mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Michal Hocko](/assets/img/avatar_default.png)
The current memory hotplug implementation relies on having all the struct pages associate with a zone/node during the physical hotplug phase (arch_add_memory->__add_pages->__add_section->__add_zone). In the vast majority of cases this means that they are added to ZONE_NORMAL. This has been so since9d99aaa31f
("[PATCH] x86_64: Support memory hotadd without sparsemem") and it wasn't a big deal back then because movable onlining didn't exist yet. Much later memory hotplug wanted to (ab)use ZONE_MOVABLE for movable onlining511c2aba8f
("mm, memory-hotplug: dynamic configure movable memory and portion memory") and then things got more complicated. Rather than reconsidering the zone association which was no longer needed (because the memory hotplug already depended on SPARSEMEM) a convoluted semantic of zone shifting has been developed. Only the currently last memblock or the one adjacent to the zone_movable can be onlined movable. This essentially means that the online type changes as the new memblocks are added. Let's simulate memory hot online manually $ echo 0x100000000 > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory32/valid_zones Normal Movable $ echo $((0x100000000+(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable $ echo $((0x100000000+2*(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal /sys/devices/system/memory/memory34/valid_zones:Normal Movable $ echo online_movable > /sys/devices/system/memory/memory34/state $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Normal This is an awkward semantic because an udev event is sent as soon as the block is onlined and an udev handler might want to online it based on some policy (e.g. association with a node) but it will inherently race with new blocks showing up. This patch changes the physical online phase to not associate pages with any zone at all. All the pages are just marked reserved and wait for the onlining phase to be associated with the zone as per the online request. There are only two requirements - existing ZONE_NORMAL and ZONE_MOVABLE cannot overlap - ZONE_NORMAL precedes ZONE_MOVABLE in physical addresses the latter one is not an inherent requirement and can be changed in the future. It preserves the current behavior and made the code slightly simpler. This is subject to change in future. This means that the same physical online steps as above will lead to the following state: Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Implementation: The current move_pfn_range is reimplemented to check the above requirements (allow_online_pfn_range) and then updates the respective zone (move_pfn_range_to_zone), the pgdat and links all the pages in the pfn range with the zone/node. __add_pages is updated to not require the zone and only initializes sections in the range. This allowed to simplify the arch_add_memory code (s390 could get rid of quite some of code). devm_memremap_pages is the only user of arch_add_memory which relies on the zone association because it only hooks into the memory hotplug only half way. It uses it to associate the new memory with ZONE_DEVICE but doesn't allow it to be {on,off}lined via sysfs. This means that this particular code path has to call move_pfn_range_to_zone explicitly. The original zone shifting code is kept in place and will be removed in the follow up patch for an easier review. Please note that this patch also changes the original behavior when offlining a memory block adjacent to another zone (Normal vs. Movable) used to allow to change its movable type. This will be handled later. [richard.weiyang@gmail.com: simplify zone_intersects()] Link: http://lkml.kernel.org/r/20170616092335.5177-1-richard.weiyang@gmail.com [richard.weiyang@gmail.com: remove duplicate call for set_page_links] Link: http://lkml.kernel.org/r/20170616092335.5177-2-richard.weiyang@gmail.com [akpm@linux-foundation.org: remove unused local `i'] Link: http://lkml.kernel.org/r/20170515085827.16474-12-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Wei Yang <richard.weiyang@gmail.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Reza Arbab <arbab@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # For s390 bits Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
883 lines
23 KiB
C
883 lines
23 KiB
C
/*
|
|
* sparse memory mappings.
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/export.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include "internal.h"
|
|
#include <asm/dma.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
/*
|
|
* Permanent SPARSEMEM data:
|
|
*
|
|
* 1) mem_section - memory sections, mem_map's for valid memory
|
|
*/
|
|
#ifdef CONFIG_SPARSEMEM_EXTREME
|
|
struct mem_section *mem_section[NR_SECTION_ROOTS]
|
|
____cacheline_internodealigned_in_smp;
|
|
#else
|
|
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
|
|
____cacheline_internodealigned_in_smp;
|
|
#endif
|
|
EXPORT_SYMBOL(mem_section);
|
|
|
|
#ifdef NODE_NOT_IN_PAGE_FLAGS
|
|
/*
|
|
* If we did not store the node number in the page then we have to
|
|
* do a lookup in the section_to_node_table in order to find which
|
|
* node the page belongs to.
