Merge branch 'nfp-cleanups-and-RX-path-rewrite'

Jakub Kicinski says:

====================
nfp: cleanups and RX path rewrite

This series lays groundwork for upcoming XDP support by updating
the RX path not to pre-allocate sk_buffs.  I start with few
cleanups, removal of NFP3200-related code being the most significant.
Patch 7 moves to alloc_frag() and build_skb() APIs.  Again, a number
of small cleanups follow.  The set ends with adding support for
different number of RX and TX rings.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/nfp_net.h

@@ -75,7 +75,6 @@
 
 /* Default size for MTU and freelist buffer sizes */
 #define NFP_NET_DEFAULT_MTU		1500
-#define NFP_NET_DEFAULT_RX_BUFSZ	2048
 
 /* Maximum number of bytes prepended to a packet */
 #define NFP_NET_MAX_PREPEND		64
@@ -88,6 +87,9 @@
 /* Queue/Ring definitions */
 #define NFP_NET_MAX_TX_RINGS	64	/* Max. # of Tx rings per device */
 #define NFP_NET_MAX_RX_RINGS	64	/* Max. # of Rx rings per device */
+#define NFP_NET_MAX_R_VECS	(NFP_NET_MAX_TX_RINGS > NFP_NET_MAX_RX_RINGS ? \
+				 NFP_NET_MAX_TX_RINGS : NFP_NET_MAX_RX_RINGS)
+#define NFP_NET_MAX_IRQS	(NFP_NET_NON_Q_VECTORS + NFP_NET_MAX_R_VECS)
 
 #define NFP_NET_MIN_TX_DESCS	256	/* Min. # of Tx descs per ring */
 #define NFP_NET_MIN_RX_DESCS	256	/* Min. # of Rx descs per ring */
@@ -102,6 +104,10 @@
 /* Offload definitions */
 #define NFP_NET_N_VXLAN_PORTS	(NFP_NET_CFG_VXLAN_SZ / sizeof(__be16))
 
+#define NFP_NET_RX_BUF_HEADROOM	(NET_SKB_PAD + NET_IP_ALIGN)
+#define NFP_NET_RX_BUF_NON_DATA	(NFP_NET_RX_BUF_HEADROOM +		\
+				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
 /* Forward declarations */
 struct nfp_net;
 struct nfp_net_r_vector;
@@ -278,11 +284,11 @@ struct nfp_net_rx_hash {
 
 /**
  * struct nfp_net_rx_buf - software RX buffer descriptor
- * @skb:	sk_buff associated with this buffer
+ * @frag:	page fragment buffer
  * @dma_addr:	DMA mapping address of the buffer
  */
 struct nfp_net_rx_buf {
-	struct sk_buff *skb;
+	void *frag;
 	dma_addr_t dma_addr;
 };
 
@@ -421,7 +427,6 @@ struct nfp_stat_pair {
  * @netdev:             Backpointer to net_device structure
  * @nfp_fallback:       Is the driver used in fallback mode?
  * @is_vf:              Is the driver attached to a VF?
- * @is_nfp3200:         Is the driver for a NFP-3200 card?
  * @fw_loaded:          Is the firmware loaded?
  * @bpf_offload_skip_sw:  Offloaded BPF program will not be rerun by cls_bpf
  * @ctrl:               Local copy of the control register/word.
@@ -451,7 +456,7 @@ struct nfp_stat_pair {
  * @rxd_cnt:            Size of the RX ring in number of descriptors
  * @tx_rings:           Array of pre-allocated TX ring structures
  * @rx_rings:           Array of pre-allocated RX ring structures
- * @num_irqs:	        Number of allocated interrupt vectors
+ * @max_r_vecs:	        Number of allocated interrupt vectors for RX/TX
  * @num_r_vecs:         Number of used ring vectors
  * @r_vecs:             Pre-allocated array of ring vectors
  * @irq_entries:        Pre-allocated array of MSI-X entries
@@ -487,7 +492,6 @@ struct nfp_net {
 
 	unsigned nfp_fallback:1;
 	unsigned is_vf:1;
-	unsigned is_nfp3200:1;
 	unsigned fw_loaded:1;
 	unsigned bpf_offload_skip_sw:1;
 
@@ -524,11 +528,11 @@ struct nfp_net {
 	struct timer_list rx_filter_stats_timer;
 	spinlock_t rx_filter_lock;
 
-	int max_tx_rings;
-	int max_rx_rings;
+	unsigned int max_tx_rings;
+	unsigned int max_rx_rings;
 
-	int num_tx_rings;
-	int num_rx_rings;
+	unsigned int num_tx_rings;
+	unsigned int num_rx_rings;
 
 	int stride_tx;
 	int stride_rx;
@@ -536,11 +540,10 @@ struct nfp_net {
 	int txd_cnt;
 	int rxd_cnt;
 
-	u8 num_irqs;
-	u8 num_r_vecs;
-	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_TX_RINGS];
-	struct msix_entry irq_entries[NFP_NET_NON_Q_VECTORS +
-				      NFP_NET_MAX_TX_RINGS];
+	unsigned int max_r_vecs;
+	unsigned int num_r_vecs;
+	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
+	struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
 
 	irq_handler_t lsc_handler;
 	char lsc_name[IFNAMSIZ + 8];
@@ -593,16 +596,13 @@ static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
 	writeb(val, nn->ctrl_bar + off);
 }
 
-/* NFP-3200 can't handle 16-bit accesses too well */
 static inline u16 nn_readw(struct nfp_net *nn, int off)
 {
-	WARN_ON_ONCE(nn->is_nfp3200);
 	return readw(nn->ctrl_bar + off);
 }
 
 static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
 {
-	WARN_ON_ONCE(nn->is_nfp3200);
 	writew(val, nn->ctrl_bar + off);
 }
 
@@ -650,7 +650,7 @@ static inline void nn_pci_flush(struct nfp_net *nn)
 #define NFP_QCP_QUEUE_STS_HI			0x000c
 #define NFP_QCP_QUEUE_STS_HI_WRITEPTR_mask	0x3ffff
 
-/* The offset of a QCP queues in the PCIe Target (same on NFP3200 and NFP6000 */
+/* The offset of a QCP queues in the PCIe Target */
 #define NFP_PCIE_QUEUE(_q) (0x80000 + (NFP_QCP_QUEUE_ADDR_SZ * ((_q) & 0xff)))
 
 /* nfp_qcp_ptr - Read or Write Pointer of a queue */
@@ -757,8 +757,9 @@ extern const char nfp_net_driver_version[];
 void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 			    void __iomem *ctrl_bar);
 
-struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
-				     int max_tx_rings, int max_rx_rings);
+struct nfp_net *
+nfp_net_netdev_alloc(struct pci_dev *pdev,
+		     unsigned int max_tx_rings, unsigned int max_rx_rings);
 void nfp_net_netdev_free(struct nfp_net *nn);
 int nfp_net_netdev_init(struct net_device *netdev);
 void nfp_net_netdev_clean(struct net_device *netdev);

drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h

@@ -50,7 +50,7 @@
 /**
  * Configuration BAR size.
  *
- * The configuration BAR is 8K in size, but on the NFP6000, due to
+ * The configuration BAR is 8K in size, but due to
  * THB-350, 32k needs to be reserved.
  */
 #define NFP_NET_CFG_BAR_SZ              (32 * 1024)
@@ -186,18 +186,13 @@
 #define NFP_NET_CFG_START_RXQ           0x004c
 
 /**
- * NFP-3200 workaround (0x0050 - 0x0058)
- * @NFP_NET_CFG_SPARE_ADDR:  DMA address for ME code to use (e.g. YDS-155 fix)
- */
-#define NFP_NET_CFG_SPARE_ADDR          0x0050
-/**
- * NFP6000/NFP4000 - Prepend configuration
+ * Prepend configuration
  */
 #define NFP_NET_CFG_RX_OFFSET		0x0050
 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC		0	/* Prepend mode */
 
 /**
- * NFP6000/NFP4000 - VXLAN/UDP encap configuration
+ * VXLAN/UDP encap configuration
  * @NFP_NET_CFG_VXLAN_PORT:	Base address of table of tunnels' UDP dst ports
  * @NFP_NET_CFG_VXLAN_SZ:	Size of the UDP port table in bytes
  */
@@ -205,7 +200,7 @@
 #define NFP_NET_CFG_VXLAN_SZ		  0x0008
 
