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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 106 insertions, 41 deletions

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 7d2390e3df77..0acb11557ed1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -555,7 +555,7 @@ static int build_sg_fd(struct dpaa2_eth_priv *priv,
 	/* Prepare the HW SGT structure */
 	sgt_buf_size = priv->tx_data_offset +
 		       sizeof(struct dpaa2_sg_entry) *  num_dma_bufs;
-	sgt_buf = netdev_alloc_frag(sgt_buf_size + DPAA2_ETH_TX_BUF_ALIGN);
+	sgt_buf = napi_alloc_frag(sgt_buf_size + DPAA2_ETH_TX_BUF_ALIGN);
 	if (unlikely(!sgt_buf)) {
 		err = -ENOMEM;
 		goto sgt_buf_alloc_failed;
@@ -757,6 +757,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	u16 queue_mapping;
 	unsigned int needed_headroom;
 	u32 fd_len;
+	u8 prio = 0;
 	int err, i;
 
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
@@ -814,6 +815,18 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 * a queue affined to the same core that processed the Rx frame
 	 */
 	queue_mapping = skb_get_queue_mapping(skb);
+
+	if (net_dev->num_tc) {
+		prio = netdev_txq_to_tc(net_dev, queue_mapping);
+		/* Hardware interprets priority level 0 as being the highest,
+		 * so we need to do a reverse mapping to the netdev tc index
+		 */
+		prio = net_dev->num_tc - prio - 1;
+		/* We have only one FQ array entry for all Tx hardware queues
+		 * with the same flow id (but different priority levels)
+		 */
+		queue_mapping %= dpaa2_eth_queue_count(priv);
+	}
 	fq = &priv->fq[queue_mapping];
 
 	fd_len = dpaa2_fd_get_len(&fd);
@@ -824,7 +837,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 * the Tx confirmation callback for this frame
 	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, 0);
+		err = priv->enqueue(priv, fq, &fd, prio);
 		if (err != -EBUSY)
 			break;
 	}
@@ -997,13 +1010,6 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
 	int i, j;
 	int new_count;
 
-	/* This is the lazy seeding of Rx buffer pools.
-	 * dpaa2_add_bufs() is also used on the Rx hotpath and calls
-	 * napi_alloc_frag(). The trouble with that is that it in turn ends up
-	 * calling this_cpu_ptr(), which mandates execution in atomic context.
-	 * Rather than splitting up the code, do a one-off preempt disable.
-	 */
-	preempt_disable();
 	for (j = 0; j < priv->num_channels; j++) {
 		for (i = 0; i < DPAA2_ETH_NUM_BUFS;
 		     i += DPAA2_ETH_BUFS_PER_CMD) {
@@ -1011,12 +1017,10 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
 			priv->channel[j]->buf_count += new_count;
 
 			if (new_count < DPAA2_ETH_BUFS_PER_CMD) {
-				preempt_enable();
 				return -ENOMEM;
 			}
 		}
 	}
-	preempt_enable();
 
 	return 0;
 }
@@ -1872,6 +1876,78 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 	return n - drops;
 }
 
+static int update_xps(struct dpaa2_eth_priv *priv)
+{
+	struct net_device *net_dev = priv->net_dev;
+	struct cpumask xps_mask;
+	struct dpaa2_eth_fq *fq;
+	int i, num_queues, netdev_queues;
+	int err = 0;
+
+	num_queues = dpaa2_eth_queue_count(priv);
+	netdev_queues = (net_dev->num_tc ? : 1) * num_queues;
+
+	/* The first <num_queues> entries in priv->fq array are Tx/Tx conf
+	 * queues, so only process those
+	 */
+	for (i = 0; i < netdev_queues; i++) {
+		fq = &priv->fq[i % num_queues];
+
+		cpumask_clear(&xps_mask);
+		cpumask_set_cpu(fq->target_cpu, &xps_mask);
+
+		err = netif_set_xps_queue(net_dev, &xps_mask, i);
+		if (err) {
+			netdev_warn_once(net_dev, "Error setting XPS queue\n");
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int dpaa2_eth_setup_tc(struct net_device *net_dev,
+			      enum tc_setup_type type, void *type_data)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct tc_mqprio_qopt *mqprio = type_data;
+	u8 num_tc, num_queues;
+	int i;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EINVAL;
+
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_queues = dpaa2_eth_queue_count(priv);
+	num_tc = mqprio->num_tc;
+
+	if (num_tc == net_dev->num_tc)
+		return 0;
+
+	if (num_tc  > dpaa2_eth_tc_count(priv)) {
+		netdev_err(net_dev, "Max %d traffic classes supported\n",
+			   dpaa2_eth_tc_count(priv));
+		return -EINVAL;
+	}
+
+	if (!num_tc) {
+		netdev_reset_tc(net_dev);
+		netif_set_real_num_tx_queues(net_dev, num_queues);
+		goto out;
+	}
+
+	netdev_set_num_tc(net_dev, num_tc);
+	netif_set_real_num_tx_queues(net_dev, num_tc * num_queues);
+
+	for (i = 0; i < num_tc; i++)
+		netdev_set_tc_queue(net_dev, i, num_queues, i * num_queues);
+
+out:
+	update_xps(priv);
+
+	return 0;
+}
+
 static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_open = dpaa2_eth_open,
 	.ndo_start_xmit = dpaa2_eth_tx,
@@ -1884,6 +1960,7 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_change_mtu = dpaa2_eth_change_mtu,
 	.ndo_bpf = dpaa2_eth_xdp,
 	.ndo_xdp_xmit = dpaa2_eth_xdp_xmit,
+	.ndo_setup_tc = dpaa2_eth_setup_tc,
 };
 
