#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/proc_fs.h>
#include <linux/nmi.h>
#include <asm/processor.h>
+#include <asm/bios_ebda.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.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>
-#ifndef Dprintk
-#define Dprintk(x...)
-#endif
-
-const struct dma_mapping_ops* dma_ops;
-EXPORT_SYMBOL(dma_ops);
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
static unsigned long dma_reserve __initdata;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+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.
*/
-void show_mem(void)
-{
- long i, total = 0, reserved = 0;
- long shared = 0, cached = 0;
- pg_data_t *pgdat;
- struct page *page;
+pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
- printk(KERN_INFO "Mem-info:\n");
- show_free_areas();
- printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+static int disable_nx __cpuinitdata;
- 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 update 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;
- }
+/*
+ * noexec=on|off
+ * Control non-executable mappings for 64-bit processes.
+ *
+ * on Enable (default)
+ * off Disable
+ */
+static int __init nonx_setup(char *str)
+{
+ if (!str)
+ return -EINVAL;
+ if (!strncmp(str, "on", 2)) {
+ __supported_pte_mask |= _PAGE_NX;
+ disable_nx = 0;
+ } else if (!strncmp(str, "off", 3)) {
+ disable_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
}
- 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);
+ return 0;
+}
+early_param("noexec", nonx_setup);
+
+void __cpuinit check_efer(void)
+{
+ unsigned long efer;
+
+ rdmsrl(MSR_EFER, efer);
+ if (!(efer & EFER_NX) || disable_nx)
+ __supported_pte_mask &= ~_PAGE_NX;
}
-int after_bootmem;
+int force_personality32;
-static __init void *spp_getpage(void)
-{
+/*
+ * 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);
+
+/*
+ * 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);
+ 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":"");
- Dprintk("spp_getpage %p\n", ptr);
- return ptr;
-}
+ if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
+ panic("set_pte_phys: cannot allocate page data %s\n",
+ after_bootmem ? "after bootmem" : "");
+ }
-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("spp_getpage %p\n", ptr);
- Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys);
+ return ptr;
+}
- pgd = pgd_offset_k(vaddr);
+static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr)
+{
if (pgd_none(*pgd)) {
- printk("PGD FIXMAP MISSING, it should be setup in head.S!\n");
- return;
+ 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));
}
- pud = pud_offset(pgd, vaddr);
+ return pud_offset(pgd, vaddr);
+}
+
+static pmd_t *fill_pmd(pud_t *pud, unsigned long 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("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0));
- return;
- }
+ 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));
}
- pmd = pmd_offset(pud, vaddr);
+ return pmd_offset(pud, vaddr);
+}
+
+static pte_t *fill_pte(pmd_t *pmd, unsigned long 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("PAGETABLE BUG #02!\n");
- return;
- }
+ 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");
}
- new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
+ 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);
- 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);
/*
__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)
+void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
{
- unsigned long address = __fix_to_virt(idx);
+ pgd_t *pgd;
+ pud_t *pud_page;
- if (idx >= __end_of_fixed_addresses) {
- printk("Invalid __set_fixmap\n");
+ 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;
}
- set_pte_phys(address, phys, prot);
+ pud_page = (pud_t*)pgd_page_vaddr(*pgd);
+ set_pte_vaddr_pud(pud_page, vaddr, pteval);
}
-unsigned long __meminitdata table_start, table_end;
+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 _end. _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 end = roundup((unsigned long)_end, PMD_SIZE) - 1;
+ pmd_t *pmd = level2_kernel_pgt;
+ pmd_t *last_pmd = pmd + PTRS_PER_PMD;
+
+ for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
+ if (pmd_none(*pmd))
+ continue;
+ if (vaddr < (unsigned long) _text || vaddr > end)
+ set_pmd(pmd, __pmd(0));
+ }
+}
-static __meminit void *alloc_low_page(unsigned long *phys)
-{
- unsigned long pfn = table_end++;
+static __ref void *alloc_low_page(unsigned long *phys)
+{
+ unsigned long pfn = e820_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");
+ if (pfn >= e820_table_top)
+ panic("alloc_low_page: ran out of memory");
- adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
+ adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
