Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 160 insertions, 264 deletions

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index 59fdd0fc2ad4..f81a17d56008 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -234,11 +234,13 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 	u32 rxd0 = le32_to_cpu(rxd[0]);
 	u32 rxd1 = le32_to_cpu(rxd[1]);
 	u32 rxd2 = le32_to_cpu(rxd[2]);
-	__le32 rxd12 = rxd[12];
-	bool unicast, remove_pad, insert_ccmp_hdr = false;
+	u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
+	bool unicast, hdr_trans, remove_pad, insert_ccmp_hdr = false;
 	int phy_idx;
 	int i, idx;
-	u8 chfreq;
+	u8 chfreq, amsdu_info, qos_ctl = 0;
+	u16 seq_ctrl = 0;
+	__le16 fc = 0;
 
 	memset(status, 0, sizeof(*status));
 
@@ -254,8 +256,12 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 	else
 		phy_idx = -1;
 
+	if (rxd2 & MT_RXD2_NORMAL_AMSDU_ERR)
+		return -EINVAL;
+
 	unicast = (rxd1 & MT_RXD1_NORMAL_ADDR_TYPE) == MT_RXD1_NORMAL_U2M;
 	idx = FIELD_GET(MT_RXD2_NORMAL_WLAN_IDX, rxd2);
+	hdr_trans = rxd1 & MT_RXD1_NORMAL_HDR_TRANS;
 	status->wcid = mt7615_rx_get_wcid(dev, idx, unicast);
 
 	if (status->wcid) {
@@ -268,6 +274,9 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 		spin_unlock_bh(&dev->sta_poll_lock);
 	}
 
+	if ((rxd0 & csum_mask) == csum_mask)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
 	if (rxd2 & MT_RXD2_NORMAL_FCS_ERR)
 		status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
@@ -288,6 +297,13 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 
 	rxd += 4;
 	if (rxd0 & MT_RXD0_NORMAL_GROUP_4) {
+		u32 v0 = le32_to_cpu(rxd[0]);
+		u32 v2 = le32_to_cpu(rxd[2]);
+
+		fc = cpu_to_le16(FIELD_GET(MT_RXD4_FRAME_CONTROL, v0));
+		qos_ctl = FIELD_GET(MT_RXD6_QOS_CTL, v2);
+		seq_ctrl = FIELD_GET(MT_RXD6_SEQ_CTRL, v2);
+
 		rxd += 4;
 		if ((u8 *)rxd - skb->data >= skb->len)
 			return -EINVAL;
@@ -312,6 +328,23 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 	}
 
 	if (rxd0 & MT_RXD0_NORMAL_GROUP_2) {
+		status->timestamp = le32_to_cpu(rxd[0]);
+		status->flag |= RX_FLAG_MACTIME_START;
+
+		if (!(rxd2 & (MT_RXD2_NORMAL_NON_AMPDU_SUB |
+			      MT_RXD2_NORMAL_NON_AMPDU))) {
+			status->flag |= RX_FLAG_AMPDU_DETAILS;
+
+			/* all subframes of an A-MPDU have the same timestamp */
+			if (phy->rx_ampdu_ts != status->timestamp) {
+				if (!++phy->ampdu_ref)
+					phy->ampdu_ref++;
+			}
+			phy->rx_ampdu_ts = status->timestamp;
+
+			status->ampdu_ref = phy->ampdu_ref;
+		}
+
 		rxd += 2;
 		if ((u8 *)rxd - skb->data >= skb->len)
 			return -EINVAL;
@@ -355,20 +388,6 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 	if (!sband->channels)
 		return -EINVAL;
 
-	if (!(rxd2 & (MT_RXD2_NORMAL_NON_AMPDU_SUB |
-		      MT_RXD2_NORMAL_NON_AMPDU))) {
-		status->flag |= RX_FLAG_AMPDU_DETAILS;
-
-		/* all subframes of an A-MPDU have the same timestamp */
-		if (phy->rx_ampdu_ts != rxd12) {
-			if (!++phy->ampdu_ref)
-				phy->ampdu_ref++;
-		}
-		phy->rx_ampdu_ts = rxd12;
-
-		status->ampdu_ref = phy->ampdu_ref;
-	}
-
 	if (rxd0 & MT_RXD0_NORMAL_GROUP_3) {
 		u32 rxdg0 = le32_to_cpu(rxd[0]);
 		u32 rxdg1 = le32_to_cpu(rxd[1]);
@@ -446,20 +465,42 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 
 	skb_pull(skb, (u8 *)rxd - skb->data + 2 * remove_pad);
 
