#include <linux/bootmem.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
-#include <linux/efi.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
#include <asm/sections.h>
#include <asm/paravirt.h>
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
- paravirt_alloc_pd(__pa(pmd_table) >> PAGE_SHIFT);
+ paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
pud = pud_offset(pgd, 0);
if (pmd_table != pmd_offset(pud, 0))
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
- pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ pte_t *page_table = NULL;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
+#endif
+ if (!page_table)
+ page_table =
+ (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
BUG_ON(page_table != pte_offset_kernel(pmd, 0));
}
-
+
return pte_offset_kernel(pmd, 0);
}
pmd = one_md_table_init(pgd);
if (pfn >= max_low_pfn)
continue;
- for (pmd_idx = 0; pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; pmd++, pmd_idx++) {
+ for (pmd_idx = 0;
+ pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn;
+ pmd++, pmd_idx++) {
unsigned int address = pfn * PAGE_SIZE + PAGE_OFFSET;
- /* Map with big pages if possible, otherwise create normal page tables. */
+ /* Map with big pages if possible, otherwise
+ create normal page tables. */
if (cpu_has_pse) {
- unsigned int address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1;
- if (is_kernel_text(address) || is_kernel_text(address2))
- set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
- else
- set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE));
+ unsigned int address2;
+ pgprot_t prot = PAGE_KERNEL_LARGE;
+
+ address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE +
+ PAGE_OFFSET + PAGE_SIZE-1;
+
+ if (is_kernel_text(address) ||
+ is_kernel_text(address2))
+ prot = PAGE_KERNEL_LARGE_EXEC;
+
+ set_pmd(pmd, pfn_pmd(pfn, prot));
pfn += PTRS_PER_PTE;
} else {
for (pte_ofs = 0;
pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn;
pte++, pfn++, pte_ofs++, address += PAGE_SIZE) {
+ pgprot_t prot = PAGE_KERNEL;
+
if (is_kernel_text(address))
- set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
- else
- set_pte(pte, pfn_pte(pfn, PAGE_KERNEL));
+ prot = PAGE_KERNEL_EXEC;
+
+ set_pte(pte, pfn_pte(pfn, prot));
}
}
}
return 0;
}
-int page_is_ram(unsigned long pagenr)
-{
- int i;
- unsigned long addr, end;
-
- if (efi_enabled) {
- efi_memory_desc_t *md;
- void *p;
-
- for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
- md = p;
- if (!is_available_memory(md))
- continue;
- addr = (md->phys_addr+PAGE_SIZE-1) >> PAGE_SHIFT;
- end = (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)) >> PAGE_SHIFT;
-
- if ((pagenr >= addr) && (pagenr < end))
- return 1;
- }
- return 0;
- }
-
- for (i = 0; i < e820.nr_map; i++) {
-
- if (e820.map[i].type != E820_RAM) /* not usable memory */
- continue;
- /*
- * !!!FIXME!!! Some BIOSen report areas as RAM that
- * are not. Notably the 640->1Mb area. We need a sanity
- * check here.
- */
- addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT;
- end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT;
- if ((pagenr >= addr) && (pagenr < end))
- return 1;
- }
- return 0;
-}
-
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
static void __init set_highmem_pages_init(int bad_ppro)
{
int pfn;
- for (pfn = highstart_pfn; pfn < highend_pfn; pfn++)
- add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
+ for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) {
+ /*
+ * Holes under sparsemem might not have no mem_map[]:
+ */
+ if (pfn_valid(pfn))
+ add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
+ }
totalram_pages += totalhigh_pages;
}
#endif /* CONFIG_FLATMEM */
#define set_highmem_pages_init(bad_ppro) do { } while (0)
#endif /* CONFIG_HIGHMEM */
-unsigned long long __PAGE_KERNEL = _PAGE_KERNEL;
+pteval_t __PAGE_KERNEL = _PAGE_KERNEL;
EXPORT_SYMBOL(__PAGE_KERNEL);
-unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;
+pteval_t __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;
#ifdef CONFIG_NUMA
extern void __init remap_numa_kva(void);
memset(&base[USER_PTRS_PER_PGD], 0,
KERNEL_PGD_PTRS * sizeof(pgd_t));
#else
- paravirt_alloc_pd(__pa(swapper_pg_dir) >> PAGE_SHIFT);
+ paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT);
#endif
}
* Fixed mappings, only the page table structure has to be
* created - mappings will be set by set_fixmap():
*/
+ early_ioremap_clear();
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
page_table_range_init(vaddr, end, pgd_base);
+ early_ioremap_reset();
permanent_kmaps_init(pgd_base);
int nx_enabled = 0;
+pteval_t __supported_pte_mask __read_mostly = ~_PAGE_NX;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+
#ifdef CONFIG_X86_PAE
static int disable_nx __initdata = 0;
-u64 __supported_pte_mask __read_mostly = ~_PAGE_NX;
-EXPORT_SYMBOL_GPL(__supported_pte_mask);
/*
* noexec = on|off
}
}
-/*
- * Enables/disables executability of a given kernel page and
- * returns the previous setting.
