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

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 00db594ee467 ("mempolicy: apply page table walker on
queue_pages_range()") broke the rule.

And commit f6d5c81a404f ("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: 00db594ee467 ("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>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index af171ccb56a29713a326b1018e38215700ffcfe5..2219e747df494e5799d5e1af97d6b456907bfa43 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -428,6 +428,13 @@ static inline bool queue_pages_required(struct page *page,
        return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
 }
 
+/*
+ * queue_pages_pmd() has three possible return values:
+ * 1 - pages are placed on the right node or queued successfully.
+ * 0 - THP was split.
+ * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
+ *        page was already on a node that does not follow the policy.
+ */
 static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
                                unsigned long end, struct mm_walk *walk)
 {
@@ -437,7 +444,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
        unsigned long flags;
 
        if (unlikely(is_pmd_migration_entry(*pmd))) {
-               ret = 1;
+               ret = -EIO;
                goto unlock;
        }
        page = pmd_page(*pmd);
@@ -454,8 +461,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
        ret = 1;
        flags = qp->flags;
        /* go to thp migration */
-       if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+       if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+               if (!vma_migratable(walk->vma)) {
+                       ret = -EIO;
+                       goto unlock;
+               }
+
                migrate_page_add(page, qp->pagelist, flags);
+       } else
+               ret = -EIO;
 unlock:
        spin_unlock(ptl);
 out:
@@ -480,8 +494,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
        ptl = pmd_trans_huge_lock(pmd, vma);
        if (ptl) {
                ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
-               if (ret)
+               if (ret > 0)
                        return 0;
+               else if (ret < 0)
+                       return ret;
        }
 
        if (pmd_trans_unstable(pmd))
@@ -502,11 +518,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
                        continue;
                if (!queue_pages_required(page, qp))
                        continue;
-               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,
@@ -576,7 +597,12 @@ 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)
@@ -603,7 +629,7 @@ 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;
 }