linux/arch/x86/mm/init_64.c

1020 lines
25 KiB
C
Raw Normal View History

/*
* linux/arch/x86_64/mm/init.c
*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
* Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/cacheflush.h>
#include <asm/init.h>
#include <linux/bootmem.h>
static unsigned long dma_reserve __initdata;
static int __init parse_direct_gbpages_off(char *arg)
{
direct_gbpages = 0;
return 0;
}
early_param("nogbpages", parse_direct_gbpages_off);
static int __init parse_direct_gbpages_on(char *arg)
{
direct_gbpages = 1;
return 0;
}
early_param("gbpages", parse_direct_gbpages_on);
/*
* NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
* physical space so we can cache the place of the first one and move
* around without checking the pgd every time.
*/
pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
int force_personality32;
/*
* noexec32=on|off
* Control non executable heap for 32bit processes.
* To control the stack too use noexec=off
*
* on PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
* off PROT_READ implies PROT_EXEC
*/
static int __init nonx32_setup(char *str)
{
if (!strcmp(str, "on"))
force_personality32 &= ~READ_IMPLIES_EXEC;
else if (!strcmp(str, "off"))
force_personality32 |= READ_IMPLIES_EXEC;
return 1;
}
__setup("noexec32=", nonx32_setup);
/*
* NOTE: This function is marked __ref because it calls __init function
* (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
*/
static __ref void *spp_getpage(void)
{
void *ptr;
if (after_bootmem)
ptr = (void *) get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
else
ptr = alloc_bootmem_pages(PAGE_SIZE);
if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
panic("set_pte_phys: cannot allocate page data %s\n",
after_bootmem ? "after bootmem" : "");
}
pr_debug("spp_getpage %p\n", ptr);
return ptr;
}
static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr)
{
if (pgd_none(*pgd)) {
pud_t *pud = (pud_t *)spp_getpage();
pgd_populate(&init_mm, pgd, pud);
if (pud != pud_offset(pgd, 0))
printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
pud, pud_offset(pgd, 0));
}
return pud_offset(pgd, vaddr);
}
static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
{
if (pud_none(*pud)) {
pmd_t *pmd = (pmd_t *) spp_getpage();
pud_populate(&init_mm, pud, pmd);
if (pmd != pmd_offset(pud, 0))
printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
pmd, pmd_offset(pud, 0));
}
return pmd_offset(pud, vaddr);
}
static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
{
if (pmd_none(*pmd)) {
pte_t *pte = (pte_t *) spp_getpage();
pmd_populate_kernel(&init_mm, pmd, pte);
if (pte != pte_offset_kernel(pmd, 0))
printk(KERN_ERR "PAGETABLE BUG #02!\n");
}
return pte_offset_kernel(pmd, vaddr);
}
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
{
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
pud = pud_page + pud_index(vaddr);
pmd = fill_pmd(pud, vaddr);
pte = fill_pte(pmd, vaddr);
set_pte(pte, new_pte);
/*
* It's enough to flush this one mapping.
* (PGE mappings get flushed as well)
*/
__flush_tlb_one(vaddr);
}
void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
{
pgd_t *pgd;
pud_t *pud_page;
pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));
pgd = pgd_offset_k(vaddr);
if (pgd_none(*pgd)) {
printk(KERN_ERR
"PGD FIXMAP MISSING, it should be setup in head.S!\n");
return;
}
pud_page = (pud_t*)pgd_page_vaddr(*pgd);
set_pte_vaddr_pud(pud_page, vaddr, pteval);
}
pmd_t * __init populate_extra_pmd(unsigned long vaddr)
{
pgd_t *pgd;
pud_t *pud;
pgd = pgd_offset_k(vaddr);
pud = fill_pud(pgd, vaddr);
return fill_pmd(pud, vaddr);
}
pte_t * __init populate_extra_pte(unsigned long vaddr)
{
pmd_t *pmd;
pmd = populate_extra_pmd(vaddr);
return fill_pte(pmd, vaddr);
}
/*
* Create large page table mappings for a range of physical addresses.
