787 memory hotplug: r... |
198 |
|
7e9f5eb03 mm/memory_hotplug... |
199 |
/* register section info */ |
f14851af0 memory hotplug: f... |
200 201 202 203 204 |
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { /* * Some platforms can assign the same pfn to multiple nodes - on * node0 as well as nodeN. To avoid registering a pfn against * multiple nodes we check that this pfn does not already |
7e9f5eb03 mm/memory_hotplug... |
205 |
* reside in some other nodes. |
f14851af0 memory hotplug: f... |
206 207 208 209 |
*/ if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) register_page_bootmem_info_section(pfn); } |
047532787 memory hotplug: r... |
210 |
} |
46723bfa5 memory-hotplug: i... |
211 |
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ |
047532787 memory hotplug: r... |
212 |
|
76cdd58e5 memory_hotplug: a... |
213 214 215 216 217 218 |
static void grow_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { unsigned long old_zone_end_pfn; zone_span_writelock(zone); |
c33bc315f mm: use zone_end_... |
219 |
old_zone_end_pfn = zone_end_pfn(zone); |
8080fc038 mm: use zone_is_e... |
220 |
if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn) |
76cdd58e5 memory_hotplug: a... |
221 222 223 224 225 226 227 |
zone->zone_start_pfn = start_pfn; zone->spanned_pages = max(old_zone_end_pfn, end_pfn) - zone->zone_start_pfn; zone_span_writeunlock(zone); } |
511c2aba8 mm, memory-hotplu... |
228 229 230 231 |
static void resize_zone(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { zone_span_writelock(zone); |
e455a9b92 memory_hotplug: h... |
232 233 234 235 236 237 238 239 240 241 242 |
if (end_pfn - start_pfn) { zone->zone_start_pfn = start_pfn; zone->spanned_pages = end_pfn - start_pfn; } else { /* * make it consist as free_area_init_core(), * if spanned_pages = 0, then keep start_pfn = 0 */ zone->zone_start_pfn = 0; zone->spanned_pages = 0; } |
511c2aba8 mm, memory-hotplu... |
243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
zone_span_writeunlock(zone); } static void fix_zone_id(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { enum zone_type zid = zone_idx(zone); int nid = zone->zone_pgdat->node_id; unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) set_page_links(pfn_to_page(pfn), zid, nid, pfn); } |
f6bbb78e5 mm: add helper en... |
257 |
/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or |
9e43aa2b8 mm/memory_hotplug... |
258 |
* alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */ |
f6bbb78e5 mm: add helper en... |
259 260 261 262 263 264 265 266 |
static int __ref ensure_zone_is_initialized(struct zone *zone, unsigned long start_pfn, unsigned long num_pages) { if (!zone_is_initialized(zone)) return init_currently_empty_zone(zone, start_pfn, num_pages, MEMMAP_HOTPLUG); return 0; } |
e455a9b92 memory_hotplug: h... |
267 |
static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, |
511c2aba8 mm, memory-hotplu... |
268 269 |
unsigned long start_pfn, unsigned long end_pfn) { |
e455a9b92 memory_hotplug: h... |
270 |
int ret; |
511c2aba8 mm, memory-hotplu... |
271 |
unsigned long flags; |
e455a9b92 memory_hotplug: h... |
272 |
unsigned long z1_start_pfn; |
64dd1b29b mm/memory_hotplug... |
273 274 275 |
ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn); if (ret) return ret; |
511c2aba8 mm, memory-hotplu... |
276 277 278 279 |
pgdat_resize_lock(z1->zone_pgdat, &flags); /* can't move pfns which are higher than @z2 */ |
108bcc96e mm: add & use zon... |
280 |
if (end_pfn > zone_end_pfn(z2)) |
511c2aba8 mm, memory-hotplu... |
281 |
goto out_fail; |
834405c3b mm: fix some triv... |
282 |
/* the move out part must be at the left most of @z2 */ |
511c2aba8 mm, memory-hotplu... |
283 284 285 286 287 |
if (start_pfn > z2->zone_start_pfn) goto out_fail; /* must included/overlap */ if (end_pfn <= z2->zone_start_pfn) goto out_fail; |
e455a9b92 memory_hotplug: h... |
288 |
/* use start_pfn for z1's start_pfn if z1 is empty */ |
8080fc038 mm: use zone_is_e... |
289 |
if (!zone_is_empty(z1)) |
e455a9b92 memory_hotplug: h... |
290 291 292 293 294 |
z1_start_pfn = z1->zone_start_pfn; else z1_start_pfn = start_pfn; resize_zone(z1, z1_start_pfn, end_pfn); |
108bcc96e mm: add & use zon... |
295 |
resize_zone(z2, end_pfn, zone_end_pfn(z2)); |
511c2aba8 mm, memory-hotplu... |
296 297 298 299 300 301 302 303 304 305 |
pgdat_resize_unlock(z1->zone_pgdat, &flags); fix_zone_id(z1, start_pfn, end_pfn); return 0; out_fail: pgdat_resize_unlock(z1->zone_pgdat, &flags); return -1; } |
e455a9b92 memory_hotplug: h... |
306 |
static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, |
511c2aba8 mm, memory-hotplu... |
307 308 |
unsigned long start_pfn, unsigned long end_pfn) { |
e455a9b92 memory_hotplug: h... |
309 |
int ret; |
511c2aba8 mm, memory-hotplu... |
310 |
unsigned long flags; |
e455a9b92 memory_hotplug: h... |
311 |
unsigned long z2_end_pfn; |
64dd1b29b mm/memory_hotplug... |
312 313 314 |
ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn); if (ret) return ret; |
511c2aba8 mm, memory-hotplu... |
315 316 317 318 319 320 321 |
pgdat_resize_lock(z1->zone_pgdat, &flags); /* can't move pfns which are lower than @z1 */ if (z1->zone_start_pfn > start_pfn) goto out_fail; /* the move out part mast at the right most of @z1 */ |
108bcc96e mm: add & use zon... |
322 |
if (zone_end_pfn(z1) > end_pfn) |
511c2aba8 mm, memory-hotplu... |
323 324 |
goto out_fail; /* must included/overlap */ |
108bcc96e mm: add & use zon... |
325 |
if (start_pfn >= zone_end_pfn(z1)) |
511c2aba8 mm, memory-hotplu... |
326 |
goto out_fail; |
e455a9b92 memory_hotplug: h... |
327 |
/* use end_pfn for z2's end_pfn if z2 is empty */ |
8080fc038 mm: use zone_is_e... |
328 |
if (!zone_is_empty(z2)) |
108bcc96e mm: add & use zon... |
329 |
z2_end_pfn = zone_end_pfn(z2); |
e455a9b92 memory_hotplug: h... |
330 331 |
else z2_end_pfn = end_pfn; |
511c2aba8 mm, memory-hotplu... |
332 |
resize_zone(z1, z1->zone_start_pfn, start_pfn); |
e455a9b92 memory_hotplug: h... |
333 |
resize_zone(z2, start_pfn, z2_end_pfn); |
511c2aba8 mm, memory-hotplu... |
334 335 336 337 338 339 340 341 342 343 |
pgdat_resize_unlock(z1->zone_pgdat, &flags); fix_zone_id(z2, start_pfn, end_pfn); return 0; out_fail: pgdat_resize_unlock(z1->zone_pgdat, &flags); return -1; } |
76cdd58e5 memory_hotplug: a... |
344 345 346 |
static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { |
83285c72e mm: use pgdat_end... |
347 |
unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat); |
76cdd58e5 memory_hotplug: a... |
348 |
|
712cd386f mm/memory_hotplug... |
349 |
if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn) |
76cdd58e5 memory_hotplug: a... |
350 351 352 353 354 |
pgdat->node_start_pfn = start_pfn; pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) - pgdat->node_start_pfn; } |
31168481c meminit section w... |
355 |
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) |
3947be196 [PATCH] memory ho... |
356 357 358 359 360 |
{ struct pglist_data *pgdat = zone->zone_pgdat; int nr_pages = PAGES_PER_SECTION; int nid = pgdat->node_id; int zone_type; |
76cdd58e5 memory_hotplug: a... |
361 |
unsigned long flags; |
64dd1b29b mm/memory_hotplug... |
362 |
int ret; |
3947be196 [PATCH] memory ho... |
363 364 |
zone_type = zone - pgdat->node_zones; |
64dd1b29b mm/memory_hotplug... |
365 366 367 |
ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages); if (ret) return ret; |
76cdd58e5 memory_hotplug: a... |
368 |
|
76cdd58e5 memory_hotplug: a... |
369 370 371 372 373 |
pgdat_resize_lock(zone->zone_pgdat, &flags); grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages); grow_pgdat_span(zone->zone_pgdat, phys_start_pfn, phys_start_pfn + nr_pages); pgdat_resize_unlock(zone->zone_pgdat, &flags); |
a2f3aa025 [PATCH] Fix spars... |
374 375 |
memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn, MEMMAP_HOTPLUG); |
718127cc3 [PATCH] wait_tabl... |
376 |
return 0; |
3947be196 [PATCH] memory ho... |
