Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "26 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (26 commits)
  userfaultfd: remove wrong comment from userfaultfd_ctx_get()
  fat: fix using uninitialized fields of fat_inode/fsinfo_inode
  sh: cayman: IDE support fix
  kasan: fix races in quarantine_remove_cache()
  kasan: resched in quarantine_remove_cache()
  mm: do not call mem_cgroup_free() from within mem_cgroup_alloc()
  thp: fix another corner case of munlock() vs. THPs
  rmap: fix NULL-pointer dereference on THP munlocking
  mm/memblock.c: fix memblock_next_valid_pfn()
  userfaultfd: selftest: vm: allow to build in vm/ directory
  userfaultfd: non-cooperative: userfaultfd_remove revalidate vma in MADV_DONTNEED
  userfaultfd: non-cooperative: fix fork fctx->new memleak
  mm/cgroup: avoid panic when init with low memory
  drivers/md/bcache/util.h: remove duplicate inclusion of blkdev.h
  mm/vmstats: add thp_split_pud event for clarity
  include/linux/fs.h: fix unsigned enum warning with gcc-4.2
  userfaultfd: non-cooperative: release all ctx in dup_userfaultfd_complete
  userfaultfd: non-cooperative: robustness check
  userfaultfd: non-cooperative: rollback userfaultfd_exit
  x86, mm: unify exit paths in gup_pte_range()
  ...

mm/huge_memory.c

@@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
 	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
 
-	count_vm_event(THP_SPLIT_PMD);
+	count_vm_event(THP_SPLIT_PUD);
 
 	pudp_huge_clear_flush_notify(vma, haddr, pud);
 }

mm/kasan/quarantine.c

@@ -25,6 +25,7 @@
 #include <linux/printk.h>
 #include <linux/shrinker.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/string.h>
 #include <linux/types.h>
 
@@ -103,6 +104,7 @@ static int quarantine_tail;
 /* Total size of all objects in global_quarantine across all batches. */
 static unsigned long quarantine_size;
 static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
 
 /* Maximum size of the global queue. */
 static unsigned long quarantine_max_size;
@@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 	struct qlist_head *q;
 	struct qlist_head temp = QLIST_INIT;
 
+	/*
+	 * Note: irq must be disabled until after we move the batch to the
+	 * global quarantine. Otherwise quarantine_remove_cache() can miss
+	 * some objects belonging to the cache if they are in our local temp
+	 * list. quarantine_remove_cache() executes on_each_cpu() at the
+	 * beginning which ensures that it either sees the objects in per-cpu
+	 * lists or in the global quarantine.
+	 */
 	local_irq_save(flags);
 
 	q = this_cpu_ptr(&cpu_quarantine);
 	qlist_put(q, &info->quarantine_link, cache->size);
-	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
 		qlist_move_all(q, &temp);
 
-	local_irq_restore(flags);
-
-	if (unlikely(!qlist_empty(&temp))) {
-		spin_lock_irqsave(&quarantine_lock, flags);
+		spin_lock(&quarantine_lock);
 		WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
 		qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
 		if (global_quarantine[quarantine_tail].bytes >=
@@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 			if (new_tail != quarantine_head)
 				quarantine_tail = new_tail;
 		}
-		spin_unlock_irqrestore(&quarantine_lock, flags);
+		spin_unlock(&quarantine_lock);
 	}
+
+	local_irq_restore(flags);
 }
 
 void quarantine_reduce(void)
 {
 	size_t total_size, new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
+	int srcu_idx;
 	struct qlist_head to_free = QLIST_INIT;
 
 	if (likely(READ_ONCE(quarantine_size) <=
 		   READ_ONCE(quarantine_max_size)))
 		return;
 
+	/*
+	 * srcu critical section ensures that quarantine_remove_cache()
+	 * will not miss objects belonging to the cache while they are in our
+	 * local to_free list. srcu is chosen because (1) it gives us private
+	 * grace period domain that does not interfere with anything else,
+	 * and (2) it allows synchronize_srcu() to return without waiting
+	 * if there are no pending read critical sections (which is the
+	 * expected case).
+	 */
+	srcu_idx = srcu_read_lock(&remove_cache_srcu);
 	spin_lock_irqsave(&quarantine_lock, flags);
 
 	/*
@@ -237,6 +257,7 @@ void quarantine_reduce(void)
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, NULL);
+	srcu_read_unlock(&remove_cache_srcu, srcu_idx);
 }
 
 static void qlist_move_cache(struct qlist_head *from,
@@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 	unsigned long flags, i;
 	struct qlist_head to_free = QLIST_INIT;
 
+	/*
+	 * Must be careful to not miss any objects that are being moved from
+	 * per-cpu list to the global quarantine in quarantine_put(),
+	 * nor objects being freed in quarantine_reduce(). on_each_cpu()
+	 * achieves the first goal, while synchronize_srcu() achieves the
+	 * second.
+	 */
 	on_each_cpu(per_cpu_remove_cache, cache, 1);
 
 	spin_lock_irqsave(&quarantine_lock, flags);
-	for (i = 0; i < QUARANTINE_BATCHES; i++)
+	for (i = 0; i < QUARANTINE_BATCHES; i++) {
+		if (qlist_empty(&global_quarantine[i]))
+			continue;
 		qlist_move_cache(&global_quarantine[i], &to_free, cache);
+		/* Scanning whole quarantine can take a while. */
+		spin_unlock_irqrestore(&quarantine_lock, flags);
+		cond_resched();
+		spin_lock_irqsave(&quarantine_lock, flags);
+	}
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, cache);
+
+	synchronize_srcu(&remove_cache_srcu);
 }

mm/madvise.c

@@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 	if (!can_madv_dontneed_vma(vma))
 		return -EINVAL;
 
