iavf: switch to Page Pool

Now that the IAVF driver simply uses dev_alloc_page() + free_page() with
no custom recycling logics, it can easily be switched to using Page
Pool / libeth API instead.
This allows to removing the whole dancing around headroom, HW buffer
size, and page order. All DMA-for-device is now done in the PP core,
for-CPU -- in the libeth helper.
Use skb_mark_for_recycle() to bring back the recycling and restore the
performance. Speaking of performance: on par with the baseline and
faster with the PP optimization series applied. But the memory usage for
1500b MTU is now almost 2x lower (x86_64) thanks to allocating a page
every second descriptor.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/iavf/iavf_main.c

 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/net/intel/libie/rx.h>
+
 #include "iavf.h"
 #include "iavf_prototype.h"
 /* All iavf tracepoints are defined by the include below, which must
@@ -45,6 +47,7 @@ MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);
 MODULE_ALIAS("i40evf");
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver");
+MODULE_IMPORT_NS(LIBETH);
 MODULE_IMPORT_NS(LIBIE);
 MODULE_LICENSE("GPL v2");
 
@@ -1586,7 +1589,6 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter)
 		rx_ring = &adapter->rx_rings[i];
 		rx_ring->queue_index = i;
 		rx_ring->netdev = adapter->netdev;
-		rx_ring->dev = &adapter->pdev->dev;
 		rx_ring->count = adapter->rx_desc_count;
 		rx_ring->itr_setting = IAVF_ITR_RX_DEF;
 	}
@@ -2613,9 +2615,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	iavf_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
-	/* MTU range: 68 - 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD;
+	netdev->max_mtu = LIBIE_MAX_MTU;
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",

drivers/net/ethernet/intel/iavf/iavf_txrx.h

@@ -80,18 +80,8 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-/* Supported Rx Buffer Sizes (a multiple of 128) */
-#define IAVF_RXBUFFER_3072  3072  /* Used for large frames w/ padding */
-#define IAVF_MAX_RXBUFFER   9728  /* largest size for single descriptor */
-
-#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
 #define iavf_rx_desc iavf_32byte_rx_desc
 
-#define IAVF_RX_DMA_ATTR \
-	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
-
-#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-
 /**
  * iavf_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -210,12 +200,6 @@ struct iavf_tx_buffer {
 	u32 tx_flags;
 };
 
-struct iavf_rx_buffer {
-	dma_addr_t dma;
-	struct page *page;
-	__u32 page_offset;
-};
-
 struct iavf_queue_stats {
 	u64 packets;
 	u64 bytes;
@@ -251,13 +235,18 @@ struct iavf_rx_queue_stats {
 struct iavf_ring {
 	struct iavf_ring *next;		/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
-	struct device *dev;		/* Used for DMA mapping */
+	union {
+		struct page_pool *pp;	/* Used on Rx for buffer management */
+		struct device *dev;	/* Used on Tx for DMA mapping */
+	};
 	struct net_device *netdev;	/* netdev ring maps to */
 	union {
+		struct libeth_fqe *rx_fqes;
 		struct iavf_tx_buffer *tx_bi;
-		struct iavf_rx_buffer *rx_bi;
 	};
 	u8 __iomem *tail;
+	u32 truesize;
+
 	u16 queue_index;		/* Queue number of ring */
 
 	/* high bit set means dynamic, use accessors routines to read/write.
@@ -305,6 +294,8 @@ struct iavf_ring {
 					 * iavf_clean_rx_ring_irq() is called
 					 * for this ring.
 					 */
+
+	u32 rx_buf_len;
 } ____cacheline_internodealigned_in_smp;
 
 #define IAVF_ITR_ADAPTIVE_MIN_INC	0x0002
@@ -328,13 +319,6 @@ struct iavf_ring_container {
 #define iavf_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
-static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring)
-{
-	return 0;
-}
-
-#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring))
-
 bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count);
 netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring);

drivers/net/ethernet/intel/iavf/iavf_virtchnl.c

 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/net/intel/libie/rx.h>
+
 #include "iavf.h"
 #include "iavf_prototype.h"
 
@@ -268,13 +270,13 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 void iavf_configure_queues(struct iavf_adapter *adapter)
 {
 	struct virtchnl_vsi_queue_config_info *vqci;
-	int i, max_frame = adapter->vf_res->max_mtu;
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
+	u32 i, max_frame;
 	size_t len;
 
-	if (max_frame > IAVF_MAX_RXBUFFER || !max_frame)
-		max_frame = IAVF_MAX_RXBUFFER;
+	max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
+	max_frame = min_not_zero(adapter->vf_res->max_mtu, max_frame);
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -304,7 +306,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		vqpi->rxq.ring_len = adapter->rx_rings[i].count;
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
 		vqpi->rxq.max_pkt_size = max_frame;
-		vqpi->rxq.databuffer_size = IAVF_RXBUFFER_3072;
+		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);

include/linux/net/intel/libie/rx.h

@@ -6,6 +6,23 @@
 
 #include <net/libeth/rx.h>
 
+/* Rx buffer management */
+
+/* The largest size for a single descriptor as per HW */
+#define LIBIE_MAX_RX_BUF_LEN	9728U
+/* "True" HW-writeable space: minimum from SW and HW values */
+#define LIBIE_RX_BUF_LEN(hr)	min_t(u32, LIBETH_RX_PAGE_LEN(hr),	\
+				      LIBIE_MAX_RX_BUF_LEN)
+
+/* The maximum frame size as per HW (S/G) */
+#define __LIBIE_MAX_RX_FRM_LEN	16382U
+/* ATST, HW can chain up to 5 Rx descriptors */
+#define LIBIE_MAX_RX_FRM_LEN(hr)					\
+	min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5)
+/* Maximum frame size minus LL overhead */
+#define LIBIE_MAX_MTU							\
+	(LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN)
+
 /* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed
  * bitfield struct.
  */