Merge tag 'v5.13-rc6' into driver-core-next

We need the driver core fix in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

56 files changed, 645 insertions, 397 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 314f8d806723..9058f09f921e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -2177,8 +2177,6 @@ int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid,
 			  bool persistent, u8 *smt_idx);
 int cxgb4_get_msix_idx_from_bmap(struct adapter *adap);
 void cxgb4_free_msix_idx_in_bmap(struct adapter *adap, u32 msix_idx);
-int cxgb_open(struct net_device *dev);
-int cxgb_close(struct net_device *dev);
 void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q);
 void cxgb4_quiesce_rx(struct sge_rspq *q);
 int cxgb4_port_mirror_alloc(struct net_device *dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 421bd9b88028..1f601de02e70 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2834,7 +2834,7 @@ static void cxgb_down(struct adapter *adapter)
 /*
  * net_device operations
  */
-int cxgb_open(struct net_device *dev)
+static int cxgb_open(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2882,7 +2882,7 @@ out_unlock:
 	return err;
 }
 
-int cxgb_close(struct net_device *dev)
+static int cxgb_close(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 1b88bd1c2dbe..dd9be229819a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -997,20 +997,16 @@ int cxgb4_tc_flower_destroy(struct net_device *dev,
 	if (!ch_flower)
 		return -ENOENT;
 
+	rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
+			       adap->flower_ht_params);
+
 	ret = cxgb4_flow_rule_destroy(dev, ch_flower->fs.tc_prio,
 				      &ch_flower->fs, ch_flower->filter_id);
 	if (ret)
-		goto err;
+		netdev_err(dev, "Flow rule destroy failed for tid: %u, ret: %d",
+			   ch_flower->filter_id, ret);
 
-	ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
-				     adap->flower_ht_params);
-	if (ret) {
-		netdev_err(dev, "Flow remove from rhashtable failed");
-		goto err;
-	}
 	kfree_rcu(ch_flower, rcu);
-
-err:
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index 6c259de96f96..338b04f339b3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -589,7 +589,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	 * down before configuring tc params.
 	 */
 	if (netif_running(dev)) {
-		cxgb_close(dev);
+		netif_tx_stop_all_queues(dev);
+		netif_carrier_off(dev);
 		needs_bring_up = true;
 	}
 
@@ -615,8 +616,10 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	}
 
 out:
-	if (needs_bring_up)
-		cxgb_open(dev);
+	if (needs_bring_up) {
+		netif_tx_start_all_queues(dev);
+		netif_carrier_on(dev);
+	}
 
 	mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
 	return ret;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 1e5f2edb70cf..6a099cb34b12 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2556,6 +2556,12 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc)
 	if (!eosw_txq)
 		return -ENOMEM;
 
+	if (!(adap->flags & CXGB4_FW_OK)) {
+		/* Don't stall caller when access to FW is lost */
+		complete(&eosw_txq->completion);
+		return -EIO;
+	}
+
 	skb = alloc_skb(len, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index de70c16ef619..b883ab809df3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+		if (result == I40E_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		result = I40E_XDP_REDIR;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 46d884417c63..68f177a86403 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -162,9 +162,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
 		rcu_read_unlock();
-		return result;
+		return I40E_XDP_REDIR;
 	}
 
 	switch (act) {
@@ -173,11 +174,14 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+		if (result == I40E_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index e35db3ff583b..2924c67567b8 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -335,6 +335,7 @@ struct ice_vsi {
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_ring **xdp_rings;	 /* XDP ring array */
+	unsigned long *af_xdp_zc_qps;	 /* tracks AF_XDP ZC enabled qps */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
 
@@ -547,15 +548,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
  */
 static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring)
 {
+	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
 	if (ice_ring_is_xdp(ring))
-		qid -= ring->vsi->num_xdp_txq;
+		qid -= vsi->num_xdp_txq;
 
-	if (!ice_is_xdp_ena_vsi(ring->vsi))
+	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
 		return NULL;
 
-	return xsk_get_pool_from_qid(ring->vsi->netdev, qid);
+	return xsk_get_pool_from_qid(vsi->netdev, qid);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index d9ddd0bcf65f..99301ad95290 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1773,49 +1773,6 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
 						100000baseKR4_Full);
 	}
-
-	/* Autoneg PHY types */
-	if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
-	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
-	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
 }
 
 #define TEST_SET_BITS_TIMEOUT	50
@@ -1972,9 +1929,7 @@ ice_get_link_ksettings(struct net_device *netdev,
 		ks->base.port = PORT_TP;
 		break;
 	case ICE_MEDIA_BACKPLANE:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Backplane);
 		ks->base.port = PORT_NONE;
@@ -2049,6 +2004,12 @@ ice_get_link_ksettings(struct net_device *netdev,
 	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
 		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
 
+	/* Set supported and advertised autoneg */
+	if (ice_is_phy_caps_an_enabled(caps)) {
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+	}
+
 done:
 	kfree(caps);
 	return err;
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index de38a0fc9665..9b8300d4a267 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -31,6 +31,7 @@
 #define PF_FW_ATQLEN_ATQOVFL_M			BIT(29)
 #define PF_FW_ATQLEN_ATQCRIT_M			BIT(30)
 #define VF_MBX_ARQLEN(_VF)			(0x0022BC00 + ((_VF) * 4))
+#define VF_MBX_ATQLEN(_VF)			(0x0022A800 + ((_VF) * 4))
 #define PF_FW_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_FW_ATQT				0x00080400
 #define PF_MBX_ARQBAH				0x0022E400
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 82e2ce23df3d..d70ee573fde5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->q_vectors)
 		goto err_vectors;
 
+	vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL);
+	if (!vsi->af_xdp_zc_qps)
+		goto err_zc_qps;
+
 	return 0;
 
+err_zc_qps:
+	devm_kfree(dev, vsi->q_vectors);
 err_vectors:
 	devm_kfree(dev, vsi->rxq_map);
 err_rxq_map:
@@ -194,6 +200,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		break;
 	case ICE_VSI_VF:
 		vf = &pf->vf[vsi->vf_id];
+		if (vf->num_req_qs)
+			vf->num_vf_qs = vf->num_req_qs;
 		vsi->alloc_txq = vf->num_vf_qs;
 		vsi->alloc_rxq = vf->num_vf_qs;
 		/* pf->num_msix_per_vf includes (VF miscellaneous vector +
@@ -288,6 +296,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 
 	dev = ice_pf_to_dev(pf);
 
+	if (vsi->af_xdp_zc_qps) {
+		bitmap_free(vsi->af_xdp_zc_qps);
+		vsi->af_xdp_zc_qps = NULL;
+	}
 	/* free the ring and vector containers */
 	if (vsi->q_vectors) {
 		devm_kfree(dev, vsi->q_vectors);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index e2b4b29ea207..04748aa4c7c8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog)
 {
 	struct ice_ring *xdp_ring;
-	int err;
+	int err, result;
 	u32 act;
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
@@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
 		return ICE_XDP_PASS;
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()];
-		return ice_xmit_xdp_buff(xdp, xdp_ring);
+		result = ice_xmit_xdp_buff(xdp, xdp_ring);
+		if (result == ICE_XDP_CONSUMED)
+			goto out_failure;
+		return result;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		return ICE_XDP_REDIR;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
@@ -2143,6 +2149,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	struct ice_tx_offload_params offload = { 0 };
 	struct ice_vsi *vsi = tx_ring->vsi;
 	struct ice_tx_buf *first;
+	struct ethhdr *eth;
 	unsigned int count;
 	int tso, csum;
 
@@ -2189,7 +2196,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 		goto out_drop;
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
-	if (unlikely(skb->priority == TC_PRIO_CONTROL &&
+	eth = (struct ethhdr *)skb_mac_header(skb);
+	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+		      eth->h_proto == htons(ETH_P_LLDP)) &&
 		     vsi->type == ICE_VSI_PF &&
 		     vsi->port_info->qos_cfg.is_sw_lldp))
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index a1d22d2aa0bd..97a46c616aca 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -713,13 +713,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
-	/* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it
-	 * in the case of VFR. If this is done for PFR, it can mess up VF
-	 * resets because the VF driver may already have started cleanup
-	 * by the time we get here.
+	/* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver
+	 * needs to clear them in the case of VFR/VFLR. If this is done for
+	 * PFR, it can mess up VF resets because the VF driver may already
+	 * have started cleanup by the time we get here.
 	 */
-	if (!is_pfr)
+	if (!is_pfr) {
 		wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0);
+		wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0);
+	}
 
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
@@ -1698,7 +1700,12 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 		ice_vf_ctrl_vsi_release(vf);
 
 	ice_vf_pre_vsi_rebuild(vf);
-	ice_vf_rebuild_vsi_with_release(vf);
+
+	if (ice_vf_rebuild_vsi_with_release(vf)) {
+		dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id);
+		return false;
+	}
+
 	ice_vf_post_vsi_rebuild(vf);
 
 	/* if the VF has been reset allow it to come up again */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index faa7b8d96adb..a1f89ea3c2bd 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -270,6 +270,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 	if (!pool)
 		return -EINVAL;
 
+	clear_bit(qid, vsi->af_xdp_zc_qps);
 	xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);
 
 	return 0;
@@ -300,6 +301,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	if (err)
 		return err;
 
+	set_bit(qid, vsi->af_xdp_zc_qps);
+
 	return 0;
 }
 
@@ -473,9 +476,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
 		rcu_read_unlock();
-		return result;
+		return ICE_XDP_REDIR;
 	}
 
 	switch (act) {
@@ -484,11 +488,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index];
 		result = ice_xmit_xdp_buff(xdp, xdp_ring);
+		if (result == ICE_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 7bda8c5edea5..2d3daf022651 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -749,7 +749,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_tx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
 int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			struct sk_buff *skb);
+			ktime_t *timestamp);
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
 void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 038a9fd1af44..b2a042f825ff 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8280,7 +8280,7 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring,
 static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 					 struct igb_rx_buffer *rx_buffer,
 					 struct xdp_buff *xdp,
-					 union e1000_adv_rx_desc *rx_desc)
+					 ktime_t timestamp)
 {
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8300,12 +8300,8 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	if (unlikely(!skb))
 		return NULL;
 
-	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
-		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
-			xdp->data += IGB_TS_HDR_LEN;
-			size -= IGB_TS_HDR_LEN;
-		}
-	}
+	if (timestamp)
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
 
 	/* Determine available headroom for copy */
 	headlen = size;
@@ -8336,7 +8332,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 				     struct igb_rx_buffer *rx_buffer,
 				     struct xdp_buff *xdp,
-				     union e1000_adv_rx_desc *rx_desc)
+				     ktime_t timestamp)
 {
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8363,11 +8359,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	/* pull timestamp out of packet data */
-	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
-		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
-			__skb_pull(skb, IGB_TS_HDR_LEN);
-	}
+	if (timestamp)
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
 
 	/* update buffer offset */
 #if (PAGE_SIZE < 8192)
@@ -8401,18 +8394,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 		break;
 	case XDP_TX:
 		result = igb_xdp_xmit_back(adapter, xdp);
+		if (result == IGB_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
-		if (!err)
-			result = IGB_XDP_REDIR;
-		else
-			result = IGB_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		result = IGB_XDP_REDIR;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
@@ -8682,7 +8677,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	while (likely(total_packets < budget)) {
 		union e1000_adv_rx_desc *rx_desc;
 		struct igb_rx_buffer *rx_buffer;
+		ktime_t timestamp = 0;
+		int pkt_offset = 0;
 		unsigned int size;
+		void *pktbuf;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -8702,14 +8700,24 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		dma_rmb();
 
 		rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
+		pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset;
+
+		/* pull rx packet timestamp if available and valid */
+		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+			int ts_hdr_len;
+
+			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
+							 pktbuf, &timestamp);
+
+			pkt_offset += ts_hdr_len;
+			size -= ts_hdr_len;
+		}
 
 		/* retrieve a buffer from the ring */
 		if (!skb) {
-			unsigned int offset = igb_rx_offset(rx_ring);
-			unsigned char *hard_start;
+			unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring);
+			unsigned int offset = pkt_offset + igb_rx_offset(rx_ring);
 
-			hard_start = page_address(rx_buffer->page) +
-				     rx_buffer->page_offset - offset;
 			xdp_prepare_buff(&xdp, hard_start, offset, size, true);
 #if (PAGE_SIZE > 4096)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
@@ -8732,10 +8740,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		} else if (skb)
 			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc);
+			skb = igb_build_skb(rx_ring, rx_buffer, &xdp,
+					    timestamp);
 		else
 			skb = igb_construct_skb(rx_ring, rx_buffer,
-						&xdp, rx_desc);
+						&xdp, timestamp);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index ba61fe9bfaf4..d68cd4466a54 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -856,30 +856,28 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 	dev_kfree_skb_any(skb);
 }
 
-#define IGB_RET_PTP_DISABLED 1
-#define IGB_RET_PTP_INVALID 2
-
 /**
  * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp
  * @q_vector: Pointer to interrupt specific structure
  * @va: Pointer to address containing Rx buffer
- * @skb: Buffer containing timestamp and packet
+ * @timestamp: Pointer where timestamp will be stored
  *
  * This function is meant to retrieve a timestamp from the first buffer of an
  * incoming frame.  The value is stored in little endian format starting on
  * byte 8
  *
- * Returns: 0 if success, nonzero if failure
+ * Returns: The timestamp header length or 0 if not available
  **/
 int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			struct sk_buff *skb)
+			ktime_t *timestamp)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
+	struct skb_shared_hwtstamps ts;
 	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
 
 	if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
-		return IGB_RET_PTP_DISABLED;
+		return 0;
 
 	/* The timestamp is recorded in little endian format.
 	 * DWORD: 0        1        2        3
@@ -888,10 +886,9 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 
 	/* check reserved dwords are zero, be/le doesn't matter for zero */
 	if (regval[0])
-		return IGB_RET_PTP_INVALID;
+		return 0;
 
-	igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
-				   le64_to_cpu(regval[1]));
+	igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
 
 	/* adjust timestamp for the RX latency based on link speed */
 	if (adapter->hw.mac.type == e1000_i210) {
@@ -907,10 +904,10 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			break;
 		}
 	}
-	skb_hwtstamps(skb)->hwtstamp =
-		ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
 
-	return 0;
+	*timestamp = ktime_sub_ns(ts.hwtstamp, adjust);
+
+	return IGB_TS_HDR_LEN;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 069471b7ffb0..f1adf154ec4a 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2047,20 +2047,19 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 		break;
 	case XDP_TX:
 		if (igc_xdp_xmit_back(adapter, xdp) < 0)
-			res = IGC_XDP_CONSUMED;
-		else
-			res = IGC_XDP_TX;
+			goto out_failure;
+		res = IGC_XDP_TX;
 		break;
 	case XDP_REDIRECT:
 		if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0)
-			res = IGC_XDP_CONSUMED;
-		else
-			res = IGC_XDP_REDIRECT;
+			goto out_failure;
+		res = IGC_XDP_REDIRECT;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(adapter->netdev, prog, act);
 		fallthrough;
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c5ec17d19c59..2ac5b82676f3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 		break;
 	case XDP_TX:
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf)) {
-			result = IXGBE_XDP_CONSUMED;
-			break;
-		}
+		if (unlikely(!xdpf))
+			goto out_failure;
 		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		if (result == IXGBE_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
-		if (!err)
-			result = IXGBE_XDP_REDIR;
-		else
-			result = IXGBE_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		result = IXGBE_XDP_REDIR;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 91ad5b902673..f72d2978263b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -106,9 +106,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
 		rcu_read_unlock();
-		return result;
+		return IXGBE_XDP_REDIR;
 	}
 
 	switch (act) {
@@ -116,16 +117,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 		break;
 	case XDP_TX:
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf)) {
-			result = IXGBE_XDP_CONSUMED;
-			break;
-		}
+		if (unlikely(!xdpf))
+			goto out_failure;
 		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		if (result == IXGBE_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index ba2ed8a43d2d..0e733cc15c58 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1067,11 +1067,14 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 	case XDP_TX:
 		xdp_ring = adapter->xdp_ring[rx_ring->queue_index];
 		result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp);
+		if (result == IXGBEVF_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index f6cfec81ccc3..dc4ac1a2b6b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET	0xa8
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET	0xac
+#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET	0xcc
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET	0xd0
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET	0xd2
@@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	if (mlx4_is_mfunc(dev))
 		disable_unsupported_roce_caps(outbox);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER);
+	dev_cap->map_clock_to_user = field & 0x80;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET);
 	dev_cap->reserved_qps = 1 << (field & 0xf);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 8f020f26ebf5..cf64e54eecb0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -131,6 +131,7 @@ struct mlx4_dev_cap {
 	u32 health_buffer_addrs;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 	bool wol_port[MLX4_MAX_PORTS + 1];
+	bool map_clock_to_user;
 };
 
 struct mlx4_func_cap {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c326b434734e..00c84656b2e7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
+	dev->caps.map_clock_to_user  = dev_cap->map_clock_to_user;
 	dev->caps.uar_page_size	     = PAGE_SIZE;
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
 	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
@@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
 	if (mlx4_is_slave(dev))
 		return -EOPNOTSUPP;
 
