2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/arch/x86/mm/init_64.c

1419 lines
34 KiB
C
Raw Normal View History

/*
* linux/arch/x86_64/mm/init.c
*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2000 Pavel Machek <pavel@ucw.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/memblock.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.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 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <asm/processor.h>
#include <asm/bios_ebda.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 <asm/uv/uv.h>
#include <asm/setup.h>
#include "mm_internal.h"
static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
unsigned long addr, unsigned long end)
{
addr &= PMD_MASK;
for (; addr < end; addr += PMD_SIZE) {
pmd_t *pmd = pmd_page + pmd_index(addr);
if (!pmd_present(*pmd))
set_pmd(pmd, __pmd(addr | pmd_flag));
}
}
static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
unsigned long addr, unsigned long end)
{
unsigned long next;
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
if (pud_present(*pud)) {
pmd = pmd_offset(pud, 0);
ident_pmd_init(info->pmd_flag, pmd, addr, next);
continue;
}
pmd = (pmd_t *)info->alloc_pgt_page(info->context);
if (!pmd)
return -ENOMEM;
ident_pmd_init(info->pmd_flag, pmd, addr, next);
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
}
return 0;
}
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
unsigned long addr, unsigned long end)
{
unsigned long next;
int result;
int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
for (; addr < end; addr = next) {
pgd_t *pgd = pgd_page + pgd_index(addr) + off;
pud_t *pud;
next = (addr & PGDIR_MASK) + PGDIR_SIZE;
if (next > end)
next = end;
if (pgd_present(*pgd)) {
pud = pud_offset(pgd, 0);
result = ident_pud_init(info, pud, addr, next);
if (result)
return result;
continue;
}
pud = (pud_t *)info->alloc_pgt_page(info->context);
if (!pud)
return -ENOMEM;
result = ident_pud_init(info, pud, addr, next);
if (result)
return result;
set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
}
return 0;
}
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);
/*
* When memory was added/removed make sure all the processes MM have
* suitable PGD entries in the local PGD level page.
*/
void sync_global_pgds(unsigned long start, unsigned long end)
{
unsigned long address;
for (address = start; address <= end; address += PGDIR_SIZE) {
const pgd_t *pgd_ref = pgd_offset_k(address);
struct page *page;
if (pgd_none(*pgd_ref))
continue;
spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
pgd_t *pgd;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(address);
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
if (pgd_none(*pgd))
set_pgd(pgd, *pgd_ref);
else
BUG_ON(pgd_page_vaddr(*pgd)
!= pgd_page_vaddr(*pgd_ref));
spin_unlock(pgt_lock);
}
spin_unlock(&pgd_lock);
}
}
/*
* 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_base 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 _brk_end. _brk_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 vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE;
unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
pmd_t *pmd = level2_kernel_pgt;
/*
* Native path, max_pfn_mapped is not set yet.
* Xen has valid max_pfn_mapped set in
* arch/x86/xen/mmu.c:xen_setup_kernel_pagetable().
*/
if (max_pfn_mapped)
vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
if (vaddr < (unsigned long) _text || vaddr > end)
set_pmd(pmd, __pmd(0));
}
}
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
pgprot_t prot)
{
unsigned long pages = 0, next;
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 = next, pte++) {
next = (addr & PAGE_MASK) + PAGE_SIZE;
if (addr >= end) {
if (!after_bootmem &&
!e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
!e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
set_pte(pte, __pte(0));
continue;
}
/*
* 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)) {
if (!after_bootmem)
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_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
unsigned long page_size_mask, pgprot_t prot)
{
unsigned long pages = 0, next;
unsigned long last_map_addr = end;
int i = pmd_index(address);
for (; i < PTRS_PER_PMD; i++, address = next) {
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
pgprot_t new_prot = prot;
next = (address & PMD_MASK) + PMD_SIZE;
if (address >= end) {
if (!after_bootmem &&
!e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
!e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
set_pmd(pmd, __pmd(0));
continue;
}
if (pmd_val(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
pte = (pte_t *)pmd_page_vaddr(*pmd);
x86-64, mm: Put early page table high While dubug kdump, found current kernel will have problem with crashkernel=512M. It turns out that initial mapping is to 512M, and later initial mapping to 4G (acutally is 2040M in my platform), will put page table near 512M. then initial mapping to 128g will be near 2g. before this patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x1fffc000-0x1fffffff] [ 0.000000] memblock_x86_reserve_range: [0x1fffc000-0x1fffdfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x7bc01000-0x7bc83fff] [ 0.000000] memblock_x86_reserve_range: [0x7bc01000-0x7bc7efff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] crashkernel reservation failed - No suitable area found. after patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] memblock_x86_reserve_range: [0x7f74c000-0x7f74dfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ff7d000-0x207fffafff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] memblock_x86_reserve_range: [0x17000000-0x36ffffff] CRASH KERNEL [ 0.000000] Reserving 512MB of memory at 368MB for crashkernel (System RAM: 133120MB) It means with the patch, page table for [0, 2g) will need 2g, instead of under 512M, page table for [4g, 128g) will be near 128g, instead of under 2g. That would good, if we have lots of memory above 4g, like 1024g, or 2048g or 16T, will not put related page table under 2g. that would be have chance to fill the under 2g if 1G or 2M page is not used. the code change will use add map_low_page() and update unmap_low_page() for 64bit, and use them to get access the corresponding high memory for page table setting. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0734.7060900@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 08:58:28 +08:00
last_map_addr = phys_pte_init(pte, 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)) {
if (!after_bootmem)
pages++;
last_map_addr = next;
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 & PMD_MASK) >> PAGE_SHIFT,
__pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = next;
continue;
}
pte = alloc_low_page();
last_map_addr = phys_pte_init(pte, address, end, new_prot);
spin_lock(&init_mm.page_table_lock);
pmd_populate_kernel(&init_mm, pmd, pte);
spin_unlock(&init_mm.page_table_lock);
}
update_page_count(PG_LEVEL_2M, pages);
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, next;
unsigned long last_map_addr = end;
int i = pud_index(addr);
for (; i < PTRS_PER_PUD; i++, addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
pgprot_t prot = PAGE_KERNEL;
next = (addr & PUD_MASK) + PUD_SIZE;
if (addr >= end) {
if (!after_bootmem &&
!e820_any_mapped(addr & PUD_MASK, next, E820_RAM) &&
!e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN))
set_pud(pud, __pud(0));
continue;
}
if (pud_val(*pud)) {
if (!pud_large(*pud)) {
pmd = pmd_offset(pud, 0);
