Merge tag 'net-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter and bpf.

  Current release - regressions:

   - sched: fix SKB_NOT_DROPPED_YET splat under debug config

  Current release - new code bugs:

   - tcp:
       - fix usec timestamps with TCP fastopen
       - fix possible out-of-bounds reads in tcp_hash_fail()
       - fix SYN option room calculation for TCP-AO

   - tcp_sigpool: fix some off by one bugs

   - bpf: fix compilation error without CGROUPS

   - ptp:
       - ptp_read() should not release queue
       - fix tsevqs corruption

  Previous releases - regressions:

   - llc: verify mac len before reading mac header

  Previous releases - always broken:

   - bpf:
       - fix check_stack_write_fixed_off() to correctly spill imm
       - fix precision tracking for BPF_ALU | BPF_TO_BE | BPF_END
       - check map->usercnt after timer->timer is assigned

   - dsa: lan9303: consequently nested-lock physical MDIO

   - dccp/tcp: call security_inet_conn_request() after setting IP addr

   - tg3: fix the TX ring stall due to incorrect full ring handling

   - phylink: initialize carrier state at creation

   - ice: fix direction of VF rules in switchdev mode

  Misc:

   - fill in a bunch of missing MODULE_DESCRIPTION()s, more to come"

* tag 'net-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (84 commits)
  net: ti: icss-iep: fix setting counter value
  ptp: fix corrupted list in ptp_open
  ptp: ptp_read should not release queue
  net_sched: sch_fq: better validate TCA_FQ_WEIGHTS and TCA_FQ_PRIOMAP
  net: kcm: fill in MODULE_DESCRIPTION()
  net/sched: act_ct: Always fill offloading tuple iifidx
  netfilter: nat: fix ipv6 nat redirect with mapped and scoped addresses
  netfilter: xt_recent: fix (increase) ipv6 literal buffer length
  ipvs: add missing module descriptions
  netfilter: nf_tables: remove catchall element in GC sync path
  netfilter: add missing module descriptions
  drivers/net/ppp: use standard array-copy-function
  net: enetc: shorten enetc_setup_xdp_prog() error message to fit NETLINK_MAX_FMTMSG_LEN
  virtio/vsock: Fix uninit-value in virtio_transport_recv_pkt()
  r8169: respect userspace disabling IFF_MULTICAST
  selftests/bpf: get trusted cgrp from bpf_iter__cgroup directly
  bpf: Let verifier consider {task,cgroup} is trusted in bpf_iter_reg
  net: phylink: initialize carrier state at creation
  test/vsock: add dobule bind connect test
  test/vsock: refactor vsock_accept
  ...

Documentation/bpf/kfuncs.rst

@@ -37,16 +37,14 @@ prototype in a header for the wrapper kfunc.
 An example is given below::
 
         /* Disables missing prototype warnings */
-        __diag_push();
-        __diag_ignore_all("-Wmissing-prototypes",
-                          "Global kfuncs as their definitions will be in BTF");
+        __bpf_kfunc_start_defs();
 
         __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
         {
                 return find_get_task_by_vpid(nr);
         }
 
-        __diag_pop();
+        __bpf_kfunc_end_defs();
 
 A wrapper kfunc is often needed when we need to annotate parameters of the
 kfunc. Otherwise one may directly make the kfunc visible to the BPF program by

Documentation/netlink/specs/devlink.yaml

@@ -71,6 +71,10 @@ definitions:
         name: roce-bit
       -
         name: migratable-bit
+      -
+        name: ipsec-crypto-bit
+      -
+        name: ipsec-packet-bit
   -
     type: enum
     name: sb-threshold-type

Documentation/networking/smc-sysctl.rst

@@ -44,18 +44,16 @@ smcr_testlink_time - INTEGER
 
 wmem - INTEGER
 	Initial size of send buffer used by SMC sockets.
-	The default value inherits from net.ipv4.tcp_wmem[1].
 
 	The minimum value is 16KiB and there is no hard limit for max value, but
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
-	Default: 16K
+	Default: 64KiB
 
 rmem - INTEGER
 	Initial size of receive buffer (RMB) used by SMC sockets.
-	The default value inherits from net.ipv4.tcp_rmem[1].
 