+	if (!dev->caps.map_clock_to_user) {
+		mlx4_dbg(dev, "Map clock to user is not supported.\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (!params)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 8360289813f0..d6513aef5cd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1624,12 +1624,13 @@ static int mlx5e_set_fecparam(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	unsigned long fec_bitmap;
 	u16 fec_policy = 0;
 	int mode;
 	int err;
 
-	if (bitmap_weight((unsigned long *)&fecparam->fec,
-			  ETHTOOL_FEC_LLRS_BIT + 1) > 1)
+	bitmap_from_arr32(&fec_bitmap, &fecparam->fec, sizeof(fecparam->fec) * BITS_PER_BYTE);
+	if (bitmap_weight(&fec_bitmap, ETHTOOL_FEC_LLRS_BIT + 1) > 1)
 		return -EOPNOTSUPP;
 
 	for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) {
@@ -1893,6 +1894,13 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 	if (curr_val == new_val)
 		return 0;
 
+	if (new_val && !priv->profile->rx_ptp_support &&
+	    priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) {
+		netdev_err(priv->netdev,
+			   "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n");
+		return -EINVAL;
+	}
+
 	new_params = priv->channels.params;
 	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
 	if (priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ad0f69480b9c..ec6bafe7a2e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3858,6 +3858,16 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 			netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n");
 	}
 
+	if (mlx5e_is_uplink_rep(priv)) {
+		features &= ~NETIF_F_HW_TLS_RX;
+		if (netdev->features & NETIF_F_HW_TLS_RX)
+			netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
+
+		features &= ~NETIF_F_HW_TLS_TX;
+		if (netdev->features & NETIF_F_HW_TLS_TX)
+			netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
+	}
+
 	mutex_unlock(&priv->state_lock);
 
 	return features;
@@ -3974,11 +3984,45 @@ int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx)
 	return mlx5e_ptp_rx_manage_fs(priv, set);
 }
 
-int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+static int mlx5e_hwstamp_config_no_ptp_rx(struct mlx5e_priv *priv, bool rx_filter)
+{
+	bool rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def;
+	int err;
+
+	if (!rx_filter)
+		/* Reset CQE compression to Admin default */
+		return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def);
+
+	if (!MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS))
+		return 0;
+
+	/* Disable CQE compression */
+	netdev_warn(priv->netdev, "Disabling RX cqe compression\n");
+	err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+	if (err)
+		netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err);
+
+	return err;
+}
+
+static int mlx5e_hwstamp_config_ptp_rx(struct mlx5e_priv *priv, bool ptp_rx)
 {
 	struct mlx5e_params new_params;
+
+	if (ptp_rx == priv->channels.params.ptp_rx)
+		return 0;
+
+	new_params = priv->channels.params;
+	new_params.ptp_rx = ptp_rx;
+	return mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx,
+					&new_params.ptp_rx, true);
+}
+
+int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+{
 	struct hwtstamp_config config;
 	bool rx_cqe_compress_def;
+	bool ptp_rx;
 	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
@@ -3998,13 +4042,12 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	}
 
 	mutex_lock(&priv->state_lock);
-	new_params = priv->channels.params;
 	rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def;
 
 	/* RX HW timestamp */
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		new_params.ptp_rx = false;
+		ptp_rx = false;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -4021,24 +4064,25 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		new_params.ptp_rx = rx_cqe_compress_def;
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		/* ptp_rx is set if both HW TS is set and CQE
+		 * compression is set
+		 */
+		ptp_rx = rx_cqe_compress_def;
 		break;
 	default:
-		mutex_unlock(&priv->state_lock);
-		return -ERANGE;
+		err = -ERANGE;
+		goto err_unlock;
 	}
 
-	if (new_params.ptp_rx == priv->channels.params.ptp_rx)
-		goto out;
+	if (!priv->profile->rx_ptp_support)
+		err = mlx5e_hwstamp_config_no_ptp_rx(priv,
+						     config.rx_filter != HWTSTAMP_FILTER_NONE);
+	else
+		err = mlx5e_hwstamp_config_ptp_rx(priv, ptp_rx);
+	if (err)
+		goto err_unlock;
 
-	err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx,
-				       &new_params.ptp_rx, true);
-	if (err) {
-		mutex_unlock(&priv->state_lock);
-		return err;
-	}
-out:
 	memcpy(&priv->tstamp, &config, sizeof(config));
 	mutex_unlock(&priv->state_lock);
 
@@ -4047,6 +4091,9 @@ out:
 
 	return copy_to_user(ifr->ifr_data, &config,
 			    sizeof(config)) ? -EFAULT : 0;
+err_unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
 }
 
 int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 2c776e7a7692..dd64878e5b38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2015,11 +2015,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				    misc_parameters_3);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
+	enum fs_flow_table_type fs_type;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 	u8 *match_level;
 	int err;
 
+	fs_type = mlx5e_is_eswitch_flow(flow) ? FS_FT_FDB : FS_FT_NIC_RX;
 	match_level = outer_match_level;
 
 	if (dissector->used_keys &
@@ -2145,6 +2147,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		if (match.mask->vlan_id ||
 		    match.mask->vlan_priority ||
 		    match.mask->vlan_tpid) {
+			if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ft_field_support.outer_second_vid,
+						     fs_type)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Matching on CVLAN is not supported");
+				return -EOPNOTSUPP;
+			}
+
 			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_misc, misc_c,
 					 outer_second_svlan_tag, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index db1e74280e57..d18a28a6e9a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -219,7 +219,8 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest,
 			 struct mlx5_fs_chains *chains,
 			 int i)
 {
-	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+	if (mlx5_chains_ignore_flow_level_supported(chains))
+		flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = mlx5_chains_get_tc_end_ft(chains);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index d5d57630015f..106b50e42b46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -349,6 +349,9 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work)
 						      reset_abort_work);
 	struct mlx5_core_dev *dev = fw_reset->dev;
 
+	if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		return;
+
 	mlx5_sync_reset_clear_reset_requested(dev, true);
 	mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n");
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index 00ef10a1a9f8..20a4047f2737 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -107,7 +107,7 @@ bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains)
 	return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED;
 }
 
-static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
 {
 	return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
index e96f345e7dae..d50bdb226cef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
@@ -28,6 +28,7 @@ struct mlx5_chains_attr {
 
 bool
 mlx5_chains_prios_supported(struct mlx5_fs_chains *chains);
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains);
 bool
 mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains);
 u32
@@ -70,6 +71,10 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
 
 #else /* CONFIG_MLX5_CLS_ACT */
 
+static inline bool
+mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+{ return false; }
+
 static inline struct mlx5_flow_table *
 mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
 		      u32 level) { return ERR_PTR(-EOPNOTSUPP); }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
index 1fbcd012bb85..7ccfd40586ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -112,7 +112,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 	int ret;
 
 	ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
-	ft_attr.level = dmn->info.caps.max_ft_level - 2;
+	ft_attr.level = min_t(int, dmn->info.caps.max_ft_level - 2,
+			      MLX5_FT_MAX_MULTIPATH_LEVEL);
 	ft_attr.reformat_en = reformat_req;
 	ft_attr.decap_en = reformat_req;
 