x86-64, mm: Put early page table high While dubug kdump, found current kernel will have problem with crashkernel=512M. It turns out that initial mapping is to 512M, and later initial mapping to 4G (acutally is 2040M in my platform), will put page table near 512M. then initial mapping to 128g will be near 2g. before this patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x1fffc000-0x1fffffff] [ 0.000000] memblock_x86_reserve_range: [0x1fffc000-0x1fffdfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x7bc01000-0x7bc83fff] [ 0.000000] memblock_x86_reserve_range: [0x7bc01000-0x7bc7efff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] crashkernel reservation failed - No suitable area found. after patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] memblock_x86_reserve_range: [0x7f74c000-0x7f74dfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ff7d000-0x207fffafff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] memblock_x86_reserve_range: [0x17000000-0x36ffffff] CRASH KERNEL [ 0.000000] Reserving 512MB of memory at 368MB for crashkernel (System RAM: 133120MB) It means with the patch, page table for [0, 2g) will need 2g, instead of under 512M, page table for [4g, 128g) will be near 128g, instead of under 2g. That would good, if we have lots of memory above 4g, like 1024g, or 2048g or 16T, will not put related page table under 2g. that would be have chance to fill the under 2g if 1G or 2M page is not used. the code change will use add map_low_page() and update unmap_low_page() for 64bit, and use them to get access the corresponding high memory for page table setting. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0734.7060900@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 08:58:28 +08:00
last_map_addr = phys_pmd_init(pmd, addr, end,
page_size_mask, prot);
x86-64, mm: Put early page table high While dubug kdump, found current kernel will have problem with crashkernel=512M. It turns out that initial mapping is to 512M, and later initial mapping to 4G (acutally is 2040M in my platform), will put page table near 512M. then initial mapping to 128g will be near 2g. before this patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x1fffc000-0x1fffffff] [ 0.000000] memblock_x86_reserve_range: [0x1fffc000-0x1fffdfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x7bc01000-0x7bc83fff] [ 0.000000] memblock_x86_reserve_range: [0x7bc01000-0x7bc7efff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] crashkernel reservation failed - No suitable area found. after patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] memblock_x86_reserve_range: [0x7f74c000-0x7f74dfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ff7d000-0x207fffafff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] memblock_x86_reserve_range: [0x17000000-0x36ffffff] CRASH KERNEL [ 0.000000] Reserving 512MB of memory at 368MB for crashkernel (System RAM: 133120MB) It means with the patch, page table for [0, 2g) will need 2g, instead of under 512M, page table for [4g, 128g) will be near 128g, instead of under 2g. That would good, if we have lots of memory above 4g, like 1024g, or 2048g or 16T, will not put related page table under 2g. that would be have chance to fill the under 2g if 1G or 2M page is not used. the code change will use add map_low_page() and update unmap_low_page() for 64bit, and use them to get access the corresponding high memory for page table setting. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0734.7060900@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 08:58:28 +08:00
__flush_tlb_all();
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)) {
if (!after_bootmem)
pages++;
last_map_addr = next;
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 & PUD_MASK) >> PAGE_SHIFT,
PAGE_KERNEL_LARGE));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = next;
continue;
}
pmd = alloc_low_page();
last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
prot);
spin_lock(&init_mm.page_table_lock);
pud_populate(&init_mm, pud, pmd);
spin_unlock(&init_mm.page_table_lock);
}
__flush_tlb_all();
update_page_count(PG_LEVEL_1G, pages);
return last_map_addr;
}
unsigned long __meminit
kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes When memory hotplug-adding happens for a large enough area that a new PGD entry is needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some CPUs oopsing like below when they have to access the unmapped areas. [ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534] [ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243229] irq event stamp: 8538759 [ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30 [ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146 [ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146 [ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34 [ 1139.243249] CPU 0: [ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R [ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69 [ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286 [ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000 [ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010 [ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000 [ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0 [ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001 [ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000 [ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0 [ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1139.243321] Call Trace: [ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69 [ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a [ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b [ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb [ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152 [ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75 [ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d [ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121 [ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a [ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f [ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b This patch makes sure to always replicate new direct mapping PGD entries to the PGDs of all processes, as well as ensures corresponding vmemmap mapping gets synced. V1: initial code by Andi Kleen. V2: fix several issues found in testing. V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all(). [ hpa: changed pgd_change from int to bool ] Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> LKML-Reference: <4C6E4FD8.6080100@linux.intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-08-20 17:50:16 +08:00
bool pgd_changed = false;
unsigned long next, last_map_addr = end;
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes When memory hotplug-adding happens for a large enough area that a new PGD entry is needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some CPUs oopsing like below when they have to access the unmapped areas. [ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534] [ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243229] irq event stamp: 8538759 [ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30 [ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146 [ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146 [ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34 [ 1139.243249] CPU 0: [ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R [ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69 [ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286 [ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000 [ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010 [ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000 [ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0 [ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001 [ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000 [ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0 [ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1139.243321] Call Trace: [ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69 [ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a [ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b [ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb [ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152 [ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75 [ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d [ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121 [ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a [ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f [ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b This patch makes sure to always replicate new direct mapping PGD entries to the PGDs of all processes, as well as ensures corresponding vmemmap mapping gets synced. V1: initial code by Andi Kleen. V2: fix several issues found in testing. V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all(). [ hpa: changed pgd_change from int to bool ] Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> LKML-Reference: <4C6E4FD8.6080100@linux.intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-08-20 17:50:16 +08:00
