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
  ...

Author: torvalds

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 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 }
 
 /* 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 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	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;