Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:

 - Add redirect_neigh() BPF packet redirect helper, allowing to limit
   stack traversal in common container configs and improving TCP
   back-pressure.

   Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.

 - Expand netlink policy support and improve policy export to user
   space. (Ge)netlink core performs request validation according to
   declared policies. Expand the expressiveness of those policies
   (min/max length and bitmasks). Allow dumping policies for particular
   commands. This is used for feature discovery by user space (instead
   of kernel version parsing or trial and error).

 - Support IGMPv3/MLDv2 multicast listener discovery protocols in
   bridge.

 - Allow more than 255 IPv4 multicast interfaces.

 - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
   packets of TCPv6.

 - In Multi-patch TCP (MPTCP) support concurrent transmission of data on
   multiple subflows in a load balancing scenario. Enhance advertising
   addresses via the RM_ADDR/ADD_ADDR options.

 - Support SMC-Dv2 version of SMC, which enables multi-subnet
   deployments.

 - Allow more calls to same peer in RxRPC.

 - Support two new Controller Area Network (CAN) protocols - CAN-FD and
   ISO 15765-2:2016.

 - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
   kernel problem.

 - Add TC actions for implementing MPLS L2 VPNs.

 - Improve nexthop code - e.g. handle various corner cases when nexthop
   objects are removed from groups better, skip unnecessary
   notifications and make it easier to offload nexthops into HW by
   converting to a blocking notifier.

 - Support adding and consuming TCP header options by BPF programs,
   opening the doors for easy experimental and deployment-specific TCP
   option use.

 - Reorganize TCP congestion control (CC) initialization to simplify
   life of TCP CC implemented in BPF.

 - Add support for shipping BPF programs with the kernel and loading
   them early on boot via the User Mode Driver mechanism, hence reusing
   all the user space infra we have.

 - Support sleepable BPF programs, initially targeting LSM and tracing.

 - Add bpf_d_path() helper for returning full path for given 'struct
   path'.

 - Make bpf_tail_call compatible with bpf-to-bpf calls.

 - Allow BPF programs to call map_update_elem on sockmaps.

 - Add BPF Type Format (BTF) support for type and enum discovery, as
   well as support for using BTF within the kernel itself (current use
   is for pretty printing structures).

 - Support listing and getting information about bpf_links via the bpf
   syscall.

 - Enhance kernel interfaces around NIC firmware update. Allow
   specifying overwrite mask to control if settings etc. are reset
   during update; report expected max time operation may take to users;
   support firmware activation without machine reboot incl. limits of
   how much impact reset may have (e.g. dropping link or not).

 - Extend ethtool configuration interface to report IEEE-standard
   counters, to limit the need for per-vendor logic in user space.

 - Adopt or extend devlink use for debug, monitoring, fw update in many
   drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx,
   dpaa2-eth).

 - In mlxsw expose critical and emergency SFP module temperature alarms.
   Refactor port buffer handling to make the defaults more suitable and
   support setting these values explicitly via the DCBNL interface.

 - Add XDP support for Intel's igb driver.

 - Support offloading TC flower classification and filtering rules to
   mscc_ocelot switches.

 - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
   fixed interval period pulse generator and one-step timestamping in
   dpaa-eth.

 - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
   offload.

 - Add Lynx PHY/PCS MDIO module, and convert various drivers which have
   this HW to use it. Convert mvpp2 to split PCS.

 - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
   7-port Mediatek MT7531 IP.

 - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
   and wcn3680 support in wcn36xx.

 - Improve performance for packets which don't require much offloads on
   recent Mellanox NICs by 20% by making multiple packets share a
   descriptor entry.

 - Move chelsio inline crypto drivers (for TLS and IPsec) from the
   crypto subtree to drivers/net. Move MDIO drivers out of the phy
   directory.

 - Clean up a lot of W=1 warnings, reportedly the actively developed
   subsections of networking drivers should now build W=1 warning free.

 - Make sure drivers don't use in_interrupt() to dynamically adapt their
   code. Convert tasklets to use new tasklet_setup API (sadly this
   conversion is not yet complete).

* tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits)
  Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH"
  net, sockmap: Don't call bpf_prog_put() on NULL pointer
  bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo
  bpf, sockmap: Add locking annotations to iterator
  netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements
  net: fix pos incrementment in ipv6_route_seq_next
  net/smc: fix invalid return code in smcd_new_buf_create()
  net/smc: fix valid DMBE buffer sizes
  net/smc: fix use-after-free of delayed events
  bpfilter: Fix build error with CONFIG_BPFILTER_UMH
  cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr
  net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info
  bpf: Fix register equivalence tracking.
  rxrpc: Fix loss of final ack on shutdown
  rxrpc: Fix bundle counting for exclusive connections
  netfilter: restore NF_INET_NUMHOOKS
  ibmveth: Identify ingress large send packets.
  ibmveth: Switch order of ibmveth_helper calls.
  cxgb4: handle 4-tuple PEDIT to NAT mode translation
  selftests: Add VRF route leaking tests
  ...