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index c84c8bf2bc20..fc99ad8e4a38 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -3815,6 +3815,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(&pdev->dev,
 			"invalid sram_size %dB or board span %ldB\n",
 			mgp->sram_size, mgp->board_span);
+		status = -EINVAL;
 		goto abort_with_ioremap;
 	}
 	memcpy_fromio(mgp->eeprom_strings,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5d956a553434..c87202cbd3d6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1240,8 +1240,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	priv->phylink_config.dev = &priv->dev->dev;
 	priv->phylink_config.type = PHYLINK_NETDEV;
 	priv->phylink_config.pcs_poll = true;
-	priv->phylink_config.ovr_an_inband =
-		priv->plat->mdio_bus_data->xpcs_an_inband;
+	if (priv->plat->mdio_bus_data)
+		priv->phylink_config.ovr_an_inband =
+			priv->plat->mdio_bus_data->xpcs_an_inband;
 
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
@@ -7048,7 +7049,6 @@ error_mdio_register:
 	stmmac_napi_del(ndev);
 error_hw_init:
 	destroy_workqueue(priv->wq);
-	stmmac_bus_clks_config(priv, false);
 	bitmap_free(priv->af_xdp_zc_qps);
 
 	return ret;
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index b9be530b285f..ff83e00b77af 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -8,8 +8,8 @@
 
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/ieee802154.h>
 #include <linux/irq.h>
@@ -1388,7 +1388,7 @@ MODULE_DEVICE_TABLE(spi, mrf24j40_ids);
 
 static struct spi_driver mrf24j40_driver = {
 	.driver = {
-		.of_match_table = of_match_ptr(mrf24j40_of_match),
+		.of_match_table = mrf24j40_of_match,
 		.name = "mrf24j40",
 	},
 	.id_table = mrf24j40_ids,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9b6a4a875c55..78a01c71a17c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -401,18 +401,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	/* If headroom is not 0, there is an offset between the beginning of the
 	 * data and the allocated space, otherwise the data and the allocated
 	 * space are aligned.
+	 *
+	 * Buffers with headroom use PAGE_SIZE as alloc size, see
+	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
-	if (headroom) {
-		/* Buffers with headroom use PAGE_SIZE as alloc size,
-		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
-		 */
-		truesize = PAGE_SIZE;
-		tailroom = truesize - len - offset;
-		buf = page_address(page);
-	} else {
-		tailroom = truesize - len;
-		buf = p;
-	}
+	truesize = headroom ? PAGE_SIZE : truesize;
+	tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len);
+	buf = p - headroom;
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -958,7 +953,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
-						       metasize, headroom);
+						       metasize,
+						       VIRTIO_XDP_HEADROOM);
 				return head_skb;
 			}
 			break;
diff --git a/drivers/net/wireguard/Makefile b/drivers/net/wireguard/Makefile
index fc52b2cb500b..dbe1f8514efc 100644
--- a/drivers/net/wireguard/Makefile
+++ b/drivers/net/wireguard/Makefile
@@ -1,5 +1,4 @@
-ccflags-y := -O3
-ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
+ccflags-y := -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
 ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG
 wireguard-y := main.o
 wireguard-y += noise.o
diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c
index 3725e9cd85f4..b7197e80f226 100644
--- a/drivers/net/wireguard/allowedips.c
+++ b/drivers/net/wireguard/allowedips.c
@@ -6,6 +6,8 @@
 #include "allowedips.h"
 #include "peer.h"
 
+static struct kmem_cache *node_cache;
+
 static void swap_endian(u8 *dst, const u8 *src, u8 bits)
 {
 	if (bits == 32) {
@@ -28,8 +30,11 @@ static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
 	node->bitlen = bits;
 	memcpy(node->bits, src, bits / 8U);
 }
-#define CHOOSE_NODE(parent, key) \
-	parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
+
+static inline u8 choose(struct allowedips_node *node, const u8 *key)
+{
+	return (key[node->bit_at_a] >> node->bit_at_b) & 1;
+}
 
 static void push_rcu(struct allowedips_node **stack,
 		     struct allowedips_node __rcu *p, unsigned int *len)
@@ -40,6 +45,11 @@ static void push_rcu(struct allowedips_node **stack,
 	}
 }
 
+static void node_free_rcu(struct rcu_head *rcu)
+{
+	kmem_cache_free(node_cache, container_of(rcu, struct allowedips_node, rcu));
+}
+
 static void root_free_rcu(struct rcu_head *rcu)
 {
 	struct allowedips_node *node, *stack[128] = {
@@ -49,7 +59,7 @@ static void root_free_rcu(struct rcu_head *rcu)
 	while (len > 0 && (node = stack[--len])) {
 		push_rcu(stack, node->bit[0], &len);
 		push_rcu(stack, node->bit[1], &len);
-		kfree(node);
+		kmem_cache_free(node_cache, node);
 	}
 }
 
@@ -66,60 +76,6 @@ static void root_remove_peer_lists(struct allowedips_node *root)
 	}
 }
 
-static void walk_remove_by_peer(struct allowedips_node __rcu **top,
-				struct wg_peer *peer, struct mutex *lock)
-{
-#define REF(p) rcu_access_pointer(p)
-#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
-#define PUSH(p) ({                                                             \
-		WARN_ON(IS_ENABLED(DEBUG) && len >= 128);                      \
-		stack[len++] = p;                                              \
-	})
-
-	struct allowedips_node __rcu **stack[128], **nptr;
-	struct allowedips_node *node, *prev;
-	unsigned int len;
-
-	if (unlikely(!peer || !REF(*top)))
-		return;
-
-	for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
-		nptr = stack[len - 1];
-		node = DEREF(nptr);
-		if (!node) {
-			--len;
-			continue;
-		}
-		if (!prev || REF(prev->bit[0]) == node ||
-		    REF(prev->bit[1]) == node) {
-			if (REF(node->bit[0]))
-				PUSH(&node->bit[0]);
-			else if (REF(node->bit[1]))
-				PUSH(&node->bit[1]);
-		} else if (REF(node->bit[0]) == prev) {
-			if (REF(node->bit[1]))
-				PUSH(&node->bit[1]);
-		} else {
-			if (rcu_dereference_protected(node->peer,
-				lockdep_is_held(lock)) == peer) {
-				RCU_INIT_POINTER(node->peer, NULL);
-				list_del_init(&node->peer_list);
-				if (!node->bit[0] || !node->bit[1]) {
-					rcu_assign_pointer(*nptr, DEREF(
-					       &node->bit[!REF(node->bit[0])]));
-					kfree_rcu(node, rcu);
-					node = DEREF(nptr);
-				}
-			}
-			--len;
-		}
-	}
-
-#undef REF
-#undef DEREF
-#undef PUSH
-}
-
 static unsigned int fls128(u64 a, u64 b)
 {
 	return a ? fls64(a) + 64U : fls64(b);
@@ -159,7 +115,7 @@ static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
 			found = node;
 		if (node->cidr == bits)
 			break;
-		node = rcu_dereference_bh(CHOOSE_NODE(node, key));
+		node = rcu_dereference_bh(node->bit[choose(node, key)]);
 	}
 	return found;
 }
@@ -191,8 +147,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 			   u8 cidr, u8 bits, struct allowedips_node **rnode,
 			   struct mutex *lock)
 {
-	struct allowedips_node *node = rcu_dereference_protected(trie,
-						lockdep_is_held(lock));
+	struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock));
 	struct allowedips_node *parent = NULL;
 	bool exact = false;
 
@@ -202,13 +157,24 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 			exact = true;
 			break;
 		}
-		node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
-						 lockdep_is_held(lock));
+		node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock));
 	}
 	*rnode = parent;
 	return exact;
 }
 
+static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node)
+{
+	node->parent_bit_packed = (unsigned long)parent | bit;
+	rcu_assign_pointer(*parent, node);
+}
+
+static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node)
+{
+	u8 bit = choose(parent, node->bits);
+	connect_node(&parent->bit[bit], bit, node);
+}
+
 static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	       u8 cidr, struct wg_peer *peer, struct mutex *lock)
 {
@@ -218,13 +184,13 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 		return -EINVAL;
 
 	if (!rcu_access_pointer(*trie)) {
-		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
 		if (unlikely(!node))
 			return -ENOMEM;
 		RCU_INIT_POINTER(node->peer, peer);
 		list_add_tail(&node->peer_list, &peer->allowedips_list);
 		copy_and_assign_cidr(node, key, cidr, bits);
-		rcu_assign_pointer(*trie, node);
+		connect_node(trie, 2, node);
 		return 0;
 	}
 	if (node_placement(*trie, key, cidr, bits, &node, lock)) {
@@ -233,7 +199,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 		return 0;
 	}
 
