mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-06 18:16:39 +07:00
02b9735c12
1) ACPI-based PCI hotplug (ACPIPHP) fixes related to spurious events After the recent ACPIPHP changes we've seen some interesting breakage on a system that triggers device check notifications during boot for non-existing devices. Although those notifications are really spurious, we should be able to deal with them nevertheless and that shouldn't introduce too much overhead. Four commits to make that work properly. 2) Memory hotplug and hibernation mutual exclusion rework This was maent to be a cleanup, but it happens to fix a classical ABBA deadlock between system suspend/hibernation and ACPI memory hotplug which is possible if they are started roughly at the same time. Three commits rework memory hotplug so that it doesn't acquire pm_mutex and make hibernation use device_hotplug_lock which prevents it from racing with memory hotplug. 3) ACPI Intel LPSS (Low-Power Subsystem) driver crash fix The ACPI LPSS driver crashes during boot on Apple Macbook Air with Haswell that has slightly unusual BIOS configuration in which one of the LPSS device's _CRS method doesn't return all of the information expected by the driver. Fix from Mika Westerberg, for stable. 4) ACPICA fix related to Store->ArgX operation AML interpreter fix for obscure breakage that causes AML to be executed incorrectly on some machines (observed in practice). From Bob Moore. 5) ACPI core fix for PCI ACPI device objects lookup There still are cases in which there is more than one ACPI device object matching a given PCI device and we don't choose the one that the BIOS expects us to choose, so this makes the lookup take more criteria into account in those cases. 6) Fix to prevent cpuidle from crashing in some rare cases If the result of cpuidle_get_driver() is NULL, which can happen on some systems, cpuidle_driver_ref() will crash trying to use that pointer and the Daniel Fu's fix prevents that from happening. 7) cpufreq fixes related to CPU hotplug Stephen Boyd reported a number of concurrency problems with cpufreq related to CPU hotplug which are addressed by a series of fixes from Srivatsa S Bhat and Viresh Kumar. 8) cpufreq fix for time conversion in time_in_state attribute Time conversion carried out by cpufreq when user space attempts to read /sys/devices/system/cpu/cpu*/cpufreq/stats/time_in_state won't work correcty if cputime_t doesn't map directly to jiffies. Fix from Andreas Schwab. 9) Revert of a troublesome cpufreq commit Commit7c30ed5
(cpufreq: make sure frequency transitions are serialized) was intended to address some known concurrency problems in cpufreq related to the ordering of transitions, but unfortunately it introduced several problems of its own, so I decided to revert it now and address the original problems later in a more robust way. 10) Intel Haswell CPU models for intel_pstate from Nell Hardcastle. 11) cpufreq fixes related to system suspend/resume The recent cpufreq changes that made it preserve CPU sysfs attributes over suspend/resume cycles introduced a possible NULL pointer dereference that caused it to crash during the second attempt to suspend. Three commits from Srivatsa S Bhat fix that problem and a couple of related issues. 12) cpufreq locking fix cpufreq_policy_restore() should acquire the lock for reading, but it acquires it for writing. Fix from Lan Tianyu. / -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (GNU/Linux) iQIcBAABCAAGBQJSMbdRAAoJEKhOf7ml8uNsiFkQAKSh1iBXuiUCxBApEGZgoQio 8lmnuyWdhNQWdjZTnh7ptjpDxdrWhxcoxvoaGABU++reDObjef1QnyrQtdO3r8dl oy0C/YGh5kq5SIffIDEwPIb/ipDe/47cgRMW8iBlnViDa1MJBqICuLyefcTRIrKp QGvv0owUM2o7TXpA10+qm8zXjv6m5mu1DTtxYI+2Eodhwi54neAqb+aKMspa2thy V9KFcVv3Td4rJrNvw6BhXNM81QbaYpRxaK3DRr1T6SM++EKvbqYFA1jgW24YvqTL nrCZlDMb6KRww5DCxA/ns9Kx5H+ZyicoRwdtAM3PBYA6MGqsLqPozC/8VKV1fSvZ sgUdbUSuLqKRAkOqM1bjKAhi9PdCGBvkQAg2AqbRK6IBl4HJC8xhdb5E6eZ/J42G GyNBpKef7wVJwYKXE2hSChZ5dYjqMizNHWxFHf8Xy1dveExbQ2nmSJmaWMy2A3kx YOXFkcTV5F6GOIZB8WCRruzUalff9xal4G+iVhGF+AZIOCm7bC+FDXfwIS82uVor ej2l+uQLLZCB499IRmM6942ZIAXshmtN7eRfGtKBc6jsbSCEdQDqf1Z7oRwqAD6h WkD/k/zz30CyM8y4snOkAXkZgqAQsZodtqfowE3e9OHd51tfcNiqdht+obwCx+eD MWXc2xATMAX6NcZTXSZS =U/Jw -----END PGP SIGNATURE----- Merge tag 'pm+acpi-fixes-3.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm Pull ACPI and power management fixes from Rafael Wysocki: "All of these commits are fixes that have emerged recently and some of them fix bugs introduced during this merge window. Specifics: 1) ACPI-based PCI hotplug (ACPIPHP) fixes related to spurious events After the recent ACPIPHP changes we've seen some interesting breakage on a system that triggers device check notifications during boot for non-existing devices. Although those notifications are really spurious, we should be able to deal with them nevertheless and that shouldn't introduce too much overhead. Four commits to make that work properly. 2) Memory hotplug and hibernation mutual exclusion rework This was maent to be a cleanup, but it happens to fix a classical ABBA deadlock between system suspend/hibernation and ACPI memory hotplug which is possible if they are started roughly at the same time. Three commits rework memory hotplug so that it doesn't acquire pm_mutex and make hibernation use device_hotplug_lock which prevents it from racing with memory hotplug. 3) ACPI Intel LPSS (Low-Power Subsystem) driver crash fix The ACPI LPSS driver crashes during boot on Apple Macbook Air with Haswell that has slightly unusual BIOS configuration in which one of the LPSS device's _CRS method doesn't return all of the information expected by the driver. Fix from Mika Westerberg, for stable. 4) ACPICA fix related to Store->ArgX operation AML interpreter fix for obscure breakage that causes AML to be executed incorrectly on some machines (observed in practice). From Bob Moore. 5) ACPI core fix for PCI ACPI device objects lookup There still are cases in which there is more than one ACPI device object matching a given PCI device and we don't choose the one that the BIOS expects us to choose, so this makes the lookup take more criteria into account in those cases. 6) Fix to prevent cpuidle from crashing in some rare cases If the result of cpuidle_get_driver() is NULL, which can happen on some systems, cpuidle_driver_ref() will crash trying to use that pointer and the Daniel Fu's fix prevents that from happening. 7) cpufreq fixes related to CPU hotplug Stephen Boyd reported a number of concurrency problems with cpufreq related to CPU hotplug which are addressed by a series of fixes from Srivatsa S Bhat and Viresh Kumar. 8) cpufreq fix for time conversion in time_in_state attribute Time conversion carried out by cpufreq when user space attempts to read /sys/devices/system/cpu/cpu*/cpufreq/stats/time_in_state won't work correcty if cputime_t doesn't map directly to jiffies. Fix from Andreas Schwab. 9) Revert of a troublesome cpufreq commit Commit7c30ed5
(cpufreq: make sure frequency transitions are serialized) was intended to address some known concurrency problems in cpufreq related to the ordering of transitions, but unfortunately it introduced several problems of its own, so I decided to revert it now and address the original problems later in a more robust way. 10) Intel Haswell CPU models for intel_pstate from Nell Hardcastle. 11) cpufreq fixes related to system suspend/resume The recent cpufreq changes that made it preserve CPU sysfs attributes over suspend/resume cycles introduced a possible NULL pointer dereference that caused it to crash during the second attempt to suspend. Three commits from Srivatsa S Bhat fix that problem and a couple of related issues. 12) cpufreq locking fix cpufreq_policy_restore() should acquire the lock for reading, but it acquires it for writing. Fix from Lan Tianyu" * tag 'pm+acpi-fixes-3.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (25 commits) cpufreq: Acquire the lock in cpufreq_policy_restore() for reading cpufreq: Prevent problems in update_policy_cpu() if last_cpu == new_cpu cpufreq: Restructure if/else block to avoid unintended behavior cpufreq: Fix crash in cpufreq-stats during suspend/resume intel_pstate: Add Haswell CPU models Revert "cpufreq: make sure frequency transitions are serialized" cpufreq: Use signed type for 'ret' variable, to store negative error values cpufreq: Remove temporary fix for race between CPU hotplug and sysfs-writes cpufreq: Synchronize the cpufreq store_*() routines with CPU hotplug cpufreq: Invoke __cpufreq_remove_dev_finish() after releasing cpu_hotplug.lock cpufreq: Split __cpufreq_remove_dev() into two parts cpufreq: Fix wrong time unit conversion cpufreq: serialize calls to __cpufreq_governor() cpufreq: don't allow governor limits to be changed when it is disabled ACPI / bind: Prefer device objects with _STA to those without it ACPI / hotplug / PCI: Avoid parent bus rescans on spurious device checks ACPI / hotplug / PCI: Use _OST to notify firmware about notify status ACPI / hotplug / PCI: Avoid doing too much for spurious notifies ACPICA: Fix for a Store->ArgX when ArgX contains a reference to a field. ACPI / hotplug / PCI: Don't trim devices before scanning the namespace ...
1874 lines
47 KiB
C
1874 lines
47 KiB
C
/*
|
|
* 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 <linux/stop_machine.h>
|
|
#include <linux/hugetlb.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);
|
|
}
|
|
|
|
void unlock_memory_hotplug(void)
|
|
{
|
|
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) {
|
|
pr_debug("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
|
|
void get_page_bootmem(unsigned long info, struct page *page,
|
|
unsigned long type)
|
|
{
|
|
page->lru.next = (struct list_head *) type;
|
|
SetPagePrivate(page);
|
|
set_page_private(page, info);
|
|
atomic_inc(&page->_count);
|
|
}
|
|
|
|
void put_page_bootmem(struct page *page)
|
|
{
|
|
unsigned long type;
|
|
|
|
type = (unsigned long) page->lru.next;
|
|
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
|
|
type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
|
|
|
|
if (atomic_dec_return(&page->_count) == 1) {
|
|
ClearPagePrivate(page);
|
|
set_page_private(page, 0);
|
|
INIT_LIST_HEAD(&page->lru);
|
|
free_reserved_page(page);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
|
|
#ifndef CONFIG_SPARSEMEM_VMEMMAP
|
|
static void register_page_bootmem_info_section(unsigned long start_pfn)
|
|
{
|
|
unsigned long *usemap, mapsize, section_nr, i;
|
|
struct mem_section *ms;
|
|
struct page *page, *memmap;
|
|
|
|
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);
|
|
|
|
}
|
|
#else /* CONFIG_SPARSEMEM_VMEMMAP */
|
|
static void register_page_bootmem_info_section(unsigned long start_pfn)
|
|
{
|
|
unsigned long *usemap, mapsize, section_nr, i;
|
|
struct mem_section *ms;
|
|
struct page *page, *memmap;
|
|
|
|
if (!pfn_valid(start_pfn))
|
|
return;
|
|
|
|
section_nr = pfn_to_section_nr(start_pfn);
|
|
ms = __nr_to_section(section_nr);
|
|
|
|
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
|
|
|
|
register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
|
|
|
|
usemap = __nr_to_section(section_nr)->pageblock_flags;
|
|
page = virt_to_page(usemap);
|
|
|
|
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
|
|
|
|
for (i = 0; i < mapsize; i++, page++)
|
|
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
|
|
}
|
|
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
|
|
|
|
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_is_initialized(zone)) {
|
|
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 = pgdat_end_pfn(pgdat);
|
|
|
|
/* register section info */
|
|
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
/*
|
|
* Some platforms can assign the same pfn to multiple nodes - on
|
|
* node0 as well as nodeN. To avoid registering a pfn against
|
|
* multiple nodes we check that this pfn does not already
|
|
* reside in some other nodes.
