thp: pte alloc trans splitting

pte alloc routines must wait for split_huge_page if the pmd is not present
and not null (i.e.  pmd_trans_splitting).  The additional branches are
optimized away at compile time by pmd_trans_splitting if the config option
is off.  However we must pass the vma down in order to know the anon_vma
lock to wait for.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 13 insertions, 6 deletions

diff --git a/mm/memory.c b/mm/memory.c
index bdf19366b705..567bca80ea53 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -394,9 +394,11 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
         }
 }
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+                pmd_t *pmd, unsigned long address)
 {
         pgtable_t new = pte_alloc_one(mm, address);
+        int wait_split_huge_page;
         if (!new)
                 return -ENOMEM;
 
@@ -416,14 +418,18 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
         smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
         spin_lock(&mm->page_table_lock);
-        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
+        wait_split_huge_page = 0;
+        if (likely(pmd_none(*pmd))) {   /* Has another populated it ? */
                 mm->nr_ptes++;
                 pmd_populate(mm, pmd, new);
                 new = NULL;
-        }
+        } else if (unlikely(pmd_trans_splitting(*pmd)))
+                wait_split_huge_page = 1;
         spin_unlock(&mm->page_table_lock);
         if (new)
                 pte_free(mm, new);
+        if (wait_split_huge_page)
+                wait_split_huge_page(vma->anon_vma, pmd);
         return 0;
 }
 
@@ -436,10 +442,11 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
         smp_wmb(); /* See comment in __pte_alloc */
 
         spin_lock(&init_mm.page_table_lock);
-        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
+        if (likely(pmd_none(*pmd))) {   /* Has another populated it ? */
                 pmd_populate_kernel(&init_mm, pmd, new);
                 new = NULL;
-        }
+        } else
+                VM_BUG_ON(pmd_trans_splitting(*pmd));
         spin_unlock(&init_mm.page_table_lock);
         if (new)
                 pte_free_kernel(&init_mm, new);
@@ -3253,7 +3260,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         pmd = pmd_alloc(mm, pud, address);
         if (!pmd)
                 return VM_FAULT_OOM;
-        pte = pte_alloc_map(mm, pmd, address);
+        pte = pte_alloc_map(mm, vma, pmd, address);
         if (!pte)
                 return VM_FAULT_OOM;