*/
static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
pgprot_t prot)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
pgd = pgd_offset_k((unsigned long)__va(phys));
if (pgd_none(*pgd)) {
pud = (pud_t *) spp_getpage();
set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
_PAGE_USER));
}
pud = pud_offset(pgd, (unsigned long)__va(phys));
if (pud_none(*pud)) {
pmd = (pmd_t *) spp_getpage();
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
_PAGE_USER));
}
pmd = pmd_offset(pud, phys);
BUG_ON(!pmd_none(*pmd));
set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
}
}
void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
{
__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
}
void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
{
__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
}
/*
* The head.S code sets up the kernel high mapping:
*
* from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
*
* phys_addr holds the negative offset to the kernel, which is added
* to the compile time generated pmds. This results in invalid pmds up
* to the point where we hit the physaddr 0 mapping.
*
* We limit the mappings to the region from _text to _end. _end is
* rounded up to the 2MB boundary. This catches the invalid pmds as
* well, as they are located before _text:
*/
void __init cleanup_highmap(void)
{
unsigned long vaddr = __START_KERNEL_map;
unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
pmd_t *pmd = level2_kernel_pgt;
pmd_t *last_pmd = pmd + PTRS_PER_PMD;
for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
if (vaddr < (unsigned long) _text || vaddr > end)
set_pmd(pmd, __pmd(0));
}
}
static __ref void *alloc_low_page(unsigned long *phys)
{
unsigned long pfn = e820_table_end++;
void *adr;
if (after_bootmem) {
adr = (void *)get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
*phys = __pa(adr);
return adr;
}
if (pfn >= e820_table_top)
panic("alloc_low_page: ran out of memory");
adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
*phys = pfn * PAGE_SIZE;
return adr;
}
static __ref void unmap_low_page(void *adr)
{
if (after_bootmem)
return;
early_iounmap(adr, PAGE_SIZE);
}
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
pgprot_t prot)
{
unsigned pages = 0;
unsigned long last_map_addr = end;
int i;
pte_t *pte = pte_page + pte_index(addr);
for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {
if (addr >= end) {
if (!after_bootmem) {
for(; i < PTRS_PER_PTE; i++, pte++)
set_pte(pte, __pte(0));
}
break;
}
/*
* We will re-use the existing mapping.
* Xen for example has some special requirements, like mapping
* pagetable pages as RO. So assume someone who pre-setup
* these mappings are more intelligent.
*/
if (pte_val(*pte)) {
pages++;
continue;
}
if (0)
printk(" pte=%p addr=%lx pte=%016lx\n",
pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
pages++;
set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
}
update_page_count(PG_LEVEL_4K, pages);
return last_map_addr;
}
static unsigned long __meminit
phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
pgprot_t prot)
{
pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
return phys_pte_init(pte, address, end, prot);
}
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
unsigned long page_size_mask, pgprot_t prot)
{
unsigned long pages = 0;
unsigned long last_map_addr = end;
int i = pmd_index(address);
for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
pgprot_t new_prot = prot;
if (address >= end) {
if (!after_bootmem) {
for (; i < PTRS_PER_PMD; i++, pmd++)
set_pmd(pmd, __pmd(0));
}
break;
}
if (pmd_val(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
last_map_addr = phys_pte_update(pmd, address,
end, prot);
spin_unlock(&init_mm.page_table_lock);
continue;
}
/*
* If we are ok with PG_LEVEL_2M mapping, then we will
* use the existing mapping,
*
* Otherwise, we will split the large page mapping but
* use the same existing protection bits except for
* large page, so that we don't violate Intel's TLB
* Application note (317080) which says, while changing
* the page sizes, new and old translations should
* not differ with respect to page frame and
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_2M)) {
pages++;
continue;
}
new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
}
if (page_size_mask & (1<<PG_LEVEL_2M)) {
pages++;
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pmd,
pfn_pte(address >> PAGE_SHIFT,
__pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = (address & PMD_MASK) + PMD_SIZE;
continue;
}
pte = alloc_low_page(&pte_phys);
last_map_addr = phys_pte_init(pte, address, end, new_prot);
unmap_low_page(pte);
spin_lock(&init_mm.page_table_lock);
pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
spin_unlock(&init_mm.page_table_lock);
}
update_page_count(PG_LEVEL_2M, pages);
return last_map_addr;
}
static unsigned long __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
unsigned long page_size_mask, pgprot_t prot)
{
pmd_t *pmd = pmd_offset(pud, 0);
