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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 200 insertions, 23 deletions

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5ec1185808e5..d0e196bff081 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -109,13 +109,14 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
 					struct ibmvnic_sub_crq_queue *);
 static int ibmvnic_poll(struct napi_struct *napi, int data);
 static void send_map_query(struct ibmvnic_adapter *adapter);
-static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
-static void send_request_unmap(struct ibmvnic_adapter *, u8);
+static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
+static int send_request_unmap(struct ibmvnic_adapter *, u8);
 static int send_login(struct ibmvnic_adapter *adapter);
 static void send_cap_queries(struct ibmvnic_adapter *adapter);
 static int init_sub_crqs(struct ibmvnic_adapter *);
 static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
 static int ibmvnic_init(struct ibmvnic_adapter *);
+static int ibmvnic_reset_init(struct ibmvnic_adapter *);
 static void release_crq_queue(struct ibmvnic_adapter *);
 static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p);
 static int init_crq_queue(struct ibmvnic_adapter *adapter);
@@ -172,6 +173,7 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb, int size)
 {
 	struct device *dev = &adapter->vdev->dev;
+	int rc;
 
 	ltb->size = size;
 	ltb->buff = dma_alloc_coherent(dev, ltb->size, &ltb->addr,
@@ -185,8 +187,12 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 	adapter->map_id++;
 
 	init_completion(&adapter->fw_done);
-	send_request_map(adapter, ltb->addr,
-			 ltb->size, ltb->map_id);
+	rc = send_request_map(adapter, ltb->addr,
+			      ltb->size, ltb->map_id);
+	if (rc) {
+		dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
+		return rc;
+	}
 	wait_for_completion(&adapter->fw_done);
 
 	if (adapter->fw_done_rc) {
@@ -215,10 +221,14 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 static int reset_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb)
 {
+	int rc;
+
 	memset(ltb->buff, 0, ltb->size);
 
 	init_completion(&adapter->fw_done);
-	send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id);
+	rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id);
+	if (rc)
+		return rc;
 	wait_for_completion(&adapter->fw_done);
 
 	if (adapter->fw_done_rc) {
@@ -789,6 +799,7 @@ static void release_napi(struct ibmvnic_adapter *adapter)
 	kfree(adapter->napi);
 	adapter->napi = NULL;
 	adapter->num_active_rx_napi = 0;
+	adapter->napi_enabled = false;
 }
 
 static int ibmvnic_login(struct net_device *netdev)
@@ -924,6 +935,10 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
 			/* Partuial success, delay and re-send */
 			mdelay(1000);
 			resend = true;
+		} else if (adapter->init_done_rc) {
+			netdev_warn(netdev, "Unable to set link state, rc=%d\n",
+				    adapter->init_done_rc);
+			return adapter->init_done_rc;
 		}
 	} while (resend);
 
@@ -956,6 +971,7 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter)
 	struct device *dev = &adapter->vdev->dev;
 	union ibmvnic_crq crq;
 	int len = 0;
+	int rc;
 
 	if (adapter->vpd->buff)
 		len = adapter->vpd->len;
@@ -963,7 +979,9 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter)
 	init_completion(&adapter->fw_done);
 	crq.get_vpd_size.first = IBMVNIC_CRQ_CMD;
 	crq.get_vpd_size.cmd = GET_VPD_SIZE;
-	ibmvnic_send_crq(adapter, &crq);
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc)
+		return rc;
 	wait_for_completion(&adapter->fw_done);
 
 	if (!adapter->vpd->len)
@@ -996,7 +1014,12 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter)
 	crq.get_vpd.cmd = GET_VPD;
 	crq.get_vpd.ioba = cpu_to_be32(adapter->vpd->dma_addr);
 	crq.get_vpd.len = cpu_to_be32((u32)adapter->vpd->len);
-	ibmvnic_send_crq(adapter, &crq);
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc) {
+		kfree(adapter->vpd->buff);
+		adapter->vpd->buff = NULL;
+		return rc;
+	}
 	wait_for_completion(&adapter->fw_done);
 
 	return 0;
@@ -1695,6 +1718,7 @@ static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	struct sockaddr *addr = p;
 	union ibmvnic_crq crq;
+	int rc;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
@@ -1705,7 +1729,9 @@ static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
 	ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data);
 
 	init_completion(&adapter->fw_done);
-	ibmvnic_send_crq(adapter, &crq);
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc)
+		return rc;
 	wait_for_completion(&adapter->fw_done);
 	/* netdev->dev_addr is changed in handle_change_mac_rsp function */
 	return adapter->fw_done_rc ? -EIO : 0;
@@ -1787,7 +1813,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			return rc;
 		}
 