 static void cdan_cb(struct dpaa2_io_notification_ctx *ctx)
@@ -2138,10 +2215,9 @@ static struct dpaa2_eth_channel *get_affine_channel(struct dpaa2_eth_priv *priv,
 static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
-	struct cpumask xps_mask;
 	struct dpaa2_eth_fq *fq;
 	int rx_cpu, txc_cpu;
-	int i, err;
+	int i;
 
 	/* For each FQ, pick one channel/CPU to deliver frames to.
 	 * This may well change at runtime, either through irqbalance or
@@ -2160,17 +2236,6 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 			break;
 		case DPAA2_TX_CONF_FQ:
 			fq->target_cpu = txc_cpu;
-
-			/* Tell the stack to affine to txc_cpu the Tx queue
-			 * associated with the confirmation one
-			 */
-			cpumask_clear(&xps_mask);
-			cpumask_set_cpu(txc_cpu, &xps_mask);
-			err = netif_set_xps_queue(priv->net_dev, &xps_mask,
-						  fq->flowid);
-			if (err)
-				dev_err(dev, "Error setting XPS queue\n");
-
 			txc_cpu = cpumask_next(txc_cpu, &priv->dpio_cpumask);
 			if (txc_cpu >= nr_cpu_ids)
 				txc_cpu = cpumask_first(&priv->dpio_cpumask);
@@ -2180,6 +2245,8 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 		}
 		fq->channel = get_affine_channel(priv, fq->target_cpu);
 	}
+
+	update_xps(priv);
 }
 
 static void setup_fqs(struct dpaa2_eth_priv *priv)
@@ -2361,11 +2428,10 @@ static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
 
 static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
 				       struct dpaa2_eth_fq *fq,
-				       struct dpaa2_fd *fd,
-				       u8 prio __always_unused)
+				       struct dpaa2_fd *fd, u8 prio)
 {
 	return dpaa2_io_service_enqueue_fq(fq->channel->dpio,
-					   fq->tx_fqid, fd);
+					   fq->tx_fqid[prio], fd);
 }
 
 static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
@@ -2479,14 +2545,9 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 	queue.destination.type = DPNI_DEST_DPCON;
 	queue.destination.priority = 1;
 	queue.user_context = (u64)(uintptr_t)fq;
-	queue.flc.stash_control = 1;
-	queue.flc.value &= 0xFFFFFFFFFFFFFFC0;
-	/* 01 01 00 - data, annotation, flow context */
-	queue.flc.value |= 0x14;
 	err = dpni_set_queue(priv->mc_io, 0, priv->mc_token,
 			     DPNI_QUEUE_RX, 0, fq->flowid,
-			     DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST |
-			     DPNI_QUEUE_OPT_FLC,
+			     DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST,
 			     &queue);
 	if (err) {
 		dev_err(dev, "dpni_set_queue(RX) failed\n");
@@ -2526,17 +2587,21 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv,
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_queue queue;
 	struct dpni_queue_id qid;
-	int err;
+	int i, err;
 
-	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
-			     DPNI_QUEUE_TX, 0, fq->flowid, &queue, &qid);
-	if (err) {
-		dev_err(dev, "dpni_get_queue(TX) failed\n");
-		return err;
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_TX, i, fq->flowid,
+				     &queue, &qid);
+		if (err) {
+			dev_err(dev, "dpni_get_queue(TX) failed\n");
+			return err;
+		}
+		fq->tx_fqid[i] = qid.fqid;
 	}
 
+	/* All Tx queues belonging to the same flowid have the same qdbin */
 	fq->tx_qdbin = qid.qdbin;
-	fq->tx_fqid = qid.fqid;
 
 	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
 			     DPNI_QUEUE_TX_CONFIRM, 0, fq->flowid,
@@ -3236,7 +3301,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	dev = &dpni_dev->dev;
 
 	/* Net device */
-	net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA2_ETH_MAX_TX_QUEUES);
+	net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA2_ETH_MAX_NETDEV_QUEUES);
 	if (!net_dev) {
 		dev_err(dev, "alloc_etherdev_mq() failed\n");
 		return -ENOMEM;