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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

5 files changed, 152 insertions, 62 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 34e9acea8747..83025bb4737c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -257,10 +257,13 @@ struct nicvf_drv_stats {
 	u64 rx_frames_jumbo;
 	u64 rx_drops;
 
+	u64 rcv_buffer_alloc_failures;
+
 	/* Tx */
 	u64 tx_frames_ok;
 	u64 tx_drops;
 	u64 tx_tso;
+	u64 tx_timeout;
 	u64 txq_stop;
 	u64 txq_wake;
 };
@@ -269,45 +272,54 @@ struct nicvf {
 	struct nicvf		*pnicvf;
 	struct net_device	*netdev;
 	struct pci_dev		*pdev;
+	void __iomem		*reg_base;
+	struct queue_set	*qs;
+	struct nicvf_cq_poll	*napi[8];
 	u8			vf_id;
-	u8			node;
-	u8			tns_mode:1;
-	u8			sqs_mode:1;
-	u8			loopback_supported:1;
+	u8			sqs_id;
+	bool                    sqs_mode;
 	bool			hw_tso;
-	u16			mtu;
-	struct queue_set	*qs;
+
+	/* Receive buffer alloc */
+	u32			rb_page_offset;
+	u16			rb_pageref;
+	bool			rb_alloc_fail;
+	bool			rb_work_scheduled;
+	struct page		*rb_page;
+	struct delayed_work	rbdr_work;
+	struct tasklet_struct	rbdr_task;
+
+	/* Secondary Qset */
+	u8			sqs_count;
 #define	MAX_SQS_PER_VF_SINGLE_NODE		5
 #define	MAX_SQS_PER_VF				11
-	u8			sqs_id;
-	u8			sqs_count; /* Secondary Qset count */
 	struct nicvf		*snicvf[MAX_SQS_PER_VF];
+
+	/* Queue count */
 	u8			rx_queues;
 	u8			tx_queues;
 	u8			max_queues;
-	void __iomem		*reg_base;
+
+	u8			node;
+	u8			cpi_alg;
+	u16			mtu;
 	bool			link_up;
 	u8			duplex;
 	u32			speed;
-	struct page		*rb_page;
-	u32			rb_page_offset;
-	bool			rb_alloc_fail;
-	bool			rb_work_scheduled;
-	struct delayed_work	rbdr_work;
-	struct tasklet_struct	rbdr_task;
-	struct tasklet_struct	qs_err_task;
-	struct tasklet_struct	cq_task;
-	struct nicvf_cq_poll	*napi[8];
+	bool			tns_mode;
+	bool			loopback_supported;
 	struct nicvf_rss_info	rss_info;
-	u8			cpi_alg;
+	struct tasklet_struct	qs_err_task;
+	struct work_struct	reset_task;
+
 	/* Interrupt coalescing settings */
 	u32			cq_coalesce_usecs;
-
 	u32			msg_enable;
+
+	/* Stats */
 	struct nicvf_hw_stats   hw_stats;
 	struct nicvf_drv_stats  drv_stats;
 	struct bgx_stats	bgx_stats;
-	struct work_struct	reset_task;
 
 	/* MSI-X  */
 	bool			msix_enabled;
@@ -315,6 +327,7 @@ struct nicvf {
 	struct msix_entry	msix_entries[NIC_VF_MSIX_VECTORS];
 	char			irq_name[NIC_VF_MSIX_VECTORS][20];
 	bool			irq_allocated[NIC_VF_MSIX_VECTORS];
+	cpumask_var_t		affinity_mask[NIC_VF_MSIX_VECTORS];
 
 	/* VF <-> PF mailbox communication */
 	bool			pf_acked;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index a12b2e38cf61..d2d8ef270142 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -89,9 +89,11 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
 	NICVF_DRV_STAT(rx_frames_1518),
 	NICVF_DRV_STAT(rx_frames_jumbo),
 	NICVF_DRV_STAT(rx_drops),
+	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
 	NICVF_DRV_STAT(tx_frames_ok),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_drops),
+	NICVF_DRV_STAT(tx_timeout),
 	NICVF_DRV_STAT(txq_stop),
 	NICVF_DRV_STAT(txq_wake),
 };
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index a009bc30dc4d..bfee298fc02a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -826,7 +826,7 @@ static irqreturn_t nicvf_intr_handler(int irq, void *cq_irq)
 	nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx);
 
 	/* Schedule NAPI */
-	napi_schedule(&cq_poll->napi);
+	napi_schedule_irqoff(&cq_poll->napi);
 
 	/* Clear interrupt */
 	nicvf_clear_intr(nic, NICVF_INTR_CQ, qidx);
@@ -897,6 +897,31 @@ static void nicvf_disable_msix(struct nicvf *nic)
 	}
 }
 
+static void nicvf_set_irq_affinity(struct nicvf *nic)
+{
+	int vec, cpu;
+	int irqnum;
+
+	for (vec = 0; vec < nic->num_vec; vec++) {
+		if (!nic->irq_allocated[vec])
+			continue;
+
+		if (!zalloc_cpumask_var(&nic->affinity_mask[vec], GFP_KERNEL))
+			return;
+		 /* CQ interrupts */
+		if (vec < NICVF_INTR_ID_SQ)
+			/* Leave CPU0 for RBDR and other interrupts */
+			cpu = nicvf_netdev_qidx(nic, vec) + 1;
+		else
+			cpu = 0;
+
+		cpumask_set_cpu(cpumask_local_spread(cpu, nic->node),
+				nic->affinity_mask[vec]);
+		irqnum = nic->msix_entries[vec].vector;
+		irq_set_affinity_hint(irqnum, nic->affinity_mask[vec]);
+	}
+}
+
 static int nicvf_register_interrupts(struct nicvf *nic)
 {
 	int irq, ret = 0;
@@ -942,8 +967,13 @@ static int nicvf_register_interrupts(struct nicvf *nic)
 	ret = request_irq(nic->msix_entries[irq].vector,
 			  nicvf_qs_err_intr_handler,
 			  0, nic->irq_name[irq], nic);
-	if (!ret)
-		nic->irq_allocated[irq] = true;
+	if (ret)
+		goto err;
+
+	nic->irq_allocated[irq] = true;
+
+	/* Set IRQ affinities */
+	nicvf_set_irq_affinity(nic);
 
 err:
 	if (ret)
@@ -961,6 +991,9 @@ static void nicvf_unregister_interrupts(struct nicvf *nic)
 		if (!nic->irq_allocated[irq])
 			continue;
 
+		irq_set_affinity_hint(nic->msix_entries[irq].vector, NULL);
+		free_cpumask_var(nic->affinity_mask[irq]);
+
 		if (irq < NICVF_INTR_ID_SQ)
 			free_irq(nic->msix_entries[irq].vector, nic->napi[irq]);
 		else
@@ -1394,6 +1427,7 @@ static void nicvf_tx_timeout(struct net_device *dev)
 		netdev_warn(dev, "%s: Transmit timed out, resetting\n",
 			    dev->name);
 
+	nic->drv_stats.tx_timeout++;
 	schedule_work(&nic->reset_task);
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 767347b1f631..fa05e347262f 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -18,6 +18,15 @@
 #include "q_struct.h"
 #include "nicvf_queues.h"
 
+static void nicvf_get_page(struct nicvf *nic)
+{
+	if (!nic->rb_pageref || !nic->rb_page)
+		return;
+
+	atomic_add(nic->rb_pageref, &nic->rb_page->_count);
+	nic->rb_pageref = 0;
+}
+
 /* Poll a register for a specific value */
 static int nicvf_poll_reg(struct nicvf *nic, int qidx,
 			  u64 reg, int bit_pos, int bits, int val)
@@ -78,32 +87,32 @@ static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem)
 static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 					 u32 buf_len, u64 **rbuf)
 {
-	int order = get_order(buf_len);
+	int order = (PAGE_SIZE <= 4096) ?  PAGE_ALLOC_COSTLY_ORDER : 0;
 
 	/* Check if request can be accomodated in previous allocated page */
-	if (nic->rb_page) {
-		if ((nic->rb_page_offset + buf_len + buf_len) >
-		    (PAGE_SIZE << order)) {
-			nic->rb_page = NULL;
-		} else {
-			nic->rb_page_offset += buf_len;
-			get_page(nic->rb_page);
-		}
+	if (nic->rb_page &&
+	    ((nic->rb_page_offset + buf_len) < (PAGE_SIZE << order))) {
+		nic->rb_pageref++;
+		goto ret;
 	}
 
+	nicvf_get_page(nic);
+	nic->rb_page = NULL;
+
 	/* Allocate a new page */
 	if (!nic->rb_page) {
 		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
 					   order);
 		if (!nic->rb_page) {
-			netdev_err(nic->netdev,
-				   "Failed to allocate new rcv buffer\n");
+			nic->drv_stats.rcv_buffer_alloc_failures++;
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
 	}
 
+ret:
 	*rbuf = (u64 *)((u64)page_address(nic->rb_page) + nic->rb_page_offset);
+	nic->rb_page_offset += buf_len;
 
 	return 0;
 }
@@ -159,6 +168,9 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 		desc = GET_RBDR_DESC(rbdr, idx);
 		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
 	}
+
+	nicvf_get_page(nic);
+
 	return 0;
 }
 
@@ -242,6 +254,8 @@ refill:
 		new_rb++;
 	}
 
+	nicvf_get_page(nic);
+
 	/* make sure all memory stores are done before ringing doorbell */
 	smp_wmb();
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 9df26c2263bc..967951582e03 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -886,7 +886,8 @@ static void bgx_get_qlm_mode(struct bgx *bgx)
 
