Merge tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  A lot of networking people were at a conference last week, busy
  catching COVID, so relatively short PR.

  Current release - regressions:

   - tcp: process the 3rd ACK with sk_socket for TFO and MPTCP

  Current release - new code bugs:

   - l2tp: protect session IDR and tunnel session list with one lock,
     make sure the state is coherent to avoid a warning

   - eth: bnxt_en: update xdp_rxq_info in queue restart logic

   - eth: airoha: fix location of the MBI_RX_AGE_SEL_MASK field

  Previous releases - regressions:

   - xsk: require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len,
     the field reuses previously un-validated pad

  Previous releases - always broken:

   - tap/tun: drop short frames to prevent crashes later in the stack

   - eth: ice: add a per-VF limit on number of FDIR filters

   - af_unix: disable MSG_OOB handling for sockets in sockmap/sockhash"

* tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (34 commits)
  tun: add missing verification for short frame
  tap: add missing verification for short frame
  mISDN: Fix a use after free in hfcmulti_tx()
  gve: Fix an edge case for TSO skb validity check
  bnxt_en: update xdp_rxq_info in queue restart logic
  tcp: process the 3rd ACK with sk_socket for TFO/MPTCP
  selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test
  xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len
  bpf: Fix a segment issue when downgrading gso_size
  net: mediatek: Fix potential NULL pointer dereference in dummy net_device handling
  MAINTAINERS: make Breno the netconsole maintainer
  MAINTAINERS: Update bonding entry
  net: nexthop: Initialize all fields in dumped nexthops
  net: stmmac: Correct byte order of perfect_match
  selftests: forwarding: skip if kernel not support setting bridge fdb learning limit
  tipc: Return non-zero value from tipc_udp_addr2str() on error
  netfilter: nft_set_pipapo_avx2: disable softinterrupts
  ice: Fix recipe read procedure
  ice: Add a per-VF limit on number of FDIR filters
  net: bonding: correctly annotate RCU in bond_should_notify_peers()
  ...

Author: torvalds

.mailmap

@@ -474,6 +474,8 @@ Nadia Yvette Chambers <[email protected]> William Lee Irwin III <wli@holomorphy
 Naoya Horiguchi <[email protected]> <[email protected]>
 Naoya Horiguchi <[email protected]> <[email protected]>
 Nathan Chancellor <[email protected]> <[email protected]>
+Naveen N Rao <[email protected]> <[email protected]>
+Naveen N Rao <[email protected]> <[email protected]>
 Neeraj Upadhyay <[email protected]> <[email protected]>
 Neeraj Upadhyay <[email protected]> <[email protected]>
 Neil Armstrong <[email protected]> <[email protected]>

Documentation/networking/xsk-tx-metadata.rst

@@ -11,12 +11,16 @@ metadata on the receive side.
 General Design
 ==============
 
-The headroom for the metadata is reserved via ``tx_metadata_len`` in
-``struct xdp_umem_reg``. The metadata length is therefore the same for
-every socket that shares the same umem. The metadata layout is a fixed UAPI,
-refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
-Thus, generally, the ``tx_metadata_len`` field above should contain
-``sizeof(union xsk_tx_metadata)``.
+The headroom for the metadata is reserved via ``tx_metadata_len`` and
+``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata
+length is therefore the same for every socket that shares the same umem.
+The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in
+``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len``
+field above should contain ``sizeof(union xsk_tx_metadata)``.
+
+Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN``
+flag was not required. Applications might attempt to create a umem
+with a flag first and if it fails, do another attempt without a flag.
 
 The headroom and the metadata itself should be located right before
 ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata

MAINTAINERS

@@ -3906,11 +3906,10 @@ F:	include/net/bluetooth/
 F:	net/bluetooth/
 
 BONDING DRIVER
-M:	Jay Vosburgh <[email protected]>
+M:	Jay Vosburgh <[email protected]>
 M:	Andy Gospodarek <[email protected]>
 L:	[email protected]
-S:	Supported
-W:	http://sourceforge.net/projects/bonding/
+S:	Maintained
 F:	Documentation/networking/bonding.rst
 F:	drivers/net/bonding/
 F:	include/net/bond*
@@ -3974,8 +3973,10 @@ S:	Odd Fixes
 F:	drivers/net/ethernet/netronome/nfp/bpf/
 
 BPF JIT for POWERPC (32-BIT AND 64-BIT)
-M:	Naveen N. Rao <[email protected]>
 M:	Michael Ellerman <[email protected]>
+M:	Hari Bathini <[email protected]>
+M:	Christophe Leroy <[email protected]>
+R:	Naveen N Rao <[email protected]>
 L:	[email protected]
 S:	Supported
 F:	arch/powerpc/net/
@@ -12529,7 +12530,7 @@ F:	mm/kmsan/
 F:	scripts/Makefile.kmsan
 
 KPROBES
-M:	Naveen N. Rao <naveen[email protected]>
+M:	Naveen N Rao <naveen@kernel.org>
 M:	Anil S Keshavamurthy <[email protected]>
 M:	"David S. Miller" <[email protected]>
 M:	Masami Hiramatsu <[email protected]>
@@ -12906,7 +12907,7 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT)
 M:	Michael Ellerman <[email protected]>
 R:	Nicholas Piggin <[email protected]>
 R:	Christophe Leroy <[email protected]>
-R:	Naveen N. Rao <naveen[email protected]>
+R:	Naveen N Rao <naveen@kernel.org>
 L:	[email protected]
 S:	Supported
 W:	https://github.com/linuxppc/wiki/wiki
@@ -15762,6 +15763,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml
 F:	drivers/hwmon/nct6775-i2c.c
 
+NETCONSOLE
+M:	Breno Leitao <[email protected]>
+S:	Maintained
+F:	Documentation/networking/netconsole.rst
+F:	drivers/net/netconsole.c
+
 NETDEVSIM
 M:	Jakub Kicinski <[email protected]>
 S:	Maintained

drivers/isdn/hardware/mISDN/hfcmulti.c

@@ -1901,7 +1901,7 @@ hfcmulti_dtmf(struct hfc_multi *hc)
 static void
 hfcmulti_tx(struct hfc_multi *hc, int ch)
 {
-	int i, ii, temp, len = 0;
+	int i, ii, temp, tmp_len, len = 0;
 	int Zspace, z1, z2; /* must be int for calculation */
 	int Fspace, f1, f2;
 	u_char *d;
@@ -2122,14 +2122,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch)
 		HFC_wait_nodebug(hc);
 	}
 
+	tmp_len = (*sp)->len;
 	dev_kfree_skb(*sp);
 	/* check for next frame */
 	if (bch && get_next_bframe(bch)) {
-		len = (*sp)->len;
+		len = tmp_len;
 		goto next_frame;
 	}
 	if (dch && get_next_dframe(dch)) {
-		len = (*sp)->len;
+		len = tmp_len;
 		goto next_frame;
 	}
 

drivers/net/bonding/bond_main.c

@@ -1121,13 +1121,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	return bestslave;
 }
 
+/* must be called in RCU critical section or with RTNL held */
 static bool bond_should_notify_peers(struct bonding *bond)
 {
-	struct slave *slave;
-
-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	rcu_read_unlock();
+	struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
 
 	if (!slave || !bond->send_peer_notif ||
 	    bond->send_peer_notif %

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -4052,6 +4052,7 @@ static void bnxt_reset_rx_ring_struct(struct bnxt *bp,
 
 	rxr->page_pool->p.napi = NULL;
 	rxr->page_pool = NULL;
+	memset(&rxr->xdp_rxq, 0, sizeof(struct xdp_rxq_info));
 
 	ring = &rxr->rx_ring_struct;
 	rmem = &ring->ring_mem;
@@ -15018,6 +15019,16 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	if (rc)
 		return rc;
 
+	rc = xdp_rxq_info_reg(&clone->xdp_rxq, bp->dev, idx, 0);
+	if (rc < 0)
+		goto err_page_pool_destroy;
+
+	rc = xdp_rxq_info_reg_mem_model(&clone->xdp_rxq,
+					MEM_TYPE_PAGE_POOL,
+					clone->page_pool);
+	if (rc)
+		goto err_rxq_info_unreg;
+
 	ring = &clone->rx_ring_struct;
 	rc = bnxt_alloc_ring(bp, &ring->ring_mem);
 	if (rc)
@@ -15047,6 +15058,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
 err_free_rx_ring:
 	bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem);
+err_rxq_info_unreg:
+	xdp_rxq_info_unreg(&clone->xdp_rxq);
+err_page_pool_destroy:
 	clone->page_pool->p.napi = NULL;
 	page_pool_destroy(clone->page_pool);
 	clone->page_pool = NULL;
@@ -15062,6 +15076,8 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	bnxt_free_one_rx_ring(bp, rxr);
 	bnxt_free_one_rx_agg_ring(bp, rxr);
 
