OpenCloudOS-Kernel/arch/x86/mm/init_64.c

949 lines
23 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 <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 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_addr holds the negative offset to the kernel, which is added
* to the compile time generated pmds. This results in invalid pmds up
* to the point where we hit the physaddr 0 mapping.
*
* We limit the mappings to the region from _text to _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 + (max_pfn_mapped << PAGE_SHIFT);
unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
pmd_t *pmd = level2_kernel_pgt;
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);
__flush_tlb_all();
return last_map_addr;
}
#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 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);
[PATCH] reduce MAX_NR_ZONES: remove two strange uses of MAX_NR_ZONES I keep seeing zones on various platforms that are never used and wonder why we compile support for them into the kernel. Counters show up for HIGHMEM and DMA32 that are alway zero. This patch allows the removal of ZONE_DMA32 for non x86_64 architectures and it will get rid of ZONE_HIGHMEM for arches not using highmem (like 64 bit architectures). If an arch does not define CONFIG_HIGHMEM then ZONE_HIGHMEM will not be defined. Similarly if an arch does not define CONFIG_ZONE_DMA32 then ZONE_DMA32 will not be defined. No current architecture uses all the 4 zones (DMA,DMA32,NORMAL,HIGH) that we have now. The patchset will reduce the number of zones for all platforms. On many platforms that do not have DMA32 or HIGHMEM this will reduce the number of zones by 50%. F.e. ia64 only uses DMA and NORMAL. Large amounts of memory can be saved for larger systemss that may have a few hundred NUMA nodes. With ZONE_DMA32 and ZONE_HIGHMEM support optional MAX_NR_ZONES will be 2 for many non i386 platforms and even for i386 without CONFIG_HIGHMEM set. Tested on ia64, x86_64 and on i386 with and without highmem. The patchset consists of 11 patches that are following this message. One could go even further than this patchset and also make ZONE_DMA optional because some platforms do not need a separate DMA zone and can do DMA to all of memory. This could reduce MAX_NR_ZONES to 1. Such a patchset will hopefully follow soon. This patch: Fix strange uses of MAX_NR_ZONES Sometimes we use MAX_NR_ZONES - x to refer to a zone. Make that explicit. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:09 +08:00
struct zone *zone = pgdat->node_zones + 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);
#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)
{
long codesize, reservedpages, datasize, initsize;
unsigned long absent_pages;
pci_iommu_alloc();
/* clear_bss() already clear the empty_zero_page */
reservedpages = 0;
/* this will put all low memory onto the freelists */
register_page_bootmem_info();
totalram_pages = free_all_bootmem();
absent_pages = absent_pages_in_range(0, max_pfn);
reservedpages = max_pfn - totalram_pages - absent_pages;
after_bootmem = 1;
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
/* Register memory areas for /proc/kcore */
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
"%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
nr_free_pages() << (PAGE_SHIFT-10),
max_pfn << (PAGE_SHIFT-10),
codesize >> 10,
absent_pages << (PAGE_SHIFT-10),
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
}
#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
int kernel_set_to_readonly;
void set_kernel_text_rw(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long end = PFN_ALIGN(__stop___ex_table);
if (!kernel_set_to_readonly)
return;
pr_debug("Set kernel text: %lx - %lx for read write\n",
start, end);
/*
* Make the kernel identity mapping for text RW. Kernel text
* mapping will always be RO. Refer to the comment in
* static_protections() in pageattr.c
*/
set_memory_rw(start, (end - start) >> PAGE_SHIFT);
}
void set_kernel_text_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long end = PFN_ALIGN(__stop___ex_table);
if (!kernel_set_to_readonly)
return;
pr_debug("Set kernel text: %lx - %lx for read only\n",
start, end);
/*
* Set the kernel identity mapping for text RO.
*/
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
}
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long rodata_start =
((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
unsigned long data_start = (unsigned long) &_sdata;
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
kernel_set_to_readonly = 1;
/*
* The rodata section (but not the kernel text!) should also be
* not-executable.
