thp: introduce deferred_split_huge_page()

Currently we don't split huge page on partial unmap.  It's not an ideal
situation.  It can lead to memory overhead.

Furtunately, we can detect partial unmap on page_remove_rmap().  But we
cannot call split_huge_page() from there due to locking context.

It's also counterproductive to do directly from munmap() codepath: in
many cases we will hit this from exit(2) and splitting the huge page
just to free it up in small pages is not what we really want.

The patch introduce deferred_split_huge_page() which put the huge page
into queue for splitting.  The splitting itself will happen when we get
memory pressure via shrinker interface.  The page will be dropped from
list on freeing through compound page destructor.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 12 insertions, 0 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 90e11e6a37ab..7aec5ee9cfdf 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -90,11 +90,15 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 
 extern unsigned long transparent_hugepage_flags;
 
+extern void prep_transhuge_page(struct page *page);
+extern void free_transhuge_page(struct page *page);
+
 int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
 	return split_huge_page_to_list(page, NULL);
 }
+void deferred_split_huge_page(struct page *page);
 
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long address);
@@ -170,6 +174,7 @@ static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
+static inline void deferred_split_huge_page(struct page *page) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e4397f640e86..aa8ae8330a75 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -508,6 +508,9 @@ enum compound_dtor_id {
 #ifdef CONFIG_HUGETLB_PAGE
 	HUGETLB_PAGE_DTOR,
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	TRANSHUGE_PAGE_DTOR,
+#endif
 	NR_COMPOUND_DTORS,
 };
 extern compound_page_dtor * const compound_page_dtors[];
@@ -537,6 +540,8 @@ static inline void set_compound_order(struct page *page, unsigned int order)
 	page[1].compound_order = order;
 }
 
+void free_compound_page(struct page *page);
+
 #ifdef CONFIG_MMU
 /*
  * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 809defe0597d..2dd9c313a8c0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -55,6 +55,7 @@ struct page {
 						 */
 		void *s_mem;			/* slab first object */
 		atomic_t compound_mapcount;	/* first tail page */
+		/* page_deferred_list().next	 -- second tail page */
 	};
 
 	/* Second double word */
@@ -62,6 +63,7 @@ struct page {
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
 			void *freelist;		/* sl[aou]b first free object */
+			/* page_deferred_list().prev	-- second tail page */
 		};
 
 		union {