unsigned long addr;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
addr = start;
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
pud_t *pud;
next = (start & PGDIR_MASK) + PGDIR_SIZE;
if (pgd_val(*pgd)) {
pud = (pud_t *)pgd_page_vaddr(*pgd);
x86-64, mm: Put early page table high While dubug kdump, found current kernel will have problem with crashkernel=512M. It turns out that initial mapping is to 512M, and later initial mapping to 4G (acutally is 2040M in my platform), will put page table near 512M. then initial mapping to 128g will be near 2g. before this patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x1fffc000-0x1fffffff] [ 0.000000] memblock_x86_reserve_range: [0x1fffc000-0x1fffdfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x7bc01000-0x7bc83fff] [ 0.000000] memblock_x86_reserve_range: [0x7bc01000-0x7bc7efff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] crashkernel reservation failed - No suitable area found. after patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] memblock_x86_reserve_range: [0x7f74c000-0x7f74dfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ff7d000-0x207fffafff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] memblock_x86_reserve_range: [0x17000000-0x36ffffff] CRASH KERNEL [ 0.000000] Reserving 512MB of memory at 368MB for crashkernel (System RAM: 133120MB) It means with the patch, page table for [0, 2g) will need 2g, instead of under 512M, page table for [4g, 128g) will be near 128g, instead of under 2g. That would good, if we have lots of memory above 4g, like 1024g, or 2048g or 16T, will not put related page table under 2g. that would be have chance to fill the under 2g if 1G or 2M page is not used. the code change will use add map_low_page() and update unmap_low_page() for 64bit, and use them to get access the corresponding high memory for page table setting. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0734.7060900@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 08:58:28 +08:00
last_map_addr = phys_pud_init(pud, __pa(start),
__pa(end), page_size_mask);
continue;
}
pud = alloc_low_page();
last_map_addr = phys_pud_init(pud, __pa(start), __pa(end),
page_size_mask);
spin_lock(&init_mm.page_table_lock);
pgd_populate(&init_mm, pgd, pud);
spin_unlock(&init_mm.page_table_lock);
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes When memory hotplug-adding happens for a large enough area that a new PGD entry is needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some CPUs oopsing like below when they have to access the unmapped areas. [ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534] [ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243229] irq event stamp: 8538759 [ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30 [ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146 [ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146 [ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34 [ 1139.243249] CPU 0: [ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R [ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69 [ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286 [ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000 [ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010 [ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000 [ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0 [ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001 [ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000 [ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0 [ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1139.243321] Call Trace: [ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69 [ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a [ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b [ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb [ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152 [ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75 [ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d [ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121 [ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a [ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f [ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b This patch makes sure to always replicate new direct mapping PGD entries to the PGDs of all processes, as well as ensures corresponding vmemmap mapping gets synced. V1: initial code by Andi Kleen. V2: fix several issues found in testing. V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all(). [ hpa: changed pgd_change from int to bool ] Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> LKML-Reference: <4C6E4FD8.6080100@linux.intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-08-20 17:50:16 +08:00
pgd_changed = true;
}
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes When memory hotplug-adding happens for a large enough area that a new PGD entry is needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some CPUs oopsing like below when they have to access the unmapped areas. [ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534] [ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243229] irq event stamp: 8538759 [ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30 [ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146 [ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146 [ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34 [ 1139.243249] CPU 0: [ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R [ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69 [ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286 [ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000 [ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010 [ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000 [ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0 [ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001 [ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000 [ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0 [ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1139.243321] Call Trace: [ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69 [ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a [ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b [ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb [ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152 [ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75 [ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d [ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121 [ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a [ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f [ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b This patch makes sure to always replicate new direct mapping PGD entries to the PGDs of all processes, as well as ensures corresponding vmemmap mapping gets synced. V1: initial code by Andi Kleen. V2: fix several issues found in testing. V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all(). [ hpa: changed pgd_change from int to bool ] Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> LKML-Reference: <4C6E4FD8.6080100@linux.intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-08-20 17:50:16 +08:00
if (pgd_changed)
sync_global_pgds(addr, end - 1);