|
|
*/
|
|
if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
|
|
register_page_bootmem_info_section(pfn);
|
|
}
|
|
}
|
|
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
|
|
|
|
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_end_pfn(zone);
|
|
if (zone_is_empty(zone) || 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 resize_zone(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
zone_span_writelock(zone);
|
|
|
|
if (end_pfn - start_pfn) {
|
|
zone->zone_start_pfn = start_pfn;
|
|
zone->spanned_pages = end_pfn - start_pfn;
|
|
} else {
|
|
/*
|
|
* make it consist as free_area_init_core(),
|
|
* if spanned_pages = 0, then keep start_pfn = 0
|
|
*/
|
|
zone->zone_start_pfn = 0;
|
|
zone->spanned_pages = 0;
|
|
}
|
|
|
|
zone_span_writeunlock(zone);
|
|
}
|
|
|
|
static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
enum zone_type zid = zone_idx(zone);
|
|
int nid = zone->zone_pgdat->node_id;
|
|
unsigned long pfn;
|
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn++)
|
|
set_page_links(pfn_to_page(pfn), zid, nid, pfn);
|
|
}
|
|
|
|
/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
|
|
* alloc_bootmem_node_nopanic() */
|
|
static int __ref ensure_zone_is_initialized(struct zone *zone,
|
|
unsigned long start_pfn, unsigned long num_pages)
|
|
{
|
|
if (!zone_is_initialized(zone))
|
|
return init_currently_empty_zone(zone, start_pfn, num_pages,
|
|
MEMMAP_HOTPLUG);
|
|
return 0;
|
|
}
|
|
|
|
static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
|
|
unsigned long start_pfn, unsigned long end_pfn)
|
|
{
|
|
int ret;
|
|
unsigned long flags;
|
|
unsigned long z1_start_pfn;
|
|
|
|
ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
|
|
if (ret)
|
|
return ret;
|
|
|
|
pgdat_resize_lock(z1->zone_pgdat, &flags);
|
|
|
|
/* can't move pfns which are higher than @z2 */
|
|
if (end_pfn > zone_end_pfn(z2))
|
|
goto out_fail;
|
|
/* the move out part must be at the left most of @z2 */
|
|
if (start_pfn > z2->zone_start_pfn)
|
|
goto out_fail;
|
|
/* must included/overlap */
|
|
if (end_pfn <= z2->zone_start_pfn)
|
|
goto out_fail;
|
|
|
|
/* use start_pfn for z1's start_pfn if z1 is empty */
|
|
if (!zone_is_empty(z1))
|
|
z1_start_pfn = z1->zone_start_pfn;
|
|
else
|
|
z1_start_pfn = start_pfn;
|
|
|
|
resize_zone(z1, z1_start_pfn, end_pfn);
|
|
resize_zone(z2, end_pfn, zone_end_pfn(z2));
|
|
|
|
pgdat_resize_unlock(z1->zone_pgdat, &flags);
|
|
|
|
fix_zone_id(z1, start_pfn, end_pfn);
|
|
|
|
return 0;
|
|
out_fail:
|
|
pgdat_resize_unlock(z1->zone_pgdat, &flags);
|
|
return -1;
|
|
}
|
|
|
|
static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
|
|
unsigned long start_pfn, unsigned long end_pfn)
|
|
{
|
|
int ret;
|
|
unsigned long flags;
|
|
unsigned long z2_end_pfn;
|
|
|
|
ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
|
|
if (ret)
|
|
return ret;
|
|
|
|
pgdat_resize_lock(z1->zone_pgdat, &flags);
|
|
|
|
/* can't move pfns which are lower than @z1 */
|
|
if (z1->zone_start_pfn > start_pfn)
|
|
goto out_fail;
|
|
/* the move out part mast at the right most of @z1 */
|
|
if (zone_end_pfn(z1) > end_pfn)
|
|
goto out_fail;
|
|
/* must included/overlap */
|
|
if (start_pfn >= zone_end_pfn(z1))
|
|
goto out_fail;
|
|
|
|
/* use end_pfn for z2's end_pfn if z2 is empty */
|
|
if (!zone_is_empty(z2))
|
|
z2_end_pfn = zone_end_pfn(z2);
|
|
else
|
|
z2_end_pfn = end_pfn;
|
|
|
|
resize_zone(z1, z1->zone_start_pfn, start_pfn);
|
|
resize_zone(z2, start_pfn, z2_end_pfn);
|
|
|
|
pgdat_resize_unlock(z1->zone_pgdat, &flags);
|
|
|
|
fix_zone_id(z2, start_pfn, end_pfn);
|
|
|
|
return 0;
|
|
out_fail:
|
|
pgdat_resize_unlock(z1->zone_pgdat, &flags);
|
|
return -1;
|
|
}
|
|
|
|
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 (!pgdat->node_spanned_pages || 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;
|
|
unsigned long flags;
|
|
int ret;
|
|
|
|
zone_type = zone - pgdat->node_zones;
|
|
ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
|
|
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;
|
|
}
|
|
|
|
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;
|
|
|
|
return register_new_memory(nid, __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 __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
|
|
unsigned long nr_pages)
|
|
{
|
|
unsigned long i;
|
|
int err = 0;
|
|
int start_sec, end_sec;
|
|
/* during initialize mem_map, align hot-added range to section */
|
|
start_sec = pfn_to_section_nr(phys_start_pfn);
|
|
end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
|
|
|
|
for (i = start_sec; i <= end_sec; i++) {
|
|
err = __add_section(nid, zone, i << PFN_SECTION_SHIFT);
|
|
|
|
/*
|
|
* EEXIST is finally dealt with by ioresource collision
|
|
* check. see add_memory() => register_memory_resource()
|
|
* Warning will be printed if there is collision.
