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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 98 insertions, 32 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index e2d342647b19..e988caa797cb 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -455,6 +455,11 @@ static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
 		q->pg_chunk.offset = 0;
 		mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
 				       0, q->alloc_size, PCI_DMA_FROMDEVICE);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev, mapping))) {
+			__free_pages(q->pg_chunk.page, order);
+			q->pg_chunk.page = NULL;
+			return -EIO;
+		}
 		q->pg_chunk.mapping = mapping;
 	}
 	sd->pg_chunk = q->pg_chunk;
@@ -949,40 +954,78 @@ static inline unsigned int calc_tx_descs(const struct sk_buff *skb)
 	return flits_to_desc(flits);
 }
 
+/*	map_skb - map a packet main body and its page fragments
+ *	@pdev: the PCI device
+ *	@skb: the packet
+ *	@addr: placeholder to save the mapped addresses
+ *
+ *	map the main body of an sk_buff and its page fragments, if any.
+ */
+static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
+		   dma_addr_t *addr)
+{
+	const skb_frag_t *fp, *end;
+	const struct skb_shared_info *si;
+
+	if (skb_headlen(skb)) {
+		*addr = pci_map_single(pdev, skb->data, skb_headlen(skb),
+				       PCI_DMA_TODEVICE);
+		if (pci_dma_mapping_error(pdev, *addr))
+			goto out_err;
+		addr++;
+	}
+
+	si = skb_shinfo(skb);
+	end = &si->frags[si->nr_frags];
+
+	for (fp = si->frags; fp < end; fp++) {
+		*addr = skb_frag_dma_map(&pdev->dev, fp, 0, skb_frag_size(fp),
+					 DMA_TO_DEVICE);
+		if (pci_dma_mapping_error(pdev, *addr))
+			goto unwind;
+		addr++;
+	}
+	return 0;
+
+unwind:
+	while (fp-- > si->frags)
+		dma_unmap_page(&pdev->dev, *--addr, skb_frag_size(fp),
+			       DMA_TO_DEVICE);
+
+	pci_unmap_single(pdev, addr[-1], skb_headlen(skb), PCI_DMA_TODEVICE);
+out_err:
+	return -ENOMEM;
+}
+
 /**
- *	make_sgl - populate a scatter/gather list for a packet
+ *	write_sgl - populate a scatter/gather list for a packet
  *	@skb: the packet
  *	@sgp: the SGL to populate
  *	@start: start address of skb main body data to include in the SGL
  *	@len: length of skb main body data to include in the SGL
- *	@pdev: the PCI device
+ *	@addr: the list of the mapped addresses
  *
- *	Generates a scatter/gather list for the buffers that make up a packet
+ *	Copies the scatter/gather list for the buffers that make up a packet
  *	and returns the SGL size in 8-byte words.  The caller must size the SGL
  *	appropriately.
  */
-static inline unsigned int make_sgl(const struct sk_buff *skb,
-				    struct sg_ent *sgp, unsigned char *start,
-				    unsigned int len, struct pci_dev *pdev)
+static inline unsigned int write_sgl(const struct sk_buff *skb,
+				     struct sg_ent *sgp, unsigned char *start,
+				     unsigned int len, const dma_addr_t *addr)
 {
-	dma_addr_t mapping;
-	unsigned int i, j = 0, nfrags;
+	unsigned int i, j = 0, k = 0, nfrags;
 
 	if (len) {
-		mapping = pci_map_single(pdev, start, len, PCI_DMA_TODEVICE);
 		sgp->len[0] = cpu_to_be32(len);
-		sgp->addr[0] = cpu_to_be64(mapping);
-		j = 1;
+		sgp->addr[j++] = cpu_to_be64(addr[k++]);
 	}
 
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-		mapping = skb_frag_dma_map(&pdev->dev, frag, 0, skb_frag_size(frag),
-					   DMA_TO_DEVICE);
 		sgp->len[j] = cpu_to_be32(skb_frag_size(frag));
-		sgp->addr[j] = cpu_to_be64(mapping);
+		sgp->addr[j] = cpu_to_be64(addr[k++]);
 		j ^= 1;
 		if (j == 0)
 			++sgp;
@@ -1138,7 +1181,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 			    const struct port_info *pi,
 			    unsigned int pidx, unsigned int gen,
 			    struct sge_txq *q, unsigned int ndesc,
-			    unsigned int compl)
+			    unsigned int compl, const dma_addr_t *addr)
 {
 	unsigned int flits, sgl_flits, cntrl, tso_info;
 	struct sg_ent *sgp, sgl[MAX_SKB_FRAGS / 2 + 1];
@@ -1196,7 +1239,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 	}
 
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = make_sgl(skb, sgp, skb->data, skb_headlen(skb), adap->pdev);
+	sgl_flits = write_sgl(skb, sgp, skb->data, skb_headlen(skb), addr);
 
 	write_wr_hdr_sgl(ndesc, skb, d, pidx, q, sgl, flits, sgl_flits, gen,
 			 htonl(V_WR_OP(FW_WROPCODE_TUNNEL_TX_PKT) | compl),
@@ -1227,6 +1270,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_queue *txq;
 	struct sge_qset *qs;
 	struct sge_txq *q;
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
 