 	The minimum value is 16KiB and there is no hard limit for max value, but
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
-	Default: 128K
+	Default: 64KiB

drivers/net/dsa/lan9303_mdio.c

@@ -32,7 +32,7 @@ static int lan9303_mdio_write(void *ctx, uint32_t reg, uint32_t val)
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff);
 	lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);
@@ -50,7 +50,7 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val)
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	*val = lan9303_mdio_real_read(sw_dev->device, reg);
 	*val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);

drivers/net/ethernet/broadcom/tg3.c

@@ -6647,9 +6647,9 @@ static void tg3_tx(struct tg3_napi *tnapi)
 
 	tnapi->tx_cons = sw_idx;
 
-	/* Need to make the tx_cons update visible to tg3_start_xmit()
+	/* Need to make the tx_cons update visible to __tg3_start_xmit()
 	 * before checking for netif_queue_stopped().  Without the
-	 * memory barrier, there is a small possibility that tg3_start_xmit()
+	 * memory barrier, there is a small possibility that __tg3_start_xmit()
 	 * will miss it and cause the queue to be stopped forever.
 	 */
 	smp_mb();
@@ -7889,7 +7889,7 @@ static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
 }
 
-static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
  * indicated in tg3_tx_frag_set()
@@ -7923,7 +7923,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 
 	skb_list_walk_safe(segs, seg, next) {
 		skb_mark_not_on_list(seg);
-		tg3_start_xmit(seg, tp->dev);
+		__tg3_start_xmit(seg, tp->dev);
 	}
 
 tg3_tso_bug_end:
@@ -7933,7 +7933,7 @@ tg3_tso_bug_end:
 }
 
 /* hard_start_xmit for all devices */
-static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	u32 len, entry, base_flags, mss, vlan = 0;
@@ -8182,11 +8182,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			netif_tx_wake_queue(txq);
 	}
 
-	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
-		/* Packets are ready, update Tx producer idx on card. */
-		tw32_tx_mbox(tnapi->prodmbox, entry);
-	}
-
 	return NETDEV_TX_OK;
 
 dma_error:
@@ -8199,6 +8194,42 @@ drop_nofree:
 	return NETDEV_TX_OK;
 }
 
+static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct netdev_queue *txq;
+	u16 skb_queue_mapping;
+	netdev_tx_t ret;
+
+	skb_queue_mapping = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, skb_queue_mapping);
+
+	ret = __tg3_start_xmit(skb, dev);
+
+	/* Notify the hardware that packets are ready by updating the TX ring
+	 * tail pointer. We respect netdev_xmit_more() thus avoiding poking
+	 * the hardware for every packet. To guarantee forward progress the TX
+	 * ring must be drained when it is full as indicated by
+	 * netif_xmit_stopped(). This needs to happen even when the current
+	 * skb was dropped or rejected with NETDEV_TX_BUSY. Otherwise packets
+	 * queued by previous __tg3_start_xmit() calls might get stuck in
+	 * the queue forever.
+	 */
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
+		struct tg3_napi *tnapi;
+		struct tg3 *tp;
+
+		tp = netdev_priv(dev);
+		tnapi = &tp->napi[skb_queue_mapping];
+
+		if (tg3_flag(tp, ENABLE_TSS))
+			tnapi++;
+
+		tw32_tx_mbox(tnapi->prodmbox, tnapi->tx_prod);
+	}
+
+	return ret;
+}
+
 static void tg3_mac_loopback(struct tg3 *tp, bool enable)
 {
 	if (enable) {
@@ -17729,7 +17760,7 @@ static int tg3_init_one(struct pci_dev *pdev,
 	 * device behind the EPB cannot support DMA addresses > 40-bit.
 	 * On 64-bit systems with IOMMU, use 40-bit dma_mask.
 	 * On 64-bit systems without IOMMU, use 64-bit dma_mask and
-	 * do DMA address check in tg3_start_xmit().
+	 * do DMA address check in __tg3_start_xmit().
 	 */
 	if (tg3_flag(tp, IS_5788))
 		persist_dma_mask = dma_mask = DMA_BIT_MASK(32);
@@ -18127,7 +18158,8 @@ static void tg3_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
-	tg3_power_down(tp);
+	if (system_state == SYSTEM_POWER_OFF)
+		tg3_power_down(tp);
 
 	rtnl_unlock();
 

drivers/net/ethernet/freescale/enetc/enetc.c

@@ -2769,7 +2769,7 @@ static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog,
 	if (priv->min_num_stack_tx_queues + num_xdp_tx_queues >
 	    priv->num_tx_rings) {
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Reserving %d XDP TXQs does not leave a minimum of %d TXQs for network stack (total %d available)",
+				       "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)",
 				       num_xdp_tx_queues,
 				       priv->min_num_stack_tx_queues,
 				       priv->num_tx_rings);

drivers/net/ethernet/intel/i40e/i40e_devlink.c

@@ -231,6 +231,5 @@ int i40e_devlink_create_port(struct i40e_pf *pf)
  **/
 void i40e_devlink_destroy_port(struct i40e_pf *pf)
 {
-	devlink_port_type_clear(&pf->devlink_port);
 	devlink_port_unregister(&pf->devlink_port);
 }

