linux/mm/memory_hotplug.c

1012 lines
24 KiB
C
Raw Normal View History

/*
* linux/mm/memory_hotplug.c
*
* Copyright (C)
*/
#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/export.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#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>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <asm/tlbflush.h>
#include "internal.h"
/*
* 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;
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);
}
/* 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;
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
if (request_resource(&iomem_resource, res) < 0) {
printk("System RAM resource %pR cannot be added\n", res);
kfree(res);
res = NULL;
}
return res;
}
static void release_memory_resource(struct resource *res)
{
if (!res)
return;
release_resource(res);
kfree(res);
return;
}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
#ifndef CONFIG_SPARSEMEM_VMEMMAP
static void get_page_bootmem(unsigned long info, struct page *page,
unsigned long type)
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
{
page->lru.next = (struct list_head *) type;
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
SetPagePrivate(page);
set_page_private(page, info);
atomic_inc(&page->_count);
}
/* 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)
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
{
unsigned long type;
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
type = (unsigned long) page->lru.next;
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
if (atomic_dec_return(&page->_count) == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
INIT_LIST_HEAD(&page->lru);
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
__free_pages_bootmem(page, 0);
}
}
static void register_page_bootmem_info_section(unsigned long start_pfn)
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
{
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++)
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
memory hotplug: register section/node id to free This patch set is to free pages which is allocated by bootmem for memory-hotremove. Some structures of memory management are allocated by bootmem. ex) memmap, etc. To remove memory physically, some of them must be freed according to circumstance. This patch set makes basis to free those pages, and free memmaps. Basic my idea is using remain members of struct page to remember information of users of bootmem (section number or node id). When the section is removing, kernel can confirm it. By this information, some issues can be solved. 1) When the memmap of removing section is allocated on other section by bootmem, it should/can be free. 2) When the memmap of removing section is allocated on the same section, it shouldn't be freed. Because the section has to be logical memory offlined already and all pages must be isolated against page allocater. If it is freed, page allocator may use it which will be removed physically soon. 3) When removing section has other section's memmap, kernel will be able to show easily which section should be removed before it for user. (Not implemented yet) 4) When the above case 2), the page isolation will be able to check and skip memmap's page when logical memory offline (offline_pages()). Current page isolation code fails in this case because this page is just reserved page and it can't distinguish this pages can be removed or not. But, it will be able to do by this patch. (Not implemented yet.) 5) The node information like pgdat has similar issues. But, this will be able to be solved too by this. (Not implemented yet, but, remembering node id in the pages.) Fortunately, current bootmem allocator just keeps PageReserved flags, and doesn't use any other members of page struct. The users of bootmem doesn't use them too. This patch: This is to register information which is node or section's id. Kernel can distinguish which node/section uses the pages allcated by bootmem. This is basis for hot-remove sections or nodes. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 11:13:31 +02:00
}
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 */
memory_hotplug: always initialize pageblock bitmap Trying to online a new memory section that was added via memory hotplug sometimes results in crashes when the new pages are added via __free_page. Reason for that is that the pageblock bitmap isn't initialized and hence contains random stuff. That means that get_pageblock_migratetype() returns also random stuff and therefore list_add(&page->lru, &zone->free_area[order].free_list[migratetype]); in __free_one_page() tries to do a list_add to something that isn't even necessarily a list. This happens since 86051ca5eaf5e560113ec7673462804c54284456 ("mm: fix usemap initialization") which makes sure that the pageblock bitmap gets only initialized for pages present in a zone. Unfortunately for hot-added memory the zones "grow" after the memmap and the pageblock memmap have been initialized. Which means that the new pages have an unitialized bitmap. To solve this the calls to grow_zone_span() and grow_pgdat_span() are moved to __add_zone() just before the initialization happens. The patch also moves the two functions since __add_zone() is the only caller and I didn't want to add a forward declaration. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-15 01:05:52 +02:00
