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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

5 files changed, 423 insertions, 107 deletions

diff --git a/drivers/net/ethernet/ibm/emac/phy.c b/drivers/net/ethernet/ibm/emac/phy.c
index 5b88cc690c22..35865d05fccd 100644
--- a/drivers/net/ethernet/ibm/emac/phy.c
+++ b/drivers/net/ethernet/ibm/emac/phy.c
@@ -276,7 +276,7 @@ static int genmii_read_link(struct mii_phy *phy)
 }
 
 /* Generic implementation for most 10/100/1000 PHYs */
-static struct mii_phy_ops generic_phy_ops = {
+static const struct mii_phy_ops generic_phy_ops = {
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
 	.poll_link	= genmii_poll_link,
@@ -340,7 +340,7 @@ static int cis8201_init(struct mii_phy *phy)
 	return 0;
 }
 
-static struct mii_phy_ops cis8201_phy_ops = {
+static const struct mii_phy_ops cis8201_phy_ops = {
 	.init		= cis8201_init,
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
@@ -420,7 +420,7 @@ static int et1011c_init(struct mii_phy *phy)
 	return 0;
 }
 
-static struct mii_phy_ops et1011c_phy_ops = {
+static const struct mii_phy_ops et1011c_phy_ops = {
 	.init		= et1011c_init,
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
@@ -439,7 +439,7 @@ static struct mii_phy_def et1011c_phy_def = {
 
 
 
-static struct mii_phy_ops m88e1111_phy_ops = {
+static const struct mii_phy_ops m88e1111_phy_ops = {
 	.init		= m88e1111_init,
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
@@ -455,7 +455,7 @@ static struct mii_phy_def m88e1111_phy_def = {
 	.ops		= &m88e1111_phy_ops,
 };
 
-static struct mii_phy_ops m88e1112_phy_ops = {
+static const struct mii_phy_ops m88e1112_phy_ops = {
 	.init		= m88e1112_init,
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
@@ -480,7 +480,7 @@ static int ar8035_init(struct mii_phy *phy)
 	return 0;
 }
 
-static struct mii_phy_ops ar8035_phy_ops = {
+static const struct mii_phy_ops ar8035_phy_ops = {
 	.init		= ar8035_init,
 	.setup_aneg	= genmii_setup_aneg,
 	.setup_forced	= genmii_setup_forced,
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 72ab7b6bf20b..3e0a695537e2 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -46,6 +46,8 @@
 #include <asm/vio.h>
 #include <asm/iommu.h>
 #include <asm/firmware.h>
+#include <net/tcp.h>
+#include <net/ip6_checksum.h>
 
 #include "ibmveth.h"
 
@@ -808,8 +810,7 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data)
 
 	ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr);
 
-	if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
-	    !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
+	if (ret == H_SUCCESS &&
 	    (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
 		ret4 = h_illan_attributes(adapter->vdev->unit_address, clr_attr,
 					 set_attr, &ret_attr);
@@ -1040,6 +1041,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	dma_addr_t dma_addr;
 	unsigned long mss = 0;
 
+	/* veth doesn't handle frag_list, so linearize the skb.
+	 * When GRO is enabled SKB's can have frag_list.
+	 */
+	if (adapter->is_active_trunk &&
+	    skb_has_frag_list(skb) && __skb_linearize(skb)) {
+		netdev->stats.tx_dropped++;
+		goto out;
+	}
+
 	/*
 	 * veth handles a maximum of 6 segments including the header, so
 	 * we have to linearize the skb if there are more than this.
@@ -1064,9 +1074,6 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 	desc_flags = IBMVETH_BUF_VALID;
 
-	if (skb_is_gso(skb) && adapter->fw_large_send_support)
-		desc_flags |= IBMVETH_BUF_LRG_SND;
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		unsigned char *buf = skb_transport_header(skb) +
 						skb->csum_offset;
@@ -1076,6 +1083,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 		/* Need to zero out the checksum */
 		buf[0] = 0;
 		buf[1] = 0;
+
+		if (skb_is_gso(skb) && adapter->fw_large_send_support)
+			desc_flags |= IBMVETH_BUF_LRG_SND;
 	}
 
 retry_bounce:
@@ -1128,7 +1138,7 @@ retry_bounce:
 		descs[i+1].fields.address = dma_addr;
 	}
 
