Blame view
mm/memory_hotplug.c
22.1 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 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 [PATCH] call mm/p... |
15 |
#include <linux/writeback.h> |
3947be196 [PATCH] memory ho... |
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 [PATCH] register ... |
23 |
#include <linux/ioport.h> |
0c0e61958 memory unplug: pa... |
24 25 26 |
#include <linux/delay.h> #include <linux/migrate.h> #include <linux/page-isolation.h> |
71088785c mm: cleanup to ma... |
27 |
#include <linux/pfn.h> |
6ad696d2c mm: allow memory ... |
28 |
#include <linux/suspend.h> |
6d9c285a6 mm: move inc_zone... |
29 |
#include <linux/mm_inline.h> |
d96ae5309 memory-hotplug: c... |
30 |
#include <linux/firmware-map.h> |
3947be196 [PATCH] memory ho... |
31 32 |
#include <asm/tlbflush.h> |
1e5ad9a3b mm/memory_hotplug... |
33 |
#include "internal.h" |
45e0b78b0 [PATCH] hot-add-m... |
34 35 36 37 38 39 40 41 42 43 |
/* 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... |
44 |
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; |
45e0b78b0 [PATCH] hot-add-m... |
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
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 [PATCH] hot-add-m... |
63 |
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE |
047532787 memory hotplug: r... |
64 |
#ifndef CONFIG_SPARSEMEM_VMEMMAP |
af370fb8c memory hotplug: s... |
65 |
static void get_page_bootmem(unsigned long info, struct page *page, int type) |
047532787 memory hotplug: r... |
66 |
{ |
af370fb8c memory hotplug: s... |
67 |
atomic_set(&page->_mapcount, type); |
047532787 memory hotplug: r... |
68 69 70 71 |
SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); } |
23ce932a5 mm: fix section m... |
72 73 74 |
/* 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 memory hotplug: r... |
75 |
{ |
af370fb8c memory hotplug: s... |
76 |
int type; |
047532787 memory hotplug: r... |
77 |
|
af370fb8c memory hotplug: s... |
78 79 |
type = atomic_read(&page->_mapcount); BUG_ON(type >= -1); |
047532787 memory hotplug: r... |
80 81 82 83 84 85 86 87 88 |
if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); reset_page_mapcount(page); __free_pages_bootmem(page, 0); } } |
d92bc3185 mm: make register... |
89 |
static void register_page_bootmem_info_section(unsigned long start_pfn) |
047532787 memory hotplug: r... |
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
{ 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 memory hotplug: s... |
122 |
get_page_bootmem(section_nr, page, MIX_SECTION_INFO); |
047532787 memory hotplug: r... |
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
} 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 memory_hotplug: a... |
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
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 meminit section w... |
190 |
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) |
3947be196 [PATCH] memory ho... |
191 192 193 194 195 |
{ 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... |
196 |
unsigned long flags; |
3947be196 [PATCH] memory ho... |
197 198 |
zone_type = zone - pgdat->node_zones; |
76cdd58e5 memory_hotplug: a... |
199 200 201 202 203 204 205 206 207 208 209 210 211 |
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 [PATCH] Fix spars... |
212 213 |
memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn, MEMMAP_HOTPLUG); |
718127cc3 [PATCH] wait_tabl... |
214 |
return 0; |
3947be196 [PATCH] memory ho... |
215 |
} |
c04fc586c mm: show node to ... |
216 217 |
static int __meminit __add_section(int nid, struct zone *zone, unsigned long phys_start_pfn) |
3947be196 [PATCH] memory ho... |
218 |
{ |
3947be196 [PATCH] memory ho... |
219 |
int nr_pages = PAGES_PER_SECTION; |
3947be196 [PATCH] memory ho... |
220 |
int ret; |
ebd15302d [PATCH] memory ho... |
221 222 |
if (pfn_valid(phys_start_pfn)) return -EEXIST; |
0b0acbec1 [PATCH] memory ho... |
223 |
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages); |
3947be196 [PATCH] memory ho... |
224 225 226 |
if (ret < 0) return ret; |
718127cc3 [PATCH] wait_tabl... |
227 228 229 230 |
ret = __add_zone(zone, phys_start_pfn); if (ret < 0) return ret; |
c04fc586c mm: show node to ... |
231 |
return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); |
3947be196 [PATCH] memory ho... |
232 |
} |
0c0a4a517 memory hotplug: f... |
233 234 235 236 237 238 239 240 241 242 |
#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 hotplug memory re... |
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 |
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 memory hotplug: f... |
261 |
#endif |
ea01ea937 hotplug memory re... |
262 |
|
3947be196 [PATCH] memory ho... |
263 264 265 266 267 268 |
/* * 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 mm: show node to ... |
269 270 |
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) |
3947be196 [PATCH] memory ho... |
271 272 273 |
{ unsigned long i; int err = 0; |
6f712711d [PATCH] memory ho... |
274 275 276 277 |
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 [PATCH] memory ho... |
278 |
|
6f712711d [PATCH] memory ho... |
279 |
for (i = start_sec; i <= end_sec; i++) { |
c04fc586c mm: show node to ... |
280 |
err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); |
3947be196 [PATCH] memory ho... |
281 |
|
6f712711d [PATCH] memory ho... |
282 |
/* |
183ff22bb spelling fixes: mm/ |
283 |
* EEXIST is finally dealt with by ioresource collision |
6f712711d [PATCH] memory ho... |
284 285 |
* check. see add_memory() => register_memory_resource() * Warning will be printed if there is collision. |
bed120c64 [PATCH] spufs: fi... |
286 287 |
*/ if (err && (err != -EEXIST)) |
3947be196 [PATCH] memory ho... |
288 |
break; |
6f712711d [PATCH] memory ho... |
289 |
err = 0; |
3947be196 [PATCH] memory ho... |
290 291 292 293 |
} return err; } |
bed120c64 [PATCH] spufs: fi... |
294 |
EXPORT_SYMBOL_GPL(__add_pages); |
3947be196 [PATCH] memory ho... |
295 |
|
ea01ea937 hotplug memory re... |
296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
/** * __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 hotplug memory re... |
318 319 320 |
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 memory hotplug: r... |
321 322 |
release_mem_region(pfn << PAGE_SHIFT, PAGES_PER_SECTION << PAGE_SHIFT); |
ea01ea937 hotplug memory re... |
323 324 325 326 327 328 329 |
ret = __remove_section(zone, __pfn_to_section(pfn)); if (ret) break; } return ret; } EXPORT_SYMBOL_GPL(__remove_pages); |
180c06efc hotplug-memory: m... |
330 331 |
void online_page(struct page *page) { |
4738e1b9c memory hotplug: f... |
332 |
unsigned long pfn = page_to_pfn(page); |
180c06efc hotplug-memory: m... |
333 |
totalram_pages++; |
4738e1b9c memory hotplug: f... |
334 335 |
if (pfn >= num_physpages) num_physpages = pfn + 1; |
180c06efc hotplug-memory: m... |
336 337 338 339 340 341 342 343 344 345 346 347 348 349 |
#ifdef CONFIG_HIGHMEM if (PageHighMem(page)) totalhigh_pages++; #endif #ifdef CONFIG_FLATMEM max_mapnr = max(page_to_pfn(page), max_mapnr); #endif ClearPageReserved(page); init_page_count(page); __free_page(page); } |
75884fb1c memory unplug: me... |
350 351 |
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) |
3947be196 [PATCH] memory ho... |
352 353 |
{ unsigned long i; |
75884fb1c memory unplug: me... |
354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 |
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; } int online_pages(unsigned long pfn, unsigned long nr_pages) { |
3947be196 [PATCH] memory ho... |
369 370 |
unsigned long onlined_pages = 0; struct zone *zone; |
6811378e7 [PATCH] wait_tabl... |
371 |
int need_zonelists_rebuild = 0; |
7b78d335a memory hotplug: r... |
372 373 374 375 376 377 378 379 380 381 382 |
int nid; int ret; struct memory_notify arg; 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 [PATCH] memory ho... |
383 |
|
7b78d335a memory hotplug: r... |
384 385 386 387 388 389 |
ret = memory_notify(MEM_GOING_ONLINE, &arg); ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); return ret; } |
3947be196 [PATCH] memory ho... |
390 391 392 |
/* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the |
da19cbcf7 driver core: memo... |
393 |
* memory_block->state_mutex. |
