[PATCH v3 05/12] powerpc: add pte_free_defer() for pgtables sharing page

Add powerpc-specific pte_free_defer(), to free table page via call_rcu().
pte_free_defer() will be called inside khugepaged's retract_page_tables()
loop, where allocating extra memory cannot be relied upon.  This precedes
the generic version to avoid build breakage from incompatible pgtable_t.

This is awkward because the struct page contains only one rcu_head, but
that page may be shared between PTE_FRAG_NR pagetables, each wanting to
use the rcu_head at the same time.  But powerpc never reuses a fragment
once it has been freed: so mark the page Active in pte_free_defer(),
before calling pte_fragment_free() directly; and there call_rcu() to
pte_free_now() when last fragment is freed and the page is PageActive.

Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Hugh Dickins <hughd@google.com>
---
 arch/powerpc/include/asm/pgalloc.h |  4 ++++
 arch/powerpc/mm/pgtable-frag.c     | 29 ++++++++++++++++++++++++++---
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 3360cad78ace..3a971e2a8c73 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h

@@ -45,6 +45,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	pte_fragment_free((unsigned long *)ptepage, 0);
 }
 
+/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */
+#define pte_free_defer pte_free_defer
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
 /*
  * Functions that deal with pagetables that could be at any level of
  * the table need to be passed an "index_size" so they know how to

diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index 20652daa1d7e..0c6b68130025 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c

@@ -106,6 +106,15 @@ pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel)
 	return __alloc_for_ptecache(mm, kernel);
 }
 
+static void pte_free_now(struct rcu_head *head)
+{
+	struct page *page;
+
+	page = container_of(head, struct page, rcu_head);
+	pgtable_pte_page_dtor(page);
+	__free_page(page);
+}
+
 void pte_fragment_free(unsigned long *table, int kernel)
 {
 	struct page *page = virt_to_page(table);

@@ -115,8 +124,22 @@ void pte_fragment_free(unsigned long *table, int kernel)
 
 	BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
 	if (atomic_dec_and_test(&page->pt_frag_refcount)) {
-		if (!kernel)
-			pgtable_pte_page_dtor(page);
-		__free_page(page);
+		if (kernel)
+			__free_page(page);
+		else if (TestClearPageActive(page))
+			call_rcu(&page->rcu_head, pte_free_now);
+		else
+			pte_free_now(&page->rcu_head);
 	}
 }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+	struct page *page;
+
+	page = virt_to_page(pgtable);
+	SetPageActive(page);
+	pte_fragment_free((unsigned long *)pgtable, 0);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */