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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

1 files changed, 123 insertions, 76 deletions

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 65088224c207..9f3d9c67e3fe 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -145,6 +145,7 @@ do {								\
 		cpsw->data.active_slave)
 #define IRQ_NUM			2
 #define CPSW_MAX_QUEUES		8
+#define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
 
 static int debug_level;
 module_param(debug_level, int, 0);
@@ -158,6 +159,10 @@ static int rx_packet_max = CPSW_MAX_PACKET_SIZE;
 module_param(rx_packet_max, int, 0);
 MODULE_PARM_DESC(rx_packet_max, "maximum receive packet size (bytes)");
 
+static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
+module_param(descs_pool_size, int, 0444);
+MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
+
 struct cpsw_wr_regs {
 	u32	id_ver;
 	u32	soft_reset;
@@ -352,7 +357,6 @@ struct cpsw_slave {
 	struct phy_device		*phy;
 	struct net_device		*ndev;
 	u32				port_vlan;
-	u32				open_stat;
 };
 
 static inline u32 slave_read(struct cpsw_slave *slave, u32 offset)
@@ -395,6 +399,7 @@ struct cpsw_common {
 	struct cpts			*cpts;
 	int				rx_ch_num, tx_ch_num;
 	int				speed;
+	int				usage_count;
 };
 
 struct cpsw_priv {
@@ -699,18 +704,9 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb);
 
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
-		bool ndev_status = false;
-		struct cpsw_slave *slave = cpsw->slaves;
-		int n;
-
-		if (cpsw->data.dual_emac) {
-			/* In dual emac mode check for all interfaces */
-			for (n = cpsw->data.slaves; n; n--, slave++)
-				if (netif_running(slave->ndev))
-					ndev_status = true;
-		}
-
-		if (ndev_status && (status >= 0)) {
+		/* In dual emac mode check for all interfaces */
+		if (cpsw->data.dual_emac && cpsw->usage_count &&
+		    (status >= 0)) {
 			/* The packet received is for the interface which
 			 * is already down and the other interface is up
 			 * and running, instead of freeing which results
@@ -934,7 +930,7 @@ static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
 	}
 
 	if (num_rx < budget) {
-		napi_complete(napi_rx);
+		napi_complete_done(napi_rx, num_rx);
 		writel(0xff, &cpsw->wr_regs->rx_en);
 		if (cpsw->quirk_irq && cpsw->rx_irq_disabled) {
 			cpsw->rx_irq_disabled = false;
@@ -1230,21 +1226,6 @@ static void cpsw_get_ethtool_stats(struct net_device *ndev,
 	}
 }
 
-static int cpsw_common_res_usage_state(struct cpsw_common *cpsw)
-{
-	u32 i;
-	u32 usage_count = 0;
-
-	if (!cpsw->data.dual_emac)
-		return 0;
-
-	for (i = 0; i < cpsw->data.slaves; i++)
-		if (cpsw->slaves[i].open_stat)
-			usage_count++;
-
-	return usage_count;
-}
-
 static inline int cpsw_tx_packet_submit(struct cpsw_priv *priv,
 					struct sk_buff *skb,
 					struct cpdma_chan *txch)
@@ -1478,8 +1459,6 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		return ret;
 	}
 
-	if (!cpsw_common_res_usage_state(cpsw))
-		cpsw_intr_disable(cpsw);
 	netif_carrier_off(ndev);
 
 	/* Notify the stack of the actual queue counts. */
@@ -1501,8 +1480,8 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		 CPSW_MAJOR_VERSION(reg), CPSW_MINOR_VERSION(reg),
 		 CPSW_RTL_VERSION(reg));
 
-	/* initialize host and slave ports */
-	if (!cpsw_common_res_usage_state(cpsw))
+	/* Initialize host and slave ports */
+	if (!cpsw->usage_count)
 		cpsw_init_host_port(priv);
 	for_each_slave(priv, cpsw_slave_open, priv);
 
