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

- Allows reclaim to access counter without looping over processor counts.

- Allows accurate statistics on how many pages are used in a zone by
  the slab. This may become useful to balance slab allocations over
  various zones.

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/mm/pgtable.c

@@ -62,7 +62,7 @@ void show_mem(void)
 	printk(KERN_INFO "%lu pages dirty\n", ps.nr_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", ps.nr_slab);
+	printk(KERN_INFO "%lu pages slab\n", global_page_state(NR_SLAB));
 	printk(KERN_INFO "%lu pages pagetables\n", ps.nr_page_table_pages);
 }
 

drivers/base/node.c

@@ -54,8 +54,6 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 		ps.nr_dirty = 0;
 	if ((long)ps.nr_writeback < 0)
 		ps.nr_writeback = 0;
-	if ((long)ps.nr_slab < 0)
-		ps.nr_slab = 0;
 
 	n = sprintf(buf, "\n"
 		       "Node %d MemTotal:     %8lu kB\n"
@@ -87,7 +85,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
-		       nid, K(ps.nr_slab));
+		       nid, K(node_page_state(nid, NR_SLAB)));
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
 }

fs/proc/proc_misc.c

@@ -194,7 +194,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		K(ps.nr_writeback),
 		K(global_page_state(NR_ANON_PAGES)),
 		K(global_page_state(NR_FILE_MAPPED)),
-		K(ps.nr_slab),
+		K(global_page_state(NR_SLAB)),
 		K(allowed),
 		K(committed),
 		K(ps.nr_page_table_pages),

include/linux/mmzone.h

@@ -51,6 +51,7 @@ enum zone_stat_item {
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
 	NR_FILE_PAGES,
+	NR_SLAB,	/* Pages used by slab allocator */
 	NR_VM_ZONE_STAT_ITEMS };
 
 struct per_cpu_pages {

include/linux/vmstat.h

@@ -26,8 +26,7 @@ struct page_state {
 	unsigned long nr_writeback;	/* Pages under writeback */
 	unsigned long nr_unstable;	/* NFS unstable pages */
 	unsigned long nr_page_table_pages;/* Pages used for pagetables */
-	unsigned long nr_slab;		/* In slab */
+#define GET_PAGE_STATE_LAST nr_page_table_pages
-#define GET_PAGE_STATE_LAST nr_slab
 
 	/*
 	 * The below are zeroed by get_page_state().  Use get_full_page_state()

mm/page_alloc.c

@@ -1318,7 +1318,7 @@ void show_free_areas(void)
 		ps.nr_writeback,
 		ps.nr_unstable,
 		nr_free_pages(),
-		ps.nr_slab,
+		global_page_state(NR_SLAB),
 		global_page_state(NR_FILE_MAPPED),
 		ps.nr_page_table_pages);
 

mm/slab.c

@@ -1507,7 +1507,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		atomic_add(nr_pages, &slab_reclaim_pages);
-	add_page_state(nr_slab, nr_pages);
+	add_zone_page_state(page_zone(page), NR_SLAB, nr_pages);
 	for (i = 0; i < nr_pages; i++)
 		__SetPageSlab(page + i);
 	return page_address(page);
@@ -1522,12 +1522,12 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	struct page *page = virt_to_page(addr);
 	const unsigned long nr_freed = i;
 
+	sub_zone_page_state(page_zone(page), NR_SLAB, nr_freed);
 	while (i--) {
 		BUG_ON(!PageSlab(page));
 		__ClearPageSlab(page);
 		page++;
 	}
-	sub_page_state(nr_slab, nr_freed);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
 	free_pages((unsigned long)addr, cachep->gfporder);

mm/vmscan.c

@@ -1362,7 +1362,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	for_each_zone(zone)
 		lru_pages += zone->nr_active + zone->nr_inactive;
 
-	nr_slab = read_page_state(nr_slab);
+	nr_slab = global_page_state(NR_SLAB);
 	/* If slab caches are huge, it's better to hit them first */
 	while (nr_slab >= lru_pages) {
 		reclaim_state.reclaimed_slab = 0;

mm/vmstat.c

@@ -398,13 +398,13 @@ static char *vmstat_text[] = {
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
+	"nr_slab",
 
 	/* Page state */
 	"nr_dirty",
 	"nr_writeback",
 	"nr_unstable",
 	"nr_page_table_pages",
-	"nr_slab",
 
 	"pgpgin",
 	"pgpgout",