[PATCH 07/12] s390: add pte_free_defer(), with use of mmdrop_async()

[Hugh Dickins]

Add s390-specific pte_free_defer(), to call pte_free() 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 version is more complicated than others: because page_table_free()
needs to know which fragment is being freed, and which mm to link it to.

page_table_free()'s fragment handling is clever, but I could too easily
break it: what's done here in pte_free_defer() and pte_free_now() might
be better integrated with page_table_free()'s cleverness, but not by me!

By the time that page_table_free() gets called via RCU, it's conceivable
that mm would already have been freed: so mmgrab() in pte_free_defer()
and mmdrop() in pte_free_now().  No, that is not a good context to call
mmdrop() from, so make mmdrop_async() public and use that.

Signed-off-by: Hugh Dickins <hughd at google.com>
---
 arch/s390/include/asm/pgalloc.h |  4 ++++
 arch/s390/mm/pgalloc.c          | 34 +++++++++++++++++++++++++++++++++
 include/linux/mm_types.h        |  2 +-
 include/linux/sched/mm.h        |  1 +
 kernel/fork.c                   |  2 +-
 5 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 17eb618f1348..89a9d5ef94f8 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -143,6 +143,10 @@ static inline void pmd_populate(struct mm_struct *mm,
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
 
+/* arch use pte_free_defer() implementation in arch/s390/mm/pgalloc.c */
+#define pte_free_defer pte_free_defer
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
 void vmem_map_init(void);
 void *vmem_crst_alloc(unsigned long val);
 pte_t *vmem_pte_alloc(void);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 66ab68db9842..0129de9addfd 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -346,6 +346,40 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	__free_page(page);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void pte_free_now(struct rcu_head *head)
+{
+	struct page *page;
+	unsigned long mm_bit;
+	struct mm_struct *mm;
+	unsigned long *table;
+
+	page = container_of(head, struct page, rcu_head);
+	table = (unsigned long *)page_to_virt(page);
+	mm_bit = (unsigned long)page->pt_mm;
+	/* 4K page has only two 2K fragments, but alignment allows eight */
+	mm = (struct mm_struct *)(mm_bit & ~7);
+	table += PTRS_PER_PTE * (mm_bit & 7);
+	page_table_free(mm, table);
+	mmdrop_async(mm);
+}
+
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+	struct page *page;
+	unsigned long mm_bit;
+
+	mmgrab(mm);
+	page = virt_to_page(pgtable);
+	/* Which 2K page table fragment of a 4K page? */
+	mm_bit = ((unsigned long)pgtable & ~PAGE_MASK) /
+			(PTRS_PER_PTE * sizeof(pte_t));
+	mm_bit += (unsigned long)mm;
+	page->pt_mm = (struct mm_struct *)mm_bit;
+	call_rcu(&page->rcu_head, pte_free_now);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 			 unsigned long vmaddr)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..1667a1bdb8a8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -146,7 +146,7 @@ struct page {
 			pgtable_t pmd_huge_pte; /* protected by page->ptl */
 			unsigned long _pt_pad_2;	/* mapping */
 			union {
-				struct mm_struct *pt_mm; /* x86 pgds only */
+				struct mm_struct *pt_mm; /* x86 pgd, s390 */
 				atomic_t pt_frag_refcount; /* powerpc */
 			};
 #if ALLOC_SPLIT_PTLOCKS
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 8d89c8c4fac1..a9043d1a0d55 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -41,6 +41,7 @@ static inline void smp_mb__after_mmgrab(void)
 	smp_mb__after_atomic();
 }
 
+extern void mmdrop_async(struct mm_struct *mm);
 extern void __mmdrop(struct mm_struct *mm);
 
 static inline void mmdrop(struct mm_struct *mm)
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..fa4486b65c56 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -942,7 +942,7 @@ static void mmdrop_async_fn(struct work_struct *work)
 	__mmdrop(mm);
 }
 
-static void mmdrop_async(struct mm_struct *mm)
+void mmdrop_async(struct mm_struct *mm)
 {
 	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
 		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
-- 
2.35.3