-	newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
+	newnode = kmem_cache_zalloc(node_cache, GFP_KERNEL);
 	if (unlikely(!newnode))
 		return -ENOMEM;
 	RCU_INIT_POINTER(newnode->peer, peer);
@@ -243,10 +209,10 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	if (!node) {
 		down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
 	} else {
-		down = rcu_dereference_protected(CHOOSE_NODE(node, key),
-						 lockdep_is_held(lock));
+		const u8 bit = choose(node, key);
+		down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock));
 		if (!down) {
-			rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
+			connect_node(&node->bit[bit], bit, newnode);
 			return 0;
 		}
 	}
@@ -254,30 +220,29 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	parent = node;
 
 	if (newnode->cidr == cidr) {
-		rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
+		choose_and_connect_node(newnode, down);
 		if (!parent)
-			rcu_assign_pointer(*trie, newnode);
+			connect_node(trie, 2, newnode);
 		else
-			rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
-					   newnode);
-	} else {
-		node = kzalloc(sizeof(*node), GFP_KERNEL);
-		if (unlikely(!node)) {
-			list_del(&newnode->peer_list);
-			kfree(newnode);
-			return -ENOMEM;
-		}
-		INIT_LIST_HEAD(&node->peer_list);
-		copy_and_assign_cidr(node, newnode->bits, cidr, bits);
+			choose_and_connect_node(parent, newnode);
+		return 0;
+	}
 
-		rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
-		rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
-		if (!parent)
-			rcu_assign_pointer(*trie, node);
-		else
-			rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
-					   node);
+	node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
+	if (unlikely(!node)) {
+		list_del(&newnode->peer_list);
+		kmem_cache_free(node_cache, newnode);
+		return -ENOMEM;
 	}
+	INIT_LIST_HEAD(&node->peer_list);
+	copy_and_assign_cidr(node, newnode->bits, cidr, bits);
+
+	choose_and_connect_node(node, down);
+	choose_and_connect_node(node, newnode);
+	if (!parent)
+		connect_node(trie, 2, node);
+	else
+		choose_and_connect_node(parent, node);
 	return 0;
 }
 
@@ -335,9 +300,41 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
 void wg_allowedips_remove_by_peer(struct allowedips *table,
 				  struct wg_peer *peer, struct mutex *lock)
 {
+	struct allowedips_node *node, *child, **parent_bit, *parent, *tmp;
+	bool free_parent;
+
+	if (list_empty(&peer->allowedips_list))
+		return;
 	++table->seq;
-	walk_remove_by_peer(&table->root4, peer, lock);
-	walk_remove_by_peer(&table->root6, peer, lock);
+	list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) {
+		list_del_init(&node->peer_list);
+		RCU_INIT_POINTER(node->peer, NULL);
+		if (node->bit[0] && node->bit[1])
+			continue;
+		child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])],
+						  lockdep_is_held(lock));
+		if (child)
+			child->parent_bit_packed = node->parent_bit_packed;
+		parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL);
+		*parent_bit = child;
+		parent = (void *)parent_bit -
+			 offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]);
+		free_parent = !rcu_access_pointer(node->bit[0]) &&
+			      !rcu_access_pointer(node->bit[1]) &&
+			      (node->parent_bit_packed & 3) <= 1 &&
+			      !rcu_access_pointer(parent->peer);
+		if (free_parent)
+			child = rcu_dereference_protected(
+					parent->bit[!(node->parent_bit_packed & 1)],
+					lockdep_is_held(lock));
+		call_rcu(&node->rcu, node_free_rcu);
+		if (!free_parent)
+			continue;
+		if (child)
+			child->parent_bit_packed = parent->parent_bit_packed;
+		*(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child;
+		call_rcu(&parent->rcu, node_free_rcu);
+	}
 }
 
 int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
@@ -374,4 +371,16 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
 	return NULL;
 }
 
+int __init wg_allowedips_slab_init(void)
+{
+	node_cache = KMEM_CACHE(allowedips_node, 0);
+	return node_cache ? 0 : -ENOMEM;
+}
+
+void wg_allowedips_slab_uninit(void)
+{
+	rcu_barrier();
+	kmem_cache_destroy(node_cache);
+}
+
 #include "selftest/allowedips.c"
diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h
index e5c83cafcef4..2346c797eb4d 100644
--- a/drivers/net/wireguard/allowedips.h
+++ b/drivers/net/wireguard/allowedips.h
@@ -15,14 +15,11 @@ struct wg_peer;
 struct allowedips_node {
 	struct wg_peer __rcu *peer;
 	struct allowedips_node __rcu *bit[2];
-	/* While it may seem scandalous that we waste space for v4,
-	 * we're alloc'ing to the nearest power of 2 anyway, so this
-	 * doesn't actually make a difference.
-	 */
-	u8 bits[16] __aligned(__alignof(u64));
 	u8 cidr, bit_at_a, bit_at_b, bitlen;
+	u8 bits[16] __aligned(__alignof(u64));
 
-	/* Keep rarely used list at bottom to be beyond cache line. */
+	/* Keep rarely used members at bottom to be beyond cache line. */
+	unsigned long parent_bit_packed;
 	union {
 		struct list_head peer_list;
 		struct rcu_head rcu;
@@ -33,7 +30,7 @@ struct allowedips {
 	struct allowedips_node __rcu *root4;
 	struct allowedips_node __rcu *root6;
 	u64 seq;
-};
+} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */
 
 void wg_allowedips_init(struct allowedips *table);
 void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
@@ -56,4 +53,7 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
 bool wg_allowedips_selftest(void);
 #endif
 
+int wg_allowedips_slab_init(void);
+void wg_allowedips_slab_uninit(void);
+
 #endif /* _WG_ALLOWEDIPS_H */
diff --git a/drivers/net/wireguard/main.c b/drivers/net/wireguard/main.c
index 7a7d5f1a80fc..75dbe77b0b4b 100644
--- a/drivers/net/wireguard/main.c
+++ b/drivers/net/wireguard/main.c
@@ -21,13 +21,22 @@ static int __init mod_init(void)
 {
 	int ret;
 
+	ret = wg_allowedips_slab_init();
+	if (ret < 0)
+		goto err_allowedips;
+
 #ifdef DEBUG
+	ret = -ENOTRECOVERABLE;
 	if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() ||
 	    !wg_ratelimiter_selftest())
-		return -ENOTRECOVERABLE;
+		goto err_peer;
 #endif
 	wg_noise_init();
 
+	ret = wg_peer_init();
+	if (ret < 0)
+		goto err_peer;
+
 	ret = wg_device_init();
 	if (ret < 0)
 		goto err_device;
@@ -44,6 +53,10 @@ static int __init mod_init(void)
 err_netlink:
 	wg_device_uninit();
 err_device:
+	wg_peer_uninit();
+err_peer:
+	wg_allowedips_slab_uninit();
+err_allowedips:
 	return ret;
 }
 
@@ -51,6 +64,8 @@ static void __exit mod_exit(void)
 {
 	wg_genetlink_uninit();
 	wg_device_uninit();
+	wg_peer_uninit();
+	wg_allowedips_slab_uninit();
 }
 
 module_init(mod_init);
diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c
index cd5cb0292cb6..1acd00ab2fbc 100644
--- a/drivers/net/wireguard/peer.c
+++ b/drivers/net/wireguard/peer.c
@@ -15,6 +15,7 @@
 #include <linux/rcupdate.h>
 #include <linux/list.h>
 
+static struct kmem_cache *peer_cache;
 static atomic64_t peer_counter = ATOMIC64_INIT(0);
 
 struct wg_peer *wg_peer_create(struct wg_device *wg,
@@ -29,10 +30,10 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	if (wg->num_peers >= MAX_PEERS_PER_DEVICE)
 		return ERR_PTR(ret);
 
-	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+	peer = kmem_cache_zalloc(peer_cache, GFP_KERNEL);
 	if (unlikely(!peer))
 		return ERR_PTR(ret);
-	if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+	if (unlikely(dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)))
 		goto err;
 
 	peer->device = wg;
@@ -64,7 +65,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	return peer;
 
 err:
-	kfree(peer);
+	kmem_cache_free(peer_cache, peer);
 	return ERR_PTR(ret);
 }
 