|
|
*/
|
|
if (err && (err != -EEXIST))
|
|
break;
|
|
err = 0;
|
|
}
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__add_pages);
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
|
|
static int find_smallest_section_pfn(int nid, struct zone *zone,
|
|
unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
struct mem_section *ms;
|
|
|
|
for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
|
|
ms = __pfn_to_section(start_pfn);
|
|
|
|
if (unlikely(!valid_section(ms)))
|
|
continue;
|
|
|
|
if (unlikely(pfn_to_nid(start_pfn) != nid))
|
|
continue;
|
|
|
|
if (zone && zone != page_zone(pfn_to_page(start_pfn)))
|
|
continue;
|
|
|
|
return start_pfn;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
|
|
static int find_biggest_section_pfn(int nid, struct zone *zone,
|
|
unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
struct mem_section *ms;
|
|
unsigned long pfn;
|
|
|
|
/* pfn is the end pfn of a memory section. */
|
|
pfn = end_pfn - 1;
|
|
for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
|
|
ms = __pfn_to_section(pfn);
|
|
|
|
if (unlikely(!valid_section(ms)))
|
|
continue;
|
|
|
|
if (unlikely(pfn_to_nid(pfn) != nid))
|
|
continue;
|
|
|
|
if (zone && zone != page_zone(pfn_to_page(pfn)))
|
|
continue;
|
|
|
|
return pfn;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
unsigned long zone_start_pfn = zone->zone_start_pfn;
|
|
unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
|
|
unsigned long zone_end_pfn = z;
|
|
unsigned long pfn;
|
|
struct mem_section *ms;
|
|
int nid = zone_to_nid(zone);
|
|
|
|
zone_span_writelock(zone);
|
|
if (zone_start_pfn == start_pfn) {
|
|
/*
|
|
* If the section is smallest section in the zone, it need
|
|
* shrink zone->zone_start_pfn and zone->zone_spanned_pages.
|
|
* In this case, we find second smallest valid mem_section
|
|
* for shrinking zone.
|
|
*/
|
|
pfn = find_smallest_section_pfn(nid, zone, end_pfn,
|
|
zone_end_pfn);
|
|
if (pfn) {
|
|
zone->zone_start_pfn = pfn;
|
|
zone->spanned_pages = zone_end_pfn - pfn;
|
|
}
|
|
} else if (zone_end_pfn == end_pfn) {
|
|
/*
|
|
* If the section is biggest section in the zone, it need
|
|
* shrink zone->spanned_pages.
|
|
* In this case, we find second biggest valid mem_section for
|
|
* shrinking zone.
|
|
*/
|
|
pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
|
|
start_pfn);
|
|
if (pfn)
|
|
zone->spanned_pages = pfn - zone_start_pfn + 1;
|
|
}
|
|
|
|
/*
|
|
* The section is not biggest or smallest mem_section in the zone, it
|
|
* only creates a hole in the zone. So in this case, we need not
|
|
* change the zone. But perhaps, the zone has only hole data. Thus
|
|
* it check the zone has only hole or not.
|
|
*/
|
|
pfn = zone_start_pfn;
|
|
for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
|
|
ms = __pfn_to_section(pfn);
|
|
|
|
if (unlikely(!valid_section(ms)))
|
|
continue;
|
|
|
|
if (page_zone(pfn_to_page(pfn)) != zone)
|
|
continue;
|
|
|
|
/* If the section is current section, it continues the loop */
|
|
if (start_pfn == pfn)
|
|
continue;
|
|
|
|
/* If we find valid section, we have nothing to do */
|
|
zone_span_writeunlock(zone);
|
|
return;
|
|
}
|
|
|
|
/* The zone has no valid section */
|
|
zone->zone_start_pfn = 0;
|
|
zone->spanned_pages = 0;
|
|
zone_span_writeunlock(zone);
|
|
}
|
|
|
|
static void shrink_pgdat_span(struct pglist_data *pgdat,
|
|
unsigned long start_pfn, unsigned long end_pfn)
|
|
{
|
|
unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
|
|
unsigned long pgdat_end_pfn =
|
|
pgdat->node_start_pfn + pgdat->node_spanned_pages;
|
|
unsigned long pfn;
|
|
struct mem_section *ms;
|
|
int nid = pgdat->node_id;
|
|
|
|
if (pgdat_start_pfn == start_pfn) {
|
|
/*
|
|
* If the section is smallest section in the pgdat, it need
|
|
* shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
|
|
* In this case, we find second smallest valid mem_section
|
|
* for shrinking zone.
|
|
*/
|
|
pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
|
|
pgdat_end_pfn);
|
|
if (pfn) {
|
|
pgdat->node_start_pfn = pfn;
|
|
pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
|
|
}
|
|
} else if (pgdat_end_pfn == end_pfn) {
|
|
/*
|
|
* If the section is biggest section in the pgdat, it need
|
|
* shrink pgdat->node_spanned_pages.
|
|
* In this case, we find second biggest valid mem_section for
|
|
* shrinking zone.
|
|
*/
|
|
pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
|
|
start_pfn);
|
|
if (pfn)
|
|
pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
|
|
}
|
|
|
|
/*
|
|
* If the section is not biggest or smallest mem_section in the pgdat,
|
|
* it only creates a hole in the pgdat. So in this case, we need not
|
|
* change the pgdat.
|
|
* But perhaps, the pgdat has only hole data. Thus it check the pgdat
|
|
* has only hole or not.
