userfaultfd: hugetlbfs: userfaultfd_huge_must_wait for hugepmd ranges

Add routine userfaultfd_huge_must_wait which has the same functionality
as the existing userfaultfd_must_wait routine.  Only difference is that
new routine must handle page table structure for hugepmd vmas.

Link: http://lkml.kernel.org/r/20161216144821.5183-24-aarcange@redhat.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 5139d05..11b5e65 100644 (file)
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -202,6 +202,49 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
        return msg;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * Same functionality as userfaultfd_must_wait below with modifications for
+ * hugepmd ranges.
+ */
+static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+                                        unsigned long address,
+                                        unsigned long flags,
+                                        unsigned long reason)
+{
+       struct mm_struct *mm = ctx->mm;
+       pte_t *pte;
+       bool ret = true;
+
+       VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+
+       pte = huge_pte_offset(mm, address);
+       if (!pte)
+               goto out;
+
+       ret = false;
+
+       /*
+        * Lockless access: we're in a wait_event so it's ok if it
+        * changes under us.
+        */
+       if (huge_pte_none(*pte))
+               ret = true;
+       if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+               ret = true;
+out:
+       return ret;
+}
+#else
+static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+                                        unsigned long address,
+                                        unsigned long flags,
+                                        unsigned long reason)
+{
+       return false;   /* should never get here */
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
 /*
  * Verify the pagetables are still not ok after having reigstered into
  * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
@@ -378,8 +421,12 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
        set_current_state(blocking_state);
        spin_unlock(&ctx->fault_pending_wqh.lock);
 
-       must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
-                                         reason);
+       if (!is_vm_hugetlb_page(vmf->vma))
+               must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
+                                                 reason);
+       else
+               must_wait = userfaultfd_huge_must_wait(ctx, vmf->address,
+                                                      vmf->flags, reason);
        up_read(&mm->mmap_sem);
 
        if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&