mm: support __GFP_REPEAT in kvmalloc_node for >32kB

vhost code uses __GFP_REPEAT when allocating vhost_virtqueue resp.
vhost_vsock because it would really like to prefer kmalloc to the
vmalloc fallback - see 23cc5a9 ("vhost-net: extend device
allocation to vmalloc") for more context.  Michael Tsirkin has also
noted:

 "__GFP_REPEAT overhead is during allocation time. Using vmalloc means
  all accesses are slowed down. Allocation is not on data path, accesses
  are."

The similar applies to other vhost_kvzalloc users.

Let's teach kvmalloc_node to handle __GFP_REPEAT properly.  There are
two things to be careful about.  First we should prevent from the OOM
killer and so have to involve __GFP_NORETRY by default and secondly
override __GFP_REPEAT for !costly order requests as the __GFP_REPEAT is
ignored for !costly orders.

Supporting __GFP_REPEAT like semantic for !costly request is possible it
would require changes in the page allocator.  This is out of scope of
this patch.

This patch shouldn't introduce any functional change.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Michal Hocko <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
Cc: David Miller <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

drivers/vhost/net.c

@@ -817,12 +817,9 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	struct vhost_virtqueue **vqs;
 	int i;
 
-	n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-	if (!n) {
-		n = vmalloc(sizeof *n);
-		if (!n)
-			return -ENOMEM;
-	}
+	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
+	if (!n)
+		return -ENOMEM;
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
 		kvfree(n);

drivers/vhost/vhost.c

@@ -534,18 +534,9 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
 
-static void *vhost_kvzalloc(unsigned long size)
-{
-	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-
-	if (!n)
-		n = vzalloc(size);
-	return n;
-}
-
 struct vhost_umem *vhost_dev_reset_owner_prepare(void)
 {
-	return vhost_kvzalloc(sizeof(struct vhost_umem));
+	return kvzalloc(sizeof(struct vhost_umem), GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
 
@@ -1276,7 +1267,7 @@ EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
 static struct vhost_umem *vhost_umem_alloc(void)
 {
-	struct vhost_umem *umem = vhost_kvzalloc(sizeof(*umem));
+	struct vhost_umem *umem = kvzalloc(sizeof(*umem), GFP_KERNEL);
 
 	if (!umem)
 		return NULL;
@@ -1302,7 +1293,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EOPNOTSUPP;
 	if (mem.nregions > max_mem_regions)
 		return -E2BIG;
-	newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions));
+	newmem = kvzalloc(size + mem.nregions * sizeof(*m->regions), GFP_KERNEL);
 	if (!newmem)
 		return -ENOMEM;
 

drivers/vhost/vsock.c

@@ -508,12 +508,9 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	/* This struct is large and allocation could fail, fall back to vmalloc
 	 * if there is no other way.
 	 */
-	vsock = kzalloc(sizeof(*vsock), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-	if (!vsock) {
-		vsock = vmalloc(sizeof(*vsock));
-		if (!vsock)
-			return -ENOMEM;
-	}
+	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
+	if (!vsock)
+		return -ENOMEM;
 
 	vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {

mm/util.c

@@ -339,7 +339,9 @@ EXPORT_SYMBOL(vm_mmap);
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
- * Reclaim modifiers - __GFP_NORETRY, __GFP_REPEAT and __GFP_NOFAIL are not supported
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
+ * is supported only for large (>32kB) allocations, and it should be used only if
+ * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
  *
  * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people.
  */
@@ -358,8 +360,18 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	 * Make sure that larger requests are not too disruptive - no OOM
 	 * killer and no allocation failure warnings as we have a fallback
 	 */
-	if (size > PAGE_SIZE)
-		kmalloc_flags |= __GFP_NORETRY | __GFP_NOWARN;
+	if (size > PAGE_SIZE) {
+		kmalloc_flags |= __GFP_NOWARN;
+
+		/*
+		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
+		 * requests because there is no other way to tell the allocator
+		 * that we want to fail rather than retry endlessly.
+		 */
+		if (!(kmalloc_flags & __GFP_REPEAT) ||
+				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+			kmalloc_flags |= __GFP_NORETRY;
+	}
 
 	ret = kmalloc_node(size, kmalloc_flags, node);