[PATCH] zoned vm counters: conversion of nr_dirty to per zone counter

This makes nr_dirty a per zone counter.  Looping over all processors is
avoided during writeback state determination.

The counter aggregation for nr_dirty had to be undone in the NFS layer since
we summed up the page counts from multiple zones.  Someone more familiar with
NFS should probably review what I have done.

[akpm@osdl.org: bugfix]
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

arch/i386/mm/pgtable.c

@@ -59,7 +59,7 @@ void show_mem(void)
 	printk(KERN_INFO "%d pages swap cached\n", cached);
 
 	get_page_state(&ps);
-	printk(KERN_INFO "%lu pages dirty\n", ps.nr_dirty);
+	printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
 	printk(KERN_INFO "%lu pages writeback\n", ps.nr_writeback);
 	printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
 	printk(KERN_INFO "%lu pages slab\n", global_page_state(NR_SLAB));

drivers/base/node.c

@@ -50,8 +50,6 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 	__get_zone_counts(&active, &inactive, &free, NODE_DATA(nid));
 
 	/* Check for negative values in these approximate counters */
-	if ((long)ps.nr_dirty < 0)
-		ps.nr_dirty = 0;
 	if ((long)ps.nr_writeback < 0)
 		ps.nr_writeback = 0;
 
@@ -81,7 +79,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 		       nid, K(i.freehigh),
 		       nid, K(i.totalram - i.totalhigh),
 		       nid, K(i.freeram - i.freehigh),
-		       nid, K(ps.nr_dirty),
+		       nid, K(node_page_state(nid, NR_FILE_DIRTY)),
 		       nid, K(ps.nr_writeback),
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),

fs/buffer.c

@@ -852,7 +852,7 @@ int __set_page_dirty_buffers(struct page *page)
 		write_lock_irq(&mapping->tree_lock);
 		if (page->mapping) {	/* Race with truncate? */
 			if (mapping_cap_account_dirty(mapping))
-				inc_page_state(nr_dirty);
+				__inc_zone_page_state(page, NR_FILE_DIRTY);
 			radix_tree_tag_set(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);

fs/fs-writeback.c

@@ -464,7 +464,7 @@ void sync_inodes_sb(struct super_block *sb, int wait)
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};
-	unsigned long nr_dirty = read_page_state(nr_dirty);
+	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
 	unsigned long nr_unstable = read_page_state(nr_unstable);
 
 	wbc.nr_to_write = nr_dirty + nr_unstable +

fs/nfs/pagelist.c

@@ -315,6 +315,7 @@ nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst,
 						req->wb_index, NFS_PAGE_TAG_DIRTY);
 				nfs_list_remove_request(req);
 				nfs_list_add_request(req, dst);
+				dec_zone_page_state(req->wb_page, NR_FILE_DIRTY);
 				res++;
 			}
 		}

fs/nfs/write.c

@@ -497,7 +497,7 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	nfs_list_add_request(req, &nfsi->dirty);
 	nfsi->ndirty++;
 	spin_unlock(&nfsi->req_lock);
-	inc_page_state(nr_dirty);
+	inc_zone_page_state(req->wb_page, NR_FILE_DIRTY);
 	mark_inode_dirty(inode);
 }
 
@@ -609,7 +609,6 @@ nfs_scan_dirty(struct inode *inode, struct list_head *dst, unsigned long idx_sta
 	if (nfsi->ndirty != 0) {
 		res = nfs_scan_lock_dirty(nfsi, dst, idx_start, npages);
 		nfsi->ndirty -= res;
-		sub_page_state(nr_dirty,res);
 		if ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty))
 			printk(KERN_ERR "NFS: desynchronized value of nfs_i.ndirty.\n");
 	}

fs/proc/proc_misc.c

@@ -190,7 +190,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		K(i.freeram-i.freehigh),
 		K(i.totalswap),
 		K(i.freeswap),
-		K(ps.nr_dirty),
+		K(global_page_state(NR_FILE_DIRTY)),
 		K(ps.nr_writeback),
 		K(global_page_state(NR_ANON_PAGES)),
 		K(global_page_state(NR_FILE_MAPPED)),

include/linux/mmzone.h

@@ -53,6 +53,7 @@ enum zone_stat_item {
 	NR_FILE_PAGES,
 	NR_SLAB,	/* Pages used by slab allocator */
 	NR_PAGETABLE,	/* used for pagetables */
+	NR_FILE_DIRTY,
 	NR_VM_ZONE_STAT_ITEMS };
 
 struct per_cpu_pages {

include/linux/vmstat.h

@@ -22,7 +22,6 @@
  * commented here.
  */
 struct page_state {
-	unsigned long nr_dirty;		/* Dirty writeable pages */
 	unsigned long nr_writeback;	/* Pages under writeback */
 	unsigned long nr_unstable;	/* NFS unstable pages */
 #define GET_PAGE_STATE_LAST nr_unstable

mm/page-writeback.c

@@ -109,7 +109,7 @@ struct writeback_state
 
 static void get_writeback_state(struct writeback_state *wbs)
 {
-	wbs->nr_dirty = read_page_state(nr_dirty);
+	wbs->nr_dirty = global_page_state(NR_FILE_DIRTY);
 	wbs->nr_unstable = read_page_state(nr_unstable);
 	wbs->nr_mapped = global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES);
@@ -641,7 +641,8 @@ int __set_page_dirty_nobuffers(struct page *page)
 			if (mapping2) { /* Race with truncate? */
 				BUG_ON(mapping2 != mapping);
 				if (mapping_cap_account_dirty(mapping))
-					inc_page_state(nr_dirty);
+					__inc_zone_page_state(page,
+								NR_FILE_DIRTY);
 				radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 			}
@@ -728,9 +729,9 @@ int test_clear_page_dirty(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
-			write_unlock_irqrestore(&mapping->tree_lock, flags);
 			if (mapping_cap_account_dirty(mapping))
-				dec_page_state(nr_dirty);
+				__dec_zone_page_state(page, NR_FILE_DIRTY);
+			write_unlock_irqrestore(&mapping->tree_lock, flags);
 			return 1;
 		}
 		write_unlock_irqrestore(&mapping->tree_lock, flags);
@@ -761,7 +762,7 @@ int clear_page_dirty_for_io(struct page *page)
 	if (mapping) {
 		if (TestClearPageDirty(page)) {
 			if (mapping_cap_account_dirty(mapping))
-				dec_page_state(nr_dirty);
+				dec_zone_page_state(page, NR_FILE_DIRTY);
 			return 1;
 		}
 		return 0;

mm/page_alloc.c

@@ -1314,7 +1314,7 @@ void show_free_areas(void)
 		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
 		active,
 		inactive,
-		ps.nr_dirty,
+		global_page_state(NR_FILE_DIRTY),
 		ps.nr_writeback,
 		ps.nr_unstable,
 		nr_free_pages(),

mm/vmstat.c

@@ -400,9 +400,9 @@ static char *vmstat_text[] = {
 	"nr_file_pages",
 	"nr_slab",
 	"nr_page_table_pages",
+	"nr_dirty",
 
 	/* Page state */
-	"nr_dirty",
 	"nr_writeback",
 	"nr_unstable",