Blame view
mm/memory_hotplug.c
22.2 KB
3947be196
|
1 2 3 4 5 |
/* * linux/mm/memory_hotplug.c * * Copyright (C) */ |
3947be196
|
6 7 8 9 10 11 12 13 14 |
#include <linux/stddef.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> #include <linux/bootmem.h> #include <linux/compiler.h> #include <linux/module.h> #include <linux/pagevec.h> |
2d1d43f6a
|
15 |
#include <linux/writeback.h> |
3947be196
|
16 17 18 19 20 21 22 |
#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
|
23 |
#include <linux/ioport.h> |
0c0e61958
|
24 25 26 |
#include <linux/delay.h> #include <linux/migrate.h> #include <linux/page-isolation.h> |
71088785c
|
27 |
#include <linux/pfn.h> |
6ad696d2c
|
28 |
#include <linux/suspend.h> |
6d9c285a6
|
29 |
#include <linux/mm_inline.h> |
d96ae5309
|
30 |
#include <linux/firmware-map.h> |
3947be196
|
31 32 |
#include <asm/tlbflush.h> |
1e5ad9a3b
|
33 |
#include "internal.h" |
20d6c96b5
|
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
DEFINE_MUTEX(mem_hotplug_mutex); void lock_memory_hotplug(void) { mutex_lock(&mem_hotplug_mutex); /* for exclusive hibernation if CONFIG_HIBERNATION=y */ lock_system_sleep(); } void unlock_memory_hotplug(void) { unlock_system_sleep(); mutex_unlock(&mem_hotplug_mutex); } |
45e0b78b0
|
49 50 51 52 53 54 55 56 57 58 |
/* 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
|
59 |
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; |
45e0b78b0
|
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
if (request_resource(&iomem_resource, res) < 0) { printk("System RAM resource %llx - %llx cannot be added ", (unsigned long long)res->start, (unsigned long long)res->end); kfree(res); res = NULL; } return res; } static void release_memory_resource(struct resource *res) { if (!res) return; release_resource(res); kfree(res); return; } |
53947027a
|
78 |
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE |
047532787
|
79 |
#ifndef CONFIG_SPARSEMEM_VMEMMAP |
5f24ce5fd
|
80 81 |
static void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) |
047532787
|
82 |
{ |
5f24ce5fd
|
83 |
page->lru.next = (struct list_head *) type; |
047532787
|
84 85 86 87 |
SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); } |
23ce932a5
|
88 89 90 |
/* reference to __meminit __free_pages_bootmem is valid * so use __ref to tell modpost not to generate a warning */ void __ref put_page_bootmem(struct page *page) |
047532787
|
91 |
{ |
5f24ce5fd
|
92 |
unsigned long type; |
047532787
|
93 |
|
5f24ce5fd
|
94 95 96 |
type = (unsigned long) page->lru.next; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); |
047532787
|
97 98 99 100 |
if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); |
5f24ce5fd
|
101 |
INIT_LIST_HEAD(&page->lru); |
047532787
|
102 103 104 105 |
__free_pages_bootmem(page, 0); } } |
d92bc3185
|
106 |
static void register_page_bootmem_info_section(unsigned long start_pfn) |
047532787
|
107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
{ 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); /* 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
|
139 |
get_page_bootmem(section_nr, page, MIX_SECTION_INFO); |
047532787
|
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
} 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++) { if (zone->wait_table) { 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; end_pfn = pfn + pgdat->node_spanned_pages; /* register_section info */ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) register_page_bootmem_info_section(pfn); } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ |
76cdd58e5
|
