Merge drm-fixes into drm-next.

Nouveau wanted this to avoid some worse conflicts when I merge that.

mm/backing-dev.c

@@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:

mm/filemap.c

@@ -195,6 +195,30 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 	else
 		cleancache_invalidate_page(mapping, page);
 
+	VM_BUG_ON_PAGE(page_mapped(page), page);
+	if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
+		int mapcount;
+
+		pr_alert("BUG: Bad page cache in process %s  pfn:%05lx\n",
+			 current->comm, page_to_pfn(page));
+		dump_page(page, "still mapped when deleted");
+		dump_stack();
+		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+
+		mapcount = page_mapcount(page);
+		if (mapping_exiting(mapping) &&
+		    page_count(page) >= mapcount + 2) {
+			/*
+			 * All vmas have already been torn down, so it's
+			 * a good bet that actually the page is unmapped,
+			 * and we'd prefer not to leak it: if we're wrong,
+			 * some other bad page check should catch it later.
+			 */
+			page_mapcount_reset(page);
+			atomic_sub(mapcount, &page->_count);
+		}
+	}
+
 	page_cache_tree_delete(mapping, page, shadow);
 
 	page->mapping = NULL;
@@ -205,7 +229,6 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 		__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
-	VM_BUG_ON_PAGE(page_mapped(page), page);
 
 	/*
 	 * At this point page must be either written or cleaned by truncate.
@@ -446,7 +469,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 {
 	int err = 0;
 
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = filemap_fdatawrite(mapping);
 		/*
 		 * Even if the above returned error, the pages may be
@@ -482,13 +506,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
-	if (dax_mapping(mapping) && mapping->nrexceptional) {
-		err = dax_writeback_mapping_range(mapping, lstart, lend);
-		if (err)
-			return err;
-	}
-
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
@@ -1890,6 +1909,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.

mm/huge_memory.c

@@ -1700,7 +1700,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
-		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
+		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
+				vma_is_anonymous(vma)) {
 			pgtable_t pgtable;
 			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
@@ -2835,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	bool young, write, dirty;
+	unsigned long addr;
 	int i;
 
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
@@ -2860,10 +2862,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	young = pmd_young(*pmd);
 	dirty = pmd_dirty(*pmd);
 
+	pmdp_huge_split_prepare(vma, haddr, pmd);
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
-	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
 		pte_t entry, *pte;
 		/*
 		 * Note that NUMA hinting access restrictions are not
@@ -2884,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		}
 		if (dirty)
 			SetPageDirty(page + i);
-		pte = pte_offset_map(&_pmd, haddr);
+		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, haddr, pte, entry);
+		set_pte_at(mm, addr, pte, entry);
 		atomic_inc(&page[i]._mapcount);
 		pte_unmap(pte);
 	}
@@ -2936,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pmd_populate(mm, pmd, pgtable);
 
 	if (freeze) {
-		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		for (i = 0; i < HPAGE_PMD_NR; i++) {
 			page_remove_rmap(page + i, false);
 			put_page(page + i);
 		}

mm/hugetlb.c

@@ -2630,8 +2630,10 @@ static int __init hugetlb_init(void)
 			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
 	}
 	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
-	if (default_hstate_max_huge_pages)
-		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	if (default_hstate_max_huge_pages) {
+		if (!default_hstate.max_huge_pages)
+			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	}
 
 	hugetlb_init_hstates();
 	gather_bootmem_prealloc();
@@ -2749,7 +2751,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	int ret;
 
 	if (!hugepages_supported())
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
@@ -2790,7 +2792,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	int ret;
 
 	if (!hugepages_supported())
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	tmp = h->nr_overcommit_huge_pages;
 
@@ -3500,7 +3502,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * COW. Warn that such a situation has occurred as it may not be obvious
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
-		pr_warning("PID %d killed due to inadequate hugepage pool\n",
+		pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
 			   current->pid);
 		return ret;
 	}

mm/kasan/kasan.c

@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
+#include <linux/linkage.h>
 #include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/mm.h>
@@ -60,6 +61,25 @@ void kasan_unpoison_shadow(const void *address, size_t size)
 	}
 }
 
+static void __kasan_unpoison_stack(struct task_struct *task, void *sp)
+{
+	void *base = task_stack_page(task);
+	size_t size = sp - base;
+
+	kasan_unpoison_shadow(base, size);
+}
+
+/* Unpoison the entire stack for a task. */
+void kasan_unpoison_task_stack(struct task_struct *task)
+{
+	__kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE);
+}
+
+/* Unpoison the stack for the current task beyond a watermark sp value. */
+asmlinkage void kasan_unpoison_remaining_stack(void *sp)
+{
+	__kasan_unpoison_stack(current, sp);
+}
 