-	if (skb_is_gso(skb)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		if (adapter->fw_large_send_support) {
 			mss = (unsigned long)skb_shinfo(skb)->gso_size;
 			adapter->tx_large_packets++;
@@ -1232,6 +1242,71 @@ static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
 	}
 }
 
+static void ibmveth_rx_csum_helper(struct sk_buff *skb,
+				   struct ibmveth_adapter *adapter)
+{
+	struct iphdr *iph = NULL;
+	struct ipv6hdr *iph6 = NULL;
+	__be16 skb_proto = 0;
+	u16 iphlen = 0;
+	u16 iph_proto = 0;
+	u16 tcphdrlen = 0;
+
+	skb_proto = be16_to_cpu(skb->protocol);
+
+	if (skb_proto == ETH_P_IP) {
+		iph = (struct iphdr *)skb->data;
+
+		/* If the IP checksum is not offloaded and if the packet
+		 *  is large send, the checksum must be rebuilt.
+		 */
+		if (iph->check == 0xffff) {
+			iph->check = 0;
+			iph->check = ip_fast_csum((unsigned char *)iph,
+						  iph->ihl);
+		}
+
+		iphlen = iph->ihl * 4;
+		iph_proto = iph->protocol;
+	} else if (skb_proto == ETH_P_IPV6) {
+		iph6 = (struct ipv6hdr *)skb->data;
+		iphlen = sizeof(struct ipv6hdr);
+		iph_proto = iph6->nexthdr;
+	}
+
+	/* In OVS environment, when a flow is not cached, specifically for a
+	 * new TCP connection, the first packet information is passed up
+	 * the user space for finding a flow. During this process, OVS computes
+	 * checksum on the first packet when CHECKSUM_PARTIAL flag is set.
+	 *
+	 * Given that we zeroed out TCP checksum field in transmit path
+	 * (refer ibmveth_start_xmit routine) as we set "no checksum bit",
+	 * OVS computed checksum will be incorrect w/o TCP pseudo checksum
+	 * in the packet. This leads to OVS dropping the packet and hence
+	 * TCP retransmissions are seen.
+	 *
+	 * So, re-compute TCP pseudo header checksum.
+	 */
+	if (iph_proto == IPPROTO_TCP && adapter->is_active_trunk) {
+		struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen);
+
+		tcphdrlen = skb->len - iphlen;
+
+		/* Recompute TCP pseudo header checksum */
+		if (skb_proto == ETH_P_IP)
+			tcph->check = ~csum_tcpudp_magic(iph->saddr,
+					iph->daddr, tcphdrlen, iph_proto, 0);
+		else if (skb_proto == ETH_P_IPV6)
+			tcph->check = ~csum_ipv6_magic(&iph6->saddr,
+					&iph6->daddr, tcphdrlen, iph_proto, 0);
+
+		/* Setup SKB fields for checksum offload */
+		skb_partial_csum_set(skb, iphlen,
+				     offsetof(struct tcphdr, check));
+		skb_reset_network_header(skb);
+	}
+}
+
 static int ibmveth_poll(struct napi_struct *napi, int budget)
 {
 	struct ibmveth_adapter *adapter =
@@ -1239,7 +1314,6 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	struct net_device *netdev = adapter->netdev;
 	int frames_processed = 0;
 	unsigned long lpar_rc;
-	struct iphdr *iph;
 	u16 mss = 0;
 
 restart_poll:
@@ -1297,17 +1371,7 @@ restart_poll:
 
 			if (csum_good) {
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
-				if (be16_to_cpu(skb->protocol) == ETH_P_IP) {
-					iph = (struct iphdr *)skb->data;
-
-					/* If the IP checksum is not offloaded and if the packet
-					 *  is large send, the checksum must be rebuilt.
-					 */
-					if (iph->check == 0xffff) {
-						iph->check = 0;
-						iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
-					}
-				}
+				ibmveth_rx_csum_helper(skb, adapter);
 			}
 
 			if (length > netdev->mtu + ETH_HLEN) {
@@ -1626,6 +1690,13 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		netdev->hw_features |= NETIF_F_TSO;
 	}
 