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes When memory hotplug-adding happens for a large enough area that a new PGD entry is needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some CPUs oopsing like below when they have to access the unmapped areas. [ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534] [ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243229] irq event stamp: 8538759 [ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30 [ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146 [ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146 [ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34 [ 1139.243249] CPU 0: [ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore [ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R [ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69 [ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286 [ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000 [ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010 [ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000 [ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0 [ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001 [ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000 [ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0 [ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1139.243321] Call Trace: [ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69 [ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a [ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b [ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb [ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152 [ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75 [ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d [ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121 [ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a [ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f [ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b This patch makes sure to always replicate new direct mapping PGD entries to the PGDs of all processes, as well as ensures corresponding vmemmap mapping gets synced. V1: initial code by Andi Kleen. V2: fix several issues found in testing. V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all(). [ hpa: changed pgd_change from int to bool ] Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> LKML-Reference: <4C6E4FD8.6080100@linux.intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-08-20 17:50:16 +08:00
__flush_tlb_all();
return last_map_addr;
}
#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
}
#endif
void __init paging_init(void)
{
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_MEMORY);
if (N_MEMORY != N_NORMAL_MEMORY)
node_clear_state(0, N_NORMAL_MEMORY);
zone_sizes_init();
}
/*
* 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);
struct zone *zone = pgdat->node_zones +
zone_for_memory(nid, start, size, ZONE_NORMAL);
x86, mm: Only direct map addresses that are marked as E820_RAM Currently direct mappings are created for [ 0 to max_low_pfn<<PAGE_SHIFT ) and [ 4GB to max_pfn<<PAGE_SHIFT ), which may include regions that are not backed by actual DRAM. This is fine for holes under 4GB which are covered by fixed and variable range MTRRs to be UC. However, we run into trouble on higher memory addresses which cannot be covered by MTRRs. Our system with 1TB of RAM has an e820 that looks like this: BIOS-e820: [mem 0x0000000000000000-0x00000000000983ff] usable BIOS-e820: [mem 0x0000000000098400-0x000000000009ffff] reserved BIOS-e820: [mem 0x00000000000d0000-0x00000000000fffff] reserved BIOS-e820: [mem 0x0000000000100000-0x00000000c7ebffff] usable BIOS-e820: [mem 0x00000000c7ec0000-0x00000000c7ed7fff] ACPI data BIOS-e820: [mem 0x00000000c7ed8000-0x00000000c7ed9fff] ACPI NVS BIOS-e820: [mem 0x00000000c7eda000-0x00000000c7ffffff] reserved BIOS-e820: [mem 0x00000000fec00000-0x00000000fec0ffff] reserved BIOS-e820: [mem 0x00000000fee00000-0x00000000fee00fff] reserved BIOS-e820: [mem 0x00000000fff00000-0x00000000ffffffff] reserved BIOS-e820: [mem 0x0000000100000000-0x000000e037ffffff] usable BIOS-e820: [mem 0x000000e038000000-0x000000fcffffffff] reserved BIOS-e820: [mem 0x0000010000000000-0x0000011ffeffffff] usable and so direct mappings are created for huge memory hole between 0x000000e038000000 to 0x0000010000000000. Even though the kernel never generates memory accesses in that region, since the page tables mark them incorrectly as being WB, our (AMD) processor ends up causing a MCE while doing some memory bookkeeping/optimizations around that area. This patch iterates through e820 and only direct maps ranges that are marked as E820_RAM, and keeps track of those pfn ranges. Depending on the alignment of E820 ranges, this may possibly result in using smaller size (i.e. 4K instead of 2M or 1G) page tables. -v2: move changes from setup.c to mm/init.c, also use for_each_mem_pfn_range instead. - Yinghai Lu -v3: add calculate_all_table_space_size() to get correct needed page table size. - Yinghai Lu -v4: fix add_pfn_range_mapped() to get correct max_low_pfn_mapped when mem map does have hole under 4g that is found by Konard on xen domU with 8g ram. - Yinghai Signed-off-by: Jacob Shin <jacob.shin@amd.com> Link: http://lkml.kernel.org/r/1353123563-3103-16-git-send-email-yinghai@kernel.org Signed-off-by: Yinghai Lu <yinghai@kernel.org> Reviewed-by: Pekka Enberg <penberg@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-11-17 11:38:52 +08:00
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
x86, mm: Only direct map addresses that are marked as E820_RAM Currently direct mappings are created for [ 0 to max_low_pfn<<PAGE_SHIFT ) and [ 4GB to max_pfn<<PAGE_SHIFT ), which may include regions that are not backed by actual DRAM. This is fine for holes under 4GB which are covered by fixed and variable range MTRRs to be UC. However, we run into trouble on higher memory addresses which cannot be covered by MTRRs. Our system with 1TB of RAM has an e820 that looks like this: BIOS-e820: [mem 0x0000000000000000-0x00000000000983ff] usable BIOS-e820: [mem 0x0000000000098400-0x000000000009ffff] reserved BIOS-e820: [mem 0x00000000000d0000-0x00000000000fffff] reserved BIOS-e820: [mem 0x0000000000100000-0x00000000c7ebffff] usable BIOS-e820: [mem 0x00000000c7ec0000-0x00000000c7ed7fff] ACPI data BIOS-e820: [mem 0x00000000c7ed8000-0x00000000c7ed9fff] ACPI NVS BIOS-e820: [mem 0x00000000c7eda000-0x00000000c7ffffff] reserved BIOS-e820: [mem 0x00000000fec00000-0x00000000fec0ffff] reserved BIOS-e820: [mem 0x00000000fee00000-0x00000000fee00fff] reserved BIOS-e820: [mem 0x00000000fff00000-0x00000000ffffffff] reserved BIOS-e820: [mem 0x0000000100000000-0x000000e037ffffff] usable BIOS-e820: [mem 0x000000e038000000-0x000000fcffffffff] reserved BIOS-e820: [mem 0x0000010000000000-0x0000011ffeffffff] usable and so direct mappings are created for huge memory hole between 0x000000e038000000 to 0x0000010000000000. Even though the kernel never generates memory accesses in that region, since the page tables mark them incorrectly as being WB, our (AMD) processor ends up causing a MCE while doing some memory bookkeeping/optimizations around that area. This patch iterates through e820 and only direct maps ranges that are marked as E820_RAM, and keeps track of those pfn ranges. Depending on the alignment of E820 ranges, this may possibly result in using smaller size (i.e. 4K instead of 2M or 1G) page tables. -v2: move changes from setup.c to mm/init.c, also use for_each_mem_pfn_range instead. - Yinghai Lu -v3: add calculate_all_table_space_size() to get correct needed page table size. - Yinghai Lu -v4: fix add_pfn_range_mapped() to get correct max_low_pfn_mapped when mem map does have hole under 4g that is found by Konard on xen domU with 8g ram. - Yinghai Signed-off-by: Jacob Shin <jacob.shin@amd.com> Link: http://lkml.kernel.org/r/1353123563-3103-16-git-send-email-yinghai@kernel.org Signed-off-by: Yinghai Lu <yinghai@kernel.org> Reviewed-by: Pekka Enberg <penberg@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-11-17 11:38:52 +08:00
init_memory_mapping(start, start + size);
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>
2009-01-07 06:39:14 +08:00
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);
