Merge tag 'v4.5-rc7' into x86/asm, to pick up SMAP fix

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

11 files changed, 87 insertions, 50 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 23edccecadb0..3461d97ecb30 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -446,7 +446,8 @@ 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 +483,8 @@ 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() */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 08fc0ba2207e..e10a4fee88d2 100644
--- a/mm/huge_memory.c
+++ b/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);
 		}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 06ae13e869d0..01f2b48c8618 100644
--- a/mm/hugetlb.c
+++ b/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();
diff --git a/mm/memory.c b/mm/memory.c
index 38090ca37a08..906d8e3b42c0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3425,8 +3425,18 @@ 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
diff --git a/mm/migrate.c b/mm/migrate.c
index b1034f9c77e7..3ad0fea5c438 100644
--- a/mm/migrate.c
+++ b/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;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index e2e9f48b06c2..90e3b869a8b9 100644
--- a/mm/mmap.c
+++ b/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);
diff --git a/mm/slab.c b/mm/slab.c
index 6ecc697a8bc4..621fbcb35a36 100644
--- a/mm/slab.c
+++ b/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;
 	}
 
@@ -2414,12 +2414,13 @@ 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;
 }
 
 /*
diff --git a/mm/slab.h b/mm/slab.h
index 834ad240c0bb..2eedacea439d 100644
--- a/mm/slab.h
+++ b/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 *);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index b50aef01ccf7..065b7bdabdc3 100644
--- a/mm/slab_common.c
+++ b/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);
diff --git a/mm/slob.c b/mm/slob.c
index 17e8f8cc7c53..5ec158054ffe 100644
--- a/mm/slob.c
+++ b/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;
diff --git a/mm/slub.c b/mm/slub.c
index 2e1355ac056b..d8fbd4a6ed59 100644
--- a/mm/slub.c
+++ b/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;
 }