unsigned long last_map_addr;
last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
__flush_tlb_all();
return last_map_addr;
}
static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
unsigned long page_size_mask)
{
unsigned long pages = 0;
unsigned long last_map_addr = end;
int i = pud_index(addr);
for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
pgprot_t prot = PAGE_KERNEL;
if (addr >= end)
break;
if (!after_bootmem &&
!e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
set_pud(pud, __pud(0));
continue;
}
if (pud_val(*pud)) {
if (!pud_large(*pud)) {
last_map_addr = phys_pmd_update(pud, addr, end,
page_size_mask, prot);
continue;
}
/*
* If we are ok with PG_LEVEL_1G mapping, then we will
* use the existing mapping.
*
* Otherwise, we will split the gbpage mapping but use
* the same existing protection bits except for large
* page, so that we don't violate Intel's TLB
* Application note (317080) which says, while changing
* the page sizes, new and old translations should
* not differ with respect to page frame and
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_1G)) {
pages++;
continue;
}
prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
}
if (page_size_mask & (1<<PG_LEVEL_1G)) {
pages++;
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pud,
pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
continue;
}
pmd = alloc_low_page(&pmd_phys);
last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
prot);
unmap_low_page(pmd);
spin_lock(&init_mm.page_table_lock);
pud_populate(&init_mm, pud, __va(pmd_phys));
spin_unlock(&init_mm.page_table_lock);
}
__flush_tlb_all();
update_page_count(PG_LEVEL_1G, pages);
return last_map_addr;
}
static unsigned long __meminit
phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
unsigned long page_size_mask)
{
pud_t *pud;
pud = (pud_t *)pgd_page_vaddr(*pgd);
return phys_pud_init(pud, addr, end, page_size_mask);
}
unsigned long __meminit
kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
unsigned long next, last_map_addr = end;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
unsigned long pud_phys;
pud_t *pud;
next = (start + PGDIR_SIZE) & PGDIR_MASK;
if (next > end)
next = end;
if (pgd_val(*pgd)) {
last_map_addr = phys_pud_update(pgd, __pa(start),
__pa(end), page_size_mask);
continue;
}
pud = alloc_low_page(&pud_phys);
last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
page_size_mask);
unmap_low_page(pud);
spin_lock(&init_mm.page_table_lock);
pgd_populate(&init_mm, pgd, __va(pud_phys));
spin_unlock(&init_mm.page_table_lock);
}
__flush_tlb_all();
return last_map_addr;
}
#ifndef CONFIG_NUMA
x86: Export k8 physical topology To eventually interleave emulated nodes over physical nodes, we need to know the physical topology of the machine without actually registering it. This does the k8 node setup in two parts: detection and registration. NUMA emulation can then used the physical topology detected to setup the address ranges of emulated nodes accordingly. If emulation isn't used, the k8 nodes are registered as normal. Two formals are added to the x86 NUMA setup functions: `acpi' and `k8'. These represent whether ACPI or K8 NUMA has been detected; both cannot be true at the same time. This specifies to the NUMA emulation code whether an underlying physical NUMA topology exists and which interface to use. This patch deals solely with separating the k8 setup path into Northbridge detection and registration steps and leaves the ACPI changes for a subsequent patch. The `acpi' formal is added here, however, to avoid touching all the header files again in the next patch. This approach also ensures emulated nodes will not span physical nodes so the true memory latency is not misrepresented. k8_get_nodes() may now be used to export the k8 physical topology of the machine for NUMA emulation. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andreas Herrmann <andreas.herrmann3@amd.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Ankita Garg <ankita@in.ibm.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <alpine.DEB.1.00.0909251518400.14754@chino.kir.corp.google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-25 22:20:00 +00:00
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
int acpi, int k8)
{
#ifndef CONFIG_NO_BOOTMEM
unsigned long bootmap_size, bootmap;
bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
/* don't touch min_low_pfn */
bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
0, end_pfn);
e820_register_active_regions(0, start_pfn, end_pfn);
free_bootmem_with_active_regions(0, end_pfn);
#else
e820_register_active_regions(0, start_pfn, end_pfn);
#endif
}
#endif
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
max_zone_pfns[ZONE_NORMAL] = max_pfn;
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
/*
* clear the default setting with node 0
* note: don't use nodes_clear here, that is really clearing when
* numa support is not compiled in, and later node_set_state
* will not set it back.