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
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); old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; if (start_pfn < zone->zone_start_pfn) zone->zone_start_pfn = start_pfn; zone->spanned_pages = max(old_zone_end_pfn, end_pfn) - zone->zone_start_pfn; zone_span_writeunlock(zone); } static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { unsigned long old_pgdat_end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages; if (start_pfn < pgdat->node_start_pfn) pgdat->node_start_pfn = start_pfn; pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) - pgdat->node_start_pfn; } |
31168481c
|
207 |
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) |
3947be196
|
208 209 210 211 212 |
{ struct pglist_data *pgdat = zone->zone_pgdat; int nr_pages = PAGES_PER_SECTION; int nid = pgdat->node_id; int zone_type; |
76cdd58e5
|
213 |
unsigned long flags; |
3947be196
|
214 215 |
zone_type = zone - pgdat->node_zones; |
76cdd58e5
|
216 217 218 219 220 221 222 223 224 225 226 227 228 |
if (!zone->wait_table) { int ret; ret = init_currently_empty_zone(zone, phys_start_pfn, nr_pages, MEMMAP_HOTPLUG); if (ret) return ret; } 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
|
229 230 |
memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn, MEMMAP_HOTPLUG); |
718127cc3
|
231 |
return 0; |
3947be196
|
232 |
} |
c04fc586c
|
233 234 |
static int __meminit __add_section(int nid, struct zone *zone, unsigned long phys_start_pfn) |
3947be196
|
235 |
{ |
3947be196
|
236 |
int nr_pages = PAGES_PER_SECTION; |
3947be196
|
237 |
int ret; |
ebd15302d
|
238 239 |
if (pfn_valid(phys_start_pfn)) return -EEXIST; |
0b0acbec1
|
240 |
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages); |
3947be196
|
241 242 243 |
if (ret < 0) return ret; |
718127cc3
|
244 245 246 247 |
ret = __add_zone(zone, phys_start_pfn); if (ret < 0) return ret; |
c04fc586c
|
248 |
return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); |
3947be196
|
249 |
} |
0c0a4a517
|
250 251 252 253 254 255 256 257 258 259 |
#ifdef CONFIG_SPARSEMEM_VMEMMAP static int __remove_section(struct zone *zone, struct mem_section *ms) { /* * XXX: Freeing memmap with vmemmap is not implement yet. * This should be removed later. */ return -EBUSY; } #else |
ea01ea937
|
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 |
static int __remove_section(struct zone *zone, struct mem_section *ms) { unsigned long flags; struct pglist_data *pgdat = zone->zone_pgdat; int ret = -EINVAL; if (!valid_section(ms)) return ret; ret = unregister_memory_section(ms); if (ret) return ret; pgdat_resize_lock(pgdat, &flags); sparse_remove_one_section(zone, ms); pgdat_resize_unlock(pgdat, &flags); return 0; } |
0c0a4a517
|
278 |
#endif |
ea01ea937
|
279 |
|
3947be196
|
280 281 282 283 284 285 |
/* * 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. */ |
c04fc586c
|
286 287 |
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) |
3947be196
|
288 289 290 |
{ unsigned long i; int err = 0; |
6f712711d
|
291 292 293 294 |
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); |
3947be196
|
295 |
|
6f712711d
|
296 |
for (i = start_sec; i <= end_sec; i++) { |
c04fc586c
|
297 |
err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); |
3947be196
|
298 |
|
6f712711d
|
299 |
/* |
183ff22bb
|
300 |
* EEXIST is finally dealt with by ioresource collision |
6f712711d
|
301 302 |
* check. see add_memory() => register_memory_resource() * Warning will be printed if there is collision. |
bed120c64
|
303 304 |
*/ if (err && (err != -EEXIST)) |