-	if (insert_ccmp_hdr) {
+	amsdu_info = FIELD_GET(MT_RXD1_NORMAL_PAYLOAD_FORMAT, rxd1);
+	status->amsdu = !!amsdu_info;
+	if (status->amsdu) {
+		status->first_amsdu = amsdu_info == MT_RXD1_FIRST_AMSDU_FRAME;
+		status->last_amsdu = amsdu_info == MT_RXD1_LAST_AMSDU_FRAME;
+		if (!hdr_trans) {
+			memmove(skb->data + 2, skb->data,
+				ieee80211_get_hdrlen_from_skb(skb));
+			skb_pull(skb, 2);
+		}
+	}
+
+	if (insert_ccmp_hdr && !hdr_trans) {
 		u8 key_id = FIELD_GET(MT_RXD1_NORMAL_KEY_ID, rxd1);
 
 		mt76_insert_ccmp_hdr(skb, key_id);
 	}
 
-	hdr = (struct ieee80211_hdr *)skb->data;
-	if (!status->wcid || !ieee80211_is_data_qos(hdr->frame_control))
+	if (!hdr_trans) {
+		hdr = (struct ieee80211_hdr *)skb->data;
+		fc = hdr->frame_control;
+		if (ieee80211_is_data_qos(fc)) {
+			seq_ctrl = le16_to_cpu(hdr->seq_ctrl);
+			qos_ctl = *ieee80211_get_qos_ctl(hdr);
+		}
+	} else {
+		status->flag |= RX_FLAG_8023;
+	}
+
+	if (!status->wcid || !ieee80211_is_data_qos(fc))
 		return 0;
 
 	status->aggr = unicast &&
-		       !ieee80211_is_qos_nullfunc(hdr->frame_control);
-	status->tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK;
-	status->seqno = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
+		       !ieee80211_is_qos_nullfunc(fc);
+	status->qos_ctl = qos_ctl;
+	status->seqno = IEEE80211_SEQ_TO_SN(seq_ctrl);
 
 	return 0;
 }
@@ -690,7 +731,7 @@ mt7615_txp_skb_unmap_fw(struct mt76_dev *dev, struct mt7615_fw_txp *txp)
 {
 	int i;
 
-	for (i = 1; i < txp->nbuf; i++)
+	for (i = 0; i < txp->nbuf; i++)
 		dma_unmap_single(dev->dev, le32_to_cpu(txp->buf[i]),
 				 le16_to_cpu(txp->len[i]), DMA_TO_DEVICE);
 }
@@ -966,6 +1007,7 @@ void mt7615_mac_set_rates(struct mt7615_phy *phy, struct mt7615_sta *sta,
 	struct mt7615_dev *dev = phy->dev;
 	struct mt7615_rate_desc rd;
 	u32 w5, w27, addr;
+	u16 idx = sta->vif->mt76.omac_idx;
 
 	if (!mt76_is_mmio(&dev->mt76)) {
 		mt7615_mac_queue_rate_update(phy, sta, probe_rate, rates);
@@ -1017,7 +1059,10 @@ void mt7615_mac_set_rates(struct mt7615_phy *phy, struct mt7615_sta *sta,
 
 	mt76_wr(dev, addr + 27 * 4, w27);
 
-	mt76_set(dev, MT_LPON_T0CR, MT_LPON_T0CR_MODE); /* TSF read */
+	idx = idx > HW_BSSID_MAX ? HW_BSSID_0 : idx;
+	addr = idx > 1 ? MT_LPON_TCR2(idx): MT_LPON_TCR0(idx);
+
+	mt76_set(dev, addr, MT_LPON_TCR_MODE); /* TSF read */
 	sta->rate_set_tsf = mt76_rr(dev, MT_LPON_UTTR0) & ~BIT(0);
 	sta->rate_set_tsf |= rd.rateset;
 
