mm: softdirty: unmapped addresses between VMAs are clean

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.

[n-horiguchi@ah.jp.nec.com: prevent pagemap_pte_range() from overrunning]
Signed-off-by: Peter Feiner <pfeiner@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Jamie Liu <jamieliu@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 1acec26a37584056f08ee4f19ea72d205920e9cf..b7a7dc963a359229ee7607a8d32b9c28221810bf 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1027,7 +1027,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
        spinlock_t *ptl;
        pte_t *pte;
        int err = 0;
-       pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
        /* find the first VMA at or above 'addr' */
        vma = find_vma(walk->mm, addr);
@@ -1041,6 +1040,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
                for (; addr != end; addr += PAGE_SIZE) {
                        unsigned long offset;
+                       pagemap_entry_t pme;
 
                        offset = (addr & ~PAGEMAP_WALK_MASK) >>
                                        PAGE_SHIFT;
@@ -1055,32 +1055,51 @@ 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) {
+               /* End of address space hole, which we mark as non-present. */
+               unsigned long hole_end;
+
+               if (vma)
+                       hole_end = min(end, vma->vm_start);
+               else
+                       hole_end = end;
+
+               for (; addr < hole_end; 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;
                }
 
-               /* check that 'vma' actually covers this address,
-                * and that it isn't a huge page vma */
-               if (vma && (vma->vm_start <= addr) &&
-                   !is_vm_hugetlb_page(vma)) {
+               if (!vma || vma->vm_start >= end)
+                       break;
+               /*
+                * 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));
+
+               /* Addresses in the VMA. */
+               for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+                       pagemap_entry_t pme;
                        pte = pte_offset_map(pmd, addr);
                        pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-                       /* unmap before userspace copy */
                        pte_unmap(pte);
+                       err = add_to_pagemap(addr, &pme, pm);
+                       if (err)
+                               return err;
                }
-               err = add_to_pagemap(addr, &pme, pm);
-               if (err)
-                       return err;
+
+               if (addr == end)
+                       break;
+
+               vma = find_vma(walk->mm, addr);
        }
 
        cond_resched();