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -14213,8 +14213,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 	}
 	set_bit(__I40E_VSI_RELEASING, vsi->state);
 	uplink_seid = vsi->uplink_seid;
-	if (vsi->type == I40E_VSI_MAIN)
-		i40e_devlink_destroy_port(pf);
+
 	if (vsi->type != I40E_VSI_SRIOV) {
 		if (vsi->netdev_registered) {
 			vsi->netdev_registered = false;
@@ -14228,6 +14227,9 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		i40e_vsi_disable_irq(vsi);
 	}
 
+	if (vsi->type == I40E_VSI_MAIN)
+		i40e_devlink_destroy_port(pf);
+
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 
 	/* clear the sync flag on all filters */
@@ -14402,14 +14404,14 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 
 err_rings:
 	i40e_vsi_free_q_vectors(vsi);
-	if (vsi->type == I40E_VSI_MAIN)
-		i40e_devlink_destroy_port(pf);
 	if (vsi->netdev_registered) {
 		vsi->netdev_registered = false;
 		unregister_netdev(vsi->netdev);
 		free_netdev(vsi->netdev);
 		vsi->netdev = NULL;
 	}
+	if (vsi->type == I40E_VSI_MAIN)
+		i40e_devlink_destroy_port(pf);
 	i40e_aq_delete_element(&pf->hw, vsi->seid, NULL);
 err_vsi:
 	i40e_vsi_clear(vsi);

drivers/net/ethernet/intel/ice/ice_lag.c

@@ -628,7 +628,7 @@ void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 		INIT_LIST_HEAD(&ndlist.node);
 		rcu_read_lock();
 		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+			nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
 			if (!nl)
 				break;
 
@@ -1555,18 +1555,12 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
 {
-	struct ice_lag_netdev_list *entry;
 	struct ice_netdev_priv *np;
-	struct net_device *netdev;
 	struct ice_pf *pf;
 
-	list_for_each_entry(entry, lag->netdev_head, node) {
-		netdev = entry->netdev;
-		np = netdev_priv(netdev);
-		pf = np->vsi->back;
-
-		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
-	}
+	np = netdev_priv(lag->netdev);
+	pf = np->vsi->back;
+	ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
 }
 
 /**
@@ -1698,7 +1692,7 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
 
 		rcu_read_lock();
 		for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) {
-			nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL);
+			nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC);
 			if (!nd_list)
 				break;
 
@@ -2075,7 +2069,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 		INIT_LIST_HEAD(&ndlist.node);
 		rcu_read_lock();
 		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+			nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
 			if (!nl)
 				break;
 

drivers/net/ethernet/intel/ice/ice_tc_lib.c

@@ -630,32 +630,83 @@ bool ice_is_tunnel_supported(struct net_device *dev)
 	return ice_tc_tun_get_type(dev) != TNL_LAST;
 }
 
-static int
-ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr,
-			    struct flow_action_entry *act)
+static bool ice_tc_is_dev_uplink(struct net_device *dev)
+{
+	return netif_is_ice(dev) || ice_is_tunnel_supported(dev);
+}
+
+static int ice_tc_setup_redirect_action(struct net_device *filter_dev,
+					struct ice_tc_flower_fltr *fltr,
+					struct net_device *target_dev)
 {
 	struct ice_repr *repr;
 
