Merge branch 'xdp-redirect-bulk'

Lorenzo Bianconi says:

====================
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.

Convert mvneta, mvpp2 and mlx5 drivers to xdp_return_frame_bulk APIs.

More details on benchmarks run on mlx5 can be found here:
https://github.com/xdp-project/xdp-project/blob/master/areas/mem/xdp_bulk_return01.org

Changes since v5:
- do not keep looping over ptr_ring if the cache is full but release leftover
  pages running page_pool_return_page

Changes since v4:
- fix comments
- introduce xdp_frame_bulk_init utility routine
- compiler annotations for I-cache code layout
- move rcu_read_lock outside fast-path
- mlx5 xdp bulking code optimization

Changes since v3:
- align DEV_MAP_BULK_SIZE to XDP_BULK_QUEUE_SIZE
- refactor page_pool_put_page_bulk to avoid code duplication

Changes since v2:
- move mvneta changes in a dedicated patch

Changes since v1:
- improve comments
- rework xdp_return_frame_bulk routine logic
- move count and xa fields at the beginning of xdp_frame_bulk struct
- invert logic in page_pool_put_page_bulk for loop
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>

drivers/net/ethernet/marvell/mvneta.c

@@ -1834,8 +1834,13 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 				 struct netdev_queue *nq, bool napi)
 {
 	unsigned int bytes_compl = 0, pkts_compl = 0;
+	struct xdp_frame_bulk bq;
 	int i;
 
+	xdp_frame_bulk_init(&bq);
+
+	rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
 	for (i = 0; i < num; i++) {
 		struct mvneta_tx_buf *buf = &txq->buf[txq->txq_get_index];
 		struct mvneta_tx_desc *tx_desc = txq->descs +
@@ -1857,9 +1862,12 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 			if (napi && buf->type == MVNETA_TYPE_XDP_TX)
 				xdp_return_frame_rx_napi(buf->xdpf);
 			else
-				xdp_return_frame(buf->xdpf);
+				xdp_return_frame_bulk(buf->xdpf, &bq);
 		}
 	}
+	xdp_flush_frame_bulk(&bq);
+
+	rcu_read_unlock();
 
 	netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
 }

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -2440,8 +2440,13 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 				struct mvpp2_tx_queue *txq,
 				struct mvpp2_txq_pcpu *txq_pcpu, int num)
 {
+	struct xdp_frame_bulk bq;
 	int i;
 
+	xdp_frame_bulk_init(&bq);
+
+	rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
 	for (i = 0; i < num; i++) {
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;
@@ -2454,10 +2459,13 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 			dev_kfree_skb_any(tx_buf->skb);
 		else if (tx_buf->type == MVPP2_TYPE_XDP_TX ||
 			 tx_buf->type == MVPP2_TYPE_XDP_NDO)
-			xdp_return_frame(tx_buf->xdpf);
+			xdp_return_frame_bulk(tx_buf->xdpf, &bq);
 
 		mvpp2_txq_inc_get(txq_pcpu);
 	}
+	xdp_flush_frame_bulk(&bq);
+
+	rcu_read_unlock();
 }
 
 static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port,

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -366,7 +366,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				  struct mlx5e_xdp_wqe_info *wi,
 				  u32 *xsk_frames,
-				  bool recycle)
+				  bool recycle,
+				  struct xdp_frame_bulk *bq)
 {
 	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
 	u16 i;
@@ -379,7 +380,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 			/* XDP_TX from the XSK RQ and XDP_REDIRECT */
 			dma_unmap_single(sq->pdev, xdpi.frame.dma_addr,
 					 xdpi.frame.xdpf->len, DMA_TO_DEVICE);
-			xdp_return_frame(xdpi.frame.xdpf);
+			xdp_return_frame_bulk(xdpi.frame.xdpf, bq);
 			break;
 		case MLX5E_XDP_XMIT_MODE_PAGE:
 			/* XDP_TX from the regular RQ */
@@ -397,12 +398,15 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 {
+	struct xdp_frame_bulk bq;
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
 	u32 xsk_frames = 0;
 	u16 sqcc;
 	int i;
 
+	xdp_frame_bulk_init(&bq);
+
 	sq = container_of(cq, struct mlx5e_xdpsq, cq);
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
@@ -434,7 +438,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 			sqcc += wi->num_wqebbs;
 
-			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true);
+			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true, &bq);
 		} while (!last_wqe);
 
 		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
@@ -447,6 +451,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		}
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	xdp_flush_frame_bulk(&bq);
+
 	if (xsk_frames)
 		xsk_tx_completed(sq->xsk_pool, xsk_frames);
 
@@ -463,8 +469,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 {
+	struct xdp_frame_bulk bq;
 	u32 xsk_frames = 0;
 
+	xdp_frame_bulk_init(&bq);
+
+	rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
 	while (sq->cc != sq->pc) {
 		struct mlx5e_xdp_wqe_info *wi;
 		u16 ci;
@@ -474,9 +485,12 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 
 		sq->cc += wi->num_wqebbs;
 
-		mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false);
+		mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false, &bq);
 	}
 
+	xdp_flush_frame_bulk(&bq);
+	rcu_read_unlock();
+
 	if (xsk_frames)
 		xsk_tx_completed(sq->xsk_pool, xsk_frames);
 }

include/net/page_pool.h

@@ -152,6 +152,8 @@ struct page_pool *page_pool_create(const struct page_pool_params *params);
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
 void page_pool_release_page(struct page_pool *pool, struct page *page);
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count);
 #else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
@@ -165,6 +167,11 @@ static inline void page_pool_release_page(struct page_pool *pool,
 					  struct page *page)
 {
 }
+
+static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+					   int count)
+{
+}
 #endif
 
 void page_pool_put_page(struct page_pool *pool, struct page *page,
@@ -215,4 +222,23 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
 	if (unlikely(pool->p.nid != new_nid))
 		page_pool_update_nid(pool, new_nid);
 }
+
+static inline void page_pool_ring_lock(struct page_pool *pool)
+	__acquires(&pool->ring.producer_lock)
+{
+	if (in_serving_softirq())
+		spin_lock(&pool->ring.producer_lock);
+	else
+		spin_lock_bh(&pool->ring.producer_lock);
+}
+
+static inline void page_pool_ring_unlock(struct page_pool *pool)
+	__releases(&pool->ring.producer_lock)
+{
+	if (in_serving_softirq())
+		spin_unlock(&pool->ring.producer_lock);
+	else
+		spin_unlock_bh(&pool->ring.producer_lock);
+}
+
 #endif /* _NET_PAGE_POOL_H */

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/page_pool.c

@@ -11,6 +11,8 @@
 #include <linux/device.h>
 
 #include <net/page_pool.h>
+#include <net/xdp.h>
+
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
 #include <linux/page-flags.h>
@@ -362,8 +364,9 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
  * If the page refcnt != 1, then the page will be returned to memory
  * subsystem.
  */
-void page_pool_put_page(struct page_pool *pool, struct page *page,
-			unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+		     unsigned int dma_sync_size, bool allow_direct)
 {
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
@@ -379,15 +382,12 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 			page_pool_dma_sync_for_device(pool, page,
 						      dma_sync_size);
 
-		if (allow_direct && in_serving_softirq())
-			if (page_pool_recycle_in_cache(page, pool))
-				return;
+		if (allow_direct && in_serving_softirq() &&
+		    page_pool_recycle_in_cache(page, pool))
+			return NULL;
 
-		if (!page_pool_recycle_in_ring(pool, page)) {
-			/* Cache full, fallback to free pages */
-			page_pool_return_page(pool, page);
-		}
-		return;
+		/* Page found as candidate for recycling */
+		return page;
 	}
 	/* Fallback/non-XDP mode: API user have elevated refcnt.
 	 *
@@ -405,9 +405,59 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 	/* Do not replace this with page_pool_return_page() */
 	page_pool_release_page(pool, page);
 	put_page(page);
+
+	return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+			unsigned int dma_sync_size, bool allow_direct)
+{
+	page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+	if (page && !page_pool_recycle_in_ring(pool, page)) {
+		/* Cache full, fallback to free pages */
+		page_pool_return_page(pool, page);
+	}
 }
 EXPORT_SYMBOL(page_pool_put_page);
 
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count)
+{
+	int i, bulk_len = 0;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = virt_to_head_page(data[i]);
+
+		page = __page_pool_put_page(pool, page, -1, false);
+		/* Approved for bulk recycling in ptr_ring cache */
+		if (page)
+			data[bulk_len++] = page;
+	}
+
+	if (unlikely(!bulk_len))
+		return;
+
+	/* Bulk producer into ptr_ring page_pool cache */
+	page_pool_ring_lock(pool);
+	for (i = 0; i < bulk_len; i++) {
+		if (__ptr_ring_produce(&pool->ring, data[i]))
+			break; /* ring full */
+	}
+	page_pool_ring_unlock(pool);
+
+	/* Hopefully all pages was return into ptr_ring */
+	if (likely(i == bulk_len))
+		return;
+
+	/* ptr_ring cache full, free remaining pages outside producer lock
+	 * since put_page() with refcnt == 1 can be an expensive operation
+	 */
+	for (; i < bulk_len; i++)
+		page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
 static void page_pool_empty_ring(struct page_pool *pool)
 {
 	struct page *page;

net/core/xdp.c

@@ -380,6 +380,60 @@ 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;
+
+	if (unlikely(!xa || !bq->count))
+		return;
+
+	page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+	/* 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);