Merge branch 'devel-stable' into for-next

7 files changed, 50 insertions, 59 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82166bf974e1..4df39b1bde91 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;
 	}
 
@@ -1545,6 +1548,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
+			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
@@ -1557,16 +1561,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = *pmd;
-				entry = pmd_mknuma(entry);
+				pmdp_set_numa(mm, addr, pmd);
 				ret = HPAGE_PMD_NR;
 			}
 		}
-
-		/* Set PMD if cleared earlier */
-		if (ret == HPAGE_PMD_NR)
-			set_pmd_at(mm, addr, pmd, entry);
-
 		spin_unlock(ptl);
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd4e6f0..ce7a8cc7b404 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -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);
 }
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f08a2d61487..2f2f34a4e77d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -945,8 +945,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 			 * to it. Similarly, page lock is shifted.
 			 */
 			if (hpage != p) {
-				put_page(hpage);
-				get_page(p);
+				if (!(flags & MF_COUNT_INCREASED)) {
+					put_page(hpage);
+					get_page(p);
+				}
 				lock_page(p);
 				unlock_page(hpage);
 				*hpagep = p;
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/mprotect.c b/mm/mprotect.c
index 7332c1785744..769a67a15803 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -58,36 +58,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				if (pte_numa(ptent))
 					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
+				/*
+				 * Avoid taking write faults for pages we
+				 * know to be dirty.
+				 */
+				if (dirty_accountable && pte_dirty(ptent))
+					ptent = pte_mkwrite(ptent);
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
 			} else {
 				struct page *page;
 
-				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page && !PageKsm(page)) {
 					if (!pte_numa(oldpte)) {
-						ptent = pte_mknuma(ptent);
-						set_pte_at(mm, addr, pte, ptent);
+						ptep_set_numa(mm, addr, pte);
 						updated = true;
 					}
 				}
 			}
-
-			/*
-			 * Avoid taking write faults for pages we know to be
-			 * dirty.
-			 */
-			if (dirty_accountable && pte_dirty(ptent)) {
-				ptent = pte_mkwrite(ptent);
-				updated = true;
-			}
-
 			if (updated)
 				pages++;
-
-			/* Only !prot_numa always clears the pte */
-			if (!prot_numa)
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
diff --git a/mm/slub.c b/mm/slub.c
index 7e3e0458bce4..25f14ad8f817 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1004,21 +1004,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 static void add_full(struct kmem_cache *s,
 	struct kmem_cache_node *n, struct page *page)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_add(&page->lru, &n->full);
 }
 
 static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_del(&page->lru);
 }
 
@@ -1520,11 +1518,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page)
 /*
  * Management of partially allocated slabs.
  */
-static inline void add_partial(struct kmem_cache_node *n,
-				struct page *page, int tail)
+static inline void
+__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	n->nr_partial++;
 	if (tail == DEACTIVATE_TO_TAIL)
 		list_add_tail(&page->lru, &n->partial);
@@ -1532,15 +1528,27 @@ static inline void add_partial(struct kmem_cache_node *n,
 		list_add(&page->lru, &n->partial);
 }
 
-static inline void remove_partial(struct kmem_cache_node *n,
-					struct page *page)
+static inline void add_partial(struct kmem_cache_node *n,
+				struct page *page, int tail)
 {
 	lockdep_assert_held(&n->list_lock);
+	__add_partial(n, page, tail);
+}
 
+static inline void
+__remove_partial(struct kmem_cache_node *n, struct page *page)
+{
 	list_del(&page->lru);
 	n->nr_partial--;
 }
 
+static inline void remove_partial(struct kmem_cache_node *n,
+					struct page *page)
+{
+	lockdep_assert_held(&n->list_lock);
+	__remove_partial(n, page);
+}
+
 /*
  * Remove slab from the partial list, freeze it and
  * return the pointer to the freelist.
@@ -2906,12 +2914,10 @@ static void early_kmem_cache_node_alloc(int node)
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
 	/*
-	 * the lock is for lockdep's sake, not for any actual
-	 * race protection
+	 * No locks need to be taken here as it has just been
+	 * initialized and there is no concurrent access.
 	 */
-	spin_lock(&n->list_lock);
-	add_partial(n, page, DEACTIVATE_TO_HEAD);
-	spin_unlock(&n->list_lock);
+	__add_partial(n, page, DEACTIVATE_TO_HEAD);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -3197,7 +3203,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			remove_partial(n, page);
+			__remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 196970a4541f..d4042e75f7c7 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/eventfd.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/printk.h>
 #include <linux/vmpressure.h>