memory-hotplug: common APIs to support page tables hot-remove When memory is removed, the corresponding pagetables should alse be removed. This patch introduces some common APIs to support vmemmap pagetable and x86_64 architecture direct mapping pagetable removing. All pages of virtual mapping in removed memory cannot be freed if some pages used as PGD/PUD include not only removed memory but also other memory. So this patch uses the following way to check whether a page can be freed or not. 1) When removing memory, the page structs of the removed memory are filled with 0FD. 2) All page structs are filled with 0xFD on PT/PMD, PT/PMD can be cleared. In this case, the page used as PT/PMD can be freed. For direct mapping pages, update direct_pages_count[level] when we freed their pagetables. And do not free the pages again because they were freed when offlining. For vmemmap pages, free the pages and their pagetables. For larger pages, do not split them into smaller ones because there is no way to know if the larger page has been split. As a result, there is no way to decide when to split. We deal the larger pages in the following way: 1) For direct mapped pages, all the pages were freed when they were offlined. And since menmory offline is done section by section, all the memory ranges being removed are aligned to PAGE_SIZE. So only need to deal with unaligned pages when freeing vmemmap pages. 2) For vmemmap pages being used to store page_struct, if part of the larger page is still in use, just fill the unused part with 0xFD. And when the whole page is fulfilled with 0xFD, then free the larger page. [akpm@linux-foundation.org: fix typo in comment] [tangchen@cn.fujitsu.com: do not calculate direct mapping pages when freeing vmemmap pagetables] [tangchen@cn.fujitsu.com: do not free direct mapping pages twice] [tangchen@cn.fujitsu.com: do not free page split from hugepage one by one] [tangchen@cn.fujitsu.com: do not split pages when freeing pagetable pages] [akpm@linux-foundation.org: use pmd_page_vaddr()] [akpm@linux-foundation.org: fix used-uninitialised bug] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Wu Jianguo <wujianguo@huawei.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 08:33:04 +08:00
#define PAGE_INUSE 0xFD
static void __meminit free_pagetable(struct page *page, int order)
{
unsigned long magic;
unsigned int nr_pages = 1 << order;
/* bootmem page has reserved flag */
if (PageReserved(page)) {
__ClearPageReserved(page);
magic = (unsigned long)page->lru.next;
if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
while (nr_pages--)
put_page_bootmem(page++);
} else
mm: make __free_pages_bootmem() only available at boot time In order to simpilify management of totalram_pages and zone->managed_pages, make __free_pages_bootmem() only available at boot time. With this change applied, __free_pages_bootmem() will only be used by bootmem.c and nobootmem.c at boot time, so mark it as __init. Other callers of __free_pages_bootmem() have been converted to use free_reserved_page(), which handles totalram_pages and zone->managed_pages in a safer way. This patch also fix a bug in free_pagetable() for x86_64, which should increase zone->managed_pages instead of zone->present_pages when freeing reserved pages. And now we have managed_pages_count_lock to protect totalram_pages and zone->managed_pages, so remove the redundant ppb_lock lock in put_page_bootmem(). This greatly simplifies the locking rules. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tejun Heo <tj@kernel.org> Cc: Will Deacon <will.deacon@arm.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:17 +08:00
while (nr_pages--)
free_reserved_page(page++);
memory-hotplug: common APIs to support page tables hot-remove When memory is removed, the corresponding pagetables should alse be removed. This patch introduces some common APIs to support vmemmap pagetable and x86_64 architecture direct mapping pagetable removing. All pages of virtual mapping in removed memory cannot be freed if some pages used as PGD/PUD include not only removed memory but also other memory. So this patch uses the following way to check whether a page can be freed or not. 1) When removing memory, the page structs of the removed memory are filled with 0FD. 2) All page structs are filled with 0xFD on PT/PMD, PT/PMD can be cleared. In this case, the page used as PT/PMD can be freed. For direct mapping pages, update direct_pages_count[level] when we freed their pagetables. And do not free the pages again because they were freed when offlining. For vmemmap pages, free the pages and their pagetables. For larger pages, do not split them into smaller ones because there is no way to know if the larger page has been split. As a result, there is no way to decide when to split. We deal the larger pages in the following way: 1) For direct mapped pages, all the pages were freed when they were offlined. And since menmory offline is done section by section, all the memory ranges being removed are aligned to PAGE_SIZE. So only need to deal with unaligned pages when freeing vmemmap pages. 2) For vmemmap pages being used to store page_struct, if part of the larger page is still in use, just fill the unused part with 0xFD. And when the whole page is fulfilled with 0xFD, then free the larger page. [akpm@linux-foundation.org: fix typo in comment] [tangchen@cn.fujitsu.com: do not calculate direct mapping pages when freeing vmemmap pagetables] [tangchen@cn.fujitsu.com: do not free direct mapping pages twice] [tangchen@cn.fujitsu.com: do not free page split from hugepage one by one] [tangchen@cn.fujitsu.com: do not split pages when freeing pagetable pages] [akpm@linux-foundation.org: use pmd_page_vaddr()] [akpm@linux-foundation.org: fix used-uninitialised bug] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Wu Jianguo <wujianguo@huawei.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 08:33:04 +08:00
} else
free_pages((unsigned long)page_address(page), order);
}
static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
{
pte_t *pte;
int i;
for (i = 0; i < PTRS_PER_PTE; i++) {
pte = pte_start + i;
if (pte_val(*pte))
return;
}
/* free a pte talbe */
free_pagetable(pmd_page(*pmd), 0);
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
}
static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
{
pmd_t *pmd;
int i;
for (i = 0; i < PTRS_PER_PMD; i++) {
pmd = pmd_start + i;
if (pmd_val(*pmd))
return;
}
/* free a pmd talbe */
free_pagetable(pud_page(*pud), 0);
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
spin_unlock(&init_mm.page_table_lock);
}
/* Return true if pgd is changed, otherwise return false. */
static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
{
pud_t *pud;
int i;
for (i = 0; i < PTRS_PER_PUD; i++) {
pud = pud_start + i;
if (pud_val(*pud))
return false;
}
/* free a pud table */
free_pagetable(pgd_page(*pgd), 0);
spin_lock(&init_mm.page_table_lock);
pgd_clear(pgd);
spin_unlock(&init_mm.page_table_lock);
return true;
}
static void __meminit
remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
bool direct)
{
unsigned long next, pages = 0;
pte_t *pte;
void *page_addr;
phys_addr_t phys_addr;
pte = pte_start + pte_index(addr);
for (; addr < end; addr = next, pte++) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
if (next > end)
next = end;
if (!pte_present(*pte))
continue;
/*
* We mapped [0,1G) memory as identity mapping when
* initializing, in arch/x86/kernel/head_64.S. These
* pagetables cannot be removed.
*/
phys_addr = pte_val(*pte) + (addr & PAGE_MASK);
if (phys_addr < (phys_addr_t)0x40000000)
return;
if (IS_ALIGNED(addr, PAGE_SIZE) &&
IS_ALIGNED(next, PAGE_SIZE)) {
/*
* Do not free direct mapping pages since they were
* freed when offlining, or simplely not in use.
*/
if (!direct)
free_pagetable(pte_page(*pte), 0);
spin_lock(&init_mm.page_table_lock);
pte_clear(&init_mm, addr, pte);
spin_unlock(&init_mm.page_table_lock);
/* For non-direct mapping, pages means nothing. */
pages++;
} else {
/*
* If we are here, we are freeing vmemmap pages since
* direct mapped memory ranges to be freed are aligned.
*
* If we are not removing the whole page, it means
* other page structs in this page are being used and
* we canot remove them. So fill the unused page_structs
* with 0xFD, and remove the page when it is wholly
* filled with 0xFD.