+	adapter->is_active_trunk = false;
+	if (ret == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK)) {
+		adapter->is_active_trunk = true;
+		netdev->hw_features |= NETIF_F_FRAGLIST;
+		netdev->features |= NETIF_F_FRAGLIST;
+	}
+
 	netdev->min_mtu = IBMVETH_MIN_MTU;
 	netdev->max_mtu = ETH_MAX_MTU;
 
@@ -1843,7 +1914,7 @@ static struct vio_device_id ibmveth_device_table[] = {
 };
 MODULE_DEVICE_TABLE(vio, ibmveth_device_table);
 
-static struct dev_pm_ops ibmveth_pm_ops = {
+static const struct dev_pm_ops ibmveth_pm_ops = {
 	.resume = ibmveth_resume
 };
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index ed8780cca982..01c587fc02c7 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -156,6 +156,7 @@ struct ibmveth_adapter {
     int pool_config;
     int rx_csum;
     int large_send;
+    bool is_active_trunk;
     void *bounce_buffer;
     dma_addr_t bounce_buffer_dma;
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c0fbeb387db4..a3e694679635 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -183,6 +183,12 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 	send_request_map(adapter, ltb->addr,
 			 ltb->size, ltb->map_id);
 	wait_for_completion(&adapter->fw_done);
+
+	if (adapter->fw_done_rc) {
+		dev_err(dev, "Couldn't map long term buffer,rc = %d\n",
+			adapter->fw_done_rc);
+		return -1;
+	}
 	return 0;
 }
 
@@ -200,6 +206,33 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
 }
 
+static int reset_long_term_buff(struct ibmvnic_adapter *adapter,
+				struct ibmvnic_long_term_buff *ltb)
+{
+	memset(ltb->buff, 0, ltb->size);
+
+	init_completion(&adapter->fw_done);
+	send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id);
+	wait_for_completion(&adapter->fw_done);
+
+	if (adapter->fw_done_rc) {
+		dev_info(&adapter->vdev->dev,
+			 "Reset failed, attempting to free and reallocate buffer\n");
+		free_long_term_buff(adapter, ltb);
+		return alloc_long_term_buff(adapter, ltb, ltb->size);
+	}
+	return 0;
+}
+
+static void deactivate_rx_pools(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+	     i++)
+		adapter->rx_pool[i].active = 0;
+}
+
 static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 			      struct ibmvnic_rx_pool *pool)
 {
@@ -217,6 +250,9 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 	int index;
 	int i;
 
+	if (!pool->active)
+		return;
+
 	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 				      be32_to_cpu(adapter->login_rsp_buf->
 				      off_rxadd_subcrqs));
@@ -287,6 +323,15 @@ failure:
 	dev_kfree_skb_any(skb);
 	adapter->replenish_add_buff_failure++;
 	atomic_add(buffers_added, &pool->available);
+
+	if (lpar_rc == H_CLOSED) {
+		/* Disable buffer pool replenishment and report carrier off if
+		 * queue is closed. Firmware guarantees that a signal will
+		 * be sent to the driver, triggering a reset.
+		 */
+		deactivate_rx_pools(adapter);
+		netif_carrier_off(adapter->netdev);
+	}
 }
 
 static void replenish_pools(struct ibmvnic_adapter *adapter)
@@ -331,6 +376,35 @@ static int init_stats_token(struct ibmvnic_adapter *adapter)
 	return 0;
 }
 
+static int reset_rx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_rx_pool *rx_pool;
+	int rx_scrqs;
+	int i, j, rc;
+
+	rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+	for (i = 0; i < rx_scrqs; i++) {
+		rx_pool = &adapter->rx_pool[i];
+
+		rc = reset_long_term_buff(adapter, &rx_pool->long_term_buff);
+		if (rc)
+			return rc;
+
+		for (j = 0; j < rx_pool->size; j++)
+			rx_pool->free_map[j] = j;
+
+		memset(rx_pool->rx_buff, 0,
+		       rx_pool->size * sizeof(struct ibmvnic_rx_buff));
+
+		atomic_set(&rx_pool->available, 0);
+		rx_pool->next_alloc = 0;
+		rx_pool->next_free = 0;
+		rx_pool->active = 1;
+	}
+
+	return 0;
+}
+
 static void release_rx_pools(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_rx_pool *rx_pool;
@@ -432,6 +506,34 @@ static int init_rx_pools(struct net_device *netdev)
 	return 0;
 }
 