377 |
} |
c04fc586c mm: show node to ... |
378 379 |
static int __meminit __add_section(int nid, struct zone *zone, unsigned long phys_start_pfn) |
3947be196 [PATCH] memory ho... |
380 |
{ |
3947be196 [PATCH] memory ho... |
381 |
int ret; |
ebd15302d [PATCH] memory ho... |
382 383 |
if (pfn_valid(phys_start_pfn)) return -EEXIST; |
85b35feae mm/sparsemem: use... |
384 |
ret = sparse_add_one_section(zone, phys_start_pfn); |
3947be196 [PATCH] memory ho... |
385 386 387 |
if (ret < 0) return ret; |
718127cc3 [PATCH] wait_tabl... |
388 389 390 391 |
ret = __add_zone(zone, phys_start_pfn); if (ret < 0) return ret; |
c04fc586c mm: show node to ... |
392 |
return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); |
3947be196 [PATCH] memory ho... |
393 |
} |
4edd7ceff mm, hotplug: avoi... |
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 |
/* * Reasonably generic function for adding memory. It is * expected that archs that support memory hotplug will * call this function after deciding the zone to which to * add the new pages. */ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { unsigned long i; int err = 0; int start_sec, end_sec; /* during initialize mem_map, align hot-added range to section */ start_sec = pfn_to_section_nr(phys_start_pfn); end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); for (i = start_sec; i <= end_sec; i++) { err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); /* * EEXIST is finally dealt with by ioresource collision * check. see add_memory() => register_memory_resource() * Warning will be printed if there is collision. */ if (err && (err != -EEXIST)) break; err = 0; } return err; } EXPORT_SYMBOL_GPL(__add_pages); #ifdef CONFIG_MEMORY_HOTREMOVE |
815121d2b memory_hotplug: c... |
428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 |
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static int find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { struct mem_section *ms; for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) { ms = __pfn_to_section(start_pfn); if (unlikely(!valid_section(ms))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) continue; if (zone && zone != page_zone(pfn_to_page(start_pfn))) continue; return start_pfn; } return 0; } /* find the biggest valid pfn in the range [start_pfn, end_pfn). */ static int find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { struct mem_section *ms; unsigned long pfn; /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) { ms = __pfn_to_section(pfn); if (unlikely(!valid_section(ms))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) continue; if (zone && zone != page_zone(pfn_to_page(pfn))) continue; return pfn; } return 0; } static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { |
c33bc315f mm: use zone_end_... |
484 485 486 |
unsigned long zone_start_pfn = zone->zone_start_pfn; unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ unsigned long zone_end_pfn = z; |
815121d2b memory_hotplug: c... |
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 |
unsigned long pfn; struct mem_section *ms; int nid = zone_to_nid(zone); zone_span_writelock(zone); if (zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need * shrink zone->zone_start_pfn and zone->zone_spanned_pages. * In this case, we find second smallest valid mem_section * for shrinking zone. */ pfn = find_smallest_section_pfn(nid, zone, end_pfn, zone_end_pfn); if (pfn) { zone->zone_start_pfn = pfn; zone->spanned_pages = zone_end_pfn - pfn; } } else if (zone_end_pfn == end_pfn) { /* * If the section is biggest section in the zone, it need * shrink zone->spanned_pages. * In this case, we find second biggest valid mem_section for * shrinking zone. */ pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, start_pfn); if (pfn) zone->spanned_pages = pfn - zone_start_pfn + 1; } /* * The section is not biggest or smallest mem_section in the zone, it * only creates a hole in the zone. So in this case, we need not * change the zone. But perhaps, the zone has only hole data. Thus * it check the zone has only hole or not. */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) { ms = __pfn_to_section(pfn); if (unlikely(!valid_section(ms))) continue; if (page_zone(pfn_to_page(pfn)) != zone) continue; /* If the section is current section, it continues the loop */ if (start_pfn == pfn) continue; /* If we find valid section, we have nothing to do */ zone_span_writeunlock(zone); return; } /* The zone has no valid section */ zone->zone_start_pfn = 0; zone->spanned_pages = 0; zone_span_writeunlock(zone); } static void shrink_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { |
83285c72e mm: use pgdat_end... |
552 553 554 |
unsigned long pgdat_start_pfn = pgdat->node_start_pfn; unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ unsigned long pgdat_end_pfn = p; |
815121d2b memory_hotplug: c... |
555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 |
unsigned long pfn; struct mem_section *ms; int nid = pgdat->node_id; if (pgdat_start_pfn == start_pfn) { /* * If the section is smallest section in the pgdat, it need * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. * In this case, we find second smallest valid mem_section * for shrinking zone. */ pfn = find_smallest_section_pfn(nid, NULL, end_pfn, pgdat_end_pfn); if (pfn) { pgdat->node_start_pfn = pfn; pgdat->node_spanned_pages = pgdat_end_pfn - pfn; } } else if (pgdat_end_pfn == end_pfn) { /* * If the section is biggest section in the pgdat, it need * shrink pgdat->node_spanned_pages. * In this case, we find second biggest valid mem_section for * shrinking zone. */ pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, start_pfn); if (pfn) pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; } /* * If the section is not biggest or smallest mem_section in the pgdat, * it only creates a hole in the pgdat. So in this case, we need not * change the pgdat. * But perhaps, the pgdat has only hole data. Thus it check the pgdat * has only hole or not. */ pfn = pgdat_start_pfn; for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) { ms = __pfn_to_section(pfn); if (unlikely(!valid_section(ms))) continue; if (pfn_to_nid(pfn) != nid) continue; /* If the section is current section, it continues the loop */ if (start_pfn == pfn) continue; /* If we find valid section, we have nothing to do */ return; } /* The pgdat has no valid section */ pgdat->node_start_pfn = 0; pgdat->node_spanned_pages = 0; } static void __remove_zone(struct zone *zone, unsigned long start_pfn) { struct pglist_data *pgdat = zone->zone_pgdat; int nr_pages = PAGES_PER_SECTION; int zone_type; unsigned long flags; zone_type = zone - pgdat->node_zones; pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); pgdat_resize_unlock(zone->zone_pgdat, &flags); } |
ea01ea937 hotplug memory re... |
629 630 |
static int __remove_section(struct zone *zone, struct mem_section *ms) { |
815121d2b memory_hotplug: c... |
631 632 |
unsigned long start_pfn; int scn_nr; |
ea01ea937 hotplug memory re... |
633 634 635 636 637 638 639 640 |
int ret = -EINVAL; if (!valid_section(ms)) return ret; ret = unregister_memory_section(ms); if (ret) return ret; |
815121d2b memory_hotplug: c... |
641 642 643 |
scn_nr = __section_nr(ms); start_pfn = section_nr_to_pfn(scn_nr); __remove_zone(zone, start_pfn); |
ea01ea937 hotplug memory re... |
644 |
sparse_remove_one_section(zone, ms); |
ea01ea937 hotplug memory re... |
645 646 |
return 0; } |
ea01ea937 hotplug memory re... |
647 648 649 650 651 652 653 654 655 656 657 658 659 660 |
/** * __remove_pages() - remove sections of pages from a zone * @zone: zone from which pages need to be removed * @phys_start_pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * * Generic helper function to remove section mappings and sysfs entries * for the section of the memory we are removing. Caller needs to make * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { |
fe74ebb10 mm: change __remo... |
661 |
unsigned long i; |
ea01ea937 hotplug memory re... |
662 |
int sections_to_remove; |
fe74ebb10 mm: change __remo... |
663 664 |
resource_size_t start, size; int ret = 0; |
ea01ea937 hotplug memory re... |
665 666 667 668 669 670 |
/* * We can only remove entire sections */ BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); |
fe74ebb10 mm: change __remo... |
671 672 673 |
start = phys_start_pfn << PAGE_SHIFT; size = nr_pages * PAGE_SIZE; ret = release_mem_region_adjustable(&iomem_resource, start, size); |
348f9f05e mm/memory_hotplug... |
674 675 676 677 678 679 680 |
if (ret) { resource_size_t endres = start + size - 1; pr_warn("Unable to release resource <%pa-%pa> (%d) ", &start, &endres, ret); } |
d760afd4d memory-hotplug: s... |
681 |
|
ea01ea937 hotplug memory re... |
682 683 684 685 686 687 688 689 690 691 |
sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; ret = __remove_section(zone, __pfn_to_section(pfn)); if (ret) break; } return ret; } EXPORT_SYMBOL_GPL(__remove_pages); |
4edd7ceff mm, hotplug: avoi... |
692 |
#endif /* CONFIG_MEMORY_HOTREMOVE */ |
ea01ea937 hotplug memory re... |
693 |
|
9d0ad8ca4 mm: extend memory... |
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 |
int set_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; lock_memory_hotplug(); if (online_page_callback == generic_online_page) { online_page_callback = callback; rc = 0; } unlock_memory_hotplug(); return rc; } EXPORT_SYMBOL_GPL(set_online_page_callback); int restore_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; lock_memory_hotplug(); if (online_page_callback == callback) { online_page_callback = generic_online_page; rc = 0; } unlock_memory_hotplug(); return rc; } EXPORT_SYMBOL_GPL(restore_online_page_callback); void __online_page_set_limits(struct page *page) |
180c06efc hotplug-memory: m... |
729 |
{ |
9d0ad8ca4 mm: extend memory... |
730 731 732 733 734 |
} EXPORT_SYMBOL_GPL(__online_page_set_limits); void __online_page_increment_counters(struct page *page) { |
3dcc0571c mm: correctly upd... |
735 |
adjust_managed_page_count(page, 1); |
9d0ad8ca4 mm: extend memory... |
736 737 |
} EXPORT_SYMBOL_GPL(__online_page_increment_counters); |
180c06efc hotplug-memory: m... |
738 |
|
9d0ad8ca4 mm: extend memory... |
739 740 |
void __online_page_free(struct page *page) { |
3dcc0571c mm: correctly upd... |
741 |
__free_reserved_page(page); |
180c06efc hotplug-memory: m... |
742 |
} |
9d0ad8ca4 mm: extend memory... |
743 744 745 746 747 748 749 750 |
EXPORT_SYMBOL_GPL(__online_page_free); static void generic_online_page(struct page *page) { __online_page_set_limits(page); __online_page_increment_counters(page); __online_page_free(page); } |
180c06efc hotplug-memory: m... |
751 |
|
75884fb1c memory unplug: me... |
752 753 |
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) |
3947be196 [PATCH] memory ho... |
754 755 |
{ unsigned long i; |
75884fb1c memory unplug: me... |
756 757 758 759 760 |
unsigned long onlined_pages = *(unsigned long *)arg; struct page *page; if (PageReserved(pfn_to_page(start_pfn))) for (i = 0; i < nr_pages; i++) { page = pfn_to_page(start_pfn + i); |
9d0ad8ca4 mm: extend memory... |
761 |
(*online_page_callback)(page); |
75884fb1c memory unplug: me... |
762 763 764 765 766 |
onlined_pages++; } *(unsigned long *)arg = onlined_pages; return 0; } |
09285af75 memory_hotplug: a... |
767 |
#ifdef CONFIG_MOVABLE_NODE |
79a4dcefd mm/memory_hotplug... |
768 769 770 771 |
/* * When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have * normal memory. */ |
09285af75 memory_hotplug: a... |
772 773 774 775 |
static bool can_online_high_movable(struct zone *zone) { return true; } |
79a4dcefd mm/memory_hotplug... |
776 |
#else /* CONFIG_MOVABLE_NODE */ |
74d42d8fe memory_hotplug: e... |
777 778 779 780 781 |
/* ensure every online node has NORMAL memory */ static bool can_online_high_movable(struct zone *zone) { return node_state(zone_to_nid(zone), N_NORMAL_MEMORY); } |
79a4dcefd mm/memory_hotplug... |
782 |
#endif /* CONFIG_MOVABLE_NODE */ |
74d42d8fe memory_hotplug: e... |
783 |
|
d9713679d memory_hotplug: f... |
784 785 786 787 788 789 790 791 |
/* check which state of node_states will be changed when online memory */ static void node_states_check_changes_online(unsigned long nr_pages, struct zone *zone, struct memory_notify *arg) { int nid = zone_to_nid(zone); enum zone_type zone_last = ZONE_NORMAL; /* |
6715ddf94 hotplug: update n... |
792 793 794 |
* If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY] * contains nodes which have zones of 0...ZONE_NORMAL, * set zone_last to ZONE_NORMAL. |
d9713679d memory_hotplug: f... |
795 |
* |
6715ddf94 hotplug: update n... |
796 797 798 |
* If we don't have HIGHMEM nor movable node, * node_states[N_NORMAL_MEMORY] contains nodes which have zones of * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE. |
d9713679d memory_hotplug: f... |
799 |
*/ |
6715ddf94 hotplug: update n... |
800 |
if (N_MEMORY == N_NORMAL_MEMORY) |
d9713679d memory_hotplug: f... |
801 802 803 804 805 806 807 808 809 810 811 812 |
zone_last = ZONE_MOVABLE; /* * if the memory to be online is in a zone of 0...zone_last, and * the zones of 0...zone_last don't have memory before online, we will * need to set the node to node_states[N_NORMAL_MEMORY] after * the memory is online. */ if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; else arg->status_change_nid_normal = -1; |
6715ddf94 hotplug: update n... |
813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 |
#ifdef CONFIG_HIGHMEM /* * If we have movable node, node_states[N_HIGH_MEMORY] * contains nodes which have zones of 0...ZONE_HIGHMEM, * set zone_last to ZONE_HIGHMEM. * * If we don't have movable node, node_states[N_NORMAL_MEMORY] * contains nodes which have zones of 0...ZONE_MOVABLE, * set zone_last to ZONE_MOVABLE. */ zone_last = ZONE_HIGHMEM; if (N_MEMORY == N_HIGH_MEMORY) zone_last = ZONE_MOVABLE; if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY)) arg->status_change_nid_high = nid; else arg->status_change_nid_high = -1; #else arg->status_change_nid_high = arg->status_change_nid_normal; #endif |
d9713679d memory_hotplug: f... |
834 835 |
/* * if the node don't have memory befor online, we will need to |
6715ddf94 hotplug: update n... |
836 |
* set the node to node_states[N_MEMORY] after the memory |
d9713679d memory_hotplug: f... |
837 838 |
* is online. */ |
6715ddf94 hotplug: update n... |
839 |
if (!node_state(nid, N_MEMORY)) |
d9713679d memory_hotplug: f... |
840 841 842 843 844 845 846 847 848 |
arg->status_change_nid = nid; else arg->status_change_nid = -1; } static void node_states_set_node(int node, struct memory_notify *arg) { if (arg->status_change_nid_normal >= 0) node_set_state(node, N_NORMAL_MEMORY); |
6715ddf94 hotplug: update n... |
849 850 851 852 |
if (arg->status_change_nid_high >= 0) node_set_state(node, N_HIGH_MEMORY); node_set_state(node, N_MEMORY); |
d9713679d memory_hotplug: f... |
853 |
} |
75884fb1c memory unplug: me... |
854 |
|
511c2aba8 mm, memory-hotplu... |
855 |
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) |
75884fb1c memory unplug: me... |
856 |
{ |
aa47228a1 memory_hotplug: u... |
857 |
unsigned long flags; |
3947be196 [PATCH] memory ho... |
858 859 |
unsigned long onlined_pages = 0; struct zone *zone; |
6811378e7 [PATCH] wait_tabl... |
860 |
int need_zonelists_rebuild = 0; |
7b78d335a memory hotplug: r... |
861 862 863 |
int nid; int ret; struct memory_notify arg; |
925268a06 memory hotplug: o... |
864 |
lock_memory_hotplug(); |
d9713679d memory_hotplug: f... |
865 866 867 868 869 870 |
/* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the * memory_block->state_mutex. */ zone = page_zone(pfn_to_page(pfn)); |
74d42d8fe memory_hotplug: e... |
871 872 873 |
if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) && !can_online_high_movable(zone)) { unlock_memory_hotplug(); |