*/
memset((void *)addr, PAGE_INUSE, next - addr);
page_addr = page_address(pte_page(*pte));
if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
free_pagetable(pte_page(*pte), 0);
spin_lock(&init_mm.page_table_lock);
pte_clear(&init_mm, addr, pte);
spin_unlock(&init_mm.page_table_lock);
}
}
}
/* Call free_pte_table() in remove_pmd_table(). */
flush_tlb_all();
if (direct)
update_page_count(PG_LEVEL_4K, -pages);
}
static void __meminit
remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
bool direct)
{
unsigned long next, pages = 0;
pte_t *pte_base;
pmd_t *pmd;
void *page_addr;
pmd = pmd_start + pmd_index(addr);
for (; addr < end; addr = next, pmd++) {
next = pmd_addr_end(addr, end);
if (!pmd_present(*pmd))
continue;
if (pmd_large(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
if (!direct)
free_pagetable(pmd_page(*pmd),
get_order(PMD_SIZE));
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
pages++;
} else {
/* If here, we are freeing vmemmap pages. */
memset((void *)addr, PAGE_INUSE, next - addr);
page_addr = page_address(pmd_page(*pmd));
if (!memchr_inv(page_addr, PAGE_INUSE,
PMD_SIZE)) {
free_pagetable(pmd_page(*pmd),
get_order(PMD_SIZE));
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
}
}
continue;
}
pte_base = (pte_t *)pmd_page_vaddr(*pmd);
remove_pte_table(pte_base, addr, next, direct);
free_pte_table(pte_base, pmd);
}
/* Call free_pmd_table() in remove_pud_table(). */
if (direct)
update_page_count(PG_LEVEL_2M, -pages);
}
static void __meminit
remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
bool direct)
{
unsigned long next, pages = 0;
pmd_t *pmd_base;
pud_t *pud;
void *page_addr;
pud = pud_start + pud_index(addr);
for (; addr < end; addr = next, pud++) {
next = pud_addr_end(addr, end);
if (!pud_present(*pud))
continue;
if (pud_large(*pud)) {
if (IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE)) {
if (!direct)
free_pagetable(pud_page(*pud),
get_order(PUD_SIZE));
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
spin_unlock(&init_mm.page_table_lock);
pages++;
} else {
/* If here, we are freeing vmemmap pages. */
memset((void *)addr, PAGE_INUSE, next - addr);
page_addr = page_address(pud_page(*pud));
if (!memchr_inv(page_addr, PAGE_INUSE,
PUD_SIZE)) {
free_pagetable(pud_page(*pud),
get_order(PUD_SIZE));
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
spin_unlock(&init_mm.page_table_lock);
}
}
continue;
}
pmd_base = (pmd_t *)pud_page_vaddr(*pud);
remove_pmd_table(pmd_base, addr, next, direct);
free_pmd_table(pmd_base, pud);
}
if (direct)
update_page_count(PG_LEVEL_1G, -pages);
}
/* start and end are both virtual address. */
static void __meminit
remove_pagetable(unsigned long start, unsigned long end, bool direct)
{
unsigned long next;
pgd_t *pgd;
pud_t *pud;
bool pgd_changed = false;
for (; start < end; start = next) {
next = pgd_addr_end(start, end);
pgd = pgd_offset_k(start);
if (!pgd_present(*pgd))
continue;
pud = (pud_t *)pgd_page_vaddr(*pgd);
remove_pud_table(pud, start, next, direct);
if (free_pud_table(pud, pgd))
pgd_changed = true;
}
if (pgd_changed)
sync_global_pgds(start, end - 1);
flush_tlb_all();
}
sparse-vmemmap: specify vmemmap population range in bytes The sparse code, when asking the architecture to populate the vmemmap, specifies the section range as a starting page and a number of pages. This is an awkward interface, because none of the arch-specific code actually thinks of the range in terms of 'struct page' units and always translates it to bytes first. In addition, later patches mix huge page and regular page backing for the vmemmap. For this, they need to call vmemmap_populate_basepages() on sub-section ranges with PAGE_SIZE and PMD_SIZE in mind. But these are not necessarily multiples of the 'struct page' size and so this unit is too coarse. Just translate the section range into bytes once in the generic sparse code, then pass byte ranges down the stack. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Bernhard Schmidt <Bernhard.Schmidt@lrz.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: David S. Miller <davem@davemloft.net> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:07:50 +08:00
void __ref vmemmap_free(unsigned long start, unsigned long end)
{
remove_pagetable(start, end, false);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
static void __meminit
kernel_physical_mapping_remove(unsigned long start, unsigned long end)
{
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
remove_pagetable(start, end, true);
}
int __ref arch_remove_memory(u64 start, u64 size)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
struct zone *zone;
int ret;
zone = page_zone(pfn_to_page(start_pfn));
kernel_physical_mapping_remove(start, start + size);
ret = __remove_pages(zone, start_pfn, nr_pages);
WARN_ON_ONCE(ret);
return ret;
}
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
static struct kcore_list kcore_vsyscall;
static void __init register_page_bootmem_info(void)
{
#ifdef CONFIG_NUMA
int i;
for_each_online_node(i)
register_page_bootmem_info_node(NODE_DATA(i));
#endif
}
void __init mem_init(void)
{
pci_iommu_alloc();
/* clear_bss() already clear the empty_zero_page */
register_page_bootmem_info();
/* this will put all memory onto the freelists */
mm: concentrate modification of totalram_pages into the mm core Concentrate code to modify totalram_pages into the mm core, so the arch memory initialized code doesn't need to take care of it. With these changes applied, only following functions from mm core modify global variable totalram_pages: free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(), adjust_managed_page_count(). With this patch applied, it will be much more easier for us to keep totalram_pages and zone->managed_pages in consistence. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: David Howells <dhowells@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:24 +08:00
free_all_bootmem();
after_bootmem = 1;
/* Register memory areas for /proc/kcore */
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR,
PAGE_SIZE, KCORE_OTHER);
mem_init_print_info(NULL);
}
#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 = PFN_ALIGN(__start_rodata);
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
x86, 64bit, mm: Mark data/bss/brk to nx HPA said, we should not have RW and +x set at the time. for kernel layout: [ 0.000000] Kernel Layout: [ 0.000000] .text: [0x01000000-0x021434f8] [ 0.000000] .rodata: [0x02200000-0x02a13fff] [ 0.000000] .data: [0x02c00000-0x02dc763f] [ 0.000000] .init: [0x02dc9000-0x0312cfff] [ 0.000000] .bss: [0x0313b000-0x03dd6fff] [ 0.000000] .brk: [0x03dd7000-0x03dfffff] before the patch, we have ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82dc9000 1828K RW GLB x pte 0xffffffff82dc9000-0xffffffff82e00000 220K RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff8313a000 1256K RW GLB NX pte 0xffffffff8313a000-0xffffffff83200000 792K RW GLB x pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB x pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd after patch,, we get ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82e00000 2M RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff83200000 2M RW GLB NX pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB NX pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd so data, bss, brk get NX ... Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-33-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 04:20:13 +08:00
unsigned long all_end = PFN_ALIGN(&_end);
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;
/*
x86, 64bit, mm: Mark data/bss/brk to nx HPA said, we should not have RW and +x set at the time. for kernel layout: [ 0.000000] Kernel Layout: [ 0.000000] .text: [0x01000000-0x021434f8] [ 0.000000] .rodata: [0x02200000-0x02a13fff] [ 0.000000] .data: [0x02c00000-0x02dc763f] [ 0.000000] .init: [0x02dc9000-0x0312cfff] [ 0.000000] .bss: [0x0313b000-0x03dd6fff] [ 0.000000] .brk: [0x03dd7000-0x03dfffff] before the patch, we have ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82dc9000 1828K RW GLB x pte 0xffffffff82dc9000-0xffffffff82e00000 220K RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff8313a000 1256K RW GLB NX pte 0xffffffff8313a000-0xffffffff83200000 792K RW GLB x pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB x pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd after patch,, we get ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82e00000 2M RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff83200000 2M RW GLB NX pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB NX pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd so data, bss, brk get NX ... Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-33-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 04:20:13 +08:00
* The rodata/data/bss/brk section (but not the kernel text!)
