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

Pull networking updates from David Miller:

 1) Support offloading wireless authentication to userspace via
    NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.

 2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
    Setup and cleanup of namespaces now all run asynchronously and thus
    performance is significantly increased.

 3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
    Streiff.

 4) Support zerocopy on RDS sockets, from Sowmini Varadhan.

 5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
    Borkmann.

 6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
    Chevallier.

 7) Support grafting of child qdiscs in mlxsw driver, from Nogah
    Frankel.

 8) Add packet forwarding tests to selftests, from Ido Schimmel.

 9) Deal with sub-optimal GSO packets better in BBR congestion control,
    from Eric Dumazet.

10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.

11) Add path MTU tests to selftests, from Stefano Brivio.

12) Various bits of IPSEC offloading support for mlx5, from Aviad
    Yehezkel, Yossi Kuperman, and Saeed Mahameed.

13) Support RSS spreading on ntuple filters in SFC driver, from Edward
    Cree.

14) Lots of sockmap work from John Fastabend. Applications can use eBPF
    to filter sendmsg and sendpage operations.

15) In-kernel receive TLS support, from Dave Watson.

16) Add XDP support to ixgbevf, this is significant because it should
    allow optimized XDP usage in various cloud environments. From Tony
    Nguyen.

17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
    Venkataramanan et al.

18) IP fragmentation match offload support in nfp driver, from Pieter
    Jansen van Vuuren.

19) Support XDP redirect in i40e driver, from Björn Töpel.

20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
    tracepoints in their raw form, from Alexei Starovoitov.

21) Lots of striding RQ improvements to mlx5 driver with many
    performance improvements, from Tariq Toukan.

22) Use rhashtable for inet frag reassembly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
  net: mvneta: improve suspend/resume
  net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
  ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
  net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
  net: bgmac: Correctly annotate register space
  route: check sysctl_fib_multipath_use_neigh earlier than hash
  fix typo in command value in drivers/net/phy/mdio-bitbang.
  sky2: Increase D3 delay to sky2 stops working after suspend
  net/mlx5e: Set EQE based as default TX interrupt moderation mode
  ibmvnic: Disable irqs before exiting reset from closed state
  net: sched: do not emit messages while holding spinlock
  vlan: also check phy_driver ts_info for vlan's real device
  Bluetooth: Mark expected switch fall-throughs
  Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
  Bluetooth: btrsi: remove unused including <linux/version.h>
  Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
  sh_eth: kill useless check in __sh_eth_get_regs()
  sh_eth: add sh_eth_cpu_data::no_xdfar flag
  ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
  ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
  ...

1 files changed, 38 insertions, 27 deletions

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e4ec32a9ca15..fd43f98ddbe7 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -454,6 +454,16 @@ static void dpaa_set_rx_mode(struct net_device *net_dev)
 				  err);
 	}
 
+	if (!!(net_dev->flags & IFF_ALLMULTI) != priv->mac_dev->allmulti) {
+		priv->mac_dev->allmulti = !priv->mac_dev->allmulti;
+		err = priv->mac_dev->set_allmulti(priv->mac_dev->fman_mac,
+						  priv->mac_dev->allmulti);
+		if (err < 0)
+			netif_err(priv, drv, net_dev,
+				  "mac_dev->set_allmulti() = %d\n",
+				  err);
+	}
+
 	err = priv->mac_dev->set_multi(net_dev, priv->mac_dev);
 	if (err < 0)
 		netif_err(priv, drv, net_dev, "mac_dev->set_multi() = %d\n",
@@ -1916,8 +1926,10 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 		goto csum_failed;
 	}
 
+	/* SGT[0] is used by the linear part */
 	sgt = (struct qm_sg_entry *)(sgt_buf + priv->tx_headroom);
-	qm_sg_entry_set_len(&sgt[0], skb_headlen(skb));
+	frag_len = skb_headlen(skb);
+	qm_sg_entry_set_len(&sgt[0], frag_len);
 	sgt[0].bpid = FSL_DPAA_BPID_INV;
 	sgt[0].offset = 0;
 	addr = dma_map_single(dev, skb->data,
@@ -1930,9 +1942,9 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 	qm_sg_entry_set64(&sgt[0], addr);
 
