Merge branch 'akpm' (patches from Andrew Morton)

Merge fixes from Andrew Morton:
 "Bunch of fixes.

  And a reversion of mhocko's "Soft limit rework" patch series.  This is
  actually your fault for opening the merge window when I was off racing ;)

  I didn't read the email thread before sending everything off.
  Johannes Weiner raised significant issues:

    http://www.spinics.net/lists/cgroups/msg08813.html

  and we agreed to back it all out"

I clearly need to be more aware of Andrew's racing schedule.

* akpm:
  MAINTAINERS: update mach-bcm related email address
  checkpatch: make extern in .h prototypes quieter
  cciss: fix info leak in cciss_ioctl32_passthru()
  cpqarray: fix info leak in ida_locked_ioctl()
  kernel/reboot.c: re-enable the function of variable reboot_default
  audit: fix endless wait in audit_log_start()
  revert "memcg, vmscan: integrate soft reclaim tighter with zone shrinking code"
  revert "memcg: get rid of soft-limit tree infrastructure"
  revert "vmscan, memcg: do softlimit reclaim also for targeted reclaim"
  revert "memcg: enhance memcg iterator to support predicates"
  revert "memcg: track children in soft limit excess to improve soft limit"
  revert "memcg, vmscan: do not attempt soft limit reclaim if it would not scan anything"
  revert "memcg: track all children over limit in the root"
  revert "memcg, vmscan: do not fall into reclaim-all pass too quickly"
  fs/ocfs2/super.c: use a bigger nodestr in ocfs2_dismount_volume
  watchdog: update watchdog_thresh properly
  watchdog: update watchdog attributes atomically

MAINTAINERS

@@ -1812,7 +1812,8 @@ S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
 BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
-M:	Christian Daudt <csd@broadcom.com>
+M:	Christian Daudt <bcm@fixthebug.org>
+L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://git.github.com/broadcom/bcm11351
 S:	Maintained
 F:	arch/arm/mach-bcm/

drivers/block/cciss.c

@@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
 	int err;
 	u32 cp;
 
+	memset(&arg64, 0, sizeof(arg64));
 	err = 0;
 	err |=
 	    copy_from_user(&arg64.LUN_info, &arg32->LUN_info,

drivers/block/cpqarray.c

@@ -1193,6 +1193,7 @@ out_passthru:
 		ida_pci_info_struct pciinfo;
 
 		if (!arg) return -EINVAL;
+		memset(&pciinfo, 0, sizeof(pciinfo));
 		pciinfo.bus = host->pci_dev->bus->number;
 		pciinfo.dev_fn = host->pci_dev->devfn;
 		pciinfo.board_id = host->board_id;

fs/ocfs2/super.c

@@ -1924,7 +1924,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 {
 	int tmp, hangup_needed = 0;
 	struct ocfs2_super *osb = NULL;
-	char nodestr[8];
+	char nodestr[12];
 
 	trace_ocfs2_dismount_volume(sb);
 

include/linux/memcontrol.h

@@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
-enum mem_cgroup_filter_t {
-	VISIT,		/* visit current node */
-	SKIP,		/* skip the current node and continue traversal */
-	SKIP_TREE,	/* skip the whole subtree and continue traversal */
-};
-
-/*
- * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to
- * iterate through the hierarchy tree. Each tree element is checked by the
- * predicate before it is returned by the iterator. If a filter returns
- * SKIP or SKIP_TREE then the iterator code continues traversal (with the
- * next node down the hierarchy or the next node that doesn't belong under the
- * memcg's subtree).
- */
-typedef enum mem_cgroup_filter_t
-(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root);
-
 #ifdef CONFIG_MEMCG
 /*
  * All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	struct page *oldpage, struct page *newpage, bool migration_ok);
 
-struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
-				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim,
-				   mem_cgroup_iter_filter cond);
-
-static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
-				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim)
-{
-	return mem_cgroup_iter_cond(root, prev, reclaim, NULL);
-}
-
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+				   struct mem_cgroup *,
+				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
 /*
@@ -260,9 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root);
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+						gfp_t gfp_mask,
+						unsigned long *total_scanned);
 
 void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
@@ -376,15 +350,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 		struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 }
-static inline struct mem_cgroup *
-mem_cgroup_iter_cond(struct mem_cgroup *root,
-		struct mem_cgroup *prev,
-		struct mem_cgroup_reclaim_cookie *reclaim,
-		mem_cgroup_iter_filter cond)
-{
-	/* first call must return non-NULL, second return NULL */
-	return (struct mem_cgroup *)(unsigned long)!prev;
-}
 
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
@@ -471,11 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 }
 
 static inline
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root)
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
 {
-	return VISIT;
+	return 0;
 }
 
 static inline void mem_cgroup_split_huge_fixup(struct page *head)

include/linux/smp.h

@@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 
 static inline void kick_all_cpus_sync(void) {  }
 
+static inline void __smp_call_function_single(int cpuid,
+		struct call_single_data *data, int wait)
+{
+	on_each_cpu(data->func, data->info, wait);
+}
+
 #endif /* !SMP */
 
 /*

kernel/audit.c

@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING

kernel/reboot.c

@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
 #endif
 enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
 
