thp: mincore transparent hugepage support

Handle transparent huge page pmd entries natively instead of splitting
them into subpages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 35 insertions, 1 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 43a694ef8904..25125fb6acf7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 extern int zap_huge_pmd(struct mmu_gather *tlb,
                         struct vm_area_struct *vma,
                         pmd_t *pmd);
+extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+                        unsigned long addr, unsigned long end,
+                        unsigned char *vec);
 
 enum transparent_hugepage_flag {
         TRANSPARENT_HUGEPAGE_FLAG,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ae2bf08b1099..37e89a32a0b1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -923,6 +923,31 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
         return ret;
 }
 
+int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+                unsigned long addr, unsigned long end,
+                unsigned char *vec)
+{
+        int ret = 0;
+
+        spin_lock(&vma->vm_mm->page_table_lock);
+        if (likely(pmd_trans_huge(*pmd))) {
+                ret = !pmd_trans_splitting(*pmd);
+                spin_unlock(&vma->vm_mm->page_table_lock);
+                if (unlikely(!ret))
+                        wait_split_huge_page(vma->anon_vma, pmd);
+                else {
+                        /*
+                         * All logical pages in the range are present
+                         * if backed by a huge page.
+                         */
+                        memset(vec, 1, (end - addr) >> PAGE_SHIFT);
+                }
+        } else
+                spin_unlock(&vma->vm_mm->page_table_lock);
+
+        return ret;
+}
+
 pmd_t *page_check_address_pmd(struct page *page,
                               struct mm_struct *mm,
                               unsigned long address,
diff --git a/mm/mincore.c b/mm/mincore.c
index 9959bb41570e..a4e6b9d75c76 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -154,7 +154,13 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
         pmd = pmd_offset(pud, addr);
         do {
                 next = pmd_addr_end(addr, end);
-                split_huge_page_pmd(vma->vm_mm, pmd);
+                if (pmd_trans_huge(*pmd)) {
+                        if (mincore_huge_pmd(vma, pmd, addr, next, vec)) {
+                                vec += (next - addr) >> PAGE_SHIFT;
+                                continue;
+                        }
+                        /* fall through */
+                }
                 if (pmd_none_or_clear_bad(pmd))
                         mincore_unmapped_range(vma, addr, next, vec);
                 else