* should also be not-executable.
*/
x86, 64bit, mm: Mark data/bss/brk to nx HPA said, we should not have RW and +x set at the time. for kernel layout: [ 0.000000] Kernel Layout: [ 0.000000] .text: [0x01000000-0x021434f8] [ 0.000000] .rodata: [0x02200000-0x02a13fff] [ 0.000000] .data: [0x02c00000-0x02dc763f] [ 0.000000] .init: [0x02dc9000-0x0312cfff] [ 0.000000] .bss: [0x0313b000-0x03dd6fff] [ 0.000000] .brk: [0x03dd7000-0x03dfffff] before the patch, we have ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82dc9000 1828K RW GLB x pte 0xffffffff82dc9000-0xffffffff82e00000 220K RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff8313a000 1256K RW GLB NX pte 0xffffffff8313a000-0xffffffff83200000 792K RW GLB x pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB x pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd after patch,, we get ---[ High Kernel Mapping ]--- 0xffffffff80000000-0xffffffff81000000 16M pmd 0xffffffff81000000-0xffffffff82200000 18M ro PSE GLB x pmd 0xffffffff82200000-0xffffffff82c00000 10M ro PSE GLB NX pmd 0xffffffff82c00000-0xffffffff82e00000 2M RW GLB NX pte 0xffffffff82e00000-0xffffffff83000000 2M RW PSE GLB NX pmd 0xffffffff83000000-0xffffffff83200000 2M RW GLB NX pte 0xffffffff83200000-0xffffffff83e00000 12M RW PSE GLB NX pmd 0xffffffff83e00000-0xffffffffa0000000 450M pmd so data, bss, brk get NX ... Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-33-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 04:20:13 +08:00
set_memory_nx(rodata_start, (all_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",
(unsigned long) __va(__pa_symbol(text_end)),
(unsigned long) __va(__pa_symbol(rodata_start)));
free_init_pages("unused kernel",
(unsigned long) __va(__pa_symbol(rodata_end)),
(unsigned long) __va(__pa_symbol(_sdata)));
}
#endif
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;
x86/mm: Check if PUD is large when validating a kernel address A user reported the following oops when a backup process reads /proc/kcore: BUG: unable to handle kernel paging request at ffffbb00ff33b000 IP: [<ffffffff8103157e>] kern_addr_valid+0xbe/0x110 [...] Call Trace: [<ffffffff811b8aaa>] read_kcore+0x17a/0x370 [<ffffffff811ad847>] proc_reg_read+0x77/0xc0 [<ffffffff81151687>] vfs_read+0xc7/0x130 [<ffffffff811517f3>] sys_read+0x53/0xa0 [<ffffffff81449692>] system_call_fastpath+0x16/0x1b Investigation determined that the bug triggered when reading system RAM at the 4G mark. On this system, that was the first address using 1G pages for the virt->phys direct mapping so the PUD is pointing to a physical address, not a PMD page. The problem is that the page table walker in kern_addr_valid() is not checking pud_large() and treats the physical address as if it was a PMD. If it happens to look like pmd_none then it'll silently fail, probably returning zeros instead of real data. If the data happens to look like a present PMD though, it will be walked resulting in the oops above. This patch adds the necessary pud_large() check. Unfortunately the problem was not readily reproducible and now they are running the backup program without accessing /proc/kcore so the patch has not been validated but I think it makes sense. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.coM> Reviewed-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: stable@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20130211145236.GX21389@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-11 22:52:36 +08:00
if (pud_large(*pud))
return pfn_valid(pud_pfn(*pud));
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 const char *gate_vma_name(struct vm_area_struct *vma)
{
return "[vsyscall]";
}
static struct vm_operations_struct gate_vma_ops = {
.name = gate_vma_name,
};
static struct vm_area_struct gate_vma = {
.vm_start = VSYSCALL_ADDR,
.vm_end = VSYSCALL_ADDR + PAGE_SIZE,
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC,
.vm_ops = &gate_vma_ops,
};
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
#ifdef CONFIG_IA32_EMULATION
if (!mm || mm->context.ia32_compat)
return NULL;
#endif
return &gate_vma;
}
int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma = get_gate_vma(mm);
if (!vma)
return 0;
return (addr >= vma->vm_start) && (addr < vma->vm_end);
}
/*
* Use this when you have no reliable mm, typically from interrupt
* context. It is less reliable than using a task's mm and may give
* false positives.