*phys = pfn * PAGE_SIZE;
return adr;
}
-static __meminit void unmap_low_page(void *adr)
-{
-
+static __ref 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)
-{
- 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;
+}
+
+static unsigned long __meminit
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
+ pgprot_t prot)
+{
+ unsigned pages = 0;
+ 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 += PAGE_SIZE, pte++) {
+
+ if (addr >= end) {
+ if (!after_bootmem) {
+ for(; i < PTRS_PER_PTE; i++, pte++)
+ set_pte(pte, __pte(0));
+ }
+ break;
+ }
+
+ /*
+ * 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)) {
+ pages++;
+ continue;
}
- 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:
- ;
+
+ 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;
}
- printk("early_ioremap(0x%lx, %lu) failed\n", addr, size);
- return NULL;
+
+ update_page_count(PG_LEVEL_4K, pages);
+
+ return last_map_addr;
}
-/* To avoid virtual aliases later */
-__meminit void early_iounmap(void *addr, unsigned long size)
+static unsigned long __meminit
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
+ pgprot_t prot)
{
- unsigned long vaddr;
- pmd_t *pmd;
- int i, pmds;
+ pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
- 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();
+ return phys_pte_init(pte, address, end, prot);
}
-static void __meminit
-phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
+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;
+ unsigned long last_map_addr = end;
+
int i = pmd_index(address);
for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
- unsigned long entry;
+ unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
+ pte_t *pte;
+ pgprot_t new_prot = prot;
if (address >= end) {
- if (!after_bootmem)
+ if (!after_bootmem) {
for (; i < PTRS_PER_PMD; i++, pmd++)
set_pmd(pmd, __pmd(0));
+ }
break;
}
- if (pmd_val(*pmd))
+ if (pmd_val(*pmd)) {
+ if (!pmd_large(*pmd)) {
+ spin_lock(&init_mm.page_table_lock);
+ last_map_addr = phys_pte_update(pmd, 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)) {
+ pages++;
+ 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 >> PAGE_SHIFT,
+ __pgprot(pgprot_val(prot) | _PAGE_PSE)));
+ spin_unlock(&init_mm.page_table_lock);
+ last_map_addr = (address & PMD_MASK) + PMD_SIZE;
continue;
+ }
+
+ pte = alloc_low_page(&pte_phys);
+ last_map_addr = phys_pte_init(pte, address, end, new_prot);
+ unmap_low_page(pte);
- entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
- entry &= __supported_pte_mask;
- set_pmd(pmd, __pmd(entry));
+ spin_lock(&init_mm.page_table_lock);
+ pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
+ spin_unlock(&init_mm.page_table_lock);
}
+ update_page_count(PG_LEVEL_2M, pages);
+ return last_map_addr;
}
-static void __meminit
-phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
+static unsigned long __meminit
+phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
+ unsigned long page_size_mask, pgprot_t prot)
{
- 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);
+ pmd_t *pmd = pmd_offset(pud, 0);
+ unsigned long last_map_addr;
+
+ last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
__flush_tlb_all();
+ return last_map_addr;
}
-static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
-{
+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;
+ unsigned long last_map_addr = end;
int i = pud_index(addr);
-
- for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) {
+ 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;
+ pgprot_t prot = PAGE_KERNEL;
if (addr >= end)
break;
- if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) {
- set_pud(pud, __pud(0));
+ 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);
+ if (!pud_large(*pud)) {
+ last_map_addr = phys_pmd_update(pud, addr, end,
+ page_size_mask, prot);
+ 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)) {
+ pages++;
+ 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 >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+ spin_unlock(&init_mm.page_table_lock);
+ last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
continue;
}
pmd = alloc_low_page(&pmd_phys);
+ last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
+ prot);
+ unmap_low_page(pmd);
+
spin_lock(&init_mm.page_table_lock);
- set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
- phys_pmd_init(pmd, addr, end);
+ pud_populate(&init_mm, pud, __va(pmd_phys));
spin_unlock(&init_mm.page_table_lock);
- unmap_low_page(pmd);
}
- __flush_tlb();
-}
+ __flush_tlb_all();
-static void __init find_early_table_space(unsigned long end)
-{
- unsigned long puds, pmds, tables, start;
+ update_page_count(PG_LEVEL_1G, pages);
- 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);
