net: xdp: Introduce bulking for xdp tx return path

XDP bulk APIs introduce a defer/flush mechanism to return
pages belonging to the same xdp_mem_allocator object
(identified via the mem.id field) in bulk to optimize
I-cache and D-cache since xdp_return_frame is usually run
inside the driver NAPI tx completion loop.
The bulk queue size is set to 16 to be aligned to how
XDP_REDIRECT bulking works. The bulk is flushed when
it is full or when mem.id changes.
xdp_frame_bulk is usually stored/allocated on the function
call-stack to avoid locking penalties.
Current implementation considers only page_pool memory model.

Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/bpf/e190c03eac71b20c8407ae0fc2c399eda7835f49.1605267335.git.lorenzo@kernel.org

include/net/xdp.h

@@ -104,6 +104,18 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+#define XDP_BULK_QUEUE_SIZE	16
+struct xdp_frame_bulk {
+	int count;
+	void *xa;
+	void *q[XDP_BULK_QUEUE_SIZE];
+};
+
+static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
+{
+	/* bq->count will be zero'ed when bq->xa gets updated */
+	bq->xa = NULL;
+}
 
 static inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)
@@ -194,6 +206,9 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
 void xdp_return_frame(struct xdp_frame *xdpf);
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
 void xdp_return_buff(struct xdp_buff *xdp);
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq);
 
 /* When sending xdp_frame into the network stack, then there is no
  * return point callback, which is needed to release e.g. DMA-mapping
@@ -245,6 +260,6 @@ bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 void xdp_attachment_setup(struct xdp_attachment_info *info,
 			  struct netdev_bpf *bpf);
 
-#define DEV_MAP_BULK_SIZE 16
+#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
 
 #endif /* __LINUX_NET_XDP_H__ */

net/core/xdp.c

@@ -380,6 +380,65 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_allocator *xa = bq->xa;
+	int i;
+
+	if (unlikely(!xa))
+		return;
+
+	for (i = 0; i < bq->count; i++) {
+		struct page *page = virt_to_head_page(bq->q[i]);
+
+		page_pool_put_full_page(xa->page_pool, page, false);
+	}
+	/* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_info *mem = &xdpf->mem;
+	struct xdp_mem_allocator *xa;
+
+	if (mem->type != MEM_TYPE_PAGE_POOL) {
+		__xdp_return(xdpf->data, &xdpf->mem, false);
+		return;
+	}
+
+	xa = bq->xa;
+	if (unlikely(!xa)) {
+		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+		bq->count = 0;
+		bq->xa = xa;
+	}
+
+	if (bq->count == XDP_BULK_QUEUE_SIZE)
+		xdp_flush_frame_bulk(bq);
+
+	if (unlikely(mem->id != xa->mem.id)) {
+		xdp_flush_frame_bulk(bq);
+		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+	}
+
+	bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);