 	/* populate the rest of SGT entries */
-	frag = &skb_shinfo(skb)->frags[0];
-	frag_len = frag->size;
-	for (i = 1; i <= nr_frags; i++, frag++) {
+	for (i = 0; i < nr_frags; i++) {
+		frag = &skb_shinfo(skb)->frags[i];
+		frag_len = frag->size;
 		WARN_ON(!skb_frag_page(frag));
 		addr = skb_frag_dma_map(dev, frag, 0,
 					frag_len, dma_dir);
@@ -1942,15 +1954,16 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 			goto sg_map_failed;
 		}
 
-		qm_sg_entry_set_len(&sgt[i], frag_len);
-		sgt[i].bpid = FSL_DPAA_BPID_INV;
-		sgt[i].offset = 0;
+		qm_sg_entry_set_len(&sgt[i + 1], frag_len);
+		sgt[i + 1].bpid = FSL_DPAA_BPID_INV;
+		sgt[i + 1].offset = 0;
 
 		/* keep the offset in the address */
-		qm_sg_entry_set64(&sgt[i], addr);
-		frag_len = frag->size;
+		qm_sg_entry_set64(&sgt[i + 1], addr);
 	}
-	qm_sg_entry_set_f(&sgt[i - 1], frag_len);
+
+	/* Set the final bit in the last used entry of the SGT */
+	qm_sg_entry_set_f(&sgt[nr_frags], frag_len);
 
 	qm_fd_set_sg(fd, priv->tx_headroom, skb->len);
 
@@ -2051,19 +2064,23 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	/* MAX_SKB_FRAGS is equal or larger than our dpaa_SGT_MAX_ENTRIES;
 	 * make sure we don't feed FMan with more fragments than it supports.
 	 */
-	if (nonlinear &&
-	    likely(skb_shinfo(skb)->nr_frags < DPAA_SGT_MAX_ENTRIES)) {
-		/* Just create a S/G fd based on the skb */
-		err = skb_to_sg_fd(priv, skb, &fd);
-		percpu_priv->tx_frag_skbuffs++;
-	} else {
+	if (unlikely(nonlinear &&
+		     (skb_shinfo(skb)->nr_frags >= DPAA_SGT_MAX_ENTRIES))) {
 		/* If the egress skb contains more fragments than we support
 		 * we have no choice but to linearize it ourselves.
 		 */
-		if (unlikely(nonlinear) && __skb_linearize(skb))
+		if (__skb_linearize(skb))
 			goto enomem;
 
-		/* Finally, create a contig FD from this skb */
+		nonlinear = skb_is_nonlinear(skb);
+	}
+
+	if (nonlinear) {
+		/* Just create a S/G fd based on the skb */
+		err = skb_to_sg_fd(priv, skb, &fd);
+		percpu_priv->tx_frag_skbuffs++;
+	} else {
+		/* Create a contig FD from this skb */
 		err = skb_to_contig_fd(priv, skb, &fd, &offset);
 	}
 	if (unlikely(err < 0))
@@ -2200,14 +2217,8 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal,
 	if (dpaa_eth_napi_schedule(percpu_priv, portal))
 		return qman_cb_dqrr_stop;
 
-	if (dpaa_eth_refill_bpools(priv))
-		/* Unable to refill the buffer pool due to insufficient
-		 * system memory. Just release the frame back into the pool,
-		 * otherwise we'll soon end up with an empty buffer pool.
-		 */
-		dpaa_fd_release(net_dev, &dq->fd);
-	else
-		dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
+	dpaa_eth_refill_bpools(priv);
+	dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
 
 	return qman_cb_dqrr_consume;
 }
@@ -2766,7 +2777,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 
 	priv->channel = (u16)channel;
 
-	/* Start a thread that will walk the CPUs with affine portals
+	/* Walk the CPUs with affine portals
 	 * and add this pool channel to each's dequeue mask.
 	 */
 	dpaa_eth_add_channel(priv->channel);