*/
node_clear_state(0, N_NORMAL_MEMORY);
free_area_init_nodes(max_zone_pfns);
}
/*
* Memory hotplug specific functions
*/
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
* updating.
*/
static void update_end_of_memory_vars(u64 start, u64 size)
{
unsigned long end_pfn = PFN_UP(start + size);
if (end_pfn > max_pfn) {
max_pfn = end_pfn;
max_low_pfn = end_pfn;
high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
}
}
/*
* Memory is added always to NORMAL zone. This means you will never get
* additional DMA/DMA32 memory.
*/
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdat = NODE_DATA(nid);
[PATCH] reduce MAX_NR_ZONES: remove two strange uses of MAX_NR_ZONES I keep seeing zones on various platforms that are never used and wonder why we compile support for them into the kernel. Counters show up for HIGHMEM and DMA32 that are alway zero. This patch allows the removal of ZONE_DMA32 for non x86_64 architectures and it will get rid of ZONE_HIGHMEM for arches not using highmem (like 64 bit architectures). If an arch does not define CONFIG_HIGHMEM then ZONE_HIGHMEM will not be defined. Similarly if an arch does not define CONFIG_ZONE_DMA32 then ZONE_DMA32 will not be defined. No current architecture uses all the 4 zones (DMA,DMA32,NORMAL,HIGH) that we have now. The patchset will reduce the number of zones for all platforms. On many platforms that do not have DMA32 or HIGHMEM this will reduce the number of zones by 50%. F.e. ia64 only uses DMA and NORMAL. Large amounts of memory can be saved for larger systemss that may have a few hundred NUMA nodes. With ZONE_DMA32 and ZONE_HIGHMEM support optional MAX_NR_ZONES will be 2 for many non i386 platforms and even for i386 without CONFIG_HIGHMEM set. Tested on ia64, x86_64 and on i386 with and without highmem. The patchset consists of 11 patches that are following this message. One could go even further than this patchset and also make ZONE_DMA optional because some platforms do not need a separate DMA zone and can do DMA to all of memory. This could reduce MAX_NR_ZONES to 1. Such a patchset will hopefully follow soon. This patch: Fix strange uses of MAX_NR_ZONES Sometimes we use MAX_NR_ZONES - x to refer to a zone. Make that explicit. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:31:09 +00:00
struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
last_mapped_pfn = init_memory_mapping(start, start + size);
if (last_mapped_pfn > max_pfn_mapped)
max_pfn_mapped = last_mapped_pfn;
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:14 +00:00
ret = __add_pages(nid, zone, start_pfn, nr_pages);
WARN_ON_ONCE(ret);
/* update max_pfn, max_low_pfn and high_memory */
update_end_of_memory_vars(start, size);
return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);
#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
int memory_add_physaddr_to_nid(u64 start)
{
return 0;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
static struct kcore_list kcore_vsyscall;
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
unsigned long absent_pages;
pci_iommu_alloc();
/* clear_bss() already clear the empty_zero_page */
reservedpages = 0;
/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
totalram_pages = numa_free_all_bootmem();
#else
totalram_pages = free_all_bootmem();
#endif
absent_pages = absent_pages_in_range(0, max_pfn);
reservedpages = max_pfn - totalram_pages - absent_pages;
after_bootmem = 1;
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