- */
-int __init set_kernel_exec(unsigned long vaddr, int enable)
-{
- pte_t *pte;
- int ret = 1;
-
- if (!nx_enabled)
- goto out;
-
- pte = lookup_address(vaddr);
- BUG_ON(!pte);
-
- if (!pte_exec_kernel(*pte))
- ret = 0;
-
- if (enable)
- pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
- else
- pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
- pte_update_defer(&init_mm, vaddr, pte);
- __flush_tlb_all();
-out:
- return ret;
-}
-
#endif
/*
return __add_pages(zone, start_pfn, nr_pages);
}
-int remove_memory(u64 start, u64 size)
-{
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(remove_memory);
#endif
struct kmem_cache *pmd_cache;
void __init pgtable_cache_init(void)
{
- size_t pgd_size = PTRS_PER_PGD*sizeof(pgd_t);
-
- if (PTRS_PER_PMD > 1) {
+ if (PTRS_PER_PMD > 1)
pmd_cache = kmem_cache_create("pmd",
- PTRS_PER_PMD*sizeof(pmd_t),
- PTRS_PER_PMD*sizeof(pmd_t),
- SLAB_PANIC,
- pmd_ctor);
- if (!SHARED_KERNEL_PMD) {
- /* If we're in PAE mode and have a non-shared
- kernel pmd, then the pgd size must be a
- page size. This is because the pgd_list
- links through the page structure, so there
- can only be one pgd per page for this to
- work. */
- pgd_size = PAGE_SIZE;
- }
- }
+ PTRS_PER_PMD*sizeof(pmd_t),
+ PTRS_PER_PMD*sizeof(pmd_t),
+ SLAB_PANIC,
+ pmd_ctor);
}
/*
}
#ifdef CONFIG_DEBUG_RODATA
+const int rodata_test_data = 0xC3;
+EXPORT_SYMBOL_GPL(rodata_test_data);
void mark_rodata_ro(void)
{
if (num_possible_cpus() <= 1)
#endif
{
- change_page_attr(virt_to_page(start),
- size >> PAGE_SHIFT, PAGE_KERNEL_RX);
+ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
printk("Write protecting the kernel text: %luk\n", size >> 10);
+
+#ifdef CONFIG_CPA_DEBUG
+ printk("Testing CPA: Reverting %lx-%lx\n", start, start+size);
+ set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT);
+
+ printk("Testing CPA: write protecting again\n");
+ set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
+#endif
}
#endif
start += size;
size = (unsigned long)__end_rodata - start;
- change_page_attr(virt_to_page(start),
- size >> PAGE_SHIFT, PAGE_KERNEL_RO);
+ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
printk("Write protecting the kernel read-only data: %luk\n",
size >> 10);
+ rodata_test();
- /*
- * change_page_attr() 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.
- */
- global_flush_tlb();
+#ifdef CONFIG_CPA_DEBUG
+ printk("Testing CPA: undo %lx-%lx\n", start, start + size);
+ set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+
+ printk("Testing CPA: write protecting again\n");
+ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+#endif
}
#endif
{
unsigned long addr;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /*
+ * 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:
+ */
+ printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
+ begin, PAGE_ALIGN(end));
+ set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+#else
+ /*
+ * We just marked the kernel text read only above, now that
+ * we are going to free part of that, we need to make that
+ * writeable first.
+ */
+ set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
+
for (addr = begin; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
totalram_pages++;
}
printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
+#endif
}
void free_initmem(void)
git.samba.org / sfrench / cifs-2.6.git / blobdiff