Merge branch 'for-linus' into for-3.18/core

Moving patches from for-linus to 3.18 instead, pull in this changes
that will go to Linus today.

mm/memblock.c

@@ -816,6 +816,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid,
 		if (nid != NUMA_NO_NODE && nid != m_nid)
 			continue;
 
+		/* skip hotpluggable memory regions if needed */
+		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
+			continue;
+
 		if (!type_b) {
 			if (out_start)
 				*out_start = m_start;

mm/memcontrol.c

@@ -2534,6 +2534,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long long size;
 	int ret = 0;
 
+	if (mem_cgroup_is_root(memcg))
+		goto done;
 retry:
 	if (consume_stock(memcg, nr_pages))
 		goto done;
@@ -2611,9 +2613,7 @@ nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
 bypass:
-	memcg = root_mem_cgroup;
-	ret = -EINTR;
-	goto retry;
+	return -EINTR;
 
 done_restock:
 	if (batch > nr_pages)
@@ -2626,6 +2626,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long bytes = nr_pages * PAGE_SIZE;
 
+	if (mem_cgroup_is_root(memcg))
+		return;
+
 	res_counter_uncharge(&memcg->res, bytes);
 	if (do_swap_account)
 		res_counter_uncharge(&memcg->memsw, bytes);
@@ -2640,6 +2643,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 {
 	unsigned long bytes = nr_pages * PAGE_SIZE;
 
+	if (mem_cgroup_is_root(memcg))
+		return;
+
 	res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
 	if (do_swap_account)
 		res_counter_uncharge_until(&memcg->memsw,
@@ -4093,6 +4099,46 @@ out:
 	return retval;
 }
 
+static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
+					       enum mem_cgroup_stat_index idx)
+{
+	struct mem_cgroup *iter;
+	long val = 0;
+
+	/* Per-cpu values can be negative, use a signed accumulator */
+	for_each_mem_cgroup_tree(iter, memcg)
+		val += mem_cgroup_read_stat(iter, idx);
+
+	if (val < 0) /* race ? */
+		val = 0;
+	return val;
+}
+
+static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
+{
+	u64 val;
+
+	if (!mem_cgroup_is_root(memcg)) {
+		if (!swap)
+			return res_counter_read_u64(&memcg->res, RES_USAGE);
+		else
+			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+	}
+
+	/*
+	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
+	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
+	 */
+	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
+	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
+
+	if (swap)
+		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
+
+	return val << PAGE_SHIFT;
+}
+
+
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
@@ -4102,8 +4148,12 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 
 	switch (type) {
 	case _MEM:
+		if (name == RES_USAGE)
+			return mem_cgroup_usage(memcg, false);
 		return res_counter_read_u64(&memcg->res, name);
 	case _MEMSWAP:
+		if (name == RES_USAGE)
+			return mem_cgroup_usage(memcg, true);
 		return res_counter_read_u64(&memcg->memsw, name);
 	case _KMEM:
 		return res_counter_read_u64(&memcg->kmem, name);
@@ -4572,10 +4622,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	if (!t)
 		goto unlock;
 
-	if (!swap)
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
-	else
-		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+	usage = mem_cgroup_usage(memcg, swap);
 
 	/*
 	 * current_threshold points to threshold just below or equal to usage.
@@ -4673,10 +4720,10 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 
 	if (type == _MEM) {
 		thresholds = &memcg->thresholds;
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		usage = mem_cgroup_usage(memcg, false);
 	} else if (type == _MEMSWAP) {
 		thresholds = &memcg->memsw_thresholds;
-		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		usage = mem_cgroup_usage(memcg, true);
 	} else
 		BUG();
 
@@ -4762,10 +4809,10 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 
 	if (type == _MEM) {
 		thresholds = &memcg->thresholds;
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		usage = mem_cgroup_usage(memcg, false);
 	} else if (type == _MEMSWAP) {
 		thresholds = &memcg->memsw_thresholds;
-		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		usage = mem_cgroup_usage(memcg, true);
 	} else
 		BUG();
 
@@ -5525,9 +5572,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		 * core guarantees its existence.
 		 */
 	} else {
-		res_counter_init(&memcg->res, &root_mem_cgroup->res);
-		res_counter_init(&memcg->memsw, &root_mem_cgroup->memsw);
-		res_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+		res_counter_init(&memcg->res, NULL);
+		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -5969,8 +6016,9 @@ static void __mem_cgroup_clear_mc(void)
 	/* we must fixup refcnts and charges */
 	if (mc.moved_swap) {
 		/* uncharge swap account from the old cgroup */
-		res_counter_uncharge(&mc.from->memsw,
-				     PAGE_SIZE * mc.moved_swap);
+		if (!mem_cgroup_is_root(mc.from))
+			res_counter_uncharge(&mc.from->memsw,
+					     PAGE_SIZE * mc.moved_swap);
 
 		for (i = 0; i < mc.moved_swap; i++)
 			css_put(&mc.from->css);
@@ -5979,8 +6027,9 @@ static void __mem_cgroup_clear_mc(void)
 		 * we charged both to->res and to->memsw, so we should
 		 * uncharge to->res.
 		 */
-		res_counter_uncharge(&mc.to->res,
-				     PAGE_SIZE * mc.moved_swap);
+		if (!mem_cgroup_is_root(mc.to))
+			res_counter_uncharge(&mc.to->res,
+					     PAGE_SIZE * mc.moved_swap);
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
@@ -6345,7 +6394,8 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 	rcu_read_lock();
 	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
-		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		if (!mem_cgroup_is_root(memcg))
+			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
@@ -6509,12 +6559,15 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 {
 	unsigned long flags;
 
-	if (nr_mem)
-		res_counter_uncharge(&memcg->res, nr_mem * PAGE_SIZE);
-	if (nr_memsw)
-		res_counter_uncharge(&memcg->memsw, nr_memsw * PAGE_SIZE);
-
-	memcg_oom_recover(memcg);
+	if (!mem_cgroup_is_root(memcg)) {
+		if (nr_mem)
+			res_counter_uncharge(&memcg->res,
+					     nr_mem * PAGE_SIZE);
+		if (nr_memsw)
+			res_counter_uncharge(&memcg->memsw,
+					     nr_memsw * PAGE_SIZE);
+		memcg_oom_recover(memcg);
+	}
 
 	local_irq_save(flags);
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon);

mm/mmap.c

@@ -369,20 +369,20 @@ static int browse_rb(struct rb_root *root)
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
 		if (vma->vm_start < prev) {
-			pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev);
+			pr_emerg("vm_start %lx prev %lx\n", vma->vm_start, prev);
 			bug = 1;
 		}
 		if (vma->vm_start < pend) {
-			pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend);
+			pr_emerg("vm_start %lx pend %lx\n", vma->vm_start, pend);
 			bug = 1;
 		}
 		if (vma->vm_start > vma->vm_end) {
-			pr_info("vm_end %lx < vm_start %lx\n",
+			pr_emerg("vm_end %lx < vm_start %lx\n",
 				vma->vm_end, vma->vm_start);
 			bug = 1;
 		}
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
-			pr_info("free gap %lx, correct %lx\n",
+			pr_emerg("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
@@ -396,7 +396,7 @@ static int browse_rb(struct rb_root *root)
 	for (nd = pn; nd; nd = rb_prev(nd))
 		j++;
 	if (i != j) {
-		pr_info("backwards %d, forwards %d\n", j, i);
+		pr_emerg("backwards %d, forwards %d\n", j, i);
 		bug = 1;
 	}
 	return bug ? -1 : i;
@@ -431,17 +431,17 @@ static void validate_mm(struct mm_struct *mm)
 		i++;
 	}
 	if (i != mm->map_count) {
-		pr_info("map_count %d vm_next %d\n", mm->map_count, i);
+		pr_emerg("map_count %d vm_next %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	if (highest_address != mm->highest_vm_end) {
-		pr_info("mm->highest_vm_end %lx, found %lx\n",
+		pr_emerg("mm->highest_vm_end %lx, found %lx\n",
 		       mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
 	i = browse_rb(&mm->mm_rb);
 	if (i != mm->map_count) {
-		pr_info("map_count %d rb %d\n", mm->map_count, i);
+		pr_emerg("map_count %d rb %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	BUG_ON(bug);

mm/nobootmem.c

@@ -119,6 +119,8 @@ static unsigned long __init free_low_memory_core_early(void)
 	phys_addr_t start, end;
 	u64 i;
 
+	memblock_clear_hotplug(0, -1);
+
 	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL)
 		count += __free_memory_core(start, end);
 

mm/percpu-vm.c

@@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			    int page_start, int page_end)
 {
 	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-	unsigned int cpu;
+	unsigned int cpu, tcpu;
 	int i;
 
 	for_each_possible_cpu(cpu) {
@@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
 
 			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-			if (!*pagep) {
-				pcpu_free_pages(chunk, pages, populated,
-						page_start, page_end);
-				return -ENOMEM;
-			}
+			if (!*pagep)
+				goto err;
 		}
 	}
 	return 0;
+
+err:
+	while (--i >= page_start)
+		__free_page(pages[pcpu_page_idx(cpu, i)]);
+
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		for (i = page_start; i < page_end; i++)
+			__free_page(pages[pcpu_page_idx(tcpu, i)]);
+	}
+	return -ENOMEM;
 }
 
 /**
@@ -263,6 +272,7 @@ err:
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
 				   page_end - page_start);
 	}
+	pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
 	return err;
 }
 

mm/percpu.c

@@ -1932,6 +1932,8 @@ void __init setup_per_cpu_areas(void)
 
 	if (pcpu_setup_first_chunk(ai, fc) < 0)
 		panic("Failed to initialize percpu areas.");
+
+	pcpu_free_alloc_info(ai);
 }
 
 #endif	/* CONFIG_SMP */