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

789 lines
18 KiB
C
Raw Normal View History

/*
* linux/arch/x86_64/mm/init.c
*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
* Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
const struct dma_mapping_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
static unsigned long dma_reserve __initdata;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
/*
* 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.
*/
void show_mem(void)
{
long i, total = 0, reserved = 0;
long shared = 0, cached = 0;
struct page *page;
pg_data_t *pgdat;
printk(KERN_INFO "Mem-info:\n");
show_free_areas();
printk(KERN_INFO "Free swap: %6ldkB\n",
nr_swap_pages << (PAGE_SHIFT-10));
for_each_online_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
/*
* This loop can take a while with 256 GB and
* 4k pages so defer the NMI watchdog:
*/
if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
touch_nmi_watchdog();
if (!pfn_valid(pgdat->node_start_pfn + i))
continue;
page = pfn_to_page(pgdat->node_start_pfn + i);
total++;
if (PageReserved(page))
reserved++;
else if (PageSwapCache(page))
cached++;
else if (page_count(page))
shared += page_count(page) - 1;
}
}
printk(KERN_INFO "%lu pages of RAM\n", total);
printk(KERN_INFO "%lu reserved pages\n", reserved);
printk(KERN_INFO "%lu pages shared\n", shared);
printk(KERN_INFO "%lu pages swap cached\n", cached);
}
int after_bootmem;
static __init void *spp_getpage(void)
{
void *ptr;
if (after_bootmem)
ptr = (void *) get_zeroed_page(GFP_ATOMIC);
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 __init void
set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte, new_pte;
pr_debug("set_pte_phys %lx to %lx\n", vaddr, phys);
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 = pud_offset(pgd, vaddr);
if (pud_none(*pud)) {
pmd = (pmd_t *) spp_getpage();
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
if (pmd != pmd_offset(pud, 0)) {
printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
pmd, pmd_offset(pud, 0));
return;
}
}
pmd = pmd_offset(pud, vaddr);
if (pmd_none(*pmd)) {
pte = (pte_t *) spp_getpage();
set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
if (pte != pte_offset_kernel(pmd, 0)) {
printk(KERN_ERR "PAGETABLE BUG #02!\n");
return;
}
}
new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
pte = pte_offset_kernel(pmd, vaddr);
if (!pte_none(*pte) &&
pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
pte_ERROR(*pte);
set_pte(pte, new_pte);
/*
* It's enough to flush this one mapping.
* (PGE mappings get flushed as well)
*/
__flush_tlb_one(vaddr);
}
/* NOTE: this is meant to be run only at boot */
void __init
__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
printk(KERN_ERR "Invalid __set_fixmap\n");
return;
}
set_pte_phys(address, phys, prot);
}
static unsigned long __initdata table_start;
static unsigned long __meminitdata table_end;
static __meminit void *alloc_low_page(unsigned long *phys)
{
unsigned long pfn = table_end++;
void *adr;
if (after_bootmem) {
adr = (void *)get_zeroed_page(GFP_ATOMIC);
*phys = __pa(adr);
return adr;
}
if (pfn >= end_pfn)
panic("alloc_low_page: ran out of memory");
adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
*phys = pfn * PAGE_SIZE;
return adr;
}
static __meminit void unmap_low_page(void *adr)
{
if (after_bootmem)
return;
early_iounmap(adr, PAGE_SIZE);
}
/* Must run before zap_low_mappings */
__meminit void *early_ioremap(unsigned long addr, unsigned long size)
{
pmd_t *pmd, *last_pmd;
unsigned long vaddr;
int i, pmds;
pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
vaddr = __START_KERNEL_map;
pmd = level2_kernel_pgt;
last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;
for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
for (i = 0; i < pmds; i++) {
if (pmd_present(pmd[i]))
goto continue_outer_loop;
}
vaddr += addr & ~PMD_MASK;
addr &= PMD_MASK;
for (i = 0; i < pmds; i++, addr += PMD_SIZE)
set_pmd(pmd+i, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
__flush_tlb_all();
return (void *)vaddr;
continue_outer_loop:
;
}
printk(KERN_ERR "early_ioremap(0x%lx, %lu) failed\n", addr, size);
return NULL;
}
/*
* To avoid virtual aliases later:
*/
__meminit void early_iounmap(void *addr, unsigned long size)
{
unsigned long vaddr;
pmd_t *pmd;
int i, pmds;
vaddr = (unsigned long)addr;
pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
pmd = level2_kernel_pgt + pmd_index(vaddr);
for (i = 0; i < pmds; i++)
pmd_clear(pmd + i);
__flush_tlb_all();
}
static void __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
{
int i = pmd_index(address);
for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
pmd_t *pmd = pmd_page + pmd_index(address);
if (address >= end) {
if (!after_bootmem) {
for (; i < PTRS_PER_PMD; i++, pmd++)
set_pmd(pmd, __pmd(0));
}
break;
}
if (pmd_val(*pmd))
continue;
set_pte((pte_t *)pmd,
pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
}
}
static void __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
{
pmd_t *pmd = pmd_offset(pud, 0);
spin_lock(&init_mm.page_table_lock);
phys_pmd_init(pmd, address, end);
spin_unlock(&init_mm.page_table_lock);
__flush_tlb_all();
}
static void __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
{
int i = pud_index(addr);
for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
if (addr >= end)
break;
if (!after_bootmem &&
!e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
set_pud(pud, __pud(0));
continue;
}
if (pud_val(*pud)) {
phys_pmd_update(pud, addr, end);
continue;
}
pmd = alloc_low_page(&pmd_phys);
spin_lock(&init_mm.page_table_lock);
set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
phys_pmd_init(pmd, addr, end);
spin_unlock(&init_mm.page_table_lock);
unmap_low_page(pmd);
}
__flush_tlb_all();
}
static void __init find_early_table_space(unsigned long end)
{
unsigned long puds, pmds, tables, start;
puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) +
round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
/*
* RED-PEN putting page tables only on node 0 could
* cause a hotspot and fill up ZONE_DMA. The page tables
* need roughly 0.5KB per GB.
*/
start = 0x8000;
x86_64: make bootmap_start page align v6 boot oopses when a system has 64 or 128 GB of RAM installed: Calling initcall 0xffffffff80bc33b6: sctp_init+0x0/0x711() BUG: unable to handle kernel NULL pointer dereference at 000000000000005f IP: [<ffffffff802bfe55>] proc_register+0xe7/0x10f PGD 0 Oops: 0000 [1] SMP CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #6 RIP: 0010:[<ffffffff802bfe55>] [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP: 0000:ffff810824c57e60 EFLAGS: 00010246 RAX: 000000000000d7d7 RBX: ffff811024c5fa80 RCX: ffff810824c57e08 RDX: 0000000000000000 RSI: 0000000000000195 RDI: ffffffff80cc2460 RBP: ffffffffffffffff R08: 0000000000000000 R09: ffff811024c5fa80 R10: 0000000000000000 R11: 0000000000000002 R12: ffff810824c57e6c R13: 0000000000000000 R14: ffff810824c57ee0 R15: 00000006abd25bee FS: 0000000000000000(0000) GS:ffffffff80b4d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000005f CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff810824c56000, task ffff812024c52000) Stack: ffffffff80a57348 0000019500000000 ffff811024c5fa80 0000000000000000 00000000ffffff97 ffffffff802bfef0 0000000000000000 ffffffffffffffff 0000000000000000 ffffffff80bc3b4b ffff810824c57ee0 ffffffff80bc34a5 Call Trace: [<ffffffff802bfef0>] ? create_proc_entry+0x73/0x8a [<ffffffff80bc3b4b>] ? sctp_snmp_proc_init+0x1c/0x34 [<ffffffff80bc34a5>] ? sctp_init+0xef/0x711 [<ffffffff80b976e3>] ? kernel_init+0x175/0x2e1 [<ffffffff8020ccf8>] ? child_rip+0xa/0x12 [<ffffffff80b9756e>] ? kernel_init+0x0/0x2e1 [<ffffffff8020ccee>] ? child_rip+0x0/0x12 Code: 1e 48 83 7b 38 00 75 08 48 c7 43 38 f0 e8 82 80 48 83 7b 30 00 75 08 48 c7 43 30 d0 e9 82 80 48 c7 c7 60 24 cc 80 e8 bd 5a 54 00 <48> 8b 45 60 48 89 6b 58 48 89 5d 60 48 89 43 50 fe 05 f5 25 a0 RIP [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP <ffff810824c57e60> CR2: 000000000000005f ---[ end trace 02c2d78def82877a ]--- Kernel panic - not syncing: Attempted to kill init! it turns out some variables near end of bss are corrupted already. in System.map we have ffffffff80d40420 b rsi_table ffffffff80d40620 B krb5_seq_lock ffffffff80d40628 b i.20437 ffffffff80d40630 b xprt_rdma_inline_write_padding ffffffff80d40638 b sunrpc_table_header ffffffff80d40640 b zero ffffffff80d40644 b min_memreg ffffffff80d40648 b rpcrdma_tk_lock_g ffffffff80d40650 B sctp_assocs_id_lock ffffffff80d40658 B proc_net_sctp ffffffff80d40660 B sctp_assocs_id ffffffff80d40680 B sysctl_sctp_mem ffffffff80d40690 B sysctl_sctp_rmem ffffffff80d406a0 B sysctl_sctp_wmem ffffffff80d406b0 b sctp_ctl_socket