Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 179 insertions, 19 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 6e0c031..b3a5947 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -28,6 +28,11 @@ struct nicpf {
 	u8			num_vf_en;      /* No of VF enabled */
 	bool			vf_enabled[MAX_NUM_VFS_SUPPORTED];
 	void __iomem		*reg_base;       /* Register start address */
+	u8			num_sqs_en;	/* Secondary qsets enabled */
+	u64			nicvf[MAX_NUM_VFS_SUPPORTED];
+	u8			vf_sqs[MAX_NUM_VFS_SUPPORTED][MAX_SQS_PER_VF];
+	u8			pqs_vf[MAX_NUM_VFS_SUPPORTED];
+	bool			sqs_used[MAX_NUM_VFS_SUPPORTED];
 	struct pkind_cfg	pkind;
 #define	NIC_SET_VF_LMAC_MAP(bgx, lmac)	(((bgx & 0xF) << 4) | (lmac & 0xF))
 #define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
@@ -139,14 +144,19 @@ static void nic_mbx_send_ready(struct nicpf *nic, int vf)
 
 	mbx.nic_cfg.tns_mode = NIC_TNS_BYPASS_MODE;
 
-	bgx_idx = 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]);
-
-	mac = bgx_get_lmac_mac(nic->node, bgx_idx, lmac);
-	if (mac)
-		ether_addr_copy((u8 *)&mbx.nic_cfg.mac_addr, mac);
+	if (vf < MAX_LMAC) {
+		bgx_idx = 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]);
 
+		mac = bgx_get_lmac_mac(nic->node, bgx_idx, lmac);
+		if (mac)
+			ether_addr_copy((u8 *)&mbx.nic_cfg.mac_addr, mac);
+	}
+	mbx.nic_cfg.sqs_mode = (vf >= nic->num_vf_en) ? true : false;
 	mbx.nic_cfg.node_id = nic->node;
+
+	mbx.nic_cfg.loopback_supported = vf < MAX_LMAC;
+
 	nic_send_msg_to_vf(nic, vf, &mbx);
 }
 
@@ -329,6 +339,10 @@ static void nic_init_hw(struct nicpf *nic)
 
 	/* Timer config */
 	nic_reg_write(nic, NIC_PF_INTR_TIMER_CFG, NICPF_CLK_PER_INT_TICK);
+
+	/* Enable VLAN ethertype matching and stripping */
+	nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7,
+		      (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q);
 }
 
 /* Channel parse index configuration */
@@ -429,6 +443,12 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
 	qset = cfg->vf_id;
 
 	for (; rssi < (rssi_base + cfg->tbl_len); rssi++) {
+		u8 svf = cfg->ind_tbl[idx] >> 3;
+
+		if (svf)
+			qset = nic->vf_sqs[cfg->vf_id][svf - 1];
+		else
+			qset = cfg->vf_id;
 		nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3),
 			      (qset << 3) | (cfg->ind_tbl[idx] & 0x7));
 		idx++;
@@ -452,19 +472,31 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
  * VNIC6-SQ0 -> TL4(528) -> TL3[132] -> TL2[33] -> TL1[1] -> BGX1
  * VNIC7-SQ0 -> TL4(536) -> TL3[134] -> TL2[33] -> TL1[1] -> BGX1
  */
-static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u8 sq_idx)
+static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
+			       struct sq_cfg_msg *sq)
 {
 	u32 bgx, lmac, chan;
 	u32 tl2, tl3, tl4;
 	u32 rr_quantum;
+	u8 sq_idx = sq->sq_num;
+	u8 pqs_vnic;
+
+	if (sq->sqs_mode)
+		pqs_vnic = nic->pqs_vf[vnic];
+	else
+		pqs_vnic = vnic;
+
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[pqs_vnic]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[pqs_vnic]);
 
-	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
-	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
 	/* 24 bytes for FCS, IPG and preamble */
 	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
 
 	tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
 	tl4 += sq_idx;
+	if (sq->sqs_mode)
+		tl4 += vnic * 8;
+
 	tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
 	nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
 		      ((u64)vnic << NIC_QS_ID_SHIFT) |
@@ -485,6 +517,86 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u8 sq_idx)
 	nic_reg_write(nic, NIC_PF_TL2_0_63_PRI | (tl2 << 3), 0x00);
 }
 
+/* Send primary nicvf pointer to secondary QS's VF */
+static void nic_send_pnicvf(struct nicpf *nic, int sqs)
+{
+	union nic_mbx mbx = {};
+
+	mbx.nicvf.msg = NIC_MBOX_MSG_PNICVF_PTR;
+	mbx.nicvf.nicvf = nic->nicvf[nic->pqs_vf[sqs]];
+	nic_send_msg_to_vf(nic, sqs, &mbx);
+}
+
+/* Send SQS's nicvf pointer to primary QS's VF */
+static void nic_send_snicvf(struct nicpf *nic, struct nicvf_ptr *nicvf)
+{
+	union nic_mbx mbx = {};
+	int sqs_id = nic->vf_sqs[nicvf->vf_id][nicvf->sqs_id];
+
+	mbx.nicvf.msg = NIC_MBOX_MSG_SNICVF_PTR;
+	mbx.nicvf.sqs_id = nicvf->sqs_id;
+	mbx.nicvf.nicvf = nic->nicvf[sqs_id];
+	nic_send_msg_to_vf(nic, nicvf->vf_id, &mbx);
+}
+
+/* Find next available Qset that can be assigned as a
+ * secondary Qset to a VF.
+ */
+static int nic_nxt_avail_sqs(struct nicpf *nic)
+{
+	int sqs;
+
+	for (sqs = 0; sqs < nic->num_sqs_en; sqs++) {
+		if (!nic->sqs_used[sqs])
+			nic->sqs_used[sqs] = true;
+		else
+			continue;
+		return sqs + nic->num_vf_en;
+	}
+	return -1;
+}
+
+/* Allocate additional Qsets for requested VF */
+static void nic_alloc_sqs(struct nicpf *nic, struct sqs_alloc *sqs)
+{
+	union nic_mbx mbx = {};
+	int idx, alloc_qs = 0;
+	int sqs_id;
+
+	if (!nic->num_sqs_en)
+		goto send_mbox;
+
+	for (idx = 0; idx < sqs->qs_count; idx++) {
+		sqs_id = nic_nxt_avail_sqs(nic);
+		if (sqs_id < 0)
+			break;
+		nic->vf_sqs[sqs->vf_id][idx] = sqs_id;
+		nic->pqs_vf[sqs_id] = sqs->vf_id;
+		alloc_qs++;
+	}
+
+send_mbox:
+	mbx.sqs_alloc.msg = NIC_MBOX_MSG_ALLOC_SQS;
+	mbx.sqs_alloc.vf_id = sqs->vf_id;
+	mbx.sqs_alloc.qs_count = alloc_qs;
+	nic_send_msg_to_vf(nic, sqs->vf_id, &mbx);
+}
+
+static int nic_config_loopback(struct nicpf *nic, struct set_loopback *lbk)
+{
+	int bgx_idx, lmac_idx;
+
+	if (lbk->vf_id > MAX_LMAC)
+		return -1;
+
+	bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lbk->vf_id]);
+	lmac_idx = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lbk->vf_id]);
+
+	bgx_lmac_internal_loopback(nic->node, bgx_idx, lmac_idx, lbk->enable);
+
+	return 0;
+}
+
 /* Interrupt handler to handle mailbox messages from VFs */
 static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 {
@@ -492,6 +604,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	u64 *mbx_data;
 	u64 mbx_addr;
 	u64 reg_addr;
+	u64 cfg;
 	int bgx, lmac;
 	int i;
 	int ret = 0;
@@ -512,15 +625,24 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	switch (mbx.msg.msg) {
 	case NIC_MBOX_MSG_READY:
 		nic_mbx_send_ready(nic, vf);
-		nic->link[vf] = 0;
-		nic->duplex[vf] = 0;
-		nic->speed[vf] = 0;
+		if (vf < MAX_LMAC) {
+			nic->link[vf] = 0;
+			nic->duplex[vf] = 0;
+			nic->speed[vf] = 0;
+		}
 		ret = 1;
 		break;
 	case NIC_MBOX_MSG_QS_CFG:
 		reg_addr = NIC_PF_QSET_0_127_CFG |
 			   (mbx.qs.num << NIC_QS_ID_SHIFT);
-		nic_reg_write(nic, reg_addr, mbx.qs.cfg);
+		cfg = mbx.qs.cfg;
+		/* Check if its a secondary Qset */
+		if (vf >= nic->num_vf_en) {
+			cfg = cfg & (~0x7FULL);
+			/* Assign this Qset to primary Qset's VF */
+			cfg |= nic->pqs_vf[vf];
+		}
+		nic_reg_write(nic, reg_addr, cfg);
 		break;
 	case NIC_MBOX_MSG_RQ_CFG:
 		reg_addr = NIC_PF_QSET_0_127_RQ_0_7_CFG |
@@ -548,9 +670,11 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 			   (mbx.sq.qs_num << NIC_QS_ID_SHIFT) |
 			   (mbx.sq.sq_num << NIC_Q_NUM_SHIFT);
 		nic_reg_write(nic, reg_addr, mbx.sq.cfg);
-		nic_tx_channel_cfg(nic, mbx.qs.num, mbx.sq.sq_num);
+		nic_tx_channel_cfg(nic, mbx.qs.num, &mbx.sq);
 		break;
 	case NIC_MBOX_MSG_SET_MAC:
+		if (vf >= nic->num_vf_en)
+			break;
 		lmac = mbx.mac.vf_id;
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]);
@@ -577,10 +701,28 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_SHUTDOWN:
 		/* First msg in VF teardown sequence */
 		nic->vf_enabled[vf] = false;
+		if (vf >= nic->num_vf_en)
+			nic->sqs_used[vf - nic->num_vf_en] = false;
+		nic->pqs_vf[vf] = 0;
 		break;
+	case NIC_MBOX_MSG_ALLOC_SQS:
+		nic_alloc_sqs(nic, &mbx.sqs_alloc);
+		goto unlock;
+	case NIC_MBOX_MSG_NICVF_PTR:
+		nic->nicvf[vf] = mbx.nicvf.nicvf;
+		break;
+	case NIC_MBOX_MSG_PNICVF_PTR:
+		nic_send_pnicvf(nic, vf);
+		goto unlock;
+	case NIC_MBOX_MSG_SNICVF_PTR:
+		nic_send_snicvf(nic, &mbx.nicvf);
+		goto unlock;
 	case NIC_MBOX_MSG_BGX_STATS:
 		nic_get_bgx_stats(nic, &mbx.bgx_stats);
 		goto unlock;
+	case NIC_MBOX_MSG_LOOPBACK:
+		ret = nic_config_loopback(nic, &mbx.lbk);
+		break;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
@@ -606,8 +748,7 @@ static void nic_mbx_intr_handler (struct nicpf *nic, int mbx)
 		if (intr & (1ULL << vf)) {
 			dev_dbg(&nic->pdev->dev, "Intr from VF %d\n",
 				vf + (mbx * vf_per_mbx_reg));
-			if ((vf + (mbx * vf_per_mbx_reg)) > nic->num_vf_en)
-				break;
+
 			nic_handle_mbx_intr(nic, vf + (mbx * vf_per_mbx_reg));
 			nic_clear_mbx_intr(nic, vf, mbx);
 		}
@@ -713,9 +854,24 @@ static void nic_unregister_interrupts(struct nicpf *nic)
 	nic_disable_msix(nic);
 }
 