|
|
*/
|
|
pfn = pgdat_start_pfn;
|
|
for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
|
|
ms = __pfn_to_section(pfn);
|
|
|
|
if (unlikely(!valid_section(ms)))
|
|
continue;
|
|
|
|
if (pfn_to_nid(pfn) != nid)
|
|
continue;
|
|
|
|
/* If the section is current section, it continues the loop */
|
|
if (start_pfn == pfn)
|
|
continue;
|
|
|
|
/* If we find valid section, we have nothing to do */
|
|
return;
|
|
}
|
|
|
|
/* The pgdat has no valid section */
|
|
pgdat->node_start_pfn = 0;
|
|
pgdat->node_spanned_pages = 0;
|
|
}
|
|
|
|
static void __remove_zone(struct zone *zone, unsigned long start_pfn)
|
|
{
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
int nr_pages = PAGES_PER_SECTION;
|
|
int zone_type;
|
|
unsigned long flags;
|
|
|
|
zone_type = zone - pgdat->node_zones;
|
|
|
|
pgdat_resize_lock(zone->zone_pgdat, &flags);
|
|
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
|
|
shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
|
|
pgdat_resize_unlock(zone->zone_pgdat, &flags);
|
|
}
|
|
|
|
static int __remove_section(struct zone *zone, struct mem_section *ms)
|
|
{
|
|
unsigned long start_pfn;
|
|
int scn_nr;
|
|
int ret = -EINVAL;
|
|
|
|
if (!valid_section(ms))
|
|
return ret;
|
|
|
|
ret = unregister_memory_section(ms);
|
|
if (ret)
|
|
return ret;
|
|
|
|
scn_nr = __section_nr(ms);
|
|
start_pfn = section_nr_to_pfn(scn_nr);
|
|
__remove_zone(zone, start_pfn);
|
|
|
|
sparse_remove_one_section(zone, ms);
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* __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;
|
|
int sections_to_remove;
|
|
resource_size_t start, size;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* We can only remove entire sections
|
|
*/
|
|
BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
|
|
BUG_ON(nr_pages % PAGES_PER_SECTION);
|
|
|
|
start = phys_start_pfn << PAGE_SHIFT;
|
|
size = nr_pages * PAGE_SIZE;
|
|
ret = release_mem_region_adjustable(&iomem_resource, start, size);
|
|
if (ret) {
|
|
resource_size_t endres = start + size - 1;
|
|
|
|
pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
|
|
&start, &endres, ret);
|
|
}
|
|
|
|
sections_to_remove = nr_pages / PAGES_PER_SECTION;
|
|
for (i = 0; i < sections_to_remove; i++) {
|
|
unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
|
|
ret = __remove_section(zone, __pfn_to_section(pfn));
|
|
if (ret)
|
|
break;
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__remove_pages);
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
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)
|
|
{
|
|
}
|
|
EXPORT_SYMBOL_GPL(__online_page_set_limits);
|
|
|
|
void __online_page_increment_counters(struct page *page)
|
|
{
|
|
adjust_managed_page_count(page, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__online_page_increment_counters);
|
|
|
|
void __online_page_free(struct page *page)
|
|
{
|
|
__free_reserved_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;
|
|
}
|
|
|
|
#ifdef CONFIG_MOVABLE_NODE
|
|
/*
|
|
* When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have
|
|
* normal memory.
|
|
*/
|
|
static bool can_online_high_movable(struct zone *zone)
|
|
{
|
|
return true;
|
|
}
|
|
#else /* CONFIG_MOVABLE_NODE */
|
|
/* ensure every online node has NORMAL memory */
|
|
static bool can_online_high_movable(struct zone *zone)
|
|
{
|
|
return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
|
|
}
|
|
#endif /* CONFIG_MOVABLE_NODE */
|
|
|
|
/* check which state of node_states will be changed when online memory */
|
|
static void node_states_check_changes_online(unsigned long nr_pages,
|
|
struct zone *zone, struct memory_notify *arg)
|
|
{
|
|
int nid = zone_to_nid(zone);
|
|
enum zone_type zone_last = ZONE_NORMAL;
|
|
|
|
/*
|
|
* If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_NORMAL,
|
|
* set zone_last to ZONE_NORMAL.
|
|
*
|
|
* If we don't have HIGHMEM nor movable node,
|
|
* node_states[N_NORMAL_MEMORY] contains nodes which have zones of
|
|
* 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
|
|
*/
|
|
if (N_MEMORY == N_NORMAL_MEMORY)
|
|
zone_last = ZONE_MOVABLE;
|
|
|
|
/*
|
|
* if the memory to be online is in a zone of 0...zone_last, and
|
|
* the zones of 0...zone_last don't have memory before online, we will
|
|
* need to set the node to node_states[N_NORMAL_MEMORY] after
|
|
* the memory is online.
|
|
*/
|
|
if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
|
|
arg->status_change_nid_normal = nid;
|
|
else
|
|
arg->status_change_nid_normal = -1;
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
/*
|
|
* If we have movable node, node_states[N_HIGH_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_HIGHMEM,
|
|
* set zone_last to ZONE_HIGHMEM.
|
|
*
|
|
* If we don't have movable node, node_states[N_NORMAL_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_MOVABLE,
|
|
* set zone_last to ZONE_MOVABLE.
|
|
*/
|
|
zone_last = ZONE_HIGHMEM;
|
|
if (N_MEMORY == N_HIGH_MEMORY)
|
|
zone_last = ZONE_MOVABLE;
|
|
|
|
if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
|
|
arg->status_change_nid_high = nid;
|
|
else
|
|
arg->status_change_nid_high = -1;
|
|
#else
|
|
arg->status_change_nid_high = arg->status_change_nid_normal;
|
|
#endif
|
|
|
|
/*
|
|
* if the node don't have memory befor online, we will need to
|
|
* set the node to node_states[N_MEMORY] after the memory
|
|
* is online.
|
|
*/
|
|
if (!node_state(nid, N_MEMORY))
|
|
arg->status_change_nid = nid;
|
|
else
|
|
arg->status_change_nid = -1;
|
|
}
|
|
|
|
static void node_states_set_node(int node, struct memory_notify *arg)
|
|
{
|
|
if (arg->status_change_nid_normal >= 0)
|
|
node_set_state(node, N_NORMAL_MEMORY);
|
|
|
|
if (arg->status_change_nid_high >= 0)
|
|
node_set_state(node, N_HIGH_MEMORY);
|
|
|
|
node_set_state(node, N_MEMORY);
|
|
}
|
|
|
|
|
|
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
|
|
{
|
|
unsigned long flags;
|
|
unsigned long onlined_pages = 0;
|
|
struct zone *zone;
|
|
int need_zonelists_rebuild = 0;
|
|
int nid;
|
|
int ret;
|
|
struct memory_notify arg;
|
|
|
|
lock_memory_hotplug();
|
|
/*
|
|
* 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 ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
|
|
!can_online_high_movable(zone)) {
|
|
unlock_memory_hotplug();
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
|
|
