Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into for-3.18

This is to receive 0a30288da1ae ("blk-mq, percpu_ref: implement a
kludge for SCSI blk-mq stall during probe") which implements
__percpu_ref_kill_expedited() to work around SCSI blk-mq stall.  The
commit reverted and patches to implement proper fix will be added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

11 files changed, 104 insertions, 43 deletions

diff --git a/mm/dmapool.c b/mm/dmapool.c
index 306baa5..ba8019b 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -176,7 +176,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 	if (list_empty(&dev->dma_pools) &&
 	    device_create_file(dev, &dev_attr_pools)) {
 		kfree(retval);
-		return NULL;
+		retval = NULL;
 	} else
 		list_add(&retval->pools, &dev->dma_pools);
 	mutex_unlock(&pools_lock);
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 9eebfad..a67c26e 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -217,7 +217,7 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 
 	if (hugetlb_cgroup_disabled())
 		return;
-	VM_BUG_ON(!spin_is_locked(&hugetlb_lock));
+	lockdep_assert_held(&hugetlb_lock);
 	h_cg = hugetlb_cgroup_from_page(page);
 	if (unlikely(!h_cg))
 		return;
diff --git a/mm/memblock.c b/mm/memblock.c
index 6d2f219..6ecb0d9 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -192,8 +192,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
 					phys_addr_t end, int nid)
 {
-	int ret;
-	phys_addr_t kernel_end;
+	phys_addr_t kernel_end, ret;
 
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
@@ -817,6 +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;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ec4dcf1..085dc6d 100644
--- a/mm/memcontrol.c
+++ b/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);
diff --git a/mm/memory.c b/mm/memory.c
index ab3537b..d17f1bc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,8 @@ __setup("norandmaps", disable_randmaps);
 unsigned long zero_pfn __read_mostly;
 unsigned long highest_memmap_pfn __read_mostly;
 
+EXPORT_SYMBOL(zero_pfn);
+
 /*
  * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
  */
@@ -751,7 +753,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 	unsigned long pfn = pte_pfn(pte);
 
 	if (HAVE_PTE_SPECIAL) {
-		if (likely(!pte_special(pte) || pte_numa(pte)))
+		if (likely(!pte_special(pte)))
 			goto check_pfn;
 		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 			return NULL;
@@ -777,15 +779,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
+	if (is_zero_pfn(pfn))
+		return NULL;
 check_pfn:
 	if (unlikely(pfn > highest_memmap_pfn)) {
 		print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
 	}
 
-	if (is_zero_pfn(pfn))
-		return NULL;
-
 	/*
 	 * NOTE! We still have PageReserved() pages in the page tables.
 	 * eg. VDSO mappings can cause them to exist.
diff --git a/mm/mmap.c b/mm/mmap.c
index d7ec93e..650a1f1 100644
--- a/mm/mmap.c
+++ b/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);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 7ed5860..7c7ab32 100644
--- a/mm/nobootmem.c
+++ b/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);
 
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index a8b9199..dfb79e0 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -195,7 +195,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 	pmd_t entry = *pmdp;
 	if (pmd_numa(entry))
 		entry = pmd_mknonnuma(entry);
-	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/mm/zbud.c b/mm/zbud.c
index a05790b..f26e7fc 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -195,6 +195,7 @@ static struct zpool_driver zbud_zpool_driver = {
 	.total_size =	zbud_zpool_total_size,
 };
 
+MODULE_ALIAS("zpool-zbud");
 #endif /* CONFIG_ZPOOL */
 
 /*****************
diff --git a/mm/zpool.c b/mm/zpool.c
index e40612a..739cdf0 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -150,7 +150,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
 	driver = zpool_get_driver(type);
 
 	if (!driver) {
-		request_module(type);
+		request_module("zpool-%s", type);
 		driver = zpool_get_driver(type);
 	}
 
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 4e2fc83..94f38fa 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -315,6 +315,7 @@ static struct zpool_driver zs_zpool_driver = {
 	.total_size =	zs_zpool_total_size,
 };
 
+MODULE_ALIAS("zpool-zsmalloc");
 #endif /* CONFIG_ZPOOL */
 
 /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */