Skip to contentSkip to conversation

xdp: introduce bulking for page_pool tx return path

PATCH Superseded Lorenzo Bianconi 2 participants 7 messages Oct 29, 2020 – Oct 30, 2020

Subsystems (8)
Networking Network drivers BPF Mellanox mlx5 core +4 more subsystems

v2 of 6 Superseded Latest is v6 →

lore
Share & tools
lore

Lorenzo Bianconi

author
#0 lore raw

v2 cover xdp: introduce bulking for page_pool 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.
Convert mvneta, mvpp2 and mlx5 drivers to xdp_return_frame_bulk APIs.

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

Lorenzo Bianconi (4):
net: xdp: introduce bulking for xdp tx return path
net: page_pool: add bulk support for ptr_ring
net: mvpp2: add xdp tx return bulking support
net: mlx5: add xdp tx return bulking support

 drivers/net/ethernet/marvell/mvneta.c         |  5 +-
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   |  5 +-
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  5 +-
 include/net/page_pool.h                       | 26 +++++++++
 include/net/xdp.h                             |  9 +++
 net/core/page_pool.c                          | 35 ++++++++++++
 net/core/xdp.c                                | 56 +++++++++++++++++++
 7 files changed, 138 insertions(+), 3 deletions(-)
Signature · 1 line
2.26.2
author
#1 lore raw

PATCH v2 1/4 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. Convert mvneta driver to xdp_return_frame_bulk APIs.

Suggested-by Jesper Dangaard Brouer <[email protected]>
Signed-off-by Lorenzo Bianconi <[email protected]>
---
 drivers/net/ethernet/marvell/mvneta.c |  5 ++-
 include/net/xdp.h                     |  9 ++++
 net/core/xdp.c                        | 61 +++++++++++++++++++++++++++
 3 files changed, 74 insertions(+), 1 deletion(-)
drivers/net/ethernet/marvell/mvneta.c +4 -1
index 54b0bf574c05..43ab8a73900e 100644
@@ -1834,8 +1834,10 @@ 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;
 
+	bq.xa = NULL;
 	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 +1859,10 @@ 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);
 
 	netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
 }
include/net/xdp.h +9 -0
index 3814fb631d52..a1f48a73e6df 100644
@@ -104,6 +104,12 @@ 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 inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)

@@ -194,6 +200,9 @@ 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
net/core/xdp.c +61 -0

67 lines not on this page · raw message

Signature · 1 line
2.26.2
maintainer
#2 lore raw

Re: [PATCH v2 net-next 1/4] net: xdp: introduce bulking for xdp tx return path

Hi Lorenzo,

Quoted 38 lines · Lorenzo Bianconi

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. Convert mvneta driver to xdp_return_frame_bulk APIs.

Suggested-by Jesper Dangaard Brouer <[email protected]>
Signed-off-by Lorenzo Bianconi <[email protected]>
---
 drivers/net/ethernet/marvell/mvneta.c |  5 ++-
 include/net/xdp.h                     |  9 ++++
 net/core/xdp.c                        | 61 +++++++++++++++++++++++++++
 3 files changed, 74 insertions(+), 1 deletion(-)
drivers/net/ethernet/marvell/mvneta.c +2 -0
index 54b0bf574c05..43ab8a73900e 100644
@@ -1834,8 +1834,10 @@ 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;
 
+	bq.xa = NULL;
 	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 +1859,10 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 			if (napi && buf->type == MVNETA_TYPE_XDP_TX)

drivers/net/ethernet/marvell/mvneta.c static void mvneta_txq_bufs_free(struct mvneta_port *pp, · line 1868

Quoted 10 lines
drivers/net/ethernet/marvell/mvneta.c +2 -1
 				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);
 
 	netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
 }

Sorry I completely forgot to mention this on the v1 review.
I think this belongs to a patch of it's own similar to mellanox and mvpp2 drivers

Quoted 102 lines
include/net/xdp.h +9 -0
index 3814fb631d52..a1f48a73e6df 100644
@@ -104,6 +104,12 @@ 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 inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)

@@ -194,6 +200,9 @@ 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
net/core/xdp.c +61 -0
index 48aba933a5a8..66ac275a0360 100644
@@ -380,6 +380,67 @@ 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->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+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;
+	}
+
+	rcu_read_lock();
+
+	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 (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;
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);
Signature · 1 line
2.26.2

Cheers
/Ilias

author
#3 lore raw

Re: [PATCH v2 net-next 1/4] net: xdp: introduce bulking for xdp tx return path

Quoted 3 lines

Hi Lorenzo,

On Thu, Oct 29, 2020 at 08:28:44PM +0100, Lorenzo Bianconi wrote:

[...]

Quoted 24 lines
Quoted 24 lines

index 54b0bf574c05..43ab8a73900e 100644

drivers/net/ethernet/marvell/mvneta.c +4 -1
@@ -1834,8 +1834,10 @@ 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;
 
+	bq.xa = NULL;
 	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 +1859,10 @@ 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);
Quoted 6 lines

drivers/net/ethernet/marvell/mvneta.c static void mvneta_txq_bufs_free(struct mvneta_port *pp, · line 1868

Quoted 2 lines
drivers/net/ethernet/marvell/mvneta.c +0 -0
 	netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
 }

Sorry I completely forgot to mention this on the v1 review.
I think this belongs to a patch of it's own similar to mellanox and mvpp2 drivers

ack, I am fine with it. I will fix it in v3.

