[PATCH] zoned vm counters: create vmstat.c/.h from page_alloc.c/.h

NOTE: ZVC are *not* the lightweight event counters.  ZVCs are reliable whereas
event counters do not need to be.

Zone based VM statistics are necessary to be able to determine what the state
of memory in one zone is.  In a NUMA system this can be helpful for local
reclaim and other memory optimizations that may be able to shift VM load in
order to get more balanced memory use.

It is also useful to know how the computing load affects the memory
allocations on various zones.  This patchset allows the retrieval of that data
from userspace.

The patchset introduces a framework for counters that is a cross between the
existing page_stats --which are simply global counters split per cpu-- and the
approach of deferred incremental updates implemented for nr_pagecache.

Small per cpu 8 bit counters are added to struct zone.  If the counter exceeds
certain thresholds then the counters are accumulated in an array of
atomic_long in the zone and in a global array that sums up all zone values.
The small 8 bit counters are next to the per cpu page pointers and so they
will be in high in the cpu cache when pages are allocated and freed.

Access to VM counter information for a zone and for the whole machine is then
possible by simply indexing an array (Thanks to Nick Piggin for pointing out
that approach).  The access to the total number of pages of various types does
no longer require the summing up of all per cpu counters.

Benefits of this patchset right now:

- Ability for UP and SMP configuration to determine how memory
  is balanced between the DMA, NORMAL and HIGHMEM zones.

- loops over all processors are avoided in writeback and
  reclaim paths. We can avoid caching the writeback information
  because the needed information is directly accessible.

- Special handling for nr_pagecache removed.

- zone_reclaim_interval vanishes since VM stats can now determine
  when it is worth to do local reclaim.

- Fast inline per node page state determination.

- Accurate counters in /sys/devices/system/node/node*/meminfo. Current
  counters are counting simply which processor allocated a page somewhere
  and guestimate based on that. So the counters were not useful to show
  the actual distribution of page use on a specific zone.

- The swap_prefetch patch requires per node statistics in order to
  figure out when processors of a node can prefetch. This patch provides
  some of the needed numbers.

- Detailed VM counters available in more /proc and /sys status files.

References to earlier discussions:
V1 http://marc.theaimsgroup.com/?l=linux-kernel&m=113511649910826&w=2
V2 http://marc.theaimsgroup.com/?l=linux-kernel&m=114980851924230&w=2
V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115014697910351&w=2
V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767318740&w=2

Performance tests with AIM7 did not show any regressions.  Seems to be a tad
faster even.  Tested on ia64/NUMA.  Builds fine on i386, SMP / UP.  Includes
fixes for s390/arm/uml arch code.

This patch:

Move counter code from page_alloc.c/page-flags.h to vmstat.c/h.

Create vmstat.c/vmstat.h by separating the counter code and the proc
functions.

Move the vm_stat_text array before zoneinfo_show.

[akpm@osdl.org: s390 build fix]
[akpm@osdl.org: HOTPLUG_CPU build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 0 insertions, 407 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 084a2de7e52..87dc1297fe3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1231,141 +1231,6 @@ static void show_node(struct zone *zone)
 #define show_node(zone)	do { } while (0)
 #endif
 