 #ifdef CONFIG_ACPI
 
-static int acpi_get_mac_address(struct acpi_device *adev, u8 *dst)
+static int acpi_get_mac_address(struct device *dev, struct acpi_device *adev,
+				u8 *dst)
 {
 	u8 mac[ETH_ALEN];
 	int ret;
@@ -897,10 +898,13 @@ static int acpi_get_mac_address(struct acpi_device *adev, u8 *dst)
 		goto out;
 
 	if (!is_valid_ether_addr(mac)) {
+		dev_err(dev, "MAC address invalid: %pM\n", mac);
 		ret = -EINVAL;
 		goto out;
 	}
 
+	dev_info(dev, "MAC address set to: %pM\n", mac);
+
 	memcpy(dst, mac, ETH_ALEN);
 out:
 	return ret;
@@ -911,14 +915,15 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle,
 					 u32 lvl, void *context, void **rv)
 {
 	struct bgx *bgx = context;
+	struct device *dev = &bgx->pdev->dev;
 	struct acpi_device *adev;
 
 	if (acpi_bus_get_device(handle, &adev))
 		goto out;
 
-	acpi_get_mac_address(adev, bgx->lmac[bgx->lmac_count].mac);
+	acpi_get_mac_address(dev, adev, bgx->lmac[bgx->lmac_count].mac);
 
-	SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, &bgx->pdev->dev);
+	SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, dev);
 
 	bgx->lmac[bgx->lmac_count].lmacid = bgx->lmac_count;
 out:
@@ -968,38 +973,63 @@ static int bgx_init_acpi_phy(struct bgx *bgx)
 
 static int bgx_init_of_phy(struct bgx *bgx)
 {
-	struct device_node *np;
-	struct device_node *np_child;
+	struct fwnode_handle *fwn;
+	struct device_node *node = NULL;
 	u8 lmac = 0;
-	char bgx_sel[5];
-	const char *mac;
-
-	/* Get BGX node from DT */
-	snprintf(bgx_sel, 5, "bgx%d", bgx->bgx_id);
-	np = of_find_node_by_name(NULL, bgx_sel);
-	if (!np)
-		return -ENODEV;
-
-	for_each_child_of_node(np, np_child) {
-		struct device_node *phy_np = of_parse_phandle(np_child,
-							      "phy-handle", 0);
-		if (!phy_np)
-			continue;
-		bgx->lmac[lmac].phydev = of_phy_find_device(phy_np);
 
-		mac = of_get_mac_address(np_child);
+	device_for_each_child_node(&bgx->pdev->dev, fwn) {
+		struct phy_device *pd;
+		struct device_node *phy_np;
+		const char *mac;
+
+		/* Should always be an OF node.  But if it is not, we
+		 * cannot handle it, so exit the loop.
+		 */
+		node = to_of_node(fwn);
+		if (!node)
+			break;
+
+		mac = of_get_mac_address(node);
 		if (mac)
 			ether_addr_copy(bgx->lmac[lmac].mac, mac);
 
 		SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev);
 		bgx->lmac[lmac].lmacid = lmac;
+
+		phy_np = of_parse_phandle(node, "phy-handle", 0);
+		/* If there is no phy or defective firmware presents
+		 * this cortina phy, for which there is no driver
+		 * support, ignore it.
+		 */
+		if (phy_np &&
+		    !of_device_is_compatible(phy_np, "cortina,cs4223-slice")) {
+			/* Wait until the phy drivers are available */
+			pd = of_phy_find_device(phy_np);
+			if (!pd)
+				goto defer;
+			bgx->lmac[lmac].phydev = pd;
+		}
+
 		lmac++;
-		if (lmac == MAX_LMAC_PER_BGX) {
-			of_node_put(np_child);
+		if (lmac == MAX_LMAC_PER_BGX)
 			break;
-		}
 	}
+	of_node_put(node);
 	return 0;
+
+defer:
+	/* We are bailing out, try not to leak device reference counts
+	 * for phy devices we may have already found.
+	 */
+	while (lmac) {
+		if (bgx->lmac[lmac].phydev) {
+			put_device(&bgx->lmac[lmac].phydev->mdio.dev);
+			bgx->lmac[lmac].phydev = NULL;
+		}
+		lmac--;
+	}
+	of_node_put(node);
+	return -EPROBE_DEFER;
 }
 
 #else
@@ -1026,9 +1056,6 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct bgx *bgx = NULL;
 	u8 lmac;
 
-	/* Load octeon mdio driver */
-	octeon_mdiobus_force_mod_depencency();
-
 	bgx = devm_kzalloc(dev, sizeof(*bgx), GFP_KERNEL);
 	if (!bgx)
 		return -ENOMEM;