 /*
  * All functions below always inlined so compiler could

mm/memory.c

@@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(pmd_none(*pmd)) &&
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+	/*
+	 * If a huge pmd materialized under us just retry later.  Use
+	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
+	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
+	 * in a different thread of this mm, in turn leading to a misleading
+	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
+	 * regular pmd that we can walk with pte_offset_map() and we can do that
+	 * through an atomic read in C, which is what pmd_trans_unstable()
+	 * provides.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd

mm/mempolicy.c

@@ -532,7 +532,7 @@ retry:
 		nid = page_to_nid(page);
 		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 			continue;
-		if (PageTail(page) && PageAnon(page)) {
+		if (PageTransCompound(page) && PageAnon(page)) {
 			get_page(page);
 			pte_unmap_unlock(pte, ptl);
 			lock_page(page);

mm/migrate.c

@@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~(__GFP_IO | __GFP_FS), 0);
+					 ~__GFP_RECLAIM, 0);
 
 	return newpage;
 }

mm/mmap.c

@@ -2664,12 +2664,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (start < vma->vm_start || start + size > vma->vm_end)
+	if (start < vma->vm_start)
 		goto out;
 
-	if (pgoff == linear_page_index(vma, start)) {
-		ret = 0;
-		goto out;
+	if (start + size > vma->vm_end) {
+		struct vm_area_struct *next;
+
+		for (next = vma->vm_next; next; next = next->vm_next) {
+			/* hole between vmas ? */
+			if (next->vm_start != next->vm_prev->vm_end)
+				goto out;
+
+			if (next->vm_file != vma->vm_file)
+				goto out;
+
+			if (next->vm_flags != vma->vm_flags)
+				goto out;
+
+			if (start + size <= next->vm_end)
+				break;
+		}
+
+		if (!next)
+			goto out;
 	}
 
 	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
@@ -2679,9 +2696,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	flags &= MAP_NONBLOCK;
 	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
 	if (vma->vm_flags & VM_LOCKED) {
+		struct vm_area_struct *tmp;
 		flags |= MAP_LOCKED;
+
 		/* drop PG_Mlocked flag for over-mapped range */
-		munlock_vma_pages_range(vma, start, start + size);
+		for (tmp = vma; tmp->vm_start >= start + size;
+				tmp = tmp->vm_next) {
+			munlock_vma_pages_range(tmp,
+					max(tmp->vm_start, start),
+					min(tmp->vm_end, start + size));
+		}
 	}
 
 	file = get_file(vma->vm_file);

mm/mprotect.c

@@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 

mm/mremap.c

@@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,

mm/pgtable-generic.c

@@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif

mm/slab.c

@@ -2275,7 +2275,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 
 	err = setup_cpu_cache(cachep, gfp);
 	if (err) {
-		__kmem_cache_shutdown(cachep);
+		__kmem_cache_release(cachep);
 		return err;
 	}
 
@@ -2413,13 +2413,14 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 }
 
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
+{
+	return __kmem_cache_shrink(cachep, false);
+}
+
+void __kmem_cache_release(struct kmem_cache *cachep)
 {
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep, false);
-
-	if (rc)
-		return rc;
 
 	free_percpu(cachep->cpu_cache);
 
@@ -2430,7 +2431,6 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 		kfree(n);
 		cachep->node[i] = NULL;
 	}
-	return 0;
 }
 
 /*

mm/slab.h

@@ -140,6 +140,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
+void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 

mm/slab_common.c

@@ -693,6 +693,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s,
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
+	__kmem_cache_release(s);
 	destroy_memcg_params(s);
 	kfree_const(s->name);
 	kmem_cache_free(kmem_cache, s);

mm/slob.c

@@ -630,6 +630,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c)
 	return 0;
 }
 
+void __kmem_cache_release(struct kmem_cache *c)
+{
+}
+
 int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;

mm/slub.c

@@ -1592,18 +1592,12 @@ static inline void add_partial(struct kmem_cache_node *n,
 	__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);
+	list_del(&page->lru);
+	n->nr_partial--;
 }
 
 /*
@@ -3184,6 +3178,12 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 	}
 }
 
+void __kmem_cache_release(struct kmem_cache *s)
+{
+	free_percpu(s->cpu_slab);
+	free_kmem_cache_nodes(s);
+}
+
 static int init_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
@@ -3443,28 +3443,31 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 
 /*
  * Attempt to free all partial slabs on a node.
- * This is called from kmem_cache_close(). We must be the last thread
- * using the cache and therefore we do not need to lock anymore.
+ * This is called from __kmem_cache_shutdown(). We must take list_lock
+ * because sysfs file might still access partial list after the shutdowning.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
 	struct page *page, *h;
 
+	BUG_ON(irqs_disabled());
+	spin_lock_irq(&n->list_lock);
 	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,
-			"Objects remaining in %s on kmem_cache_close()");
+			"Objects remaining in %s on __kmem_cache_shutdown()");
 		}
 	}
+	spin_unlock_irq(&n->list_lock);
 }
 
 /*
  * Release all resources used by a slab cache.
  */
-static inline int kmem_cache_close(struct kmem_cache *s)
+int __kmem_cache_shutdown(struct kmem_cache *s)
 {
 	int node;
 	struct kmem_cache_node *n;
@@ -3476,16 +3479,9 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
-	free_percpu(s->cpu_slab);
-	free_kmem_cache_nodes(s);
 	return 0;
 }
 
-int __kmem_cache_shutdown(struct kmem_cache *s)
-{
-	return kmem_cache_close(s);
-}
-
 /********************************************************************
  *		Kmalloc subsystem
  *******************************************************************/
@@ -3980,7 +3976,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	memcg_propagate_slab_attrs(s);
 	err = sysfs_slab_add(s);
 	if (err)
-		kmem_cache_close(s);
+		__kmem_cache_release(s);
 
 	return err;
 }