/*
* The mincore() system call.
*/
-#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/syscalls.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/hugetlb.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
+static void mincore_hugetlb_page_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ struct hstate *h;
+
+ h = hstate_vma(vma);
+ while (1) {
+ unsigned char present;
+ pte_t *ptep;
+ /*
+ * Huge pages are always in RAM for now, but
+ * theoretically it needs to be checked.
+ */
+ ptep = huge_pte_offset(current->mm,
+ addr & huge_page_mask(h));
+ present = ptep && !huge_pte_none(huge_ptep_get(ptep));
+ while (1) {
+ *vec = present;
+ vec++;
+ addr += PAGE_SIZE;
+ if (addr == end)
+ return;
+ /* check hugepage border */
+ if (!(addr & ~huge_page_mask(h)))
+ break;
+ }
+ }
+#else
+ BUG();
+#endif
+}
+
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
-static unsigned char mincore_page(struct vm_area_struct * vma,
- unsigned long pgoff)
+static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
{
unsigned char present = 0;
- struct address_space * as = vma->vm_file->f_mapping;
- struct page * page;
+ struct page *page;
- page = find_get_page(as, pgoff);
+ /*
+ * When tmpfs swaps out a page from a file, any process mapping that
+ * file will not get a swp_entry_t in its pte, but rather it is like
+ * any other file mapping (ie. marked !present and faulted in with
+ * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
+ *
+ * However when tmpfs moves the page from pagecache and into swapcache,
+ * it is still in core, but the find_get_page below won't find it.
+ * No big deal, but make a note of it.
+ */
+ page = find_get_page(mapping, pgoff);
if (page) {
present = PageUptodate(page);
page_cache_release(page);
return present;
}
+static void mincore_unmapped_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+ unsigned long nr = (end - addr) >> PAGE_SHIFT;
+ int i;
+
+ if (vma->vm_file) {
+ pgoff_t pgoff;
+
+ pgoff = linear_page_index(vma, addr);
+ for (i = 0; i < nr; i++, pgoff++)
+ vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
+ } else {
+ for (i = 0; i < nr; i++)
+ vec[i] = 0;
+ }
+}
+
+static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+ unsigned long next;
+ spinlock_t *ptl;
+ pte_t *ptep;
+
+ ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ do {
+ pte_t pte = *ptep;
+ pgoff_t pgoff;
+
+ next = addr + PAGE_SIZE;
+ if (pte_none(pte))
+ mincore_unmapped_range(vma, addr, next, vec);
+ else if (pte_present(pte))
+ *vec = 1;
+ else if (pte_file(pte)) {
+ pgoff = pte_to_pgoff(pte);
+ *vec = mincore_page(vma->vm_file->f_mapping, pgoff);
+ } else { /* pte is a swap entry */
+ swp_entry_t entry = pte_to_swp_entry(pte);
+
+ if (is_migration_entry(entry)) {
+ /* migration entries are always uptodate */
+ *vec = 1;
+ } else {
+#ifdef CONFIG_SWAP
+ pgoff = entry.val;
+ *vec = mincore_page(&swapper_space, pgoff);
+#else
+ WARN_ON(1);
+ *vec = 1;
+#endif
+ }
+ }
+ vec++;
+ } while (ptep++, addr = next, addr != end);
+ pte_unmap_unlock(ptep - 1, ptl);
+}
+
+static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+ unsigned long next;
+ pmd_t *pmd;
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none_or_clear_bad(pmd))
+ mincore_unmapped_range(vma, addr, next, vec);
+ else
+ mincore_pte_range(vma, pmd, addr, next, vec);
+ vec += (next - addr) >> PAGE_SHIFT;
+ } while (pmd++, addr = next, addr != end);
+}
+
+static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+ unsigned long next;
+ pud_t *pud;
+
+ pud = pud_offset(pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(pud))
+ mincore_unmapped_range(vma, addr, next, vec);
+ else
+ mincore_pmd_range(vma, pud, addr, next, vec);
+ vec += (next - addr) >> PAGE_SHIFT;
+ } while (pud++, addr = next, addr != end);
+}
+
+static void mincore_page_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end,
+ unsigned char *vec)
+{
+ unsigned long next;
+ pgd_t *pgd;
+
+ pgd = pgd_offset(vma->vm_mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(pgd))
+ mincore_unmapped_range(vma, addr, next, vec);
+ else
+ mincore_pud_range(vma, pgd, addr, next, vec);
+ vec += (next - addr) >> PAGE_SHIFT;
+ } while (pgd++, addr = next, addr != end);
+}
+
/*
* Do a chunk of "sys_mincore()". We've already checked
* all the arguments, we hold the mmap semaphore: we should
* just return the amount of info we're asked for.
*/
-static long do_mincore(unsigned long addr, unsigned char *vec, unsigned long pages)
+static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
{
- unsigned long i, nr, pgoff;
- struct vm_area_struct *vma = find_vma(current->mm, addr);
+ struct vm_area_struct *vma;
+ unsigned long end;
- /*
- * find_vma() didn't find anything above us, or we're
- * in an unmapped hole in the address space: ENOMEM.
- */
+ vma = find_vma(current->mm, addr);
if (!vma || addr < vma->vm_start)
return -ENOMEM;
- /*
- * Ok, got it. But check whether it's a segment we support
- * mincore() on. Right now, we don't do any anonymous mappings.
- *
- * FIXME: This is just stupid. And returning ENOMEM is
- * stupid too. We should just look at the page tables. But
- * this is what we've traditionally done, so we'll just
- * continue doing it.
- */
- if (!vma->vm_file)
- return -ENOMEM;
+ end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
- /*
- * Calculate how many pages there are left in the vma, and
- * what the pgoff is for our address.
- */
- nr = (vma->vm_end - addr) >> PAGE_SHIFT;
- if (nr > pages)
- nr = pages;
+ if (is_vm_hugetlb_page(vma)) {
+ mincore_hugetlb_page_range(vma, addr, end, vec);
+ return (end - addr) >> PAGE_SHIFT;
+ }
- pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
- pgoff += vma->vm_pgoff;
+ end = pmd_addr_end(addr, end);
- /* And then we just fill the sucker in.. */
- for (i = 0 ; i < nr; i++, pgoff++)
- vec[i] = mincore_page(vma, pgoff);
+ if (is_vm_hugetlb_page(vma))
+ mincore_hugetlb_page_range(vma, addr, end, vec);
+ else
+ mincore_page_range(vma, addr, end, vec);
- return nr;
+ return (end - addr) >> PAGE_SHIFT;
}
/*
* mapped
* -EAGAIN - A kernel resource was temporarily unavailable.
*/
-asmlinkage long sys_mincore(unsigned long start, size_t len,
- unsigned char __user * vec)
+SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
+ unsigned char __user *, vec)
{
long retval;
unsigned long pages;
* the temporary buffer size.
*/
down_read(¤t->mm->mmap_sem);
- retval = do_mincore(start, tmp, min(pages, PAGE_SIZE));
+ retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
up_read(¤t->mm->mmap_sem);
if (retval <= 0)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff