Merge tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth, netfilter, WiFi.

  Feels like an up-tick in regression fixes, mostly for older releases.
  The hfsc fix, tcp_disconnect() and Intel WWAN fixes stand out as
  fairly clear-cut user reported regressions. The mlx5 DMA bug was
  causing strife for 390x folks. The fixes themselves are not
  particularly scary, tho. No open investigations / outstanding reports
  at the time of writing.

  Current release - regressions:

   - eth: mlx5: perform DMA operations in the right locations, make
     devices usable on s390x, again

   - sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner
     curve, previous fix of rejecting invalid config broke some scripts

   - rfkill: reduce data->mtx scope in rfkill_fop_open, avoid deadlock

   - revert "ethtool: Fix mod state of verbose no_mask bitset", needs
     more work

  Current release - new code bugs:

   - tcp: fix listen() warning with v4-mapped-v6 address

  Previous releases - regressions:

   - tcp: allow tcp_disconnect() again when threads are waiting, it was
     denied to plug a constant source of bugs but turns out .NET depends
     on it

   - eth: mlx5: fix double-free if buffer refill fails under OOM

   - revert "net: wwan: iosm: enable runtime pm support for 7560", it's
     causing regressions and the WWAN team at Intel disappeared

   - tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a
     single skb, fix single-stream perf regression on some devices

  Previous releases - always broken:

   - Bluetooth:
      - fix issues in legacy BR/EDR PIN code pairing
      - correctly bounds check and pad HCI_MON_NEW_INDEX name

   - netfilter:
      - more fixes / follow ups for the large "commit protocol" rework,
        which went in as a fix to 6.5
      - fix null-derefs on netlink attrs which user may not pass in

   - tcp: fix excessive TLP and RACK timeouts from HZ rounding (bless
     Debian for keeping HZ=250 alive)

   - net: more strict VIRTIO_NET_HDR_GSO_UDP_L4 validation, prevent
     letting frankenstein UDP super-frames from getting into the stack

   - net: fix interface altnames when ifc moves to a new namespace

   - eth: qed: fix the size of the RX buffers

   - mptcp: avoid sending RST when closing the initial subflow"

* tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  Revert "ethtool: Fix mod state of verbose no_mask bitset"
  selftests: mptcp: join: no RST when rm subflow/addr
  mptcp: avoid sending RST when closing the initial subflow
  mptcp: more conservative check for zero probes
  tcp: check mptcp-level constraints for backlog coalescing
  selftests: mptcp: join: correctly check for no RST
  net: ti: icssg-prueth: Fix r30 CMDs bitmasks
  selftests: net: add very basic test for netdev names and namespaces
  net: move altnames together with the netdevice
  net: avoid UAF on deleted altname
  net: check for altname conflicts when changing netdev's netns
  net: fix ifname in netlink ntf during netns move
  net: ethernet: ti: Fix mixed module-builtin object
  net: phy: bcm7xxx: Add missing 16nm EPHY statistics
  ipv4: fib: annotate races around nh->nh_saddr_genid and nh->nh_saddr
  tcp_bpf: properly release resources on error paths
  net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve
  net: mdio-mux: fix C45 access returning -EIO after API change
  tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb
  octeon_ep: update BQL sent bytes before ringing doorbell
  ...

Author: torvalds

Documentation/netlink/specs/devlink.yaml

@@ -323,7 +323,7 @@ operations:
             - dev-name
             - sb-index
         reply: &sb-get-reply
-          value: 11
+          value: 13
           attributes: *sb-id-attrs
       dump:
         request:
@@ -350,7 +350,7 @@ operations:
             - sb-index
             - sb-pool-index
         reply: &sb-pool-get-reply
-          value: 15
+          value: 17
           attributes: *sb-pool-id-attrs
       dump:
         request:
@@ -378,7 +378,7 @@ operations:
             - sb-index
             - sb-pool-index
         reply: &sb-port-pool-get-reply
-          value: 19
+          value: 21
           attributes: *sb-port-pool-id-attrs
       dump:
         request:
@@ -407,7 +407,7 @@ operations:
             - sb-pool-type
             - sb-tc-index
         reply: &sb-tc-pool-bind-get-reply
-          value: 23
+          value: 25
           attributes: *sb-tc-pool-bind-id-attrs
       dump:
         request:
@@ -538,7 +538,7 @@ operations:
             - dev-name
             - trap-name
         reply: &trap-get-reply
-          value: 61
+          value: 63
           attributes: *trap-id-attrs
       dump:
         request:
@@ -564,7 +564,7 @@ operations:
             - dev-name
             - trap-group-name
         reply: &trap-group-get-reply
-          value: 65
+          value: 67
           attributes: *trap-group-id-attrs
       dump:
         request:
@@ -590,7 +590,7 @@ operations:
             - dev-name
             - trap-policer-id
         reply: &trap-policer-get-reply
-          value: 69
+          value: 71
           attributes: *trap-policer-id-attrs
       dump:
         request:
@@ -617,7 +617,7 @@ operations:
             - port-index
             - rate-node-name
         reply: &rate-get-reply
-          value: 74
+          value: 76
           attributes: *rate-id-attrs
       dump:
         request:
@@ -643,7 +643,7 @@ operations:
             - dev-name
             - linecard-index
         reply: &linecard-get-reply
-          value: 78
+          value: 80
           attributes: *linecard-id-attrs
       dump:
         request:

Documentation/networking/representors.rst

@@ -162,9 +162,11 @@ How are representors identified?
 The representor netdevice should *not* directly refer to a PCIe device (e.g.
 through ``net_dev->dev.parent`` / ``SET_NETDEV_DEV()``), either of the
 representee or of the switchdev function.
-Instead, it should implement the ``ndo_get_devlink_port()`` netdevice op, which
-the kernel uses to provide the ``phys_switch_id`` and ``phys_port_name`` sysfs
-nodes.  (Some legacy drivers implement ``ndo_get_port_parent_id()`` and
+Instead, the driver should use the ``SET_NETDEV_DEVLINK_PORT`` macro to
+assign a devlink port instance to the netdevice before registering the
+netdevice; the kernel uses the devlink port to provide the ``phys_switch_id``
+and ``phys_port_name`` sysfs nodes.
+(Some legacy drivers implement ``ndo_get_port_parent_id()`` and
 ``ndo_get_phys_port_name()`` directly, but this is deprecated.)  See
 :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>` for the
 details of this API.

drivers/bluetooth/btrtl.c

@@ -962,13 +962,10 @@ static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb)
 	skb_put_data(skb, buf, strlen(buf));
 }
 
-static int btrtl_register_devcoredump_support(struct hci_dev *hdev)
+static void btrtl_register_devcoredump_support(struct hci_dev *hdev)
 {
-	int err;
+	hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
 
-	err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
-
-	return err;
 }
 
 void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name)
@@ -1255,8 +1252,7 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	}
 
 done:
-	if (!err)
-		err = btrtl_register_devcoredump_support(hdev);
+	btrtl_register_devcoredump_support(hdev);
 
 	return err;
 }

drivers/bluetooth/hci_vhci.c

@@ -74,7 +74,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	struct vhci_data *data = hci_get_drvdata(hdev);
 
 	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+	mutex_lock(&data->open_mutex);
 	skb_queue_tail(&data->readq, skb);
+	mutex_unlock(&data->open_mutex);
 
 	wake_up_interruptible(&data->read_wait);
 	return 0;

drivers/net/bonding/bond_main.c

@@ -4023,7 +4023,7 @@ static inline const void *bond_pull_data(struct sk_buff *skb,
 	if (likely(n <= hlen))
 		return data;
 	else if (skb && likely(pskb_may_pull(skb, n)))
-		return skb->head;
+		return skb->data;
 
 	return NULL;
 }

drivers/net/dsa/bcm_sf2.c

@@ -617,17 +617,16 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
 	priv->master_mii_bus = of_mdio_find_bus(dn);
 	if (!priv->master_mii_bus) {
-		of_node_put(dn);
-		return -EPROBE_DEFER;
+		err = -EPROBE_DEFER;
+		goto err_of_node_put;
 	}
 
-	get_device(&priv->master_mii_bus->dev);
 	priv->master_mii_dn = dn;
 
 	priv->slave_mii_bus = mdiobus_alloc();
 	if (!priv->slave_mii_bus) {
-		of_node_put(dn);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_put_master_mii_bus_dev;
 	}
 
 	priv->slave_mii_bus->priv = priv;
@@ -684,18 +683,25 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	}
 
 	err = mdiobus_register(priv->slave_mii_bus);
-	if (err && dn) {
-		mdiobus_free(priv->slave_mii_bus);
-		of_node_put(dn);
-	}
+	if (err && dn)
+		goto err_free_slave_mii_bus;
 
+	return 0;
+
+err_free_slave_mii_bus:
+	mdiobus_free(priv->slave_mii_bus);
+err_put_master_mii_bus_dev:
+	put_device(&priv->master_mii_bus->dev);
+err_of_node_put:
+	of_node_put(dn);
 	return err;
 }
 
 static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv)
 {
 	mdiobus_unregister(priv->slave_mii_bus);
 	mdiobus_free(priv->slave_mii_bus);
+	put_device(&priv->master_mii_bus->dev);
 	of_node_put(priv->master_mii_dn);
 }
 

drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c

@@ -911,7 +911,7 @@ static int csk_wait_memory(struct chtls_dev *cdev,
 			   struct sock *sk, long *timeo_p)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	int err = 0;
+	int ret, err = 0;
 	long current_timeo;
 	long vm_wait = 0;
 	bool noblock;
@@ -942,10 +942,13 @@ static int csk_wait_memory(struct chtls_dev *cdev,
 
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
-		sk_wait_event(sk, &current_timeo, sk->sk_err ||
-			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
-			      (csk_mem_free(cdev, sk) && !vm_wait), &wait);
+		ret = sk_wait_event(sk, &current_timeo, sk->sk_err ||
+				    (sk->sk_shutdown & SEND_SHUTDOWN) ||
+				    (csk_mem_free(cdev, sk) && !vm_wait),
+				    &wait);
 		sk->sk_write_pending--;
+		if (ret < 0)
+			goto do_error;
 
 		if (vm_wait) {
 			vm_wait -= current_timeo;
@@ -1348,6 +1351,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int copied = 0;
 	int target;
 	long timeo;
+	int ret;
 
 	buffers_freed = 0;
 
@@ -1423,7 +1427,11 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		if (copied >= target)
 			break;
 		chtls_cleanup_rbuf(sk, copied);
-		sk_wait_data(sk, &timeo, NULL);
+		ret = sk_wait_data(sk, &timeo, NULL);
+		if (ret < 0) {
+			copied = copied ? : ret;
+			goto unlock;
+		}
 		continue;
 found_ok_skb:
 		if (!skb->len) {
@@ -1518,6 +1526,8 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (buffers_freed)
 		chtls_cleanup_rbuf(sk, copied);
+
+unlock:
 	release_sock(sk);
 	return copied;
 }
@@ -1534,6 +1544,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
 	int copied = 0;
 	size_t avail;          /* amount of available data in current skb */
 	long timeo;
+	int ret;
 
 	lock_sock(sk);
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
@@ -1585,7 +1596,12 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
 			release_sock(sk);
 			lock_sock(sk);
 		} else {
-			sk_wait_data(sk, &timeo, NULL);
+			ret = sk_wait_data(sk, &timeo, NULL);
+			if (ret < 0) {
+				/* here 'copied' is 0 due to previous checks */
+				copied = ret;
+				break;
+			}
 		}
 
 		if (unlikely(peek_seq != tp->copied_seq)) {
@@ -1656,6 +1672,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int copied = 0;
 	long timeo;
 	int target;             /* Read at least this many bytes */
+	int ret;
 
 	buffers_freed = 0;
 
@@ -1747,7 +1764,11 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		if (copied >= target)
 			break;
 		chtls_cleanup_rbuf(sk, copied);
-		sk_wait_data(sk, &timeo, NULL);
+		ret = sk_wait_data(sk, &timeo, NULL);
+		if (ret < 0) {
+			copied = copied ? : ret;
+			goto unlock;
+		}
 		continue;
 
 found_ok_skb:
@@ -1816,6 +1837,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (buffers_freed)
 		chtls_cleanup_rbuf(sk, copied);
 
+unlock:
 	release_sock(sk);
 	return copied;
 }

drivers/net/ethernet/google/gve/gve_rx.c

@@ -146,7 +146,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 		err = gve_rx_alloc_buffer(priv, &priv->pdev->dev, &rx->data.page_info[i],
 					  &rx->data.data_ring[i]);
 		if (err)
-			goto alloc_err;
+			goto alloc_err_rda;
 	}
 
 	if (!rx->data.raw_addressing) {
@@ -171,12 +171,26 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 	return slots;
 
 alloc_err_qpl:
+	/* Fully free the copy pool pages. */
 	while (j--) {
 		page_ref_sub(rx->qpl_copy_pool[j].page,
 			     rx->qpl_copy_pool[j].pagecnt_bias - 1);
 		put_page(rx->qpl_copy_pool[j].page);
 	}
-alloc_err:
+
+	/* Do not fully free QPL pages - only remove the bias added in this
+	 * function with gve_setup_rx_buffer.
+	 */
+	while (i--)
+		page_ref_sub(rx->data.page_info[i].page,
+			     rx->data.page_info[i].pagecnt_bias - 1);
+
+	gve_unassign_qpl(priv, rx->data.qpl->id);
+	rx->data.qpl = NULL;
+
+	return err;
+
+alloc_err_rda:
 	while (i--)
 		gve_rx_free_buffer(&priv->pdev->dev,
 				   &rx->data.page_info[i],

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -1082,7 +1082,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 		     I40E_PFLAN_QALLOC_FIRSTQ_SHIFT;
 	j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >>
 	    I40E_PFLAN_QALLOC_LASTQ_SHIFT;
-	if (val & I40E_PFLAN_QALLOC_VALID_MASK)
+	if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue)
 		num_queues = (j - base_queue) + 1;
 	else
 		num_queues = 0;
@@ -1092,7 +1092,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 	    I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT;
 	j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >>
 	    I40E_PF_VT_PFALLOC_LASTVF_SHIFT;
-	if (val & I40E_PF_VT_PFALLOC_VALID_MASK)
+	if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i)
 		num_vfs = (j - i) + 1;
 	else
 		num_vfs = 0;

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

@@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 
 	ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
 				ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
-				((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
-				 ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+				(hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
 }
 
 static void