Merge tag 'net-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - bpf: synchronize dispatcher update with bpf_dispatcher_xdp_func

   - rxrpc:
      - fix security setting propagation
      - fix null-deref in rxrpc_unuse_local()
      - fix switched parameters in peer tracing

  Current release - new code bugs:

   - rxrpc:
      - fix I/O thread startup getting skipped
      - fix locking issues in rxrpc_put_peer_locked()
      - fix I/O thread stop
      - fix uninitialised variable in rxperf server
      - fix the return value of rxrpc_new_incoming_call()

   - microchip: vcap: fix initialization of value and mask

   - nfp: fix unaligned io read of capabilities word

  Previous releases - regressions:

   - stop in-kernel socket users from corrupting socket's task_frag

   - stream: purge sk_error_queue in sk_stream_kill_queues()

   - openvswitch: fix flow lookup to use unmasked key

   - dsa: mv88e6xxx: avoid reg_lock deadlock in mv88e6xxx_setup_port()

   - devlink:
      - hold region lock when flushing snapshots
      - protect devlink dump by the instance lock

  Previous releases - always broken:

   - bpf:
      - prevent leak of lsm program after failed attach
      - resolve fext program type when checking map compatibility

   - skbuff: account for tail adjustment during pull operations

   - macsec: fix net device access prior to holding a lock

   - bonding: switch back when high prio link up

   - netfilter: flowtable: really fix NAT IPv6 offload

   - enetc: avoid buffer leaks on xdp_do_redirect() failure

   - unix: fix race in SOCK_SEQPACKET's unix_dgram_sendmsg()

   - dsa: microchip: remove IRQF_TRIGGER_FALLING in
     request_threaded_irq"

* tag 'net-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (64 commits)
  net: fec: check the return value of build_skb()
  net: simplify sk_page_frag
  Treewide: Stop corrupting socket's task_frag
  net: Introduce sk_use_task_frag in struct sock.
  mctp: Remove device type check at unregister
  net: dsa: microchip: remove IRQF_TRIGGER_FALLING in request_threaded_irq
  can: kvaser_usb: hydra: help gcc-13 to figure out cmd_len
  can: flexcan: avoid unbalanced pm_runtime_enable warning
  Documentation: devlink: add missing toc entry for etas_es58x devlink doc
  mctp: serial: Fix starting value for frame check sequence
  nfp: fix unaligned io read of capabilities word
  net: stream: purge sk_error_queue in sk_stream_kill_queues()
  myri10ge: Fix an error handling path in myri10ge_probe()
  net: microchip: vcap: Fix initialization of value and mask
  rxrpc: Fix the return value of rxrpc_new_incoming_call()
  rxrpc: rxperf: Fix uninitialised variable
  rxrpc: Fix I/O thread stop
  rxrpc: Fix switched parameters in peer tracing
  rxrpc: Fix locking issues in rxrpc_put_peer_locked()
  rxrpc: Fix I/O thread startup getting skipped
  ...

Author: torvalds

Documentation/bpf/map_sk_storage.rst

@@ -34,13 +34,12 @@ bpf_sk_storage_get()
 
    void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
 
-Socket-local storage can be retrieved using the ``bpf_sk_storage_get()``
-helper. The helper gets the storage from ``sk`` that is associated with ``map``.
-If the ``BPF_LOCAL_STORAGE_GET_F_CREATE`` flag is used then
-``bpf_sk_storage_get()`` will create the storage for ``sk`` if it does not
-already exist. ``value`` can be used together with
-``BPF_LOCAL_STORAGE_GET_F_CREATE`` to initialize the storage value, otherwise it
-will be zero initialized. Returns a pointer to the storage on success, or
+Socket-local storage for ``map`` can be retrieved from socket ``sk`` using the
+``bpf_sk_storage_get()`` helper. If the ``BPF_LOCAL_STORAGE_GET_F_CREATE``
+flag is used then ``bpf_sk_storage_get()`` will create the storage for ``sk``
+if it does not already exist. ``value`` can be used together with
+``BPF_LOCAL_STORAGE_GET_F_CREATE`` to initialize the storage value, otherwise
+it will be zero initialized. Returns a pointer to the storage on success, or
 ``NULL`` in case of failure.
 
 .. note::
@@ -54,9 +53,9 @@ bpf_sk_storage_delete()
 
    long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
 
-Socket-local storage can be deleted using the ``bpf_sk_storage_delete()``
-helper. The helper deletes the storage from ``sk`` that is identified by
-``map``. Returns ``0`` on success, or negative error in case of failure.
+Socket-local storage for ``map`` can be deleted from socket ``sk`` using the
+``bpf_sk_storage_delete()`` helper. Returns ``0`` on success, or negative
+error in case of failure.
 
 User space
 ----------
@@ -68,16 +67,20 @@ bpf_map_update_elem()
 
    int bpf_map_update_elem(int map_fd, const void *key, const void *value, __u64 flags)
 
-Socket-local storage for the socket identified by ``key`` belonging to
-``map_fd`` can be added or updated using the ``bpf_map_update_elem()`` libbpf
-function. ``key`` must be a pointer to a valid ``fd`` in the user space
-program. The ``flags`` parameter can be used to control the update behaviour:
+Socket-local storage for map ``map_fd`` can be added or updated locally to a
+socket using the ``bpf_map_update_elem()`` libbpf function. The socket is
+identified by a `socket` ``fd`` stored in the pointer ``key``. The pointer
+``value`` has the data to be added or updated to the socket ``fd``. The type
+and size of ``value`` should be the same as the value type of the map
+definition.
 
-- ``BPF_ANY`` will create storage for ``fd`` or update existing storage.
-- ``BPF_NOEXIST`` will create storage for ``fd`` only if it did not already
-  exist, otherwise the call will fail with ``-EEXIST``.
-- ``BPF_EXIST`` will update existing storage for ``fd`` if it already exists,
-  otherwise the call will fail with ``-ENOENT``.
+The ``flags`` parameter can be used to control the update behaviour:
+
+- ``BPF_ANY`` will create storage for `socket` ``fd`` or update existing storage.
+- ``BPF_NOEXIST`` will create storage for `socket` ``fd`` only if it did not
+  already exist, otherwise the call will fail with ``-EEXIST``.
+- ``BPF_EXIST`` will update existing storage for `socket` ``fd`` if it already
+  exists, otherwise the call will fail with ``-ENOENT``.
 
 Returns ``0`` on success, or negative error in case of failure.
 
@@ -88,10 +91,10 @@ bpf_map_lookup_elem()
 
    int bpf_map_lookup_elem(int map_fd, const void *key, void *value)
 
-Socket-local storage for the socket identified by ``key`` belonging to
-``map_fd`` can be retrieved using the ``bpf_map_lookup_elem()`` libbpf
-function. ``key`` must be a pointer to a valid ``fd`` in the user space
-program. Returns ``0`` on success, or negative error in case of failure.
+Socket-local storage for map ``map_fd`` can be retrieved from a socket using
+the ``bpf_map_lookup_elem()`` libbpf function. The storage is retrieved from
+the socket identified by a `socket` ``fd`` stored in the pointer
+``key``. Returns ``0`` on success, or negative error in case of failure.
 
 bpf_map_delete_elem()
 ~~~~~~~~~~~~~~~~~~~~~
@@ -100,9 +103,10 @@ bpf_map_delete_elem()
 
    int bpf_map_delete_elem(int map_fd, const void *key)
 
-Socket-local storage for the socket identified by ``key`` belonging to
-``map_fd`` can be deleted using the ``bpf_map_delete_elem()`` libbpf
-function. Returns ``0`` on success, or negative error in case of failure.
+Socket-local storage for map ``map_fd`` can be deleted from a socket using the
+``bpf_map_delete_elem()`` libbpf function. The storage is deleted from the
+socket identified by a `socket` ``fd`` stored in the pointer ``key``. Returns
+``0`` on success, or negative error in case of failure.
 
 Examples
 ========

Documentation/networking/devlink/index.rst

@@ -50,6 +50,7 @@ parameters, info versions, and other features it supports.
    :maxdepth: 1
 
    bnxt
+   etas_es58x
    hns3
    ionic
    ice

Documentation/networking/nf_conntrack-sysctl.rst

@@ -163,6 +163,39 @@ nf_conntrack_timestamp - BOOLEAN
 
 	Enable connection tracking flow timestamping.
 
+nf_conntrack_sctp_timeout_closed - INTEGER (seconds)
+	default 10
+
+nf_conntrack_sctp_timeout_cookie_wait - INTEGER (seconds)
+	default 3
+
+nf_conntrack_sctp_timeout_cookie_echoed - INTEGER (seconds)
+	default 3
+
+nf_conntrack_sctp_timeout_established - INTEGER (seconds)
+	default 432000 (5 days)
+
+nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds)
+	default 0.3
+
+nf_conntrack_sctp_timeout_shutdown_recd - INTEGER (seconds)
+	default 0.3
+
+nf_conntrack_sctp_timeout_shutdown_ack_sent - INTEGER (seconds)
+	default 3
+
+nf_conntrack_sctp_timeout_heartbeat_sent - INTEGER (seconds)
+	default 30
+
+	This timeout is used to setup conntrack entry on secondary paths.
+	Default is set to hb_interval.
+
+nf_conntrack_sctp_timeout_heartbeat_acked - INTEGER (seconds)
+	default 210
+
+	This timeout is used to setup conntrack entry on secondary paths.
+	Default is set to (hb_interval * path_max_retrans + rto_max)
+
 nf_conntrack_udp_timeout - INTEGER (seconds)
 	default 30
 

drivers/block/drbd/drbd_receiver.c

@@ -1030,6 +1030,9 @@ static int conn_connect(struct drbd_connection *connection)
 	sock.socket->sk->sk_allocation = GFP_NOIO;
 	msock.socket->sk->sk_allocation = GFP_NOIO;
 
+	sock.socket->sk->sk_use_task_frag = false;
+	msock.socket->sk->sk_use_task_frag = false;
+
 	sock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE_BULK;
 	msock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE;
 

drivers/block/nbd.c

@@ -512,6 +512,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 	noreclaim_flag = memalloc_noreclaim_save();
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
+		sock->sk->sk_use_task_frag = false;
 		msg.msg_name = NULL;
 		msg.msg_namelen = 0;
 		msg.msg_control = NULL;

drivers/isdn/hardware/mISDN/hfcmulti.c

@@ -3217,6 +3217,7 @@ static int
 hfcm_l1callback(struct dchannel *dch, u_int cmd)
 {
 	struct hfc_multi	*hc = dch->hw;
+	struct sk_buff_head	free_queue;
 	u_long	flags;
 
 	switch (cmd) {
@@ -3245,6 +3246,7 @@ hfcm_l1callback(struct dchannel *dch, u_int cmd)
 		l1_event(dch->l1, HW_POWERUP_IND);
 		break;
 	case HW_DEACT_REQ:
+		__skb_queue_head_init(&free_queue);
 		/* start deactivation */
 		spin_lock_irqsave(&hc->lock, flags);
 		if (hc->ctype == HFC_TYPE_E1) {
@@ -3264,20 +3266,21 @@ hfcm_l1callback(struct dchannel *dch, u_int cmd)
 				plxsd_checksync(hc, 0);
 			}
 		}
