mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-28 07:13:34 +00:00
426e5c429d
Patch series "Free some vmemmap pages of HugeTLB page", v23.
This patch series will free some vmemmap pages(struct page structures)
associated with each HugeTLB page when preallocated to save memory.
In order to reduce the difficulty of the first version of code review. In
this version, we disable PMD/huge page mapping of vmemmap if this feature
was enabled. This acutely eliminates a bunch of the complex code doing
page table manipulation. When this patch series is solid, we cam add the
code of vmemmap page table manipulation in the future.
The struct page structures (page structs) are used to describe a physical
page frame. By default, there is an one-to-one mapping from a page frame
to it's corresponding page struct.
The HugeTLB pages consist of multiple base page size pages and is
supported by many architectures. See hugetlbpage.rst in the Documentation
directory for more details. On the x86 architecture, HugeTLB pages of
size 2MB and 1GB are currently supported. Since the base page size on x86
is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB
page consists of 4096 base pages. For each base page, there is a
corresponding page struct.
Within the HugeTLB subsystem, only the first 4 page structs are used to
contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER
provides this upper limit. The only 'useful' information in the remaining
page structs is the compound_head field, and this field is the same for
all tail pages.
By removing redundant page structs for HugeTLB pages, memory can returned
to the buddy allocator for other uses.
When the system boot up, every 2M HugeTLB has 512 struct page structs which
size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).
HugeTLB struct pages(8 pages) page frame(8 pages)
+-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
| | | 0 | -------------> | 0 |
| | +-----------+ +-----------+
| | | 1 | -------------> | 1 |
| | +-----------+ +-----------+
| | | 2 | -------------> | 2 |
| | +-----------+ +-----------+
| | | 3 | -------------> | 3 |
| | +-----------+ +-----------+
| | | 4 | -------------> | 4 |
| 2MB | +-----------+ +-----------+
| | | 5 | -------------> | 5 |
| | +-----------+ +-----------+
| | | 6 | -------------> | 6 |
| | +-----------+ +-----------+
| | | 7 | -------------> | 7 |
| | +-----------+ +-----------+
| |
| |
| |
+-----------+
The value of page->compound_head is the same for all tail pages. The
first page of page structs (page 0) associated with the HugeTLB page
contains the 4 page structs necessary to describe the HugeTLB. The only
use of the remaining pages of page structs (page 1 to page 7) is to point
to page->compound_head. Therefore, we can remap pages 2 to 7 to page 1.
Only 2 pages of page structs will be used for each HugeTLB page. This
will allow us to free the remaining 6 pages to the buddy allocator.
Here is how things look after remapping.
HugeTLB struct pages(8 pages) page frame(8 pages)
+-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
| | | 0 | -------------> | 0 |
| | +-----------+ +-----------+
| | | 1 | -------------> | 1 |
| | +-----------+ +-----------+
| | | 2 | ----------------^ ^ ^ ^ ^ ^
| | +-----------+ | | | | |
| | | 3 | ------------------+ | | | |
| | +-----------+ | | | |
| | | 4 | --------------------+ | | |
| 2MB | +-----------+ | | |
| | | 5 | ----------------------+ | |
| | +-----------+ | |
| | | 6 | ------------------------+ |
| | +-----------+ |
| | | 7 | --------------------------+
| | +-----------+
| |
| |
| |
+-----------+
When a HugeTLB is freed to the buddy system, we should allocate 6 pages
for vmemmap pages and restore the previous mapping relationship.
Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar
to the 2MB HugeTLB page. We also can use this approach to free the
vmemmap pages.
In this case, for the 1GB HugeTLB page, we can save 4094 pages. This is a
very substantial gain. On our server, run some SPDK/QEMU applications
which will use 1024GB HugeTLB page. With this feature enabled, we can
save ~16GB (1G hugepage)/~12GB (2MB hugepage) memory.
Because there are vmemmap page tables reconstruction on the
freeing/allocating path, it increases some overhead. Here are some
overhead analysis.
1) Allocating 10240 2MB HugeTLB pages.
a) With this patch series applied:
# time echo 10240 > /proc/sys/vm/nr_hugepages
real 0m0.166s
user 0m0.000s
sys 0m0.166s
# bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; }
kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs -
@start[tid]); delete(@start[tid]); }'
Attaching 2 probes...
@latency:
[8K, 16K) 5476 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[16K, 32K) 4760 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[32K, 64K) 4 | |
b) Without this patch series:
# time echo 10240 > /proc/sys/vm/nr_hugepages
real 0m0.067s
user 0m0.000s
sys 0m0.067s
# bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; }
kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs -
@start[tid]); delete(@start[tid]); }'
Attaching 2 probes...
@latency:
[4K, 8K) 10147 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[8K, 16K) 93 | |
Summarize: this feature is about ~2x slower than before.
2) Freeing 10240 2MB HugeTLB pages.
a) With this patch series applied:
# time echo 0 > /proc/sys/vm/nr_hugepages
real 0m0.213s
user 0m0.000s
sys 0m0.213s
# bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; }
kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs -
@start[tid]); delete(@start[tid]); }'
Attaching 2 probes...
@latency:
[8K, 16K) 6 | |
[16K, 32K) 10227 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[32K, 64K) 7 | |
b) Without this patch series:
# time echo 0 > /proc/sys/vm/nr_hugepages
real 0m0.081s
user 0m0.000s
sys 0m0.081s
# bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; }
kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs -
@start[tid]); delete(@start[tid]); }'
Attaching 2 probes...
@latency:
[4K, 8K) 6805 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[8K, 16K) 3427 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[16K, 32K) 8 | |
Summary: The overhead of __free_hugepage is about ~2-3x slower than before.
Although the overhead has increased, the overhead is not significant.
Like Mike said, "However, remember that the majority of use cases create
HugeTLB pages at or shortly after boot time and add them to the pool. So,
additional overhead is at pool creation time. There is no change to
'normal run time' operations of getting a page from or returning a page to
the pool (think page fault/unmap)".
Despite the overhead and in addition to the memory gains from this series.
The following data is obtained by Joao Martins. Very thanks to his
effort.
There's an additional benefit which is page (un)pinners will see an improvement
and Joao presumes because there are fewer memmap pages and thus the tail/head
pages are staying in cache more often.
Out of the box Joao saw (when comparing linux-next against linux-next +
this series) with gup_test and pinning a 16G HugeTLB file (with 1G pages):
get_user_pages(): ~32k -> ~9k
unpin_user_pages(): ~75k -> ~70k
Usually any tight loop fetching compound_head(), or reading tail pages
data (e.g. compound_head) benefit a lot. There's some unpinning
inefficiencies Joao was fixing[2], but with that in added it shows even
more:
unpin_user_pages(): ~27k -> ~3.8k
[1] https://lore.kernel.org/linux-mm/20210409205254.242291-1-mike.kravetz@oracle.com/
[2] https://lore.kernel.org/linux-mm/20210204202500.26474-1-joao.m.martins@oracle.com/
This patch (of 9):
Move bootmem info registration common API to individual bootmem_info.c.
And we will use {get,put}_page_bootmem() to initialize the page for the
vmemmap pages or free the vmemmap pages to buddy in the later patch. So
move them out of CONFIG_MEMORY_HOTPLUG_SPARSE. This is just code movement
without any functional change.
Link: https://lkml.kernel.org/r/20210510030027.56044-1-songmuchun@bytedance.com
Link: https://lkml.kernel.org/r/20210510030027.56044-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Tested-by: Chen Huang <chenhuang5@huawei.com>
Tested-by: Bodeddula Balasubramaniam <bodeddub@amazon.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Mina Almasry <almasrymina@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Barry Song <song.bao.hua@hisilicon.com>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
350 lines
11 KiB
C
350 lines
11 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_MEMORY_HOTPLUG_H
|
|
#define __LINUX_MEMORY_HOTPLUG_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/bug.h>
|
|
|
|
struct page;
|
|
struct zone;
|
|
struct pglist_data;
|
|
struct mem_section;
|
|
struct memory_block;
|
|
struct resource;
|
|
struct vmem_altmap;
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
struct page *pfn_to_online_page(unsigned long pfn);
|
|
|
|
/* Types for control the zone type of onlined and offlined memory */
|
|
enum {
|
|
/* Offline the memory. */
|
|
MMOP_OFFLINE = 0,
|
|
/* Online the memory. Zone depends, see default_zone_for_pfn(). */
|
|
MMOP_ONLINE,
|
|
/* Online the memory to ZONE_NORMAL. */
|
|
MMOP_ONLINE_KERNEL,
|
|
/* Online the memory to ZONE_MOVABLE. */
|
|
MMOP_ONLINE_MOVABLE,
|
|
};
|
|
|
|
/* Flags for add_memory() and friends to specify memory hotplug details. */
|
|
typedef int __bitwise mhp_t;
|
|
|
|
/* No special request */
|
|
#define MHP_NONE ((__force mhp_t)0)
|
|
/*
|
|
* Allow merging of the added System RAM resource with adjacent,
|
|
* mergeable resources. After a successful call to add_memory_resource()
|
|
* with this flag set, the resource pointer must no longer be used as it
|
|
* might be stale, or the resource might have changed.