3947be196 [PATCH] memory ho... |
394 395 |
*/ zone = page_zone(pfn_to_page(pfn)); |
6811378e7 [PATCH] wait_tabl... |
396 397 398 399 400 |
/* * 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 ... |
401 |
mutex_lock(&zonelists_mutex); |
6811378e7 [PATCH] wait_tabl... |
402 403 |
if (!populated_zone(zone)) need_zonelists_rebuild = 1; |
908eedc61 walk system ram r... |
404 |
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages, |
75884fb1c memory unplug: me... |
405 |
online_pages_range); |
fd8a4221a memory_hotplug: c... |
406 |
if (ret) { |
4eaf3f643 mem-hotplug: fix ... |
407 |
mutex_unlock(&zonelists_mutex); |
fd8a4221a memory_hotplug: c... |
408 409 410 411 412 413 |
printk(KERN_DEBUG "online_pages %lx at %lx failed ", nr_pages, pfn); memory_notify(MEM_CANCEL_ONLINE, &arg); return ret; } |
3947be196 [PATCH] memory ho... |
414 |
zone->present_pages += onlined_pages; |
f2937be58 [PATCH] memory ho... |
415 |
zone->zone_pgdat->node_present_pages += onlined_pages; |
1f522509c mem-hotplug: avoi... |
416 417 418 419 |
if (need_zonelists_rebuild) build_all_zonelists(zone); else zone_pcp_update(zone); |
3947be196 [PATCH] memory ho... |
420 |
|
4eaf3f643 mem-hotplug: fix ... |
421 |
mutex_unlock(&zonelists_mutex); |
bc75d33f0 page-allocator: c... |
422 |
setup_per_zone_wmarks(); |
bce7394a3 page-allocator: r... |
423 |
calculate_zone_inactive_ratio(zone); |
7ea1530ab Memoryless nodes:... |
424 425 426 427 |
if (onlined_pages) { kswapd_run(zone_to_nid(zone)); node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); } |
61b13993a [PATCH] memory ho... |
428 |
|
1f522509c mem-hotplug: avoi... |
429 |
vm_total_pages = nr_free_pagecache_pages(); |
2f7f24eca memory-hotplug: d... |
430 |
|
2d1d43f6a [PATCH] call mm/p... |
431 |
writeback_set_ratelimit(); |
7b78d335a memory hotplug: r... |
432 433 434 |
if (onlined_pages) memory_notify(MEM_ONLINE, &arg); |
3947be196 [PATCH] memory ho... |
435 436 |
return 0; } |
53947027a [PATCH] hot-add-m... |
437 |
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ |
bc02af93d [PATCH] pgdat all... |
438 |
|
e13193319 mm/memory_hotplug... |
439 440 |
/* 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... |
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 |
{ 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 mm: drop unneeded... |
456 |
free_area_init_node(nid, zones_size, start_pfn, zholes_size); |
9af3c2dea [PATCH] pgdat all... |
457 458 459 460 461 462 463 464 465 466 |
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 ... |
467 |
|
cf23422b9 cpu/mem hotplug: ... |
468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 |
/* * called by cpu_up() to online a node without onlined memory. */ int mem_online_node(int nid) { pg_data_t *pgdat; int ret; lock_system_sleep(); 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: unlock_system_sleep(); return ret; } |
31168481c meminit section w... |
490 491 |
/* 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... |
492 |
{ |
9af3c2dea [PATCH] pgdat all... |
493 494 |
pg_data_t *pgdat = NULL; int new_pgdat = 0; |
ebd15302d [PATCH] memory ho... |
495 |
struct resource *res; |
bc02af93d [PATCH] pgdat all... |
496 |
int ret; |
6ad696d2c mm: allow memory ... |
497 |
lock_system_sleep(); |
ebd15302d [PATCH] memory ho... |
498 |
res = register_memory_resource(start, size); |
6ad696d2c mm: allow memory ... |
499 |
ret = -EEXIST; |
ebd15302d [PATCH] memory ho... |
500 |
if (!res) |
6ad696d2c mm: allow memory ... |
501 |
goto out; |
ebd15302d [PATCH] memory ho... |
502 |
|
9af3c2dea [PATCH] pgdat all... |
503 504 |
if (!node_online(nid)) { pgdat = hotadd_new_pgdat(nid, start); |
6ad696d2c mm: allow memory ... |
505 |
ret = -ENOMEM; |
9af3c2dea [PATCH] pgdat all... |
506 |
if (!pgdat) |
6ad696d2c mm: allow memory ... |
507 |
goto out; |
9af3c2dea [PATCH] pgdat all... |
508 |
new_pgdat = 1; |
9af3c2dea [PATCH] pgdat all... |
509 |
} |
bc02af93d [PATCH] pgdat all... |
510 511 |
/* call arch's memory hotadd */ ret = arch_add_memory(nid, start, size); |
9af3c2dea [PATCH] pgdat all... |
512 513 |
if (ret < 0) goto error; |
0fc44159b [PATCH] Register ... |