-		skb_queue_purge(&dch->squeue);
+		skb_queue_splice_init(&dch->squeue, &free_queue);
 		if (dch->tx_skb) {
-			dev_kfree_skb(dch->tx_skb);
+			__skb_queue_tail(&free_queue, dch->tx_skb);
 			dch->tx_skb = NULL;
 		}
 		dch->tx_idx = 0;
 		if (dch->rx_skb) {
-			dev_kfree_skb(dch->rx_skb);
+			__skb_queue_tail(&free_queue, dch->rx_skb);
 			dch->rx_skb = NULL;
 		}
 		test_and_clear_bit(FLG_TX_BUSY, &dch->Flags);
 		if (test_and_clear_bit(FLG_BUSY_TIMER, &dch->Flags))
 			del_timer(&dch->timer);
 		spin_unlock_irqrestore(&hc->lock, flags);
+		__skb_queue_purge(&free_queue);
 		break;
 	case HW_POWERUP_REQ:
 		spin_lock_irqsave(&hc->lock, flags);
@@ -3384,6 +3387,9 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb)
 	case PH_DEACTIVATE_REQ:
 		test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags);
 		if (dch->dev.D.protocol != ISDN_P_TE_S0) {
+			struct sk_buff_head free_queue;
+
+			__skb_queue_head_init(&free_queue);
 			spin_lock_irqsave(&hc->lock, flags);
 			if (debug & DEBUG_HFCMULTI_MSG)
 				printk(KERN_DEBUG
@@ -3405,14 +3411,14 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb)
 				/* deactivate */
 				dch->state = 1;
 			}
-			skb_queue_purge(&dch->squeue);
+			skb_queue_splice_init(&dch->squeue, &free_queue);
 			if (dch->tx_skb) {
-				dev_kfree_skb(dch->tx_skb);
+				__skb_queue_tail(&free_queue, dch->tx_skb);
 				dch->tx_skb = NULL;
 			}
 			dch->tx_idx = 0;
 			if (dch->rx_skb) {
-				dev_kfree_skb(dch->rx_skb);
+				__skb_queue_tail(&free_queue, dch->rx_skb);
 				dch->rx_skb = NULL;
 			}
 			test_and_clear_bit(FLG_TX_BUSY, &dch->Flags);
@@ -3424,6 +3430,7 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb)
 #endif
 			ret = 0;
 			spin_unlock_irqrestore(&hc->lock, flags);
+			__skb_queue_purge(&free_queue);
 		} else
 			ret = l1_event(dch->l1, hh->prim);
 		break;

drivers/isdn/hardware/mISDN/hfcpci.c

@@ -1617,16 +1617,19 @@ hfcpci_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb)
 		test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags);
 		spin_lock_irqsave(&hc->lock, flags);
 		if (hc->hw.protocol == ISDN_P_NT_S0) {
+			struct sk_buff_head free_queue;
+
+			__skb_queue_head_init(&free_queue);
 			/* prepare deactivation */
 			Write_hfc(hc, HFCPCI_STATES, 0x40);
-			skb_queue_purge(&dch->squeue);
+			skb_queue_splice_init(&dch->squeue, &free_queue);
 			if (dch->tx_skb) {
-				dev_kfree_skb(dch->tx_skb);
+				__skb_queue_tail(&free_queue, dch->tx_skb);
 				dch->tx_skb = NULL;
 			}
 			dch->tx_idx = 0;
 			if (dch->rx_skb) {
-				dev_kfree_skb(dch->rx_skb);
+				__skb_queue_tail(&free_queue, dch->rx_skb);
 				dch->rx_skb = NULL;
 			}
 			test_and_clear_bit(FLG_TX_BUSY, &dch->Flags);
@@ -1639,10 +1642,12 @@ hfcpci_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb)
 			hc->hw.mst_m &= ~HFCPCI_MASTER;
 			Write_hfc(hc, HFCPCI_MST_MODE, hc->hw.mst_m);
 			ret = 0;
+			spin_unlock_irqrestore(&hc->lock, flags);
+			__skb_queue_purge(&free_queue);
 		} else {
 			ret = l1_event(dch->l1, hh->prim);
+			spin_unlock_irqrestore(&hc->lock, flags);
 		}
-		spin_unlock_irqrestore(&hc->lock, flags);
 		break;
 	}
 	if (!ret)

drivers/isdn/hardware/mISDN/hfcsusb.c

@@ -326,20 +326,24 @@ hfcusb_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb)
 		test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags);
 
 		if (hw->protocol == ISDN_P_NT_S0) {
