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()
  ...

16 files changed, 80 insertions, 19 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index af9ddd3902cc..1cd92c12e782 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/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 %
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bb3be33c1bbd..ffa74c26ee53 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/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 @@ err_free_rx_agg_ring:
 	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);
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 0b3cca3fc792..f879426cb552 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/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;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index e3cab8e98f52..5412eff8ef23 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/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;
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 021ecbac7848..ab5b118daa2d 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/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 *
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 3caafcdc301f..fe8847184cb1 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/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 &
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 8e4ff3af86c6..b4feb0927687 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -536,6 +536,8 @@ static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir)
 		fdir->fdir_fltr_cnt[flow][0] = 0;
 		fdir->fdir_fltr_cnt[flow][1] = 0;
 	}
+
+	fdir->fdir_fltr_cnt_total = 0;
 }
 
 /**
@@ -1560,6 +1562,7 @@ ice_vc_add_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 	resp->status = status;
 	resp->flow_id = conf->flow_id;
 	vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]++;
+	vf->fdir.fdir_fltr_cnt_total++;
 
 	ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
 				    (u8 *)resp, len);
@@ -1624,6 +1627,7 @@ ice_vc_del_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 	resp->status = status;
 	ice_vc_fdir_remove_entry(vf, conf, conf->flow_id);
 	vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]--;
+	vf->fdir.fdir_fltr_cnt_total--;
 
 	ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
 				    (u8 *)resp, len);
@@ -1790,6 +1794,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	struct virtchnl_fdir_add *stat = NULL;
 	struct virtchnl_fdir_fltr_conf *conf;
 	enum virtchnl_status_code v_ret;
+	struct ice_vsi *vf_vsi;
 	struct device *dev;
 	struct ice_pf *pf;
 	int is_tun = 0;
@@ -1798,6 +1803,17 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
+	vf_vsi = ice_get_vf_vsi(vf);
+
+#define ICE_VF_MAX_FDIR_FILTERS	128
+	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
+	    vf->fdir.fdir_fltr_cnt_total >= ICE_VF_MAX_FDIR_FILTERS) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		dev_err(dev, "Max number of FDIR filters for VF %d is reached\n",
+			vf->vf_id);
+		goto err_exit;
+	}
+
 	ret = ice_vc_fdir_param_check(vf, fltr->vsi_id);
 	if (ret) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
index c5bcc8d7481c..ac6dcab454b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
@@ -29,6 +29,7 @@ struct ice_vf_fdir_ctx {
 struct ice_vf_fdir {
 	u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
 	int prof_entry_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
+	u16 fdir_fltr_cnt_total;
 	struct ice_fd_hw_prof **fdir_prof;
 
 	struct idr fdir_rule_idr;
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 16761fde6c6c..1c5b85a86df1 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -249,7 +249,7 @@
 #define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
 
 #define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
-#define MBI_RX_AGE_SEL_MASK		GENMASK(18, 17)
+#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
 #define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
 
 #define REG_GDM3_FWD_CFG		GDM3_BASE
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 0cc2dd85652f..16ca427cf4c3 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4223,8 +4223,6 @@ static int mtk_free_dev(struct mtk_eth *eth)
 		metadata_dst_free(eth->dsa_meta[i]);
 	}
 
-	free_netdev(eth->dummy_dev);
-
 	return 0;
 }
 
@@ -5090,6 +5088,7 @@ static void mtk_remove(struct platform_device *pdev)
 	netif_napi_del(&eth->tx_napi);
 	netif_napi_del(&eth->rx_napi);
 	mtk_cleanup(eth);
+	free_netdev(eth->dummy_dev);
 	mtk_mdio_cleanup(eth);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index dbd9f93b2460..f98741d2607e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -977,7 +977,7 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
 }
 
 static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				    __le16 perfect_match, bool is_double)
+				    u16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 6a987cf598e4..f196cd99d510 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -615,7 +615,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 }
 
 static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				      __le16 perfect_match, bool is_double)
+				      u16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 97934ccba5b1..e53c32362774 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -393,7 +393,7 @@ struct stmmac_ops {
 			     struct stmmac_rss *cfg, u32 num_rxq);
 	/* VLAN */
 	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
-				 __le16 perfect_match, bool is_double);
+				 u16 perfect_match, bool is_double);
 	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
 	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
 			   struct sk_buff *skb);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4b6a359e5a94..12689774d755 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6641,7 +6641,7 @@ static u32 stmmac_vid_crc32_le(__le16 vid_le)
 static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 {
 	u32 crc, hash = 0;
-	__le16 pmatch = 0;
+	u16 pmatch = 0;
 	int count = 0;
 	u16 vid = 0;
 
@@ -6656,7 +6656,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 		if (count > 2) /* VID = 0 always passes filter */
 			return -EOPNOTSUPP;
 
-		pmatch = cpu_to_le16(vid);
+		pmatch = vid;
 		hash = 0;
 	}
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index bfdd3875fe86..77574f7a3bd4 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1177,6 +1177,11 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	struct sk_buff *skb;
 	int err, depth;
 
+	if (unlikely(xdp->data_end - xdp->data < ETH_HLEN)) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	if (q->flags & IFF_VNET_HDR)
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9b24861464bc..1d06c560c5e6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2455,6 +2455,9 @@ static int tun_xdp_one(struct tun_struct *tun,
 	bool skb_xdp = false;
 	struct page *page;
 
+	if (unlikely(datasize < ETH_HLEN))
+		return -EINVAL;
+
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog) {
 		if (gso->gso_type) {