Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Cross merge.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

13 files changed, 209 insertions, 66 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index b1448aa81e15..f30a18a0e37d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -333,10 +333,9 @@ config SHUFFLE_PAGE_ALLOCATOR
 
 	  While the randomization improves cache utilization it may
 	  negatively impact workloads on platforms without a cache. For
-	  this reason, by default, the randomization is enabled only
-	  after runtime detection of a direct-mapped memory-side-cache.
-	  Otherwise, the randomization may be force enabled with the
-	  'page_alloc.shuffle' kernel command line parameter.
+	  this reason, by default, the randomization is not enabled even
+	  if SHUFFLE_PAGE_ALLOCATOR=y. The randomization may be force enabled
+	  with the 'page_alloc.shuffle' kernel command line parameter.
 
 	  Say Y if unsure.
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 30de18c4fd28..1d6b3a369077 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1540,7 +1540,7 @@ EXPORT_SYMBOL(folio_end_private_2);
  * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
  * @folio: The folio to wait on.
  *
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio.
+ * Wait for PG_private_2 to be cleared on a folio.
  */
 void folio_wait_private_2(struct folio *folio)
 {
@@ -1553,8 +1553,8 @@ EXPORT_SYMBOL(folio_wait_private_2);
  * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
  * @folio: The folio to wait on.
  *
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a
- * fatal signal is received by the calling task.
+ * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is
+ * received by the calling task.
  *
  * Return:
  * - 0 if successful.
@@ -4134,6 +4134,60 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 }
 EXPORT_SYMBOL(filemap_release_folio);
 
+/**
+ * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache
+ * @inode: The inode to flush
+ * @flush: Set to write back rather than simply invalidate.
+ * @start: First byte to in range.
+ * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start
+ *       onwards.
+ *
+ * Invalidate all the folios on an inode that contribute to the specified
+ * range, possibly writing them back first.  Whilst the operation is
+ * undertaken, the invalidate lock is held to prevent new folios from being
+ * installed.
+ */
+int filemap_invalidate_inode(struct inode *inode, bool flush,
+			     loff_t start, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t first = start >> PAGE_SHIFT;
+	pgoff_t last = end >> PAGE_SHIFT;
+	pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1;
+
+	if (!mapping || !mapping->nrpages || end < start)
+		goto out;
+
+	/* Prevent new folios from being added to the inode. */
+	filemap_invalidate_lock(mapping);
+
+	if (!mapping->nrpages)
+		goto unlock;
+
+	unmap_mapping_pages(mapping, first, nr, false);
+
+	/* Write back the data if we're asked to. */
+	if (flush) {
+		struct writeback_control wbc = {
+			.sync_mode	= WB_SYNC_ALL,
+			.nr_to_write	= LONG_MAX,
+			.range_start	= start,
+			.range_end	= end,
+		};
+
+		filemap_fdatawrite_wbc(mapping, &wbc);
+	}
+
+	/* Wait for writeback to complete on all folios and discard. */
+	truncate_inode_pages_range(mapping, start, end);
+
+unlock:
+	filemap_invalidate_unlock(mapping);
+out:
+	return filemap_check_errors(mapping);
+}
+EXPORT_SYMBOL_GPL(filemap_invalidate_inode);
+
 #ifdef CONFIG_CACHESTAT_SYSCALL
 /**
  * filemap_cachestat() - compute the page cache statistics of a mapping
diff --git a/mm/mmap.c b/mm/mmap.c
index 6dbda99a47da..3490af70f259 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1294,7 +1294,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		if (!file_mmap_ok(file, inode, pgoff, len))
 			return -EOVERFLOW;
 
-		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
+		flags_mask = LEGACY_MAP_MASK;
+		if (file->f_op->fop_flags & FOP_MMAP_SYNC)
+			flags_mask |= MAP_SYNC;
 
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
diff --git a/mm/nommu.c b/mm/nommu.c
index 5ec8f44e7ce9..a34a0e376611 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -355,6 +355,13 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
+int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
+			struct page **pages, unsigned long *num)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vm_insert_pages);
+
 int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
 			unsigned long num)
 {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e19b87049db..06fc89d981e8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2546,6 +2546,7 @@ done:
 	folio_batch_release(&wbc->fbatch);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(writeback_iter);
 
 /**
  * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 742f432e5bf0..8eed0f3dc085 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -170,7 +170,7 @@ static void add_stack_record_to_list(struct stack_record *stack_record,
 