if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
|
|
unlock_memory_hotplug();
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
|
|
if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
|
|
unlock_memory_hotplug();
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
|
|
/* Previous code may changed the zone of the pfn range */
|
|
zone = page_zone(pfn_to_page(pfn));
|
|
|
|
arg.start_pfn = pfn;
|
|
arg.nr_pages = nr_pages;
|
|
node_states_check_changes_online(nr_pages, zone, &arg);
|
|
|
|
nid = page_to_nid(pfn_to_page(pfn));
|
|
|
|
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;
|
|
}
|
|
/*
|
|
* 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;
|
|
build_all_zonelists(NULL, zone);
|
|
}
|
|
|
|
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
|
|
online_pages_range);
|
|
if (ret) {
|
|
if (need_zonelists_rebuild)
|
|
zone_pcp_reset(zone);
|
|
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;
|
|
|
|
pgdat_resize_lock(zone->zone_pgdat, &flags);
|
|
zone->zone_pgdat->node_present_pages += onlined_pages;
|
|
pgdat_resize_unlock(zone->zone_pgdat, &flags);
|
|
|
|
if (onlined_pages) {
|
|
node_states_set_node(zone_to_nid(zone), &arg);
|
|
if (need_zonelists_rebuild)
|
|
build_all_zonelists(NULL, NULL);
|
|
else
|
|
zone_pcp_update(zone);
|
|
}
|
|
|
|
mutex_unlock(&zonelists_mutex);
|
|
|
|
init_per_zone_wmark_min();
|
|
|
|
if (onlined_pages)
|
|
kswapd_run(zone_to_nid(zone));
|
|
|
|
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)
|
|
{
|
|
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 = NODE_DATA(nid);
|
|
if (!pgdat) {
|
|
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);
|
|
|
|
/*
|
|
* 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);
|
|
|
|
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;
|
|
}
|
|
|
|
static int check_hotplug_memory_range(u64 start, u64 size)
|
|
{
|
|
u64 start_pfn = start >> PAGE_SHIFT;
|
|
u64 nr_pages = size >> PAGE_SHIFT;
|
|
|
|
/* Memory range must be aligned with section */
|
|
if ((start_pfn & ~PAGE_SECTION_MASK) ||
|
|
(nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
|
|
pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
|
|
(unsigned long long)start,
|
|
(unsigned long long)size);
|
|
return -EINVAL;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
|
|
int __ref add_memory(int nid, u64 start, u64 size)
|
|
{
|
|
pg_data_t *pgdat = NULL;
|
|
bool new_pgdat;
|
|
bool new_node;
|
|
struct resource *res;
|
|
int ret;
|
|
|
|
ret = check_hotplug_memory_range(start, size);
|
|
if (ret)
|
|
return ret;
|
|
|
|
lock_memory_hotplug();
|
|
|
|
res = register_memory_resource(start, size);
|
|
ret = -EEXIST;
|
|
if (!res)
|
|
goto out;
|
|
|
|
{ /* Stupid hack to suppress address-never-null warning */
|
|
void *p = NODE_DATA(nid);
|
|
new_pgdat = !p;
|
|
}
|
|
new_node = !node_online(nid);
|
|
if (new_node) {
|
|
pgdat = hotadd_new_pgdat(nid, start);
|
|
ret = -ENOMEM;
|
|
if (!pgdat)
|
|
goto error;
|
|
}
|
|
|
|
/* call arch's memory hotadd */
|
|
ret = arch_add_memory(nid, start, size);
|
|
|
|
if (ret < 0)
|
|
goto error;
|
|
|
|
/* we online node here. we can't roll back from here. */
|
|
node_set_online(nid);
|
|
|
|
if (new_node) {
|
|
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;
|
|
|
|
error:
|
|
/* rollback pgdat allocation and others */
|
|
if (new_pgdat)
|
|
rollback_node_hotadd(nid, pgdat);
|
|
release_memory_resource(res);
|
|
|
|
out:
|
|
unlock_memory_hotplug();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(add_memory);
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
return page + pageblock_nr_pages;
|
|
}
|
|
|
|
/* 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))
|
|
return 0;
|
|
cond_resched();
|
|
}
|
|
|
|
/* 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;
|
|
}
|
|
|
|
/*
|
|
* Scan pfn range [start,end) to find movable/migratable pages (LRU pages
|
|
* and hugepages). We scan pfn because it's much easier than scanning over
|
|
* linked list. This function returns the pfn of the first found movable
|
|
* page if it's found, otherwise 0.
|
|
*/
|
|
static unsigned long scan_movable_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;
|
|
if (PageHuge(page)) {
|
|
if (is_hugepage_active(page))
|
|
return pfn;
|
|
else
|
|
pfn = round_up(pfn + 1,
|
|
1 << compound_order(page)) - 1;
|
|
}
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
#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 (PageHuge(page)) {
|
|
struct page *head = compound_head(page);
|
|
pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
|
|
if (compound_order(head) > PFN_SECTION_SHIFT) {
|
|
ret = -EBUSY;
|
|
break;
|
|
}
|
|
if (isolate_huge_page(page, &source))
|
|
move_pages -= 1 << compound_order(head);
|
|
continue;
|
|
}
|
|
|
|
if (!get_page_unless_zero(page))
|
|
continue;
|
|
/*
|
|
* We can skip free pages. And we can only deal with pages on
|
|
* LRU.
|
|
*/
|
|
ret = isolate_lru_page(page);
|
|
if (!ret) { /* Success */
|
|
put_page(page);
|
|
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_movable_pages(&source);
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* alloc_migrate_target should be improooooved!!
|
|
* migrate_pages returns # of failed pages.
|
|
*/
|
|
ret = migrate_pages(&source, alloc_migrate_target, 0,
|
|
MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
|
|
if (ret)
|
|
putback_movable_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, true);
|
|
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;
|
|
}
|
|
|
|
#ifdef CONFIG_MOVABLE_NODE
|
|
/*
|
|
* When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have
|
|
* normal memory.
|
|
*/
|
|
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
|
|
{
|
|
return true;
|
|
}
|
|
#else /* CONFIG_MOVABLE_NODE */
|
|
/* ensure the node has NORMAL memory if it is still online */
|
|
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
|
|
{
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
unsigned long present_pages = 0;
|
|
enum zone_type zt;
|
|
|
|
for (zt = 0; zt <= ZONE_NORMAL; zt++)
|
|
present_pages += pgdat->node_zones[zt].present_pages;
|
|
|
|
if (present_pages > nr_pages)
|
|
return true;
|
|
|
|
present_pages = 0;
|
|
for (; zt <= ZONE_MOVABLE; zt++)
|
|
present_pages += pgdat->node_zones[zt].present_pages;
|
|
|
|
/*
|
|
* we can't offline the last normal memory until all
|
|
* higher memory is offlined.