+ return last_map_addr;
+}
- /* 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");
+static unsigned long __meminit
+phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
+ unsigned long page_size_mask)
+{
+ pud_t *pud;
- table_start >>= PAGE_SHIFT;
- table_end = table_start;
+ pud = (pud_t *)pgd_page_vaddr(*pgd);
- early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
- end, table_start << PAGE_SHIFT,
- (table_start << PAGE_SHIFT) + tables);
+ return phys_pud_init(pud, addr, end, page_size_mask);
}
-/* 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;
-
- Dprintk("init_memory_mapping\n");
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+ unsigned long end,
+ unsigned long page_size_mask)
+{
- /*
- * 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);
+ unsigned long next, last_map_addr = end;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
for (; start < end; start = next) {
- unsigned long pud_phys;
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));
+ next = (start + PGDIR_SIZE) & PGDIR_MASK;
+ if (next > end)
+ next = end;
+
+ if (pgd_val(*pgd)) {
+ last_map_addr = phys_pud_update(pgd, __pa(start),
+ __pa(end), page_size_mask);
+ continue;
+ }
+
+ pud = alloc_low_page(&pud_phys);
+ last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
+ page_size_mask);
unmap_low_page(pud);
- }
- if (!after_bootmem)
- mmu_cr4_features = read_cr4();
+ spin_lock(&init_mm.page_table_lock);
+ pgd_populate(&init_mm, pgd, __va(pud_phys));
+ spin_unlock(&init_mm.page_table_lock);
+ }
__flush_tlb_all();
+
+ return last_map_addr;
}
#ifndef CONFIG_NUMA
+void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long bootmap_size, bootmap;
+
+ bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
+ bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
+ PAGE_SIZE);
+ if (bootmap == -1L)
+ panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+ /* don't touch min_low_pfn */
+ bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
+ 0, end_pfn);
+ e820_register_active_regions(0, start_pfn, end_pfn);
+ free_bootmem_with_active_regions(0, end_pfn);
+ early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
+ reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
+}
+
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;
+ max_zone_pfns[ZONE_NORMAL] = max_pfn;
- memory_present(0, 0, end_pfn);
+ memory_present(0, 0, max_pfn);
sparse_init();
free_area_init_nodes(max_zone_pfns);
}
#endif
-/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches
- from the CPU leading to inconsistent cache lines. address and size
- must be aligned to 2MB boundaries.
- Does nothing when the mapping doesn't exist. */
-void __init clear_kernel_mapping(unsigned long address, unsigned long size)
-{
- unsigned long end = address + size;
-
- BUG_ON(address & ~LARGE_PAGE_MASK);
- BUG_ON(size & ~LARGE_PAGE_MASK);
-
- for (; address < end; address += LARGE_PAGE_SIZE) {
- pgd_t *pgd = pgd_offset_k(address);
- pud_t *pud;
- pmd_t *pmd;
- if (pgd_none(*pgd))
- continue;
- pud = pud_offset(pgd, address);
- if (pud_none(*pud))
- continue;
- pmd = pmd_offset(pud, address);
- if (!pmd || pmd_none(*pmd))
- continue;
- if (0 == (pmd_val(*pmd) & _PAGE_PSE)) {
- /* Could handle this, but it should not happen currently. */
- printk(KERN_ERR
- "clear_kernel_mapping: mapping has been split. will leak memory\n");
- pmd_ERROR(*pmd);
- }
- set_pmd(pmd, __pmd(0));
- }
- __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
{
struct pglist_data *pgdat = NODE_DATA(nid);
struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
- unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
- init_memory_mapping(start, (start + size -1));
+ last_mapped_pfn = init_memory_mapping(start, start + size);
+ if (last_mapped_pfn > max_pfn_mapped)
+ max_pfn_mapped = last_mapped_pfn;
- ret = __add_pages(zone, start_pfn, nr_pages);
- if (ret)
- goto error;
+ ret = __add_pages(nid, zone, start_pfn, nr_pages);
+ WARN_ON_ONCE(ret);
return ret;
-error:
- printk("%s: Problem encountered in __add_pages!\n", __func__);
- return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);
#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;
+static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
+ kcore_modules, kcore_vsyscall;
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
+ unsigned long absent_pages;
pci_iommu_alloc();
- /* clear the zero-page */
- memset(empty_zero_page, 0, PAGE_SIZE);
+ /* clear_bss() already clear the empty_zero_page */
reservedpages = 0;
#else
totalram_pages = free_all_bootmem();
#endif
- reservedpages = end_pfn - totalram_pages -
- absent_pages_in_range(0, end_pfn);
+ 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;