+	fltr->action.fltr_act = ICE_FWD_TO_VSI;
+
+	if (ice_is_port_repr_netdev(filter_dev) &&
+	    ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_is_port_repr_netdev(filter_dev) &&
+		   ice_tc_is_dev_uplink(target_dev)) {
+		repr = ice_netdev_to_repr(filter_dev);
+
+		fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_tc_is_dev_uplink(filter_dev) &&
+		   ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+	} else {
+		NL_SET_ERR_MSG_MOD(fltr->extack,
+				   "Unsupported netdevice in switchdev mode");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+ice_tc_setup_drop_action(struct net_device *filter_dev,
+			 struct ice_tc_flower_fltr *fltr)
+{
+	fltr->action.fltr_act = ICE_DROP_PACKET;
+
+	if (ice_is_port_repr_netdev(filter_dev)) {
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_tc_is_dev_uplink(filter_dev)) {
+		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+	} else {
+		NL_SET_ERR_MSG_MOD(fltr->extack,
+				   "Unsupported netdevice in switchdev mode");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
+				       struct ice_tc_flower_fltr *fltr,
+				       struct flow_action_entry *act)
+{
+	int err;
+
 	switch (act->id) {
 	case FLOW_ACTION_DROP:
-		fltr->action.fltr_act = ICE_DROP_PACKET;
+		err = ice_tc_setup_drop_action(filter_dev, fltr);
+		if (err)
+			return err;
+
 		break;
 
 	case FLOW_ACTION_REDIRECT:
-		fltr->action.fltr_act = ICE_FWD_TO_VSI;
-
-		if (ice_is_port_repr_netdev(act->dev)) {
-			repr = ice_netdev_to_repr(act->dev);
-
-			fltr->dest_vsi = repr->src_vsi;
-			fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-		} else if (netif_is_ice(act->dev) ||
-			   ice_is_tunnel_supported(act->dev)) {
-			fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-		} else {
-			NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode");
-			return -EINVAL;
-		}
+		err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev);
+		if (err)
+			return err;
 
 		break;
 
@@ -696,10 +747,6 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		goto exit;
 	}
 
-	/* egress traffic is always redirect to uplink */
-	if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS)
-		fltr->dest_vsi = vsi->back->switchdev.uplink_vsi;
-
 	rule_info.sw_act.fltr_act = fltr->action.fltr_act;
 	if (fltr->action.fltr_act != ICE_DROP_PACKET)
 		rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx;
@@ -713,13 +760,21 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	rule_info.flags_info.act_valid = true;
 
 	if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
+		/* Uplink to VF */
 		rule_info.sw_act.flag |= ICE_FLTR_RX;
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
-	} else {
+	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+		   fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) {
+		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
 		rule_info.sw_act.src = vsi->idx;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE;
+	} else {
+		/* VF to VF */
+		rule_info.sw_act.flag |= ICE_FLTR_TX;
+		rule_info.sw_act.src = vsi->idx;
+		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	}
 
 	/* specify the cookie as filter_rule_id */
@@ -1745,16 +1800,17 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr,
 
 /**
  * ice_parse_tc_flower_actions - Parse the actions for a TC filter
+ * @filter_dev: Pointer to device on which filter is being added
  * @vsi: Pointer to VSI
  * @cls_flower: Pointer to TC flower offload structure
  * @fltr: Pointer to TC flower filter structure
  *
  * Parse the actions for a TC filter
  */
-static int
-ice_parse_tc_flower_actions(struct ice_vsi *vsi,
-			    struct flow_cls_offload *cls_flower,
-			    struct ice_tc_flower_fltr *fltr)
+static int ice_parse_tc_flower_actions(struct net_device *filter_dev,
+				       struct ice_vsi *vsi,
+				       struct flow_cls_offload *cls_flower,
+				       struct ice_tc_flower_fltr *fltr)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower);
 	struct flow_action *flow_action = &rule->action;
@@ -1769,7 +1825,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi,
 
 	flow_action_for_each(i, act, flow_action) {
 		if (ice_is_eswitch_mode_switchdev(vsi->back))
-			err = ice_eswitch_tc_parse_action(fltr, act);
+			err = ice_eswitch_tc_parse_action(filter_dev, fltr, act);
 		else
 			err = ice_tc_parse_action(vsi, fltr, act);
 		if (err)
@@ -1856,7 +1912,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 	if (err < 0)
 		goto err;
 
-	err = ice_parse_tc_flower_actions(vsi, f, fltr);
+	err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr);
 	if (err < 0)
 		goto err;
 

drivers/net/ethernet/intel/idpf/idpf_txrx.c

@@ -2365,7 +2365,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
  */
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 {
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	const struct skb_shared_info *shinfo;
 	union {
 		struct iphdr *v4;
 		struct ipv6hdr *v6;
@@ -2379,13 +2379,15 @@ int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 	u32 paylen, l4_start;
 	int err;
 
-	if (!shinfo->gso_size)
+	if (!skb_is_gso(skb))
 		return 0;
 
 	err = skb_cow_head(skb, 0);
 	if (err < 0)
 		return err;
 