@@ -1513,7 +1492,8 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		cpsw_ale_add_vlan(cpsw->ale, cpsw->data.default_vlan,
 				  ALE_ALL_PORTS, ALE_ALL_PORTS, 0, 0);
 
-	if (!cpsw_common_res_usage_state(cpsw)) {
+	/* initialize shared resources for every ndev */
+	if (!cpsw->usage_count) {
 		/* disable priority elevation */
 		__raw_writel(0, &cpsw->regs->ptype);
 
@@ -1555,9 +1535,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 
 	cpdma_ctlr_start(cpsw->dma);
 	cpsw_intr_enable(cpsw);
-
-	if (cpsw->data.dual_emac)
-		cpsw->slaves[priv->emac_port].open_stat = true;
+	cpsw->usage_count++;
 
 	return 0;
 
@@ -1578,7 +1556,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 	netif_tx_stop_all_queues(priv->ndev);
 	netif_carrier_off(priv->ndev);
 
-	if (cpsw_common_res_usage_state(cpsw) <= 1) {
+	if (cpsw->usage_count <= 1) {
 		napi_disable(&cpsw->napi_rx);
 		napi_disable(&cpsw->napi_tx);
 		cpts_unregister(cpsw->cpts);
@@ -1591,9 +1569,8 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 	if (cpsw_need_resplit(cpsw))
 		cpsw_split_res(ndev);
 
+	cpsw->usage_count--;
 	pm_runtime_put_sync(cpsw->dev);
-	if (cpsw->data.dual_emac)
-		cpsw->slaves[priv->emac_port].open_stat = false;
 	return 0;
 }
 
@@ -1606,12 +1583,10 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	struct cpdma_chan *txch;
 	int ret, q_idx;
 
-	netif_trans_update(ndev);
-
 	if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) {
 		cpsw_err(priv, tx_err, "packet pad failed\n");
 		ndev->stats.tx_dropped++;
-		return NETDEV_TX_OK;
+		return NET_XMIT_DROP;
 	}
 
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
@@ -2363,17 +2338,11 @@ static int cpsw_update_channels(struct cpsw_priv *priv,
 	return 0;
 }
 
-static int cpsw_set_channels(struct net_device *ndev,
-			     struct ethtool_channels *chs)
+static void cpsw_suspend_data_pass(struct net_device *ndev)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
 	struct cpsw_slave *slave;
-	int i, ret;
-
-	ret = cpsw_check_ch_settings(cpsw, chs);
-	if (ret < 0)
-		return ret;
+	int i;
 
 	/* Disable NAPI scheduling */
 	cpsw_intr_disable(cpsw);
@@ -2391,6 +2360,51 @@ static int cpsw_set_channels(struct net_device *ndev,
 
 	/* Handle rest of tx packets and stop cpdma channels */
 	cpdma_ctlr_stop(cpsw->dma);
+}
+
+static int cpsw_resume_data_pass(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	int i, ret;
+
+	/* Allow rx packets handling */
+	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
+		if (slave->ndev && netif_running(slave->ndev))
+			netif_dormant_off(slave->ndev);
+
+	/* After this receive is started */
+	if (cpsw->usage_count) {
+		ret = cpsw_fill_rx_channels(priv);
+		if (ret)
+			return ret;
+
+		cpdma_ctlr_start(cpsw->dma);
+		cpsw_intr_enable(cpsw);
+	}
+
+	/* Resume transmit for every affected interface */
+	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
+		if (slave->ndev && netif_running(slave->ndev))
+			netif_tx_start_all_queues(slave->ndev);
+
+	return 0;
+}
+
+static int cpsw_set_channels(struct net_device *ndev,
+			     struct ethtool_channels *chs)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	int i, ret;
+
+	ret = cpsw_check_ch_settings(cpsw, chs);
+	if (ret < 0)
+		return ret;
+
+	cpsw_suspend_data_pass(ndev);
 	ret = cpsw_update_channels(priv, chs);
 	if (ret)
 		goto err;
@@ -2413,30 +2427,14 @@ static int cpsw_set_channels(struct net_device *ndev,
 			dev_err(priv->dev, "cannot set real number of rx queues\n");
 			goto err;
 		}
-
-		/* Enable rx packets handling */
-		netif_dormant_off(slave->ndev);
 	}
 
