[PATCH v11 3/4] mm, thp: introduce FOLL_SPLIT_PMD

[Song Liu <songliubraving@fb.com>]

This patches introduces a new foll_flag: FOLL_SPLIT_PMD. As the name says
FOLL_SPLIT_PMD splits huge pmd for given mm_struct, the underlining huge
page stays as-is.

FOLL_SPLIT_PMD is useful for cases where we need to use regular pages,
but would switch back to huge page and huge pmd on. One of such example
is uprobe. The following patches use FOLL_SPLIT_PMD in uprobe.

Cc: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 include/linux/mm.h | 1 +
 mm/gup.c           | 8 ++++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f189176dabed..74db879711eb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2614,6 +2614,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_COW	0x4000	/* internal GUP flag */
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
+#define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 
 /*
  * NOTE on FOLL_LONGTERM:
diff --git a/mm/gup.c b/mm/gup.c
index 98f13ab37bac..c20afe800b3f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -399,7 +399,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-	if (flags & FOLL_SPLIT) {
+	if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
 		int ret;
 		page = pmd_page(*pmd);
 		if (is_huge_zero_page(page)) {
@@ -408,7 +408,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			split_huge_pmd(vma, pmd, address);
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
-		} else {
+		} else if (flags & FOLL_SPLIT) {
 			if (unlikely(!try_get_page(page))) {
 				spin_unlock(ptl);
 				return ERR_PTR(-ENOMEM);
@@ -420,6 +420,10 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			put_page(page);
 			if (pmd_none(*pmd))
 				return no_page_table(vma, flags);
+		} else {  /* flags & FOLL_SPLIT_PMD */
+			spin_unlock(ptl);
+			split_huge_pmd(vma, pmd, address);
+			ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
 		}
 
 		return ret ? ERR_PTR(ret) :
-- 
2.17.1