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
 int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;

kernel/watchdog.c

@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	int ret;
+
+	/*
+	 * No need to cancel and restart hrtimer if it is currently executing
+	 * because it will reprogram itself with the new period now.
+	 * We should never see it unqueued here because we are running per-cpu
+	 * with interrupts disabled.
+	 */
+	ret = hrtimer_try_to_cancel(hrtimer);
+	if (ret == 1)
+		hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+				HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+	struct call_single_data data = {.func = restart_watchdog_hrtimer};
+	/*
+	 * Make sure that perf event counter will adopt to a new
+	 * sampling period. Updating the sampling period directly would
+	 * be much nicer but we do not have an API for that now so
+	 * let's use a big hammer.
+	 * Hrtimer will adopt the new period on the next tick but this
+	 * might be late already so we have to restart the timer as well.
+	 */
+	watchdog_nmi_disable(cpu);
+	__smp_call_function_single(cpu, &data, 1);
+	watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+	int cpu;
+
+	get_online_cpus();
+	preempt_disable();
+	for_each_online_cpu(cpu)
+		update_timers(cpu);
+	preempt_enable();
+	put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
 {
 	int err = 0;
 
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
 			pr_err("Failed to create watchdog threads, disabled\n");
 		else
 			watchdog_running = 1;
+	} else if (sample_period_changed) {
+		update_timers_all_cpus();
 	}
 
 	return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	static DEFINE_MUTEX(watchdog_proc_mutex);
 
+	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
-		return err;
+		goto out;
 
 	set_sample_period();
 	/*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
 	if (watchdog_user_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
+		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
 	else
 		watchdog_disable_all_cpus();
 
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
 	}
-
+out:
+	mutex_unlock(&watchdog_proc_mutex);
 	return err;
 }
 #endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
 	set_sample_period();
 
 	if (watchdog_user_enabled)
-		watchdog_enable_all_cpus();
+		watchdog_enable_all_cpus(false);
 }

mm/vmscan.c

@@ -139,23 +139,11 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	return !mem_cgroup_disabled() &&
-		mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	return false;
-}
 #endif
 
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -2176,11 +2164,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static int
-__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long nr_reclaimed, nr_scanned;
-	int groups_scanned = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2188,17 +2174,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 			.zone = zone,
 			.priority = sc->priority,
 		};
-		struct mem_cgroup *memcg = NULL;
-		mem_cgroup_iter_filter filter = (soft_reclaim) ?
-			mem_cgroup_soft_reclaim_eligible : NULL;
+		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
-		while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
+		memcg = mem_cgroup_iter(root, NULL, &reclaim);
+		do {
 			struct lruvec *lruvec;
 
-			groups_scanned++;
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
 			shrink_lruvec(lruvec, sc);
@@ -2218,7 +2202,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-		}
+			memcg = mem_cgroup_iter(root, memcg, &reclaim);
+		} while (memcg);
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
@@ -2226,37 +2211,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
-
-	return groups_scanned;
-}
-
-
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
-	unsigned long nr_scanned = sc->nr_scanned;
-	int scanned_groups;
-
-	scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
-	/*
-	 * memcg iterator might race with other reclaimer or start from
-	 * a incomplete tree walk so the tree walk in __shrink_zone
-	 * might have missed groups that are above the soft limit. Try
-	 * another loop to catch up with others. Do it just once to
-	 * prevent from reclaim latencies when other reclaimers always
-	 * preempt this one.
-	 */
-	if (do_soft_reclaim && !scanned_groups)
-		__shrink_zone(zone, sc, do_soft_reclaim);
-
-	/*
-	 * No group is over the soft limit or those that are do not have
-	 * pages in the zone we are reclaiming so we have to reclaim everybody
-	 */
-	if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
-		__shrink_zone(zone, sc, false);
-		return;
-	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2320,6 +2274,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
 	/*
@@ -2359,6 +2315,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 					continue;
 				}
 			}
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
 			/* need some check for avoid more shrink_zone() */
 		}
 
@@ -2952,6 +2920,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.priority = DEF_PRIORITY,
@@ -3066,6 +3036,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
 			sc.nr_scanned = 0;
 
+			nr_soft_scanned = 0;
+			/*
+			 * Call soft limit reclaim before calling shrink_zone.
+			 */
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+							order, sc.gfp_mask,
+							&nr_soft_scanned);
+			sc.nr_reclaimed += nr_soft_reclaimed;
+
 			/*
 			 * There should be no need to raise the scanning
 			 * priority if enough pages are already being scanned

scripts/checkpatch.pl

@@ -3975,8 +3975,8 @@ sub string_find_replace {
 # check for new externs in .h files.
 		if ($realfile =~ /\.h$/ &&
 		    $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) {
-			if (WARN("AVOID_EXTERNS",
-				 "extern prototypes should be avoided in .h files\n" . $herecurr) &&
+			if (CHK("AVOID_EXTERNS",
+				"extern prototypes should be avoided in .h files\n" . $herecurr) &&
 			    $fix) {
 				$fixed[$linenr - 1] =~ s/(.*)\bextern\b\s*(.*)/$1$2/;
 			}