+static int reset_tx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_tx_pool *tx_pool;
+	int tx_scrqs;
+	int i, j, rc;
+
+	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	for (i = 0; i < tx_scrqs; i++) {
+		tx_pool = &adapter->tx_pool[i];
+
+		rc = reset_long_term_buff(adapter, &tx_pool->long_term_buff);
+		if (rc)
+			return rc;
+
+		memset(tx_pool->tx_buff, 0,
+		       adapter->req_tx_entries_per_subcrq *
+		       sizeof(struct ibmvnic_tx_buff));
+
+		for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
+			tx_pool->free_map[j] = j;
+
+		tx_pool->consumer_index = 0;
+		tx_pool->producer_index = 0;
+	}
+
+	return 0;
+}
+
 static void release_tx_pools(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_tx_pool *tx_pool;
@@ -518,6 +620,32 @@ static void release_error_buffers(struct ibmvnic_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
 }
 
+static void ibmvnic_napi_enable(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	if (adapter->napi_enabled)
+		return;
+
+	for (i = 0; i < adapter->req_rx_queues; i++)
+		napi_enable(&adapter->napi[i]);
+
+	adapter->napi_enabled = true;
+}
+
+static void ibmvnic_napi_disable(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	if (!adapter->napi_enabled)
+		return;
+
+	for (i = 0; i < adapter->req_rx_queues; i++)
+		napi_disable(&adapter->napi[i]);
+
+	adapter->napi_enabled = false;
+}
+
 static int ibmvnic_login(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
@@ -635,12 +763,6 @@ static int init_resources(struct ibmvnic_adapter *adapter)
 	if (rc)
 		return rc;
 
-	rc = init_sub_crq_irqs(adapter);
-	if (rc) {
-		netdev_err(netdev, "failed to initialize sub crq irqs\n");
-		return -1;
-	}
-
 	rc = init_stats_token(adapter);
 	if (rc)
 		return rc;
@@ -674,9 +796,7 @@ static int __ibmvnic_open(struct net_device *netdev)
 
 	adapter->state = VNIC_OPENING;
 	replenish_pools(adapter);
-
-	for (i = 0; i < adapter->req_rx_queues; i++)
-		napi_enable(&adapter->napi[i]);
+	ibmvnic_napi_enable(adapter);
 
 	/* We're ready to receive frames, enable the sub-crq interrupts and
 	 * set the logical link state to up
@@ -778,14 +898,14 @@ static int __ibmvnic_close(struct net_device *netdev)
 	int i;
 
 	adapter->state = VNIC_CLOSING;
-	netif_tx_stop_all_queues(netdev);
 
-	if (adapter->napi) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			napi_disable(&adapter->napi[i]);
-	}
+	/* ensure that transmissions are stopped if called by do_reset */
+	if (adapter->resetting)
+		netif_tx_disable(netdev);
+	else
+		netif_tx_stop_all_queues(netdev);
 
-	clean_tx_pools(adapter);
+	ibmvnic_napi_disable(adapter);
 
 	if (adapter->tx_scrq) {
 		for (i = 0; i < adapter->req_tx_queues; i++)
@@ -814,6 +934,7 @@ static int __ibmvnic_close(struct net_device *netdev)
 		}
 	}
 
+	clean_tx_pools(adapter);
 	adapter->state = VNIC_CLOSED;
 	return rc;
 }
@@ -1092,8 +1213,14 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		dev_kfree_skb_any(skb);
 		tx_buff->skb = NULL;
 
-		if (lpar_rc == H_CLOSED)
-			netif_stop_subqueue(netdev, queue_num);
+		if (lpar_rc == H_CLOSED) {
+			/* Disable TX and report carrier off if queue is closed.
+			 * Firmware guarantees that a signal will be sent to the
+			 * driver, triggering a reset or some other action.
+			 */
+			netif_tx_stop_all_queues(netdev);
+			netif_carrier_off(netdev);
+		}
 
 		tx_send_failed++;
 		tx_dropped++;
@@ -1206,37 +1333,39 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	if (rc)
 		return rc;
 