+	shinfo = skb_shinfo(skb);
+
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c

@@ -818,7 +818,6 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 	int qidx, sqe_tail, sqe_head;
 	struct otx2_snd_queue *sq;
 	u64 incr, *ptr, val;
-	int timeout = 1000;
 
 	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
 	for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
@@ -827,15 +826,11 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 			continue;
 
 		incr = (u64)qidx << 32;
-		while (timeout) {
-			val = otx2_atomic64_add(incr, ptr);
-			sqe_head = (val >> 20) & 0x3F;
-			sqe_tail = (val >> 28) & 0x3F;
-			if (sqe_head == sqe_tail)
-				break;
-			usleep_range(1, 3);
-			timeout--;
-		}
+		val = otx2_atomic64_add(incr, ptr);
+		sqe_head = (val >> 20) & 0x3F;
+		sqe_tail = (val >> 28) & 0x3F;
+		if (sqe_head != sqe_tail)
+			usleep_range(50, 60);
 	}
 }
 

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h

@@ -977,6 +977,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool pfc_en);
 int otx2_txsch_alloc(struct otx2_nic *pfvf);
 void otx2_txschq_stop(struct otx2_nic *pfvf);
 void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
+void otx2_free_pending_sqe(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 		    dma_addr_t *dma);

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -1193,31 +1193,32 @@ static char *nix_mnqerr_e_str[NIX_MNQERR_MAX] = {
 };
 
 static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] =  {
-	"NIX_SND_STATUS_GOOD",
-	"NIX_SND_STATUS_SQ_CTX_FAULT",
-	"NIX_SND_STATUS_SQ_CTX_POISON",
-	"NIX_SND_STATUS_SQB_FAULT",
-	"NIX_SND_STATUS_SQB_POISON",
-	"NIX_SND_STATUS_HDR_ERR",
-	"NIX_SND_STATUS_EXT_ERR",
-	"NIX_SND_STATUS_JUMP_FAULT",
-	"NIX_SND_STATUS_JUMP_POISON",
-	"NIX_SND_STATUS_CRC_ERR",
-	"NIX_SND_STATUS_IMM_ERR",
-	"NIX_SND_STATUS_SG_ERR",
-	"NIX_SND_STATUS_MEM_ERR",
-	"NIX_SND_STATUS_INVALID_SUBDC",
-	"NIX_SND_STATUS_SUBDC_ORDER_ERR",
-	"NIX_SND_STATUS_DATA_FAULT",
-	"NIX_SND_STATUS_DATA_POISON",
-	"NIX_SND_STATUS_NPC_DROP_ACTION",
-	"NIX_SND_STATUS_LOCK_VIOL",
-	"NIX_SND_STATUS_NPC_UCAST_CHAN_ERR",
-	"NIX_SND_STATUS_NPC_MCAST_CHAN_ERR",
-	"NIX_SND_STATUS_NPC_MCAST_ABORT",
-	"NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
-	"NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
-	"NIX_SND_STATUS_SEND_STATS_ERR",
+	[NIX_SND_STATUS_GOOD] = "NIX_SND_STATUS_GOOD",
+	[NIX_SND_STATUS_SQ_CTX_FAULT] = "NIX_SND_STATUS_SQ_CTX_FAULT",
+	[NIX_SND_STATUS_SQ_CTX_POISON] = "NIX_SND_STATUS_SQ_CTX_POISON",
+	[NIX_SND_STATUS_SQB_FAULT] = "NIX_SND_STATUS_SQB_FAULT",
+	[NIX_SND_STATUS_SQB_POISON] = "NIX_SND_STATUS_SQB_POISON",
+	[NIX_SND_STATUS_HDR_ERR] = "NIX_SND_STATUS_HDR_ERR",
+	[NIX_SND_STATUS_EXT_ERR] = "NIX_SND_STATUS_EXT_ERR",
+	[NIX_SND_STATUS_JUMP_FAULT] = "NIX_SND_STATUS_JUMP_FAULT",
+	[NIX_SND_STATUS_JUMP_POISON] = "NIX_SND_STATUS_JUMP_POISON",
+	[NIX_SND_STATUS_CRC_ERR] = "NIX_SND_STATUS_CRC_ERR",
+	[NIX_SND_STATUS_IMM_ERR] = "NIX_SND_STATUS_IMM_ERR",
+	[NIX_SND_STATUS_SG_ERR] = "NIX_SND_STATUS_SG_ERR",
+	[NIX_SND_STATUS_MEM_ERR] = "NIX_SND_STATUS_MEM_ERR",
+	[NIX_SND_STATUS_INVALID_SUBDC] = "NIX_SND_STATUS_INVALID_SUBDC",
+	[NIX_SND_STATUS_SUBDC_ORDER_ERR] = "NIX_SND_STATUS_SUBDC_ORDER_ERR",
+	[NIX_SND_STATUS_DATA_FAULT] = "NIX_SND_STATUS_DATA_FAULT",
+	[NIX_SND_STATUS_DATA_POISON] = "NIX_SND_STATUS_DATA_POISON",
+	[NIX_SND_STATUS_NPC_DROP_ACTION] = "NIX_SND_STATUS_NPC_DROP_ACTION",
+	[NIX_SND_STATUS_LOCK_VIOL] = "NIX_SND_STATUS_LOCK_VIOL",
+	[NIX_SND_STATUS_NPC_UCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_UCAST_CHAN_ERR",
+	[NIX_SND_STATUS_NPC_MCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_MCAST_CHAN_ERR",
+	[NIX_SND_STATUS_NPC_MCAST_ABORT] = "NIX_SND_STATUS_NPC_MCAST_ABORT",
+	[NIX_SND_STATUS_NPC_VTAG_PTR_ERR] = "NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
+	[NIX_SND_STATUS_NPC_VTAG_SIZE_ERR] = "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
+	[NIX_SND_STATUS_SEND_MEM_FAULT] = "NIX_SND_STATUS_SEND_MEM_FAULT",
+	[NIX_SND_STATUS_SEND_STATS_ERR] = "NIX_SND_STATUS_SEND_STATS_ERR",
 };
 