3947be196
|
305 |
break; |
6f712711d
|
306 |
err = 0; |
3947be196
|
307 308 309 310 |
} return err; } |
bed120c64
|
311 |
EXPORT_SYMBOL_GPL(__add_pages); |
3947be196
|
312 |
|
ea01ea937
|
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 |
/** * __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) { unsigned long i, ret = 0; int sections_to_remove; /* * We can only remove entire sections */ BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); |
ea01ea937
|
335 336 337 |
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; |
de7f0cba9
|
338 339 |
release_mem_region(pfn << PAGE_SHIFT, PAGES_PER_SECTION << PAGE_SHIFT); |
ea01ea937
|
340 341 342 343 344 345 346 |
ret = __remove_section(zone, __pfn_to_section(pfn)); if (ret) break; } return ret; } EXPORT_SYMBOL_GPL(__remove_pages); |
180c06efc
|
347 348 |
void online_page(struct page *page) { |
4738e1b9c
|
349 |
unsigned long pfn = page_to_pfn(page); |
180c06efc
|
350 |
totalram_pages++; |
4738e1b9c
|
351 352 |
if (pfn >= num_physpages) num_physpages = pfn + 1; |
180c06efc
|
353 354 355 356 357 |
#ifdef CONFIG_HIGHMEM if (PageHighMem(page)) totalhigh_pages++; #endif |
180c06efc
|
358 359 360 361 |
ClearPageReserved(page); init_page_count(page); __free_page(page); } |
75884fb1c
|
362 363 |
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) |
3947be196
|
364 365 |
{ unsigned long i; |
75884fb1c
|
366 367 368 369 370 371 372 373 374 375 376 |
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); online_page(page); onlined_pages++; } *(unsigned long *)arg = onlined_pages; return 0; } |
839a4fcc8
|
377 |
int __ref online_pages(unsigned long pfn, unsigned long nr_pages) |
75884fb1c
|
378 |
{ |
3947be196
|
379 380 |
unsigned long onlined_pages = 0; struct zone *zone; |
6811378e7
|
381 |
int need_zonelists_rebuild = 0; |
7b78d335a
|
382 383 384 |
int nid; int ret; struct memory_notify arg; |
925268a06
|
385 |
lock_memory_hotplug(); |
7b78d335a
|
386 387 388 389 390 391 392 |
arg.start_pfn = pfn; arg.nr_pages = nr_pages; arg.status_change_nid = -1; nid = page_to_nid(pfn_to_page(pfn)); if (node_present_pages(nid) == 0) arg.status_change_nid = nid; |
3947be196
|
393 |
|
7b78d335a
|
394 395 396 397 |
ret = memory_notify(MEM_GOING_ONLINE, &arg); ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); |
925268a06
|
398 |
unlock_memory_hotplug(); |
7b78d335a
|
399 400 |
return ret; } |
3947be196
|
401 402 403 |
/* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the |
da19cbcf7
|
404 |
* memory_block->state_mutex. |
3947be196
|
405 406 |
*/ zone = page_zone(pfn_to_page(pfn)); |
6811378e7
|
407 408 409 410 411 |
/* * 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
|
412 |
mutex_lock(&zonelists_mutex); |
6811378e7
|
413 414 |
if (!populated_zone(zone)) need_zonelists_rebuild = 1; |
908eedc61
|
415 |
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages, |
75884fb1c
|
416 |
online_pages_range); |
fd8a4221a
|
417 |
if (ret) { |
4eaf3f643
|
418 |
mutex_unlock(&zonelists_mutex); |
fd8a4221a
|
419 420 421 422 |
printk(KERN_DEBUG "online_pages %lx at %lx failed ", nr_pages, pfn); memory_notify(MEM_CANCEL_ONLINE, &arg); |
925268a06
|
423 |
unlock_memory_hotplug(); |
fd8a4221a
|
424 425 |
return ret; } |
3947be196
|
426 |
zone->present_pages += onlined_pages; |
f2937be58
|
427 |
zone->zone_pgdat->node_present_pages += onlined_pages; |
1f522509c
|
428 429 430 431 |
if (need_zonelists_rebuild) build_all_zonelists(zone); else zone_pcp_update(zone); |
3947be196
|
432 |
|
4eaf3f643
|
433 |
mutex_unlock(&zonelists_mutex); |
1b79acc91
|
434 435 |
init_per_zone_wmark_min(); |