 /**
- * NFP6000 - BPF section
+ * BPF section
  * @NFP_NET_CFG_BPF_ABI:	BPF ABI version
  * @NFP_NET_CFG_BPF_CAP:	BPF capabilities
  * @NFP_NET_CFG_BPF_MAX_LEN:	Maximum size of JITed BPF code in bytes

drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c

@@ -44,8 +44,8 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_rx_ring *rx_ring;
 	struct nfp_net_rx_desc *rxd;
-	struct sk_buff *skb;
 	struct nfp_net *nn;
+	void *frag;
 	int i;
 
 	rtnl_lock();
@@ -73,10 +73,9 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 		seq_printf(file, "%04d: 0x%08x 0x%08x", i,
 			   rxd->vals[0], rxd->vals[1]);
 
-		skb = READ_ONCE(rx_ring->rxbufs[i].skb);
-		if (skb)
-			seq_printf(file, " skb->head=%p skb->data=%p",
-				   skb->head, skb->data);
+		frag = READ_ONCE(rx_ring->rxbufs[i].frag);
+		if (frag)
+			seq_printf(file, " frag=%p", frag);
 
 		if (rx_ring->rxbufs[i].dma_addr)
 			seq_printf(file, " dma_addr=%pad",

drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c

@@ -63,9 +63,7 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn)
 	u8 mac_addr[ETH_ALEN];
 
 	put_unaligned_be32(nn_readl(nn, NFP_NET_CFG_MACADDR + 0), &mac_addr[0]);
-	/* We can't do readw for NFP-3200 compatibility */
-	put_unaligned_be16(nn_readl(nn, NFP_NET_CFG_MACADDR + 4) >> 16,
-			   &mac_addr[4]);
+	put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]);
 
 	if (!is_valid_ether_addr(mac_addr)) {
 		eth_hw_addr_random(nn->netdev);
@@ -86,7 +84,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	int tx_bar_no, rx_bar_no;
 	u8 __iomem *ctrl_bar;
 	struct nfp_net *nn;
-	int is_nfp3200;
 	u32 startq;
 	int stride;
 	int err;
@@ -101,15 +98,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 		goto err_pci_disable;
 	}
 
-	switch (pdev->device) {
-	case PCI_DEVICE_NFP6000VF:
-		is_nfp3200 = 0;
-		break;
-	default:
-		err = -ENODEV;
-		goto err_pci_regions;
-	}
-
 	pci_set_master(pdev);
 
 	err = dma_set_mask_and_coherent(&pdev->dev,
@@ -149,15 +137,9 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	} else {
 		switch (fw_ver.major) {
 		case 1 ... 4:
-			if (is_nfp3200) {
-				stride = 2;
-				tx_bar_no = NFP_NET_Q0_BAR;
-				rx_bar_no = NFP_NET_Q1_BAR;
-			} else {
-				stride = 4;
-				tx_bar_no = NFP_NET_Q0_BAR;
-				rx_bar_no = tx_bar_no;
-			}
+			stride = 4;
+			tx_bar_no = NFP_NET_Q0_BAR;
+			rx_bar_no = tx_bar_no;
 			break;
 		default:
 			dev_err(&pdev->dev, "Unsupported Firmware ABI %d.%d.%d.%d\n",
@@ -189,20 +171,10 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 		max_rx_rings = (rx_bar_sz / NFP_QCP_QUEUE_ADDR_SZ) / 2;
 	}
 
-	/* XXX Implement a workaround for THB-350 here.  Ideally, we
-	 * have a different PCI ID for A rev VFs.
-	 */
-	switch (pdev->device) {
-	case PCI_DEVICE_NFP6000VF:
-		startq = readl(ctrl_bar + NFP_NET_CFG_START_TXQ);
-		tx_bar_off = NFP_PCIE_QUEUE(startq);
-		startq = readl(ctrl_bar + NFP_NET_CFG_START_RXQ);
-		rx_bar_off = NFP_PCIE_QUEUE(startq);
-		break;
-	default:
-		err = -ENODEV;
-		goto err_ctrl_unmap;
-	}
+	startq = readl(ctrl_bar + NFP_NET_CFG_START_TXQ);
+	tx_bar_off = NFP_PCIE_QUEUE(startq);
+	startq = readl(ctrl_bar + NFP_NET_CFG_START_RXQ);
+	rx_bar_off = NFP_PCIE_QUEUE(startq);
 
 	/* Allocate and initialise the netdev */
 	nn = nfp_net_netdev_alloc(pdev, max_tx_rings, max_rx_rings);
@@ -214,7 +186,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	nn->fw_ver = fw_ver;
 	nn->ctrl_bar = ctrl_bar;
 	nn->is_vf = 1;
-	nn->is_nfp3200 = is_nfp3200;
 	nn->stride_tx = stride;
 	nn->stride_rx = stride;