/* Register memory areas for /proc/kcore */
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
"%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
nr_free_pages() << (PAGE_SHIFT-10),
max_pfn << (PAGE_SHIFT-10),
codesize >> 10,
absent_pages << (PAGE_SHIFT-10),
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
}
#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
int kernel_set_to_readonly;
void set_kernel_text_rw(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long end = PFN_ALIGN(__stop___ex_table);
if (!kernel_set_to_readonly)
return;
pr_debug("Set kernel text: %lx - %lx for read write\n",
start, end);
/*
* Make the kernel identity mapping for text RW. Kernel text
* mapping will always be RO. Refer to the comment in
* static_protections() in pageattr.c
*/
set_memory_rw(start, (end - start) >> PAGE_SHIFT);
}
void set_kernel_text_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long end = PFN_ALIGN(__stop___ex_table);
if (!kernel_set_to_readonly)
return;
pr_debug("Set kernel text: %lx - %lx for read only\n",
start, end);
/*
* Set the kernel identity mapping for text RO.
*/
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
}
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long rodata_start =
((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
unsigned long data_start = (unsigned long) &_sdata;
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
kernel_set_to_readonly = 1;
/*
* The rodata section (but not the kernel text!) should also be
* not-executable.
*/
set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
rodata_test();
#ifdef CONFIG_CPA_DEBUG
printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
set_memory_rw(start, (end-start) >> PAGE_SHIFT);
printk(KERN_INFO "Testing CPA: again\n");
set_memory_ro(start, (end-start) >> PAGE_SHIFT);
#endif
free_init_pages("unused kernel memory",
(unsigned long) page_address(virt_to_page(text_end)),
(unsigned long)
page_address(virt_to_page(rodata_start)));
free_init_pages("unused kernel memory",
(unsigned long) page_address(virt_to_page(rodata_end)),
(unsigned long) page_address(virt_to_page(data_start)));
}
#endif
int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
int flags)
{
#ifdef CONFIG_NUMA
int nid, next_nid;
int ret;
#endif
unsigned long pfn = phys >> PAGE_SHIFT;
if (pfn >= max_pfn) {
/*
* This can happen with kdump kernels when accessing
* firmware tables:
*/
if (pfn < max_pfn_mapped)
return -EFAULT;
printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
phys, len);
return -EFAULT;
}
/* Should check here against the e820 map to avoid double free */
#ifdef CONFIG_NUMA
nid = phys_to_nid(phys);
next_nid = phys_to_nid(phys + len - 1);
if (nid == next_nid)
ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
else
ret = reserve_bootmem(phys, len, flags);
if (ret != 0)
return ret;
#else
reserve_bootmem(phys, len, flags);
#endif
if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
dma_reserve += len / PAGE_SIZE;
set_dma_reserve(dma_reserve);
}
return 0;
}
int kern_addr_valid(unsigned long addr)
{
unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (above != 0 && above != -1UL)
return 0;
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd))
return 0;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
return 0;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return 0;
if (pmd_large(*pmd))
return pfn_valid(pmd_pfn(*pmd));
pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte))
return 0;
return pfn_valid(pte_pfn(*pte));
}
/*
