Merge tag 'v3.0.39' into v3.0-rt

This is the 3.0.39 stable release

Conflicts:
	kernel/hrtimer.c
	kernel/time/ntp.c
	kernel/time/timekeeping.c

Required fixup:

diff --cc kernel/hrtimer.c
index 363965f,957869f..0000000
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@@ -1597,17 -1407,24 +1611,24 @@@ void hrtimer_peek_ahead_timers(void
  	local_irq_restore(flags);
  }

 +#else /* CONFIG_HIGH_RES_TIMERS */
 +
 +static inline void __hrtimer_peek_ahead_timers(void) { }
 +
 +#endif	/* !CONFIG_HIGH_RES_TIMERS */
 +
  static void run_hrtimer_softirq(struct softirq_action *h)
  {
+ 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+ 	if (cpu_base->clock_was_set) {
+ 		cpu_base->clock_was_set = 0;
+ 		clock_was_set();
+ 	}
+
 -	hrtimer_peek_ahead_timers();
 +	hrtimer_rt_run_pending();
  }

 -#else /* CONFIG_HIGH_RES_TIMERS */
 -
 -static inline void __hrtimer_peek_ahead_timers(void) { }
 -
 -#endif	/* !CONFIG_HIGH_RES_TIMERS */
 -
  /*
   * Called from timer softirq every jiffy, expire hrtimers:
   *
diff --cc kernel/time/ntp.c
index 419cbaa,61fc450..0000000
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@@ -389,24 -406,7 +406,6 @@@ int second_overflow(unsigned long secs
  		break;
  	}

- 	write_seqcount_end(&xtime_seq);
- 	raw_spin_unlock(&xtime_lock);
--
- 	return res;
- }
-
- /*
-  * this routine handles the overflow of the microsecond field
-  *
-  * The tricky bits of code to handle the accurate clock support
-  * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
-  * They were originally developed for SUN and DEC kernels.
-  * All the kudos should go to Dave for this stuff.
-  */
- void second_overflow(void)
- {
- 	s64 delta;
-
  	/* Bump the maxerror field */
  	time_maxerror += MAXFREQ / NSEC_PER_USEC;
  	if (time_maxerror > NTP_PHASE_LIMIT) {
diff --cc kernel/time/timekeeping.c
index 6ac6438,678ae31..0000000
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@@ -376,14 -395,9 +396,10 @@@ int do_settimeofday(const struct timesp

  	xtime = *tv;

- 	timekeeper.ntp_error = 0;
- 	ntp_clear();
-
- 	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- 				timekeeper.mult);
+ 	timekeeping_update(true);

 -	write_sequnlock_irqrestore(&xtime_lock, flags);
 +	write_seqcount_end(&xtime_seq);
 +	raw_spin_unlock_irqrestore(&xtime_lock, flags);

  	/* signal hrtimers about time change */
  	clock_was_set();
@@@ -415,14 -428,9 +431,10 @@@ int timekeeping_inject_offset(struct ti
  	xtime = timespec_add(xtime, *ts);
  	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);

- 	timekeeper.ntp_error = 0;
- 	ntp_clear();
-
- 	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- 				timekeeper.mult);
+ 	timekeeping_update(true);

 -	write_sequnlock_irqrestore(&xtime_lock, flags);
 +	write_seqcount_end(&xtime_seq);
 +	raw_spin_unlock_irqrestore(&xtime_lock, flags);

  	/* signal hrtimers about time change */
  	clock_was_set();
@@@ -596,10 -603,10 +608,11 @@@ void __init timekeeping_init(void
  	}
  	set_normalized_timespec(&wall_to_monotonic,
  				-boot.tv_sec, -boot.tv_nsec);
+ 	update_rt_offset();
  	total_sleep_time.tv_sec = 0;
  	total_sleep_time.tv_nsec = 0;
 -	write_sequnlock_irqrestore(&xtime_lock, flags);
 +	write_seqcount_end(&xtime_seq);
 +	raw_spin_unlock_irqrestore(&xtime_lock, flags);
  }

  /* time in seconds when suspend began */
@@@ -646,13 -658,9 +665,10 @@@ void timekeeping_inject_sleeptime(struc

  	__timekeeping_inject_sleeptime(delta);

- 	timekeeper.ntp_error = 0;
- 	ntp_clear();
- 	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- 				timekeeper.mult);
+ 	timekeeping_update(true);

 -	write_sequnlock_irqrestore(&xtime_lock, flags);
 +	write_seqcount_end(&xtime_seq);
 +	raw_spin_unlock_irqrestore(&xtime_lock, flags);

  	/* signal hrtimers about time change */
  	clock_was_set();
@@@ -686,8 -693,8 +702,9 @@@ static void timekeeping_resume(void
  	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
  	timekeeper.ntp_error = 0;
  	timekeeping_suspended = 0;
+ 	timekeeping_update(false);
 -	write_sequnlock_irqrestore(&xtime_lock, flags);
 +	write_seqcount_end(&xtime_seq);
 +	raw_spin_unlock_irqrestore(&xtime_lock, flags);

  	touch_softlockup_watchdog();

@@@ -1111,9 -1124,43 +1136,43 @@@ void get_xtime_and_monotonic_and_sleep_
  		*xtim = xtime;
  		*wtom = wall_to_monotonic;
  		*sleep = total_sleep_time;
 -	} while (read_seqretry(&xtime_lock, seq));
 +	} while (read_seqcount_retry(&xtime_seq, seq));
  }

