linux/mm/sparse.c
Wen Congyang 8a356ce38e memory-hotplug: consider compound pages when free memmap
usemap could also be allocated as compound pages.  Should also consider
compound pages when freeing memmap.

If we don't fix it, there could be problems when we free vmemmap
pagetables which are stored in compound pages.  The old pagetables will
not be freed properly, and when we add the memory again, no new
pagetable will be created.  And the old pagetable entry is used, than
the kernel will panic.

The call trace is like the following:

  BUG: unable to handle kernel paging request at ffffea0040000000
  IP: [<ffffffff816a483f>] sparse_add_one_section+0xef/0x166
  PGD 7ff7d4067 PUD 78e035067 PMD 78e11d067 PTE 0
  Oops: 0002 [#1] SMP
  Modules linked in: ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel microcode pcspkr sg lpc_ich mfd_core i2c_i801 i2c_core i7core_edac edac_core ioatdma e1000e igb dca ptp pps_core sd_mod crc_t10dif megaraid_sas mptsas mptscsih mptbase scsi_transport_sas scsi_mod
  CPU 0
  Pid: 4, comm: kworker/0:0 Tainted: G        W 3.8.0-rc3-phy-hot-remove+ #3 FUJITSU-SV PRIMEQUEST 1800E/SB
  RIP: 0010:[<ffffffff816a483f>]  [<ffffffff816a483f>] sparse_add_one_section+0xef/0x166
  RSP: 0018:ffff8807bdcb35d8  EFLAGS: 00010006
  RAX: 0000000000000000 RBX: 0000000000000200 RCX: 0000000000200000
  RDX: ffff88078df01148 RSI: 0000000000000282 RDI: ffffea0040000000
  RBP: ffff8807bdcb3618 R08: 4cf05005b019467a R09: 0cd98fa09631467a
  R10: 0000000000000000 R11: 0000000000030e20 R12: 0000000000008000
  R13: ffffea0040000000 R14: ffff88078df66248 R15: ffff88078ea13b10
  FS:  0000000000000000(0000) GS:ffff8807c1a00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: ffffea0040000000 CR3: 0000000001c0c000 CR4: 00000000000007f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
  Process kworker/0:0 (pid: 4, threadinfo ffff8807bdcb2000, task ffff8807bde18000)
  Call Trace:
    __add_pages+0x85/0x120
    arch_add_memory+0x71/0xf0
    add_memory+0xd6/0x1f0
    acpi_memory_device_add+0x170/0x20c
    acpi_device_probe+0x50/0x18a
    really_probe+0x6c/0x320
    driver_probe_device+0x47/0xa0
    __device_attach+0x53/0x60
    bus_for_each_drv+0x6c/0xa0
    device_attach+0xa8/0xc0
    bus_probe_device+0xb0/0xe0
    device_add+0x301/0x570
    device_register+0x1e/0x30
    acpi_device_register+0x1d8/0x27c
    acpi_add_single_object+0x1df/0x2b9
    acpi_bus_check_add+0x112/0x18f
    acpi_ns_walk_namespace+0x105/0x255
    acpi_walk_namespace+0xcf/0x118
    acpi_bus_scan+0x5b/0x7c
    acpi_bus_add+0x2a/0x2c
    container_notify_cb+0x112/0x1a9
    acpi_ev_notify_dispatch+0x46/0x61
    acpi_os_execute_deferred+0x27/0x34
    process_one_work+0x20e/0x5c0
    worker_thread+0x12e/0x370
    kthread+0xee/0x100
    ret_from_fork+0x7c/0xb0
  Code: 00 00 48 89 df 48 89 45 c8 e8 3e 71 b1 ff 48 89 c2 48 8b 75 c8 b8 ef ff ff ff f6 02 01 75 4b 49 63 cc 31 c0 4c 89 ef 48 c1 e1 06 <f3> aa 48 8b 02 48 83 c8 01 48 85 d2 48 89 02 74 29 a8 01 74 25
  RIP  [<ffffffff816a483f>] sparse_add_one_section+0xef/0x166
   RSP <ffff8807bdcb35d8>
  CR2: ffffea0040000000
  ---[ end trace e7f94e3a34c442d4 ]---
  Kernel panic - not syncing: Fatal exception

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.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>
2013-02-23 17:50:13 -08:00

