mempolicy: do not try to queue pages from !vma_migratable()

Maybe I miss some point, but I don't see a reason why we try to queue
pages from non migratable VMAs.

This testcase steps on VM_BUG_ON_PAGE() in isolate_lru_page():

    #include <fcntl.h>
    #include <unistd.h>
    #include <stdio.h>
    #include <sys/mman.h>
    #include <numaif.h>

    #define SIZE 0x2000

    int foo;

    int main()
    {
        int fd;
        char *p;
        unsigned long mask = 2;

        fd = open("/dev/sg0", O_RDWR);
        p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
        /* Faultin pages */
        foo = p[0] + p[0x1000];
        mbind(p, SIZE, MPOL_BIND, &mask, 4, MPOL_MF_MOVE | MPOL_MF_STRICT);
        return 0;
    }

The only case when we can queue pages from such VMA is MPOL_MF_STRICT
plus MPOL_MF_MOVE or MPOL_MF_MOVE_ALL for VMA which has pages on LRU,
but gfp mask is not sutable for migaration (see mapping_gfp_mask() check
in vma_migratable()).  That's looks like a bug to me.

Let's filter out non-migratable vma at start of queue_pages_test_walk()
and go to queue_pages_pte_range() only if MPOL_MF_MOVE or
MPOL_MF_MOVE_ALL flag is set.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 27d135408a22057a5b166e7eb2bf2e080bbd33f2..4c4187c0e1deeb25bdbf5eb383132d27feb9be90 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -548,8 +548,7 @@ retry:
                        goto retry;
                }
 
-               if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-                       migrate_page_add(page, qp->pagelist, flags);
+               migrate_page_add(page, qp->pagelist, flags);
        }
        pte_unmap_unlock(pte - 1, ptl);
        cond_resched();
@@ -625,7 +624,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
        unsigned long endvma = vma->vm_end;
        unsigned long flags = qp->flags;
 
-       if (vma->vm_flags & VM_PFNMAP)
+       if (!vma_migratable(vma))
                return 1;
 
        if (endvma > end)
@@ -644,16 +643,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 
        if (flags & MPOL_MF_LAZY) {
                /* Similar to task_numa_work, skip inaccessible VMAs */
-               if (vma_migratable(vma) &&
-                       vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+               if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
                        change_prot_numa(vma, start, endvma);
                return 1;
        }
 
-       if ((flags & MPOL_MF_STRICT) ||
-           ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-            vma_migratable(vma)))
-               /* queue pages from current vma */
+       /* queue pages from current vma */
+       if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
                return 0;
        return 1;
 }