0a1be1509 mm/memory_hotplug... |
874 |
return -EINVAL; |
74d42d8fe memory_hotplug: e... |
875 |
} |
511c2aba8 mm, memory-hotplu... |
876 877 878 |
if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) { if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) { unlock_memory_hotplug(); |
0a1be1509 mm/memory_hotplug... |
879 |
return -EINVAL; |
511c2aba8 mm, memory-hotplu... |
880 881 882 883 884 |
} } if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) { if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) { unlock_memory_hotplug(); |
0a1be1509 mm/memory_hotplug... |
885 |
return -EINVAL; |
511c2aba8 mm, memory-hotplu... |
886 887 888 889 890 |
} } /* Previous code may changed the zone of the pfn range */ zone = page_zone(pfn_to_page(pfn)); |
7b78d335a memory hotplug: r... |
891 892 |
arg.start_pfn = pfn; arg.nr_pages = nr_pages; |
d9713679d memory_hotplug: f... |
893 |
node_states_check_changes_online(nr_pages, zone, &arg); |
7b78d335a memory hotplug: r... |
894 |
|
9c2606b77 mm/memory_hotplug... |
895 |
nid = pfn_to_nid(pfn); |
3947be196 [PATCH] memory ho... |
896 |
|
7b78d335a memory hotplug: r... |
897 898 899 900 |
ret = memory_notify(MEM_GOING_ONLINE, &arg); ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); |
925268a06 memory hotplug: o... |
901 |
unlock_memory_hotplug(); |
7b78d335a memory hotplug: r... |
902 903 |
return ret; } |
3947be196 [PATCH] memory ho... |
904 |
/* |
6811378e7 [PATCH] wait_tabl... |
905 906 907 908 |
* If this zone is not populated, then it is not in zonelist. * This means the page allocator ignores this zone. * So, zonelist must be updated after online. */ |
4eaf3f643 mem-hotplug: fix ... |
909 |
mutex_lock(&zonelists_mutex); |
6dcd73d70 memory-hotplug: a... |
910 |
if (!populated_zone(zone)) { |
6811378e7 [PATCH] wait_tabl... |
911 |
need_zonelists_rebuild = 1; |
6dcd73d70 memory-hotplug: a... |
912 913 |
build_all_zonelists(NULL, zone); } |
6811378e7 [PATCH] wait_tabl... |
914 |
|
908eedc61 walk system ram r... |
915 |
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages, |
75884fb1c memory unplug: me... |
916 |
online_pages_range); |
fd8a4221a memory_hotplug: c... |
917 |
if (ret) { |
6dcd73d70 memory-hotplug: a... |
918 919 |
if (need_zonelists_rebuild) zone_pcp_reset(zone); |
4eaf3f643 mem-hotplug: fix ... |
920 |
mutex_unlock(&zonelists_mutex); |
a62e2f4f5 mm: print physica... |
921 922 923 924 925 |
printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed ", (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); |
fd8a4221a memory_hotplug: c... |
926 |
memory_notify(MEM_CANCEL_ONLINE, &arg); |
925268a06 memory hotplug: o... |
927 |
unlock_memory_hotplug(); |
fd8a4221a memory_hotplug: c... |
928 929 |
return ret; } |
3947be196 [PATCH] memory ho... |
930 |
zone->present_pages += onlined_pages; |
aa47228a1 memory_hotplug: u... |
931 932 |
pgdat_resize_lock(zone->zone_pgdat, &flags); |
f2937be58 [PATCH] memory ho... |
933 |
zone->zone_pgdat->node_present_pages += onlined_pages; |
aa47228a1 memory_hotplug: u... |
934 |
pgdat_resize_unlock(zone->zone_pgdat, &flags); |
08dff7b7d mm/hotplug: corre... |
935 |
if (onlined_pages) { |
d9713679d memory_hotplug: f... |
936 |
node_states_set_node(zone_to_nid(zone), &arg); |
08dff7b7d mm/hotplug: corre... |
937 |
if (need_zonelists_rebuild) |
6dcd73d70 memory-hotplug: a... |
938 |
build_all_zonelists(NULL, NULL); |
08dff7b7d mm/hotplug: corre... |
939 940 941 |
else zone_pcp_update(zone); } |
3947be196 [PATCH] memory ho... |
942 |
|
4eaf3f643 mem-hotplug: fix ... |
943 |
mutex_unlock(&zonelists_mutex); |
1b79acc91 mm, mem-hotplug: ... |
944 945 |
init_per_zone_wmark_min(); |
08dff7b7d mm/hotplug: corre... |
946 |
if (onlined_pages) |
7ea1530ab Memoryless nodes:... |
947 |
kswapd_run(zone_to_nid(zone)); |
61b13993a [PATCH] memory ho... |
948 |
|
1f522509c mem-hotplug: avoi... |
949 |
vm_total_pages = nr_free_pagecache_pages(); |
2f7f24eca memory-hotplug: d... |
950 |
|
2d1d43f6a [PATCH] call mm/p... |
951 |
writeback_set_ratelimit(); |
7b78d335a memory hotplug: r... |
952 953 954 |
if (onlined_pages) memory_notify(MEM_ONLINE, &arg); |
925268a06 memory hotplug: o... |
955 |
unlock_memory_hotplug(); |
7b78d335a memory hotplug: r... |
956 |
|
3947be196 [PATCH] memory ho... |
957 958 |
return 0; } |
53947027a [PATCH] hot-add-m... |
959 |
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ |
bc02af93d [PATCH] pgdat all... |
960 |
|
e13193319 mm/memory_hotplug... |
961 962 |
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) |
9af3c2dea [PATCH] pgdat all... |
963 964 965 966 967 |
{ struct pglist_data *pgdat; unsigned long zones_size[MAX_NR_ZONES] = {0}; unsigned long zholes_size[MAX_NR_ZONES] = {0}; unsigned long start_pfn = start >> PAGE_SHIFT; |
a1e565aa3 memory-hotplug: d... |
968 969 970 971 972 |
pgdat = NODE_DATA(nid); if (!pgdat) { pgdat = arch_alloc_nodedata(nid); if (!pgdat) return NULL; |
9af3c2dea [PATCH] pgdat all... |
973 |
|
a1e565aa3 memory-hotplug: d... |
974 975 |
arch_refresh_nodedata(nid, pgdat); } |
9af3c2dea [PATCH] pgdat all... |
976 977 978 979 |
/* we can use NODE_DATA(nid) from here */ /* init node's zones as empty zones, we don't have any present pages.*/ |
9109fb7b3 mm: drop unneeded... |
980 |
free_area_init_node(nid, zones_size, start_pfn, zholes_size); |
9af3c2dea [PATCH] pgdat all... |
981 |
|
959ecc48f mm/memory_hotplug... |
982 983 984 985 |
/* * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ |
f957db4fc mm, hotplug: prot... |
986 |
mutex_lock(&zonelists_mutex); |
9adb62a5d mm/hotplug: corre... |
987 |
build_all_zonelists(pgdat, NULL); |
f957db4fc mm, hotplug: prot... |
988 |
mutex_unlock(&zonelists_mutex); |
959ecc48f mm/memory_hotplug... |
989 |
|
9af3c2dea [PATCH] pgdat all... |
990 991 992 993 994 995 996 997 998 |
return pgdat; } static void rollback_node_hotadd(int nid, pg_data_t *pgdat) { arch_refresh_nodedata(nid, NULL); arch_free_nodedata(pgdat); return; } |
0a5470390 [PATCH] register ... |
999 |
|
01b0f1970 cpu/mem hotplug: ... |
1000 1001 1002 |
/** * try_online_node - online a node if offlined * |
cf23422b9 cpu/mem hotplug: ... |
1003 1004 |
* called by cpu_up() to online a node without onlined memory. */ |
01b0f1970 cpu/mem hotplug: ... |
1005 |
int try_online_node(int nid) |
cf23422b9 cpu/mem hotplug: ... |
1006 1007 1008 |
{ pg_data_t *pgdat; int ret; |
01b0f1970 cpu/mem hotplug: ... |
1009 1010 |
if (node_online(nid)) return 0; |
20d6c96b5 mem-hotplug: intr... |
1011 |
lock_memory_hotplug(); |
cf23422b9 cpu/mem hotplug: ... |
1012 |
pgdat = hotadd_new_pgdat(nid, 0); |
7553e8f2d mm, hotplug: fix ... |
1013 |
if (!pgdat) { |
01b0f1970 cpu/mem hotplug: ... |
1014 1015 |
pr_err("Cannot online node %d due to NULL pgdat ", nid); |
cf23422b9 cpu/mem hotplug: ... |
1016 1017 1018 1019 1020 1021 |
ret = -ENOMEM; goto out; } node_set_online(nid); ret = register_one_node(nid); BUG_ON(ret); |
01b0f1970 cpu/mem hotplug: ... |
1022 1023 1024 1025 1026 |
if (pgdat->node_zonelists->_zonerefs->zone == NULL) { mutex_lock(&zonelists_mutex); build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } |
cf23422b9 cpu/mem hotplug: ... |
1027 |
out: |
20d6c96b5 mem-hotplug: intr... |
1028 |
unlock_memory_hotplug(); |
cf23422b9 cpu/mem hotplug: ... |
1029 1030 |
return ret; } |
27356f54c mm/hotplug: verif... |
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 |
static int check_hotplug_memory_range(u64 start, u64 size) { u64 start_pfn = start >> PAGE_SHIFT; u64 nr_pages = size >> PAGE_SHIFT; /* Memory range must be aligned with section */ if ((start_pfn & ~PAGE_SECTION_MASK) || (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) { pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx ", (unsigned long long)start, (unsigned long long)size); return -EINVAL; } return 0; } |
31168481c meminit section w... |
1048 1049 |