Regards,
Lorenzo

Quoted 107 lines
Quoted 103 lines
include/net/xdp.h +9 -0
index 3814fb631d52..a1f48a73e6df 100644
@@ -104,6 +104,12 @@ 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 inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)

@@ -194,6 +200,9 @@ 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
net/core/xdp.c +61 -0
index 48aba933a5a8..66ac275a0360 100644
@@ -380,6 +380,67 @@ 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->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+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;
+	}
+
+	rcu_read_lock();
+
+	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 (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;
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);
Signature · 1 line
2.26.2

Cheers
/Ilias

author
#4 lore raw

PATCH v2 2/4 net: page_pool: add bulk support for ptr_ring

In reply to Lorenzo Bianconi

Introduce the capability to batch page_pool ptr_ring refill since it is usually run inside the driver NAPI tx completion loop.

Suggested-by Jesper Dangaard Brouer <[email protected]>
Signed-off-by Lorenzo Bianconi <[email protected]>
---
 include/net/page_pool.h | 26 ++++++++++++++++++++++++++
 net/core/page_pool.c    | 35 +++++++++++++++++++++++++++++++++++
 net/core/xdp.c          |  9 ++-------
 3 files changed, 63 insertions(+), 7 deletions(-)
include/net/page_pool.h +26 -0
index 81d7773f96cd..b5b195305346 100644
@@ -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 */
net/core/page_pool.c +35 -0
index ef98372facf6..236c5ed3aa66 100644
@@ -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>

@@ -408,6 +410,39 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 }
 EXPORT_SYMBOL(page_pool_put_page);
 
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count)
+{
+	int i, len = 0;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = virt_to_head_page(data[i]);
+
+		if (likely(page_ref_count(page) == 1 &&
+			   pool_page_reusable(pool, page))) {
+			if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+				page_pool_dma_sync_for_device(pool, page, -1);
+
+			/* bulk pages for ptr_ring cache */
+			data[len++] = page;
+		} else {
+			page_pool_release_page(pool, page);
+			put_page(page);
+		}
+	}
+
+	/* Grab the producer spinlock for concurrent access to
+	 * ptr_ring page_pool cache
+	 */
+	page_pool_ring_lock(pool);
+	for (i = 0; i < len; i++) {
+		if (__ptr_ring_produce(&pool->ring, data[i]))
+			page_pool_return_page(pool, data[i]);
+	}
+	page_pool_ring_unlock(pool);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
 static void page_pool_empty_ring(struct page_pool *pool)
 {
 	struct page *page;
net/core/xdp.c +2 -7
index 66ac275a0360..ff7c801bd40c 100644
@@ -393,16 +393,11 @@ EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
 {
 	struct xdp_mem_allocator *xa = bq->xa;
-	int i;
 
-	if (unlikely(!xa))
+	if (unlikely(!xa || !bq->count))
 		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);
-	}
+	page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
 	bq->count = 0;
 }
 EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
Signature · 1 line
2.26.2
author
#5 lore raw

PATCH v2 3/4 net: mvpp2: add xdp tx return bulking support

In reply to Lorenzo Bianconi

Convert mvpp2 driver to xdp_return_frame_bulk APIs.

XDP_REDIRECT (upstream codepath): 1.79Mpps XDP_REDIRECT (upstream codepath + bulking APIs): 1.93Mpps

Tested-by Matteo Croce <[email protected]>
Signed-off-by Lorenzo Bianconi <[email protected]>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +4 -1
index f6616c8933ca..04f24d1d72ab 100644
@@ -2440,8 +2440,10 @@ 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;
 
+	bq.xa = NULL;
 	for (i = 0; i < num; i++) {
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;

@@ -2454,10 +2456,11 @@ 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);
 }
 
 static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port,
Signature · 1 line
2.26.2
author
#6 lore raw

PATCH v2 4/4 net: mlx5: add xdp tx return bulking support

In reply to Lorenzo Bianconi

Convert mlx5 driver to xdp_return_frame_bulk APIs.

XDP_REDIRECT (upstream codepath): 8.5Mpps XDP_REDIRECT (upstream codepath + bulking APIs): 10.1Mpps

Signed-off-by Lorenzo Bianconi <[email protected]>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +4 -1
index ae90d533a350..5fdfbf390d5c 100644
@@ -369,8 +369,10 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				  bool recycle)
 {
 	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	struct xdp_frame_bulk bq;
 	u16 i;
 
+	bq.xa = NULL;
 	for (i = 0; i < wi->num_pkts; i++) {
 		struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 

@@ -379,7 +381,7 @@ 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 */

@@ -393,6 +395,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 			WARN_ON_ONCE(true);
 		}
 	}
+	xdp_flush_frame_bulk(&bq);
 }
 
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
Signature · 1 line
2.26.2