thp: avoid breaking huge pmd invariants in case of vma_adjust failures

An huge pmd can only be mapped if the corresponding 2M virtual range is
fully contained in the vma.  At times the VM calls split_vma twice, if the
first split_vma succeeds and the second fail, the first split_vma remains
in effect and it's not rolled back.  For split_vma or vma_adjust to fail
an allocation failure is needed so it's a very unlikely event (the out of
memory killer would normally fire before any allocation failure is visible
to kernel and userland and if an out of memory condition happens it's
unlikely to happen exactly here).  Nevertheless it's safer to ensure that
no huge pmd can be left around if the vma is adjusted in a way that can't
fit hugepages anymore at the new vm_start/vm_end address.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 80 insertions, 2 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 30c3cec..b6facc3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1075,8 +1075,16 @@ pmd_t *page_check_address_pmd(struct page *page,
 		goto out;
 	if (pmd_page(*pmd) != page)
 		goto out;
-	VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
-		  pmd_trans_splitting(*pmd));
+	/*
+	 * split_vma() may create temporary aliased mappings. There is
+	 * no risk as long as all huge pmd are found and have their
+	 * splitting bit set before __split_huge_page_refcount
+	 * runs. Finding the same huge pmd more than once during the
+	 * same rmap walk is not a problem.
+	 */
+	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
+	    pmd_trans_splitting(*pmd))
+		goto out;
 	if (pmd_trans_huge(*pmd)) {
 		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
 			  !pmd_trans_splitting(*pmd));
@@ -2196,3 +2204,71 @@ void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
 	put_page(page);
 	BUG_ON(pmd_trans_huge(*pmd));
 }
+
+static void split_huge_page_address(struct mm_struct *mm,
+				    unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		return;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return;
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(*pmd))
+		return;
+	/*
+	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
+	 * materialize from under us.
+	 */
+	split_huge_page_pmd(mm, pmd);
+}
+
+void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+			     unsigned long start,
+			     unsigned long end,
+			     long adjust_next)
+{
+	/*
+	 * If the new start address isn't hpage aligned and it could
+	 * previously contain an hugepage: check if we need to split
+	 * an huge pmd.
+	 */
+	if (start & ~HPAGE_PMD_MASK &&
+	    (start & HPAGE_PMD_MASK) >= vma->vm_start &&
+	    (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
+		split_huge_page_address(vma->vm_mm, start);
+
+	/*
+	 * If the new end address isn't hpage aligned and it could
+	 * previously contain an hugepage: check if we need to split
+	 * an huge pmd.
+	 */
+	if (end & ~HPAGE_PMD_MASK &&
+	    (end & HPAGE_PMD_MASK) >= vma->vm_start &&
+	    (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
+		split_huge_page_address(vma->vm_mm, end);
+
+	/*
+	 * If we're also updating the vma->vm_next->vm_start, if the new
+	 * vm_next->vm_start isn't page aligned and it could previously
+	 * contain an hugepage: check if we need to split an huge pmd.
+	 */
+	if (adjust_next > 0) {
+		struct vm_area_struct *next = vma->vm_next;
+		unsigned long nstart = next->vm_start;
+		nstart += adjust_next << PAGE_SHIFT;
+		if (nstart & ~HPAGE_PMD_MASK &&
+		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
+		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
+			split_huge_page_address(next->vm_mm, nstart);
+	}
+}
diff --git a/mm/mmap.c b/mm/mmap.c
index 753f44d..73cc648 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -589,6 +589,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 		}
 	}
 
+	vma_adjust_trans_huge(vma, start, end, adjust_next);
+
 	/*
 	 * When changing only vma->vm_end, we don't really need anon_vma
 	 * lock. This is a fairly rare case by itself, but the anon_vma