514 |
/* we online node here. we can't roll back from here. */ |
9af3c2dea [PATCH] pgdat all... |
515 |
node_set_online(nid); |
0fc44159b [PATCH] Register ... |
516 517 518 519 520 521 522 523 524 |
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 memory-hotplug: c... |
525 526 |
/* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); |
6ad696d2c mm: allow memory ... |
527 |
goto out; |
9af3c2dea [PATCH] pgdat all... |
528 529 530 531 |
error: /* rollback pgdat allocation and others */ if (new_pgdat) rollback_node_hotadd(nid, pgdat); |
ebd15302d [PATCH] memory ho... |
532 533 |
if (res) release_memory_resource(res); |
9af3c2dea [PATCH] pgdat all... |
534 |
|
6ad696d2c mm: allow memory ... |
535 536 |
out: unlock_system_sleep(); |
bc02af93d [PATCH] pgdat all... |
537 538 539 |
return ret; } EXPORT_SYMBOL_GPL(add_memory); |
0c0e61958 memory unplug: pa... |
540 541 542 |
#ifdef CONFIG_MEMORY_HOTREMOVE /* |
5c755e9fd memory-hotplug: a... |
543 544 545 546 547 548 549 550 551 552 553 554 555 556 |
* 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... |
557 558 |
/* Ensure the starting page is pageblock-aligned */ BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1)); |
5c755e9fd memory-hotplug: a... |
559 |
/* If the entire pageblock is free, move to the end of free page */ |
0dcc48c15 memory hotplug: f... |
560 561 562 563 564 565 566 |
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... |
567 |
|
0dcc48c15 memory hotplug: f... |
568 |
return page + pageblock_nr_pages; |
5c755e9fd memory-hotplug: a... |
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 |
} /* 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) { int type; 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)) { type = get_pageblock_migratetype(page); /* * A pageblock containing MOVABLE or free pages is considered * removable */ if (type != MIGRATE_MOVABLE && !pageblock_free(page)) return 0; /* * A pageblock starting with a PageReserved page is not * considered removable. */ if (PageReserved(page)) return 0; } /* All pageblocks in the memory block are likely to be hot-removable */ return 1; } /* |
0c0e61958 memory unplug: pa... |
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 |
* 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. */ int scan_lru_pages(unsigned long start, unsigned long end) { 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 mm: remove GFP_HI... |
646 |
hotremove_migrate_alloc(struct page *page, unsigned long private, int **x) |
0c0e61958 memory unplug: pa... |
647 |
{ |
3c1d43787 mm: remove GFP_HI... |
648 649 |
/* This should be improooooved!! */ return alloc_page(GFP_HIGHUSER_MOVABLE); |
0c0e61958 memory unplug: pa... |
650 |
} |
0c0e61958 memory unplug: pa... |
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 |
#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); if (!page_count(page)) continue; /* * We can skip free pages. And we can only deal with pages on * LRU. */ |
62695a84e vmscan: move isol... |
672 |
ret = isolate_lru_page(page); |
0c0e61958 memory unplug: pa... |
673 |
if (!ret) { /* Success */ |
62695a84e vmscan: move isol... |
674 |
list_add_tail(&page->lru, &source); |
0c0e61958 memory unplug: pa... |
675 |
move_pages--; |
6d9c285a6 mm: move inc_zone... |
676 677 |
inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); |
0c0e61958 memory unplug: pa... |
678 679 680 681 682 683 |
} else { /* Becasue we don't have big zone->lock. we should check this again here. */ if (page_count(page)) not_managed++; #ifdef CONFIG_DEBUG_VM |
718a38211 mm: introduce dum... |
684 685 686 687 |
printk(KERN_ALERT "removing pfn %lx from LRU failed ", pfn); dump_page(page); |
0c0e61958 memory unplug: pa... |
688 689 690 691 692 693 694 695 696 697 698 699 700 |
#endif } } ret = -EBUSY; if (not_managed) { if (!list_empty(&source)) putback_lru_pages(&source); goto out; } ret = 0; if (list_empty(&source)) goto out; /* this function returns # of failed pages */ |
62b61f611 ksm: memory hotre... |
701 |
ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1); |
0c0e61958 memory unplug: pa... |
