Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

One conflict in the BPF samples Makefile, some fixes in 'net' whilst
we were converting over to Makefile.target rules in 'net-next'.

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 61 insertions, 25 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 0a1b4b484ac5..f05d27b7183d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	anon_vma_lock_write(vma->anon_vma);
 
-	pte = pte_offset_map(pmd, address);
-	pte_ptl = pte_lockptr(mm, pmd);
-
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
 				address, address + HPAGE_PMD_SIZE);
 	mmu_notifier_invalidate_range_start(&range);
+
+	pte = pte_offset_map(pmd, address);
+	pte_ptl = pte_lockptr(mm, pmd);
+
 	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
 	 * After this gup_fast can't run anymore. This also removes
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 363106578876..37592dd7ae32 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageHead(page) && PageSlab(page))
+	if (PageSlab(page) && !PageTail(page))
 		memcg = memcg_from_slab_page(page);
 	else
 		memcg = READ_ONCE(page->mem_cgroup);
@@ -2535,6 +2535,15 @@ retry:
 	}
 
 	/*
+	 * Memcg doesn't have a dedicated reserve for atomic
+	 * allocations. But like the global atomic pool, we need to
+	 * put the burden of reclaim on regular allocation requests
+	 * and let these go through as privileged allocations.
+	 */
+	if (gfp_mask & __GFP_ATOMIC)
+		goto force;
+
+	/*
 	 * Unlike in global OOM situations, memcg is not in a physical
 	 * memory shortage.  Allow dying and OOM-killed tasks to
 	 * bypass the last charges so that they can exit quickly and
@@ -5014,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	/*
-	 * Flush percpu vmstats and vmevents to guarantee the value correctness
-	 * on parent's and all ancestor levels.
-	 */
-	memcg_flush_percpu_vmstats(memcg, false);
-	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
@@ -5030,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	memcg_wb_domain_exit(memcg);
+	/*
+	 * Flush percpu vmstats and vmevents to guarantee the value correctness
+	 * on parent's and all ancestor levels.
+	 */
+	memcg_flush_percpu_vmstats(memcg, false);
+	memcg_flush_percpu_vmevents(memcg);
 	__mem_cgroup_free(memcg);
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index df570e5c71cc..07e5c67f48a8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -447,6 +447,14 @@ static void update_pgdat_span(struct pglist_data *pgdat)
 					     zone->spanned_pages;
 
 		/* No need to lock the zones, they can't change. */
+		if (!zone->spanned_pages)
+			continue;
+		if (!node_end_pfn) {
+			node_start_pfn = zone->zone_start_pfn;
+			node_end_pfn = zone_end_pfn;
+			continue;
+		}
+
 		if (zone_end_pfn > node_end_pfn)
 			node_end_pfn = zone_end_pfn;
 		if (zone->zone_start_pfn < node_start_pfn)
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 7fde88695f35..9a889e456168 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 					mn->ops->invalidate_range_start, _ret,
 					!mmu_notifier_range_blockable(range) ? "non-" : "");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
-					ret != -EAGAIN);
+					_ret != -EAGAIN);
 				ret = _ret;
 			}
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ecc3dbad606b..f391c0c4ed1d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void)
 	wait_for_completion(&pgdat_init_all_done_comp);
 
 	/*
+	 * The number of managed pages has changed due to the initialisation
+	 * so the pcpu batch and high limits needs to be updated or the limits
+	 * will be artificially small.
+	 */
+	for_each_populated_zone(zone)
+		zone_pcp_update(zone);
+
+	/*
 	 * We initialized the rest of the deferred pages.  Permanently disable
 	 * on-demand struct page initialization.
 	 */
@@ -3720,10 +3728,6 @@ try_this_zone:
 static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
-	static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
-
-	if (!__ratelimit(&show_mem_rs))
-		return;
 
 	/*
 	 * This documents exceptions given to allocations in certain
@@ -3744,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
+	static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
 
 	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
 		return;
@@ -8514,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages)
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.
@@ -8528,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone)
 				per_cpu_ptr(zone->pageset, cpu));
 	mutex_unlock(&pcp_batch_high_lock);
 }
-#endif
 
 void zone_pcp_reset(struct zone *zone)
 {
diff --git a/mm/slab.h b/mm/slab.h
index 68e455f2b698..b2b01694dc43 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
  * Expects a pointer to a slab page. Please note, that PageSlab() check
  * isn't sufficient, as it returns true also for tail compound slab pages,
  * which do not have slab_cache pointer set.
- * So this function assumes that the page can pass PageHead() and PageSlab()
- * checks.
+ * So this function assumes that the page can pass PageSlab() && !PageTail()
+ * check.
  *
  * The kmem_cache can be reparented asynchronously. The caller must ensure
  * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6afc892a148a..a8222041bd44 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 			unsigned long freecount = 0;
 			struct free_area *area;
 			struct list_head *curr;
+			bool overflow = false;
 
 			area = &(zone->free_area[order]);
 
-			list_for_each(curr, &area->free_list[mtype])
-				freecount++;
-			seq_printf(m, "%6lu ", freecount);
+			list_for_each(curr, &area->free_list[mtype]) {
+				/*
+				 * Cap the free_list iteration because it might
+				 * be really large and we are under a spinlock
+				 * so a long time spent here could trigger a
+				 * hard lockup detector. Anyway this is a
+				 * debugging tool so knowing there is a handful
+				 * of pages of this order should be more than
+				 * sufficient.
+				 */
+				if (++freecount >= 100000) {
+					overflow = true;
+					break;
+				}
+			}
+			seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount);
+			spin_unlock_irq(&zone->lock);
+			cond_resched();
+			spin_lock_irq(&zone->lock);
 		}
 		seq_putc(m, '\n');
 	}
@@ -1972,7 +1989,7 @@ void __init init_mm_internals(void)
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
-	proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
+	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
 	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
 	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
 #endif