-	/* remove the closed state so when we call open it appears
-	 * we are coming from the probed state.
-	 */
-	adapter->state = VNIC_PROBED;
+	if (adapter->reset_reason != VNIC_RESET_NON_FATAL) {
+		/* remove the closed state so when we call open it appears
+		 * we are coming from the probed state.
+		 */
+		adapter->state = VNIC_PROBED;
 
-	release_resources(adapter);
-	release_sub_crqs(adapter);
-	release_crq_queue(adapter);
+		rc = ibmvnic_init(adapter);
+		if (rc)
+			return 0;
 
-	rc = ibmvnic_init(adapter);
-	if (rc)
-		return 0;
+		/* If the adapter was in PROBE state prior to the reset,
+		 * exit here.
+		 */
+		if (reset_state == VNIC_PROBED)
+			return 0;
 
-	/* If the adapter was in PROBE state prior to the reset, exit here. */
-	if (reset_state == VNIC_PROBED)
-		return 0;
+		rc = ibmvnic_login(netdev);
+		if (rc) {
+			adapter->state = VNIC_PROBED;
+			return 0;
+		}
 
-	rc = ibmvnic_login(netdev);
-	if (rc) {
-		adapter->state = VNIC_PROBED;
-		return 0;
-	}
+		rc = reset_tx_pools(adapter);
+		if (rc)
+			return rc;
 
-	rtnl_lock();
-	rc = init_resources(adapter);
-	rtnl_unlock();
-	if (rc)
-		return rc;
+		rc = reset_rx_pools(adapter);
+		if (rc)
+			return rc;
 
-	if (reset_state == VNIC_CLOSED)
-		return 0;
+		if (reset_state == VNIC_CLOSED)
+			return 0;
+	}
 
 	rc = __ibmvnic_open(netdev);
 	if (rc) {
@@ -1254,6 +1383,9 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_schedule(&adapter->napi[i]);
 
+	if (adapter->reset_reason != VNIC_RESET_FAILOVER)
+		netdev_notify_peers(netdev);
+
 	return 0;
 }
 
@@ -1313,6 +1445,7 @@ static void __ibmvnic_reset(struct work_struct *work)
 
 	if (rc) {
 		free_all_rwi(adapter);
+		mutex_unlock(&adapter->reset_lock);
 		return;
 	}
 
@@ -1333,6 +1466,12 @@ static void ibmvnic_reset(struct ibmvnic_adapter *adapter,
 		return;
 	}
 
+	if (adapter->state == VNIC_PROBING) {
+		netdev_warn(netdev, "Adapter reset during probe\n");
+		adapter->init_done_rc = EAGAIN;
+		return;
+	}
+
 	mutex_lock(&adapter->rwi_lock);
 
 	list_for_each(entry, &adapter->rwi_list) {
@@ -1383,6 +1522,7 @@ static int ibmvnic_poll(struct napi_struct *napi, int budget)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	int scrq_num = (int)(napi - adapter->napi);
 	int frames_processed = 0;
+
 restart_poll:
 	while (frames_processed < budget) {
 		struct sk_buff *skb;
@@ -1392,6 +1532,12 @@ restart_poll:
 		u16 offset;
 		u8 flags = 0;
 
+		if (unlikely(adapter->resetting)) {
+			enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
+			napi_complete_done(napi, frames_processed);
+			return frames_processed;
+		}
+
 		if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
 			break;
 		next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
@@ -1441,7 +1587,9 @@ restart_poll:
 		netdev->stats.rx_bytes += length;
 		frames_processed++;
 	}
-	replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
+
+	if (adapter->state != VNIC_CLOSING)
+		replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
 
 	if (frames_processed < budget) {
 		enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
@@ -1614,6 +1762,44 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = {
 
