mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified

commit a7f40cfe3b7ada57af9b62fd28430eeb4a7cfcb7 upstream.

When MPOL_MF_STRICT was specified and an existing page was already on a
node that does not follow the policy, mbind() should return -EIO.  But
commit 6f4576e3687b ("mempolicy: apply page table walker on
queue_pages_range()") broke the rule.

And commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support
thp migration") didn't return the correct value for THP mbind() too.

If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it
reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an
existing page was already on a node that does not follow the policy.
And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or
MPOL_MF_MOVE_ALL was specified.

Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind/mbind02.c

[akpm@linux-foundation.org: tweak code comment]
Link: http://lkml.kernel.org/r/1553020556-38583-1-git-send-email-yang.shi@linux.alibaba.com
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()")
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reported-by: Cyril Hrubis <chrubis@suse.cz>
Suggested-by: Kirill A. Shutemov <kirill@shutemov.name>
Acked-by: Rafael Aquini <aquini@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 593b74b..5cb5147 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -547,11 +547,16 @@ retry:
                        goto retry;
                }
 
-               migrate_page_add(page, qp->pagelist, flags);
+               if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+                       if (!vma_migratable(vma))
+                               break;
+                       migrate_page_add(page, qp->pagelist, flags);
+               } else
+                       break;
        }
        pte_unmap_unlock(pte - 1, ptl);
        cond_resched();
-       return 0;
+       return addr != end ? -EIO : 0;
 }
 
 static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
@@ -623,7 +628,12 @@ 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_migratable(vma))
+       /*
+        * Need check MPOL_MF_STRICT to return -EIO if possible
+        * regardless of vma_migratable
+        */
+       if (!vma_migratable(vma) &&
+           !(flags & MPOL_MF_STRICT))
                return 1;
 
        if (endvma > end)
@@ -650,7 +660,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
        }
 
        /* queue pages from current vma */
-       if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+       if (flags & MPOL_MF_VALID)
                return 0;
        return 1;
 }