|
|
*/
|
|
#if MAX_NUMNODES <= 256
|
|
static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
|
|
#else
|
|
static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
|
|
#endif
|
|
|
|
int page_to_nid(const struct page *page)
|
|
{
|
|
return section_to_node_table[page_to_section(page)];
|
|
}
|
|
EXPORT_SYMBOL(page_to_nid);
|
|
|
|
static void set_section_nid(unsigned long section_nr, int nid)
|
|
{
|
|
section_to_node_table[section_nr] = nid;
|
|
}
|
|
#else /* !NODE_NOT_IN_PAGE_FLAGS */
|
|
static inline void set_section_nid(unsigned long section_nr, int nid)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SPARSEMEM_EXTREME
|
|
static noinline struct mem_section __ref *sparse_index_alloc(int nid)
|
|
{
|
|
struct mem_section *section = NULL;
|
|
unsigned long array_size = SECTIONS_PER_ROOT *
|
|
sizeof(struct mem_section);
|
|
|
|
if (slab_is_available()) {
|
|
if (node_state(nid, N_HIGH_MEMORY))
|
|
section = kzalloc_node(array_size, GFP_KERNEL, nid);
|
|
else
|
|
section = kzalloc(array_size, GFP_KERNEL);
|
|
} else {
|
|
section = memblock_virt_alloc_node(array_size, nid);
|
|
}
|
|
|
|
return section;
|
|
}
|
|
|
|
static int __meminit sparse_index_init(unsigned long section_nr, int nid)
|
|
{
|
|
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
|
|
struct mem_section *section;
|
|
|
|
if (mem_section[root])
|
|
return -EEXIST;
|
|
|
|
section = sparse_index_alloc(nid);
|
|
if (!section)
|
|
return -ENOMEM;
|
|
|
|
mem_section[root] = section;
|
|
|
|
return 0;
|
|
}
|
|
#else /* !SPARSEMEM_EXTREME */
|
|
static inline int sparse_index_init(unsigned long section_nr, int nid)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SPARSEMEM_EXTREME
|
|
int __section_nr(struct mem_section* ms)
|
|
{
|
|
unsigned long root_nr;
|
|
struct mem_section* root;
|
|
|
|
for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
|
|
root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
|
|
if (!root)
|
|
continue;
|
|
|
|
if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
|
|
break;
|
|
}
|
|
|
|
VM_BUG_ON(root_nr == NR_SECTION_ROOTS);
|
|
|
|
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
|
|
}
|
|
#else
|
|
int __section_nr(struct mem_section* ms)
|
|
{
|
|
return (int)(ms - mem_section[0]);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* During early boot, before section_mem_map is used for an actual
|
|
* mem_map, we use section_mem_map to store the section's NUMA
|
|
* node. This keeps us from having to use another data structure. The
|
|
* node information is cleared just before we store the real mem_map.
|
|
*/
|
|
static inline unsigned long sparse_encode_early_nid(int nid)
|
|
{
|
|
return (nid << SECTION_NID_SHIFT);
|
|
}
|
|
|
|
static inline int sparse_early_nid(struct mem_section *section)
|
|
{
|
|
return (section->section_mem_map >> SECTION_NID_SHIFT);
|
|
}
|
|
|
|
/* Validate the physical addressing limitations of the model */
|
|
void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
unsigned long *end_pfn)
|
|
{
|
|
unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
|
|
|
|
/*
|
|
* Sanity checks - do not allow an architecture to pass
|
|
* in larger pfns than the maximum scope of sparsemem:
|
|
*/
|
|
if (*start_pfn > max_sparsemem_pfn) {
|
|
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
|
|
"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
|
|
*start_pfn, *end_pfn, max_sparsemem_pfn);
|
|
WARN_ON_ONCE(1);
|
|
*start_pfn = max_sparsemem_pfn;
|
|
*end_pfn = max_sparsemem_pfn;
|
|
} else if (*end_pfn > max_sparsemem_pfn) {
|
|
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
|
|
"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
|
|
*start_pfn, *end_pfn, max_sparsemem_pfn);
|
|
WARN_ON_ONCE(1);
|
|
*end_pfn = max_sparsemem_pfn;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* There are a number of times that we loop over NR_MEM_SECTIONS,
|
|
* looking for section_present() on each. But, when we have very
|
|
* large physical address spaces, NR_MEM_SECTIONS can also be
|
|
* very large which makes the loops quite long.
