* Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
*/
-#include <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
+#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#define Dprintk(x...)
#endif
-struct dma_mapping_ops* dma_ops;
+const struct dma_mapping_ops* dma_ops;
EXPORT_SYMBOL(dma_ops);
static unsigned long dma_reserve __initdata;
unsigned long __initdata table_start, table_end;
-extern pmd_t temp_boot_pmds[];
-
-static struct temp_map {
- pmd_t *pmd;
- void *address;
- int allocated;
-} temp_mappings[] __initdata = {
- { &temp_boot_pmds[0], (void *)(40UL * 1024 * 1024) },
- { &temp_boot_pmds[1], (void *)(42UL * 1024 * 1024) },
- {}
-};
-
-static __meminit void *alloc_low_page(int *index, unsigned long *phys)
+static __meminit void *alloc_low_page(unsigned long *phys)
{
- struct temp_map *ti;
- int i;
- unsigned long pfn = table_end++, paddr;
+ unsigned long pfn = table_end++;
void *adr;
if (after_bootmem) {
if (pfn >= end_pfn)
panic("alloc_low_page: ran out of memory");
- for (i = 0; temp_mappings[i].allocated; i++) {
- if (!temp_mappings[i].pmd)
- panic("alloc_low_page: ran out of temp mappings");
- }
- ti = &temp_mappings[i];
- paddr = (pfn << PAGE_SHIFT) & PMD_MASK;
- set_pmd(ti->pmd, __pmd(paddr | _KERNPG_TABLE | _PAGE_PSE));
- ti->allocated = 1;
- __flush_tlb();
- adr = ti->address + ((pfn << PAGE_SHIFT) & ~PMD_MASK);
+
+ adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
- *index = i;
- *phys = pfn * PAGE_SIZE;
- return adr;
-}
+ *phys = pfn * PAGE_SIZE;
+ return adr;
+}
-static __meminit void unmap_low_page(int i)
+static __meminit void unmap_low_page(void *adr)
{
- struct temp_map *ti;
if (after_bootmem)
return;
- ti = &temp_mappings[i];
- set_pmd(ti->pmd, __pmd(0));
- ti->allocated = 0;
+ early_iounmap(adr, PAGE_SIZE);
}
/* Must run before zap_low_mappings */
__init void *early_ioremap(unsigned long addr, unsigned long size)
{
- unsigned long map = round_down(addr, LARGE_PAGE_SIZE);
-
- /* actually usually some more */
- if (size >= LARGE_PAGE_SIZE) {
- printk("SMBIOS area too long %lu\n", size);
- return NULL;
+ unsigned long vaddr;
+ pmd_t *pmd, *last_pmd;
+ 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 next;
+ }
+ vaddr += addr & ~PMD_MASK;
+ addr &= PMD_MASK;
+ for (i = 0; i < pmds; i++, addr += PMD_SIZE)
+ set_pmd(pmd + i,__pmd(addr | _KERNPG_TABLE | _PAGE_PSE));
+ __flush_tlb();
+ return (void *)vaddr;
+ next:
+ ;
}
- set_pmd(temp_mappings[0].pmd, __pmd(map | _KERNPG_TABLE | _PAGE_PSE));
- map += LARGE_PAGE_SIZE;
- set_pmd(temp_mappings[1].pmd, __pmd(map | _KERNPG_TABLE | _PAGE_PSE));
- __flush_tlb();
- return temp_mappings[0].address + (addr & (LARGE_PAGE_SIZE-1));
+ printk("early_ioremap(0x%lx, %lu) failed\n", addr, size);
+ return NULL;
}
/* To avoid virtual aliases later */
__init void early_iounmap(void *addr, unsigned long size)
{
- if ((void *)round_down((unsigned long)addr, LARGE_PAGE_SIZE) != temp_mappings[0].address)
- printk("early_iounmap: bad address %p\n", addr);
- set_pmd(temp_mappings[0].pmd, __pmd(0));
- set_pmd(temp_mappings[1].pmd, __pmd(0));
+ 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();
}
static void __meminit
-phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end)
+phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
{
- int i;
+ int i = pmd_index(address);
- for (i = 0; i < PTRS_PER_PMD; pmd++, i++, address += PMD_SIZE) {
+ for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
unsigned long entry;
+ pmd_t *pmd = pmd_page + pmd_index(address);
if (address >= end) {
if (!after_bootmem)
set_pmd(pmd, __pmd(0));
break;
}
+
+ if (pmd_val(*pmd))
+ continue;
+
entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
entry &= __supported_pte_mask;
set_pmd(pmd, __pmd(entry));