-/*
- * Accumulate the page_state information across all CPUs.
- * The result is unavoidably approximate - it can change
- * during and after execution of this function.
- */
-static DEFINE_PER_CPU(struct page_state, page_states) = {0};
-
-atomic_t nr_pagecache = ATOMIC_INIT(0);
-EXPORT_SYMBOL(nr_pagecache);
-#ifdef CONFIG_SMP
-DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
-#endif
-
-static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
-{
-	unsigned cpu;
-
-	memset(ret, 0, nr * sizeof(unsigned long));
-	cpus_and(*cpumask, *cpumask, cpu_online_map);
-
-	for_each_cpu_mask(cpu, *cpumask) {
-		unsigned long *in;
-		unsigned long *out;
-		unsigned off;
-		unsigned next_cpu;
-
-		in = (unsigned long *)&per_cpu(page_states, cpu);
-
-		next_cpu = next_cpu(cpu, *cpumask);
-		if (likely(next_cpu < NR_CPUS))
-			prefetch(&per_cpu(page_states, next_cpu));
-
-		out = (unsigned long *)ret;
-		for (off = 0; off < nr; off++)
-			*out++ += *in++;
-	}
-}
-
-void get_page_state_node(struct page_state *ret, int node)
-{
-	int nr;
-	cpumask_t mask = node_to_cpumask(node);
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr+1, &mask);
-}
-
-void get_page_state(struct page_state *ret)
-{
-	int nr;
-	cpumask_t mask = CPU_MASK_ALL;
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr + 1, &mask);
-}
-
-void get_full_page_state(struct page_state *ret)
-{
-	cpumask_t mask = CPU_MASK_ALL;
-
-	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
-}
-
-unsigned long read_page_state_offset(unsigned long offset)
-{
-	unsigned long ret = 0;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		unsigned long in;
-
-		in = (unsigned long)&per_cpu(page_states, cpu) + offset;
-		ret += *((unsigned long *)in);
-	}
-	return ret;
-}
-
-void __mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-	void *ptr;
-
-	ptr = &__get_cpu_var(page_states);
-	*(unsigned long *)(ptr + offset) += delta;
-}
-EXPORT_SYMBOL(__mod_page_state_offset);
-
-void mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-	unsigned long flags;
-	void *ptr;
-
-	local_irq_save(flags);
-	ptr = &__get_cpu_var(page_states);
-	*(unsigned long *)(ptr + offset) += delta;
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_page_state_offset);
-
-void __get_zone_counts(unsigned long *active, unsigned long *inactive,
-			unsigned long *free, struct pglist_data *pgdat)
-{
-	struct zone *zones = pgdat->node_zones;
-	int i;
-
-	*active = 0;
-	*inactive = 0;
-	*free = 0;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		*active += zones[i].nr_active;
-		*inactive += zones[i].nr_inactive;
-		*free += zones[i].free_pages;
-	}
-}
-
-void get_zone_counts(unsigned long *active,
-		unsigned long *inactive, unsigned long *free)
-{
-	struct pglist_data *pgdat;
-
-	*active = 0;
-	*inactive = 0;
-	*free = 0;
-	for_each_online_pgdat(pgdat) {
-		unsigned long l, m, n;
-		__get_zone_counts(&l, &m, &n, pgdat);
-		*active += l;
-		*inactive += m;
-		*free += n;
-	}
-}
-
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
@@ -2253,278 +2118,6 @@ void __init free_area_init(unsigned long *zones_size)
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
 