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;
}
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
int nid = pgdat->node_id;
int zone_type;
memory_hotplug: always initialize pageblock bitmap Trying to online a new memory section that was added via memory hotplug sometimes results in crashes when the new pages are added via __free_page. Reason for that is that the pageblock bitmap isn't initialized and hence contains random stuff. That means that get_pageblock_migratetype() returns also random stuff and therefore list_add(&page->lru, &zone->free_area[order].free_list[migratetype]); in __free_one_page() tries to do a list_add to something that isn't even necessarily a list. This happens since 86051ca5eaf5e560113ec7673462804c54284456 ("mm: fix usemap initialization") which makes sure that the pageblock bitmap gets only initialized for pages present in a zone. Unfortunately for hot-added memory the zones "grow" after the memmap and the pageblock memmap have been initialized. Which means that the new pages have an unitialized bitmap. To solve this the calls to grow_zone_span() and grow_pgdat_span() are moved to __add_zone() just before the initialization happens. The patch also moves the two functions since __add_zone() is the only caller and I didn't want to add a forward declaration. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-15 01:05:52 +02:00
unsigned long flags;
zone_type = zone - pgdat->node_zones;
memory_hotplug: always initialize pageblock bitmap Trying to online a new memory section that was added via memory hotplug sometimes results in crashes when the new pages are added via __free_page. Reason for that is that the pageblock bitmap isn't initialized and hence contains random stuff. That means that get_pageblock_migratetype() returns also random stuff and therefore list_add(&page->lru, &zone->free_area[order].free_list[migratetype]); in __free_one_page() tries to do a list_add to something that isn't even necessarily a list. This happens since 86051ca5eaf5e560113ec7673462804c54284456 ("mm: fix usemap initialization") which makes sure that the pageblock bitmap gets only initialized for pages present in a zone. Unfortunately for hot-added memory the zones "grow" after the memmap and the pageblock memmap have been initialized. Which means that the new pages have an unitialized bitmap. To solve this the calls to grow_zone_span() and grow_pgdat_span() are moved to __add_zone() just before the initialization happens. The patch also moves the two functions since __add_zone() is the only caller and I didn't want to add a forward declaration. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-15 01:05:52 +02:00
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);
memmap_init_zone(nr_pages, nid, zone_type,
phys_start_pfn, MEMMAP_HOTPLUG);
return 0;
}
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:14 +01:00
static int __meminit __add_section(int nid, struct zone *zone,
unsigned long phys_start_pfn)
{
int nr_pages = PAGES_PER_SECTION;
int ret;
if (pfn_valid(phys_start_pfn))
return -EEXIST;
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
if (ret < 0)
return ret;
ret = __add_zone(zone, phys_start_pfn);
if (ret < 0)
return ret;
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:14 +01:00
return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
}
#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
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;
}
#endif
/*
* 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.
*/
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:14 +01:00
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++) {
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:14 +01:00
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);
/**
* __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);
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;
release_mem_region(pfn << PAGE_SHIFT,
PAGES_PER_SECTION << PAGE_SHIFT);
ret = __remove_section(zone, __pfn_to_section(pfn));
if (ret)
break;
}
return ret;
}
EXPORT_SYMBOL_GPL(__remove_pages);
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)
{
unsigned long pfn = page_to_pfn(page);
if (pfn >= num_physpages)
num_physpages = pfn + 1;
}
EXPORT_SYMBOL_GPL(__online_page_set_limits);
void __online_page_increment_counters(struct page *page)
{
totalram_pages++;
#ifdef CONFIG_HIGHMEM
if (PageHighMem(page))
totalhigh_pages++;
#endif
}
EXPORT_SYMBOL_GPL(__online_page_increment_counters);
void __online_page_free(struct page *page)
{
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
}
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);
}
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg)
{
unsigned long i;
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_callback)(page);
onlined_pages++;
}
*(unsigned long *)arg = onlined_pages;
return 0;
}
int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
{
unsigned long onlined_pages = 0;
struct zone *zone;
int need_zonelists_rebuild = 0;
int nid;
int ret;
struct memory_notify arg;
lock_memory_hotplug();
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;
ret = memory_notify(MEM_GOING_ONLINE, &arg);
ret = notifier_to_errno(ret);
if (ret) {
memory_notify(MEM_CANCEL_ONLINE, &arg);
unlock_memory_hotplug();
return ret;
}
/*
* 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));
/*
* 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.
