2005-10-30 02:16:54 +01:00
|
|
|
/*
|
|
|
|
* linux/mm/memory_hotplug.c
|
|
|
|
*
|
|
|
|
* Copyright (C)
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/config.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/bootmem.h>
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/pagevec.h>
|
|
|
|
#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>
|
2006-06-27 11:53:35 +02:00
|
|
|
#include <linux/ioport.h>
|
2005-10-30 02:16:54 +01:00
|
|
|
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
|
|
|
|
extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
|
|
|
|
unsigned long size);
|
2006-06-23 11:03:10 +02:00
|
|
|
static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
|
2005-10-30 02:16:54 +01:00
|
|
|
{
|
|
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
|
|
int nr_pages = PAGES_PER_SECTION;
|
|
|
|
int nid = pgdat->node_id;
|
|
|
|
int zone_type;
|
|
|
|
|
|
|
|
zone_type = zone - pgdat->node_zones;
|
2006-06-23 11:03:10 +02:00
|
|
|
if (!populated_zone(zone)) {
|
|
|
|
int ret = 0;
|
|
|
|
ret = init_currently_empty_zone(zone, phys_start_pfn, nr_pages);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
}
|
2005-10-30 02:16:54 +01:00
|
|
|
memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
|
|
|
|
zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
|
2006-06-23 11:03:10 +02:00
|
|
|
return 0;
|
2005-10-30 02:16:54 +01:00
|
|
|
}
|
|
|
|
|
2005-10-30 02:16:55 +01:00
|
|
|
extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
|
|
|
|
int nr_pages);
|
2005-10-30 02:16:54 +01:00
|
|
|
static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
|
|
|
|
{
|
|
|
|
int nr_pages = PAGES_PER_SECTION;
|
|
|
|
int ret;
|
|
|
|
|
2005-10-30 02:16:55 +01:00
|
|
|
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
|
2005-10-30 02:16:54 +01:00
|
|
|
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
2006-06-23 11:03:10 +02:00
|
|
|
ret = __add_zone(zone, phys_start_pfn);
|
|
|
|
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
2005-10-30 02:16:54 +01:00
|
|
|
return register_new_memory(__pfn_to_section(phys_start_pfn));
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reasonably generic function for adding memory. It is
|
|
|
|
* expected that archs that support memory hotplug will
|
|
|
|
* call this function after deciding the zone to which to
|
|
|
|
* add the new pages.
|
|
|
|
*/
|
|
|
|
int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
|
|
|
|
unsigned long nr_pages)
|
|
|
|
{
|
|
|
|
unsigned long i;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
|
|
|
|
err = __add_section(zone, phys_start_pfn + i);
|
|
|
|
|
2006-05-01 21:16:11 +02:00
|
|
|
/* We want to keep adding the rest of the
|
|
|
|
* sections if the first ones already exist
|
|
|
|
*/
|
|
|
|
if (err && (err != -EEXIST))
|
2005-10-30 02:16:54 +01:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
2006-05-01 21:16:11 +02:00
|
|
|
EXPORT_SYMBOL_GPL(__add_pages);
|
2005-10-30 02:16:54 +01:00
|
|
|
|
|
|
|
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;
|
|
|
|
|
2006-05-31 06:25:42 +02:00
|
|
|
zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
|
|
|
|
zone->zone_start_pfn;
|
2005-10-30 02:16:54 +01:00
|
|
|
|
|
|
|
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;
|
|
|
|
|
2006-05-31 06:25:42 +02:00
|
|
|
pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
|
|
|
|
pgdat->node_start_pfn;
|
2005-10-30 02:16:54 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
int online_pages(unsigned long pfn, unsigned long nr_pages)
|
|
|
|
{
|
|
|
|
unsigned long i;
|
|
|
|
unsigned long flags;
|
|
|
|
unsigned long onlined_pages = 0;
|
|
|
|
struct zone *zone;
|
2006-06-23 11:03:11 +02:00
|
|
|
int need_zonelists_rebuild = 0;
|
2005-10-30 02:16:54 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This doesn't need a lock to do pfn_to_page().
|
|
|
|
* The section can't be removed here because of the
|
|
|
|
* memory_block->state_sem.
|
|
|
|
*/
|
|
|
|
zone = page_zone(pfn_to_page(pfn));
|
|
|
|
pgdat_resize_lock(zone->zone_pgdat, &flags);
|
|
|
|
grow_zone_span(zone, pfn, pfn + nr_pages);
|
|
|
|
grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
|
|
|
|
pgdat_resize_unlock(zone->zone_pgdat, &flags);
|
|
|
|
|
2006-06-23 11:03:11 +02:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
if (!populated_zone(zone))
|
|
|
|
need_zonelists_rebuild = 1;
|
|
|
|
|
2005-10-30 02:16:54 +01:00
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
struct page *page = pfn_to_page(pfn + i);
|
|
|
|
online_page(page);
|
|
|
|
onlined_pages++;
|
|
|
|
}
|
|
|
|
zone->present_pages += onlined_pages;
|
2006-03-10 02:33:51 +01:00
|
|
|
zone->zone_pgdat->node_present_pages += onlined_pages;
|
2005-10-30 02:16:54 +01:00
|
|
|
|
2005-10-30 02:16:56 +01:00
|
|
|
setup_per_zone_pages_min();
|
|
|
|
|
2006-06-23 11:03:11 +02:00
|
|
|
if (need_zonelists_rebuild)
|
|
|
|
build_all_zonelists();
|
2006-06-23 11:03:47 +02:00
|
|
|
vm_total_pages = nr_free_pagecache_pages();
|
2005-10-30 02:16:54 +01:00
|
|
|
return 0;
|
|
|
|
}
|
2006-06-27 11:53:30 +02:00
|
|
|
|
[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
|
|
|
static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
|
|
|
|
{
|
|
|
|
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, pgdat, zones_size, start_pfn, zholes_size);
|
|
|
|
|
|
|
|
return pgdat;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
|
|
|
|
{
|
|
|
|
arch_refresh_nodedata(nid, NULL);
|
|
|
|
arch_free_nodedata(pgdat);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2006-06-27 11:53:35 +02:00
|
|
|
/* add this memory to iomem resource */
|
|
|
|
static void 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;
|
|
|
|
if (request_resource(&iomem_resource, res) < 0) {
|
|
|
|
printk("System RAM resource %llx - %llx cannot be added\n",
|
|
|
|
(unsigned long long)res->start, (unsigned long long)res->end);
|
|
|
|
kfree(res);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-06-27 11:53:30 +02:00
|
|
|
int 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;
|
2006-06-27 11:53:30 +02:00
|
|
|
int ret;
|
|
|
|
|
[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);
|
|
|
|
if (!pgdat)
|
|
|
|
return -ENOMEM;
|
|
|
|
new_pgdat = 1;
|
|
|
|
ret = kswapd_run(nid);
|
|
|
|
if (ret)
|
|
|
|
goto error;
|
|
|
|
}
|
|
|
|
|
2006-06-27 11:53:30 +02:00
|
|
|
/* 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 have no error path from here. */
|
|
|
|
node_set_online(nid);
|
|
|
|
|
2006-06-27 11:53:35 +02:00
|
|
|
/* register this memory as resource */
|
|
|
|
register_memory_resource(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
|
|
|
return ret;
|
|
|
|
error:
|
|
|
|
/* rollback pgdat allocation and others */
|
|
|
|
if (new_pgdat)
|
|
|
|
rollback_node_hotadd(nid, pgdat);
|
|
|
|
|
2006-06-27 11:53:30 +02:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(add_memory);
|