|
|
*/
|
|
return present_pages == 0;
|
|
}
|
|
#endif /* CONFIG_MOVABLE_NODE */
|
|
|
|
/* check which state of node_states will be changed when offline memory */
|
|
static void node_states_check_changes_offline(unsigned long nr_pages,
|
|
struct zone *zone, struct memory_notify *arg)
|
|
{
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
unsigned long present_pages = 0;
|
|
enum zone_type zt, zone_last = ZONE_NORMAL;
|
|
|
|
/*
|
|
* If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_NORMAL,
|
|
* set zone_last to ZONE_NORMAL.
|
|
*
|
|
* If we don't have HIGHMEM nor movable node,
|
|
* node_states[N_NORMAL_MEMORY] contains nodes which have zones of
|
|
* 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
|
|
*/
|
|
if (N_MEMORY == N_NORMAL_MEMORY)
|
|
zone_last = ZONE_MOVABLE;
|
|
|
|
/*
|
|
* check whether node_states[N_NORMAL_MEMORY] will be changed.
|
|
* If the memory to be offline is in a zone of 0...zone_last,
|
|
* and it is the last present memory, 0...zone_last will
|
|
* become empty after offline , thus we can determind we will
|
|
* need to clear the node from node_states[N_NORMAL_MEMORY].
|
|
*/
|
|
for (zt = 0; zt <= zone_last; zt++)
|
|
present_pages += pgdat->node_zones[zt].present_pages;
|
|
if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
|
|
arg->status_change_nid_normal = zone_to_nid(zone);
|
|
else
|
|
arg->status_change_nid_normal = -1;
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
/*
|
|
* If we have movable node, node_states[N_HIGH_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_HIGHMEM,
|
|
* set zone_last to ZONE_HIGHMEM.
|
|
*
|
|
* If we don't have movable node, node_states[N_NORMAL_MEMORY]
|
|
* contains nodes which have zones of 0...ZONE_MOVABLE,
|
|
* set zone_last to ZONE_MOVABLE.
|
|
*/
|
|
zone_last = ZONE_HIGHMEM;
|
|
if (N_MEMORY == N_HIGH_MEMORY)
|
|
zone_last = ZONE_MOVABLE;
|
|
|
|
for (; zt <= zone_last; zt++)
|
|
present_pages += pgdat->node_zones[zt].present_pages;
|
|
if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
|
|
arg->status_change_nid_high = zone_to_nid(zone);
|
|
else
|
|
arg->status_change_nid_high = -1;
|
|
#else
|
|
arg->status_change_nid_high = arg->status_change_nid_normal;
|
|
#endif
|
|
|
|
/*
|
|
* node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
|
|
*/
|
|
zone_last = ZONE_MOVABLE;
|
|
|
|
/*
|
|
* check whether node_states[N_HIGH_MEMORY] will be changed
|
|
* If we try to offline the last present @nr_pages from the node,
|
|
* we can determind we will need to clear the node from
|
|
* node_states[N_HIGH_MEMORY].
|
|
*/
|
|
for (; zt <= zone_last; zt++)
|
|
present_pages += pgdat->node_zones[zt].present_pages;
|
|
if (nr_pages >= present_pages)
|
|
arg->status_change_nid = zone_to_nid(zone);
|
|
else
|
|
arg->status_change_nid = -1;
|
|
}
|
|
|
|
static void node_states_clear_node(int node, struct memory_notify *arg)
|
|
{
|
|
if (arg->status_change_nid_normal >= 0)
|
|
node_clear_state(node, N_NORMAL_MEMORY);
|
|
|
|
if ((N_MEMORY != N_NORMAL_MEMORY) &&
|
|
(arg->status_change_nid_high >= 0))
|
|
node_clear_state(node, N_HIGH_MEMORY);
|
|
|
|
if ((N_MEMORY != N_HIGH_MEMORY) &&
|
|
(arg->status_change_nid >= 0))
|
|
node_clear_state(node, N_MEMORY);
|
|
}
|
|
|
|
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;
|
|
unsigned long flags;
|
|
struct zone *zone;
|
|
struct memory_notify arg;
|
|
|
|
/* 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;
|
|
|
|
ret = -EINVAL;
|
|
if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
|
|
goto out;
|
|
|
|
/* set above range as isolated */
|
|
ret = start_isolate_page_range(start_pfn, end_pfn,
|
|
MIGRATE_MOVABLE, true);
|
|
if (ret)
|
|
goto out;
|
|
|
|
arg.start_pfn = start_pfn;
|
|
arg.nr_pages = nr_pages;
|
|
node_states_check_changes_offline(nr_pages, zone, &arg);
|
|
|
|
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_movable_pages(start_pfn, end_pfn);
|
|
if (pfn) { /* We have movable pages */
|
|
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 asynchronous... */
|
|
lru_add_drain_all();
|
|
yield();
|
|
/* drain pcp pages, this is synchronous. */
|
|
drain_all_pages();
|
|
/*
|
|
* dissolve free hugepages in the memory block before doing offlining
|
|
* actually in order to make hugetlbfs's object counting consistent.
|
|
*/
|
|
dissolve_free_huge_pages(start_pfn, end_pfn);
|
|
/* 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 isolated.
|
|
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 */
|
|
adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
|
|
zone->present_pages -= offlined_pages;
|
|
|
|
pgdat_resize_lock(zone->zone_pgdat, &flags);
|
|
zone->zone_pgdat->node_present_pages -= offlined_pages;
|
|
pgdat_resize_unlock(zone->zone_pgdat, &flags);
|
|
|
|
init_per_zone_wmark_min();
|
|
|
|
if (!populated_zone(zone)) {
|
|
zone_pcp_reset(zone);
|
|
mutex_lock(&zonelists_mutex);
|
|
build_all_zonelists(NULL, NULL);
|
|
mutex_unlock(&zonelists_mutex);
|
|
} else
|
|
zone_pcp_update(zone);
|
|
|
|
node_states_clear_node(node, &arg);
|
|
if (arg.status_change_nid >= 0)
|
|
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 offline_pages(unsigned long start_pfn, unsigned long nr_pages)
|
|
{
|
|
return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
/**
|
|
* walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
|
|
* @start_pfn: start pfn of the memory range
|
|
* @end_pfn: end pfn of the memory range
|
|
* @arg: argument passed to func
|
|
* @func: callback for each memory section walked
|
|
*
|
|
* This function walks through all present mem sections in range
|
|
* [start_pfn, end_pfn) and call func on each mem section.