@@ -88,7 +89,7 @@ static void peer_make_dead(struct wg_peer *peer)
 	/* Mark as dead, so that we don't allow jumping contexts after. */
 	WRITE_ONCE(peer->is_dead, true);
 
-	/* The caller must now synchronize_rcu() for this to take effect. */
+	/* The caller must now synchronize_net() for this to take effect. */
 }
 
 static void peer_remove_after_dead(struct wg_peer *peer)
@@ -160,7 +161,7 @@ void wg_peer_remove(struct wg_peer *peer)
 	lockdep_assert_held(&peer->device->device_update_lock);
 
 	peer_make_dead(peer);
-	synchronize_rcu();
+	synchronize_net();
 	peer_remove_after_dead(peer);
 }
 
@@ -178,7 +179,7 @@ void wg_peer_remove_all(struct wg_device *wg)
 		peer_make_dead(peer);
 		list_add_tail(&peer->peer_list, &dead_peers);
 	}
-	synchronize_rcu();
+	synchronize_net();
 	list_for_each_entry_safe(peer, temp, &dead_peers, peer_list)
 		peer_remove_after_dead(peer);
 }
@@ -193,7 +194,8 @@ static void rcu_release(struct rcu_head *rcu)
 	/* The final zeroing takes care of clearing any remaining handshake key
 	 * material and other potentially sensitive information.
 	 */
-	kfree_sensitive(peer);
+	memzero_explicit(peer, sizeof(*peer));
+	kmem_cache_free(peer_cache, peer);
 }
 
 static void kref_release(struct kref *refcount)
@@ -225,3 +227,14 @@ void wg_peer_put(struct wg_peer *peer)
 		return;
 	kref_put(&peer->refcount, kref_release);
 }
+
+int __init wg_peer_init(void)
+{
+	peer_cache = KMEM_CACHE(wg_peer, 0);
+	return peer_cache ? 0 : -ENOMEM;
+}
+
+void wg_peer_uninit(void)
+{
+	kmem_cache_destroy(peer_cache);
+}
diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h
index 8d53b687a1d1..76e4d3128ad4 100644
--- a/drivers/net/wireguard/peer.h
+++ b/drivers/net/wireguard/peer.h
@@ -80,4 +80,7 @@ void wg_peer_put(struct wg_peer *peer);
 void wg_peer_remove(struct wg_peer *peer);
 void wg_peer_remove_all(struct wg_device *wg);
 
+int wg_peer_init(void);
+void wg_peer_uninit(void);
+
 #endif /* _WG_PEER_H */
diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c
index 846db14cb046..e173204ae7d7 100644
--- a/drivers/net/wireguard/selftest/allowedips.c
+++ b/drivers/net/wireguard/selftest/allowedips.c
@@ -19,32 +19,22 @@
 
 #include <linux/siphash.h>
 
-static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits,
-					      u8 cidr)
-{
-	swap_endian(dst, src, bits);
-	memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8);
-	if (cidr)
-		dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8);
-}
-
 static __init void print_node(struct allowedips_node *node, u8 bits)
 {
 	char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n";
-	char *fmt_declaration = KERN_DEBUG
-		"\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
+	char *fmt_declaration = KERN_DEBUG "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
+	u8 ip1[16], ip2[16], cidr1, cidr2;
 	char *style = "dotted";
-	u8 ip1[16], ip2[16];
 	u32 color = 0;
 
+	if (node == NULL)
+		return;
 	if (bits == 32) {
 		fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n";
-		fmt_declaration = KERN_DEBUG
-			"\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
+		fmt_declaration = KERN_DEBUG "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
 	} else if (bits == 128) {
 		fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n";
-		fmt_declaration = KERN_DEBUG
-			"\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
+		fmt_declaration = KERN_DEBUG "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
 	}
 	if (node->peer) {
 		hsiphash_key_t key = { { 0 } };
@@ -55,24 +45,20 @@ static __init void print_node(struct allowedips_node *node, u8 bits)
 			hsiphash_1u32(0xabad1dea, &key) % 200;
 		style = "bold";
 	}
-	swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr);
-	printk(fmt_declaration, ip1, node->cidr, style, color);
+	wg_allowedips_read_node(node, ip1, &cidr1);
+	printk(fmt_declaration, ip1, cidr1, style, color);
 	if (node->bit[0]) {
-		swap_endian_and_apply_cidr(ip2,
-				rcu_dereference_raw(node->bit[0])->bits, bits,
-				node->cidr);
-		printk(fmt_connection, ip1, node->cidr, ip2,
-		       rcu_dereference_raw(node->bit[0])->cidr);
-		print_node(rcu_dereference_raw(node->bit[0]), bits);
+		wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2);
+		printk(fmt_connection, ip1, cidr1, ip2, cidr2);
 	}
 	if (node->bit[1]) {
-		swap_endian_and_apply_cidr(ip2,
-				rcu_dereference_raw(node->bit[1])->bits,
-				bits, node->cidr);
-		printk(fmt_connection, ip1, node->cidr, ip2,
-		       rcu_dereference_raw(node->bit[1])->cidr);
-		print_node(rcu_dereference_raw(node->bit[1]), bits);
+		wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2);
+		printk(fmt_connection, ip1, cidr1, ip2, cidr2);
 	}
+	if (node->bit[0])
+		print_node(rcu_dereference_raw(node->bit[0]), bits);
+	if (node->bit[1])
+		print_node(rcu_dereference_raw(node->bit[1]), bits);
 }
 
 static __init void print_tree(struct allowedips_node __rcu *top, u8 bits)
@@ -121,8 +107,8 @@ static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr)
 {
 	union nf_inet_addr mask;
 
-	memset(&mask, 0x00, 128 / 8);
-	memset(&mask, 0xff, cidr / 8);
+	memset(&mask, 0, sizeof(mask));
+	memset(&mask.all, 0xff, cidr / 8);
 	if (cidr % 32)
 		mask.all[cidr / 32] = (__force u32)htonl(
 			(0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL);
@@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allowedips_node *node)
 }
 
 static __init inline bool
-horrible_match_v4(const struct horrible_allowedips_node *node,
-		  struct in_addr *ip)
+horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip)
 {
 	return (ip->s_addr & node->mask.ip) == node->ip.ip;
 }
 
 static __init inline bool
-horrible_match_v6(const struct horrible_allowedips_node *node,
-		  struct in6_addr *ip)
+horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip)
 {
-	return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) ==
-		       node->ip.ip6[0] &&
-	       (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) ==
-		       node->ip.ip6[1] &&
-	       (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) ==
-		       node->ip.ip6[2] &&
+	return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] &&
+	       (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] &&
+	       (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] &&
 	       (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3];
 }
 
 static __init void
-horrible_insert_ordered(struct horrible_allowedips *table,
-			struct horrible_allowedips_node *node)
+horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node)
 {
 	struct horrible_allowedips_node *other = NULL, *where = NULL;
 	u8 my_cidr = horrible_mask_to_cidr(node->mask);
 
 	hlist_for_each_entry(other, &table->head, table) {
-		if (!memcmp(&other->mask, &node->mask,
-			    sizeof(union nf_inet_addr)) &&
-		    !memcmp(&other->ip, &node->ip,
-			    sizeof(union nf_inet_addr)) &&
-		    other->ip_version == node->ip_version) {
+		if (other->ip_version == node->ip_version &&
+		    !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) &&
+		    !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) {
 			other->value = node->value;
 			kfree(node);
 			return;
 		}
+	}
+	hlist_for_each_entry(other, &table->head, table) {
 		where = other;
 		if (horrible_mask_to_cidr(other->mask) <= my_cidr)
 			break;
@@ -201,8 +181,7 @@ static __init int
 horrible_allowedips_insert_v4(struct horrible_allowedips *table,
 			      struct in_addr *ip, u8 cidr, void *value)
 {
-	struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
-							GFP_KERNEL);
+	struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
 
 	if (unlikely(!node))
 		return -ENOMEM;
@@ -219,8 +198,7 @@ static __init int
 horrible_allowedips_insert_v6(struct horrible_allowedips *table,
 			      struct in6_addr *ip, u8 cidr, void *value)
 {
-	struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
-							GFP_KERNEL);
+	struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
 
