On Wed, 10 Sep 2014 16:24:46 -0700 Peter Feiner <pfeiner@xxxxxxxxxx> wrote:
> If a /proc/pid/pagemap read spans a [VMA, an unmapped region, then a
> VM_SOFTDIRTY VMA], the virtual pages in the unmapped region are reported
> as softdirty. Here's a program to demonstrate the bug:
>
> int main() {
> const uint64_t PAGEMAP_SOFTDIRTY = 1ul << 55;
> uint64_t pme[3];
> int fd = open("/proc/self/pagemap", O_RDONLY);;
> char *m = mmap(NULL, 3 * getpagesize(), PROT_READ,
> MAP_ANONYMOUS | MAP_SHARED, -1, 0);
> munmap(m + getpagesize(), getpagesize());
> pread(fd, pme, 24, (unsigned long) m / getpagesize() * 8);
> assert(pme[0] & PAGEMAP_SOFTDIRTY); /* passes */
> assert(!(pme[1] & PAGEMAP_SOFTDIRTY)); /* fails */
> assert(pme[2] & PAGEMAP_SOFTDIRTY); /* passes */
> return 0;
> }
>
> (Note that all pages in new VMAs are softdirty until cleared).
>
> Tested:
> Used the program given above. I'm going to include this code in
> a selftest in the future.
>
> ...
>
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
>
> ...
>
> @@ -1048,32 +1048,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
>
> if (pmd_trans_unstable(pmd))
> return 0;
> - for (; addr != end; addr += PAGE_SIZE) {
> - int flags2;
> -
> - /* check to see if we've left 'vma' behind
> - * and need a new, higher one */
> - if (vma && (addr >= vma->vm_end)) {
> - vma = find_vma(walk->mm, addr);
> - if (vma && (vma->vm_flags & VM_SOFTDIRTY))
> - flags2 = __PM_SOFT_DIRTY;
> - else
> - flags2 = 0;
> - pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
> +
> + while (1) {
> + unsigned long vm_start = end;
Did you really mean to do that? If so, perhaps a little comment to
explain how it works?
> + unsigned long vm_end = end;
> + unsigned long vm_flags = 0;
> +
> + if (vma) {
> + /*
> + * We can't possibly be in a hugetlb VMA. In general,
> + * for a mm_walk with a pmd_entry and a hugetlb_entry,
> + * the pmd_entry can only be called on addresses in a
> + * hugetlb if the walk starts in a non-hugetlb VMA and
> + * spans a hugepage VMA. Since pagemap_read walks are
> + * PMD-sized and PMD-aligned, this will never be true.
> + */
> + BUG_ON(is_vm_hugetlb_page(vma));
> + vm_start = vma->vm_start;
> + vm_end = min(end, vma->vm_end);
> + vm_flags = vma->vm_flags;
> + }
> +
> + /* Addresses before the VMA. */
> + for (; addr < vm_start; addr += PAGE_SIZE) {
> + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
> +
> + err = add_to_pagemap(addr, &pme, pm);
> + if (err)
> + return err;
>
> ...
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>