* A pseudo VMA to allow ptrace access for the vsyscall page. This only
* covers the 64bit vsyscall page now. 32bit has a real VMA now and does
* not need special handling anymore:
*/
static struct vm_area_struct gate_vma = {
.vm_start = VSYSCALL_START,
.vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC
};
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef CONFIG_IA32_EMULATION
if (test_tsk_thread_flag(tsk, TIF_IA32))
return NULL;
#endif
return &gate_vma;
}
int in_gate_area(struct task_struct *task, unsigned long addr)
{
struct vm_area_struct *vma = get_gate_vma(task);
if (!vma)
return 0;
return (addr >= vma->vm_start) && (addr < vma->vm_end);
}
/*
* Use this when you have no reliable task/vma, typically from interrupt
* context. It is less reliable than using the task's vma and may give
* false positives:
*/
int in_gate_area_no_task(unsigned long addr)
{
return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
return "[vdso]";
if (vma == &gate_vma)
return "[vsyscall]";
return NULL;
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
*/
x86_64/mm: check and print vmemmap allocation continuous On big systems with lots of memory, don't print out too much during bootup, and make it easy to find if it is continuous. on 256G 8 sockets system will get [ffffe20000000000-ffffe20002bfffff] PMD -> [ffff810001400000-ffff810003ffffff] on node 0 [ffffe2001c700000-ffffe2001c7fffff] potential offnode page_structs [ffffe20002c00000-ffffe2001c7fffff] PMD -> [ffff81000c000000-ffff8100255fffff] on node 0 [ffffe20038700000-ffffe200387fffff] potential offnode page_structs [ffffe2001c800000-ffffe200387fffff] PMD -> [ffff810820200000-ffff81083c1fffff] on node 1 [ffffe20040000000-ffffe2007fffffff] PUD ->ffff811027a00000 on node 2 [ffffe20038800000-ffffe2003fffffff] PMD -> [ffff811020200000-ffff8110279fffff] on node 2 [ffffe20054700000-ffffe200547fffff] potential offnode page_structs [ffffe20040000000-ffffe200547fffff] PMD -> [ffff811027c00000-ffff81103c3fffff] on node 2 [ffffe20070700000-ffffe200707fffff] potential offnode page_structs [ffffe20054800000-ffffe200707fffff] PMD -> [ffff811820200000-ffff81183c1fffff] on node 3 [ffffe20080000000-ffffe200bfffffff] PUD ->ffff81202fa00000 on node 4 [ffffe20070800000-ffffe2007fffffff] PMD -> [ffff812020200000-ffff81202f9fffff] on node 4 [ffffe2008c700000-ffffe2008c7fffff] potential offnode page_structs [ffffe20080000000-ffffe2008c7fffff] PMD -> [ffff81202fc00000-ffff81203c3fffff] on node 4 [ffffe200a8700000-ffffe200a87fffff] potential offnode page_structs [ffffe2008c800000-ffffe200a87fffff] PMD -> [ffff812820200000-ffff81283c1fffff] on node 5 [ffffe200c0000000-ffffe200ffffffff] PUD ->ffff813037a00000 on node 6 [ffffe200a8800000-ffffe200bfffffff] PMD -> [ffff813020200000-ffff8130379fffff] on node 6 [ffffe200c4700000-ffffe200c47fffff] potential offnode page_structs [ffffe200c0000000-ffffe200c47fffff] PMD -> [ffff813037c00000-ffff81303c3fffff] on node 6 [ffffe200c4800000-ffffe200e07fffff] PMD -> [ffff813820200000-ffff81383c1fffff] on node 7 instead of a very long print out... Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-12 08:19:24 +00:00
static long __meminitdata addr_start, addr_end;
static void __meminitdata *p_start, *p_end;
static int __meminitdata node_start;
int __meminit
vmemmap_populate(struct page *start_page, unsigned long size, int node)
{
unsigned long addr = (unsigned long)start_page;
unsigned long end = (unsigned long)(start_page + size);
unsigned long next;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
for (; addr < end; addr = next) {
void *p = NULL;
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
pud = vmemmap_pud_populate(pgd, addr, node);
if (!pud)
return -ENOMEM;
if (!cpu_has_pse) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
pmd = vmemmap_pmd_populate(pud, addr, node);
if (!pmd)
return -ENOMEM;
p = vmemmap_pte_populate(pmd, addr, node);
if (!p)
return -ENOMEM;
addr_end = addr + PAGE_SIZE;
p_end = p + PAGE_SIZE;
} else {
next = pmd_addr_end(addr, end);
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
pte_t entry;
sparsemem: Put mem map for one node together. Add vmemmap_alloc_block_buf for mem map only. It will fallback to the old way if it cannot get a block that big. Before this patch, when a node have 128g ram installed, memmap are split into two parts or more. [ 0.000000] [ffffea0000000000-ffffea003fffffff] PMD -> [ffff880100600000-ffff88013e9fffff] on node 1 [ 0.000000] [ffffea0040000000-ffffea006fffffff] PMD -> [ffff88013ec00000-ffff88016ebfffff] on node 1 [ 0.000000] [ffffea0070000000-ffffea007fffffff] PMD -> [ffff882000600000-ffff8820105fffff] on node 0 [ 0.000000] [ffffea0080000000-ffffea00bfffffff] PMD -> [ffff882010800000-ffff8820507fffff] on node 0 [ 0.000000] [ffffea00c0000000-ffffea00dfffffff] PMD -> [ffff882050a00000-ffff8820709fffff] on node 0 [ 0.000000] [ffffea00e0000000-ffffea00ffffffff] PMD -> [ffff884000600000-ffff8840205fffff] on node 2 [ 0.000000] [ffffea0100000000-ffffea013fffffff] PMD -> [ffff884020800000-ffff8840607fffff] on node 2 [ 0.000000] [ffffea0140000000-ffffea014fffffff] PMD -> [ffff884060a00000-ffff8840709fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea017fffffff] PMD -> [ffff886000600000-ffff8860305fffff] on node 3 [ 0.000000] [ffffea0180000000-ffffea01bfffffff] PMD -> [ffff886030800000-ffff8860707fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea01ffffffff] PMD -> [ffff888000600000-ffff8880405fffff] on node 4 [ 0.000000] [ffffea0200000000-ffffea022fffffff] PMD -> [ffff888040800000-ffff8880707fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea023fffffff] PMD -> [ffff88a000600000-ffff88a0105fffff] on node 5 [ 0.000000] [ffffea0240000000-ffffea027fffffff] PMD -> [ffff88a010800000-ffff88a0507fffff] on node 5 [ 0.000000] [ffffea0280000000-ffffea029fffffff] PMD -> [ffff88a050a00000-ffff88a0709fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea02bfffffff] PMD -> [ffff88c000600000-ffff88c0205fffff] on node 6 [ 0.000000] [ffffea02c0000000-ffffea02ffffffff] PMD -> [ffff88c020800000-ffff88c0607fffff] on node 6 [ 0.000000] [ffffea0300000000-ffffea030fffffff] PMD -> [ffff88c060a00000-ffff88c0709fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea033fffffff] PMD -> [ffff88e000600000-ffff88e0305fffff] on node 7 [ 0.000000] [ffffea0340000000-ffffea037fffffff] PMD -> [ffff88e030800000-ffff88e0707fffff] on node 7 after patch will get [ 0.000000] [ffffea0000000000-ffffea006fffffff] PMD -> [ffff880100200000-ffff88016e5fffff] on node 0 [ 0.000000] [ffffea0070000000-ffffea00dfffffff] PMD -> [ffff882000200000-ffff8820701fffff] on node 1 [ 0.000000] [ffffea00e0000000-ffffea014fffffff] PMD -> [ffff884000200000-ffff8840701fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea01bfffffff] PMD -> [ffff886000200000-ffff8860701fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea022fffffff] PMD -> [ffff888000200000-ffff8880701fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea029fffffff] PMD -> [ffff88a000200000-ffff88a0701fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea030fffffff] PMD -> [ffff88c000200000-ffff88c0701fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea037fffffff] PMD -> [ffff88e000200000-ffff88e0701fffff] on node 7 -v2: change buf to vmemmap_buf instead according to Ingo also add CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER according to Ingo -v3: according to Andrew, use sizeof(name) instead of hard coded 15 Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <1265793639-15071-19-git-send-email-yinghai@kernel.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-10 09:20:22 +00:00
p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (!p)
return -ENOMEM;
entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
PAGE_KERNEL_LARGE);
set_pmd(pmd, __pmd(pte_val(entry)));
/* check to see if we have contiguous blocks */
if (p_end != p || node_start != node) {
if (p_start)
printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
addr_start, addr_end-1, p_start, p_end-1, node_start);
addr_start = addr;
node_start = node;
p_start = p;
}
addr_end = addr + PMD_SIZE;
p_end = p + PMD_SIZE;
} else
vmemmap_verify((pte_t *)pmd, node, addr, next);
}
}
return 0;
}
x86_64/mm: check and print vmemmap allocation continuous On big systems with lots of memory, don't print out too much during bootup, and make it easy to find if it is continuous. on 256G 8 sockets system will get [ffffe20000000000-ffffe20002bfffff] PMD -> [ffff810001400000-ffff810003ffffff] on node 0 [ffffe2001c700000-ffffe2001c7fffff] potential offnode page_structs [ffffe20002c00000-ffffe2001c7fffff] PMD -> [ffff81000c000000-ffff8100255fffff] on node 0 [ffffe20038700000-ffffe200387fffff] potential offnode page_structs [ffffe2001c800000-ffffe200387fffff] PMD -> [ffff810820200000-ffff81083c1fffff] on node 1 [ffffe20040000000-ffffe2007fffffff] PUD ->ffff811027a00000 on node 2 [ffffe20038800000-ffffe2003fffffff] PMD -> [ffff811020200000-ffff8110279fffff] on node 2 [ffffe20054700000-ffffe200547fffff] potential offnode page_structs [ffffe20040000000-ffffe200547fffff] PMD -> [ffff811027c00000-ffff81103c3fffff] on node 2 [ffffe20070700000-ffffe200707fffff] potential offnode page_structs [ffffe20054800000-ffffe200707fffff] PMD -> [ffff811820200000-ffff81183c1fffff] on node 3 [ffffe20080000000-ffffe200bfffffff] PUD ->ffff81202fa00000 on node 4 [ffffe20070800000-ffffe2007fffffff] PMD -> [ffff812020200000-ffff81202f9fffff] on node 4 [ffffe2008c700000-ffffe2008c7fffff] potential offnode page_structs [ffffe20080000000-ffffe2008c7fffff] PMD -> [ffff81202fc00000-ffff81203c3fffff] on node 4 [ffffe200a8700000-ffffe200a87fffff] potential offnode page_structs [ffffe2008c800000-ffffe200a87fffff] PMD -> [ffff812820200000-ffff81283c1fffff] on node 5 [ffffe200c0000000-ffffe200ffffffff] PUD ->ffff813037a00000 on node 6 [ffffe200a8800000-ffffe200bfffffff] PMD -> [ffff813020200000-ffff8130379fffff] on node 6 [ffffe200c4700000-ffffe200c47fffff] potential offnode page_structs [ffffe200c0000000-ffffe200c47fffff] PMD -> [ffff813037c00000-ffff81303c3fffff] on node 6 [ffffe200c4800000-ffffe200e07fffff] PMD -> [ffff813820200000-ffff81383c1fffff] on node 7 instead of a very long print out... Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-12 08:19:24 +00:00
void __meminit vmemmap_populate_print_last(void)
{
if (p_start) {
printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
addr_start, addr_end-1, p_start, p_end-1, node_start);
p_start = NULL;
p_end = NULL;
node_start = 0;
}
}
#endif