 	/*
 	 * The chip min packet length is 9 octets but play safe and reject
@@ -1255,6 +1299,14 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
+	/* Check if ethernet packet can't be sent as immediate data */
+	if (skb->len > (WR_LEN - sizeof(struct cpl_tx_pkt))) {
+		if (unlikely(map_skb(adap->pdev, skb, addr) < 0)) {
+			dev_kfree_skb(skb);
+			return NETDEV_TX_OK;
+		}
+	}
+
 	q->in_use += ndesc;
 	if (unlikely(credits - ndesc < q->stop_thres)) {
 		t3_stop_tx_queue(txq, qs, q);
@@ -1312,7 +1364,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (likely(!skb_shared(skb)))
 		skb_orphan(skb);
 
-	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl);
+	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl, addr);
 	check_ring_tx_db(adap, q);
 	return NETDEV_TX_OK;
 }
@@ -1577,7 +1629,8 @@ static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
  */
 static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 			  struct sge_txq *q, unsigned int pidx,
-			  unsigned int gen, unsigned int ndesc)
+			  unsigned int gen, unsigned int ndesc,
+			  const dma_addr_t *addr)
 {
 	unsigned int sgl_flits, flits;
 	struct work_request_hdr *from;
@@ -1598,10 +1651,9 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 
 	flits = skb_transport_offset(skb) / 8;
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
-			     skb_tail_pointer(skb) -
-			     skb_transport_header(skb),
-			     adap->pdev);
+	sgl_flits = write_sgl(skb, sgp, skb_transport_header(skb),
+			      skb_tail_pointer(skb) - skb_transport_header(skb),
+			      addr);
 	if (need_skb_unmap()) {
 		setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
 		skb->destructor = deferred_unmap_destructor;
@@ -1659,6 +1711,12 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		goto again;
 	}
 
+	if (!immediate(skb) &&
+	    map_skb(adap->pdev, skb, (dma_addr_t *)skb->head)) {
+		spin_unlock(&q->lock);
+		return NET_XMIT_SUCCESS;
+	}
+
 	gen = q->gen;
 	q->in_use += ndesc;
 	pidx = q->pidx;
@@ -1669,7 +1727,7 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	}
 	spin_unlock(&q->lock);
 
-	write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
+	write_ofld_wr(adap, skb, q, pidx, gen, ndesc, (dma_addr_t *)skb->head);
 	check_ring_tx_db(adap, q);
 	return NET_XMIT_SUCCESS;
 }
@@ -1687,6 +1745,7 @@ static void restart_offloadq(unsigned long data)
 	struct sge_txq *q = &qs->txq[TXQ_OFLD];
 	const struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
+	unsigned int written = 0;
 
 	spin_lock(&q->lock);
 again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
@@ -1706,10 +1765,15 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 			break;
 		}
 
+		if (!immediate(skb) &&
+		    map_skb(adap->pdev, skb, (dma_addr_t *)skb->head))
+			break;
+
 		gen = q->gen;
 		q->in_use += ndesc;
 		pidx = q->pidx;
 		q->pidx += ndesc;
+		written += ndesc;
 		if (q->pidx >= q->size) {
 			q->pidx -= q->size;
 			q->gen ^= 1;
@@ -1717,7 +1781,8 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		__skb_unlink(skb, &q->sendq);
 		spin_unlock(&q->lock);
 
-		write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
+		write_ofld_wr(adap, skb, q, pidx, gen, ndesc,
+			      (dma_addr_t *)skb->head);
 		spin_lock(&q->lock);
 	}
 	spin_unlock(&q->lock);
@@ -1727,8 +1792,9 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	set_bit(TXQ_LAST_PKT_DB, &q->flags);
 #endif
 	wmb();
-	t3_write_reg(adap, A_SG_KDOORBELL,
-		     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
+	if (likely(written))
+		t3_write_reg(adap, A_SG_KDOORBELL,
+			     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
 }
 
 /**
@@ -2853,9 +2919,9 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
  *	bother cleaning them up here.
  *
  */
-static void sge_timer_tx(unsigned long data)
+static void sge_timer_tx(struct timer_list *t)
 {
-	struct sge_qset *qs = (struct sge_qset *)data;
+	struct sge_qset *qs = from_timer(qs, t, tx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	unsigned int tbd[SGE_TXQ_PER_SET] = {0, 0};
@@ -2893,10 +2959,10 @@ static void sge_timer_tx(unsigned long data)
  *	starved.
  *
  */
-static void sge_timer_rx(unsigned long data)
+static void sge_timer_rx(struct timer_list *t)
 {
 	spinlock_t *lock;
-	struct sge_qset *qs = (struct sge_qset *)data;
+	struct sge_qset *qs = from_timer(qs, t, rx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	u32 status;
@@ -2976,8 +3042,8 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	struct sge_qset *q = &adapter->sge.qs[id];
 
 	init_qset_cntxt(q, id);
-	setup_timer(&q->tx_reclaim_timer, sge_timer_tx, (unsigned long)q);
-	setup_timer(&q->rx_reclaim_timer, sge_timer_rx, (unsigned long)q);
+	timer_setup(&q->tx_reclaim_timer, sge_timer_tx, 0);
+	timer_setup(&q->rx_reclaim_timer, sge_timer_rx, 0);
 
 	q->fl[0].desc = alloc_ring(adapter->pdev, p->fl_size,
 				   sizeof(struct rx_desc),