+	xdp_rxq_info_unreg(&rxr->xdp_rxq);
+
 	page_pool_destroy(rxr->page_pool);
 	rxr->page_pool = NULL;
 
@@ -15145,6 +15161,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod;
 	rxr->rx_next_cons = clone->rx_next_cons;
 	rxr->page_pool = clone->page_pool;
+	rxr->xdp_rxq = clone->xdp_rxq;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 

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

@@ -866,22 +866,42 @@ static bool gve_can_send_tso(const struct sk_buff *skb)
 	const int header_len = skb_tcp_all_headers(skb);
 	const int gso_size = shinfo->gso_size;
 	int cur_seg_num_bufs;
+	int prev_frag_size;
 	int cur_seg_size;
 	int i;
 
 	cur_seg_size = skb_headlen(skb) - header_len;
+	prev_frag_size = skb_headlen(skb);
 	cur_seg_num_bufs = cur_seg_size > 0;
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		if (cur_seg_size >= gso_size) {
 			cur_seg_size %= gso_size;
 			cur_seg_num_bufs = cur_seg_size > 0;
+
+			if (prev_frag_size > GVE_TX_MAX_BUF_SIZE_DQO) {
+				int prev_frag_remain = prev_frag_size %
+					GVE_TX_MAX_BUF_SIZE_DQO;
+
+				/* If the last descriptor of the previous frag
+				 * is less than cur_seg_size, the segment will
+				 * span two descriptors in the previous frag.
+				 * Since max gso size (9728) is less than
+				 * GVE_TX_MAX_BUF_SIZE_DQO, it is impossible
+				 * for the segment to span more than two
+				 * descriptors.
+				 */
+				if (prev_frag_remain &&
+				    cur_seg_size > prev_frag_remain)
+					cur_seg_num_bufs++;
+			}
 		}
 
 		if (unlikely(++cur_seg_num_bufs > max_bufs_per_seg))
 			return false;
 
-		cur_seg_size += skb_frag_size(&shinfo->frags[i]);
+		prev_frag_size = skb_frag_size(&shinfo->frags[i]);
+		cur_seg_size += prev_frag_size;
 	}
 
 	return true;

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

@@ -534,7 +534,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
  *
  * Returns the number of available flow director filters to this VSI
  */
-static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
+int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
 {
 	u16 vsi_num = ice_get_hw_vsi_num(hw, vsi->idx);
 	u16 num_guar;

drivers/net/ethernet/intel/ice/ice_fdir.h

@@ -207,6 +207,8 @@ struct ice_fdir_base_pkt {
 	const u8 *tun_pkt;
 };
 
+struct ice_vsi;
+
 int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
 int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
 int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
@@ -218,6 +220,7 @@ int
 ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 			  u8 *pkt, bool frag, bool tun);
 int ice_get_fdir_cnt_all(struct ice_hw *hw);
+int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi);
 bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input);
 bool ice_fdir_has_frag(enum ice_fltr_ptype flow);
 struct ice_fdir_fltr *

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

@@ -2400,10 +2400,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
 
 		/* Propagate some data to the recipe database */
 		recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority;
-		recps[idx].need_pass_l2 = root_bufs.content.act_ctrl &
-					  ICE_AQ_RECIPE_ACT_NEED_PASS_L2;
-		recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl &
-					   ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2;
+		recps[idx].need_pass_l2 = !!(root_bufs.content.act_ctrl &
+					     ICE_AQ_RECIPE_ACT_NEED_PASS_L2);
+		recps[idx].allow_pass_l2 = !!(root_bufs.content.act_ctrl &
+					      ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2);
 		bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS);
 		if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) {
 			set_bit(root_bufs.content.result_indx &