|
|
*
|
|
* Keeping track of this gives us an easy way to break out of
|
|
* those loops early.
|
|
*/
|
|
int __highest_present_section_nr;
|
|
static void section_mark_present(struct mem_section *ms)
|
|
{
|
|
int section_nr = __section_nr(ms);
|
|
|
|
if (section_nr > __highest_present_section_nr)
|
|
__highest_present_section_nr = section_nr;
|
|
|
|
ms->section_mem_map |= SECTION_MARKED_PRESENT;
|
|
}
|
|
|
|
static inline int next_present_section_nr(int section_nr)
|
|
{
|
|
do {
|
|
section_nr++;
|
|
if (present_section_nr(section_nr))
|
|
return section_nr;
|
|
} while ((section_nr < NR_MEM_SECTIONS) &&
|
|
(section_nr <= __highest_present_section_nr));
|
|
|
|
return -1;
|
|
}
|
|
#define for_each_present_section_nr(start, section_nr) \
|
|
for (section_nr = next_present_section_nr(start-1); \
|
|
((section_nr >= 0) && \
|
|
(section_nr < NR_MEM_SECTIONS) && \
|
|
(section_nr <= __highest_present_section_nr)); \
|
|
section_nr = next_present_section_nr(section_nr))
|
|
|
|
/* Record a memory area against a node. */
|
|
void __init memory_present(int nid, unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long pfn;
|
|
|
|
start &= PAGE_SECTION_MASK;
|
|
mminit_validate_memmodel_limits(&start, &end);
|
|
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
|
|
unsigned long section = pfn_to_section_nr(pfn);
|
|
struct mem_section *ms;
|
|
|
|
sparse_index_init(section, nid);
|
|
set_section_nid(section, nid);
|
|
|
|
ms = __nr_to_section(section);
|
|
if (!ms->section_mem_map) {
|
|
ms->section_mem_map = sparse_encode_early_nid(nid) |
|
|
SECTION_IS_ONLINE;
|
|
section_mark_present(ms);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Only used by the i386 NUMA architecures, but relatively
|
|
* generic code.
|
|
*/
|
|
unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
unsigned long pfn;
|
|
unsigned long nr_pages = 0;
|
|
|
|
mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
if (nid != early_pfn_to_nid(pfn))
|
|
continue;
|
|
|
|
if (pfn_present(pfn))
|
|
nr_pages += PAGES_PER_SECTION;
|
|
}
|
|
|
|
return nr_pages * sizeof(struct page);
|
|
}
|
|
|
|
/*
|
|
* Subtle, we encode the real pfn into the mem_map such that
|
|
* the identity pfn - section_mem_map will return the actual
|
|
* physical page frame number.
|
|
*/
|
|
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
|
|
{
|
|
return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
|
|
}
|
|
|
|
/*
|
|
* Decode mem_map from the coded memmap
|
|
*/
|
|
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
|
|
{
|
|
/* mask off the extra low bits of information */
|
|
coded_mem_map &= SECTION_MAP_MASK;
|
|
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
|
|
}
|
|
|
|
static int __meminit sparse_init_one_section(struct mem_section *ms,
|
|
unsigned long pnum, struct page *mem_map,
|
|
unsigned long *pageblock_bitmap)
|
|
{
|
|
if (!present_section(ms))
|
|
return -EINVAL;
|
|
|
|
ms->section_mem_map &= ~SECTION_MAP_MASK;
|
|
ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
|
|
SECTION_HAS_MEM_MAP;
|
|
ms->pageblock_flags = pageblock_bitmap;
|
|
|
|
return 1;
|
|
}
|
|
|
|
unsigned long usemap_size(void)
|
|
{
|
|
return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
static unsigned long *__kmalloc_section_usemap(void)
|
|
{
|
|
return kmalloc(usemap_size(), GFP_KERNEL);
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static unsigned long * __init
|
|
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
|
|
unsigned long size)
|
|
{
|
|
unsigned long goal, limit;
|
|
unsigned long *p;
|
|
int nid;
|
|
/*
|
|
* A page may contain usemaps for other sections preventing the
|
|
* page being freed and making a section unremovable while
|
|
* other sections referencing the usemap remain active. Similarly,
|
|
* a pgdat can prevent a section being removed. If section A
|
|
* contains a pgdat and section B contains the usemap, both
|
|
* sections become inter-dependent. This allocates usemaps
|
|
* from the same section as the pgdat where possible to avoid
|
|
* this problem.
