mm: move most file-based accounting to the node

There are now a number of accounting oddities such as mapped file pages
being accounted for on the node while the total number of file pages are
accounted on the zone.  This can be coped with to some extent but it's
confusing so this patch moves the relevant file-based accounted.  Due to
throttling logic in the page allocator for reliable OOM detection, it is
still necessary to track dirty and writeback pages on a per-zone basis.

[mgorman@techsingularity.net: fix NR_ZONE_WRITE_PENDING accounting]
  Link: http://lkml.kernel.org/r/1468404004-5085-5-git-send-email-mgorman@techsingularity.net
Link: http://lkml.kernel.org/r/1467970510-21195-20-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/s390/appldata/appldata_mem.c

@@ -102,7 +102,7 @@ static void appldata_get_mem_data(void *data)
 	mem_data->totalhigh = P2K(val.totalhigh);
 	mem_data->freehigh  = P2K(val.freehigh);
 	mem_data->bufferram = P2K(val.bufferram);
-	mem_data->cached    = P2K(global_page_state(NR_FILE_PAGES)
+	mem_data->cached    = P2K(global_node_page_state(NR_FILE_PAGES)
 				- val.bufferram);
 
 	si_swapinfo(&val);

arch/tile/mm/pgtable.c

@@ -49,16 +49,16 @@ void show_mem(unsigned int filter)
 		global_node_page_state(NR_ACTIVE_FILE)),
 	       (global_node_page_state(NR_INACTIVE_ANON) +
 		global_node_page_state(NR_INACTIVE_FILE)),
-	       global_page_state(NR_FILE_DIRTY),
-	       global_page_state(NR_WRITEBACK),
-	       global_page_state(NR_UNSTABLE_NFS),
+	       global_node_page_state(NR_FILE_DIRTY),
+	       global_node_page_state(NR_WRITEBACK),
+	       global_node_page_state(NR_UNSTABLE_NFS),
 	       global_page_state(NR_FREE_PAGES),
 	       (global_page_state(NR_SLAB_RECLAIMABLE) +
 		global_page_state(NR_SLAB_UNRECLAIMABLE)),
 	       global_node_page_state(NR_FILE_MAPPED),
 	       global_page_state(NR_PAGETABLE),
 	       global_page_state(NR_BOUNCE),
-	       global_page_state(NR_FILE_PAGES),
+	       global_node_page_state(NR_FILE_PAGES),
 	       get_nr_swap_pages());
 
 	for_each_zone(zone) {

drivers/base/node.c

@@ -118,28 +118,28 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d ShmemPmdMapped: %8lu kB\n"
 #endif
 			,
-		       nid, K(sum_zone_node_page_state(nid, NR_FILE_DIRTY)),
-		       nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK)),
-		       nid, K(sum_zone_node_page_state(nid, NR_FILE_PAGES)),
+		       nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
+		       nid, K(node_page_state(pgdat, NR_WRITEBACK)),
+		       nid, K(node_page_state(pgdat, NR_FILE_PAGES)),
 		       nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
 		       nid, K(i.sharedram),
 		       nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
 		       nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_UNSTABLE_NFS)),
+		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_WRITEBACK_TEMP)),
+		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
 		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
 				sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_ANON_THPS) *
+		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
-		       nid, K(sum_zone_node_page_state(nid, NR_SHMEM_THPS) *
+		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
-		       nid, K(sum_zone_node_page_state(nid, NR_SHMEM_PMDMAPPED) *
+		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
 				       HPAGE_PMD_NR));
 #else
 		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));

drivers/staging/android/lowmemorykiller.c

@@ -91,8 +91,8 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 	short selected_oom_score_adj;
 	int array_size = ARRAY_SIZE(lowmem_adj);
 	int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
-	int other_file = global_page_state(NR_FILE_PAGES) -
-						global_page_state(NR_SHMEM) -
+	int other_file = global_node_page_state(NR_FILE_PAGES) -
+						global_node_page_state(NR_SHMEM) -
 						total_swapcache_pages();
 
 	if (lowmem_adj_size < array_size)

drivers/staging/lustre/lustre/osc/osc_cache.c

@@ -1864,7 +1864,8 @@ void osc_dec_unstable_pages(struct ptlrpc_request *req)
 	LASSERT(page_count >= 0);
 
 	for (i = 0; i < page_count; i++)
-		dec_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+		dec_node_page_state(desc->bd_iov[i].kiov_page,
+							NR_UNSTABLE_NFS);
 
 	atomic_sub(page_count, &cli->cl_cache->ccc_unstable_nr);
 	LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
@@ -1898,7 +1899,8 @@ void osc_inc_unstable_pages(struct ptlrpc_request *req)
 	LASSERT(page_count >= 0);
 
 	for (i = 0; i < page_count; i++)
-		inc_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+		inc_node_page_state(desc->bd_iov[i].kiov_page,
+							NR_UNSTABLE_NFS);
 