ffffffff80d406b8 b sctp_pf_inet6_specific ffffffff80d406c0 b sctp_pf_inet_specific ffffffff80d406c8 b sctp_af_v4_specific ffffffff80d406d0 b sctp_af_v6_specific ffffffff80d406d8 b sctp_rand.33270 ffffffff80d406dc b sctp_memory_pressure ffffffff80d406e0 b sctp_sockets_allocated ffffffff80d406e4 b sctp_memory_allocated ffffffff80d406e8 b sctp_sysctl_header ffffffff80d406f0 b zero ffffffff80d406f4 A __bss_stop ffffffff80d406f4 A _end and setup_node_bootmem() will use that page 0xd40000 for bootmap Bootmem setup node 0 0000000000000000-0000000828000000 NODE_DATA [000000000008a485 - 0000000000091484] bootmap [0000000000d406f4 - 0000000000e456f3] pages 105 Bootmem setup node 1 0000000828000000-0000001028000000 NODE_DATA [0000000828000000 - 0000000828006fff] bootmap [0000000828007000 - 0000000828106fff] pages 100 Bootmem setup node 2 0000001028000000-0000001828000000 NODE_DATA [0000001028000000 - 0000001028006fff] bootmap [0000001028007000 - 0000001028106fff] pages 100 Bootmem setup node 3 0000001828000000-0000002028000000 NODE_DATA [0000001828000000 - 0000001828006fff] bootmap [0000001828007000 - 0000001828106fff] pages 100 setup_node_bootmem() makes NODE_DATA cacheline aligned, and bootmap is page-aligned. the patch updates find_e820_area() to make sure we can meet the alignment constraints. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-02 00:49:41 +08:00
table_start = find_e820_area(start, end, tables, PAGE_SIZE);
if (table_start == -1UL)
panic("Cannot find space for the kernel page tables");
table_start >>= PAGE_SHIFT;
table_end = table_start;
early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
end, table_start << PAGE_SHIFT,
(table_start << PAGE_SHIFT) + tables);
}
/*
* Setup the direct mapping of the physical memory at PAGE_OFFSET.
* This runs before bootmem is initialized and gets pages directly from
* the physical memory. To access them they are temporarily mapped.
*/
void __init_refok init_memory_mapping(unsigned long start, unsigned long end)
{
unsigned long next;
pr_debug("init_memory_mapping\n");
/*
* Find space for the kernel direct mapping tables.
*
* Later we should allocate these tables in the local node of the
* memory mapped. Unfortunately this is done currently before the
* nodes are discovered.
*/
if (!after_bootmem)
find_early_table_space(end);
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
unsigned long pud_phys;
pud_t *pud;
if (after_bootmem)
pud = pud_offset(pgd, start & PGDIR_MASK);
else
pud = alloc_low_page(&pud_phys);
next = start + PGDIR_SIZE;
if (next > end)
next = end;
phys_pud_init(pud, __pa(start), __pa(next));
if (!after_bootmem)
set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
unmap_low_page(pud);
}
if (!after_bootmem)
mmu_cr4_features = read_cr4();
__flush_tlb_all();
x86_64: make bootmap_start page align v6 boot oopses when a system has 64 or 128 GB of RAM installed: Calling initcall 0xffffffff80bc33b6: sctp_init+0x0/0x711() BUG: unable to handle kernel NULL pointer dereference at 000000000000005f IP: [<ffffffff802bfe55>] proc_register+0xe7/0x10f PGD 0 Oops: 0000 [1] SMP CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #6 RIP: 0010:[<ffffffff802bfe55>] [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP: 0000:ffff810824c57e60 EFLAGS: 00010246 RAX: 000000000000d7d7 RBX: ffff811024c5fa80 RCX: ffff810824c57e08 RDX: 0000000000000000 RSI: 0000000000000195 RDI: ffffffff80cc2460 RBP: ffffffffffffffff R08: 0000000000000000 R09: ffff811024c5fa80 R10: 0000000000000000 R11: 0000000000000002 R12: ffff810824c57e6c R13: 0000000000000000 R14: ffff810824c57ee0 R15: 00000006abd25bee FS: 0000000000000000(0000) GS:ffffffff80b4d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000005f CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff810824c56000, task ffff812024c52000) Stack: ffffffff80a57348 0000019500000000 ffff811024c5fa80 0000000000000000 00000000ffffff97 ffffffff802bfef0 0000000000000000 ffffffffffffffff 0000000000000000 ffffffff80bc3b4b ffff810824c57ee0 ffffffff80bc34a5 Call Trace: [<ffffffff802bfef0>] ? create_proc_entry+0x73/0x8a [<ffffffff80bc3b4b>] ? sctp_snmp_proc_init+0x1c/0x34 [<ffffffff80bc34a5>] ? sctp_init+0xef/0x711 [<ffffffff80b976e3>] ? kernel_init+0x175/0x2e1 [<ffffffff8020ccf8>] ? child_rip+0xa/0x12 [<ffffffff80b9756e>] ? kernel_init+0x0/0x2e1 [<ffffffff8020ccee>] ? child_rip+0x0/0x12 Code: 1e 48 