 	/* Filter gfp_mask the same way stackdepot does, for consistency */
 	gfp_mask &= ~GFP_ZONEMASK;
-	gfp_mask &= (GFP_ATOMIC | GFP_KERNEL);
+	gfp_mask &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
 	gfp_mask |= __GFP_NOWARN;
 
 	set_current_in_page_owner();
@@ -328,7 +328,7 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
 	if (unlikely(!page_ext))
 		return;
 	__update_page_owner_handle(page_ext, handle, order, gfp_mask, -1,
-				   current->pid, current->tgid, ts_nsec,
+				   ts_nsec, current->pid, current->tgid,
 				   current->comm);
 	page_ext_put(page_ext);
 	inc_stack_record_count(handle, gfp_mask, 1 << order);
diff --git a/mm/readahead.c b/mm/readahead.c
index 130c0e7df99f..d55138e9560b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -490,6 +490,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	pgoff_t index = readahead_index(ractl);
 	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	pgoff_t mark = index + ra->size - ra->async_size;
+	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
 
@@ -504,6 +505,8 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		new_order = min_t(unsigned int, new_order, ilog2(ra->size));
 	}
 
+	/* See comment in page_cache_ra_unbounded() */
+	nofs = memalloc_nofs_save();
 	filemap_invalidate_lock_shared(mapping);
 	while (index <= limit) {
 		unsigned int order = new_order;
@@ -527,6 +530,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 
 	read_pages(ractl);
 	filemap_invalidate_unlock_shared(mapping);
+	memalloc_nofs_restore(nofs);
 
 	/*
 	 * If there were already pages in the page cache, then we may have
diff --git a/mm/shmem.c b/mm/shmem.c
index 94ab99b6b574..1f84a41aeb85 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3467,8 +3467,7 @@ static int shmem_rename2(struct mnt_idmap *idmap,
 			return error;
 	}
 
-	simple_offset_remove(shmem_get_offset_ctx(old_dir), old_dentry);
-	error = simple_offset_add(shmem_get_offset_ctx(new_dir), old_dentry);
+	error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (error)
 		return error;
 
diff --git a/mm/slab.h b/mm/slab.h
index d2bc9b191222..78e205b46e19 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -496,9 +496,6 @@ struct slabinfo {
 };
 
 void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
-void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-		       size_t count, loff_t *ppos);
 
 #ifdef CONFIG_SLUB_DEBUG
 #ifdef CONFIG_SLUB_DEBUG_ON
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f5234672f03c..c37f8c41ffb0 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -916,22 +916,15 @@ void __init create_kmalloc_caches(void)
 	 * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined
 	 */
 	for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) {
-		for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
-			if (!kmalloc_caches[type][i])
-				new_kmalloc_cache(i, type);
-
-			/*
-			 * Caches that are not of the two-to-the-power-of size.
-			 * These have to be created immediately after the
-			 * earlier power of two caches
-			 */
-			if (KMALLOC_MIN_SIZE <= 32 && i == 6 &&
-					!kmalloc_caches[type][1])
-				new_kmalloc_cache(1, type);
-			if (KMALLOC_MIN_SIZE <= 64 && i == 7 &&
-					!kmalloc_caches[type][2])
-				new_kmalloc_cache(2, type);
-		}
+		/* Caches that are NOT of the two-to-the-power-of size. */
+		if (KMALLOC_MIN_SIZE <= 32)
+			new_kmalloc_cache(1, type);
+		if (KMALLOC_MIN_SIZE <= 64)
+			new_kmalloc_cache(2, type);
+
+		/* Caches that are of the two-to-the-power-of size. */
+		for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
+			new_kmalloc_cache(i, type);
 	}
 #ifdef CONFIG_RANDOM_KMALLOC_CACHES
 	random_kmalloc_seed = get_random_u64();
@@ -1078,7 +1071,6 @@ static void cache_show(struct kmem_cache *s, struct seq_file *m)
 		   sinfo.limit, sinfo.batchcount, sinfo.shared);
 	seq_printf(m, " : slabdata %6lu %6lu %6lu",
 		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
-	slabinfo_show_stats(m, s);
 	seq_putc(m, '\n');
 }
 
@@ -1155,7 +1147,6 @@ static const struct proc_ops slabinfo_proc_ops = {
 	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_open	= slabinfo_open,
 	.proc_read	= seq_read,
-	.proc_write	= slabinfo_write,
 	.proc_lseek	= seq_lseek,
 	.proc_release	= seq_release,
 };
diff --git a/mm/slub.c b/mm/slub.c
index 24f702afd458..4954999183d5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -624,11 +624,21 @@ static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
 	nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
 	s->cpu_partial_slabs = nr_slabs;
 }
+
+static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
+{
+	return s->cpu_partial_slabs;
+}
 #else
 static inline void
 slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
 {
 }
+
+static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
+{
+	return 0;
+}
 #endif /* CONFIG_SLUB_CPU_PARTIAL */
 