-		rc = ibmvnic_init(adapter);
+		rc = ibmvnic_reset_init(adapter);
 		if (rc)
 			return IBMVNIC_INIT_FAILED;
 
@@ -1857,6 +1883,85 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	return 0;
 }
 
+static int do_hard_reset(struct ibmvnic_adapter *adapter,
+			 struct ibmvnic_rwi *rwi, u32 reset_state)
+{
+	struct net_device *netdev = adapter->netdev;
+	int rc;
+
+	netdev_dbg(adapter->netdev, "Hard resetting driver (%d)\n",
+		   rwi->reset_reason);
+
+	netif_carrier_off(netdev);
+	adapter->reset_reason = rwi->reset_reason;
+
+	ibmvnic_cleanup(netdev);
+	release_resources(adapter);
+	release_sub_crqs(adapter, 0);
+	release_crq_queue(adapter);
+
+	/* remove the closed state so when we call open it appears
+	 * we are coming from the probed state.
+	 */
+	adapter->state = VNIC_PROBED;
+
+	rc = init_crq_queue(adapter);
+	if (rc) {
+		netdev_err(adapter->netdev,
+			   "Couldn't initialize crq. rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = ibmvnic_init(adapter);
+	if (rc)
+		return rc;
+
+	/* 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;
+	}
+	/* netif_set_real_num_xx_queues needs to take rtnl lock here
+	 * unless wait_for_reset is set, in which case the rtnl lock
+	 * has already been taken before initializing the reset
+	 */
+	if (!adapter->wait_for_reset) {
+		rtnl_lock();
+		rc = init_resources(adapter);
+		rtnl_unlock();
+	} else {
+		rc = init_resources(adapter);
+	}
+	if (rc)
+		return rc;
+
+	ibmvnic_disable_irqs(adapter);
+	adapter->state = VNIC_CLOSED;
+
+	if (reset_state == VNIC_CLOSED)
+		return 0;
+
+	rc = __ibmvnic_open(netdev);
+	if (rc) {
+		if (list_empty(&adapter->rwi_list))
+			adapter->state = VNIC_CLOSED;
+		else
+			adapter->state = reset_state;
+
+		return 0;
+	}
+
+	netif_carrier_on(netdev);
+
+	return 0;
+}
+
 static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_rwi *rwi;
@@ -1898,14 +2003,19 @@ static void __ibmvnic_reset(struct work_struct *work)
 	netdev = adapter->netdev;
 
 	mutex_lock(&adapter->reset_lock);
-	adapter->resetting = true;
 	reset_state = adapter->state;
 
 	rwi = get_next_rwi(adapter);
 	while (rwi) {
-		rc = do_reset(adapter, rwi, reset_state);
+		if (adapter->force_reset_recovery) {
+			adapter->force_reset_recovery = false;
+			rc = do_hard_reset(adapter, rwi, reset_state);
+		} else {
+			rc = do_reset(adapter, rwi, reset_state);
+		}
 		kfree(rwi);
-		if (rc && rc != IBMVNIC_INIT_FAILED)
+		if (rc && rc != IBMVNIC_INIT_FAILED &&
+		    !adapter->force_reset_recovery)
 			break;
 
 		rwi = get_next_rwi(adapter);
@@ -1931,9 +2041,9 @@ static void __ibmvnic_reset(struct work_struct *work)
 static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 			 enum ibmvnic_reset_reason reason)
 {
+	struct list_head *entry, *tmp_entry;
 	struct ibmvnic_rwi *rwi, *tmp;
 	struct net_device *netdev = adapter->netdev;
-	struct list_head *entry;
 	int ret;
 
 	if (adapter->state == VNIC_REMOVING ||
@@ -1969,11 +2079,17 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 		ret = ENOMEM;
 		goto err;
 	}
-
+	/* if we just received a transport event,
+	 * flush reset queue and process this reset
+	 */
+	if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) {
+		list_for_each_safe(entry, tmp_entry, &adapter->rwi_list)
+			list_del(entry);
+	}
 	rwi->reset_reason = reason;
 	list_add_tail(&rwi->list, &adapter->rwi_list);
 	mutex_unlock(&adapter->rwi_lock);
-
+	adapter->resetting = true;
 	netdev_dbg(adapter->netdev, "Scheduling reset (reason %d)\n", reason);
 	schedule_work(&adapter->ibmvnic_reset);
 