 static irqreturn_t otx2_q_intr_handler(int irq, void *data)
@@ -1238,14 +1239,16 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			continue;
 
 		if (val & BIT_ULL(42)) {
-			netdev_err(pf->netdev, "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+			netdev_err(pf->netdev,
+				   "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
 				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
 		} else {
 			if (val & BIT_ULL(NIX_CQERRINT_DOOR_ERR))
 				netdev_err(pf->netdev, "CQ%lld: Doorbell error",
 					   qidx);
 			if (val & BIT_ULL(NIX_CQERRINT_CQE_FAULT))
-				netdev_err(pf->netdev, "CQ%lld: Memory fault on CQE write to LLC/DRAM",
+				netdev_err(pf->netdev,
+					   "CQ%lld: Memory fault on CQE write to LLC/DRAM",
 					   qidx);
 		}
 
@@ -1272,7 +1275,8 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			     (val & NIX_SQINT_BITS));
 
 		if (val & BIT_ULL(42)) {
-			netdev_err(pf->netdev, "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+			netdev_err(pf->netdev,
+				   "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
 				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
 			goto done;
 		}
@@ -1282,8 +1286,11 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			goto chk_mnq_err_dbg;
 
 		sq_op_err_code = FIELD_GET(GENMASK(7, 0), sq_op_err_dbg);
-		netdev_err(pf->netdev, "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(%llx)  err=%s\n",
-			   qidx, sq_op_err_dbg, nix_sqoperr_e_str[sq_op_err_code]);
+		netdev_err(pf->netdev,
+			   "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(0x%llx)  err=%s(%#x)\n",
+			   qidx, sq_op_err_dbg,
+			   nix_sqoperr_e_str[sq_op_err_code],
+			   sq_op_err_code);
 
 		otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, BIT_ULL(44));
 
@@ -1300,16 +1307,21 @@ chk_mnq_err_dbg:
 			goto chk_snd_err_dbg;
 
 		mnq_err_code = FIELD_GET(GENMASK(7, 0), mnq_err_dbg);
-		netdev_err(pf->netdev, "SQ%lld: NIX_LF_MNQ_ERR_DBG(%llx)  err=%s\n",
-			   qidx, mnq_err_dbg,  nix_mnqerr_e_str[mnq_err_code]);
+		netdev_err(pf->netdev,
+			   "SQ%lld: NIX_LF_MNQ_ERR_DBG(0x%llx)  err=%s(%#x)\n",
+			   qidx, mnq_err_dbg,  nix_mnqerr_e_str[mnq_err_code],
+			   mnq_err_code);
 		otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, BIT_ULL(44));
 
 chk_snd_err_dbg:
 		snd_err_dbg = otx2_read64(pf, NIX_LF_SEND_ERR_DBG);
 		if (snd_err_dbg & BIT(44)) {
 			snd_err_code = FIELD_GET(GENMASK(7, 0), snd_err_dbg);
-			netdev_err(pf->netdev, "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s\n",
-				   qidx, snd_err_dbg, nix_snd_status_e_str[snd_err_code]);
+			netdev_err(pf->netdev,
+				   "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s(%#x)\n",
+				   qidx, snd_err_dbg,
+				   nix_snd_status_e_str[snd_err_code],
+				   snd_err_code);
 			otx2_write64(pf, NIX_LF_SEND_ERR_DBG, BIT_ULL(44));
 		}
 