 	if (unlikely(!node))
 		return -ENOMEM;
@@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct horrible_allowedips *table,
 }
 
 static __init void *
-horrible_allowedips_lookup_v4(struct horrible_allowedips *table,
-			      struct in_addr *ip)
+horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip)
 {
 	struct horrible_allowedips_node *node;
-	void *ret = NULL;
 
 	hlist_for_each_entry(node, &table->head, table) {
-		if (node->ip_version != 4)
-			continue;
-		if (horrible_match_v4(node, ip)) {
-			ret = node->value;
-			break;
-		}
+		if (node->ip_version == 4 && horrible_match_v4(node, ip))
+			return node->value;
 	}
-	return ret;
+	return NULL;
 }
 
 static __init void *
-horrible_allowedips_lookup_v6(struct horrible_allowedips *table,
-			      struct in6_addr *ip)
+horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip)
 {
 	struct horrible_allowedips_node *node;
-	void *ret = NULL;
 
 	hlist_for_each_entry(node, &table->head, table) {
-		if (node->ip_version != 6)
+		if (node->ip_version == 6 && horrible_match_v6(node, ip))
+			return node->value;
+	}
+	return NULL;
+}
+
+
+static __init void
+horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value)
+{
+	struct horrible_allowedips_node *node;
+	struct hlist_node *h;
+
+	hlist_for_each_entry_safe(node, h, &table->head, table) {
+		if (node->value != value)
 			continue;
-		if (horrible_match_v6(node, ip)) {
-			ret = node->value;
-			break;
-		}
+		hlist_del(&node->table);
+		kfree(node);
 	}
-	return ret;
+
 }
 
 static __init bool randomized_test(void)
@@ -296,6 +278,7 @@ static __init bool randomized_test(void)
 			goto free;
 		}
 		kref_init(&peers[i]->refcount);
+		INIT_LIST_HEAD(&peers[i]->allowedips_list);
 	}
 
 	mutex_lock(&mutex);
@@ -333,7 +316,7 @@ static __init bool randomized_test(void)
 			if (wg_allowedips_insert_v4(&t,
 						    (struct in_addr *)mutated,
 						    cidr, peer, &mutex) < 0) {
-				pr_err("allowedips random malloc: FAIL\n");
+				pr_err("allowedips random self-test malloc: FAIL\n");
 				goto free_locked;
 			}
 			if (horrible_allowedips_insert_v4(&h,
@@ -396,23 +379,33 @@ static __init bool randomized_test(void)
 		print_tree(t.root6, 128);
 	}
 
-	for (i = 0; i < NUM_QUERIES; ++i) {
-		prandom_bytes(ip, 4);
-		if (lookup(t.root4, 32, ip) !=
-		    horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
-			pr_err("allowedips random self-test: FAIL\n");
-			goto free;
+	for (j = 0;; ++j) {
+		for (i = 0; i < NUM_QUERIES; ++i) {
+			prandom_bytes(ip, 4);
+			if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
+				horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip);
+				pr_err("allowedips random v4 self-test: FAIL\n");
+				goto free;
+			}
+			prandom_bytes(ip, 16);
+			if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
+				pr_err("allowedips random v6 self-test: FAIL\n");
+				goto free;
+			}
 		}
+		if (j >= NUM_PEERS)
+			break;
+		mutex_lock(&mutex);
+		wg_allowedips_remove_by_peer(&t, peers[j], &mutex);
+		mutex_unlock(&mutex);
+		horrible_allowedips_remove_by_value(&h, peers[j]);
 	}
 
-	for (i = 0; i < NUM_QUERIES; ++i) {
-		prandom_bytes(ip, 16);
-		if (lookup(t.root6, 128, ip) !=
-		    horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
-			pr_err("allowedips random self-test: FAIL\n");
-			goto free;
-		}
+	if (t.root4 || t.root6) {
+		pr_err("allowedips random self-test removal: FAIL\n");
+		goto free;
 	}
+
 	ret = true;
 
 free:
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index d9ad850daa79..8c496b747108 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -430,7 +430,7 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
 	if (new4)
 		wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
 	mutex_unlock(&wg->socket_update_lock);
-	synchronize_rcu();
+	synchronize_net();
 	sock_free(old4);
 	sock_free(old6);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 977acab0360a..03fe62837557 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -514,10 +514,36 @@ EXPORT_SYMBOL_GPL(mt76_free_device);
 static void mt76_rx_release_amsdu(struct mt76_phy *phy, enum mt76_rxq_id q)
 {
 	struct sk_buff *skb = phy->rx_amsdu[q].head;
+	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
 	struct mt76_dev *dev = phy->dev;
 
 	phy->rx_amsdu[q].head = NULL;
 	phy->rx_amsdu[q].tail = NULL;
+
+	/*
+	 * Validate if the amsdu has a proper first subframe.
+	 * A single MSDU can be parsed as A-MSDU when the unauthenticated A-MSDU
+	 * flag of the QoS header gets flipped. In such cases, the first
+	 * subframe has a LLC/SNAP header in the location of the destination
+	 * address.
+	 */
+	if (skb_shinfo(skb)->frag_list) {
+		int offset = 0;
+
+		if (!(status->flag & RX_FLAG_8023)) {
+			offset = ieee80211_get_hdrlen_from_skb(skb);
+
+			if ((status->flag &
+			     (RX_FLAG_DECRYPTED | RX_FLAG_IV_STRIPPED)) ==
+			    RX_FLAG_DECRYPTED)
+				offset += 8;
+		}
+
+		if (ether_addr_equal(skb->data + offset, rfc1042_header)) {
+			dev_kfree_skb(skb);
+			return;
+		}
+	}
 	__skb_queue_tail(&dev->rx_skb[q], skb);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index 86341d1f82f3..d20f05a7717d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -510,7 +510,6 @@ void mt7615_init_device(struct mt7615_dev *dev)
 	mutex_init(&dev->pm.mutex);
 	init_waitqueue_head(&dev->pm.wait);
 	spin_lock_init(&dev->pm.txq_lock);
-	set_bit(MT76_STATE_PM, &dev->mphy.state);
 	INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7615_mac_work);
 	INIT_DELAYED_WORK(&dev->phy.scan_work, mt7615_scan_work);
 	INIT_DELAYED_WORK(&dev->coredump.work, mt7615_coredump_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index f81a17d56008..e2dcfee6be81 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -1912,8 +1912,9 @@ void mt7615_pm_wake_work(struct work_struct *work)
 			napi_schedule(&dev->mt76.napi[i]);
 		mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
 		mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_WM], false);
-		ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
-					     MT7615_WATCHDOG_TIME);
+		if (test_bit(MT76_STATE_RUNNING, &mphy->state))
+			ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
+						     MT7615_WATCHDOG_TIME);
 	}
 
 	ieee80211_wake_queues(mphy->hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
index 17fe4187d1de..d1be78b0711c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
@@ -51,16 +51,13 @@ mt7663s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	return ret;
 }
 
-static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
+static int __mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	u32 status;
 	int ret;
 
-	if (!test_and_clear_bit(MT76_STATE_PM, &mphy->state))
-		goto out;
-
 	sdio_claim_host(func);
 
 	sdio_writel(func, WHLPCR_FW_OWN_REQ_CLR, MCR_WHLPCR, NULL);
@@ -76,13 +73,21 @@ static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
 	}
 
 	sdio_release_host(func);
-
-out:
 	dev->pm.last_activity = jiffies;
 
 	return 0;
 }
 
+static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+
+	if (test_and_clear_bit(MT76_STATE_PM, &mphy->state))
+		return __mt7663s_mcu_drv_pmctrl(dev);
+
+	return 0;
+}
+
 static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
@@ -123,7 +128,7 @@ int mt7663s_mcu_init(struct mt7615_dev *dev)
 	struct mt7615_mcu_ops *mcu_ops;
 	int ret;
 