|
|
*/
|
|
goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
|
|
limit = goal + (1UL << PA_SECTION_SHIFT);
|
|
nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
|
|
again:
|
|
p = memblock_virt_alloc_try_nid_nopanic(size,
|
|
SMP_CACHE_BYTES, goal, limit,
|
|
nid);
|
|
if (!p && limit) {
|
|
limit = 0;
|
|
goto again;
|
|
}
|
|
return p;
|
|
}
|
|
|
|
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
|
|
{
|
|
unsigned long usemap_snr, pgdat_snr;
|
|
static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
|
|
static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
|
|
struct pglist_data *pgdat = NODE_DATA(nid);
|
|
int usemap_nid;
|
|
|
|
usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
|
|
pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
|
|
if (usemap_snr == pgdat_snr)
|
|
return;
|
|
|
|
if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
|
|
/* skip redundant message */
|
|
return;
|
|
|
|
old_usemap_snr = usemap_snr;
|
|
old_pgdat_snr = pgdat_snr;
|
|
|
|
usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
|
|
if (usemap_nid != nid) {
|
|
pr_info("node %d must be removed before remove section %ld\n",
|
|
nid, usemap_snr);
|
|
return;
|
|
}
|
|
/*
|
|
* There is a circular dependency.
|
|
* Some platforms allow un-removable section because they will just
|
|
* gather other removable sections for dynamic partitioning.
|
|
* Just notify un-removable section's number here.
|
|
*/
|
|
pr_info("Section %ld and %ld (node %d) have a circular dependency on usemap and pgdat allocations\n",
|
|
usemap_snr, pgdat_snr, nid);
|
|
}
|
|
#else
|
|
static unsigned long * __init
|
|
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
|
|
unsigned long size)
|
|
{
|
|
return memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
|
|
}
|
|
|
|
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
static void __init sparse_early_usemaps_alloc_node(void *data,
|
|
unsigned long pnum_begin,
|
|
unsigned long pnum_end,
|
|
unsigned long usemap_count, int nodeid)
|
|
{
|
|
void *usemap;
|
|
unsigned long pnum;
|
|
unsigned long **usemap_map = (unsigned long **)data;
|
|
int size = usemap_size();
|
|
|
|
usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
|
|
size * usemap_count);
|
|
if (!usemap) {
|
|
pr_warn("%s: allocation failed\n", __func__);
|
|
return;
|
|
}
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
if (!present_section_nr(pnum))
|
|
continue;
|
|
usemap_map[pnum] = usemap;
|
|
usemap += size;
|
|
check_usemap_section_nr(nodeid, usemap_map[pnum]);
|
|
}
|
|
}
|
|
|
|
#ifndef CONFIG_SPARSEMEM_VMEMMAP
|
|
struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
|
|
{
|
|
struct page *map;
|
|
unsigned long size;
|
|
|
|
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
|
|
if (map)
|
|
return map;
|
|
|
|
size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
|
|
map = memblock_virt_alloc_try_nid(size,
|
|
PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
|
|
BOOTMEM_ALLOC_ACCESSIBLE, nid);
|
|
return map;
|
|
}
|
|
void __init sparse_mem_maps_populate_node(struct page **map_map,
|
|
unsigned long pnum_begin,
|
|
unsigned long pnum_end,
|
|
unsigned long map_count, int nodeid)
|
|
{
|
|
void *map;
|
|
unsigned long pnum;
|
|
unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
|
|
|
|
map = alloc_remap(nodeid, size * map_count);
|
|
if (map) {
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
if (!present_section_nr(pnum))
|
|
continue;
|
|
map_map[pnum] = map;
|
|
map += size;
|
|
}
|
|
return;
|
|
}
|
|
|
|
size = PAGE_ALIGN(size);
|
|
map = memblock_virt_alloc_try_nid(size * map_count,
|
|
PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
|
|
BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
|
|
if (map) {
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
if (!present_section_nr(pnum))
|
|
continue;
|
|
map_map[pnum] = map;
|
|
map += size;
|
|
}
|
|
return;
|
|
}
|
|
|
|
/* fallback */
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
struct mem_section *ms;
|
|
|
|
if (!present_section_nr(pnum))
|
|
continue;
|
|
map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
|
|
if (map_map[pnum])
|
|
continue;
|
|
ms = __nr_to_section(pnum);
|
|
pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
|
|
__func__);
|
|
ms->section_mem_map = 0;
|
|
}
|
|
}
|
|
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
|
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
static void __init sparse_early_mem_maps_alloc_node(void *data,
|
|
unsigned long pnum_begin,
|
|
unsigned long pnum_end,
|
|
unsigned long map_count, int nodeid)
|
|
{
|
|
struct page **map_map = (struct page **)data;
|
|
sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
|
|
map_count, nodeid);
|
|
}
|
|
#else
|
|
static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
|
|
{
|
|
struct page *map;
|
|
struct mem_section *ms = __nr_to_section(pnum);
|
|
int nid = sparse_early_nid(ms);
|
|
|
|
map = sparse_mem_map_populate(pnum, nid);
|
|
if (map)
|
|
return map;
|
|
|
|
pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
|
|
__func__);
|
|
ms->section_mem_map = 0;
|
|
return NULL;
|
|
}
|
|
#endif
|
|
|
|
void __weak __meminit vmemmap_populate_print_last(void)
|
|
{
|
|
}
|
|
|
|
/**
|
|
* alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
|
|
* @map: usemap_map for pageblock flags or mmap_map for vmemmap
|
|
*/
|
|
static void __init alloc_usemap_and_memmap(void (*alloc_func)
|
|
(void *, unsigned long, unsigned long,
|
|
unsigned long, int), void *data)
|
|
{
|
|
unsigned long pnum;
|
|
unsigned long map_count;
|
|
int nodeid_begin = 0;
|
|
unsigned long pnum_begin = 0;
|
|
|
|
for_each_present_section_nr(0, pnum) {
|
|
struct mem_section *ms;
|
|
|
|
ms = __nr_to_section(pnum);
|
|
nodeid_begin = sparse_early_nid(ms);
|
|
pnum_begin = pnum;
|
|
break;
|
|
}
|
|
map_count = 1;
|
|
for_each_present_section_nr(pnum_begin + 1, pnum) {
|
|
struct mem_section *ms;
|
|
int nodeid;
|
|
|
|
ms = __nr_to_section(pnum);
|
|
nodeid = sparse_early_nid(ms);
|
|
if (nodeid == nodeid_begin) {
|
|
map_count++;
|
|
continue;
|
|
}
|
|
/* ok, we need to take cake of from pnum_begin to pnum - 1*/
|
|
alloc_func(data, pnum_begin, pnum,
|
|
map_count, nodeid_begin);
|
|
/* new start, update count etc*/
|
|
nodeid_begin = nodeid;
|
|
pnum_begin = pnum;
|
|
map_count = 1;
|
|
}
|
|
/* ok, last chunk */
|
|
alloc_func(data, pnum_begin, NR_MEM_SECTIONS,
|
|
map_count, nodeid_begin);
|
|
}
|
|
|
|
/*
|
|
* Allocate the accumulated non-linear sections, allocate a mem_map
|
|
* for each and record the physical to section mapping.
|
|
*/
|
|
void __init sparse_init(void)
|
|
{
|
|
unsigned long pnum;
|
|
struct page *map;
|
|
unsigned long *usemap;
|
|
unsigned long **usemap_map;
|
|
int size;
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
int size2;
|
|
struct page **map_map;
|
|
#endif
|
|
|
|
/* see include/linux/mmzone.h 'struct mem_section' definition */
|
|
BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
|
|
|
|
/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
|
|
set_pageblock_order();
|
|
|
|
/*
|
|
* map is using big page (aka 2M in x86 64 bit)
|
|
* usemap is less one page (aka 24 bytes)
|
|
* so alloc 2M (with 2M align) and 24 bytes in turn will
|
|
* make next 2M slip to one more 2M later.
|
|
* then in big system, the memory will have a lot of holes...
|
|
* here try to allocate 2M pages continuously.