@@ -1589,6 +1601,7 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 		else
 			otx2_cleanup_tx_cqes(pf, cq);
 	}
+	otx2_free_pending_sqe(pf);
 
 	otx2_free_sq_res(pf);
 

drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h

@@ -318,23 +318,23 @@ enum nix_snd_status_e {
 	NIX_SND_STATUS_EXT_ERR = 0x6,
 	NIX_SND_STATUS_JUMP_FAULT = 0x7,
 	NIX_SND_STATUS_JUMP_POISON = 0x8,
-	NIX_SND_STATUS_CRC_ERR = 0x9,
-	NIX_SND_STATUS_IMM_ERR = 0x10,
-	NIX_SND_STATUS_SG_ERR = 0x11,
-	NIX_SND_STATUS_MEM_ERR = 0x12,
-	NIX_SND_STATUS_INVALID_SUBDC = 0x13,
-	NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x14,
-	NIX_SND_STATUS_DATA_FAULT = 0x15,
-	NIX_SND_STATUS_DATA_POISON = 0x16,
-	NIX_SND_STATUS_NPC_DROP_ACTION = 0x17,
-	NIX_SND_STATUS_LOCK_VIOL = 0x18,
-	NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x19,
-	NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x20,
-	NIX_SND_STATUS_NPC_MCAST_ABORT = 0x21,
-	NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x22,
-	NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x23,
-	NIX_SND_STATUS_SEND_MEM_FAULT = 0x24,
-	NIX_SND_STATUS_SEND_STATS_ERR = 0x25,
+	NIX_SND_STATUS_CRC_ERR = 0x10,
+	NIX_SND_STATUS_IMM_ERR = 0x11,
+	NIX_SND_STATUS_SG_ERR = 0x12,
+	NIX_SND_STATUS_MEM_ERR = 0x13,
+	NIX_SND_STATUS_INVALID_SUBDC = 0x14,
+	NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x15,
+	NIX_SND_STATUS_DATA_FAULT = 0x16,
+	NIX_SND_STATUS_DATA_POISON = 0x17,
+	NIX_SND_STATUS_NPC_DROP_ACTION = 0x20,
+	NIX_SND_STATUS_LOCK_VIOL = 0x21,
+	NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x22,
+	NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x23,
+	NIX_SND_STATUS_NPC_MCAST_ABORT = 0x24,
+	NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x25,
+	NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x26,
+	NIX_SND_STATUS_SEND_MEM_FAULT = 0x27,
+	NIX_SND_STATUS_SEND_STATS_ERR = 0x28,
 	NIX_SND_STATUS_MAX,
 };
 

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c

@@ -1247,9 +1247,11 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q
 
 void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
 {
+	int tx_pkts = 0, tx_bytes = 0;
 	struct sk_buff *skb = NULL;
 	struct otx2_snd_queue *sq;
 	struct nix_cqe_tx_s *cqe;
+	struct netdev_queue *txq;
 	int processed_cqe = 0;
 	struct sg_list *sg;
 	int qidx;
@@ -1270,12 +1272,20 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
 		sg = &sq->sg[cqe->comp.sqe_id];
 		skb = (struct sk_buff *)sg->skb;
 		if (skb) {
+			tx_bytes += skb->len;
+			tx_pkts++;
 			otx2_dma_unmap_skb_frags(pfvf, sg);
 			dev_kfree_skb_any(skb);
 			sg->skb = (u64)NULL;
 		}
 	}
 
+	if (likely(tx_pkts)) {
+		if (qidx >= pfvf->hw.tx_queues)
+			qidx -= pfvf->hw.xdp_queues;
+		txq = netdev_get_tx_queue(pfvf->netdev, qidx);
+		netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+	}
 	/* Free CQEs to HW */
 	otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR,
 		     ((u64)cq->cq_idx << 32) | processed_cqe);
@@ -1302,6 +1312,38 @@ int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable)
 	return err;
 }
 