|
|
*
|
|
* Returns the return value of func.
|
|
*/
|
|
int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
|
|
void *arg, int (*func)(struct memory_block *, void *))
|
|
{
|
|
struct memory_block *mem = NULL;
|
|
struct mem_section *section;
|
|
unsigned long pfn, section_nr;
|
|
int ret;
|
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
section_nr = pfn_to_section_nr(pfn);
|
|
if (!present_section_nr(section_nr))
|
|
continue;
|
|
|
|
section = __nr_to_section(section_nr);
|
|
/* same memblock? */
|
|
if (mem)
|
|
if ((section_nr >= mem->start_section_nr) &&
|
|
(section_nr <= mem->end_section_nr))
|
|
continue;
|
|
|
|
mem = find_memory_block_hinted(section, mem);
|
|
if (!mem)
|
|
continue;
|
|
|
|
ret = func(mem, arg);
|
|
if (ret) {
|
|
kobject_put(&mem->dev.kobj);
|
|
return ret;
|
|
}
|
|
}
|
|
|
|
if (mem)
|
|
kobject_put(&mem->dev.kobj);
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
|
|
{
|
|
int ret = !is_memblock_offlined(mem);
|
|
|
|
if (unlikely(ret)) {
|
|
phys_addr_t beginpa, endpa;
|
|
|
|
beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
|
|
endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1;
|
|
pr_warn("removing memory fails, because memory "
|
|
"[%pa-%pa] is onlined\n",
|
|
&beginpa, &endpa);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int check_cpu_on_node(pg_data_t *pgdat)
|
|
{
|
|
int cpu;
|
|
|
|
for_each_present_cpu(cpu) {
|
|
if (cpu_to_node(cpu) == pgdat->node_id)
|
|
/*
|
|
* the cpu on this node isn't removed, and we can't
|
|
* offline this node.
|
|
*/
|
|
return -EBUSY;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void unmap_cpu_on_node(pg_data_t *pgdat)
|
|
{
|
|
#ifdef CONFIG_ACPI_NUMA
|
|
int cpu;
|
|
|
|
for_each_possible_cpu(cpu)
|
|
if (cpu_to_node(cpu) == pgdat->node_id)
|
|
numa_clear_node(cpu);
|
|
#endif
|
|
}
|
|
|
|
static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
|
|
{
|
|
int ret;
|
|
|
|
ret = check_cpu_on_node(pgdat);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/*
|
|
* the node will be offlined when we come here, so we can clear
|
|
* the cpu_to_node() now.
|
|
*/
|
|
|
|
unmap_cpu_on_node(pgdat);
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* try_offline_node
|
|
*
|
|
* Offline a node if all memory sections and cpus of the node are removed.
|
|
*
|
|
* NOTE: The caller must call lock_device_hotplug() to serialize hotplug
|
|
* and online/offline operations before this call.
|
|
*/
|
|
void try_offline_node(int nid)
|
|
{
|
|
pg_data_t *pgdat = NODE_DATA(nid);
|
|
unsigned long start_pfn = pgdat->node_start_pfn;
|
|
unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
|
|
unsigned long pfn;
|
|
struct page *pgdat_page = virt_to_page(pgdat);
|
|
int i;
|
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
unsigned long section_nr = pfn_to_section_nr(pfn);
|
|
|
|
if (!present_section_nr(section_nr))
|
|
continue;
|
|
|
|
if (pfn_to_nid(pfn) != nid)
|
|
continue;
|
|
|
|
/*
|
|
* some memory sections of this node are not removed, and we
|
|
* can't offline node now.
|
|
*/
|
|
return;
|
|
}
|
|
|
|
if (check_and_unmap_cpu_on_node(pgdat))
|
|
return;
|
|
|
|
/*
|
|
* all memory/cpu of this node are removed, we can offline this
|
|
* node now.
|
|
*/
|
|
node_set_offline(nid);
|
|
unregister_one_node(nid);
|
|
|
|
if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page))
|
|
/* node data is allocated from boot memory */
|
|
return;
|
|
|
|
/* free waittable in each zone */
|
|
for (i = 0; i < MAX_NR_ZONES; i++) {
|
|
struct zone *zone = pgdat->node_zones + i;
|
|
|
|
/*
|
|
* wait_table may be allocated from boot memory,
|
|
* here only free if it's allocated by vmalloc.
|
|
*/
|
|
if (is_vmalloc_addr(zone->wait_table))
|
|
vfree(zone->wait_table);
|
|
}
|
|
|
|
/*
|
|
* Since there is no way to guarentee the address of pgdat/zone is not
|
|
* on stack of any kernel threads or used by other kernel objects
|
|
* without reference counting or other symchronizing method, do not
|
|
* reset node_data and free pgdat here. Just reset it to 0 and reuse
|
|
* the memory when the node is online again.
|
|
*/
|
|
memset(pgdat, 0, sizeof(*pgdat));
|
|
}
|
|
EXPORT_SYMBOL(try_offline_node);
|
|
|
|
/**
|
|
* remove_memory
|
|
*
|
|
* NOTE: The caller must call lock_device_hotplug() to serialize hotplug
|
|
* and online/offline operations before this call, as required by
|
|
* try_offline_node().
|
|
*/
|
|
void __ref remove_memory(int nid, u64 start, u64 size)
|
|
{
|
|
int ret;
|
|
|
|
BUG_ON(check_hotplug_memory_range(start, size));
|
|
|
|
lock_memory_hotplug();
|
|
|
|
/*
|
|
* All memory blocks must be offlined before removing memory. Check
|
|
* whether all memory blocks in question are offline and trigger a BUG()
|
|
* if this is not the case.
|
|
*/
|
|
ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
|
|
is_memblock_offlined_cb);
|
|
if (ret) {
|
|
unlock_memory_hotplug();
|
|
BUG();
|
|
}
|
|
|
|
/* remove memmap entry */
|
|
firmware_map_remove(start, start + size, "System RAM");
|
|
|
|
arch_remove_memory(start, size);
|
|
|
|
try_offline_node(nid);
|
|
|
|
unlock_memory_hotplug();
|
|
}
|
|
EXPORT_SYMBOL_GPL(remove_memory);
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|