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

Pull networking fixes from David Miller:
 "Hopefully the last pull request for this release. Fingers crossed:

   1) Only refcount ESP stats on full sockets, from Martin Willi.

   2) Missing barriers in AF_UNIX, from Al Viro.

   3) RCU protection fixes in ipv6 route code, from Paolo Abeni.

   4) Avoid false positives in untrusted GSO validation, from Willem de
      Bruijn.

   5) Forwarded mesh packets in mac80211 need more tailroom allocated,
      from Felix Fietkau.

   6) Use operstate consistently for linkup in team driver, from George
      Wilkie.

   7) ThunderX bug fixes from Vadim Lomovtsev. Mostly races between VF
      and PF code paths.

   8) Purge ipv6 exceptions during netdevice removal, from Paolo Abeni.

   9) nfp eBPF code gen fixes from Jiong Wang.

  10) bnxt_en firmware timeout fix from Michael Chan.

  11) Use after free in udp/udpv6 error handlers, from Paolo Abeni.

  12) Fix a race in x25_bind triggerable by syzbot, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (65 commits)
  net: phy: realtek: Dummy IRQ calls for RTL8366RB
  tcp: repaired skbs must init their tso_segs
  net/x25: fix a race in x25_bind()
  net: dsa: Remove documentation for port_fdb_prepare
  Revert "bridge: do not add port to router list when receives query with source 0.0.0.0"
  selftests: fib_tests: sleep after changing carrier. again.
  net: set static variable an initial value in atl2_probe()
  net: phy: marvell10g: Fix Multi-G advertisement to only advertise 10G
  bpf, doc: add bpf list as secondary entry to maintainers file
  udp: fix possible user after free in error handler
  udpv6: fix possible user after free in error handler
  fou6: fix proto error handler argument type
  udpv6: add the required annotation to mib type
  mdio_bus: Fix use-after-free on device_register fails
  net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255
  bnxt_en: Wait longer for the firmware message response to complete.
  bnxt_en: Fix typo in firmware message timeout logic.
  nfp: bpf: fix ALU32 high bits clearance bug
  nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K
  Documentation: networking: switchdev: Update port parent ID section
  ...

1 files changed, 86 insertions, 42 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 88f8a8fa93cd..503cfadff4ac 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -68,9 +68,6 @@ module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
-/* workqueue for handling kernel ndo_set_rx_mode() calls */
-static struct workqueue_struct *nicvf_rx_mode_wq;
-
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -127,6 +124,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 {
 	int timeout = NIC_MBOX_MSG_TIMEOUT;
 	int sleep = 10;
+	int ret = 0;
+
+	mutex_lock(&nic->rx_mode_mtx);
 
 	nic->pf_acked = false;
 	nic->pf_nacked = false;
@@ -139,7 +139,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF NACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EINVAL;
+			ret = -EINVAL;
+			break;
 		}
 		msleep(sleep);
 		if (nic->pf_acked)
@@ -149,10 +150,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF didn't ACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EBUSY;
+			ret = -EBUSY;
+			break;
 		}
 	}
-	return 0;
+	mutex_unlock(&nic->rx_mode_mtx);
+	return ret;
 }
 
 /* Checks if VF is able to comminicate with PF
@@ -172,6 +175,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic)
 	return 1;
 }
 
+static void nicvf_send_cfg_done(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	if (nicvf_send_msg_to_pf(nic, &mbx)) {
+		netdev_err(nic->netdev,
+			   "PF didn't respond to CFG DONE msg\n");
+	}
+}
+
 static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx)
 {
 	if (bgx->rx)
@@ -228,21 +242,24 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 		break;
 	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
 		nic->pf_acked = true;
-		nic->link_up = mbx.link_status.link_up;
-		nic->duplex = mbx.link_status.duplex;
-		nic->speed = mbx.link_status.speed;
-		nic->mac_type = mbx.link_status.mac_type;
-		if (nic->link_up) {
-			netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n",
-				    nic->speed,
-				    nic->duplex == DUPLEX_FULL ?
-				    "Full" : "Half");
-			netif_carrier_on(nic->netdev);
-			netif_tx_start_all_queues(nic->netdev);
-		} else {
-			netdev_info(nic->netdev, "Link is Down\n");
-			netif_carrier_off(nic->netdev);
-			netif_tx_stop_all_queues(nic->netdev);
+		if (nic->link_up != mbx.link_status.link_up) {
+			nic->link_up = mbx.link_status.link_up;
+			nic->duplex = mbx.link_status.duplex;
+			nic->speed = mbx.link_status.speed;
+			nic->mac_type = mbx.link_status.mac_type;
+			if (nic->link_up) {
+				netdev_info(nic->netdev,
+					    "Link is Up %d Mbps %s duplex\n",
+					    nic->speed,
+					    nic->duplex == DUPLEX_FULL ?
+					    "Full" : "Half");
+				netif_carrier_on(nic->netdev);
+				netif_tx_start_all_queues(nic->netdev);
+			} else {
+				netdev_info(nic->netdev, "Link is Down\n");
+				netif_carrier_off(nic->netdev);
+				netif_tx_stop_all_queues(nic->netdev);
+			}
 		}
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
@@ -1311,6 +1328,11 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
+	cancel_delayed_work_sync(&nic->link_change_work);
+
+	/* wait till all queued set_rx_mode tasks completes */
+	drain_workqueue(nic->nicvf_rx_mode_wq);
+
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
 
@@ -1410,13 +1432,27 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
 	return nicvf_send_msg_to_pf(nic, &mbx);
 }
 
+static void nicvf_link_status_check_task(struct work_struct *work_arg)
+{
+	struct nicvf *nic = container_of(work_arg,
+					 struct nicvf,
+					 link_change_work.work);
+	union nic_mbx mbx = {};
+	mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+	nicvf_send_msg_to_pf(nic, &mbx);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 2 * HZ);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
 	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-	union nic_mbx mbx = {};
+
+	/* wait till all queued set_rx_mode tasks completes if any */
+	drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1512,8 +1548,12 @@ int nicvf_open(struct net_device *netdev)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
 	/* Send VF config done msg to PF */
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
-	nicvf_write_to_mbx(nic, &mbx);
+	nicvf_send_cfg_done(nic);
+
+	INIT_DELAYED_WORK(&nic->link_change_work,
+			  nicvf_link_status_check_task);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 0);
 
 	return 0;
 cleanup:
@@ -1941,15 +1981,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 
 	/* flush DMAC filters and reset RX mode */
 	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
-	nicvf_send_msg_to_pf(nic, &mbx);
+	if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+		goto free_mc;
 
 	if (mode & BGX_XCAST_MCAST_FILTER) {
 		/* once enabling filtering, we need to signal to PF to add
 		 * its' own LMAC to the filter to accept packets for it.
 		 */
 		mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-		mbx.xcast.data.mac = 0;
-		nicvf_send_msg_to_pf(nic, &mbx);
+		mbx.xcast.mac = 0;
+		if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+			goto free_mc;
 	}
 
 	/* check if we have any specific MACs to be added to PF DMAC filter */
@@ -1957,23 +1999,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 		/* now go through kernel list of MACs and add them one by one */
 		for (idx = 0; idx < mc_addrs->count; idx++) {
 			mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-			mbx.xcast.data.mac = mc_addrs->mc[idx];
-			nicvf_send_msg_to_pf(nic, &mbx);
+			mbx.xcast.mac = mc_addrs->mc[idx];
+			if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+				goto free_mc;
 		}
-		kfree(mc_addrs);
 	}
 
 	/* and finally set rx mode for PF accordingly */
 	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
-	mbx.xcast.data.mode = mode;
+	mbx.xcast.mode = mode;
 
 	nicvf_send_msg_to_pf(nic, &mbx);
+free_mc:
+	kfree(mc_addrs);
 }
 
 static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 {
 	struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
-						  work.work);
+						  work);
 	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
 	u8 mode;
 	struct xcast_addr_list *mc;
@@ -2030,7 +2074,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev)
 	kfree(nic->rx_mode_work.mc);
 	nic->rx_mode_work.mc = mc_list;
 	nic->rx_mode_work.mode = mode;
-	queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0);
+	queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work);
 	spin_unlock(&nic->rx_mode_wq_lock);
 }
 
@@ -2187,8 +2231,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
-	INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+	nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d",
+							WQ_MEM_RECLAIM,
+							nic->vf_id);
+	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
 	spin_lock_init(&nic->rx_mode_wq_lock);
+	mutex_init(&nic->rx_mode_mtx);
 
 	err = register_netdev(netdev);
 	if (err) {
@@ -2228,13 +2276,15 @@ static void nicvf_remove(struct pci_dev *pdev)
 	nic = netdev_priv(netdev);
 	pnetdev = nic->pnicvf->netdev;
 
-	cancel_delayed_work_sync(&nic->rx_mode_work.work);
-
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
 	 */
 	if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED))
 		unregister_netdev(pnetdev);
+	if (nic->nicvf_rx_mode_wq) {
+		destroy_workqueue(nic->nicvf_rx_mode_wq);
+		nic->nicvf_rx_mode_wq = NULL;
+	}
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
 	if (nic->drv_stats)
@@ -2261,17 +2311,11 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-	nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic",
-						   WQ_MEM_RECLAIM);
 	return pci_register_driver(&nicvf_driver);
 }
 
 static void __exit nicvf_cleanup_module(void)
 {
-	if (nicvf_rx_mode_wq) {
-		destroy_workqueue(nicvf_rx_mode_wq);
-		nicvf_rx_mode_wq = NULL;
-	}
 	pci_unregister_driver(&nicvf_driver);
 }