83 7b 38 00 75 08 48 c7 43 38 f0 e8 82 80 48 83 7b 30 00 75 08 48 c7 43 30 d0 e9 82 80 48 c7 c7 60 24 cc 80 e8 bd 5a 54 00 <48> 8b 45 60 48 89 6b 58 48 89 5d 60 48 89 43 50 fe 05 f5 25 a0 RIP [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP <ffff810824c57e60> CR2: 000000000000005f ---[ end trace 02c2d78def82877a ]--- Kernel panic - not syncing: Attempted to kill init! it turns out some variables near end of bss are corrupted already. in System.map we have ffffffff80d40420 b rsi_table ffffffff80d40620 B krb5_seq_lock ffffffff80d40628 b i.20437 ffffffff80d40630 b xprt_rdma_inline_write_padding ffffffff80d40638 b sunrpc_table_header ffffffff80d40640 b zero ffffffff80d40644 b min_memreg ffffffff80d40648 b rpcrdma_tk_lock_g ffffffff80d40650 B sctp_assocs_id_lock ffffffff80d40658 B proc_net_sctp ffffffff80d40660 B sctp_assocs_id ffffffff80d40680 B sysctl_sctp_mem ffffffff80d40690 B sysctl_sctp_rmem ffffffff80d406a0 B sysctl_sctp_wmem ffffffff80d406b0 b sctp_ctl_socket ffffffff80d406b8 b sctp_pf_inet6_specific ffffffff80d406c0 b sctp_pf_inet_specific ffffffff80d406c8 b sctp_af_v4_specific ffffffff80d406d0 b sctp_af_v6_specific ffffffff80d406d8 b sctp_rand.33270 ffffffff80d406dc b sctp_memory_pressure ffffffff80d406e0 b sctp_sockets_allocated ffffffff80d406e4 b sctp_memory_allocated ffffffff80d406e8 b sctp_sysctl_header ffffffff80d406f0 b zero ffffffff80d406f4 A __bss_stop ffffffff80d406f4 A _end and setup_node_bootmem() will use that page 0xd40000 for bootmap Bootmem setup node 0 0000000000000000-0000000828000000 NODE_DATA [000000000008a485 - 0000000000091484] bootmap [0000000000d406f4 - 0000000000e456f3] pages 105 Bootmem setup node 1 0000000828000000-0000001028000000 NODE_DATA [0000000828000000 - 0000000828006fff] bootmap [0000000828007000 - 0000000828106fff] pages 100 Bootmem setup node 2 0000001028000000-0000001828000000 NODE_DATA [0000001028000000 - 0000001028006fff] bootmap [0000001028007000 - 0000001028106fff] pages 100 Bootmem setup node 3 0000001828000000-0000002028000000 NODE_DATA [0000001828000000 - 0000001828006fff] bootmap [0000001828007000 - 0000001828106fff] pages 100 setup_node_bootmem() makes NODE_DATA cacheline aligned, and bootmap is page-aligned. the patch updates find_e820_area() to make sure we can meet the alignment constraints. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-02 00:49:41 +08:00
if (!after_bootmem)
reserve_early(table_start << PAGE_SHIFT,
table_end << PAGE_SHIFT, "PGTABLE");
}
#ifndef CONFIG_NUMA
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
max_zone_pfns[ZONE_NORMAL] = end_pfn;
memory_present(0, 0, end_pfn);
sparse_init();
free_area_init_nodes(max_zone_pfns);
}
#endif
/*
* Memory hotplug specific functions
*/
void online_page(struct page *page)
{
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
totalram_pages++;
num_physpages++;
}
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* 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;
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
init_memory_mapping(start, start + size-1);
ret = __add_pages(zone, start_pfn, nr_pages);
WARN_ON(1);
return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);
#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
int memory_add_physaddr_to_nid(u64 start)
{
return 0;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
kcore_modules, kcore_vsyscall;
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
pci_iommu_alloc();
/* clear_bss() already clear the empty_zero_page */
/* temporary debugging - double check it's true: */
{
int i;
for (i = 0; i < 1024; i++)
WARN_ON_ONCE(empty_zero_page[i]);
}
reservedpages = 0;
/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
totalram_pages = numa_free_all_bootmem();
#else
totalram_pages = free_all_bootmem();
#endif
reservedpages = end_pfn - totalram_pages -
absent_pages_in_range(0, end_pfn);
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_mem, __va(0), max_low_pfn << PAGE_SHIFT);
kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
VMALLOC_END-VMALLOC_START);
kclist_add(&kcore_kernel, &_stext, _end - _stext);
kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
VSYSCALL_END - VSYSCALL_START);
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
"%ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
end_pfn << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
cpa_init();