*/
mutex_lock(&zonelists_mutex);
if (!populated_zone(zone))
need_zonelists_rebuild = 1;
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
online_pages_range);
if (ret) {
mutex_unlock(&zonelists_mutex);
printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages)
<< PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_ONLINE, &arg);
unlock_memory_hotplug();
return ret;
}
zone->present_pages += onlined_pages;
zone->zone_pgdat->node_present_pages += onlined_pages;
mm/hotplug: correctly add new zone to all other nodes' zone lists When online_pages() is called to add new memory to an empty zone, it rebuilds all zone lists by calling build_all_zonelists(). But there's a bug which prevents the new zone to be added to other nodes' zone lists. online_pages() { build_all_zonelists() ..... node_set_state(zone_to_nid(zone), N_HIGH_MEMORY) } Here the node of the zone is put into N_HIGH_MEMORY state after calling build_all_zonelists(), but build_all_zonelists() only adds zones from nodes in N_HIGH_MEMORY state to the fallback zone lists. build_all_zonelists() ->__build_all_zonelists() ->build_zonelists() ->find_next_best_node() ->for_each_node_state(n, N_HIGH_MEMORY) So memory in the new zone will never be used by other nodes, and it may cause strange behavor when system is under memory pressure. So put node into N_HIGH_MEMORY state before calling build_all_zonelists(). Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Jiang Liu <liuj97@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Keping Chen <chenkeping@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 01:43:30 +02:00
if (onlined_pages) {
node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
if (need_zonelists_rebuild)
build_all_zonelists(NULL, zone);
else
zone_pcp_update(zone);
}
mutex_unlock(&zonelists_mutex);
init_per_zone_wmark_min();
mm/hotplug: correctly add new zone to all other nodes' zone lists When online_pages() is called to add new memory to an empty zone, it rebuilds all zone lists by calling build_all_zonelists(). But there's a bug which prevents the new zone to be added to other nodes' zone lists. online_pages() { build_all_zonelists() ..... node_set_state(zone_to_nid(zone), N_HIGH_MEMORY) } Here the node of the zone is put into N_HIGH_MEMORY state after calling build_all_zonelists(), but build_all_zonelists() only adds zones from nodes in N_HIGH_MEMORY state to the fallback zone lists. build_all_zonelists() ->__build_all_zonelists() ->build_zonelists() ->find_next_best_node() ->for_each_node_state(n, N_HIGH_MEMORY) So memory in the new zone will never be used by other nodes, and it may cause strange behavor when system is under memory pressure. So put node into N_HIGH_MEMORY state before calling build_all_zonelists(). Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Jiang Liu <liuj97@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Keping Chen <chenkeping@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 01:43:30 +02:00
if (onlined_pages)
kswapd_run(zone_to_nid(zone));
mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset For each new populated zone of hotadded node, need to update its pagesets with dynamically allocated per_cpu_pageset struct for all possible CPUs: 1) Detach zone->pageset from the shared boot_pageset at end of __build_all_zonelists(). 2) Use mutex to protect zone->pageset when it's still shared in onlined_pages() Otherwises, multiple zones of different nodes would share same boot strapping boot_pageset for same CPU, which will finally cause below kernel panic: ------------[ cut here ]------------ kernel BUG at mm/page_alloc.c:1239! invalid opcode: 0000 [#1] SMP ... Call Trace: [<ffffffff811300c1>] __alloc_pages_nodemask+0x131/0x7b0 [<ffffffff81162e67>] alloc_pages_current+0x87/0xd0 [<ffffffff81128407>] __page_cache_alloc+0x67/0x70 [<ffffffff811325f0>] __do_page_cache_readahead+0x120/0x260 [<ffffffff81132751>] ra_submit+0x21/0x30 [<ffffffff811329c6>] ondemand_readahead+0x166/0x2c0 [<ffffffff81132ba0>] page_cache_async_readahead+0x80/0xa0 [<ffffffff8112a0e4>] generic_file_aio_read+0x364/0x670 [<ffffffff81266cfa>] nfs_file_read+0xca/0x130 [<ffffffff8117b20a>] do_sync_read+0xfa/0x140 [<ffffffff8117bf75>] vfs_read+0xb5/0x1a0 [<ffffffff8117c151>] sys_read+0x51/0x80 [<ffffffff8103c032>] system_call_fastpath+0x16/0x1b RIP [<ffffffff8112ff13>] get_page_from_freelist+0x883/0x900 RSP <ffff88000d1e78a8> ---[ end trace 4bda28328b9990db ] [akpm@linux-foundation.org: merge fix] Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <andi.kleen@intel.com> Reviewed-by: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-24 23:32:51 +02:00
vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
if (onlined_pages)
memory_notify(MEM_ONLINE, &arg);
unlock_memory_hotplug();
return 0;
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
{
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.*/
free_area_init_node(nid, zones_size, start_pfn, zholes_size);
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
/*
* The node we allocated has no zone fallback lists. For avoiding
* to access not-initialized zonelist, build here.