|
|
*
|
|
* powerpc need to call sparse_init_one_section right after each
|
|
* sparse_early_mem_map_alloc, so allocate usemap_map at first.
|
|
*/
|
|
size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
|
|
usemap_map = memblock_virt_alloc(size, 0);
|
|
if (!usemap_map)
|
|
panic("can not allocate usemap_map\n");
|
|
alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
|
|
(void *)usemap_map);
|
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
|
|
map_map = memblock_virt_alloc(size2, 0);
|
|
if (!map_map)
|
|
panic("can not allocate map_map\n");
|
|
alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
|
|
(void *)map_map);
|
|
#endif
|
|
|
|
for_each_present_section_nr(0, pnum) {
|
|
usemap = usemap_map[pnum];
|
|
if (!usemap)
|
|
continue;
|
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
map = map_map[pnum];
|
|
#else
|
|
map = sparse_early_mem_map_alloc(pnum);
|
|
#endif
|
|
if (!map)
|
|
continue;
|
|
|
|
sparse_init_one_section(__nr_to_section(pnum), pnum, map,
|
|
usemap);
|
|
}
|
|
|
|
vmemmap_populate_print_last();
|
|
|
|
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
|
|
memblock_free_early(__pa(map_map), size2);
|
|
#endif
|
|
memblock_free_early(__pa(usemap_map), size);
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
|
|
/* Mark all memory sections within the pfn range as online */
|
|
void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
|
|
{
|
|
unsigned long pfn;
|
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
unsigned long section_nr = pfn_to_section_nr(start_pfn);
|
|
struct mem_section *ms;
|
|
|
|
/* onlining code should never touch invalid ranges */
|
|
if (WARN_ON(!valid_section_nr(section_nr)))
|
|
continue;
|
|
|
|
ms = __nr_to_section(section_nr);
|
|
ms->section_mem_map |= SECTION_IS_ONLINE;
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
/* Mark all memory sections within the pfn range as online */
|
|
void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
|
|
{
|
|
unsigned long pfn;
|
|
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
|
|
unsigned long section_nr = pfn_to_section_nr(start_pfn);
|
|
struct mem_section *ms;
|
|
|
|
/*
|
|
* TODO this needs some double checking. Offlining code makes
|
|
* sure to check pfn_valid but those checks might be just bogus
|
|
*/
|
|
if (WARN_ON(!valid_section_nr(section_nr)))
|
|
continue;
|
|
|
|
ms = __nr_to_section(section_nr);
|
|
ms->section_mem_map &= ~SECTION_IS_ONLINE;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SPARSEMEM_VMEMMAP
|
|
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
|
|
{
|
|
/* This will make the necessary allocations eventually. */
|
|
return sparse_mem_map_populate(pnum, nid);
|
|
}
|
|
static void __kfree_section_memmap(struct page *memmap)
|
|
{
|
|
unsigned long start = (unsigned long)memmap;
|
|
unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
|
|
|
|
vmemmap_free(start, end);
|
|
}
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static void free_map_bootmem(struct page *memmap)
|
|
{
|
|
unsigned long start = (unsigned long)memmap;
|
|
unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
|
|
|
|
vmemmap_free(start, end);
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
#else
|
|
static struct page *__kmalloc_section_memmap(void)
|
|
{
|
|
struct page *page, *ret;
|
|
unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
|
|
|
|
page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
|
|
if (page)
|
|
goto got_map_page;
|
|
|
|
ret = vmalloc(memmap_size);
|
|
if (ret)
|
|
goto got_map_ptr;
|
|
|
|
return NULL;
|
|
got_map_page:
|
|
ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
|
|
got_map_ptr:
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
|
|
{
|
|
return __kmalloc_section_memmap();
|
|
}
|
|
|
|
static void __kfree_section_memmap(struct page *memmap)
|
|
{
|
|
if (is_vmalloc_addr(memmap))
|
|
vfree(memmap);
|
|
else
|
|
free_pages((unsigned long)memmap,
|
|
get_order(sizeof(struct page) * PAGES_PER_SECTION));
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static void free_map_bootmem(struct page *memmap)
|
|
{
|
|
unsigned long maps_section_nr, removing_section_nr, i;
|
|
unsigned long magic, nr_pages;
|
|
struct page *page = virt_to_page(memmap);
|
|
|
|
nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
|
|
>> PAGE_SHIFT;
|
|
|
|
for (i = 0; i < nr_pages; i++, page++) {
|
|
magic = (unsigned long) page->freelist;
|
|
|
|
BUG_ON(magic == NODE_INFO);
|
|
|
|
maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
|
|
removing_section_nr = page_private(page);
|
|
|
|
/*
|
|
* When this function is called, the removing section is
|
|
* logical offlined state. This means all pages are isolated
|
|
* from page allocator. If removing section's memmap is placed
|
|
* on the same section, it must not be freed.