7ea1530ab
|
436 437 438 439 |
if (onlined_pages) { kswapd_run(zone_to_nid(zone)); node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); } |
61b13993a
|
440 |
|
1f522509c
|
441 |
vm_total_pages = nr_free_pagecache_pages(); |
2f7f24eca
|
442 |
|
2d1d43f6a
|
443 |
writeback_set_ratelimit(); |
7b78d335a
|
444 445 446 |
if (onlined_pages) memory_notify(MEM_ONLINE, &arg); |
925268a06
|
447 |
unlock_memory_hotplug(); |
7b78d335a
|
448 |
|
3947be196
|
449 450 |
return 0; } |
53947027a
|
451 |
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ |
bc02af93d
|
452 |
|
e13193319
|
453 454 |
/* 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
|
455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 |
{ 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; pgdat = arch_alloc_nodedata(nid); if (!pgdat) return NULL; arch_refresh_nodedata(nid, pgdat); /* we can use NODE_DATA(nid) from here */ /* init node's zones as empty zones, we don't have any present pages.*/ |
9109fb7b3
|
470 |
free_area_init_node(nid, zones_size, start_pfn, zholes_size); |
9af3c2dea
|
471 472 473 474 475 476 477 478 479 480 |
return pgdat; } static void rollback_node_hotadd(int nid, pg_data_t *pgdat) { arch_refresh_nodedata(nid, NULL); arch_free_nodedata(pgdat); return; } |
0a5470390
|
481 |
|
cf23422b9
|
482 483 484 485 486 487 488 |
/* * called by cpu_up() to online a node without onlined memory. */ int mem_online_node(int nid) { pg_data_t *pgdat; int ret; |
20d6c96b5
|
489 |
lock_memory_hotplug(); |
cf23422b9
|
490 491 492 493 494 495 496 497 498 499 |
pgdat = hotadd_new_pgdat(nid, 0); if (pgdat) { ret = -ENOMEM; goto out; } node_set_online(nid); ret = register_one_node(nid); BUG_ON(ret); out: |
20d6c96b5
|
500 |
unlock_memory_hotplug(); |
cf23422b9
|
501 502 |
return ret; } |
31168481c
|
503 504 |
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ int __ref add_memory(int nid, u64 start, u64 size) |
bc02af93d
|
505 |
{ |
9af3c2dea
|
506 507 |
pg_data_t *pgdat = NULL; int new_pgdat = 0; |
ebd15302d
|
508 |
struct resource *res; |
bc02af93d
|
509 |
int ret; |
20d6c96b5
|
510 |
lock_memory_hotplug(); |
6ad696d2c
|
511 |
|
ebd15302d
|
512 |
res = register_memory_resource(start, size); |
6ad696d2c
|
513 |
ret = -EEXIST; |
ebd15302d
|
514 |
if (!res) |
6ad696d2c
|
515 |
goto out; |
ebd15302d
|
516 |
|
9af3c2dea
|
517 518 |
if (!node_online(nid)) { pgdat = hotadd_new_pgdat(nid, start); |
6ad696d2c
|
519 |
ret = -ENOMEM; |
9af3c2dea
|
520 |
if (!pgdat) |
6ad696d2c
|
521 |
goto out; |
9af3c2dea
|
522 |
new_pgdat = 1; |
9af3c2dea
|
523 |
} |
bc02af93d
|
524 525 |
/* call arch's memory hotadd */ ret = arch_add_memory(nid, start, size); |
9af3c2dea
|
526 527 |
if (ret < 0) goto error; |
0fc44159b
|
528 |
/* we online node here. we can't roll back from here. */ |
9af3c2dea
|
529 |
node_set_online(nid); |
0fc44159b
|
530 531 532 533 534 535 536 537 538 |
if (new_pgdat) { 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
|
539 540 |
/* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); |
6ad696d2c
|
541 |
goto out; |
9af3c2dea
|
542 543 544 545 |
error: /* rollback pgdat allocation and others */ if (new_pgdat) rollback_node_hotadd(nid, pgdat); |
ebd15302d
|
546 547 |
if (res) release_memory_resource(res); |
9af3c2dea
|
548 |
|
6ad696d2c
|
549 |
out: |
20d6c96b5
|
550 |
unlock_memory_hotplug(); |
bc02af93d
|
551 552 553 |
return ret; } EXPORT_SYMBOL_GPL(add_memory); |
0c0e61958
|
554 555 556 |
#ifdef CONFIG_MEMORY_HOTREMOVE /* |
5c755e9fd
|
557 558 559 560 561 562 563 564 565 566 567 568 569 570 |
* 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