-	ret = mt7663s_mcu_drv_pmctrl(dev);
+	ret = __mt7663s_mcu_drv_pmctrl(dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
index c55698f9c49a..028ff432d811 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
@@ -55,10 +55,7 @@ int mt7663u_mcu_init(struct mt7615_dev *dev)
 
 	dev->mt76.mcu_ops = &mt7663u_mcu_ops,
 
-	/* usb does not support runtime-pm */
-	clear_bit(MT76_STATE_PM, &dev->mphy.state);
 	mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
-
 	if (test_and_clear_bit(MT76_STATE_POWER_OFF, &dev->mphy.state)) {
 		mt7615_mcu_restart(&dev->mt76);
 		if (!mt76_poll_msec(dev, MT_CONN_ON_MISC,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index fe0ab5e5ff81..619561606f96 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -721,6 +721,10 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb,
 	phy->phy_type = mt76_connac_get_phy_mode_v2(mphy, vif, band, sta);
 	phy->basic_rate = cpu_to_le16((u16)vif->bss_conf.basic_rates);
 	phy->rcpi = rcpi;
+	phy->ampdu = FIELD_PREP(IEEE80211_HT_AMPDU_PARM_FACTOR,
+				sta->ht_cap.ampdu_factor) |
+		     FIELD_PREP(IEEE80211_HT_AMPDU_PARM_DENSITY,
+				sta->ht_cap.ampdu_density);
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra_info));
 	ra_info = (struct sta_rec_ra_info *)tlv;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 5847f943e8da..b795e7245c07 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.reconfig_complete = mt76x02_reconfig_complete,
 };
 
-static int mt76x0e_register_device(struct mt76x02_dev *dev)
+static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume)
 {
 	int err;
 
@@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
 	if (err < 0)
 		return err;
 
-	err = mt76x02_dma_init(dev);
-	if (err < 0)
-		return err;
+	if (!resume) {
+		err = mt76x02_dma_init(dev);
+		if (err < 0)
+			return err;
+	}
 
 	err = mt76x0_init_hardware(dev);
 	if (err < 0)
@@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
 	mt76_clear(dev, 0x110, BIT(9));
 	mt76_set(dev, MT_MAX_LEN_CFG, BIT(13));
 
+	return 0;
+}
+
+static int mt76x0e_register_device(struct mt76x02_dev *dev)
+{
+	int err;
+
+	err = mt76x0e_init_hardware(dev, false);
+	if (err < 0)
+		return err;
+
 	err = mt76x0_register_device(dev);
 	if (err < 0)
 		return err;
@@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		return ret;
 
+	mt76_pci_disable_aspm(pdev);
+
 	mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops,
 				 &drv_ops);
 	if (!mdev)
@@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev)
 	mt76_free_device(mdev);
 }
 
+#ifdef CONFIG_PM
+static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mt76_dev *mdev = pci_get_drvdata(pdev);
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	int i;
+
+	mt76_worker_disable(&mdev->tx_worker);
+	for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++)
+		mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true);
+	for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++)
+		mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true);
+	napi_disable(&mdev->tx_napi);
+
+	mt76_for_each_q_rx(mdev, i)
+		napi_disable(&mdev->napi[i]);
+
+	mt76x02_dma_disable(dev);
+	mt76x02_mcu_cleanup(dev);
+	mt76x0_chip_onoff(dev, false, false);
+
+	pci_enable_wake(pdev, pci_choose_state(pdev, state), true);
+	pci_save_state(pdev);
+
+	return pci_set_power_state(pdev, pci_choose_state(pdev, state));
+}
+
+static int mt76x0e_resume(struct pci_dev *pdev)
+{
+	struct mt76_dev *mdev = pci_get_drvdata(pdev);
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	int err, i;
+
+	err = pci_set_power_state(pdev, PCI_D0);
+	if (err)
+		return err;
+
+	pci_restore_state(pdev);
+
+	mt76_worker_enable(&mdev->tx_worker);
+
+	mt76_for_each_q_rx(mdev, i) {
+		mt76_queue_rx_reset(dev, i);
+		napi_enable(&mdev->napi[i]);
+		napi_schedule(&mdev->napi[i]);
+	}
+
+	napi_enable(&mdev->tx_napi);
+	napi_schedule(&mdev->tx_napi);
+
+	return mt76x0e_init_hardware(dev, true);
+}
+#endif /* CONFIG_PM */
+
 static const struct pci_device_id mt76x0e_device_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7610) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7630) },
@@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = {
 	.id_table	= mt76x0e_device_table,
 	.probe		= mt76x0e_probe,
 	.remove		= mt76x0e_remove,
+#ifdef CONFIG_PM
+	.suspend	= mt76x0e_suspend,
+	.resume		= mt76x0e_resume,
+#endif /* CONFIG_PM */
 };
 
 module_pci_driver(mt76x0e_driver);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index fe28bf4050c4..1763ea0614ce 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -76,8 +76,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 	struct wiphy *wiphy = hw->wiphy;
 
 	hw->queues = 4;
-	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
-	hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+	hw->max_rx_aggregation_subframes = 64;
+	hw->max_tx_aggregation_subframes = 128;
 
 	hw->radiotap_timestamp.units_pos =
 		IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 214bd1859792..decf2d5f0ce3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -1404,8 +1404,9 @@ void mt7921_pm_wake_work(struct work_struct *work)
 			napi_schedule(&dev->mt76.napi[i]);
 		mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
 		mt7921_tx_cleanup(dev);
-		ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
-					     MT7921_WATCHDOG_TIME);
+		if (test_bit(MT76_STATE_RUNNING, &mphy->state))
+			ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
+						     MT7921_WATCHDOG_TIME);
 	}
 
 	ieee80211_wake_queues(mphy->hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index f4c27aa41048..97a0ef331ac3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -74,8 +74,7 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band,
 				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G;
 		else if (band == NL80211_BAND_5GHZ)
 			he_cap_elem->phy_cap_info[0] =
-				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
-				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G;
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G;
 
 		he_cap_elem->phy_cap_info[1] =
 			IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 5f3d56d570a5..67dc4b4cc094 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -402,20 +402,22 @@ static void
 mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
 			  u16 wlan_idx)
 {
-	struct mt7921_mcu_wlan_info_event *wtbl_info =
-		(struct mt7921_mcu_wlan_info_event *)(skb->data);
-	struct rate_info rate = {};
-	u8 curr_idx = wtbl_info->rate_info.rate_idx;
-	u16 curr = le16_to_cpu(wtbl_info->rate_info.rate[curr_idx]);
-	struct mt7921_mcu_peer_cap peer = wtbl_info->peer_cap;
+	struct mt7921_mcu_wlan_info_event *wtbl_info;
 	struct mt76_phy *mphy = &dev->mphy;
 	struct mt7921_sta_stats *stats;
+	struct rate_info rate = {};
 	struct mt7921_sta *msta;
 	struct mt76_wcid *wcid;
+	u8 idx;
 
 	if (wlan_idx >= MT76_N_WCIDS)
 		return;
 
+	wtbl_info = (struct mt7921_mcu_wlan_info_event *)skb->data;
+	idx = wtbl_info->rate_info.rate_idx;
+	if (idx >= ARRAY_SIZE(wtbl_info->rate_info.rate))
+		return;
+
 	rcu_read_lock();
 
 	wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
@@ -426,7 +428,8 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
 	stats = &msta->stats;
 
 	/* current rate */
-	mt7921_mcu_tx_rate_parse(mphy, &peer, &rate, curr);
+	mt7921_mcu_tx_rate_parse(mphy, &wtbl_info->peer_cap, &rate,
+				 le16_to_cpu(wtbl_info->rate_info.rate[idx]));
 	stats->tx_rate = rate;
 out:
 	rcu_read_unlock();
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 193b723fe3bd..c58996c1e230 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -684,6 +684,7 @@ static void xenvif_disconnect_queue(struct xenvif_queue *queue)
 {
 	if (queue->task) {
 		kthread_stop(queue->task);
+		put_task_struct(queue->task);
 		queue->task = NULL;
 	}
 
@@ -745,6 +746,11 @@ int xenvif_connect_data(struct xenvif_queue *queue,
 	if (IS_ERR(task))
 		goto kthread_err;
 	queue->task = task;
+	/*
+	 * Take a reference to the task in order to prevent it from being freed
+	 * if the thread function returns before kthread_stop is called.
+	 */
+	get_task_struct(task);
 
 	task = kthread_run(xenvif_dealloc_kthread, queue,
 			   "%s-dealloc", queue->name);