817 lines
21 KiB
C

/*
* sparse memory mappings.
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/mmzone.h>
#include <linux/bootmem.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 struct mem_section noinline __init_refok *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 = alloc_bootmem_node(NODE_DATA(nid), array_size);
}
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;
int ret = 0;
if (mem_section[root])
return -EEXIST;
section = sparse_index_alloc(nid);
if (!section)
return -ENOMEM;
mem_section[root] = section;
return ret;
}
#else /* !SPARSEMEM_EXTREME */
static inline int sparse_index_init(unsigned long section_nr, int nid)
{
return 0;
}
#endif
/*
* Although written for the SPARSEMEM_EXTREME case, this happens
* to also work for the flat array case because
* NR_SECTION_ROOTS==NR_MEM_SECTIONS.
*/
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);
}
/*
* 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;
}
}
/* 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_MARKED_PRESENT;
}
}
/*
* 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)
{
unsigned long size_bytes;
size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
size_bytes = roundup(size_bytes, sizeof(unsigned long));
return size_bytes;
}
#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 retmain 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 = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
SMP_CACHE_BYTES, goal, limit);
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) {
printk(KERN_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.
*/
printk(KERN_INFO "Section %ld and %ld (node %d)", usemap_snr,
pgdat_snr, nid);
printk(KERN_CONT
" have a circular dependency on usemap and pgdat allocations\n");
}
#else
static unsigned long * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
unsigned long size)
{
return alloc_bootmem_node_nopanic(pgdat, size);
}
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
unsigned long pnum_begin,
unsigned long pnum_end,
unsigned long usemap_count, int nodeid)
{
void *usemap;
unsigned long pnum;
int size = usemap_size();
usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
size * usemap_count);
if (!usemap) {
printk(KERN_WARNING "%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 = __alloc_bootmem_node_high(NODE_DATA(nid), size,
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
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 = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count,
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
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);
printk(KERN_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(struct page **map_map,
unsigned long pnum_begin,
unsigned long pnum_end,
unsigned long map_count, int nodeid)
{
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;
printk(KERN_ERR "%s: sparsemem memory map backing failed "
"some memory will not be available.\n", __func__);
ms->section_mem_map = 0;
return NULL;
}
#endif
void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
{
}
/*
* 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;
int nodeid_begin = 0;
unsigned long pnum_begin = 0;
unsigned long usemap_count;
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
unsigned long map_count;
int size2;
struct page **map_map;
#endif
/* 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 = alloc_bootmem(size);
if (!usemap_map)
panic("can not allocate usemap_map\n");
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
struct mem_section *ms;
if (!present_section_nr(pnum))
continue;
ms = __nr_to_section(pnum);
nodeid_begin = sparse_early_nid(ms);
pnum_begin = pnum;
break;
}
usemap_count = 1;
for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
struct mem_section *ms;
int nodeid;
if (!present_section_nr(pnum))
continue;
ms = __nr_to_section(pnum);
nodeid = sparse_early_nid(ms);
if (nodeid == nodeid_begin) {
usemap_count++;
continue;
}
/* ok, we need to take cake of from pnum_begin to pnum - 1*/
sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum,
usemap_count, nodeid_begin);
/* new start, update count etc*/
nodeid_begin = nodeid;
pnum_begin = pnum;
usemap_count = 1;
}
/* ok, last chunk */
sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
usemap_count, nodeid_begin);
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
map_map = alloc_bootmem(size2);
if (!map_map)
panic("can not allocate map_map\n");
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
struct mem_section *ms;
if (!present_section_nr(pnum))
continue;
ms = __nr_to_section(pnum);
nodeid_begin = sparse_early_nid(ms);
pnum_begin = pnum;
break;
}
map_count = 1;
for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
struct mem_section *ms;
int nodeid;
if (!present_section_nr(pnum))
continue;
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*/
sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
map_count, nodeid_begin);
/* new start, update count etc*/
nodeid_begin = nodeid;
pnum_begin = pnum;
map_count = 1;
}
/* ok, last chunk */
sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
map_count, nodeid_begin);
#endif
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
if (!present_section_nr(pnum))
continue;
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
free_bootmem(__pa(map_map), size2);
#endif
free_bootmem(__pa(usemap_map), size);
}
#ifdef CONFIG_MEMORY_HOTPLUG
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
unsigned long nr_pages)
{
/* This will make the necessary allocations eventually. */
return sparse_mem_map_populate(pnum, nid);
}
static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
{
vmemmap_free(memmap, nr_pages);
}
static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
{
vmemmap_free(memmap, nr_pages);
}
#else
static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
{
struct page *page, *ret;
unsigned long memmap_size = sizeof(struct page) * nr_pages;
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,
unsigned long nr_pages)
{
return __kmalloc_section_memmap(nr_pages);
}
static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
{
if (is_vmalloc_addr(memmap))
vfree(memmap);
else
free_pages((unsigned long)memmap,
get_order(sizeof(struct page) * nr_pages));
}
static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
{
unsigned long maps_section_nr, removing_section_nr, i;
unsigned long magic;
struct page *page = virt_to_page(memmap);
for (i = 0; i < nr_pages; i++, page++) {
magic = (unsigned long) page->lru.next;
BUG_ON(magic == NODE_INFO);
maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
removing_section_nr = page->private;
/*
* 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_SPARSEMEM_VMEMMAP */
static void free_section_usemap(struct page *memmap, unsigned long *usemap)
{
struct page *usemap_page;
unsigned long nr_pages;
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, PAGES_PER_SECTION);
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) {
nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
>> PAGE_SHIFT;
free_map_bootmem(memmap, nr_pages);
}
}
/*
* 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 zone *zone, unsigned long start_pfn,
int nr_pages)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
struct pglist_data *pgdat = zone->zone_pgdat;
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, nr_pages);
if (!memmap)
return -ENOMEM;
usemap = __kmalloc_section_usemap();
if (!usemap) {
__kfree_section_memmap(memmap, nr_pages);
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) * nr_pages);
ms->section_mem_map |= SECTION_MARKED_PRESENT;
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, nr_pages);
}
return ret;
}
#ifdef CONFIG_MEMORY_FAILURE
static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
{
int i;
if (!memmap)
return;
for (i = 0; i < PAGES_PER_SECTION; i++) {
if (PageHWPoison(&memmap[i])) {
atomic_long_sub(1, &mce_bad_pages);
ClearPageHWPoison(&memmap[i]);
}
}
}
#else
static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
{
}
#endif
void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
{
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, PAGES_PER_SECTION);
free_section_usemap(memmap, usemap);
}
#endif