@@ -2369,6 +2485,7 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 	struct ibmvnic_adapter *adapter = netdev_priv(dev);
 	union ibmvnic_crq crq;
 	int i, j;
+	int rc;
 
 	memset(&crq, 0, sizeof(crq));
 	crq.request_statistics.first = IBMVNIC_CRQ_CMD;
@@ -2379,7 +2496,9 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 
 	/* Wait for data to be written */
 	init_completion(&adapter->stats_done);
-	ibmvnic_send_crq(adapter, &crq);
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc)
+		return;
 	wait_for_completion(&adapter->stats_done);
 
 	for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
@@ -3154,6 +3273,12 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter,
 		   (unsigned long int)cpu_to_be64(u64_crq[0]),
 		   (unsigned long int)cpu_to_be64(u64_crq[1]));
 
+	if (!adapter->crq.active &&
+	    crq->generic.first != IBMVNIC_CRQ_INIT_CMD) {
+		dev_warn(dev, "Invalid request detected while CRQ is inactive, possible device state change during reset\n");
+		return -EINVAL;
+	}
+
 	/* Make sure the hypervisor sees the complete request */
 	mb();
 
@@ -3378,8 +3503,8 @@ buf_alloc_failed:
 	return -1;
 }
 
-static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr,
-			     u32 len, u8 map_id)
+static int send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr,
+			    u32 len, u8 map_id)
 {
 	union ibmvnic_crq crq;
 
@@ -3389,10 +3514,10 @@ static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr,
 	crq.request_map.map_id = map_id;
 	crq.request_map.ioba = cpu_to_be32(addr);
 	crq.request_map.len = cpu_to_be32(len);
-	ibmvnic_send_crq(adapter, &crq);
+	return ibmvnic_send_crq(adapter, &crq);
 }
 
-static void send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id)
+static int send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id)
 {
 	union ibmvnic_crq crq;
 
@@ -3400,7 +3525,7 @@ static void send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id)
 	crq.request_unmap.first = IBMVNIC_CRQ_CMD;
 	crq.request_unmap.cmd = REQUEST_UNMAP;
 	crq.request_unmap.map_id = map_id;
-	ibmvnic_send_crq(adapter, &crq);
+	return ibmvnic_send_crq(adapter, &crq);
 }
 
 static void send_map_query(struct ibmvnic_adapter *adapter)
@@ -4227,11 +4352,15 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			dev_info(dev, "Partner initialized\n");
 			adapter->from_passive_init = true;
 			adapter->failover_pending = false;
-			complete(&adapter->init_done);
+			if (!completion_done(&adapter->init_done)) {
+				complete(&adapter->init_done);
+				adapter->init_done_rc = -EIO;
+			}
 			ibmvnic_reset(adapter, VNIC_RESET_FAILOVER);
 			break;
 		case IBMVNIC_CRQ_INIT_COMPLETE:
 			dev_info(dev, "Partner initialization complete\n");
+			adapter->crq.active = true;
 			send_version_xchg(adapter);
 			break;
 		default:
@@ -4240,6 +4369,9 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		return;
 	case IBMVNIC_CRQ_XPORT_EVENT:
 		netif_carrier_off(netdev);
+		adapter->crq.active = false;
+		if (adapter->resetting)
+			adapter->force_reset_recovery = true;
 		if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
 			dev_info(dev, "Migrated, re-enabling adapter\n");
 			ibmvnic_reset(adapter, VNIC_RESET_MOBILITY);
@@ -4427,6 +4559,7 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter)
 	/* Clean out the queue */
 	memset(crq->msgs, 0, PAGE_SIZE);
 	crq->cur = 0;
+	crq->active = false;
 
 	/* And re-open it again */
 	rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
@@ -4461,6 +4594,7 @@ static void release_crq_queue(struct ibmvnic_adapter *adapter)
 			 DMA_BIDIRECTIONAL);
 	free_page((unsigned long)crq->msgs);
 	crq->msgs = NULL;
+	crq->active = false;
 }
 
 static int init_crq_queue(struct ibmvnic_adapter *adapter)
@@ -4538,7 +4672,7 @@ map_failed:
 	return retrc;
 }
 
-static int ibmvnic_init(struct ibmvnic_adapter *adapter)
+static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	unsigned long timeout = msecs_to_jiffies(30000);
@@ -4597,6 +4731,49 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 	return rc;
 }
 
+static int ibmvnic_init(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	unsigned long timeout = msecs_to_jiffies(30000);
+	int 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 (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)