static void __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
{
- pmd_t *pmd = pmd_offset(pud, (unsigned long)__va(address));
-
- if (pmd_none(*pmd)) {
- spin_lock(&init_mm.page_table_lock);
- phys_pmd_init(pmd, address, end);
- spin_unlock(&init_mm.page_table_lock);
- __flush_tlb_all();
- }
+ 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, unsigned long address, unsigned long end)
+static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
{
- long i = pud_index(address);
-
- pud = pud + i;
+ int i = pud_index(addr);
- if (after_bootmem && pud_val(*pud)) {
- phys_pmd_update(pud, address, end);
- return;
- }
- for (; i < PTRS_PER_PUD; pud++, i++) {
- int map;
- unsigned long paddr, pmd_phys;
+ 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;
- paddr = (address & PGDIR_MASK) + i*PUD_SIZE;
- if (paddr >= end)
+ if (addr >= end)
break;
- if (!after_bootmem && !e820_any_mapped(paddr, paddr+PUD_SIZE, 0)) {
+ if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) {
set_pud(pud, __pud(0));
continue;
}
- pmd = alloc_low_page(&map, &pmd_phys);
+ 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, paddr, end);
+ phys_pmd_init(pmd, addr, end);
spin_unlock(&init_mm.page_table_lock);
- unmap_low_page(map);
+ unmap_low_page(pmd);
}
__flush_tlb();
}
end = (unsigned long)__va(end);
for (; start < end; start = next) {
- int map;
unsigned long pud_phys;
pgd_t *pgd = pgd_offset_k(start);
pud_t *pud;
if (after_bootmem)
pud = pud_offset(pgd, start & PGDIR_MASK);
else
- pud = alloc_low_page(&map, &pud_phys);
+ pud = alloc_low_page(&pud_phys);
next = start + PGDIR_SIZE;
if (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(map);
+ unmap_low_page(pud);
}
if (!after_bootmem)
__flush_tlb_all();
}
-/* Compute zone sizes for the DMA and DMA32 zones in a node. */
-__init void
-size_zones(unsigned long *z, unsigned long *h,
- unsigned long start_pfn, unsigned long end_pfn)
-{
- int i;
- unsigned long w;
-
- for (i = 0; i < MAX_NR_ZONES; i++)
- z[i] = 0;
-
- if (start_pfn < MAX_DMA_PFN)
- z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
- if (start_pfn < MAX_DMA32_PFN) {
- unsigned long dma32_pfn = MAX_DMA32_PFN;
- if (dma32_pfn > end_pfn)
- dma32_pfn = end_pfn;
- z[ZONE_DMA32] = dma32_pfn - start_pfn;
- }
- z[ZONE_NORMAL] = end_pfn - start_pfn;
-
- /* Remove lower zones from higher ones. */
- w = 0;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- if (z[i])
- z[i] -= w;
- w += z[i];
- }
-
- /* Compute holes */
- w = start_pfn;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- unsigned long s = w;
- w += z[i];
- h[i] = e820_hole_size(s, w);
- }
-
- /* Add the space pace needed for mem_map to the holes too. */
- for (i = 0; i < MAX_NR_ZONES; i++)
- h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
-
- /* The 16MB DMA zone has the kernel and other misc mappings.
- Account them too */
- if (h[ZONE_DMA]) {
- h[ZONE_DMA] += dma_reserve;
- if (h[ZONE_DMA] >= z[ZONE_DMA]) {
- printk(KERN_WARNING
- "Kernel too large and filling up ZONE_DMA?\n");
- h[ZONE_DMA] = z[ZONE_DMA];
- }
- }
-}
-
#ifndef CONFIG_NUMA
void __init paging_init(void)
{
- unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
+ 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();
- size_zones(zones, holes, 0, end_pfn);
- free_area_init_node(0, NODE_DATA(0), zones,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
+ free_area_init_nodes(max_zone_pfns);
}
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
- * XXX: memory_add_physaddr_to_nid() is to find node id from physical address
- * via probe interface of sysfs. If acpi notifies hot-add event, then it
- * can tell node id by searching dsdt. But, probe interface doesn't have
- * node id. So, return 0 as node id at this time.