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ int __ref add_memory(int nid, u64 start, u64 size) |
bc02af93d [PATCH] pgdat all... |
1050 |
{ |
9af3c2dea [PATCH] pgdat all... |
1051 |
pg_data_t *pgdat = NULL; |
a1e565aa3 memory-hotplug: d... |
1052 1053 |
bool new_pgdat; bool new_node; |
ebd15302d [PATCH] memory ho... |
1054 |
struct resource *res; |
bc02af93d [PATCH] pgdat all... |
1055 |
int ret; |
27356f54c mm/hotplug: verif... |
1056 1057 1058 |
ret = check_hotplug_memory_range(start, size); if (ret) return ret; |
ebd15302d [PATCH] memory ho... |
1059 |
res = register_memory_resource(start, size); |
6ad696d2c mm: allow memory ... |
1060 |
ret = -EEXIST; |
ebd15302d [PATCH] memory ho... |
1061 |
if (!res) |
ac13c4622 mm/memory_hotplug... |
1062 |
return ret; |
ebd15302d [PATCH] memory ho... |
1063 |
|
a1e565aa3 memory-hotplug: d... |
1064 1065 1066 1067 |
{ /* Stupid hack to suppress address-never-null warning */ void *p = NODE_DATA(nid); new_pgdat = !p; } |
ac13c4622 mm/memory_hotplug... |
1068 1069 |
lock_memory_hotplug(); |
a1e565aa3 memory-hotplug: d... |
1070 1071 |
new_node = !node_online(nid); if (new_node) { |
9af3c2dea [PATCH] pgdat all... |
1072 |
pgdat = hotadd_new_pgdat(nid, start); |
6ad696d2c mm: allow memory ... |
1073 |
ret = -ENOMEM; |
9af3c2dea [PATCH] pgdat all... |
1074 |
if (!pgdat) |
41b9e2d7e mm/memory_hotplug... |
1075 |
goto error; |
9af3c2dea [PATCH] pgdat all... |
1076 |
} |
bc02af93d [PATCH] pgdat all... |
1077 1078 |
/* call arch's memory hotadd */ ret = arch_add_memory(nid, start, size); |
9af3c2dea [PATCH] pgdat all... |
1079 1080 |
if (ret < 0) goto error; |
0fc44159b [PATCH] Register ... |
1081 |
/* we online node here. we can't roll back from here. */ |
9af3c2dea [PATCH] pgdat all... |
1082 |
node_set_online(nid); |
a1e565aa3 memory-hotplug: d... |
1083 |
if (new_node) { |
0fc44159b [PATCH] Register ... |
1084 1085 1086 1087 1088 1089 1090 1091 |
ret = register_one_node(nid); /* * If sysfs file of new node can't create, cpu on the node * can't be hot-added. There is no rollback way now. * So, check by BUG_ON() to catch it reluctantly.. */ BUG_ON(ret); } |
d96ae5309 memory-hotplug: c... |
1092 1093 |
/* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); |
6ad696d2c mm: allow memory ... |
1094 |
goto out; |
9af3c2dea [PATCH] pgdat all... |
1095 1096 1097 1098 |
error: /* rollback pgdat allocation and others */ if (new_pgdat) rollback_node_hotadd(nid, pgdat); |
a864b9d06 mm: memory_hotplu... |
1099 |
release_memory_resource(res); |
9af3c2dea [PATCH] pgdat all... |
1100 |
|
6ad696d2c mm: allow memory ... |
1101 |
out: |
20d6c96b5 mem-hotplug: intr... |
1102 |
unlock_memory_hotplug(); |
bc02af93d [PATCH] pgdat all... |
1103 1104 1105 |
return ret; } EXPORT_SYMBOL_GPL(add_memory); |
0c0e61958 memory unplug: pa... |
1106 1107 1108 |
#ifdef CONFIG_MEMORY_HOTREMOVE /* |
5c755e9fd memory-hotplug: a... |
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 |
* A free page on the buddy free lists (not the per-cpu lists) has PageBuddy * set and the size of the free page is given by page_order(). Using this, * the function determines if the pageblock contains only free pages. * Due to buddy contraints, a free page at least the size of a pageblock will * be located at the start of the pageblock */ static inline int pageblock_free(struct page *page) { return PageBuddy(page) && page_order(page) >= pageblock_order; } /* Return the start of the next active pageblock after a given page */ static struct page *next_active_pageblock(struct page *page) { |
5c755e9fd memory-hotplug: a... |
1123 1124 |
/* Ensure the starting page is pageblock-aligned */ BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1)); |
5c755e9fd memory-hotplug: a... |
1125 |
/* If the entire pageblock is free, move to the end of free page */ |
0dcc48c15 memory hotplug: f... |
1126 1127 1128 1129 1130 1131 1132 |
if (pageblock_free(page)) { int order; /* be careful. we don't have locks, page_order can be changed.*/ order = page_order(page); if ((order < MAX_ORDER) && (order >= pageblock_order)) return page + (1 << order); } |
5c755e9fd memory-hotplug: a... |
1133 |
|
0dcc48c15 memory hotplug: f... |
1134 |
return page + pageblock_nr_pages; |
5c755e9fd memory-hotplug: a... |
1135 1136 1137 1138 1139 |
} /* Checks if this range of memory is likely to be hot-removable. */ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { |
5c755e9fd memory-hotplug: a... |
1140 1141 1142 1143 1144 |
struct page *page = pfn_to_page(start_pfn); struct page *end_page = page + nr_pages; /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { |
49ac82558 memory hotplug: u... |
1145 |
if (!is_pageblock_removable_nolock(page)) |
5c755e9fd memory-hotplug: a... |
1146 |
return 0; |
49ac82558 memory hotplug: u... |
1147 |
cond_resched(); |
5c755e9fd memory-hotplug: a... |
1148 1149 1150 1151 1152 1153 1154 |
} /* All pageblocks in the memory block are likely to be hot-removable */ return 1; } /* |
0c0e61958 memory unplug: pa... |
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 |
* Confirm all pages in a range [start, end) is belongs to the same zone. */ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct zone *zone = NULL; struct page *page; int i; for (pfn = start_pfn; pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) { i = 0; /* This is just a CONFIG_HOLES_IN_ZONE check.*/ while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i)) i++; if (i == MAX_ORDER_NR_PAGES) continue; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; zone = page_zone(page); } return 1; } /* |
c8721bbbd mm: memory-hotplu... |
1181 1182 1183 1184 |
* Scan pfn range [start,end) to find movable/migratable pages (LRU pages * and hugepages). We scan pfn because it's much easier than scanning over * linked list. This function returns the pfn of the first found movable * page if it's found, otherwise 0. |
0c0e61958 memory unplug: pa... |
1185 |
*/ |
c8721bbbd mm: memory-hotplu... |
1186 |
static unsigned long scan_movable_pages(unsigned long start, unsigned long end) |
0c0e61958 memory unplug: pa... |
1187 1188 1189 1190 1191 1192 1193 1194 |
{ unsigned long pfn; struct page *page; for (pfn = start; pfn < end; pfn++) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); if (PageLRU(page)) return pfn; |
c8721bbbd mm: memory-hotplu... |
1195 1196 1197 1198 1199 1200 1201 |
if (PageHuge(page)) { if (is_hugepage_active(page)) return pfn; else pfn = round_up(pfn + 1, 1 << compound_order(page)) - 1; } |
0c0e61958 memory unplug: pa... |
1202 1203 1204 1205 |
} } return 0; } |
0c0e61958 memory unplug: pa... |
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 |
#define NR_OFFLINE_AT_ONCE_PAGES (256) static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; int move_pages = NR_OFFLINE_AT_ONCE_PAGES; int not_managed = 0; int ret = 0; LIST_HEAD(source); for (pfn = start_pfn; pfn < end_pfn && move_pages > 0; pfn++) { if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); |
c8721bbbd mm: memory-hotplu... |
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 |
if (PageHuge(page)) { struct page *head = compound_head(page); pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1; if (compound_order(head) > PFN_SECTION_SHIFT) { ret = -EBUSY; break; } if (isolate_huge_page(page, &source)) move_pages -= 1 << compound_order(head); continue; } |
700c2a46e mem-hotplug: call... |
1233 |
if (!get_page_unless_zero(page)) |
0c0e61958 memory unplug: pa... |
1234 1235 1236 1237 1238 |
continue; /* * We can skip free pages. And we can only deal with pages on * LRU. */ |
62695a84e vmscan: move isol... |
1239 |
ret = isolate_lru_page(page); |
0c0e61958 memory unplug: pa... |
1240 |
if (!ret) { /* Success */ |
700c2a46e mem-hotplug: call... |
1241 |
put_page(page); |
62695a84e vmscan: move isol... |
1242 |
list_add_tail(&page->lru, &source); |
0c0e61958 memory unplug: pa... |
1243 |
move_pages--; |
6d9c285a6 mm: move inc_zone... |
1244 1245 |
inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); |
0c0e61958 memory unplug: pa... |
1246 |
} else { |
0c0e61958 memory unplug: pa... |
1247 |
#ifdef CONFIG_DEBUG_VM |
718a38211 mm: introduce dum... |
1248 1249 1250 |
printk(KERN_ALERT "removing pfn %lx from LRU failed ", pfn); |
f0b791a34 mm: print more de... |
1251 |
dump_page(page, "failed to remove from LRU"); |
0c0e61958 memory unplug: pa... |
1252 |
#endif |
700c2a46e mem-hotplug: call... |
1253 |
put_page(page); |
25985edce Fix common misspe... |
1254 |
/* Because we don't have big zone->lock. we should |
809c44497 mm: do_migrate_ra... |
1255 1256 1257 |
check this again here. */ if (page_count(page)) { not_managed++; |
f3ab2636c mm: do_migrate_ra... |
1258 |
ret = -EBUSY; |
809c44497 mm: do_migrate_ra... |
1259 1260 |
break; } |
0c0e61958 memory unplug: pa... |
1261 1262 |
} } |
f3ab2636c mm: do_migrate_ra... |
1263 1264 |
if (!list_empty(&source)) { if (not_managed) { |
c8721bbbd mm: memory-hotplu... |
1265 |
putback_movable_pages(&source); |
f3ab2636c mm: do_migrate_ra... |
1266 1267 |
goto out; } |
74c08f982 memory-hotplug: d... |
1268 1269 1270 1271 1272 1273 |
/* * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ ret = migrate_pages(&source, alloc_migrate_target, 0, |
9c620e2bc mm: remove offlin... |
1274 |
MIGRATE_SYNC, MR_MEMORY_HOTPLUG); |
f3ab2636c mm: do_migrate_ra... |
1275 |
if (ret) |
c8721bbbd mm: memory-hotplu... |
1276 |
putback_movable_pages(&source); |
0c0e61958 memory unplug: pa... |
1277 |
} |
0c0e61958 memory unplug: pa... |
1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 |
out: return ret; } /* * remove from free_area[] and mark all as Reserved. */ static int offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages, void *data) { __offline_isolated_pages(start, start + nr_pages); return 0; } static void offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { |
908eedc61 walk system ram r... |
1296 |
walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL, |
0c0e61958 memory unplug: pa... |
1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 |
offline_isolated_pages_cb); } /* * Check all pages in range, recoreded as memory resource, are isolated. */ static int check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages, void *data) { int ret; long offlined = *(long *)data; |
b023f4681 memory-hotplug: s... |
1309 |
ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true); |
0c0e61958 memory unplug: pa... |
1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 |
offlined = nr_pages; if (!ret) *(long *)data += offlined; return ret; } static long check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn) { long offlined = 0; int ret; |
908eedc61 walk system ram r... |
1321 |
ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined, |
0c0e61958 memory unplug: pa... |
1322 1323 1324 1325 1326 |
check_pages_isolated_cb); if (ret < 0) offlined = (long)ret; return offlined; } |
09285af75 memory_hotplug: a... |
1327 |
#ifdef CONFIG_MOVABLE_NODE |
79a4dcefd mm/memory_hotplug... |
1328 1329 1330 1331 |
/* * When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have * normal memory. */ |
09285af75 memory_hotplug: a... |
1332 1333 1334 1335 |
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages) { return true; } |
79a4dcefd mm/memory_hotplug... |
1336 |
#else /* CONFIG_MOVABLE_NODE */ |
74d42d8fe memory_hotplug: e... |
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 |
/* ensure the node has NORMAL memory if it is still online */ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long present_pages = 0; enum zone_type zt; for (zt = 0; zt <= ZONE_NORMAL; zt++) present_pages += pgdat->node_zones[zt].present_pages; if (present_pages > nr_pages) return true; present_pages = 0; for (; zt <= ZONE_MOVABLE; zt++) present_pages += pgdat->node_zones[zt].present_pages; /* * we can't offline the last normal memory until all * higher memory is offlined. */ return present_pages == 0; } |
79a4dcefd mm/memory_hotplug... |
1360 |
#endif /* CONFIG_MOVABLE_NODE */ |
74d42d8fe memory_hotplug: e... |
1361 |
|
c5320926e mem-hotplug: intr... |
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 |
static int __init cmdline_parse_movable_node(char *p) { #ifdef CONFIG_MOVABLE_NODE /* * Memory used by the kernel cannot be hot-removed because Linux * cannot migrate the kernel pages. When memory hotplug is * enabled, we should prevent memblock from allocating memory * for the kernel. * * ACPI SRAT records all hotpluggable memory ranges. But before * SRAT is parsed, we don't know about it. * * The kernel image is loaded into memory at very early time. We * cannot prevent this anyway. So on NUMA system, we set any * node the kernel resides in as un-hotpluggable. * * Since on modern servers, one node could have double-digit * gigabytes memory, we can assume the memory around the kernel * image is also un-hotpluggable. So before SRAT is parsed, just * allocate memory near the kernel image to try the best to keep * the kernel away from hotpluggable memory. */ memblock_set_bottom_up(true); |
55ac590c2 memblock, mem_hot... |
1385 |
movable_node_enabled = true; |
c5320926e mem-hotplug: intr... |
1386 1387 1388 1389 1390 1391 1392 |
#else pr_warn("movable_node option not supported "); #endif return 0; } early_param("movable_node", cmdline_parse_movable_node); |
d9713679d memory_hotplug: f... |
1393 1394 1395 1396 1397 1398 1399 1400 1401 |
/* check which state of node_states will be changed when offline memory */ static void node_states_check_changes_offline(unsigned long nr_pages, struct zone *zone, struct memory_notify *arg) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long present_pages = 0; enum zone_type zt, zone_last = ZONE_NORMAL; /* |
6715ddf94 hotplug: update n... |
1402 1403 1404 |
* If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY] * contains nodes which have zones of 0...ZONE_NORMAL, * set zone_last to ZONE_NORMAL. |
d9713679d memory_hotplug: f... |
1405 |
* |
6715ddf94 hotplug: update n... |
1406 1407 1408 |
* If we don't have HIGHMEM nor movable node, * node_states[N_NORMAL_MEMORY] contains nodes which have zones of * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE. |
d9713679d memory_hotplug: f... |
1409 |
*/ |
6715ddf94 hotplug: update n... |
1410 |
if (N_MEMORY == N_NORMAL_MEMORY) |
d9713679d memory_hotplug: f... |
1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 |
zone_last = ZONE_MOVABLE; /* * check whether node_states[N_NORMAL_MEMORY] will be changed. * If the memory to be offline is in a zone of 0...zone_last, * and it is the last present memory, 0...zone_last will * become empty after offline , thus we can determind we will * need to clear the node from node_states[N_NORMAL_MEMORY]. */ for (zt = 0; zt <= zone_last; zt++) present_pages += pgdat->node_zones[zt].present_pages; if (zone_idx(zone) <= zone_last && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); else arg->status_change_nid_normal = -1; |
6715ddf94 hotplug: update n... |
1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 |
#ifdef CONFIG_HIGHMEM /* * If we have movable node, node_states[N_HIGH_MEMORY] * contains nodes which have zones of 0...ZONE_HIGHMEM, * set zone_last to ZONE_HIGHMEM. * * If we don't have movable node, node_states[N_NORMAL_MEMORY] * contains nodes which have zones of 0...ZONE_MOVABLE, * set zone_last to ZONE_MOVABLE. */ zone_last = ZONE_HIGHMEM; if (N_MEMORY == N_HIGH_MEMORY) zone_last = ZONE_MOVABLE; for (; zt <= zone_last; zt++) present_pages += pgdat->node_zones[zt].present_pages; if (zone_idx(zone) <= zone_last && nr_pages >= present_pages) arg->status_change_nid_high = zone_to_nid(zone); else arg->status_change_nid_high = -1; #else arg->status_change_nid_high = arg->status_change_nid_normal; #endif |
d9713679d memory_hotplug: f... |
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 |
/* * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE */ zone_last = ZONE_MOVABLE; /* * check whether node_states[N_HIGH_MEMORY] will be changed * If we try to offline the last present @nr_pages from the node, * we can determind we will need to clear the node from * node_states[N_HIGH_MEMORY]. */ for (; zt <= zone_last; zt++) present_pages += pgdat->node_zones[zt].present_pages; if (nr_pages >= present_pages) arg->status_change_nid = zone_to_nid(zone); else arg->status_change_nid = -1; } static void node_states_clear_node(int node, struct memory_notify *arg) { if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); |
6715ddf94 hotplug: update n... |
1472 1473 |
if ((N_MEMORY != N_NORMAL_MEMORY) && (arg->status_change_nid_high >= 0)) |
d9713679d memory_hotplug: f... |
1474 |
node_clear_state(node, N_HIGH_MEMORY); |
6715ddf94 hotplug: update n... |
1475 1476 1477 1478 |
if ((N_MEMORY != N_HIGH_MEMORY) && (arg->status_change_nid >= 0)) node_clear_state(node, N_MEMORY); |
d9713679d memory_hotplug: f... |
1479 |
} |
a16cee10c memory-hotplug: p... |
1480 |
static int __ref __offline_pages(unsigned long start_pfn, |
0c0e61958 memory unplug: pa... |
1481 1482 1483 1484 |
unsigned long end_pfn, unsigned long timeout) { unsigned long pfn, nr_pages, expire; long offlined_pages; |
7b78d335a memory hotplug: r... |
1485 |
int ret, drain, retry_max, node; |
d702909f0 memory_hotplug: u... |
1486 |
unsigned long flags; |
0c0e61958 memory unplug: pa... |
1487 |
struct zone *zone; |
7b78d335a memory hotplug: r... |
1488 |
struct memory_notify arg; |
0c0e61958 memory unplug: pa... |
1489 |
|
0c0e61958 memory unplug: pa... |
1490 1491 1492 1493 1494 1495 1496 1497 1498 |
/* at least, alignment against pageblock is necessary */ if (!IS_ALIGNED(start_pfn, pageblock_nr_pages)) return -EINVAL; if (!IS_ALIGNED(end_pfn, pageblock_nr_pages)) return -EINVAL; /* This makes hotplug much easier...and readable. we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; |
7b78d335a memory hotplug: r... |
1499 |
|
20d6c96b5 mem-hotplug: intr... |
1500 |
lock_memory_hotplug(); |
6ad696d2c mm: allow memory ... |
1501 |
|
7b78d335a memory hotplug: r... |
1502 1503 1504 |
zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; |
74d42d8fe memory_hotplug: e... |
1505 1506 1507 |
ret = -EINVAL; if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages)) goto out; |
0c0e61958 memory unplug: pa... |
1508 |
/* set above range as isolated */ |
b023f4681 memory-hotplug: s... |
1509 1510 |
ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, true); |
0c0e61958 memory unplug: pa... |
1511 |
if (ret) |
6ad696d2c mm: allow memory ... |
1512 |
goto out; |
7b78d335a memory hotplug: r... |
1513 1514 1515 |
arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; |
d9713679d memory_hotplug: f... |
1516 |
node_states_check_changes_offline(nr_pages, zone, &arg); |
7b78d335a memory hotplug: r... |
1517 1518 1519 1520 1521 |
ret = memory_notify(MEM_GOING_OFFLINE, &arg); ret = notifier_to_errno(ret); if (ret) goto failed_removal; |
0c0e61958 memory unplug: pa... |
1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 |
pfn = start_pfn; expire = jiffies + timeout; drain = 0; retry_max = 5; repeat: /* start memory hot removal */ ret = -EAGAIN; if (time_after(jiffies, expire)) goto failed_removal; ret = -EINTR; if (signal_pending(current)) goto failed_removal; ret = 0; if (drain) { lru_add_drain_all(); |
0c0e61958 memory unplug: pa... |
1537 |
cond_resched(); |
9f8f21725 Page allocator: c... |
1538 |
drain_all_pages(); |
0c0e61958 memory unplug: pa... |
1539 |
} |
c8721bbbd mm: memory-hotplu... |
1540 1541 |
pfn = scan_movable_pages(start_pfn, end_pfn); if (pfn) { /* We have movable pages */ |
0c0e61958 memory unplug: pa... |
1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 |
ret = do_migrate_range(pfn, end_pfn); if (!ret) { drain = 1; goto repeat; } else { if (ret < 0) if (--retry_max == 0) goto failed_removal; yield(); drain = 1; goto repeat; } } |
b3834be5c various: Fix spel... |
1555 |
/* drain all zone's lru pagevec, this is asynchronous... */ |
0c0e61958 memory unplug: pa... |
1556 |
lru_add_drain_all(); |
0c0e61958 memory unplug: pa... |
1557 |
yield(); |
b3834be5c various: Fix spel... |
1558 |
/* drain pcp pages, this is synchronous. */ |
9f8f21725 Page allocator: c... |
1559 |
drain_all_pages(); |
c8721bbbd mm: memory-hotplu... |
1560 1561 1562 1563 1564 |
/* * dissolve free hugepages in the memory block before doing offlining * actually in order to make hugetlbfs's object counting consistent. */ dissolve_free_huge_pages(start_pfn, end_pfn); |
0c0e61958 memory unplug: pa... |
1565 1566 1567 1568 1569 1570 1571 1572 |
/* check again */ offlined_pages = check_pages_isolated(start_pfn, end_pfn); if (offlined_pages < 0) { ret = -EBUSY; goto failed_removal; } printk(KERN_INFO "Offlined Pages %ld ", offlined_pages); |
b3834be5c various: Fix spel... |
1573 |
/* Ok, all of our target is isolated. |
0c0e61958 memory unplug: pa... |
1574 1575 |
We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); |
dbc0e4cef memory hotremove:... |
1576 |
/* reset pagetype flags and makes migrate type to be MOVABLE */ |
0815f3d81 mm: page_isolatio... |
1577 |
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); |
0c0e61958 memory unplug: pa... |
1578 |
/* removal success */ |
3dcc0571c mm: correctly upd... |
1579 |
adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages); |
0c0e61958 memory unplug: pa... |
1580 |
zone->present_pages -= offlined_pages; |
d702909f0 memory_hotplug: u... |
1581 1582 |
pgdat_resize_lock(zone->zone_pgdat, &flags); |
0c0e61958 memory unplug: pa... |
1583 |
zone->zone_pgdat->node_present_pages -= offlined_pages; |
d702909f0 memory_hotplug: u... |
1584 |
pgdat_resize_unlock(zone->zone_pgdat, &flags); |
7b78d335a memory hotplug: r... |
1585 |
|
1b79acc91 mm, mem-hotplug: ... |
1586 |
init_per_zone_wmark_min(); |
1e8537baa memory-hotplug: b... |
1587 |
if (!populated_zone(zone)) { |
340175b7d mm/hotplug: free ... |
1588 |
zone_pcp_reset(zone); |
1e8537baa memory-hotplug: b... |
1589 1590 1591 1592 1593 |
mutex_lock(&zonelists_mutex); build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } else zone_pcp_update(zone); |
340175b7d mm/hotplug: free ... |
1594 |
|
d9713679d memory_hotplug: f... |
1595 1596 |
node_states_clear_node(node, &arg); if (arg.status_change_nid >= 0) |
8fe23e057 mm: clear node in... |
1597 |
kswapd_stop(node); |
bce7394a3 page-allocator: r... |
1598 |
|
0c0e61958 memory unplug: pa... |
1599 1600 |
vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); |
7b78d335a memory hotplug: r... |
1601 1602 |
memory_notify(MEM_OFFLINE, &arg); |
20d6c96b5 mem-hotplug: intr... |
1603 |
unlock_memory_hotplug(); |
0c0e61958 memory unplug: pa... |
1604 1605 1606 |
return 0; failed_removal: |
a62e2f4f5 mm: print physica... |
1607 1608 1609 1610 |
printk(KERN_INFO "memory offlining [mem %#010llx-%#010llx] failed ", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1); |
7b78d335a memory hotplug: r... |
1611 |
memory_notify(MEM_CANCEL_OFFLINE, &arg); |
0c0e61958 memory unplug: pa... |
1612 |
/* pushback to free area */ |
0815f3d81 mm: page_isolatio... |
1613 |
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); |
7b78d335a memory hotplug: r... |
1614 |
|
6ad696d2c mm: allow memory ... |
1615 |
out: |
20d6c96b5 mem-hotplug: intr... |
1616 |
unlock_memory_hotplug(); |
0c0e61958 memory unplug: pa... |
1617 1618 |
return ret; } |
71088785c mm: cleanup to ma... |
1619 |
|
a16cee10c memory-hotplug: p... |
1620 1621 1622 1623 |
int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); } |
e2ff39400 ACPI / memhotplug... |
1624 |
#endif /* CONFIG_MEMORY_HOTREMOVE */ |
a16cee10c memory-hotplug: p... |
1625 |
|
bbc76be67 memory-hotplug: r... |
1626 1627 1628 |
/** * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) * @start_pfn: start pfn of the memory range |
e05c4bbfa mm: walk_memory_r... |
1629 |