+static int nic_num_sqs_en(struct nicpf *nic, int vf_en)
+{
+	int pos, sqs_per_vf = MAX_SQS_PER_VF_SINGLE_NODE;
+	u16 total_vf;
+
+	/* Check if its a multi-node environment */
+	if (nr_node_ids > 1)
+		sqs_per_vf = MAX_SQS_PER_VF;
+
+	pos = pci_find_ext_capability(nic->pdev, PCI_EXT_CAP_ID_SRIOV);
+	pci_read_config_word(nic->pdev, (pos + PCI_SRIOV_TOTAL_VF), &total_vf);
+	return min(total_vf - vf_en, vf_en * sqs_per_vf);
+}
+
 static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
 {
 	int pos = 0;
+	int vf_en;
 	int err;
 	u16 total_vf_cnt;
 
@@ -732,16 +888,20 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
 	if (!total_vf_cnt)
 		return 0;
 
-	err = pci_enable_sriov(pdev, nic->num_vf_en);
+	vf_en = nic->num_vf_en;
+	nic->num_sqs_en = nic_num_sqs_en(nic, nic->num_vf_en);
+	vf_en += nic->num_sqs_en;
+
+	err = pci_enable_sriov(pdev, vf_en);
 	if (err) {
 		dev_err(&pdev->dev, "SRIOV enable failed, num VF is %d\n",
-			nic->num_vf_en);
+			vf_en);
 		nic->num_vf_en = 0;
 		return err;
 	}
 
 	dev_info(&pdev->dev, "SRIOV enabled, number of VF available %d\n",
-		 nic->num_vf_en);
+		 vf_en);
 
 	nic->flags |= NIC_SRIOV_ENABLED;
 	return 0;