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-
-static void *frag_start(struct seq_file *m, loff_t *pos)
-{
-	pg_data_t *pgdat;
-	loff_t node = *pos;
-	for (pgdat = first_online_pgdat();
-	     pgdat && node;
-	     pgdat = next_online_pgdat(pgdat))
-		--node;
-
-	return pgdat;
-}
-
-static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-	pg_data_t *pgdat = (pg_data_t *)arg;
-
-	(*pos)++;
-	return next_online_pgdat(pgdat);
-}
-
-static void frag_stop(struct seq_file *m, void *arg)
-{
-}
-
-/* 
- * This walks the free areas for each zone.
- */
-static int frag_show(struct seq_file *m, void *arg)
-{
-	pg_data_t *pgdat = (pg_data_t *)arg;
-	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
-	unsigned long flags;
-	int order;
-
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
-		if (!populated_zone(zone))
-			continue;
-
-		spin_lock_irqsave(&zone->lock, flags);
-		seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
-		for (order = 0; order < MAX_ORDER; ++order)
-			seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
-		spin_unlock_irqrestore(&zone->lock, flags);
-		seq_putc(m, '\n');
-	}
-	return 0;
-}
-
-struct seq_operations fragmentation_op = {
-	.start	= frag_start,
-	.next	= frag_next,
-	.stop	= frag_stop,
-	.show	= frag_show,
-};
-
-/*
- * Output information about zones in @pgdat.
- */
-static int zoneinfo_show(struct seq_file *m, void *arg)
-{
-	pg_data_t *pgdat = arg;
-	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
-	unsigned long flags;
-
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
-		int i;
-
-		if (!populated_zone(zone))
-			continue;
-
-		spin_lock_irqsave(&zone->lock, flags);
-		seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
-		seq_printf(m,
-			   "\n  pages free     %lu"
-			   "\n        min      %lu"
-			   "\n        low      %lu"
-			   "\n        high     %lu"
-			   "\n        active   %lu"
-			   "\n        inactive %lu"
-			   "\n        scanned  %lu (a: %lu i: %lu)"
-			   "\n        spanned  %lu"
-			   "\n        present  %lu",
-			   zone->free_pages,
-			   zone->pages_min,
-			   zone->pages_low,
-			   zone->pages_high,
-			   zone->nr_active,
-			   zone->nr_inactive,
-			   zone->pages_scanned,
-			   zone->nr_scan_active, zone->nr_scan_inactive,
-			   zone->spanned_pages,
-			   zone->present_pages);
-		seq_printf(m,
-			   "\n        protection: (%lu",
-			   zone->lowmem_reserve[0]);
-		for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
-			seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
-		seq_printf(m,
-			   ")"
-			   "\n  pagesets");
-		for_each_online_cpu(i) {
-			struct per_cpu_pageset *pageset;
-			int j;
-
-			pageset = zone_pcp(zone, i);
-			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-				if (pageset->pcp[j].count)
-					break;
-			}
-			if (j == ARRAY_SIZE(pageset->pcp))
-				continue;
-			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-				seq_printf(m,
-					   "\n    cpu: %i pcp: %i"
-					   "\n              count: %i"
-					   "\n              high:  %i"
-					   "\n              batch: %i",
-					   i, j,
-					   pageset->pcp[j].count,
-					   pageset->pcp[j].high,
-					   pageset->pcp[j].batch);
-			}
-#ifdef CONFIG_NUMA
-			seq_printf(m,
-				   "\n            numa_hit:       %lu"
-				   "\n            numa_miss:      %lu"
-				   "\n            numa_foreign:   %lu"
-				   "\n            interleave_hit: %lu"
-				   "\n            local_node:     %lu"
-				   "\n            other_node:     %lu",
-				   pageset->numa_hit,
-				   pageset->numa_miss,
-				   pageset->numa_foreign,
-				   pageset->interleave_hit,
-				   pageset->local_node,
-				   pageset->other_node);
-#endif
-		}
-		seq_printf(m,
-			   "\n  all_unreclaimable: %u"
-			   "\n  prev_priority:     %i"
-			   "\n  temp_priority:     %i"
-			   "\n  start_pfn:         %lu",
-			   zone->all_unreclaimable,
-			   zone->prev_priority,
-			   zone->temp_priority,
-			   zone->zone_start_pfn);
-		spin_unlock_irqrestore(&zone->lock, flags);
-		seq_putc(m, '\n');
-	}
-	return 0;
-}
-
-struct seq_operations zoneinfo_op = {
-	.start	= frag_start, /* iterate over all zones. The same as in
-			       * fragmentation. */
-	.next	= frag_next,
-	.stop	= frag_stop,
-	.show	= zoneinfo_show,
-};
-
-static char *vmstat_text[] = {
-	"nr_dirty",
-	"nr_writeback",
-	"nr_unstable",
-	"nr_page_table_pages",
-	"nr_mapped",
-	"nr_slab",
-
-	"pgpgin",
-	"pgpgout",
-	"pswpin",
-	"pswpout",
-
-	"pgalloc_high",
-	"pgalloc_normal",
-	"pgalloc_dma32",
-	"pgalloc_dma",
-
-	"pgfree",
-	"pgactivate",
-	"pgdeactivate",
-
-	"pgfault",
-	"pgmajfault",
-
-	"pgrefill_high",
-	"pgrefill_normal",
-	"pgrefill_dma32",
-	"pgrefill_dma",
-
-	"pgsteal_high",
-	"pgsteal_normal",
-	"pgsteal_dma32",
-	"pgsteal_dma",
-
-	"pgscan_kswapd_high",
-	"pgscan_kswapd_normal",
-	"pgscan_kswapd_dma32",
-	"pgscan_kswapd_dma",
-
-	"pgscan_direct_high",
-	"pgscan_direct_normal",
-	"pgscan_direct_dma32",
-	"pgscan_direct_dma",
-
-	"pginodesteal",
-	"slabs_scanned",
-	"kswapd_steal",
-	"kswapd_inodesteal",
-	"pageoutrun",
-	"allocstall",
-
-	"pgrotated",
-	"nr_bounce",
-};
-
-static void *vmstat_start(struct seq_file *m, loff_t *pos)
-{
-	struct page_state *ps;
-
-	if (*pos >= ARRAY_SIZE(vmstat_text))
-		return NULL;
-
-	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
-	m->private = ps;
-	if (!ps)
-		return ERR_PTR(-ENOMEM);
-	get_full_page_state(ps);
-	ps->pgpgin /= 2;		/* sectors -> kbytes */
-	ps->pgpgout /= 2;
-	return (unsigned long *)ps + *pos;
-}
-
-static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-	(*pos)++;
-	if (*pos >= ARRAY_SIZE(vmstat_text))
-		return NULL;
-	return (unsigned long *)m->private + *pos;
-}
-
-static int vmstat_show(struct seq_file *m, void *arg)
-{
-	unsigned long *l = arg;
-	unsigned long off = l - (unsigned long *)m->private;
-
-	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
-	return 0;
-}
-
-static void vmstat_stop(struct seq_file *m, void *arg)
-{
-	kfree(m->private);
-	m->private = NULL;
-}
-
-struct seq_operations vmstat_op = {
-	.start	= vmstat_start,
-	.next	= vmstat_next,
-	.stop	= vmstat_stop,
-	.show	= vmstat_show,
-};
-
-#endif /* CONFIG_PROC_FS */
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int page_alloc_cpu_notify(struct notifier_block *self,
 				 unsigned long action, void *hcpu)