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
unsigned long addr = begin;
if (addr >= end)
return;
/*
* If debugging page accesses then do not free this memory but
* mark them not present - any buggy init-section access will
* create a kernel page fault:
*/
#ifdef CONFIG_DEBUG_PAGEALLOC
printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
begin, PAGE_ALIGN(end));
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
for (; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
memset((void *)(addr & ~(PAGE_SIZE-1)),
POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
#endif
}
void free_initmem(void)
{
free_init_pages("unused kernel memory",
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
}
#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
void mark_rodata_ro(void)
{
unsigned long start = (unsigned long)_stext, end;
#ifdef CONFIG_HOTPLUG_CPU
/* It must still be possible to apply SMP alternatives. */
if (num_possible_cpus() > 1)
start = (unsigned long)_etext;
#endif
#ifdef CONFIG_KPROBES
start = (unsigned long)__start_rodata;
#endif
end = (unsigned long)__end_rodata;
start = (start + PAGE_SIZE - 1) & PAGE_MASK;
end &= PAGE_MASK;
if (end <= start)
return;
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
/*
* The rodata section (but not the kernel text!) should also be
* not-executable.
*/
start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
set_memory_nx(start, (end - 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
}
#endif
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
free_init_pages("initrd memory", start, end);
}
#endif
void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
{
#ifdef CONFIG_NUMA
int nid = phys_to_nid(phys);
#endif
unsigned long pfn = phys >> PAGE_SHIFT;
if (pfn >= end_pfn) {
/*
* This can happen with kdump kernels when accessing
* firmware tables:
*/
if (pfn < end_pfn_map)
return;
printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n",
phys, len);
return;
}
/* Should check here against the e820 map to avoid double free */
#ifdef CONFIG_NUMA
reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
#else
reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
#endif
if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
dma_reserve += len / PAGE_SIZE;
set_dma_reserve(dma_reserve);
}
}
int kern_addr_valid(unsigned long addr)
{
unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (above != 0 && above != -1UL)
return 0;
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd))
return 0;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
return 0;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return 0;
if (pmd_large(*pmd))
return pfn_valid(pmd_pfn(*pmd));
pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte))
return 0;
return pfn_valid(pte_pfn(*pte));
}
/*
* A pseudo VMA to allow ptrace access for the vsyscall page. This only
* covers the 64bit vsyscall page now. 32bit has a real VMA now and does
* not need special handling anymore:
*/
static struct vm_area_struct gate_vma = {
.vm_start = VSYSCALL_START,
.vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC
};
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef CONFIG_IA32_EMULATION
if (test_tsk_thread_flag(tsk, TIF_IA32))
return NULL;
#endif
return &gate_vma;
}
int in_gate_area(struct task_struct *task, unsigned long addr)
{
struct vm_area_struct *vma = get_gate_vma(task);
if (!vma)
return 0;
return (addr >= vma->vm_start) && (addr < vma->vm_end);
}
/*
* Use this when you have no reliable task/vma, typically from interrupt
* context. It is less reliable than using the task's vma and may give
* false positives:
*/
int in_gate_area_no_task(unsigned long addr)
{
return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
return "[vdso]";
if (vma == &gate_vma)
return "[vsyscall]";
return NULL;
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
*/
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) {
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)) {
pte_t entry;
void *p;
p = vmemmap_alloc_block(PMD_SIZE, node);
if (!p)
return -ENOMEM;
entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
PAGE_KERNEL_LARGE);
set_pmd(pmd, __pmd(pte_val(entry)));
printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
addr, addr + PMD_SIZE - 1, p, node);
} else {
vmemmap_verify((pte_t *)pmd, node, addr, next);
}
}
return 0;
}
#endif