702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 |
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... |
721 |
walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL, |
0c0e61958 memory unplug: pa... |
722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 |
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 walk system ram r... |
746 |
ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined, |
0c0e61958 memory unplug: pa... |
747 748 749 750 751 |
check_pages_isolated_cb); if (ret < 0) offlined = (long)ret; return offlined; } |
b4e655a4a mm: memory_hotplu... |
752 |
static int offline_pages(unsigned long start_pfn, |
0c0e61958 memory unplug: pa... |
753 754 755 756 |
unsigned long end_pfn, unsigned long timeout) { unsigned long pfn, nr_pages, expire; long offlined_pages; |
7b78d335a memory hotplug: r... |
757 |
int ret, drain, retry_max, node; |
0c0e61958 memory unplug: pa... |
758 |
struct zone *zone; |
7b78d335a memory hotplug: r... |
759 |
struct memory_notify arg; |
0c0e61958 memory unplug: pa... |
760 761 762 763 764 765 766 767 768 769 770 |
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 memory hotplug: r... |
771 |
|
6ad696d2c mm: allow memory ... |
772 |
lock_system_sleep(); |
7b78d335a memory hotplug: r... |
773 774 775 |
zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; |
0c0e61958 memory unplug: pa... |
776 777 778 |
/* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn); if (ret) |
6ad696d2c mm: allow memory ... |
779 |
goto out; |
7b78d335a memory hotplug: r... |
780 781 782 783 784 785 786 787 788 789 790 |
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 memory unplug: pa... |
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 |
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(); flush_scheduled_work(); cond_resched(); |
9f8f21725 Page allocator: c... |
808 |
drain_all_pages(); |
0c0e61958 memory unplug: pa... |
809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 |
} 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(); flush_scheduled_work(); yield(); /* drain pcp pages , this is synchrouns. */ |
9f8f21725 Page allocator: c... |
831 |
drain_all_pages(); |
0c0e61958 memory unplug: pa... |
832 833 834 835 836 837 838 839 840 841 842 |
/* 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 memory hotremove:... |
843 844 |
/* reset pagetype flags and makes migrate type to be MOVABLE */ undo_isolate_page_range(start_pfn, end_pfn); |
0c0e61958 memory unplug: pa... |
845 |
/* removal success */ |
0c0e61958 memory unplug: pa... |
846 847 848 |
zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; totalram_pages -= offlined_pages; |
7b78d335a memory hotplug: r... |
849 |
|
bce7394a3 page-allocator: r... |
850 851 |
setup_per_zone_wmarks(); calculate_zone_inactive_ratio(zone); |
8fe23e057 mm: clear node in... |
852 853 854 855 |
if (!node_present_pages(node)) { node_clear_state(node, N_HIGH_MEMORY); kswapd_stop(node); } |
bce7394a3 page-allocator: r... |
856 |
|
0c0e61958 memory unplug: pa... |
857 858 |
vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); |
7b78d335a memory hotplug: r... |
859 860 |
memory_notify(MEM_OFFLINE, &arg); |
6ad696d2c mm: allow memory ... |
861 |
unlock_system_sleep(); |
0c0e61958 memory unplug: pa... |
862 863 864 865 866 867 |
return 0; failed_removal: printk(KERN_INFO "memory offlining %lx to %lx failed ", start_pfn, end_pfn); |
7b78d335a memory hotplug: r... |
868 |
memory_notify(MEM_CANCEL_OFFLINE, &arg); |
0c0e61958 memory unplug: pa... |
869 870 |
/* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn); |
7b78d335a memory hotplug: r... |
871 |
|
6ad696d2c mm: allow memory ... |
872 873 |
out: unlock_system_sleep(); |
0c0e61958 memory unplug: pa... |
874 875 |
return ret; } |
71088785c mm: cleanup to ma... |
876 877 878 879 880 881 882 883 884 |
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 fix memory hot re... |
885 886 887 888 889 |
#else int remove_memory(u64 start, u64 size) { return -EINVAL; } |
0c0e61958 memory unplug: pa... |
890 |
#endif /* CONFIG_MEMORY_HOTREMOVE */ |
71088785c mm: cleanup to ma... |
891 |
EXPORT_SYMBOL_GPL(remove_memory); |