+ #ifdef CONFIG_HIGH_RES_TIMERS
+ /**
+  * ktime_get_update_offsets - hrtimer helper
+  * @real:	pointer to storage for monotonic -> realtime offset
+  * @_boot:	pointer to storage for monotonic -> boottime offset
+  *
+  * Returns current monotonic time and updates the offsets
+  * Called from hrtimer_interupt() or retrigger_next_event()
+  */
+ ktime_t ktime_get_update_offsets(ktime_t *real, ktime_t *boot)
+ {
+ 	ktime_t now;
+ 	unsigned int seq;
+ 	u64 secs, nsecs;
+
+ 	do {
 -		seq = read_seqbegin(&xtime_lock);
++		seq = read_seqcount_begin(&xtime_seq);
+
+ 		secs = xtime.tv_sec;
+ 		nsecs = xtime.tv_nsec;
+ 		nsecs += timekeeping_get_ns();
+ 		/* If arch requires, add in gettimeoffset() */
+ 		nsecs += arch_gettimeoffset();
+
+ 		*real = offs_real;
+ 		*boot = offs_boot;
 -	} while (read_seqretry(&xtime_lock, seq));
++	} while (read_seqcount_retry(&xtime_seq, seq));
+
+ 	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+ 	now = ktime_sub(now, *real);
+ 	return now;
+ }
+ #endif
+
  /**
   * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
   */

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 82 insertions, 36 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3950dab34bf8..2de8eef09fc5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1956,14 +1956,20 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	if (!order || compaction_deferred(preferred_zone))
+	if (!order)
 		return NULL;
 
+	if (compaction_deferred(preferred_zone)) {
+		*deferred_compaction = true;
+		return NULL;
+	}
+
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration);
@@ -1991,7 +1997,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * but not enough to satisfy watermarks.
 		 */
 		count_vm_event(COMPACTFAIL);
-		defer_compaction(preferred_zone);
+
+		/*
+		 * As async compaction considers a subset of pageblocks, only
+		 * defer if the failure was a sync compaction failure.
+		 */
+		if (sync_migration)
+			defer_compaction(preferred_zone);
 
 		cond_resched();
 	}
@@ -2003,8 +2015,9 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2154,6 +2167,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
 	bool sync_migration = false;
+	bool deferred_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2234,12 +2248,22 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 	if (page)
 		goto got_pg;
 	sync_migration = true;
 
+	/*
+	 * If compaction is deferred for high-order allocations, it is because
+	 * sync compaction recently failed. In this is the case and the caller
+	 * has requested the system not be heavily disrupted, fail the
+	 * allocation now instead of entering direct reclaim
+	 */
+	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+		goto nopage;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2302,8 +2326,9 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 		if (page)
 			goto got_pg;
 	}
@@ -2327,8 +2352,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
-	struct page *page;
+	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
+	unsigned int cpuset_mems_cookie;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2347,15 +2373,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
-	if (!preferred_zone) {
-		put_mems_allowed();
-		return NULL;
-	}
+	if (!preferred_zone)
+		goto out;
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2365,9 +2391,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+	/*
+	 * When updating a task's mems_allowed, it is possible to race with
+	 * parallel threads in such a way that an allocation can fail while
+	 * the mask is being updated. If a page allocation is about to fail,
+	 * check if the cpuset changed during allocation and if so, retry.
+	 */
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2591,13 +2627,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
+	unsigned int cpuset_mems_cookie;
 
 	if (!(flags & SHOW_MEM_FILTER_NODES))
 		goto out;
 
-	get_mems_allowed();
-	ret = !node_isset(nid, cpuset_current_mems_allowed);
-	put_mems_allowed();
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		ret = !node_isset(nid, cpuset_current_mems_allowed);
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -3477,25 +3515,33 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 		if (page_to_nid(page) != zone_to_nid(zone))
 			continue;
 
-		/* Blocks with reserved pages will never free, skip them. */
-		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
-		if (pageblock_is_reserved(pfn, block_end_pfn))
-			continue;
-
 		block_migratetype = get_pageblock_migratetype(page);
 
-		/* If this block is reserved, account for it */
-		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
-			reserve--;
-			continue;
-		}
+		/* Only test what is necessary when the reserves are not met */
+		if (reserve > 0) {
+			/*
+			 * Blocks with reserved pages will never free, skip
+			 * them.
+			 */
+			block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+			if (pageblock_is_reserved(pfn, block_end_pfn))
+				continue;
 
-		/* Suitable for reserving if this block is movable */
-		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
-			set_pageblock_migratetype(page, MIGRATE_RESERVE);
-			move_freepages_block(zone, page, MIGRATE_RESERVE);
-			reserve--;
-			continue;
+			/* If this block is reserved, account for it */
+			if (block_migratetype == MIGRATE_RESERVE) {
+				reserve--;
+				continue;
+			}
+
+			/* Suitable for reserving if this block is movable */
+			if (block_migratetype == MIGRATE_MOVABLE) {
+				set_pageblock_migratetype(page,
+							MIGRATE_RESERVE);
+				move_freepages_block(zone, page,
+							MIGRATE_RESERVE);
+				reserve--;
+				continue;
+			}
 		}
 
 		/*