Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into sh-fixes-for-linus

6 files changed, 42 insertions, 51 deletions

diff --git a/mm/highmem.c b/mm/highmem.c
index 693394daa2ed..5ef672c07f75 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -326,7 +326,7 @@ static struct page_address_slot {
 	spinlock_t lock;			/* Protect this bucket's list */
 } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
 
-static struct page_address_slot *page_slot(struct page *page)
+static struct page_address_slot *page_slot(const struct page *page)
 {
 	return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
 }
@@ -337,7 +337,7 @@ static struct page_address_slot *page_slot(struct page *page)
  *
  * Returns the page's virtual address.
  */
-void *page_address(struct page *page)
+void *page_address(const struct page *page)
 {
 	unsigned long flags;
 	void *ret;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ec4e7ca4cd..ebd1e86bef1c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1841,29 +1841,23 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
  */
 static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 {
-	int lock_count = -1;
 	struct mem_cgroup *iter, *failed = NULL;
 	bool cond = true;
 
 	for_each_mem_cgroup_tree_cond(iter, mem, cond) {
-		bool locked = iter->oom_lock;
-
-		iter->oom_lock = true;
-		if (lock_count == -1)
-			lock_count = iter->oom_lock;
-		else if (lock_count != locked) {
+		if (iter->oom_lock) {
 			/*
 			 * this subtree of our hierarchy is already locked
 			 * so we cannot give a lock.
 			 */
-			lock_count = 0;
 			failed = iter;
 			cond = false;
-		}
+		} else
+			iter->oom_lock = true;
 	}
 
 	if (!failed)
-		goto done;
+		return true;
 
 	/*
 	 * OK, we failed to lock the whole subtree so we have to clean up
@@ -1877,8 +1871,7 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 		}
 		iter->oom_lock = false;
 	}
-done:
-	return lock_count;
+	return false;
 }
 
 /*
@@ -2091,6 +2084,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -2168,13 +2162,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
-	/*
-	 * Get a hint for avoiding draining charges on the current cpu,
-	 * which must be exhausted by our charging.  It is not required that
-	 * this be a precise check, so we use raw_smp_processor_id() instead of
-	 * getcpu()/putcpu().
-	 */
-	curcpu = raw_smp_processor_id();
+	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *mem;
@@ -2191,14 +2179,14 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
+	put_cpu();
 
 	if (!sync)
 		goto out;
 
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (mem_cgroup_same_or_subtree(root_mem, stock->cached) &&
-				test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
 			flush_work(&stock->work);
 	}
 out:
@@ -2213,14 +2201,22 @@ out:
  */
 static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
+	 */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	drain_all_stock(root_mem, false);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /* This is a synchronous drain interface. */
 static void drain_all_stock_sync(struct mem_cgroup *root_mem)
 {
 	/* called when force_empty is called */
+	mutex_lock(&percpu_charge_mutex);
 	drain_all_stock(root_mem, true);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d1960744f881..0e309cd1b5b9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -754,21 +754,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * 200ms is typically more than enough to curb heavy dirtiers;
 		 * (b) the pause time limit makes the dirtiers more responsive.
 		 */
-		if (nr_dirty < dirty_thresh +
-			       dirty_thresh / DIRTY_MAXPAUSE_AREA &&
+		if (nr_dirty < dirty_thresh &&
+		    bdi_dirty < (task_bdi_thresh + bdi_thresh) / 2 &&
 		    time_after(jiffies, start_time + MAX_PAUSE))
 			break;
-		/*
-		 * pass-good area. When some bdi gets blocked (eg. NFS server
-		 * not responding), or write bandwidth dropped dramatically due
-		 * to concurrent reads, or dirty threshold suddenly dropped and
-		 * the dirty pages cannot be brought down anytime soon (eg. on
-		 * slow USB stick), at least let go of the good bdi's.
-		 */
-		if (nr_dirty < dirty_thresh +
-			       dirty_thresh / DIRTY_PASSGOOD_AREA &&
-		    bdi_dirty < bdi_thresh)
-			break;
 
 		/*
 		 * Increase the delay for each loop, up to our previous
diff --git a/mm/slub.c b/mm/slub.c
index eb5a8f93338a..9f662d70eb47 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -701,7 +701,7 @@ static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes)
 		return check_bytes8(start, value, bytes);
 
 	value64 = value | value << 8 | value << 16 | value << 24;
-	value64 = value64 | value64 << 32;
+	value64 = (value64 & 0xffffffff) | value64 << 32;
 	prefix = 8 - ((unsigned long)start) % 8;
 
 	if (prefix) {
@@ -1854,7 +1854,7 @@ redo:
 
 	new.frozen = 0;
 
-	if (!new.inuse && n->nr_partial < s->min_partial)
+	if (!new.inuse && n->nr_partial > s->min_partial)
 		m = M_FREE;
 	else if (new.freelist) {
 		m = M_PARTIAL;
@@ -2387,11 +2387,13 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 slab_empty:
 	if (prior) {
 		/*
-		 * Slab still on the partial list.
+		 * Slab on the partial list.
 		 */
 		remove_partial(n, page);
 		stat(s, FREE_REMOVE_PARTIAL);
-	}
+	} else
+		/* Slab must be on the full list */
+		remove_full(s, page);
 
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 464621d18eb2..7ef0903058ee 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -725,9 +725,10 @@ static void free_unmap_vmap_area_addr(unsigned long addr)
 #define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
 #define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
 #define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
-#define VMAP_BBMAP_BITS		VMAP_MIN(VMAP_BBMAP_BITS_MAX,		\
-					VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
-						VMALLOC_PAGES / NR_CPUS / 16))
+#define VMAP_BBMAP_BITS		\
+		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
+		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
+			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
 
 #define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7ef69124fa3e..b7719ec10dc5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2283,7 +2283,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.mem_cgroup = mem,
 		.memcg_record = rec,
 	};
-	unsigned long start, end;
+	ktime_t start, end;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2292,7 +2292,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						      sc.may_writepage,
 						      sc.gfp_mask);
 
-	start = sched_clock();
+	start = ktime_get();
 	/*
 	 * NOTE: Although we can get the priority field, using it
 	 * here is not a good idea, since it limits the pages we can scan.
@@ -2301,10 +2301,10 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 	 * the priority and make it zero.
 	 */
 	shrink_zone(0, zone, &sc);
-	end = sched_clock();
+	end = ktime_get();
 
 	if (rec)
-		rec->elapsed += end - start;
+		rec->elapsed += ktime_to_ns(ktime_sub(end, start));
 	*scanned = sc.nr_scanned;
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
@@ -2319,7 +2319,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
-	unsigned long start, end;
+	ktime_t start, end;
 	int nid;
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
@@ -2337,7 +2337,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.gfp_mask = sc.gfp_mask,
 	};
 
-	start = sched_clock();
+	start = ktime_get();
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
 	 * take care of from where we get pages. So the node where we start the
@@ -2352,9 +2352,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					    sc.gfp_mask);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
-	end = sched_clock();
+	end = ktime_get();
 	if (rec)
-		rec->elapsed += end - start;
+		rec->elapsed += ktime_to_ns(ktime_sub(end, start));
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -2529,6 +2529,9 @@ loop_again:
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
+			} else {
+				/* If balanced, clear the congested flag */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
 		if (i < 0)