@@ -1033,7 +1078,7 @@ EXPORT_SYMBOL_GPL(mt7615_mac_set_rates);
 static int
 mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key,
-			   enum mt7615_cipher_type cipher,
+			   enum mt7615_cipher_type cipher, u16 cipher_mask,
 			   enum set_key_cmd cmd)
 {
 	u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx) + 30 * 4;
@@ -1050,22 +1095,22 @@ mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 			memcpy(data + 16, key->key + 24, 8);
 			memcpy(data + 24, key->key + 16, 8);
 		} else {
-			if (cipher != MT_CIPHER_BIP_CMAC_128 && wcid->cipher)
-				memmove(data + 16, data, 16);
-			if (cipher != MT_CIPHER_BIP_CMAC_128 || !wcid->cipher)
+			if (cipher_mask == BIT(cipher))
 				memcpy(data, key->key, key->keylen);
-			else if (cipher == MT_CIPHER_BIP_CMAC_128)
+			else if (cipher != MT_CIPHER_BIP_CMAC_128)
+				memcpy(data, key->key, 16);
+			if (cipher == MT_CIPHER_BIP_CMAC_128)
 				memcpy(data + 16, key->key, 16);
 		}
 	} else {
-		if (wcid->cipher & ~BIT(cipher)) {
-			if (cipher != MT_CIPHER_BIP_CMAC_128)
-				memmove(data, data + 16, 16);
+		if (cipher == MT_CIPHER_BIP_CMAC_128)
 			memset(data + 16, 0, 16);
-		} else {
+		else if (cipher_mask)
+			memset(data, 0, 16);
+		if (!cipher_mask)
 			memset(data, 0, sizeof(data));
-		}
 	}
+
 	mt76_wr_copy(dev, addr, data, sizeof(data));
 
 	return 0;
@@ -1073,7 +1118,7 @@ mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 
 static int
 mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid,
-			  enum mt7615_cipher_type cipher,
+			  enum mt7615_cipher_type cipher, u16 cipher_mask,
 			  int keyidx, enum set_key_cmd cmd)
 {
 	u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx), w0, w1;
@@ -1083,20 +1128,23 @@ mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 
 	w0 = mt76_rr(dev, addr);
 	w1 = mt76_rr(dev, addr + 4);
-	if (cmd == SET_KEY) {
-		w0 |= MT_WTBL_W0_RX_KEY_VALID |
-		      FIELD_PREP(MT_WTBL_W0_RX_IK_VALID,
-				 cipher == MT_CIPHER_BIP_CMAC_128);
-		if (cipher != MT_CIPHER_BIP_CMAC_128 ||
-		    !wcid->cipher)
-			w0 |= FIELD_PREP(MT_WTBL_W0_KEY_IDX, keyidx);
-	}  else {
-		if (!(wcid->cipher & ~BIT(cipher)))
-			w0 &= ~(MT_WTBL_W0_RX_KEY_VALID |
-				MT_WTBL_W0_KEY_IDX);
-		if (cipher == MT_CIPHER_BIP_CMAC_128)
-			w0 &= ~MT_WTBL_W0_RX_IK_VALID;
+
+	if (cipher_mask)
+		w0 |= MT_WTBL_W0_RX_KEY_VALID;
+	else
+		w0 &= ~(MT_WTBL_W0_RX_KEY_VALID | MT_WTBL_W0_KEY_IDX);
+	if (cipher_mask & BIT(MT_CIPHER_BIP_CMAC_128))
+		w0 |= MT_WTBL_W0_RX_IK_VALID;
+	else
+		w0 &= ~MT_WTBL_W0_RX_IK_VALID;
+
+	if (cmd == SET_KEY &&
+	    (cipher != MT_CIPHER_BIP_CMAC_128 ||
+	     cipher_mask == BIT(cipher))) {
+		w0 &= ~MT_WTBL_W0_KEY_IDX;
+		w0 |= FIELD_PREP(MT_WTBL_W0_KEY_IDX, keyidx);
 	}
+
 	mt76_wr(dev, MT_WTBL_RICR0, w0);
 	mt76_wr(dev, MT_WTBL_RICR1, w1);
 