* @end_pfn: end pfn of the memory range |
bbc76be67 memory-hotplug: r... |
1630 1631 1632 1633 1634 1635 1636 1637 |
* @arg: argument passed to func * @func: callback for each memory section walked * * This function walks through all present mem sections in range * [start_pfn, end_pfn) and call func on each mem section. * * Returns the return value of func. */ |
e2ff39400 ACPI / memhotplug... |
1638 |
int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, |
bbc76be67 memory-hotplug: r... |
1639 |
void *arg, int (*func)(struct memory_block *, void *)) |
71088785c mm: cleanup to ma... |
1640 |
{ |
e90bdb7f5 memory-hotplug: u... |
1641 1642 |
struct memory_block *mem = NULL; struct mem_section *section; |
e90bdb7f5 memory-hotplug: u... |
1643 1644 |
unsigned long pfn, section_nr; int ret; |
e90bdb7f5 memory-hotplug: u... |
1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 |
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { section_nr = pfn_to_section_nr(pfn); if (!present_section_nr(section_nr)) continue; section = __nr_to_section(section_nr); /* same memblock? */ if (mem) if ((section_nr >= mem->start_section_nr) && (section_nr <= mem->end_section_nr)) continue; mem = find_memory_block_hinted(section, mem); if (!mem) continue; |
bbc76be67 memory-hotplug: r... |
1661 |
ret = func(mem, arg); |
e90bdb7f5 memory-hotplug: u... |
1662 |
if (ret) { |
bbc76be67 memory-hotplug: r... |
1663 1664 |
kobject_put(&mem->dev.kobj); return ret; |
e90bdb7f5 memory-hotplug: u... |
1665 1666 1667 1668 1669 |
} } if (mem) kobject_put(&mem->dev.kobj); |
bbc76be67 memory-hotplug: r... |
1670 1671 |
return 0; } |
e2ff39400 ACPI / memhotplug... |
1672 |
#ifdef CONFIG_MEMORY_HOTREMOVE |
d6de9d534 mm/memory_hotplug... |
1673 |
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) |
bbc76be67 memory-hotplug: r... |
1674 1675 |
{ int ret = !is_memblock_offlined(mem); |
349daa0f9 mm: fix memory_ho... |
1676 1677 1678 1679 1680 |
if (unlikely(ret)) { phys_addr_t beginpa, endpa; beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1; |
bbc76be67 memory-hotplug: r... |
1681 |
pr_warn("removing memory fails, because memory " |
349daa0f9 mm: fix memory_ho... |
1682 1683 1684 1685 |
"[%pa-%pa] is onlined ", &beginpa, &endpa); } |
bbc76be67 memory-hotplug: r... |
1686 1687 1688 |
return ret; } |
0f1cfe9d0 mm/hotplug: remov... |
1689 |
static int check_cpu_on_node(pg_data_t *pgdat) |
60a5a19e7 memory-hotplug: r... |
1690 |
{ |
60a5a19e7 memory-hotplug: r... |
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 |
int cpu; for_each_present_cpu(cpu) { if (cpu_to_node(cpu) == pgdat->node_id) /* * the cpu on this node isn't removed, and we can't * offline this node. */ return -EBUSY; } return 0; } |
0f1cfe9d0 mm/hotplug: remov... |
1704 |
static void unmap_cpu_on_node(pg_data_t *pgdat) |
e13fe8695 cpu-hotplug,memor... |
1705 1706 |
{ #ifdef CONFIG_ACPI_NUMA |
e13fe8695 cpu-hotplug,memor... |
1707 1708 1709 1710 1711 1712 1713 |
int cpu; for_each_possible_cpu(cpu) if (cpu_to_node(cpu) == pgdat->node_id) numa_clear_node(cpu); #endif } |
0f1cfe9d0 mm/hotplug: remov... |
1714 |
static int check_and_unmap_cpu_on_node(pg_data_t *pgdat) |
e13fe8695 cpu-hotplug,memor... |
1715 |
{ |
0f1cfe9d0 mm/hotplug: remov... |
1716 |
int ret; |
e13fe8695 cpu-hotplug,memor... |
1717 |
|
0f1cfe9d0 mm/hotplug: remov... |
1718 |
ret = check_cpu_on_node(pgdat); |
e13fe8695 cpu-hotplug,memor... |
1719 1720 1721 1722 1723 1724 1725 |
if (ret) return ret; /* * the node will be offlined when we come here, so we can clear * the cpu_to_node() now. */ |
0f1cfe9d0 mm/hotplug: remov... |
1726 |
unmap_cpu_on_node(pgdat); |
e13fe8695 cpu-hotplug,memor... |
1727 1728 |
return 0; } |
0f1cfe9d0 mm/hotplug: remov... |
1729 1730 1731 1732 1733 1734 1735 1736 |
/** * try_offline_node * * Offline a node if all memory sections and cpus of the node are removed. * * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call. */ |
90b30cdc1 memory-hotplug: e... |
1737 |
void try_offline_node(int nid) |
60a5a19e7 memory-hotplug: r... |
1738 |
{ |
d822b86a9 memory-hotplug: f... |
1739 1740 1741 |
pg_data_t *pgdat = NODE_DATA(nid); unsigned long start_pfn = pgdat->node_start_pfn; unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; |
60a5a19e7 memory-hotplug: r... |
1742 |
unsigned long pfn; |
d822b86a9 memory-hotplug: f... |
1743 1744 |
struct page *pgdat_page = virt_to_page(pgdat); int i; |
60a5a19e7 memory-hotplug: r... |
1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 |
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { unsigned long section_nr = pfn_to_section_nr(pfn); if (!present_section_nr(section_nr)) continue; if (pfn_to_nid(pfn) != nid) continue; /* * some memory sections of this node are not removed, and we * can't offline node now. */ return; } |
0f1cfe9d0 mm/hotplug: remov... |
1761 |
if (check_and_unmap_cpu_on_node(pgdat)) |
60a5a19e7 memory-hotplug: r... |
1762 1763 1764 1765 1766 1767 1768 1769 |
return; /* * all memory/cpu of this node are removed, we can offline this * node now. */ node_set_offline(nid); unregister_one_node(nid); |
d822b86a9 memory-hotplug: f... |
1770 1771 1772 1773 1774 1775 1776 1777 |
if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page)) /* node data is allocated from boot memory */ return; /* free waittable in each zone */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; |
ca4b3f302 mm/hotplug: only ... |
1778 1779 1780 1781 1782 |
/* * wait_table may be allocated from boot memory, * here only free if it's allocated by vmalloc. */ if (is_vmalloc_addr(zone->wait_table)) |
d822b86a9 memory-hotplug: f... |
1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 |
vfree(zone->wait_table); } /* * Since there is no way to guarentee the address of pgdat/zone is not * on stack of any kernel threads or used by other kernel objects * without reference counting or other symchronizing method, do not * reset node_data and free pgdat here. Just reset it to 0 and reuse * the memory when the node is online again. */ memset(pgdat, 0, sizeof(*pgdat)); |
60a5a19e7 memory-hotplug: r... |
1794 |
} |
90b30cdc1 memory-hotplug: e... |
1795 |
EXPORT_SYMBOL(try_offline_node); |
60a5a19e7 memory-hotplug: r... |
1796 |
|
0f1cfe9d0 mm/hotplug: remov... |
1797 1798 1799 1800 1801 1802 1803 |
/** * remove_memory * * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call, as required by * try_offline_node(). */ |
242831eb1 Memory hotplug / ... |
1804 |
void __ref remove_memory(int nid, u64 start, u64 size) |
bbc76be67 memory-hotplug: r... |
1805 |
{ |
242831eb1 Memory hotplug / ... |
1806 |
int ret; |
993c1aad8 memory-hotplug: t... |
1807 |
|
27356f54c mm/hotplug: verif... |
1808 |
BUG_ON(check_hotplug_memory_range(start, size)); |
6677e3eaf memory-hotplug: c... |
1809 1810 1811 |
lock_memory_hotplug(); /* |
242831eb1 Memory hotplug / ... |
1812 1813 1814 |
* All memory blocks must be offlined before removing memory. Check * whether all memory blocks in question are offline and trigger a BUG() * if this is not the case. |
6677e3eaf memory-hotplug: c... |
1815 |
*/ |
242831eb1 Memory hotplug / ... |
1816 |
ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, |
d6de9d534 mm/memory_hotplug... |
1817 |
check_memblock_offlined_cb); |
bbc76be67 memory-hotplug: r... |
1818 1819 |
if (ret) { unlock_memory_hotplug(); |
242831eb1 Memory hotplug / ... |
1820 |
BUG(); |
6677e3eaf memory-hotplug: c... |
1821 |
} |
46c66c4b7 memory-hotplug: r... |
1822 1823 |
/* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); |
24d335ca3 memory-hotplug: i... |
1824 |
arch_remove_memory(start, size); |
60a5a19e7 memory-hotplug: r... |
1825 |
try_offline_node(nid); |
6677e3eaf memory-hotplug: c... |
1826 |
unlock_memory_hotplug(); |
71088785c mm: cleanup to ma... |
1827 |
} |
71088785c mm: cleanup to ma... |
1828 |
EXPORT_SYMBOL_GPL(remove_memory); |
aba6efc47 Memory hotplug: M... |
1829 |
#endif /* CONFIG_MEMORY_HOTREMOVE */ |