*/
set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
rodata_test();
#ifdef CONFIG_CPA_DEBUG
printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
set_memory_rw(start, (end-start) >> PAGE_SHIFT);
printk(KERN_INFO "Testing CPA: again\n");
set_memory_ro(start, (end-start) >> PAGE_SHIFT);
#endif
free_init_pages("unused kernel memory",
(unsigned long) page_address(virt_to_page(text_end)),
(unsigned long)
page_address(virt_to_page(rodata_start)));
free_init_pages("unused kernel memory",
(unsigned long) page_address(virt_to_page(rodata_end)),
(unsigned long) page_address(virt_to_page(data_start)));
}
#endif
int kern_addr_valid(unsigned long addr)
{
unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (above != 0 && above != -1UL)
return 0;
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd))
return 0;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
return 0;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return 0;
if (pmd_large(*pmd))
return pfn_valid(pmd_pfn(*pmd));
pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte))
return 0;
return pfn_valid(pte_pfn(*pte));
}
/*
* A pseudo VMA to allow ptrace access for the vsyscall page. This only
* covers the 64bit vsyscall page now. 32bit has a real VMA now and does
* not need special handling anymore:
*/
static struct vm_area_struct gate_vma = {
.vm_start = VSYSCALL_START,
.vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC
};
struct vm_area_struct *get_gate_vma(struct 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 >= VSYSCALL_START) && (addr < VSYSCALL_END);
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
return "[vdso]";
if (vma == &gate_vma)
return "[vsyscall]";
return NULL;
}
#ifdef CONFIG_X86_UV
unsigned long memory_block_size_bytes(void)
{
if (is_uv_system()) {
printk(KERN_INFO "UV: memory block size 2GB\n");
return 2UL * 1024 * 1024 * 1024;
}
return MIN_MEMORY_BLOCK_SIZE;
}
#endif
#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;
int __meminit
vmemmap_populate(struct page *start_page, unsigned long size, int node)
{
unsigned long addr = (unsigned long)start_page;
unsigned long end = (unsigned long)(start_page + size);
unsigned long next;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
for (; addr < end; addr = next) {
void *p = NULL;
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
pud = vmemmap_pud_populate(pgd, addr, node);
if (!pud)
return -ENOMEM;
if (!cpu_has_pse) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
pmd = vmemmap_pmd_populate(pud, addr, node);
if (!pmd)
return -ENOMEM;
p = vmemmap_pte_populate(pmd, addr, node);
if (!p)
return -ENOMEM;
addr_end = addr + PAGE_SIZE;
p_end = p + PAGE_SIZE;
} else {
next = pmd_addr_end(addr, end);
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
pte_t entry;
sparsemem: Put mem map for one node together. Add vmemmap_alloc_block_buf for mem map only. It will fallback to the old way if it cannot get a block that big. Before this patch, when a node have 128g ram installed, memmap are split into two parts or more. [ 0.000000] [ffffea0000000000-ffffea003fffffff] PMD -> [ffff880100600000-ffff88013e9fffff] on node 1 [ 0.000000] [ffffea0040000000-ffffea006fffffff] PMD -> [ffff88013ec00000-ffff88016ebfffff] on node 1 [ 0.000000] [ffffea0070000000-ffffea007fffffff] PMD -> [ffff882000600000-ffff8820105fffff] on node 0 [ 0.000000] [ffffea0080000000-ffffea00bfffffff] PMD -> [ffff882010800000-ffff8820507fffff] on node 0 [ 0.000000] [ffffea00c0000000-ffffea00dfffffff] PMD -> [ffff882050a00000-ffff8820709fffff] on node 0 [ 0.000000] [ffffea00e0000000-ffffea00ffffffff] PMD -> [ffff884000600000-ffff8840205fffff] on node 2 [ 0.000000] [ffffea0100000000-ffffea013fffffff] PMD -> [ffff884020800000-ffff8840607fffff] on node 2 [ 0.000000] [ffffea0140000000-ffffea014fffffff] PMD -> [ffff884060a00000-ffff8840709fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea017fffffff] PMD -> [ffff886000600000-ffff8860305fffff] on node 3 [ 0.000000] [ffffea0180000000-ffffea01bfffffff] PMD -> [ffff886030800000-ffff8860707fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea01ffffffff] PMD -> [ffff888000600000-ffff8880405fffff] on node 4 [ 0.000000] [ffffea0200000000-ffffea022fffffff] PMD -> [ffff888040800000-ffff8880707fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea023fffffff] PMD -> [ffff88a000600000-ffff88a0105fffff] on node 5 [ 0.000000] [ffffea0240000000-ffffea027fffffff] PMD -> [ffff88a010800000-ffff88a0507fffff] on node 5 [ 0.000000] [ffffea0280000000-ffffea029fffffff] PMD -> [ffff88a050a00000-ffff88a0709fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea02bfffffff] PMD -> [ffff88c000600000-ffff88c0205fffff] on node 6 [ 0.000000] [ffffea02c0000000-ffffea02ffffffff] PMD -> [ffff88c020800000-ffff88c0607fffff] on node 6 [ 0.000000] [ffffea0300000000-ffffea030fffffff] PMD -> [ffff88c060a00000-ffff88c0709fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea033fffffff] PMD -> [ffff88e000600000-ffff88e0305fffff] on node 7 [ 0.000000] [ffffea0340000000-ffffea037fffffff] PMD -> [ffff88e030800000-ffff88e0707fffff] on node 7 after patch will get [ 0.000000] [ffffea0000000000-ffffea006fffffff] PMD -> [ffff880100200000-ffff88016e5fffff] on node 0 [ 0.000000] [ffffea0070000000-ffffea00dfffffff] PMD -> [ffff882000200000-ffff8820701fffff] on node 1 [ 0.000000] [ffffea00e0000000-ffffea014fffffff] PMD -> [ffff884000200000-ffff8840701fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea01bfffffff] PMD -> [ffff886000200000-ffff8860701fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea022fffffff] PMD -> [ffff888000200000-ffff8880701fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea029fffffff] PMD -> [ffff88a000200000-ffff88a0701fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea030fffffff] PMD -> [ffff88c000200000-ffff88c0701fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea037fffffff] PMD -> [ffff88e000200000-ffff88e0701fffff] on node 7 -v2: change buf to vmemmap_buf instead according to Ingo also add CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER according to Ingo -v3: according to Andrew, use sizeof(name) instead of hard coded 15 Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <1265793639-15071-19-git-send-email-yinghai@kernel.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-10 17:20:22 +08:00
p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (!p)
return -ENOMEM;
entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
PAGE_KERNEL_LARGE);
set_pmd(pmd, __pmd(pte_val(entry)));
/* check to see if we have contiguous blocks */
if (p_end != p || node_start != node) {
if (p_start)
printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
addr_start, addr_end-1, p_start, p_end-1, node_start);
addr_start = addr;
node_start = node;
p_start = p;
}
addr_end = addr + PMD_SIZE;
p_end = p + PMD_SIZE;
} else
vmemmap_verify((pte_t *)pmd, node, addr, next);
}
}
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
sync_global_pgds((unsigned long)start_page, end);
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
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