+			struct sk_buff_head free_queue;
+
+			__skb_queue_head_init(&free_queue);
 			hfcsusb_ph_command(hw, HFC_L1_DEACTIVATE_NT);
 			spin_lock_irqsave(&hw->lock, flags);
-			skb_queue_purge(&dch->squeue);
+			skb_queue_splice_init(&dch->squeue, &free_queue);
 			if (dch->tx_skb) {
-				dev_kfree_skb(dch->tx_skb);
+				__skb_queue_tail(&free_queue, dch->tx_skb);
 				dch->tx_skb = NULL;
 			}
 			dch->tx_idx = 0;
 			if (dch->rx_skb) {
-				dev_kfree_skb(dch->rx_skb);
+				__skb_queue_tail(&free_queue, dch->rx_skb);
 				dch->rx_skb = NULL;
 			}
 			test_and_clear_bit(FLG_TX_BUSY, &dch->Flags);
 			spin_unlock_irqrestore(&hw->lock, flags);
+			__skb_queue_purge(&free_queue);
 #ifdef FIXME
 			if (test_and_clear_bit(FLG_L1_BUSY, &dch->Flags))
 				dchannel_sched_event(&hc->dch, D_CLEARBUSY);
@@ -1330,7 +1334,7 @@ tx_iso_complete(struct urb *urb)
 					printk("\n");
 				}
 
-				dev_kfree_skb(tx_skb);
+				dev_consume_skb_irq(tx_skb);
 				tx_skb = NULL;
 				if (fifo->dch && get_next_dframe(fifo->dch))
 					tx_skb = fifo->dch->tx_skb;

drivers/net/bonding/bond_main.c

@@ -2654,8 +2654,9 @@ static void bond_miimon_link_change(struct bonding *bond,
 
 static void bond_miimon_commit(struct bonding *bond)
 {
-	struct list_head *iter;
 	struct slave *slave, *primary;
+	bool do_failover = false;
+	struct list_head *iter;
 
 	bond_for_each_slave(bond, slave, iter) {
 		switch (slave->link_new_state) {
@@ -2699,8 +2700,9 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			bond_miimon_link_change(bond, slave, BOND_LINK_UP);
 
-			if (!bond->curr_active_slave || slave == primary)
-				goto do_failover;
+			if (!rcu_access_pointer(bond->curr_active_slave) || slave == primary ||
+			    slave->prio > rcu_dereference(bond->curr_active_slave)->prio)
+				do_failover = true;
 
 			continue;
 
@@ -2721,7 +2723,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);
 
 			if (slave == rcu_access_pointer(bond->curr_active_slave))
-				goto do_failover;
+				do_failover = true;
 
 			continue;
 
@@ -2732,8 +2734,9 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			continue;
 		}
+	}
 
-do_failover:
+	if (do_failover) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
 		unblock_netpoll_tx();
@@ -3531,6 +3534,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
  */
 static void bond_ab_arp_commit(struct bonding *bond)
 {
+	bool do_failover = false;
 	struct list_head *iter;
 	unsigned long last_tx;
 	struct slave *slave;
@@ -3560,8 +3564,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				slave_info(bond->dev, slave->dev, "link status definitely up\n");
 
 				if (!rtnl_dereference(bond->curr_active_slave) ||
-				    slave == rtnl_dereference(bond->primary_slave))
-					goto do_failover;
+				    slave == rtnl_dereference(bond->primary_slave) ||
+				    slave->prio > rtnl_dereference(bond->curr_active_slave)->prio)
+					do_failover = true;
 
 			}
 
@@ -3580,7 +3585,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			if (slave == rtnl_dereference(bond->curr_active_slave)) {
 				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
-				goto do_failover;
+				do_failover = true;
 			}
 
 			continue;
@@ -3604,8 +3609,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				  slave->link_new_state);
 			continue;
 		}
+	}
 
-do_failover:
+	if (do_failover) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
 		unblock_netpoll_tx();