Merge branch 'sched/urgent' into sched/core

Pick up fixes before queueing up new changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 75 insertions, 44 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 2d9f1504d75e..2888024e0b0a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -575,5 +575,5 @@ config PGTABLE_MAPPING
 	  then you should select this. This causes zsmalloc to use page table
 	  mapping rather than copying for object mapping.
 
-	  You can check speed with zsmalloc benchmark[1].
-	  [1] https://github.com/spartacus06/zsmalloc
+	  You can check speed with zsmalloc benchmark:
+	  https://github.com/spartacus06/zsmapbench
diff --git a/mm/compaction.c b/mm/compaction.c
index b48c5259ea33..918577595ea8 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,7 +251,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
 
@@ -264,11 +263,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -289,12 +289,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da23eb96779f..1546655a2d78 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,8 +1166,10 @@ alloc:
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
-			if (ret & VM_FAULT_OOM)
+			if (ret & VM_FAULT_OOM) {
 				split_huge_page(page);
+				ret |= VM_FAULT_FALLBACK;
+			}
 			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
@@ -1179,9 +1181,10 @@ alloc:
 		if (page) {
 			split_huge_page(page);
 			put_page(page);
-		}
+		} else
+			split_huge_page_pmd(vma, address, pmd);
+		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
@@ -1958,7 +1961,7 @@ out:
 	return ret;
 }
 
-#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
+#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
 
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
diff --git a/mm/ksm.c b/mm/ksm.c
index aa4c7c7250c1..68710e80994a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item)
 static struct page *page_trans_compound_anon(struct page *page)
 {
 	if (PageTransCompound(page)) {
-		struct page *head = compound_trans_head(page);
+		struct page *head = compound_head(page);
 		/*
 		 * head may actually be splitted and freed from under
 		 * us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd4e6f0..5b6b0039f725 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,8 +1127,8 @@ skip_node:
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css->flags & CSS_ONLINE) &&
-				(next_css == &root->css || css_tryget(next_css)))
+		if ((next_css == &root->css) ||
+		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
 			return mem_cgroup_from_css(next_css);
 
 		prev_css = next_css;
@@ -1687,7 +1687,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	 * protects memcg_name and makes sure that parallel ooms do not
 	 * interleave
 	 */
-	static DEFINE_SPINLOCK(oom_info_lock);
+	static DEFINE_MUTEX(oom_info_lock);
 	struct cgroup *task_cgrp;
 	struct cgroup *mem_cgrp;
 	static char memcg_name[PATH_MAX];
@@ -1698,7 +1698,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	if (!p)
 		return;
 
-	spin_lock(&oom_info_lock);
+	mutex_lock(&oom_info_lock);
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1767,7 +1767,7 @@ done:
 
 		pr_cont("\n");
 	}
-	spin_unlock(&oom_info_lock);
+	mutex_unlock(&oom_info_lock);
 }
 
 /*
@@ -6595,6 +6595,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event, *tmp;
+	struct cgroup_subsys_state *iter;
 
 	/*
 	 * Unregister events and notify userspace.
@@ -6611,7 +6612,14 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	kmem_cgroup_css_offline(memcg);
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
-	mem_cgroup_reparent_charges(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	css_for_each_descendant_post(iter, css)
+		mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
+
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2f2f34a4e77d..90002ea43638 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1651,7 +1651,7 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_trans_head(page);
+	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
diff --git a/mm/memory.c b/mm/memory.c
index be6a0c0d4ae0..22dfa617bddb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3348,6 +3348,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
 		ret = VM_FAULT_HWPOISON;
+		page_cache_release(vmf.page);
 		goto uncharge_out;
 	}
 
@@ -3703,7 +3704,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
-retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3741,20 +3741,13 @@ retry:
 			if (dirty && !pmd_write(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
-				/*
-				 * If COW results in an oom, the huge pmd will
-				 * have been split, so retry the fault on the
-				 * pte for a smaller charge.
-				 */
-				if (unlikely(ret & VM_FAULT_OOM))
-					goto retry;
-				return ret;
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
 			} else {
 				huge_pmd_set_accessed(mm, vma, address, pmd,
 						      orig_pmd, dirty);
+				return 0;
 			}
-
-			return 0;
 		}
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 482a33d89134..b494fdb9a636 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1158,7 +1158,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 					pm->node);
 	else
 		return alloc_pages_exact_node(pm->node,
-				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
 /*
@@ -1544,9 +1544,9 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 	struct page *newpage;
 
 	newpage = alloc_pages_exact_node(nid,
-					 (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
-					  __GFP_NOMEMALLOC | __GFP_NORETRY |
-					  __GFP_NOWARN) &
+					 (GFP_HIGHUSER_MOVABLE |
+					  __GFP_THISNODE | __GFP_NOMEMALLOC |
+					  __GFP_NORETRY | __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 
 	return newpage;
@@ -1747,7 +1747,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a09a009..3bac76ae4b30 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-		__SetPageTail(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -1236,6 +1238,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	}
 	local_irq_restore(flags);
 }
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return false;
+}
 #endif
 
 /*
@@ -1572,7 +1583,13 @@ again:
 					  get_pageblock_migratetype(page));
 	}
 
-	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	/*
+	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+	 * aging protocol, so they can't be fair.
+	 */
+	if (!gfp_thisnode_allocation(gfp_flags))
+		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
@@ -1944,8 +1961,12 @@ zonelist_scan:
 		 * ultimately fall back to remote zones that do not
 		 * partake in the fairness round-robin cycle of this
 		 * zonelist.
+		 *
+		 * NOTE: GFP_THISNODE allocations do not partake in
+		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if (alloc_flags & ALLOC_WMARK_LOW) {
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    !gfp_thisnode_allocation(gfp_mask)) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
 			if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (IS_ENABLED(CONFIG_NUMA) &&
-			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (gfp_thisnode_allocation(gfp_mask))
 		goto nopage;
 
 restart:
diff --git a/mm/swap.c b/mm/swap.c
index b31ba67d440a..0092097b3f4c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -98,7 +98,7 @@ static void put_compound_page(struct page *page)
 	}
 
 	/* __split_huge_page_refcount can run under us */
-	page_head = compound_trans_head(page);
+	page_head = compound_head(page);
 
 	/*
 	 * THP can not break up slab pages so avoid taking
@@ -253,7 +253,7 @@ bool __get_page_tail(struct page *page)
 	 */
 	unsigned long flags;
 	bool got;
-	struct page *page_head = compound_trans_head(page);
+	struct page *page_head = compound_head(page);
 
 	/* Ref to put_compound_page() comment. */
 	if (!__compound_tail_refcounted(page_head)) {