 	LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
 	atomic_add(page_count, &cli->cl_cache->ccc_unstable_nr);

fs/fs-writeback.c

@@ -1807,8 +1807,8 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
  */
 static unsigned long get_nr_dirty_pages(void)
 {
-	return global_page_state(NR_FILE_DIRTY) +
-		global_page_state(NR_UNSTABLE_NFS) +
+	return global_node_page_state(NR_FILE_DIRTY) +
+		global_node_page_state(NR_UNSTABLE_NFS) +
 		get_nr_dirty_inodes();
 }
 

fs/fuse/file.c

@@ -1452,7 +1452,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 	list_del(&req->writepages_entry);
 	for (i = 0; i < req->num_pages; i++) {
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-		dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
+		dec_node_page_state(req->pages[i], NR_WRITEBACK_TEMP);
 		wb_writeout_inc(&bdi->wb);
 	}
 	wake_up(&fi->page_waitq);
@@ -1642,7 +1642,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->inode = inode;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
-	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
 	list_add(&req->writepages_entry, &fi->writepages);
@@ -1756,7 +1756,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 		spin_unlock(&fc->lock);
 
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-		dec_zone_page_state(page, NR_WRITEBACK_TEMP);
+		dec_node_page_state(page, NR_WRITEBACK_TEMP);
 		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
@@ -1855,7 +1855,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
-	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
 	if (is_writeback && fuse_writepage_in_flight(req, page)) {

fs/nfs/internal.h

@@ -623,7 +623,7 @@ void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
 	if (!cinfo->dreq) {
 		struct inode *inode = page_file_mapping(page)->host;
 
-		inc_zone_page_state(page, NR_UNSTABLE_NFS);
+		inc_node_page_state(page, NR_UNSTABLE_NFS);
 		inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
 		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	}

fs/nfs/write.c

@@ -898,7 +898,7 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
 static void
 nfs_clear_page_commit(struct page *page)
 {
-	dec_zone_page_state(page, NR_UNSTABLE_NFS);
+	dec_node_page_state(page, NR_UNSTABLE_NFS);
 	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
 		    WB_RECLAIMABLE);
 }

fs/proc/meminfo.c

@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	si_swapinfo(&i);
 	committed = percpu_counter_read_positive(&vm_committed_as);
 
-	cached = global_page_state(NR_FILE_PAGES) -
+	cached = global_node_page_state(NR_FILE_PAGES) -
 			total_swapcache_pages() - i.bufferram;
 	if (cached < 0)
 		cached = 0;
@@ -138,8 +138,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 		K(i.totalswap),
 		K(i.freeswap),
-		K(global_page_state(NR_FILE_DIRTY)),
-		K(global_page_state(NR_WRITEBACK)),
+		K(global_node_page_state(NR_FILE_DIRTY)),
+		K(global_node_page_state(NR_WRITEBACK)),
 		K(global_node_page_state(NR_ANON_MAPPED)),
 		K(global_node_page_state(NR_FILE_MAPPED)),
 		K(i.sharedram),
@@ -152,9 +152,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_QUICKLIST
 		K(quicklist_total_size()),
 #endif
-		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_node_page_state(NR_UNSTABLE_NFS)),
 		K(global_page_state(NR_BOUNCE)),
-		K(global_page_state(NR_WRITEBACK_TEMP)),
+		K(global_node_page_state(NR_WRITEBACK_TEMP)),
 		K(vm_commit_limit()),
 		K(committed),
 		(unsigned long)VMALLOC_TOTAL >> 10,
@@ -164,9 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		, K(global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
-		, K(global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
-		, K(global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
 #endif
 #ifdef CONFIG_CMA
 		, K(totalcma_pages)

include/linux/mmzone.h

@@ -114,21 +114,16 @@ enum zone_stat_item {
 	NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
 	NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
 	NR_ZONE_LRU_FILE,
+	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_FILE_PAGES,
-	NR_FILE_DIRTY,
-	NR_WRITEBACK,
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK,
 	/* Second 128 byte cacheline */
-	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
 	NR_VMSCAN_WRITE,
 	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
-	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
-	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
 #if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -142,9 +137,6 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
-	NR_ANON_THPS,
-	NR_SHMEM_THPS,
-	NR_SHMEM_PMDMAPPED,
 	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
 