-	userfaultfd_remove(vma, prev, start, end);
+	if (!userfaultfd_remove(vma, start, end)) {
+		*prev = NULL; /* mmap_sem has been dropped, prev is stale */
+
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, start);
+		if (!vma)
+			return -ENOMEM;
+		if (start < vma->vm_start) {
+			/*
+			 * This "vma" under revalidation is the one
+			 * with the lowest vma->vm_start where start
+			 * is also < vma->vm_end. If start <
+			 * vma->vm_start it means an hole materialized
+			 * in the user address space within the
+			 * virtual range passed to MADV_DONTNEED.
+			 */
+			return -ENOMEM;
+		}
+		if (!can_madv_dontneed_vma(vma))
+			return -EINVAL;
+		if (end > vma->vm_end) {
+			/*
+			 * Don't fail if end > vma->vm_end. If the old
+			 * vma was splitted while the mmap_sem was
+			 * released the effect of the concurrent
+			 * operation may not cause MADV_DONTNEED to
+			 * have an undefined result. There may be an
+			 * adjacent next vma that we'll walk
+			 * next. userfaultfd_remove() will generate an
+			 * UFFD_EVENT_REMOVE repetition on the
+			 * end-vma->vm_end range, but the manager can
+			 * handle a repetition fine.
+			 */
+			end = vma->vm_end;
+		}
+		VM_WARN_ON(start >= end);
+	}
 	zap_page_range(vma, start, end - start);
 	return 0;
 }
@@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
 	 * mmap_sem.
 	 */
 	get_file(f);
-	userfaultfd_remove(vma, prev, start, end);
-	up_read(&current->mm->mmap_sem);
+	if (userfaultfd_remove(vma, start, end)) {
+		/* mmap_sem was not released by userfaultfd_remove() */
+		up_read(&current->mm->mmap_sem);
+	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);

mm/memblock.c

@@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
 		}
 	} while (left < right);
 
-	return min(PHYS_PFN(type->regions[right].base), max_pfn);
+	if (right == type->cnt)
+		return max_pfn;
+	else
+		return min(PHYS_PFN(type->regions[right].base), max_pfn);
 }
 
 /**

mm/memcontrol.c

@@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	struct mem_cgroup_tree_per_node *mctz;
 
 	mctz = soft_limit_tree_from_page(page);
+	if (!mctz)
+		return;
 	/*
 	 * Necessary to update all ancestors when hierarchy is used.
 	 * because their event counter is not touched.
@@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 	for_each_node(nid) {
 		mz = mem_cgroup_nodeinfo(memcg, nid);
 		mctz = soft_limit_tree_node(nid);
-		mem_cgroup_remove_exceeded(mz, mctz);
+		if (mctz)
+			mem_cgroup_remove_exceeded(mz, mctz);
 	}
 }
 
@@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 	 * is empty. Do it lockless to prevent lock bouncing. Races
 	 * are acceptable as soft limit is best effort anyway.
 	 */
-	if (RB_EMPTY_ROOT(&mctz->rb_root))
+	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
 		return 0;
 
 	/*
@@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	kfree(memcg->nodeinfo[node]);
 }
 
-static void mem_cgroup_free(struct mem_cgroup *memcg)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);
 }
 
+static void mem_cgroup_free(struct mem_cgroup *memcg)
+{
+	memcg_wb_domain_exit(memcg);
+	__mem_cgroup_free(memcg);
+}
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
@@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	if (memcg->id.id > 0)
 		idr_remove(&mem_cgroup_idr, memcg->id.id);
-	mem_cgroup_free(memcg);
+	__mem_cgroup_free(memcg);
 	return NULL;
 }
 

mm/mlock.c

@@ -442,7 +442,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page;
-		unsigned int page_mask;
+		unsigned int page_mask = 0;
 		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
@@ -456,8 +456,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 		 * suits munlock very well (and if somehow an abnormal page
 		 * has sneaked into the range, we won't oops here: great).
 		 */
-		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
-				&page_mask);
+		page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
 
 		if (page && !IS_ERR(page)) {
 			if (PageTransTail(page)) {
@@ -468,8 +467,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				/*
 				 * Any THP page found by follow_page_mask() may
 				 * have gotten split before reaching
-				 * munlock_vma_page(), so we need to recompute
-				 * the page_mask here.
+				 * munlock_vma_page(), so we need to compute
+				 * the page_mask here instead.
 				 */
 				page_mask = munlock_vma_page(page);
 				unlock_page(page);

mm/rmap.c

@@ -1316,12 +1316,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	}
 
 	while (page_vma_mapped_walk(&pvmw)) {
-		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
-		address = pvmw.address;
-
-		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_PAGE(!pvmw.pte, page);
-
 		/*
 		 * If the page is mlock()d, we cannot swap it out.
 		 * If it's recently referenced (perhaps page_referenced
@@ -1345,6 +1339,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				continue;
 		}
 
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		address = pvmw.address;
+
+
 		if (!(flags & TTU_IGNORE_ACCESS)) {
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte)) {

mm/vmstat.c

@@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
 	"thp_split_page_failed",
 	"thp_deferred_split_page",
 	"thp_split_pmd",
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	"thp_split_pud",
+#endif
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif