Merge branch 'akpm' (patches from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - Some pidns/fork/exec tweaks
 - OCFS2 updates
 - Most of MM - there remain quite a few memcg parts which depend on
   pending core cgroups changes.  Which might have been already merged -
   I'll check tomorrow...
 - Various misc stuff all over the place
 - A few block bits which I never got around to sending to Jens -
   relatively minor things.
 - MAINTAINERS maintenance
 - A small number of lib/ updates
 - checkpatch updates
 - epoll
 - firmware/dmi-scan
 - Some kprobes work for S390
 - drivers/rtc updates
 - hfsplus feature work
 - vmcore feature work
 - rbtree upgrades
 - AOE updates
 - pktcdvd cleanups
 - PPS
 - memstick
 - w1
 - New "inittmpfs" feature, which does the obvious
 - More IPC work from Davidlohr.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (303 commits)
  lz4: fix compression/decompression signedness mismatch
  ipc: drop ipc_lock_check
  ipc, shm: drop shm_lock_check
  ipc: drop ipc_lock_by_ptr
  ipc, shm: guard against non-existant vma in shmdt(2)
  ipc: document general ipc locking scheme
  ipc,msg: drop msg_unlock
  ipc: rename ids->rw_mutex
  ipc,shm: shorten critical region for shmat
  ipc,shm: cleanup do_shmat pasta
  ipc,shm: shorten critical region for shmctl
  ipc,shm: make shmctl_nolock lockless
  ipc,shm: introduce shmctl_nolock
  ipc: drop ipcctl_pre_down
  ipc,shm: shorten critical region in shmctl_down
  ipc,shm: introduce lockless functions to obtain the ipc object
  initmpfs: use initramfs if rootfstype= or root= specified
  initmpfs: make rootfs use tmpfs when CONFIG_TMPFS enabled
  initmpfs: move rootfs code from fs/ramfs/ to init/
  initmpfs: move bdi setup from init_rootfs to init_ramfs
  ...

1 files changed, 67 insertions, 28 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c2ef4458fa..9bb314577911 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -19,6 +19,9 @@
 #include <linux/math64.h>
 #include <linux/writeback.h>
 #include <linux/compaction.h>
+#include <linux/mm_inline.h>
+
+#include "internal.h"
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -414,12 +417,17 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 EXPORT_SYMBOL(dec_zone_page_state);
 #endif
 
+static inline void fold_diff(int *diff)
+{
+	int i;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		if (diff[i])
+			atomic_long_add(diff[i], &vm_stat[i]);
+}
+
 /*
- * Update the zone counters for one cpu.
- *
- * The cpu specified must be either the current cpu or a processor that
- * is not online. If it is the current cpu then the execution thread must
- * be pinned to the current cpu.
+ * Update the zone counters for the current cpu.
  *
  * Note that refresh_cpu_vm_stats strives to only access
  * node local memory. The per cpu pagesets on remote zones are placed
@@ -432,33 +440,29 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
  */
-void refresh_cpu_vm_stats(int cpu)
+static void refresh_cpu_vm_stats(void)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
 
 	for_each_populated_zone(zone) {
-		struct per_cpu_pageset *p;
+		struct per_cpu_pageset __percpu *p = zone->pageset;
 
-		p = per_cpu_ptr(zone->pageset, cpu);
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
+			int v;
 
-		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-			if (p->vm_stat_diff[i]) {
-				unsigned long flags;
-				int v;
+			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
+			if (v) {
 
-				local_irq_save(flags);
-				v = p->vm_stat_diff[i];
-				p->vm_stat_diff[i] = 0;
-				local_irq_restore(flags);
 				atomic_long_add(v, &zone->vm_stat[i]);
 				global_diff[i] += v;
 #ifdef CONFIG_NUMA
 				/* 3 seconds idle till flush */
-				p->expire = 3;
+				__this_cpu_write(p->expire, 3);
 #endif
 			}
+		}
 		cond_resched();
 #ifdef CONFIG_NUMA
 		/*
@@ -468,29 +472,57 @@ void refresh_cpu_vm_stats(int cpu)
 		 * Check if there are pages remaining in this pageset
 		 * if not then there is nothing to expire.
 		 */
-		if (!p->expire || !p->pcp.count)
+		if (!__this_cpu_read(p->expire) ||
+			       !__this_cpu_read(p->pcp.count))
 			continue;
 
 		/*
 		 * We never drain zones local to this processor.
 		 */
 		if (zone_to_nid(zone) == numa_node_id()) {
-			p->expire = 0;
+			__this_cpu_write(p->expire, 0);
 			continue;
 		}
 
-		p->expire--;
-		if (p->expire)
+
+		if (__this_cpu_dec_return(p->expire))
 			continue;
 
-		if (p->pcp.count)
-			drain_zone_pages(zone, &p->pcp);
+		if (__this_cpu_read(p->pcp.count))
+			drain_zone_pages(zone, __this_cpu_ptr(&p->pcp));
 #endif
 	}
+	fold_diff(global_diff);
+}
 
-	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (global_diff[i])
-			atomic_long_add(global_diff[i], &vm_stat[i]);
+/*
+ * Fold the data for an offline cpu into the global array.
+ * There cannot be any access by the offline cpu and therefore
+ * synchronization is simplified.
+ */
+void cpu_vm_stats_fold(int cpu)
+{
+	struct zone *zone;
+	int i;
+	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p;
+
+		p = per_cpu_ptr(zone->pageset, cpu);
+
+		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+			if (p->vm_stat_diff[i]) {
+				int v;
+
+				v = p->vm_stat_diff[i];
+				p->vm_stat_diff[i] = 0;
+				atomic_long_add(v, &zone->vm_stat[i]);
+				global_diff[i] += v;
+			}
+	}
+
+	fold_diff(global_diff);
 }
 
 /*
@@ -703,6 +735,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 const char * const vmstat_text[] = {
 	/* Zoned VM counters */
 	"nr_free_pages",
+	"nr_alloc_batch",
 	"nr_inactive_anon",
 	"nr_active_anon",
 	"nr_inactive_file",
@@ -817,6 +850,12 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_SMP
+	"nr_tlb_remote_flush",
+	"nr_tlb_remote_flush_received",
+#endif
+	"nr_tlb_local_flush_all",
+	"nr_tlb_local_flush_one",
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
@@ -1052,7 +1091,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n  all_unreclaimable: %u"
 		   "\n  start_pfn:         %lu"
 		   "\n  inactive_ratio:    %u",
-		   zone->all_unreclaimable,
+		   !zone_reclaimable(zone),
 		   zone->zone_start_pfn,
 		   zone->inactive_ratio);
 	seq_putc(m, '\n');
@@ -1177,7 +1216,7 @@ int sysctl_stat_interval __read_mostly = HZ;
 
 static void vmstat_update(struct work_struct *w)
 {
-	refresh_cpu_vm_stats(smp_processor_id());
+	refresh_cpu_vm_stats();
 	schedule_delayed_work(&__get_cpu_var(vmstat_work),
 		round_jiffies_relative(sysctl_stat_interval));
 }