|
|
*/
|
|
#define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0))
|
|
|
|
/*
|
|
* We want memmap (struct page array) to be self contained.
|
|
* To do so, we will use the beginning of the hot-added range to build
|
|
* the page tables for the memmap array that describes the entire range.
|
|
* Only selected architectures support it with SPARSE_VMEMMAP.
|
|
*/
|
|
#define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1))
|
|
|
|
/*
|
|
* Extended parameters for memory hotplug:
|
|
* altmap: alternative allocator for memmap array (optional)
|
|
* pgprot: page protection flags to apply to newly created page tables
|
|
* (required)
|
|
*/
|
|
struct mhp_params {
|
|
struct vmem_altmap *altmap;
|
|
pgprot_t pgprot;
|
|
};
|
|
|
|
bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
|
|
struct range mhp_get_pluggable_range(bool need_mapping);
|
|
|
|
/*
|
|
* Zone resizing functions
|
|
*
|
|
* Note: any attempt to resize a zone should has pgdat_resize_lock()
|
|
* zone_span_writelock() both held. This ensure the size of a zone
|
|
* can't be changed while pgdat_resize_lock() held.
|
|
*/
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return read_seqbegin(&zone->span_seqlock);
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return read_seqretry(&zone->span_seqlock, iv);
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone)
|
|
{
|
|
write_seqlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_span_writeunlock(struct zone *zone)
|
|
{
|
|
write_sequnlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_seqlock_init(struct zone *zone)
|
|
{
|
|
seqlock_init(&zone->span_seqlock);
|
|
}
|
|
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
|
|
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
|
|
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
|
|
extern void adjust_present_page_count(struct zone *zone, long nr_pages);
|
|
/* VM interface that may be used by firmware interface */
|
|
extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
|
|
struct zone *zone);
|
|
extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
|
|
extern int online_pages(unsigned long pfn, unsigned long nr_pages,
|
|
struct zone *zone);
|
|
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
|
|
unsigned long end_pfn);
|
|
extern void __offline_isolated_pages(unsigned long start_pfn,
|
|
unsigned long end_pfn);
|
|
|
|
typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
|
|
|
|
extern void generic_online_page(struct page *page, unsigned int order);
|
|
extern int set_online_page_callback(online_page_callback_t callback);
|
|
extern int restore_online_page_callback(online_page_callback_t callback);
|
|
|
|
extern int try_online_node(int nid);
|
|
|
|
extern int arch_add_memory(int nid, u64 start, u64 size,
|
|
struct mhp_params *params);
|
|
extern u64 max_mem_size;
|
|
|
|
extern int mhp_online_type_from_str(const char *str);
|
|
|
|
/* Default online_type (MMOP_*) when new memory blocks are added. */
|
|
extern int mhp_default_online_type;
|
|
/* If movable_node boot option specified */
|
|
extern bool movable_node_enabled;
|
|
static inline bool movable_node_is_enabled(void)
|
|
{
|
|
return movable_node_enabled;
|
|
}
|
|
|
|
extern void arch_remove_memory(int nid, u64 start, u64 size,
|
|
struct vmem_altmap *altmap);
|
|
extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
|
|
struct vmem_altmap *altmap);
|
|
|
|
/* reasonably generic interface to expand the physical pages */
|
|
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
|
|
struct mhp_params *params);
|
|
|
|
#ifndef CONFIG_ARCH_HAS_ADD_PAGES
|
|
static inline int add_pages(int nid, unsigned long start_pfn,
|
|
unsigned long nr_pages, struct mhp_params *params)
|
|
{
|
|
return __add_pages(nid, start_pfn, nr_pages, params);
|
|
}
|
|
#else /* ARCH_HAS_ADD_PAGES */
|
|
int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
|
|
struct mhp_params *params);
|
|
#endif /* ARCH_HAS_ADD_PAGES */
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
|
|
/*
|
|
* For supporting node-hotadd, we have to allocate a new pgdat.
|
|
*
|
|
* If an arch has generic style NODE_DATA(),
|
|
* node_data[nid] = kzalloc() works well. But it depends on the architecture.
|
|
*
|
|
* In general, generic_alloc_nodedata() is used.
|
|
* Now, arch_free_nodedata() is just defined for error path of node_hot_add.
|
|
*
|
|
*/
|
|
extern pg_data_t *arch_alloc_nodedata(int nid);
|
|
extern void arch_free_nodedata(pg_data_t *pgdat);
|
|
extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
|
|
|
|
#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid)
|
|
#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
|
|
* XXX: kmalloc_node() can't work well to get new node's memory at this time.
|
|
* Because, pgdat for the new node is not allocated/initialized yet itself.
|
|
* To use new node's memory, more consideration will be necessary.
|
|
*/
|
|
#define generic_alloc_nodedata(nid) \
|
|
({ \
|
|
kzalloc(sizeof(pg_data_t), GFP_KERNEL); \
|
|
})
|
|
/*
|
|
* This definition is just for error path in node hotadd.
|
|
* For node hotremove, we have to replace this.
|
|
*/
|
|
#define generic_free_nodedata(pgdat) kfree(pgdat)
|
|
|
|
extern pg_data_t *node_data[];
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
node_data[nid] = pgdat;
|
|
}
|
|
|
|
#else /* !CONFIG_NUMA */
|
|
|
|
/* never called */
|
|
static inline pg_data_t *generic_alloc_nodedata(int nid)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
static inline void generic_free_nodedata(pg_data_t *pgdat)
|
|
{
|
|
}
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
void get_online_mems(void);
|
|
void put_online_mems(void);
|
|
|
|
void mem_hotplug_begin(void);
|
|
void mem_hotplug_done(void);
|
|
|
|
#else /* ! CONFIG_MEMORY_HOTPLUG */
|
|
#define pfn_to_online_page(pfn) \
|
|
({ \
|
|
struct page *___page = NULL; \
|
|
if (pfn_valid(pfn)) \
|
|
___page = pfn_to_page(pfn); \
|
|
___page; \
|
|
})
|
|
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone) {}
|
|
static inline void zone_span_writeunlock(struct zone *zone) {}
|
|
static inline void zone_seqlock_init(struct zone *zone) {}
|
|
|
|
static inline int try_online_node(int nid)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void get_online_mems(void) {}
|
|
static inline void put_online_mems(void) {}
|
|
|
|
static inline void mem_hotplug_begin(void) {}
|
|
static inline void mem_hotplug_done(void) {}
|
|
|
|
static inline bool movable_node_is_enabled(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* ! CONFIG_MEMORY_HOTPLUG */
|
|
|
|
/*
|
|
* Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some
|
|
* platforms might override and use arch_get_mappable_range()
|
|
* for internal non memory hotplug purposes.
|
|
*/
|
|
struct range arch_get_mappable_range(void);
|
|
|
|
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
|
|
/*
|
|
* pgdat resizing functions
|
|
*/
|
|
static inline
|
|
void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_lock_irqsave(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_init(struct pglist_data *pgdat)
|
|
{
|
|
spin_lock_init(&pgdat->node_size_lock);
|
|
}
|
|
#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
|
|
/*
|
|
* Stub functions for when hotplug is off
|
|
*/
|
|
static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
|
|
#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
extern void try_offline_node(int nid);
|
|
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
|
|
extern int remove_memory(int nid, u64 start, u64 size);
|
|
extern void __remove_memory(int nid, u64 start, u64 size);
|
|
extern int offline_and_remove_memory(int nid, u64 start, u64 size);
|
|
|
|
#else
|
|
static inline void try_offline_node(int nid) {}
|
|
|
|
static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
static inline int remove_memory(int nid, u64 start, u64 size)
|
|
{
|
|
return -EBUSY;
|
|
}
|
|
|
|
static inline void __remove_memory(int nid, u64 start, u64 size) {}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
extern void set_zone_contiguous(struct zone *zone);
|
|
extern void clear_zone_contiguous(struct zone *zone);
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
extern void __ref free_area_init_core_hotplug(int nid);
|
|
extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
|
|
extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
|
|
extern int add_memory_resource(int nid, struct resource *resource,
|
|
mhp_t mhp_flags);
|
|
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
|
|
const char *resource_name,
|
|
mhp_t mhp_flags);
|
|
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages,
|
|
struct vmem_altmap *altmap, int migratetype);
|
|
extern void remove_pfn_range_from_zone(struct zone *zone,
|
|
unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
extern bool is_memblock_offlined(struct memory_block *mem);
|
|
extern int sparse_add_section(int nid, unsigned long pfn,
|
|
unsigned long nr_pages, struct vmem_altmap *altmap);
|
|
extern void sparse_remove_section(struct mem_section *ms,
|
|
unsigned long pfn, unsigned long nr_pages,
|
|
unsigned long map_offset, struct vmem_altmap *altmap);
|
|
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
|
|
unsigned long pnum);
|
|
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
|
|
unsigned long nr_pages);
|
|
extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
|
|
struct mhp_params *params);
|
|
void arch_remove_linear_mapping(u64 start, u64 size);
|
|
extern bool mhp_supports_memmap_on_memory(unsigned long size);
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|
|
|
|
#endif /* __LINUX_MEMORY_HOTPLUG_H */
|