-	if (cpsw_common_res_usage_state(cpsw)) {
-		ret = cpsw_fill_rx_channels(priv);
-		if (ret)
-			goto err;
-
+	if (cpsw->usage_count)
 		cpsw_split_res(ndev);
 
-		/* After this receive is started */
-		cpdma_ctlr_start(cpsw->dma);
-		cpsw_intr_enable(cpsw);
-	}
-
-	/* Resume transmit for every affected interface */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
-		if (!(slave->ndev && netif_running(slave->ndev)))
-			continue;
-		netif_tx_start_all_queues(slave->ndev);
-	}
-	return 0;
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
 err:
 	dev_err(priv->dev, "cannot update channels number, closing device\n");
 	dev_close(ndev);
@@ -2479,6 +2477,52 @@ static int cpsw_nway_reset(struct net_device *ndev)
 		return -EOPNOTSUPP;
 }
 
+static void cpsw_get_ringparam(struct net_device *ndev,
+			       struct ethtool_ringparam *ering)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	/* not supported */
+	ering->tx_max_pending = 0;
+	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
+	ering->rx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
+	ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma);
+}
+
+static int cpsw_set_ringparam(struct net_device *ndev,
+			      struct ethtool_ringparam *ering)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+
+	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
+
+	if (ering->rx_mini_pending || ering->rx_jumbo_pending ||
+	    ering->rx_pending < CPSW_MAX_QUEUES ||
+	    ering->rx_pending > (descs_pool_size - CPSW_MAX_QUEUES))
+		return -EINVAL;
+
+	if (ering->rx_pending == cpdma_get_num_rx_descs(cpsw->dma))
+		return 0;
+
+	cpsw_suspend_data_pass(ndev);
+
+	cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+
+	if (cpsw->usage_count)
+		cpdma_chan_split_pool(cpsw->dma);
+
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
+
+	dev_err(&ndev->dev, "cannot set ring params, closing device\n");
+	dev_close(ndev);
+	return ret;
+}
+
 static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_drvinfo	= cpsw_get_drvinfo,
 	.get_msglevel	= cpsw_get_msglevel,
@@ -2505,6 +2549,8 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_eee	= cpsw_get_eee,
 	.set_eee	= cpsw_set_eee,
 	.nway_reset	= cpsw_nway_reset,
+	.get_ringparam = cpsw_get_ringparam,
+	.set_ringparam = cpsw_set_ringparam,
 };
 
 static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_common *cpsw,
@@ -2969,6 +3015,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	dma_params.has_ext_regs		= true;
 	dma_params.desc_hw_addr         = dma_params.desc_mem_phys;
 	dma_params.bus_freq_mhz		= cpsw->bus_freq_mhz;
+	dma_params.descs_pool_size	= descs_pool_size;
 
 	cpsw->dma = cpdma_ctlr_create(&dma_params);
 	if (!cpsw->dma) {
@@ -2985,7 +3032,7 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_dma_ret;
 	}
 
-	ale_params.dev			= &ndev->dev;
+	ale_params.dev			= &pdev->dev;
 	ale_params.ale_ageout		= ale_ageout;
 	ale_params.ale_entries		= data->ale_entries;
 	ale_params.ale_ports		= data->slaves;
@@ -3072,9 +3119,9 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_ale_ret;
 	}
 
-	cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d)\n",
-		    &ss_res->start, ndev->irq);
-
+	cpsw_notice(priv, probe,
+		    "initialized device (regs %pa, irq %d, pool size %d)\n",
+		    &ss_res->start, ndev->irq, dma_params.descs_pool_size);
 	if (cpsw->data.dual_emac) {
 		ret = cpsw_probe_dual_emac(priv);
 		if (ret) {