 /* Routines for managing CRQs/sCRQs  */
 
+static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter,
+				   struct ibmvnic_sub_crq_queue *scrq)
+{
+	int rc;
+
+	if (scrq->irq) {
+		free_irq(scrq->irq, scrq);
+		irq_dispose_mapping(scrq->irq);
+		scrq->irq = 0;
+	}
+
+	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
+	scrq->cur = 0;
+
+	rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token,
+			   4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq);
+	return rc;
+}
+
+static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter)
+{
+	int i, rc;
+
+	for (i = 0; i < adapter->req_tx_queues; i++) {
+		rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]);
+		if (rc)
+			return rc;
+	}
+
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		rc = reset_one_sub_crq_queue(adapter, adapter->rx_scrq[i]);
+		if (rc)
+			return rc;
+	}
+
+	return rc;
+}
+
 static void release_sub_crq_queue(struct ibmvnic_adapter *adapter,
 				  struct ibmvnic_sub_crq_queue *scrq)
 {
@@ -2109,8 +2295,7 @@ static int pending_scrq(struct ibmvnic_adapter *adapter,
 {
 	union sub_crq *entry = &scrq->msgs[scrq->cur];
 
-	if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP ||
-	    adapter->state == VNIC_CLOSING)
+	if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP)
 		return 1;
 	else
 		return 0;
@@ -2748,6 +2933,8 @@ static void handle_error_indication(union ibmvnic_crq *crq,
 
 	if (crq->error_indication.flags & IBMVNIC_FATAL_ERROR)
 		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
+	else
+		ibmvnic_reset(adapter, VNIC_RESET_NON_FATAL);
 }
 
 static void handle_change_mac_rsp(union ibmvnic_crq *crq,
@@ -2899,36 +3086,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	return 0;
 }
 
-static void handle_request_map_rsp(union ibmvnic_crq *crq,
-				   struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	u8 map_id = crq->request_map_rsp.map_id;
-	int tx_subcrqs;
-	int rx_subcrqs;
-	long rc;
-	int i;
-
-	tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
-	rx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
-
-	rc = crq->request_map_rsp.rc.code;
-	if (rc) {
-		dev_err(dev, "Error %ld in REQUEST_MAP_RSP\n", rc);
-		adapter->map_id--;
-		/* need to find and zero tx/rx_pool map_id */
-		for (i = 0; i < tx_subcrqs; i++) {
-			if (adapter->tx_pool[i].long_term_buff.map_id == map_id)
-				adapter->tx_pool[i].long_term_buff.map_id = 0;
-		}
-		for (i = 0; i < rx_subcrqs; i++) {
-			if (adapter->rx_pool[i].long_term_buff.map_id == map_id)
-				adapter->rx_pool[i].long_term_buff.map_id = 0;
-		}
-	}
-	complete(&adapter->fw_done);
-}
-
 static void handle_request_unmap_rsp(union ibmvnic_crq *crq,
 				     struct ibmvnic_adapter *adapter)
 {
@@ -3153,6 +3310,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		switch (gen_crq->cmd) {
 		case IBMVNIC_CRQ_INIT:
 			dev_info(dev, "Partner initialized\n");
+			adapter->from_passive_init = true;
+			complete(&adapter->init_done);
 			break;
 		case IBMVNIC_CRQ_INIT_COMPLETE:
 			dev_info(dev, "Partner initialization complete\n");
@@ -3207,7 +3366,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		handle_query_map_rsp(crq, adapter);
 		break;
 	case REQUEST_MAP_RSP:
-		handle_request_map_rsp(crq, adapter);
+		adapter->fw_done_rc = crq->request_map_rsp.rc.code;
+		complete(&adapter->fw_done);
 		break;
 	case REQUEST_UNMAP_RSP:
 		handle_request_unmap_rsp(crq, adapter);
@@ -3461,29 +3621,61 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 	unsigned long timeout = msecs_to_jiffies(30000);
 	int rc;
 
-	rc = init_crq_queue(adapter);
+	if (adapter->resetting) {
+		rc = ibmvnic_reset_crq(adapter);
+		if (!rc)
+			rc = vio_enable_interrupts(adapter->vdev);
+	} else {
+		rc = init_crq_queue(adapter);
+	}
+
 	if (rc) {
 		dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc);
 		return rc;
 	}
 
+	adapter->from_passive_init = false;
+
 	init_completion(&adapter->init_done);
+	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
 		dev_err(dev, "Initialization sequence timed out\n");
+		return -1;
+	}
+
+	if (adapter->init_done_rc) {
 		release_crq_queue(adapter);
+		return adapter->init_done_rc;
+	}
+
+	if (adapter->from_passive_init) {
+		adapter->state = VNIC_OPEN;
+		adapter->from_passive_init = false;
 		return -1;
 	}
 