@@ -1109,24 +1157,25 @@ mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 
 static void
 mt7615_mac_wtbl_update_cipher(struct mt7615_dev *dev, struct mt76_wcid *wcid,
-			      enum mt7615_cipher_type cipher,
+			      enum mt7615_cipher_type cipher, u16 cipher_mask,
 			      enum set_key_cmd cmd)
 {
 	u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx);
 
-	if (cmd == SET_KEY) {
-		if (cipher != MT_CIPHER_BIP_CMAC_128 || !wcid->cipher)
-			mt76_rmw(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE,
-				 FIELD_PREP(MT_WTBL_W2_KEY_TYPE, cipher));
-	} else {
-		if (cipher != MT_CIPHER_BIP_CMAC_128 &&
-		    wcid->cipher & BIT(MT_CIPHER_BIP_CMAC_128))
-			mt76_rmw(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE,
-				 FIELD_PREP(MT_WTBL_W2_KEY_TYPE,
-					    MT_CIPHER_BIP_CMAC_128));
-		else if (!(wcid->cipher & ~BIT(cipher)))
-			mt76_clear(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE);
+	if (!cipher_mask) {
+		mt76_clear(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE);
+		return;
 	}
+
+	if (cmd != SET_KEY)
+		return;
+
+	if (cipher == MT_CIPHER_BIP_CMAC_128 &&
+	    cipher_mask & ~BIT(MT_CIPHER_BIP_CMAC_128))
+		return;
+
+	mt76_rmw(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE,
+		 FIELD_PREP(MT_WTBL_W2_KEY_TYPE, cipher));
 }
 
 int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev,
@@ -1135,25 +1184,30 @@ int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev,
 			      enum set_key_cmd cmd)
 {
 	enum mt7615_cipher_type cipher;
+	u16 cipher_mask = wcid->cipher;
 	int err;
 
 	cipher = mt7615_mac_get_cipher(key->cipher);
 	if (cipher == MT_CIPHER_NONE)
 		return -EOPNOTSUPP;
 
-	mt7615_mac_wtbl_update_cipher(dev, wcid, cipher, cmd);
-	err = mt7615_mac_wtbl_update_key(dev, wcid, key, cipher, cmd);
+	if (cmd == SET_KEY)
+		cipher_mask |= BIT(cipher);
+	else
+		cipher_mask &= ~BIT(cipher);
+
+	mt7615_mac_wtbl_update_cipher(dev, wcid, cipher, cipher_mask, cmd);
+	err = mt7615_mac_wtbl_update_key(dev, wcid, key, cipher, cipher_mask,
+					 cmd);
 	if (err < 0)
 		return err;
 
-	err = mt7615_mac_wtbl_update_pk(dev, wcid, cipher, key->keyidx, cmd);
+	err = mt7615_mac_wtbl_update_pk(dev, wcid, cipher, cipher_mask,
+					key->keyidx, cmd);
 	if (err < 0)
 		return err;
 
-	if (cmd == SET_KEY)
-		wcid->cipher |= BIT(cipher);
-	else
-		wcid->cipher &= ~BIT(cipher);
+	wcid->cipher = cipher_mask;
 
 	return 0;
 }
@@ -1411,11 +1465,7 @@ mt7615_mac_tx_free_token(struct mt7615_dev *dev, u16 token)
 	u8 wcid;
 
 	trace_mac_tx_free(dev, token);
-
-	spin_lock_bh(&dev->token_lock);
-	txwi = idr_remove(&dev->token, token);
-	spin_unlock_bh(&dev->token_lock);
-
+	txwi = mt76_token_put(mdev, token);
 	if (!txwi)
 		return;
 
@@ -1460,14 +1510,10 @@ static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb)
 
 	dev_kfree_skb(skb);
 
-	if (test_bit(MT76_STATE_PM, &dev->phy.mt76->state))
-		return;
-
 	rcu_read_lock();
 	mt7615_mac_sta_poll(dev);
 	rcu_read_unlock();
 