@@ -164,6 +156,15 @@ enum node_stat_item {
 	NR_ANON_MAPPED,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
+	NR_FILE_PAGES,
+	NR_FILE_DIRTY,
+	NR_WRITEBACK,
+	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
+	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
+	NR_SHMEM_THPS,
+	NR_SHMEM_PMDMAPPED,
+	NR_ANON_THPS,
+	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_VM_NODE_STAT_ITEMS
 };
 

include/trace/events/writeback.h

@@ -412,9 +412,9 @@ TRACE_EVENT(global_dirty_state,
 	),
 
 	TP_fast_assign(
-		__entry->nr_dirty	= global_page_state(NR_FILE_DIRTY);
-		__entry->nr_writeback	= global_page_state(NR_WRITEBACK);
-		__entry->nr_unstable	= global_page_state(NR_UNSTABLE_NFS);
+		__entry->nr_dirty	= global_node_page_state(NR_FILE_DIRTY);
+		__entry->nr_writeback	= global_node_page_state(NR_WRITEBACK);
+		__entry->nr_unstable	= global_node_page_state(NR_UNSTABLE_NFS);
 		__entry->nr_dirtied	= global_page_state(NR_DIRTIED);
 		__entry->nr_written	= global_page_state(NR_WRITTEN);
 		__entry->background_thresh = background_thresh;

mm/filemap.c

@@ -218,11 +218,11 @@ 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);
+		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
 	if (PageSwapBacked(page)) {
-		__mod_zone_page_state(page_zone(page), NR_SHMEM, -nr);
+		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
 		if (PageTransHuge(page))
-			__dec_zone_page_state(page, NR_SHMEM_THPS);
+			__dec_node_page_state(page, NR_SHMEM_THPS);
 	} else {
 		VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page);
 	}
@@ -568,9 +568,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		 * hugetlb pages do not participate in page cache accounting.
 		 */
 		if (!PageHuge(new))
-			__inc_zone_page_state(new, NR_FILE_PAGES);
+			__inc_node_page_state(new, NR_FILE_PAGES);
 		if (PageSwapBacked(new))
-			__inc_zone_page_state(new, NR_SHMEM);
+			__inc_node_page_state(new, NR_SHMEM);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		mem_cgroup_migrate(old, new);
 		radix_tree_preload_end();
@@ -677,7 +677,7 @@ static int __add_to_page_cache_locked(struct page *page,
 
 	/* hugetlb pages do not participate in page cache accounting. */
 	if (!huge)
-		__inc_zone_page_state(page, NR_FILE_PAGES);
+		__inc_node_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	if (!huge)
 		mem_cgroup_commit_charge(page, memcg, false, false);

mm/huge_memory.c

@@ -1586,7 +1586,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
 		/* Last compound_mapcount is gone. */
-		__dec_zone_page_state(page, NR_ANON_THPS);
+		__dec_node_page_state(page, NR_ANON_THPS);
 		if (TestClearPageDoubleMap(page)) {
 			/* No need in mapcount reference anymore */
 			for (i = 0; i < HPAGE_PMD_NR; i++)
@@ -2061,7 +2061,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			list_del(page_deferred_list(head));
 		}
 		if (mapping)
-			__dec_zone_page_state(page, NR_SHMEM_THPS);
+			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
 		__split_huge_page(page, list, flags);
 		ret = 0;

mm/khugepaged.c

@@ -1483,10 +1483,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		}
 
 		local_irq_save(flags);
-		__inc_zone_page_state(new_page, NR_SHMEM_THPS);
+		__inc_node_page_state(new_page, NR_SHMEM_THPS);
 		if (nr_none) {
-			__mod_zone_page_state(zone, NR_FILE_PAGES, nr_none);
-			__mod_zone_page_state(zone, NR_SHMEM, nr_none);
+			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
 		}
 		local_irq_restore(flags);
 

mm/migrate.c

@@ -505,15 +505,17 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * are mapped to swap space.
 	 */
 	if (newzone != oldzone) {
-		__dec_zone_state(oldzone, NR_FILE_PAGES);
-		__inc_zone_state(newzone, NR_FILE_PAGES);
+		__dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES);
+		__inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES);
 		if (PageSwapBacked(page) && !PageSwapCache(page)) {
-			__dec_zone_state(oldzone, NR_SHMEM);
-			__inc_zone_state(newzone, NR_SHMEM);
+			__dec_node_state(oldzone->zone_pgdat, NR_SHMEM);
+			__inc_node_state(newzone->zone_pgdat, NR_SHMEM);
 		}
 		if (dirty && mapping_cap_account_dirty(mapping)) {
-			__dec_zone_state(oldzone, NR_FILE_DIRTY);
-			__inc_zone_state(newzone, NR_FILE_DIRTY);
+			__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
+			__dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
+			__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
+			__inc_zone_state(newzone, NR_ZONE_WRITE_PENDING);
 		}
 	}
 	local_irq_enable();