*/
int in_gate_area_no_mm(unsigned long addr)
{
return (addr & PAGE_MASK) == VSYSCALL_ADDR;
}
static unsigned long probe_memory_block_size(void)
{
/* start from 2g */
unsigned long bz = 1UL<<31;
#ifdef CONFIG_X86_UV
if (is_uv_system()) {
printk(KERN_INFO "UV: memory block size 2GB\n");
return 2UL * 1024 * 1024 * 1024;
}
#endif
/* less than 64g installed */
if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
return MIN_MEMORY_BLOCK_SIZE;
/* get the tail size */
while (bz > MIN_MEMORY_BLOCK_SIZE) {
if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
break;
bz >>= 1;
}
printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
return bz;
}
static unsigned long memory_block_size_probed;
unsigned long memory_block_size_bytes(void)
{
if (!memory_block_size_probed)
memory_block_size_probed = probe_memory_block_size();
return memory_block_size_probed;
}
#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 16:19:24 +08:00
static long __meminitdata addr_start, addr_end;
static void __meminitdata *p_start, *p_end;
static int __meminitdata node_start;
static int __meminit vmemmap_populate_hugepages(unsigned long start,
unsigned long end, int node)
{
sparse-vmemmap: specify vmemmap population range in bytes The sparse code, when asking the architecture to populate the vmemmap, specifies the section range as a starting page and a number of pages. This is an awkward interface, because none of the arch-specific code actually thinks of the range in terms of 'struct page' units and always translates it to bytes first. In addition, later patches mix huge page and regular page backing for the vmemmap. For this, they need to call vmemmap_populate_basepages() on sub-section ranges with PAGE_SIZE and PMD_SIZE in mind. But these are not necessarily multiples of the 'struct page' size and so this unit is too coarse. Just translate the section range into bytes once in the generic sparse code, then pass byte ranges down the stack. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Bernhard Schmidt <Bernhard.Schmidt@lrz.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: David S. Miller <davem@davemloft.net> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:07:50 +08:00
unsigned long addr;
unsigned long next;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
sparse-vmemmap: specify vmemmap population range in bytes The sparse code, when asking the architecture to populate the vmemmap, specifies the section range as a starting page and a number of pages. This is an awkward interface, because none of the arch-specific code actually thinks of the range in terms of 'struct page' units and always translates it to bytes first. In addition, later patches mix huge page and regular page backing for the vmemmap. For this, they need to call vmemmap_populate_basepages() on sub-section ranges with PAGE_SIZE and PMD_SIZE in mind. But these are not necessarily multiples of the 'struct page' size and so this unit is too coarse. Just translate the section range into bytes once in the generic sparse code, then pass byte ranges down the stack. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Bernhard Schmidt <Bernhard.Schmidt@lrz.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: David S. Miller <davem@davemloft.net> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:07:50 +08:00
for (addr = start; addr < end; addr = next) {
next = pmd_addr_end(addr, end);
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
pud = vmemmap_pud_populate(pgd, addr, node);
if (!pud)
return -ENOMEM;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
void *p;
p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (p) {
pte_t entry;
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;
continue;
}
} else if (pmd_large(*pmd)) {
vmemmap_verify((pte_t *)pmd, node, addr, next);
continue;
}
pr_warn_once("vmemmap: falling back to regular page backing\n");
if (vmemmap_populate_basepages(addr, next, node))
return -ENOMEM;
}
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 16:19:24 +08:00
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
int err;
if (cpu_has_pse)
err = vmemmap_populate_hugepages(start, end, node);
else
err = vmemmap_populate_basepages(start, end, node);
if (!err)
sync_global_pgds(start, end - 1);
return err;
}
memory-hotplug: implement register_page_bootmem_info_section of sparse-vmemmap For removing memmap region of sparse-vmemmap which is allocated bootmem, memmap region of sparse-vmemmap needs to be registered by get_page_bootmem(). So the patch searches pages of virtual mapping and registers the pages by get_page_bootmem(). NOTE: register_page_bootmem_memmap() is not implemented for ia64, ppc, s390, and sparc. So introduce CONFIG_HAVE_BOOTMEM_INFO_NODE and revert register_page_bootmem_info_node() when platform doesn't support it. It's implemented by adding a new Kconfig option named CONFIG_HAVE_BOOTMEM_INFO_NODE, which will be automatically selected by memory-hotplug feature fully supported archs(currently only on x86_64). Since we have 2 config options called MEMORY_HOTPLUG and MEMORY_HOTREMOVE used for memory hot-add and hot-remove separately, and codes in function register_page_bootmem_info_node() are only used for collecting infomation for hot-remove, so reside it under MEMORY_HOTREMOVE. Besides page_isolation.c selected by MEMORY_ISOLATION under MEMORY_HOTPLUG is also such case, move it too. [mhocko@suse.cz: put register_page_bootmem_memmap inside CONFIG_MEMORY_HOTPLUG_SPARSE] [linfeng@cn.fujitsu.com: introduce CONFIG_HAVE_BOOTMEM_INFO_NODE and revert register_page_bootmem_info_node()] [mhocko@suse.cz: remove the arch specific functions without any implementation] [linfeng@cn.fujitsu.com: mm/Kconfig: move auto selects from MEMORY_HOTPLUG to MEMORY_HOTREMOVE as needed] [rientjes@google.com: fix defined but not used warning] Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Wu Jianguo <wujianguo@huawei.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.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: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Lin Feng <linfeng@cn.fujitsu.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 08:33:00 +08:00
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
void register_page_bootmem_memmap(unsigned long section_nr,
struct page *start_page, unsigned long size)
{
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;
unsigned int nr_pages;
struct page *page;
for (; addr < end; addr = next) {
pte_t *pte = NULL;
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd)) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
continue;
}
get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
continue;
}
get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
if (!cpu_has_pse) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
continue;
get_page_bootmem(section_nr, pmd_page(*pmd),
MIX_SECTION_INFO);
pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte))
continue;
get_page_bootmem(section_nr, pte_page(*pte),
SECTION_INFO);
} else {
next = pmd_addr_end(addr, end);
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
continue;
nr_pages = 1 << (get_order(PMD_SIZE));
page = pmd_page(*pmd);
while (nr_pages--)
get_page_bootmem(section_nr, page++,
SECTION_INFO);
}
}
}
#endif
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 16:19:24 +08:00
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