*/
mutex_lock(&zonelists_mutex);
mm/hotplug: correctly setup fallback zonelists when creating new pgdat When hotadd_new_pgdat() is called to create new pgdat for a new node, a fallback zonelist should be created for the new node. There's code to try to achieve that in hotadd_new_pgdat() as below: /* * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ mutex_lock(&zonelists_mutex); build_all_zonelists(pgdat, NULL); mutex_unlock(&zonelists_mutex); But it doesn't work as expected. When hotadd_new_pgdat() is called, the new node is still in offline state because node_set_online(nid) hasn't been called yet. And build_all_zonelists() only builds zonelists for online nodes as: for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); build_zonelists(pgdat); build_zonelist_cache(pgdat); } Though we hope to create zonelist for the new pgdat, but it doesn't. So add a new parameter "pgdat" the build_all_zonelists() to build pgdat for the new pgdat too. Signed-off-by: Jiang Liu <liuj97@gmail.com> Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Keping Chen <chenkeping@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 01:43:28 +02:00
build_all_zonelists(pgdat, NULL);
mutex_unlock(&zonelists_mutex);
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
return pgdat;
}
static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
arch_refresh_nodedata(nid, NULL);
arch_free_nodedata(pgdat);
return;
}
/*
* called by cpu_up() to online a node without onlined memory.
*/
int mem_online_node(int nid)
{
pg_data_t *pgdat;
int ret;
lock_memory_hotplug();
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_memory_hotplug();
return ret;
}
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
int __ref add_memory(int nid, u64 start, u64 size)
{
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
pg_data_t *pgdat = NULL;
int new_pgdat = 0;
struct resource *res;
int ret;
lock_memory_hotplug();
res = register_memory_resource(start, size);
ret = -EEXIST;
if (!res)
goto out;
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
ret = -ENOMEM;
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
if (!pgdat)
goto error;
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
new_pgdat = 1;
}
/* call arch's memory hotadd */
ret = arch_add_memory(nid, start, size);
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
if (ret < 0)
goto error;
/* we online node here. we can't roll back from here. */
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
node_set_online(nid);
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);
}
/* create new memmap entry */
firmware_map_add_hotplug(start, start + size, "System RAM");
goto out;
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
rollback_node_hotadd(nid, pgdat);
if (res)
release_memory_resource(res);
[PATCH] pgdat allocation for new node add (call pgdat allocation) Add node-hot-add support to add_memory(). node hotadd uses this sequence. 1. allocate pgdat. 2. refresh NODE_DATA() 3. call free_area_init_node() to initialize 4. create sysfs entry 5. add memory (old add_memory()) 6. set node online 7. run kswapd for new node. (8). update zonelist after pages are onlined. (This is already merged in -mm due to update phase is difference.) Note: To make common function as much as possible, there is 2 changes from v2. - The old add_memory(), which is defiend by each archs, is renamed to arch_add_memory(). New add_memory becomes caller of arch dependent function as a common code. - This patch changes add_memory()'s interface From: add_memory(start, end) TO : add_memory(nid, start, end). It was cause of similar code that finding node id from physical address is inside of old add_memory() on each arch. In addition, acpi memory hotplug driver can find node id easier. In v2, it must walk DSDT'S _CRS by matching physical address to get the handle of its memory device, then get _PXM and node id. Because input is just physical address. However, in v3, the acpi driver can use handle to get _PXM and node id for the new memory device. It can pass just node id to add_memory(). Fix interface of arch_add_memory() is in next patche. Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 11:53:34 +02:00
out:
unlock_memory_hotplug();
return ret;
}
EXPORT_SYMBOL_GPL(add_memory);
#ifdef CONFIG_MEMORY_HOTREMOVE
memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 06:28:19 +02:00
/*
* 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)
{
/* Ensure the starting page is pageblock-aligned */
BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
/* If the entire pageblock is free, move to the end of free page */
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);
}
memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 06:28:19 +02:00
return page + pageblock_nr_pages;
memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 06:28:19 +02:00
}
/* 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)
{
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)) {
if (!is_pageblock_removable_nolock(page))
memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 06:28:19 +02:00
return 0;
cond_resched();
memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 06:28:19 +02:00
}
/* All pageblocks in the memory block are likely to be hot-removable */
return 1;
}
/*
* 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.