 /*
@@ -2609,19 +2619,18 @@ static struct slab *get_partial_node(struct kmem_cache *s,
 		if (!partial) {
 			partial = slab;
 			stat(s, ALLOC_FROM_PARTIAL);
+
+			if ((slub_get_cpu_partial(s) == 0)) {
+				break;
+			}
 		} else {
 			put_cpu_partial(s, slab, 0);
 			stat(s, CPU_PARTIAL_NODE);
-			partial_slabs++;
-		}
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-		if (!kmem_cache_has_cpu_partial(s)
-			|| partial_slabs > s->cpu_partial_slabs / 2)
-			break;
-#else
-		break;
-#endif
 
+			if (++partial_slabs > slub_get_cpu_partial(s) / 2) {
+				break;
+			}
+		}
 	}
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	return partial;
@@ -2704,7 +2713,7 @@ static struct slab *get_partial(struct kmem_cache *s, int node,
 		searchnode = numa_mem_id();
 
 	slab = get_partial_node(s, get_node(s, searchnode), pc);
-	if (slab || node != NUMA_NO_NODE)
+	if (slab || (node != NUMA_NO_NODE && (pc->flags & __GFP_THISNODE)))
 		return slab;
 
 	return get_any_partial(s, pc);
@@ -2802,7 +2811,7 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 	struct slab new;
 	struct slab old;
 
-	if (slab->freelist) {
+	if (READ_ONCE(slab->freelist)) {
 		stat(s, DEACTIVATE_REMOTE_FREES);
 		tail = DEACTIVATE_TO_TAIL;
 	}
@@ -3234,6 +3243,43 @@ static unsigned long count_partial(struct kmem_cache_node *n,
 #endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */
 
 #ifdef CONFIG_SLUB_DEBUG
+#define MAX_PARTIAL_TO_SCAN 10000
+
+static unsigned long count_partial_free_approx(struct kmem_cache_node *n)
+{
+	unsigned long flags;
+	unsigned long x = 0;
+	struct slab *slab;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	if (n->nr_partial <= MAX_PARTIAL_TO_SCAN) {
+		list_for_each_entry(slab, &n->partial, slab_list)
+			x += slab->objects - slab->inuse;
+	} else {
+		/*
+		 * For a long list, approximate the total count of objects in
+		 * it to meet the limit on the number of slabs to scan.
+		 * Scan from both the list's head and tail for better accuracy.
+		 */
+		unsigned long scanned = 0;
+
+		list_for_each_entry(slab, &n->partial, slab_list) {
+			x += slab->objects - slab->inuse;
+			if (++scanned == MAX_PARTIAL_TO_SCAN / 2)
+				break;
+		}
+		list_for_each_entry_reverse(slab, &n->partial, slab_list) {
+			x += slab->objects - slab->inuse;
+			if (++scanned == MAX_PARTIAL_TO_SCAN)
+				break;
+		}
+		x = mult_frac(x, n->nr_partial, scanned);
+		x = min(x, node_nr_objs(n));
+	}
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	return x;
+}
+
 static noinline void
 slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 {
@@ -3260,7 +3306,7 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 		unsigned long nr_objs;
 		unsigned long nr_free;
 
-		nr_free  = count_partial(n, count_free);
+		nr_free  = count_partial_free_approx(n);
 		nr_slabs = node_nr_slabs(n);
 		nr_objs  = node_nr_objs(n);
 
@@ -3380,6 +3426,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	struct slab *slab;
 	unsigned long flags;
 	struct partial_context pc;
+	bool try_thisnode = true;
 
 	stat(s, ALLOC_SLOWPATH);
 
@@ -3506,6 +3553,21 @@ new_slab:
 new_objects:
 
 	pc.flags = gfpflags;
+	/*
+	 * When a preferred node is indicated but no __GFP_THISNODE
+	 *
+	 * 1) try to get a partial slab from target node only by having
+	 *    __GFP_THISNODE in pc.flags for get_partial()
+	 * 2) if 1) failed, try to allocate a new slab from target node with
+	 *    GPF_NOWAIT | __GFP_THISNODE opportunistically
+	 * 3) if 2) failed, retry with original gfpflags which will allow
+	 *    get_partial() try partial lists of other nodes before potentially
+	 *    allocating new page from other nodes
+	 */
+	if (unlikely(node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE)
+		     && try_thisnode))
+		pc.flags = GFP_NOWAIT | __GFP_THISNODE;
+
 	pc.orig_size = orig_size;
 	slab = get_partial(s, node, &pc);
 	if (slab) {
@@ -3527,10 +3589,15 @@ new_objects:
 	}
 
 	slub_put_cpu_ptr(s->cpu_slab);
-	slab = new_slab(s, gfpflags, node);
+	slab = new_slab(s, pc.flags, node);
 	c = slub_get_cpu_ptr(s->cpu_slab);
 
 	if (unlikely(!slab)) {
+		if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE)
+		    && try_thisnode) {
+			try_thisnode = false;
+			goto new_objects;
+		}
 		slab_out_of_memory(s, gfpflags, node);
 		return NULL;
 	}
@@ -4232,7 +4299,7 @@ redo:
 	c = raw_cpu_ptr(s->cpu_slab);
 	tid = READ_ONCE(c->tid);
 
-	/* Same with comment on barrier() in slab_alloc_node() */
+	/* Same with comment on barrier() in __slab_alloc_node() */
 	barrier();
 
 	if (unlikely(slab != c->slab)) {
@@ -4853,7 +4920,6 @@ static void early_kmem_cache_node_alloc(int node)
 	BUG_ON(!n);
 #ifdef CONFIG_SLUB_DEBUG
 	init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
-	init_tracking(kmem_cache_node, n);
 #endif
 	n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false);
 	slab->freelist = get_freepointer(kmem_cache_node, n);
@@ -5066,9 +5132,7 @@ static int calculate_sizes(struct kmem_cache *s)
 	if ((int)order < 0)
 		return 0;
 
-	s->allocflags = 0;
-	if (order)
-		s->allocflags |= __GFP_COMP;
+	s->allocflags = __GFP_COMP;
 
 	if (s->flags & SLAB_CACHE_DMA)
 		s->allocflags |= GFP_DMA;
@@ -6042,7 +6106,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 				else if (flags & SO_OBJECTS)
 					WARN_ON_ONCE(1);
 				else
-					x = slab->slabs;
+					x = data_race(slab->slabs);
 				total += x;
 				nodes[node] += x;
 			}
@@ -6247,7 +6311,7 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
 		slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
 
 		if (slab)
-			slabs += slab->slabs;
+			slabs += data_race(slab->slabs);
 	}
 #endif
 
@@ -6261,7 +6325,7 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
 
 		slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
 		if (slab) {
-			slabs = READ_ONCE(slab->slabs);
+			slabs = data_race(slab->slabs);
 			objects = (slabs * oo_objects(s->oo)) / 2;
 			len += sysfs_emit_at(buf, len, " C%d=%d(%d)",
 					     cpu, objects, slabs);
@@ -7095,7 +7159,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	for_each_kmem_cache_node(s, node, n) {
 		nr_slabs += node_nr_slabs(n);
 		nr_objs += node_nr_objs(n);
-		nr_free += count_partial(n, count_free);
+		nr_free += count_partial_free_approx(n);
 	}
 
 	sinfo->active_objs = nr_objs - nr_free;
@@ -7105,14 +7169,4 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	sinfo->objects_per_slab = oo_objects(s->oo);
 	sinfo->cache_order = oo_order(s->oo);
 }
-
-void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
-{
-}
-
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-		       size_t count, loff_t *ppos)
-{
-	return -EIO;
-}
 #endif /* CONFIG_SLUB_DEBUG */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 3c3539c573e7..829f7b1089fc 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -316,6 +316,38 @@ out_release:
 	goto out;
 }
 
+static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd,
+					 struct vm_area_struct *dst_vma,
+					 unsigned long dst_addr)
+{
+	struct folio *folio;
+	int ret = -ENOMEM;
+
+	folio = vma_alloc_zeroed_movable_folio(dst_vma, dst_addr);
+	if (!folio)
+		return ret;
+
+	if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL))
+		goto out_put;
+
+	/*
+	 * The memory barrier inside __folio_mark_uptodate makes sure that
+	 * zeroing out the folio become visible before mapping the page
+	 * using set_pte_at(). See do_anonymous_page().
+	 */
+	__folio_mark_uptodate(folio);
+
+	ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
+				       &folio->page, true, 0);
+	if (ret)
+		goto out_put;
+
+	return 0;
+out_put:
+	folio_put(folio);
+	return ret;
+}
+
 static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd,
 				     struct vm_area_struct *dst_vma,
 				     unsigned long dst_addr)
@@ -324,6 +356,9 @@ static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd,
 	spinlock_t *ptl;
 	int ret;
 
+	if (mm_forbids_zeropage(dst_vma->vm_mm))
+		return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr);
+
 	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
 					 dst_vma->vm_page_prot));
 	ret = -EAGAIN;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 68fa001648cc..125427cbdb87 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2710,7 +2710,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 		 * get_order(0) returns funny result. Just warn and terminate
 		 * early.
 		 */
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 	order = get_order(size);