|
|
* If it is freed, page allocator may allocate it which will
|
|
* be removed physically soon.
|
|
*/
|
|
if (maps_section_nr != removing_section_nr)
|
|
put_page_bootmem(page);
|
|
}
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
|
|
|
|
/*
|
|
* returns the number of sections whose mem_maps were properly
|
|
* set. If this is <=0, then that means that the passed-in
|
|
* map was not consumed and must be freed.
|
|
*/
|
|
int __meminit sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn)
|
|
{
|
|
unsigned long section_nr = pfn_to_section_nr(start_pfn);
|
|
struct mem_section *ms;
|
|
struct page *memmap;
|
|
unsigned long *usemap;
|
|
unsigned long flags;
|
|
int ret;
|
|
|
|
/*
|
|
* no locking for this, because it does its own
|
|
* plus, it does a kmalloc
|
|
*/
|
|
ret = sparse_index_init(section_nr, pgdat->node_id);
|
|
if (ret < 0 && ret != -EEXIST)
|
|
return ret;
|
|
memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
|
|
if (!memmap)
|
|
return -ENOMEM;
|
|
usemap = __kmalloc_section_usemap();
|
|
if (!usemap) {
|
|
__kfree_section_memmap(memmap);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
pgdat_resize_lock(pgdat, &flags);
|
|
|
|
ms = __pfn_to_section(start_pfn);
|
|
if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
|
|
ret = -EEXIST;
|
|
goto out;
|
|
}
|
|
|
|
memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
|
|
|
|
section_mark_present(ms);
|
|
|
|
ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
|
|
|
|
out:
|
|
pgdat_resize_unlock(pgdat, &flags);
|
|
if (ret <= 0) {
|
|
kfree(usemap);
|
|
__kfree_section_memmap(memmap);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
|
|
{
|
|
int i;
|
|
|
|
if (!memmap)
|
|
return;
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
if (PageHWPoison(&memmap[i])) {
|
|
atomic_long_sub(1, &num_poisoned_pages);
|
|
ClearPageHWPoison(&memmap[i]);
|
|
}
|
|
}
|
|
}
|
|
#else
|
|
static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
static void free_section_usemap(struct page *memmap, unsigned long *usemap)
|
|
{
|
|
struct page *usemap_page;
|
|
|
|
if (!usemap)
|
|
return;
|
|
|
|
usemap_page = virt_to_page(usemap);
|
|
/*
|
|
* Check to see if allocation came from hot-plug-add
|
|
*/
|
|
if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
|
|
kfree(usemap);
|
|
if (memmap)
|
|
__kfree_section_memmap(memmap);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* The usemap came from bootmem. This is packed with other usemaps
|
|
* on the section which has pgdat at boot time. Just keep it as is now.
|
|
*/
|
|
|
|
if (memmap)
|
|
free_map_bootmem(memmap);
|
|
}
|
|
|
|
void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
|
|
unsigned long map_offset)
|
|
{
|
|
struct page *memmap = NULL;
|
|
unsigned long *usemap = NULL, flags;
|
|
struct pglist_data *pgdat = zone->zone_pgdat;
|
|
|
|
pgdat_resize_lock(pgdat, &flags);
|
|
if (ms->section_mem_map) {
|
|
usemap = ms->pageblock_flags;
|
|
memmap = sparse_decode_mem_map(ms->section_mem_map,
|
|
__section_nr(ms));
|
|
ms->section_mem_map = 0;
|
|
ms->pageblock_flags = NULL;
|
|
}
|
|
pgdat_resize_unlock(pgdat, &flags);
|
|
|
|
clear_hwpoisoned_pages(memmap + map_offset,
|
|
PAGES_PER_SECTION - map_offset);
|
|
free_section_usemap(memmap, usemap);
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|