*/
static unsigned long 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 *
hotremove_migrate_alloc(struct page *page, unsigned long private, int **x)
{
/* This should be improooooved!! */
return alloc_page(GFP_HIGHUSER_MOVABLE);
}
#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 (!get_page_unless_zero(page))
continue;
/*
* We can skip free pages. And we can only deal with pages on
* LRU.
*/
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:09 +02:00
ret = isolate_lru_page(page);
if (!ret) { /* Success */
put_page(page);
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 05:26:09 +02:00
list_add_tail(&page->lru, &source);
move_pages--;
inc_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
} else {
#ifdef CONFIG_DEBUG_VM
printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
pfn);
dump_page(page);
#endif
put_page(page);
/* Because we don't have big zone->lock. we should
check this again here. */
if (page_count(page)) {
not_managed++;
ret = -EBUSY;
break;
}
}
}
if (!list_empty(&source)) {
if (not_managed) {
putback_lru_pages(&source);
goto out;
}
/* this function returns # of failed pages */
ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
true, MIGRATE_SYNC);
if (ret)
putback_lru_pages(&source);
}
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)
{
walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL,
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;
ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
check_pages_isolated_cb);
if (ret < 0)
offlined = (long)ret;
return offlined;
}
static int __ref offline_pages(unsigned long start_pfn,
unsigned long end_pfn, unsigned long timeout)
{
unsigned long pfn, nr_pages, expire;
long offlined_pages;
int ret, drain, retry_max, node;
struct zone *zone;
struct memory_notify arg;
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;
lock_memory_hotplug();
zone = page_zone(pfn_to_page(start_pfn));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
if (ret)
goto out;
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;
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();
cond_resched();
drain_all_pages();
}
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();
yield();
/* drain pcp pages , this is synchrouns. */
drain_all_pages();
/* 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\n", offlined_pages);
/* Ok, all of our target is islaoted.
We cannot do rollback at this point. */
offline_isolated_pages(start_pfn, end_pfn);
/* reset pagetype flags and makes migrate type to be MOVABLE */
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
/* removal success */
zone->present_pages -= offlined_pages;
zone->zone_pgdat->node_present_pages -= offlined_pages;
totalram_pages -= offlined_pages;
init_per_zone_wmark_min();
if (!populated_zone(zone))
zone_pcp_reset(zone);
if (!node_present_pages(node)) {
node_clear_state(node, N_HIGH_MEMORY);
kswapd_stop(node);
}
vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
unlock_memory_hotplug();
return 0;
failed_removal:
printk(KERN_INFO "memory offlining [mem %#010llx-%#010llx] failed\n",
(unsigned long long) start_pfn << PAGE_SHIFT,
((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_OFFLINE, &arg);
/* pushback to free area */
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
out:
unlock_memory_hotplug();
return ret;
}
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);
}
#else
int remove_memory(u64 start, u64 size)
{
return -EINVAL;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
EXPORT_SYMBOL_GPL(remove_memory);