1 files changed, 47 insertions, 19 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 874c70e8cc54..33081b24f10a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -102,7 +102,7 @@ int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 		if (ldev->pf[i].netdev == ndev)
 			return i;
 
-	return -1;
+	return -ENOENT;
 }
 
 static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev)
@@ -271,7 +271,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	bool do_bond, roce_lag;
 	int err;
 
-	if (!dev0 || !dev1)
+	if (!mlx5_lag_is_ready(ldev))
 		return;
 
 	spin_lock(&lag_lock);
@@ -355,7 +355,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 {
 	struct net_device *upper = info->upper_dev, *ndev_tmp;
 	struct netdev_lag_upper_info *lag_upper_info = NULL;
-	bool is_bonded;
+	bool is_bonded, is_in_lag, mode_supported;
 	int bond_status = 0;
 	int num_slaves = 0;
 	int idx;
@@ -374,7 +374,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	rcu_read_lock();
 	for_each_netdev_in_bond_rcu(upper, ndev_tmp) {
 		idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev_tmp);
-		if (idx > -1)
+		if (idx >= 0)
 			bond_status |= (1 << idx);
 
 		num_slaves++;
@@ -391,13 +391,24 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	/* Determine bonding status:
 	 * A device is considered bonded if both its physical ports are slaves
 	 * of the same lag master, and only them.
-	 * Lag mode must be activebackup or hash.
 	 */
-	is_bonded = (num_slaves == MLX5_MAX_PORTS) &&
-		    (bond_status == 0x3) &&
-		    ((tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) ||
-		     (tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH));
+	is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3;
 
+	if (!mlx5_lag_is_ready(ldev) && is_in_lag) {
+		NL_SET_ERR_MSG_MOD(info->info.extack,
+				   "Can't activate LAG offload, PF is configured with more than 64 VFs");
+		return 0;
+	}
+
+	/* Lag mode must be activebackup or hash. */
+	mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP ||
+			 tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH;
+
+	if (is_in_lag && !mode_supported)
+		NL_SET_ERR_MSG_MOD(info->info.extack,
+				   "Can't activate LAG offload, TX type isn't supported");
+
+	is_bonded = is_in_lag && mode_supported;
 	if (tracker->is_bonded != is_bonded) {
 		tracker->is_bonded = is_bonded;
 		return 1;
@@ -418,7 +429,7 @@ static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev,
 		return 0;
 
 	idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev);
-	if (idx == -1)
+	if (idx < 0)
 		return 0;
 
 	/* This information is used to determine virtual to physical
@@ -445,6 +456,10 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	ldev    = container_of(this, struct mlx5_lag, nb);
+
+	if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE)
+		return NOTIFY_DONE;
+
 	tracker = ldev->tracker;
 
 	switch (event) {
@@ -493,14 +508,14 @@ static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
 	kfree(ldev);
 }
 
-static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
-				struct mlx5_core_dev *dev,
-				struct net_device *netdev)
+static int mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
+			       struct mlx5_core_dev *dev,
+			       struct net_device *netdev)
 {
 	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
 
 	if (fn >= MLX5_MAX_PORTS)
-		return;
+		return -EPERM;
 
 	spin_lock(&lag_lock);
 	ldev->pf[fn].dev    = dev;
@@ -511,6 +526,8 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 	dev->priv.lag = ldev;
 
 	spin_unlock(&lag_lock);
+
+	return fn;
 }
 
 static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
@@ -537,11 +554,9 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 {
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
-	int err;
+	int i, err;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
-	    !MLX5_CAP_GEN(dev, lag_master) ||
-	    (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS))
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return;
 
 	tmp_dev = mlx5_get_next_phys_dev(dev);
@@ -556,7 +571,18 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 		}
 	}
 
-	mlx5_lag_dev_add_pf(ldev, dev, netdev);
+	if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
+		return;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+		tmp_dev = ldev->pf[i].dev;
+		if (!tmp_dev || !MLX5_CAP_GEN(tmp_dev, lag_master) ||
+		    MLX5_CAP_GEN(tmp_dev, num_lag_ports) != MLX5_MAX_PORTS)
+			break;
+	}
+
+	if (i >= MLX5_MAX_PORTS)
+		ldev->flags |= MLX5_LAG_FLAG_READY;
 
 	if (!ldev->nb.notifier_call) {
 		ldev->nb.notifier_call = mlx5_lag_netdev_event;
@@ -587,6 +613,8 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 
 	mlx5_lag_dev_remove_pf(ldev, dev);
 
+	ldev->flags &= ~MLX5_LAG_FLAG_READY;
+
 	for (i = 0; i < MLX5_MAX_PORTS; i++)
 		if (ldev->pf[i].dev)
 			break;