-	mt76_connac_power_save_sched(&dev->mphy, &dev->pm);
 	mt76_worker_schedule(&dev->mt76.tx_worker);
 }
 
@@ -1821,10 +1867,8 @@ mt7615_mac_update_mib_stats(struct mt7615_phy *phy)
 	int i, aggr;
 	u32 val, val2;
 
-	memset(mib, 0, sizeof(*mib));
-
-	mib->fcs_err_cnt = mt76_get_field(dev, MT_MIB_SDR3(ext_phy),
-					  MT_MIB_SDR3_FCS_ERR_MASK);
+	mib->fcs_err_cnt += mt76_get_field(dev, MT_MIB_SDR3(ext_phy),
+					   MT_MIB_SDR3_FCS_ERR_MASK);
 
 	val = mt76_get_field(dev, MT_MIB_SDR14(ext_phy),
 			     MT_MIB_AMPDU_MPDU_COUNT);
@@ -1837,24 +1881,16 @@ mt7615_mac_update_mib_stats(struct mt7615_phy *phy)
 	aggr = ext_phy ? ARRAY_SIZE(dev->mt76.aggr_stats) / 2 : 0;
 	for (i = 0; i < 4; i++) {
 		val = mt76_rr(dev, MT_MIB_MB_SDR1(ext_phy, i));
-
-		val2 = FIELD_GET(MT_MIB_ACK_FAIL_COUNT_MASK, val);
-		if (val2 > mib->ack_fail_cnt)
-			mib->ack_fail_cnt = val2;
-
-		val2 = FIELD_GET(MT_MIB_BA_MISS_COUNT_MASK, val);
-		if (val2 > mib->ba_miss_cnt)
-			mib->ba_miss_cnt = val2;
+		mib->ba_miss_cnt += FIELD_GET(MT_MIB_BA_MISS_COUNT_MASK, val);
+		mib->ack_fail_cnt += FIELD_GET(MT_MIB_ACK_FAIL_COUNT_MASK,
+					       val);
 
 		val = mt76_rr(dev, MT_MIB_MB_SDR0(ext_phy, i));
-		val2 = FIELD_GET(MT_MIB_RTS_RETRIES_COUNT_MASK, val);
-		if (val2 > mib->rts_retries_cnt) {
-			mib->rts_cnt = FIELD_GET(MT_MIB_RTS_COUNT_MASK, val);
-			mib->rts_retries_cnt = val2;
-		}
+		mib->rts_cnt += FIELD_GET(MT_MIB_RTS_COUNT_MASK, val);
+		mib->rts_retries_cnt += FIELD_GET(MT_MIB_RTS_RETRIES_COUNT_MASK,
+						  val);
 
 		val = mt76_rr(dev, MT_TX_AGG_CNT(ext_phy, i));
-
 		dev->mt76.aggr_stats[aggr++] += val & 0xffff;
 		dev->mt76.aggr_stats[aggr++] += val >> 16;
 	}
@@ -1869,13 +1905,19 @@ void mt7615_pm_wake_work(struct work_struct *work)
 						pm.wake_work);
 	mphy = dev->phy.mt76;
 
-	if (!mt7615_mcu_set_drv_ctrl(dev))
+	if (!mt7615_mcu_set_drv_ctrl(dev)) {
+		int i;
+
+		mt76_for_each_q_rx(&dev->mt76, i)
+			napi_schedule(&dev->mt76.napi[i]);
 		mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
-	else
-		dev_err(mphy->dev->dev, "failed to wake device\n");
+		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);
+	}
 
 	ieee80211_wake_queues(mphy->hw);
-	complete_all(&dev->pm.wake_cmpl);
+	wake_up(&dev->pm.wait);
 }
 
 void mt7615_pm_power_save_work(struct work_struct *work)
@@ -1887,6 +1929,10 @@ void mt7615_pm_power_save_work(struct work_struct *work)
 						pm.ps_work.work);
 
 	delta = dev->pm.idle_timeout;
+	if (test_bit(MT76_HW_SCANNING, &dev->mphy.state) ||
+	    test_bit(MT76_HW_SCHED_SCANNING, &dev->mphy.state))
+		goto out;
+
 	if (time_is_after_jiffies(dev->pm.last_activity + delta)) {
 		delta = dev->pm.last_activity + delta - jiffies;
 		goto out;
@@ -1924,179 +1970,27 @@ void mt7615_mac_work(struct work_struct *work)
 				     MT7615_WATCHDOG_TIME);
 }
 