|
571 572 |
/* Ensure the starting page is pageblock-aligned */ BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1)); |
5c755e9fd
|
573 |
/* If the entire pageblock is free, move to the end of free page */ |
0dcc48c15
|
574 575 576 577 578 579 580 |
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
|
581 |
|
0dcc48c15
|
582 |
return page + pageblock_nr_pages; |
5c755e9fd
|
583 584 585 586 587 |
} /* 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
|
588 589 590 591 592 |
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
|
593 |
if (!is_pageblock_removable_nolock(page)) |
5c755e9fd
|
594 |
return 0; |
49ac82558
|
595 |
cond_resched(); |
5c755e9fd
|
596 597 598 599 600 601 602 |
} /* All pageblocks in the memory block are likely to be hot-removable */ return 1; } /* |
0c0e61958
|
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 |
* 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; } /* * Scanning pfn is much easier than scanning lru list. * Scan pfn from start to end and Find LRU page. */ |
7bbc0905e
|
632 |
static unsigned long scan_lru_pages(unsigned long start, unsigned long end) |
0c0e61958
|
633 634 635 636 637 638 639 640 641 642 643 644 645 646 |
{ 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; } } return 0; } static struct page * |
3c1d43787
|
647 |
hotremove_migrate_alloc(struct page *page, unsigned long private, int **x) |
0c0e61958
|
648 |
{ |
3c1d43787
|
649 650 |
/* This should be improooooved!! */ return alloc_page(GFP_HIGHUSER_MOVABLE); |
0c0e61958
|
651 |
} |
0c0e61958
|
652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 |
#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); |
700c2a46e
|
667 |
if (!get_page_unless_zero(page)) |
0c0e61958
|
668 669 670 671 672 |
continue; /* * We can skip free pages. And we can only deal with pages on * LRU. */ |
62695a84e
|
673 |
ret = isolate_lru_page(page); |
0c0e61958
|
674 |
if (!ret) { /* Success */ |
700c2a46e
|
675 |
put_page(page); |
62695a84e
|
676 |
list_add_tail(&page->lru, &source); |
0c0e61958
|
677 |
move_pages--; |
6d9c285a6
|
678 679 |
inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); |
0c0e61958
|
680 |
} else { |
0c0e61958
|
681 |
#ifdef CONFIG_DEBUG_VM |
718a38211
|
682 683 684 685 |
printk(KERN_ALERT "removing pfn %lx from LRU failed ", pfn); dump_page(page); |
0c0e61958
|
686 |
#endif |
700c2a46e
|
687 |
put_page(page); |
25985edce
|
688 |
/* Because we don't have big zone->lock. we should |
809c44497
|
689 690 691 |
check this again here. */ if (page_count(page)) { not_managed++; |
f3ab2636c
|
692 |
ret = -EBUSY; |
809c44497
|
693 694 |
break; } |
0c0e61958
|
695 696 |
} } |
f3ab2636c
|
697 698 699 700 701 702 |
if (!list_empty(&source)) { if (not_managed) { putback_lru_pages(&source); goto out; } /* this function returns # of failed pages */ |
77f1fe6b0
|
703 |
ret = migrate_pages(&source, hotremove_migrate_alloc, 0, |
7f0f24967
|
704 |
true, true); |
f3ab2636c
|
705 |
if (ret) |
0c0e61958
|
706 |
putback_lru_pages(&source); |
0c0e61958
|
707 |
} |
0c0e61958
|
708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 |
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
|
726 |
walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL, |
0c0e61958
|
727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 |
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; ret = test_pages_isolated(start_pfn, start_pfn + nr_pages); 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
|
751 |
ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined, |
0c0e61958
|