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,
+ 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,
+ kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
VSYSCALL_END - VSYSCALL_START);
- printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n",
+ printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
+ "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
- end_pfn << (PAGE_SHIFT-10),
+ max_pfn << (PAGE_SHIFT-10),
codesize >> 10,
+ absent_pages << (PAGE_SHIFT-10),
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
}
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
- unsigned long addr;
-
- if (begin >= end)
- return;
-
- printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
- 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)),
- POISON_FREE_INITMEM, PAGE_SIZE);
- if (addr >= __START_KERNEL_map)
- change_page_attr_addr(addr, 1, __pgprot(0));
- free_page(addr);
- totalram_pages++;
- }
- if (addr > __START_KERNEL_map)
- global_flush_tlb();
-}
-
-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;
+ unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
+ unsigned long rodata_start =
+ ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
-#ifdef CONFIG_HOTPLUG_CPU
- /* It must still be possible to apply SMP alternatives. */
- if (num_possible_cpus() > 1)
- start = (unsigned long)_etext;
+#ifdef CONFIG_DYNAMIC_FTRACE
+ /* Dynamic tracing modifies the kernel text section */
+ start = rodata_start;
#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;
-
- change_page_attr_addr(start, (end - start) >> PAGE_SHIFT, PAGE_KERNEL_RO);
-
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
+ set_memory_ro(start, (end - start) >> PAGE_SHIFT);
/*
- * change_page_attr_addr() requires a global_flush_tlb() call after it.
- * We do this after the printk so that if something went wrong in the
- * change, the printk gets out at least to give a better debug hint
- * of who is the culprit.
+ * The rodata section (but not the kernel text!) should also be
+ * not-executable.
*/
- global_flush_tlb();
-}
-#endif
+ set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- free_init_pages("initrd memory", start, end);
+ 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
-void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
-{
+int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+ int flags)
+{
#ifdef CONFIG_NUMA
- int nid = phys_to_nid(phys);
+ int nid, next_nid;
+ int ret;
#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",
+
+ if (pfn >= max_pfn) {
+ /*
+ * This can happen with kdump kernels when accessing
+ * firmware tables:
+ */
+ if (pfn < max_pfn_mapped)
+ return -EFAULT;
+
+ printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
phys, len);
- return;
+ return -EFAULT;
}
/* 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);
+ nid = phys_to_nid(phys);
+ next_nid = phys_to_nid(phys + len - 1);
+ if (nid == next_nid)
+ ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
+ else
+ ret = reserve_bootmem(phys, len, flags);
+
+ if (ret != 0)
+ return ret;
+
+#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);
}
+
+ return 0;
}
-int kern_addr_valid(unsigned long addr)
-{
+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;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
if (above != 0 && above != -1UL)
- return 0;
-
+ return 0;
+
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd))
return 0;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
- return 0;
+ 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. */
-
+/*
+ * 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_SHIFT),
- .vm_page_prot = PAGE_READONLY_EXEC,
- .vm_flags = VM_READ | VM_EXEC
+ .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)
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.
+/*
+ * 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)
{
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
*/
-int __meminit vmemmap_populate(struct page *start_page,
- unsigned long size, int node)
+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);
pmd_t *pmd;
for (; addr < end; addr = next) {
- next = pmd_addr_end(addr, end);
+ void *p = NULL;
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 = vmemmap_alloc_block(PMD_SIZE, node);
+ 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;
- entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
- mk_pte_huge(entry);
- set_pmd(pmd, __pmd(pte_val(entry)));
+ 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;
+
+ 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)));
+
+ /* 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);
+ }
- 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;
}
+
+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