-static bool
-mt7615_wait_reset_state(struct mt7615_dev *dev, u32 state)
-{
-	bool ret;
-
-	ret = wait_event_timeout(dev->reset_wait,
-				 (READ_ONCE(dev->reset_state) & state),
-				 MT7615_RESET_TIMEOUT);
-	WARN(!ret, "Timeout waiting for MCU reset state %x\n", state);
-	return ret;
-}
-
-static void
-mt7615_update_vif_beacon(void *priv, u8 *mac, struct ieee80211_vif *vif)
-{
-	struct ieee80211_hw *hw = priv;
-	struct mt7615_dev *dev = mt7615_hw_dev(hw);
-
-	switch (vif->type) {
-	case NL80211_IFTYPE_MESH_POINT:
-	case NL80211_IFTYPE_ADHOC:
-	case NL80211_IFTYPE_AP:
-		mt7615_mcu_add_beacon(dev, hw, vif,
-				      vif->bss_conf.enable_beacon);
-		break;
-	default:
-		break;
-	}
-}
-
-static void
-mt7615_update_beacons(struct mt7615_dev *dev)
-{
-	ieee80211_iterate_active_interfaces(dev->mt76.hw,
-		IEEE80211_IFACE_ITER_RESUME_ALL,
-		mt7615_update_vif_beacon, dev->mt76.hw);
-
-	if (!dev->mt76.phy2)
-		return;
-
-	ieee80211_iterate_active_interfaces(dev->mt76.phy2->hw,
-		IEEE80211_IFACE_ITER_RESUME_ALL,
-		mt7615_update_vif_beacon, dev->mt76.phy2->hw);
-}
-
-void mt7615_dma_reset(struct mt7615_dev *dev)
-{
-	int i;
-
-	mt76_clear(dev, MT_WPDMA_GLO_CFG,
-		   MT_WPDMA_GLO_CFG_RX_DMA_EN | MT_WPDMA_GLO_CFG_TX_DMA_EN |
-		   MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE);
-	usleep_range(1000, 2000);
-
-	mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_WM], true);
-	for (i = 0; i < __MT_TXQ_MAX; i++)
-		mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[i], true);
-
-	mt76_for_each_q_rx(&dev->mt76, i) {
-		mt76_queue_rx_reset(dev, i);
-	}
-
-	mt76_set(dev, MT_WPDMA_GLO_CFG,
-		 MT_WPDMA_GLO_CFG_RX_DMA_EN | MT_WPDMA_GLO_CFG_TX_DMA_EN |
-		 MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE);
-}
-EXPORT_SYMBOL_GPL(mt7615_dma_reset);
-
 void mt7615_tx_token_put(struct mt7615_dev *dev)
 {
 	struct mt76_txwi_cache *txwi;
 	int id;
 
-	spin_lock_bh(&dev->token_lock);
-	idr_for_each_entry(&dev->token, txwi, id) {
+	spin_lock_bh(&dev->mt76.token_lock);
+	idr_for_each_entry(&dev->mt76.token, txwi, id) {
 		mt7615_txp_skb_unmap(&dev->mt76, txwi);
-		if (txwi->skb)
-			dev_kfree_skb_any(txwi->skb);
+		if (txwi->skb) {
+			struct ieee80211_hw *hw;
+
+			hw = mt76_tx_status_get_hw(&dev->mt76, txwi->skb);
+			ieee80211_free_txskb(hw, txwi->skb);
+		}
 		mt76_put_txwi(&dev->mt76, txwi);
 	}
-	spin_unlock_bh(&dev->token_lock);
-	idr_destroy(&dev->token);
+	spin_unlock_bh(&dev->mt76.token_lock);
+	idr_destroy(&dev->mt76.token);
 }
 EXPORT_SYMBOL_GPL(mt7615_tx_token_put);
 
-void mt7615_mac_reset_work(struct work_struct *work)
-{
-	struct mt7615_phy *phy2;
-	struct mt76_phy *ext_phy;
-	struct mt7615_dev *dev;
-
-	dev = container_of(work, struct mt7615_dev, reset_work);
-	ext_phy = dev->mt76.phy2;
-	phy2 = ext_phy ? ext_phy->priv : NULL;
-
-	if (!(READ_ONCE(dev->reset_state) & MT_MCU_CMD_STOP_PDMA))
-		return;
-
-	ieee80211_stop_queues(mt76_hw(dev));
-	if (ext_phy)
-		ieee80211_stop_queues(ext_phy->hw);
-
-	set_bit(MT76_RESET, &dev->mphy.state);
-	set_bit(MT76_MCU_RESET, &dev->mphy.state);
-	wake_up(&dev->mt76.mcu.wait);
-	cancel_delayed_work_sync(&dev->mphy.mac_work);
-	del_timer_sync(&dev->phy.roc_timer);
-	cancel_work_sync(&dev->phy.roc_work);
-	if (phy2) {
-		cancel_delayed_work_sync(&phy2->mt76->mac_work);
-		del_timer_sync(&phy2->roc_timer);
-		cancel_work_sync(&phy2->roc_work);
-	}
-
-	/* lock/unlock all queues to ensure that no tx is pending */
-	mt76_txq_schedule_all(&dev->mphy);
-	if (ext_phy)
-		mt76_txq_schedule_all(ext_phy);
-
-	mt76_worker_disable(&dev->mt76.tx_worker);
-	napi_disable(&dev->mt76.napi[0]);
-	napi_disable(&dev->mt76.napi[1]);
-	napi_disable(&dev->mt76.tx_napi);
-
-	mt7615_mutex_acquire(dev);
-
-	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_PDMA_STOPPED);
-
-	mt7615_tx_token_put(dev);
-	idr_init(&dev->token);
-
-	if (mt7615_wait_reset_state(dev, MT_MCU_CMD_RESET_DONE)) {
-		mt7615_dma_reset(dev);
-
-		mt76_wr(dev, MT_WPDMA_MEM_RNG_ERR, 0);
-
-		mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_PDMA_INIT);
-		mt7615_wait_reset_state(dev, MT_MCU_CMD_RECOVERY_DONE);
-	}
-
-	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
-	clear_bit(MT76_RESET, &dev->mphy.state);
-
-	mt76_worker_enable(&dev->mt76.tx_worker);
-	napi_enable(&dev->mt76.tx_napi);
-	napi_schedule(&dev->mt76.tx_napi);
-
-	napi_enable(&dev->mt76.napi[0]);
-	napi_schedule(&dev->mt76.napi[0]);
-
-	napi_enable(&dev->mt76.napi[1]);
-	napi_schedule(&dev->mt76.napi[1]);
-
-	ieee80211_wake_queues(mt76_hw(dev));
-	if (ext_phy)
-		ieee80211_wake_queues(ext_phy->hw);
-
-	mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE);
-	mt7615_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
-
-	mt7615_update_beacons(dev);
-
-	mt7615_mutex_release(dev);
-
-	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mphy.mac_work,
-				     MT7615_WATCHDOG_TIME);
-	if (phy2)
-		ieee80211_queue_delayed_work(ext_phy->hw,
-					     &phy2->mt76->mac_work,
-					     MT7615_WATCHDOG_TIME);
-
-}
-
 static void mt7615_dfs_stop_radar_detector(struct mt7615_phy *phy)
 {
 	struct mt7615_dev *dev = phy->dev;
@@ -2304,8 +2198,10 @@ void mt7615_coredump_work(struct work_struct *work)
 			break;
 
 		skb_pull(skb, sizeof(struct mt7615_mcu_rxd));
-		if (data + skb->len - dump > MT76_CONNAC_COREDUMP_SZ)
-			break;
+		if (data + skb->len - dump > MT76_CONNAC_COREDUMP_SZ) {
+			dev_kfree_skb(skb);
+			continue;
+		}
 
 		memcpy(data, skb->data, skb->len);
 		data += skb->len;