752 753 754 755 756 |
check_pages_isolated_cb); if (ret < 0) offlined = (long)ret; return offlined; } |
839a4fcc8
|
757 |
static int __ref offline_pages(unsigned long start_pfn, |
0c0e61958
|
758 759 760 761 |
unsigned long end_pfn, unsigned long timeout) { unsigned long pfn, nr_pages, expire; long offlined_pages; |
7b78d335a
|
762 |
int ret, drain, retry_max, node; |
0c0e61958
|
763 |
struct zone *zone; |
7b78d335a
|
764 |
struct memory_notify arg; |
0c0e61958
|
765 766 767 768 769 770 771 772 773 774 775 |
BUG_ON(start_pfn >= end_pfn); /* 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
|
776 |
|
20d6c96b5
|
777 |
lock_memory_hotplug(); |
6ad696d2c
|
778 |
|
7b78d335a
|
779 780 781 |
zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; |
0c0e61958
|
782 783 784 |
/* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn); if (ret) |
6ad696d2c
|
785 |
goto out; |
7b78d335a
|
786 787 788 789 790 791 792 793 794 795 796 |
arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; arg.status_change_nid = -1; if (nr_pages >= node_present_pages(node)) arg.status_change_nid = node; ret = memory_notify(MEM_GOING_OFFLINE, &arg); ret = notifier_to_errno(ret); if (ret) goto failed_removal; |
0c0e61958
|
797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 |
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
|
812 |
cond_resched(); |
9f8f21725
|
813 |
drain_all_pages(); |
0c0e61958
|
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 |
} pfn = scan_lru_pages(start_pfn, end_pfn); if (pfn) { /* We have page on LRU */ 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; } } /* drain all zone's lru pagevec, this is asyncronous... */ lru_add_drain_all(); |
0c0e61958
|
833 834 |
yield(); /* drain pcp pages , this is synchrouns. */ |
9f8f21725
|
835 |
drain_all_pages(); |
0c0e61958
|
836 837 838 839 840 841 842 843 844 845 846 |
/* 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); /* Ok, all of our target is islaoted. We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); |
dbc0e4cef
|
847 848 |
/* reset pagetype flags and makes migrate type to be MOVABLE */ undo_isolate_page_range(start_pfn, end_pfn); |
0c0e61958
|
849 |
/* removal success */ |
0c0e61958
|
850 851 852 |
zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; totalram_pages -= offlined_pages; |
7b78d335a
|
853 |
|
1b79acc91
|
854 |
init_per_zone_wmark_min(); |
8fe23e057
|
855 856 857 858 |
if (!node_present_pages(node)) { node_clear_state(node, N_HIGH_MEMORY); kswapd_stop(node); } |
bce7394a3
|
859 |
|
0c0e61958
|
860 861 |
vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); |
7b78d335a
|
862 863 |
memory_notify(MEM_OFFLINE, &arg); |
20d6c96b5
|
864 |
unlock_memory_hotplug(); |
0c0e61958
|
865 866 867 868 869 870 |
return 0; failed_removal: printk(KERN_INFO "memory offlining %lx to %lx failed ", start_pfn, end_pfn); |
7b78d335a
|
871 |
memory_notify(MEM_CANCEL_OFFLINE, &arg); |
0c0e61958
|
872 873 |
/* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn); |
7b78d335a
|
874 |
|
6ad696d2c
|
875 |
out: |
20d6c96b5
|
876 |
unlock_memory_hotplug(); |
0c0e61958
|
877 878 |
return ret; } |
71088785c
|
879 880 881 882 883 884 885 886 887 |
int remove_memory(u64 start, u64 size) { unsigned long start_pfn, end_pfn; start_pfn = PFN_DOWN(start); end_pfn = start_pfn + PFN_DOWN(size); return offline_pages(start_pfn, end_pfn, 120 * HZ); } |
48e94196a
|
888 889 890 891 892 |
#else int remove_memory(u64 start, u64 size) { return -EINVAL; } |
0c0e61958
|
893 |
#endif /* CONFIG_MEMORY_HOTREMOVE */ |
71088785c
|
894 |
EXPORT_SYMBOL_GPL(remove_memory); |