Merge branch 'thunderx-DMAC-filtering'

Vadim Lomovtsev says:

====================
net: thunderx: implement DMAC filtering support

By default CN88XX BGX accepts all incoming multicast and broadcast
packets and filtering is disabled. The nic driver doesn't provide
an ability to change such behaviour.

This series is to implement DMAC filtering management for CN88XX
nic driver allowing user to enable/disable filtering and configure
specific MAC addresses to filter traffic.

Changes from v1:
build issues:
 - update code in order to address compiler warnings;
checkpatch.pl reported issues:
 - update code in order to fit 80 symbols length;
 - update commit descriptions in order to fit 80 symbols length;
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/cavium/thunder/nic.h

@@ -265,6 +265,22 @@ struct nicvf_drv_stats {
 
 struct cavium_ptp;
 
+struct xcast_addr {
+	struct list_head list;
+	u64              addr;
+};
+
+struct xcast_addr_list {
+	struct list_head list;
+	int              count;
+};
+
+struct nicvf_work {
+	struct delayed_work    work;
+	u8                     mode;
+	struct xcast_addr_list *mc;
+};
+
 struct nicvf {
 	struct nicvf		*pnicvf;
 	struct net_device	*netdev;
@@ -313,6 +329,7 @@ struct nicvf {
 	struct nicvf_pfc	pfc;
 	struct tasklet_struct	qs_err_task;
 	struct work_struct	reset_task;
+	struct nicvf_work       rx_mode_work;
 
 	/* PTP timestamp */
 	struct cavium_ptp	*ptp_clock;
@@ -403,6 +420,9 @@ struct nicvf {
 #define	NIC_MBOX_MSG_PTP_CFG		0x19	/* HW packet timestamp */
 #define	NIC_MBOX_MSG_CFG_DONE		0xF0	/* VF configuration done */
 #define	NIC_MBOX_MSG_SHUTDOWN		0xF1	/* VF is being shutdown */
+#define	NIC_MBOX_MSG_RESET_XCAST	0xF2    /* Reset DCAM filtering mode */
+#define	NIC_MBOX_MSG_ADD_MCAST		0xF3    /* Add MAC to DCAM filters */
+#define	NIC_MBOX_MSG_SET_XCAST		0xF4    /* Set MCAST/BCAST RX mode */
 
 struct nic_cfg_msg {
 	u8    msg;
@@ -556,6 +576,14 @@ struct set_ptp {
 	bool  enable;
 };
 
+struct xcast {
+	u8    msg;
+	union {
+		u8    mode;
+		u64   mac;
+	} data;
+};
+
 /* 128 bit shared memory between PF and each VF */
 union nic_mbx {
 	struct { u8 msg; }	msg;
@@ -576,6 +604,7 @@ union nic_mbx {
 	struct reset_stat_cfg	reset_stat;
 	struct pfc		pfc;
 	struct set_ptp		ptp;
+	struct xcast            xcast;
 };
 
 #define NIC_NODE_ID_MASK	0x03

drivers/net/ethernet/cavium/thunder/nic_main.c

@@ -21,6 +21,8 @@
 #define DRV_NAME	"nicpf"
 #define DRV_VERSION	"1.0"
 
+#define NIC_VF_PER_MBX_REG      64
+
 struct hw_info {
 	u8		bgx_cnt;
 	u8		chans_per_lmac;
@@ -1072,6 +1074,40 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_PTP_CFG:
 		nic_config_timestamp(nic, vf, &mbx.ptp);
 		break;
+	case NIC_MBOX_MSG_RESET_XCAST:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		bgx_reset_xcast_mode(nic->node, bgx, lmac,
+				     vf < NIC_VF_PER_MBX_REG ? vf :
+				     vf - NIC_VF_PER_MBX_REG);
+		break;
+
+	case NIC_MBOX_MSG_ADD_MCAST:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		bgx_set_dmac_cam_filter(nic->node, bgx, lmac,
+					mbx.xcast.data.mac,
+					vf < NIC_VF_PER_MBX_REG ? vf :
+					vf - NIC_VF_PER_MBX_REG);
+		break;
+
+	case NIC_MBOX_MSG_SET_XCAST:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode);
+		break;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
@@ -1094,7 +1130,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
 	struct nicpf *nic = (struct nicpf *)nic_irq;
 	int mbx;
 	u64 intr;
-	u8  vf, vf_per_mbx_reg = 64;
+	u8  vf;
 
 	if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0))
 		mbx = 0;
@@ -1103,12 +1139,13 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
 
 	intr = nic_reg_read(nic, NIC_PF_MAILBOX_INT + (mbx << 3));
 	dev_dbg(&nic->pdev->dev, "PF interrupt Mbox%d 0x%llx\n", mbx, intr);
-	for (vf = 0; vf < vf_per_mbx_reg; vf++) {
+	for (vf = 0; vf < NIC_VF_PER_MBX_REG; vf++) {
 		if (intr & (1ULL << vf)) {
 			dev_dbg(&nic->pdev->dev, "Intr from VF %d\n",
-				vf + (mbx * vf_per_mbx_reg));
+				vf + (mbx * NIC_VF_PER_MBX_REG));
 