+void otx2_free_pending_sqe(struct otx2_nic *pfvf)
+{
+	int tx_pkts = 0, tx_bytes = 0;
+	struct sk_buff *skb = NULL;
+	struct otx2_snd_queue *sq;
+	struct netdev_queue *txq;
+	struct sg_list *sg;
+	int sq_idx, sqe;
+
+	for (sq_idx = 0; sq_idx < pfvf->hw.tx_queues; sq_idx++) {
+		sq = &pfvf->qset.sq[sq_idx];
+		for (sqe = 0; sqe < sq->sqe_cnt; sqe++) {
+			sg = &sq->sg[sqe];
+			skb = (struct sk_buff *)sg->skb;
+			if (skb) {
+				tx_bytes += skb->len;
+				tx_pkts++;
+				otx2_dma_unmap_skb_frags(pfvf, sg);
+				dev_kfree_skb_any(skb);
+				sg->skb = (u64)NULL;
+			}
+		}
+
+		if (!tx_pkts)
+			continue;
+		txq = netdev_get_tx_queue(pfvf->netdev, sq_idx);
+		netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+		tx_pkts = 0;
+		tx_bytes = 0;
+	}
+}
+
 static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
 				int len, int *offset)
 {

drivers/net/ethernet/realtek/r8169_main.c

@@ -2582,9 +2582,13 @@ static void rtl_set_rx_mode(struct net_device *dev)
 
 	if (dev->flags & IFF_PROMISC) {
 		rx_mode |= AcceptAllPhys;
+	} else if (!(dev->flags & IFF_MULTICAST)) {
+		rx_mode &= ~AcceptMulticast;
 	} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
 		   dev->flags & IFF_ALLMULTI ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_35) {
+		   tp->mac_version == RTL_GIGA_MAC_VER_35 ||
+		   tp->mac_version == RTL_GIGA_MAC_VER_46 ||
+		   tp->mac_version == RTL_GIGA_MAC_VER_48) {
 		/* accept all multicasts */
 	} else if (netdev_mc_empty(dev)) {
 		rx_mode &= ~AcceptMulticast;

drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h

@@ -259,7 +259,7 @@
 	((val) << XGMAC_PPS_MINIDX(x))
 #define XGMAC_PPSCMD_START		0x2
 #define XGMAC_PPSCMD_STOP		0x5
-#define XGMAC_PPSEN0			BIT(4)
+#define XGMAC_PPSENx(x)			BIT(4 + (x) * 8)
 #define XGMAC_PPSx_TARGET_TIME_SEC(x)	(0x00000d80 + (x) * 0x10)
 #define XGMAC_PPSx_TARGET_TIME_NSEC(x)	(0x00000d84 + (x) * 0x10)
 #define XGMAC_TRGTBUSY0			BIT(31)

drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c

@@ -1178,7 +1178,19 @@ static int dwxgmac2_flex_pps_config(void __iomem *ioaddr, int index,
 
 	val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_START);
 	val |= XGMAC_TRGTMODSELx(index, XGMAC_PPSCMD_START);
-	val |= XGMAC_PPSEN0;
+
+	/* XGMAC Core has 4 PPS outputs at most.
+	 *
+	 * Prior XGMAC Core 3.20, Fixed mode or Flexible mode are selectable for
+	 * PPS0 only via PPSEN0. PPS{1,2,3} are in Flexible mode by default,
+	 * and can not be switched to Fixed mode, since PPSEN{1,2,3} are
+	 * read-only reserved to 0.
+	 * But we always set PPSEN{1,2,3} do not make things worse ;-)
+	 *
+	 * From XGMAC Core 3.20 and later, PPSEN{0,1,2,3} are writable and must
+	 * be set, or the PPS outputs stay in Fixed PPS mode by default.
+	 */
+	val |= XGMAC_PPSENx(index);
 
 	writel(cfg->start.tv_sec, ioaddr + XGMAC_PPSx_TARGET_TIME_SEC(index));
 

drivers/net/ethernet/ti/am65-cpsw-nuss.c

@@ -1588,10 +1588,10 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy
 
 	/* rx_pause/tx_pause */
 	if (rx_pause)
-		mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
+		mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
 
 	if (tx_pause)
-		mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
+		mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
 
 	cpsw_sl_ctl_set(port->slave.mac_sl, mac_control);