shmem: add huge pages support

Here's basic implementation of huge pages support for shmem/tmpfs.

It's all pretty streight-forward:

  - shmem_getpage() allcoates huge page if it can and try to inserd into
    radix tree with shmem_add_to_page_cache();

  - shmem_add_to_page_cache() puts the page onto radix-tree if there's
    space for it;

  - shmem_undo_range() removes huge pages, if it fully within range.
    Partial truncate of huge pages zero out this part of THP.

    This have visible effect on fallocate(FALLOC_FL_PUNCH_HOLE)
    behaviour. As we don't really create hole in this case,
    lseek(SEEK_HOLE) may have inconsistent results depending what
    pages happened to be allocated.

  - no need to change shmem_fault: core-mm will map an compound page as
    huge if VMA is suitable;

Link: http://lkml.kernel.org/r/1466021202-61880-30-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/huge_mm.h

@@ -156,6 +156,8 @@ void put_huge_zero_page(void);
 
 #define transparent_hugepage_enabled(__vma) 0
 
+static inline void prep_transhuge_page(struct page *page) {}
+
 #define transparent_hugepage_flags 0UL
 static inline int
 split_huge_page_to_list(struct page *page, struct list_head *list)

include/linux/shmem_fs.h

@@ -71,6 +71,9 @@ static inline struct page *shmem_read_mapping_page(
 					mapping_gfp_mask(mapping));
 }
 
+extern bool shmem_charge(struct inode *inode, long pages);
+extern void shmem_uncharge(struct inode *inode, long pages);
+
 #ifdef CONFIG_TMPFS
 
 extern int shmem_add_seals(struct file *file, unsigned int seals);

mm/filemap.c

@@ -219,8 +219,13 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 	/* hugetlb pages do not participate in page cache accounting. */
 	if (!PageHuge(page))
 		__mod_zone_page_state(page_zone(page), NR_FILE_PAGES, -nr);
-	if (PageSwapBacked(page))
+	if (PageSwapBacked(page)) {
 		__mod_zone_page_state(page_zone(page), NR_SHMEM, -nr);
+		if (PageTransHuge(page))
+			__dec_zone_page_state(page, NR_SHMEM_THPS);
+	} else {
+		VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page);
+	}
 
 	/*
 	 * At this point page must be either written or cleaned by truncate.

mm/huge_memory.c

@@ -3316,6 +3316,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		if (head[i].index >= end) {
 			__ClearPageDirty(head + i);
 			__delete_from_page_cache(head + i, NULL);
+			if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
+				shmem_uncharge(head->mapping->host, 1);
 			put_page(head + i);
 		}
 	}

mm/memory.c

@@ -1142,7 +1142,7 @@ again:
 				 * unmap shared but keep private pages.
 				 */
 				if (details->check_mapping &&
-				    details->check_mapping != page->mapping)
+				    details->check_mapping != page_rmapping(page))
 					continue;
 			}
 			ptent = ptep_get_and_clear_full(mm, addr, pte,

mm/mempolicy.c

@@ -531,7 +531,7 @@ retry:
 		nid = page_to_nid(page);
 		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 			continue;
-		if (PageTransCompound(page) && PageAnon(page)) {
+		if (PageTransCompound(page)) {
 			get_page(page);
 			pte_unmap_unlock(pte, ptl);
 			lock_page(page);

mm/page-writeback.c

@@ -2563,6 +2563,7 @@ int set_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
+	page = compound_head(page);
 	if (likely(mapping)) {
 		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
 		/*

mm/swap.c

@@ -292,6 +292,7 @@ static bool need_activate_page_drain(int cpu)
 
 void activate_page(struct page *page)
 {
+	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
 		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
 
@@ -316,6 +317,7 @@ void activate_page(struct page *page)
 {
 	struct zone *zone = page_zone(page);
 
+	page = compound_head(page);
 	spin_lock_irq(&zone->lru_lock);
 	__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
 	spin_unlock_irq(&zone->lru_lock);