-	rc = init_sub_crqs(adapter);
+	if (adapter->resetting)
+		rc = reset_sub_crq_queues(adapter);
+	else
+		rc = init_sub_crqs(adapter);
 	if (rc) {
 		dev_err(dev, "Initialization of sub crqs failed\n");
 		release_crq_queue(adapter);
+		return rc;
+	}
+
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(dev, "Failed to initialize sub crq irqs\n");
+		release_crq_queue(adapter);
 	}
 
 	return rc;
 }
 
+static struct device_attribute dev_attr_failover;
+
 static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 {
 	struct ibmvnic_adapter *adapter;
@@ -3532,17 +3724,26 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	mutex_init(&adapter->rwi_lock);
 	adapter->resetting = false;
 
-	rc = ibmvnic_init(adapter);
+	do {
+		rc = ibmvnic_init(adapter);
+		if (rc && rc != EAGAIN) {
+			free_netdev(netdev);
+			return rc;
+		}
+	} while (rc == EAGAIN);
+
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
+
+	rc = device_create_file(&dev->dev, &dev_attr_failover);
 	if (rc) {
 		free_netdev(netdev);
 		return rc;
 	}
 
-	netdev->mtu = adapter->req_mtu - ETH_HLEN;
-
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
+		device_remove_file(&dev->dev, &dev_attr_failover);
 		free_netdev(netdev);
 		return rc;
 	}
@@ -3568,12 +3769,49 @@ static int ibmvnic_remove(struct vio_dev *dev)
 	adapter->state = VNIC_REMOVED;
 
 	mutex_unlock(&adapter->reset_lock);
+	device_remove_file(&dev->dev, &dev_attr_failover);
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
 
 	return 0;
 }
 
+static ssize_t failover_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	__be64 session_token;
+	long rc;
+
+	if (!sysfs_streq(buf, "1"))
+		return -EINVAL;
+
+	rc = plpar_hcall(H_VIOCTL, retbuf, adapter->vdev->unit_address,
+			 H_GET_SESSION_TOKEN, 0, 0, 0);
+	if (rc) {
+		netdev_err(netdev, "Couldn't retrieve session token, rc %ld\n",
+			   rc);
+		return -EINVAL;
+	}
+
+	session_token = (__be64)retbuf[0];
+	netdev_dbg(netdev, "Initiating client failover, session id %llx\n",
+		   be64_to_cpu(session_token));
+	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
+				H_SESSION_ERR_DETECTED, session_token, 0, 0);
+	if (rc) {
+		netdev_err(netdev, "Client initiated failover failed, rc %ld\n",
+			   rc);
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static DEVICE_ATTR(failover, 0200, NULL, failover_store);
+
 static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev)
 {
 	struct net_device *netdev = dev_get_drvdata(&vdev->dev);
@@ -3610,6 +3848,9 @@ static int ibmvnic_resume(struct device *dev)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	if (adapter->state != VNIC_OPEN)
+		return 0;
+
 	/* kick the interrupt handlers just in case we lost an interrupt */
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq,
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 4702b48cfa44..8eff6e15f4bb 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -595,7 +595,7 @@ struct ibmvnic_request_map_rsp {
 	u8 cmd;
 	u8 reserved1;
 	u8 map_id;
-	u8 reserved2[4];
+	u8 reserved2[8];
 	struct ibmvnic_rc rc;
 } __packed __aligned(8);
 
@@ -925,6 +925,7 @@ enum vnic_state {VNIC_PROBING = 1,
 enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
 			   VNIC_RESET_MOBILITY,
 			   VNIC_RESET_FATAL,
+			   VNIC_RESET_NON_FATAL,
 			   VNIC_RESET_TIMEOUT};
 
 struct ibmvnic_rwi {
@@ -987,6 +988,7 @@ struct ibmvnic_adapter {
 	spinlock_t error_list_lock;
 
 	struct completion fw_done;
+	int fw_done_rc;
 
 	/* partner capabilities */
 	u64 min_tx_queues;
@@ -1031,4 +1033,5 @@ struct ibmvnic_adapter {
 	struct list_head rwi_list;
 	struct work_struct ibmvnic_reset;
 	bool resetting;
+	bool napi_enabled, from_passive_init;
 };