* 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>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
-#include <asm/dma-mapping.h>
-#include <asm/swiotlb.h>
#ifndef Dprintk
#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;
show_free_areas();
printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
- for_each_pgdat(pgdat) {
+ for_each_online_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
page = pfn_to_page(pgdat->node_start_pfn + i);
total++;
printk(KERN_INFO "%lu pages swap cached\n",cached);
}
-/* References to section boundaries */
-
int after_bootmem;
-static void *spp_getpage(void)
+static __init void *spp_getpage(void)
{
void *ptr;
if (after_bootmem)
return ptr;
}
-static void set_pte_phys(unsigned long vaddr,
+static __init void set_pte_phys(unsigned long vaddr,
unsigned long phys, pgprot_t prot)
{
pgd_t *pgd;
}
/* NOTE: this is meant to be run only at boot */
-void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+void __init
+__set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
unsigned long address = __fix_to_virt(idx);
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 __init 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) {
+ adr = (void *)get_zeroed_page(GFP_ATOMIC);
+ *phys = __pa(adr);
+ return adr;
+ }
+
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);
- *index = i;
- *phys = pfn * PAGE_SIZE;
- return adr;
-}
-static __init void unmap_low_page(int i)
+ 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)
{
- struct temp_map *ti = &temp_mappings[i];
- set_pmd(ti->pmd, __pmd(0));
- ti->allocated = 0;
+
+ if (after_bootmem)
+ return;
+
+ early_iounmap(adr, PAGE_SIZE);
}
-static void __init phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
+/* Must run before zap_low_mappings */
+__init void *early_ioremap(unsigned long addr, unsigned long size)
+{
+ 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:
+ ;
+ }
+ 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)
+{
+ 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_page, unsigned long address, unsigned long end)
+{
+ int i = pmd_index(address);
+
+ 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)
+ for (; i < PTRS_PER_PMD; i++, pmd++)
+ 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,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)
{
- long i, j;
+ int i = pud_index(addr);
+
- i = pud_index(address);
- pud = pud + i;
- 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 + i*PUD_SIZE;
- if (paddr >= end) {
- for (; i < PTRS_PER_PUD; i++, pud++)
- set_pud(pud, __pud(0));
+ if (addr >= end)
break;
- }
- if (!e820_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);
- set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
- for (j = 0; j < PTRS_PER_PMD; pmd++, j++, paddr += PMD_SIZE) {
- unsigned long pe;
-
- if (paddr >= end) {
- for (; j < PTRS_PER_PMD; j++, pmd++)
- set_pmd(pmd, __pmd(0));
- break;
- }
- pe = _PAGE_NX|_PAGE_PSE | _KERNPG_TABLE | _PAGE_GLOBAL | paddr;
- pe &= __supported_pte_mask;
- set_pmd(pmd, __pmd(pe));
+ if (pud_val(*pud)) {
+ phys_pmd_update(pud, addr, end);
+ continue;
}
- unmap_low_page(map);
+
+ 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();
}
tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) +
round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
- /* Put page tables beyond the DMA zones if possible.
- RED-PEN might be better to spread them out more over
- memory to avoid hotspots */
- if (end > MAX_DMA32_PFN<<PAGE_SHIFT)
- start = MAX_DMA32_PFN << PAGE_SHIFT;
- else if (end > MAX_DMA_PFN << PAGE_SHIFT)
- start = MAX_DMA_PFN << PAGE_SHIFT;
- else
- start = 0x8000;
-
- table_start = find_e820_area(start, end, tables);
- if (table_start == -1)
- table_start = find_e820_area(0x8000, end, tables);
+ /* 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;
+ table_start = find_e820_area(start, end, tables);
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 init_memory_mapping(unsigned long start, unsigned long end)
+void __meminit init_memory_mapping(unsigned long start, unsigned long end)
{
unsigned long next;
* mapped. Unfortunately this is done currently before the nodes are
* discovered.
*/
- find_early_table_space(end);
+ if (!after_bootmem)
+ find_early_table_space(end);
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
for (; start < end; start = next) {
- int map;
unsigned long pud_phys;
- pud_t *pud = alloc_low_page(&map, &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(&pud_phys);
+
next = start + PGDIR_SIZE;
if (next > end)
next = end;
phys_pud_init(pud, __pa(start), __pa(next));
- set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
- unmap_low_page(map);
+ if (!after_bootmem)
+ set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
+ unmap_low_page(pud);
}
- asm volatile("movq %%cr4,%0" : "=r" (mmu_cr4_features));
+ if (!after_bootmem)
+ asm volatile("movq %%cr4,%0" : "=r" (mmu_cr4_features));
__flush_tlb_all();
- early_printk("kernel direct mapping tables upto %lx @ %lx-%lx\n", end,
- table_start<<PAGE_SHIFT,
- table_end<<PAGE_SHIFT);
}
void __cpuinit zap_low_mappings(int cpu)
__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];
- size_zones(zones, holes, 0, end_pfn);
- free_area_init_node(0, NODE_DATA(0), zones,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
+ 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
__flush_tlb_all();
}
+/*
+ * 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);
+ 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;
+
+ return ret;
+error:
+ printk("%s: Problem encountered in __add_pages!\n", __func__);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arch_add_memory);
+
+int remove_memory(u64 start, u64 size)
+{
+ return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(remove_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 */
+
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+/*
+ * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
+ * just online the pages.
+ */
+int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+{
+ int err = -EIO;
+ unsigned long pfn;
+ unsigned long total = 0, mem = 0;
+ for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
+ if (pfn_valid(pfn)) {
+ online_page(pfn_to_page(pfn));
+ err = 0;
+ mem++;
+ }
+ total++;
+ }
+ if (!err) {
+ z->spanned_pages += total;
+ z->present_pages += mem;
+ z->zone_pgdat->node_spanned_pages += total;
+ z->zone_pgdat->node_present_pages += mem;
+ }
+ return err;
+}
+#endif
+
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
kcore_vsyscall;
{
long codesize, reservedpages, datasize, initsize;
-#ifdef CONFIG_SWIOTLB
- pci_swiotlb_init();
-#endif
- no_iommu_init();
-
- /* 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);
+ pci_iommu_alloc();
/* 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;
#endif
}
-void free_initmem(void)
+void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
unsigned long addr;
- addr = (unsigned long)(&__init_begin);
- for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ if (begin >= end)
+ return;
+
+ printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
- set_page_count(virt_to_page(addr), 1);
- memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE);
+ init_page_count(virt_to_page(addr));
+ memset((void *)(addr & ~(PAGE_SIZE-1)),
+ POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
- memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
- printk ("Freeing unused kernel memory: %luk freed\n", (__init_end - __init_begin) >> 10);
+}
+
+void free_initmem(void)
+{
+ 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.
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
- if (start < (unsigned long)&_end)
- return;
- printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
- for (; start < end; start += PAGE_SIZE) {
- ClearPageReserved(virt_to_page(start));
- set_page_count(virt_to_page(start), 1);
- free_page(start);
- totalram_pages++;
- }
+ free_init_pages("initrd memory", start, end);
}
#endif
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