-			nic_handle_mbx_intr(nic, vf + (mbx * vf_per_mbx_reg));
+			nic_handle_mbx_intr(nic, vf +
+					    (mbx * NIC_VF_PER_MBX_REG));
 			nic_clear_mbx_intr(nic, vf, mbx);
 		}
 	}

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -21,6 +21,7 @@
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
 #include <linux/net_tstamp.h>
+#include <linux/workqueue.h>
 
 #include "nic_reg.h"
 #include "nic.h"
@@ -67,6 +68,9 @@ module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
+/* workqueue for handling kernel ndo_set_rx_mode() calls */
+static struct workqueue_struct *nicvf_rx_mode_wq;
+
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -1919,6 +1923,100 @@ static int nicvf_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 	}
 }
 
+static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
+{
+	struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
+						  work.work);
+	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
+	union nic_mbx mbx = {};
+	struct xcast_addr *xaddr, *next;
+
+	if (!vf_work)
+		return;
+
+	/* From the inside of VM code flow we have only 128 bits memory
+	 * available to send message to host's PF, so send all mc addrs
+	 * one by one, starting from flush command in case if kernel
+	 * requests to configure specific MAC filtering
+	 */
+
+	/* flush DMAC filters and reset RX mode */
+	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	if (vf_work->mode & BGX_XCAST_MCAST_FILTER) {
+		/* once enabling filtering, we need to signal to PF to add
+		 * its' own LMAC to the filter to accept packets for it.
+		 */
+		mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
+		mbx.xcast.data.mac = 0;
+		nicvf_send_msg_to_pf(nic, &mbx);
+	}
+
+	/* check if we have any specific MACs to be added to PF DMAC filter */
+	if (vf_work->mc) {
+		/* now go through kernel list of MACs and add them one by one */
+		list_for_each_entry_safe(xaddr, next,
+					 &vf_work->mc->list, list) {
+			mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
+			mbx.xcast.data.mac = xaddr->addr;
+			nicvf_send_msg_to_pf(nic, &mbx);
+
+			/* after receiving ACK from PF release memory */
+			list_del(&xaddr->list);
+			kfree(xaddr);
+			vf_work->mc->count--;
+		}
+		kfree(vf_work->mc);
+	}
+
+	/* and finally set rx mode for PF accordingly */
+	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
+	mbx.xcast.data.mode = vf_work->mode;
+
+	nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static void nicvf_set_rx_mode(struct net_device *netdev)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct netdev_hw_addr *ha;
+	struct xcast_addr_list *mc_list = NULL;
+	u8 mode = 0;
+
+	if (netdev->flags & IFF_PROMISC) {
+		mode = BGX_XCAST_BCAST_ACCEPT | BGX_XCAST_MCAST_ACCEPT;
+	} else {
+		if (netdev->flags & IFF_BROADCAST)
+			mode |= BGX_XCAST_BCAST_ACCEPT;
+
+		if (netdev->flags & IFF_ALLMULTI) {
+			mode |= BGX_XCAST_MCAST_ACCEPT;
+		} else if (netdev->flags & IFF_MULTICAST) {
+			mode |= BGX_XCAST_MCAST_FILTER;
+			/* here we need to copy mc addrs */
+			if (netdev_mc_count(netdev)) {
+				struct xcast_addr *xaddr;
+
+				mc_list = kmalloc(sizeof(*mc_list), GFP_ATOMIC);
+				INIT_LIST_HEAD(&mc_list->list);
+				netdev_hw_addr_list_for_each(ha, &netdev->mc) {
+					xaddr = kmalloc(sizeof(*xaddr),
+							GFP_ATOMIC);
+					xaddr->addr =
+						ether_addr_to_u64(ha->addr);
+					list_add_tail(&xaddr->list,
+						      &mc_list->list);
+					mc_list->count++;
+				}
+			}
+		}
+	}
+	nic->rx_mode_work.mc = mc_list;
+	nic->rx_mode_work.mode = mode;
+	queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 2 * HZ);
+}
+
 static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_open		= nicvf_open,
 	.ndo_stop		= nicvf_stop,
@@ -1931,6 +2029,7 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_set_features       = nicvf_set_features,
 	.ndo_bpf		= nicvf_xdp,
 	.ndo_do_ioctl           = nicvf_ioctl,
+	.ndo_set_rx_mode        = nicvf_set_rx_mode,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -2071,6 +2170,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
+	INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(dev, "Failed to register netdevice\n");
@@ -2109,6 +2210,8 @@ static void nicvf_remove(struct pci_dev *pdev)
 	nic = netdev_priv(netdev);
 	pnetdev = nic->pnicvf->netdev;
 
+	cancel_delayed_work_sync(&nic->rx_mode_work.work);
+
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
 	 */
@@ -2140,12 +2243,17 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-
+	nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic",
+						   WQ_MEM_RECLAIM);
 	return pci_register_driver(&nicvf_driver);
 }
 
 static void __exit nicvf_cleanup_module(void)
 {
+	if (nicvf_rx_mode_wq) {
+		destroy_workqueue(nicvf_rx_mode_wq);
+		nicvf_rx_mode_wq = NULL;
+	}
 	pci_unregister_driver(&nicvf_driver);
 }