- */
-#ifdef CONFIG_NUMA
-int memory_add_physaddr_to_nid(u64 start)
-{
- return 0;
-}
-#endif
-
-/*
* Memory is added always to NORMAL zone. This means you will never get
* additional DMA/DMA32 memory.
*/
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdat = NODE_DATA(nid);
- struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
+ 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);
if (ret)
goto error;
- init_memory_mapping(start, (start + size -1));
-
return ret;
error:
printk("%s: Problem encountered in __add_pages!\n", __func__);
}
EXPORT_SYMBOL_GPL(remove_memory);
-#else /* CONFIG_MEMORY_HOTPLUG */
+#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 */
+
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
/*
* Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
* just online the pages.
}
return err;
}
-#endif /* CONFIG_MEMORY_HOTPLUG */
+#endif
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
kcore_vsyscall;
pci_iommu_alloc();
- /* How many end-of-memory variables you have, grandma! */
- max_low_pfn = end_pfn;
- max_pfn = end_pfn;
- num_physpages = end_pfn;
- high_memory = (void *) __va(end_pfn * PAGE_SIZE);
-
/* clear the zero-page */
memset(empty_zero_page, 0, PAGE_SIZE);
#else
totalram_pages = free_all_bootmem();
#endif
- reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);
+ reservedpages = end_pfn - totalram_pages -
+ absent_pages_in_range(0, end_pfn);
after_bootmem = 1;
for (addr = begin; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
- memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE);
+ memset((void *)(addr & ~(PAGE_SIZE-1)),
+ POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
void free_initmem(void)
{
- memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
+ memset(__initdata_begin, POISON_FREE_INITDATA,
+ __initdata_end - __initdata_begin);
free_init_pages("unused kernel memory",
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
#ifdef CONFIG_DEBUG_RODATA
-extern char __start_rodata, __end_rodata;
void mark_rodata_ro(void)
{
- unsigned long addr = (unsigned long)&__start_rodata;
+ unsigned long addr = (unsigned long)__start_rodata;
- for (; addr < (unsigned long)&__end_rodata; addr += PAGE_SIZE)
+ for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
change_page_attr_addr(addr, 1, PAGE_KERNEL_RO);
printk ("Write protecting the kernel read-only data: %luk\n",
- (&__end_rodata - &__start_rodata) >> 10);
+ (__end_rodata - __start_rodata) >> 10);
/*
* change_page_attr_addr() requires a global_flush_tlb() call after it.
void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
{
- /* Should check here against the e820 map to avoid double free */
#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);
#else
reserve_bootmem(phys, len);
#endif
- if (phys+len <= MAX_DMA_PFN*PAGE_SIZE)
+ 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)
extern int exception_trace, page_fault_trace;
static ctl_table debug_table2[] = {
- { 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL,
- proc_dointvec },
- { 0, }
+ {
+ .ctl_name = 99,
+ .procname = "exception-trace",
+ .data = &exception_trace,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {}
};
static ctl_table debug_root_table2[] = {
- { .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555,
- .child = debug_table2 },
- { 0 },
+ {
+ .ctl_name = CTL_DEBUG,
+ .procname = "debug",
+ .mode = 0555,
+ .child = debug_table2
+ },
+ {}
};
static __init int x8664_sysctl_init(void)
{
- register_sysctl_table(debug_root_table2, 1);
+ register_sysctl_table(debug_root_table2);
return 0;
}
__initcall(x8664_sysctl_init);
#endif
-/* A pseudo VMAs to allow ptrace access for the vsyscall page. This only
+/* 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_END,
- .vm_page_prot = PAGE_READONLY
+ .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES << PAGE_SHIFT),
+ .vm_page_prot = PAGE_READONLY_EXEC,
+ .vm_flags = VM_READ | VM_EXEC
};
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff