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, 88 insertions, 11 deletions

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 8bf45497cfca..36ede65919f8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -17,12 +17,14 @@
 #include "util.h"
 #include "testmode.h"
 
-#define MT_MCU_RING_SIZE    32
-#define MT_RX_BUF_SIZE      2048
-#define MT_SKB_HEAD_LEN     128
+#define MT_MCU_RING_SIZE	32
+#define MT_RX_BUF_SIZE		2048
+#define MT_SKB_HEAD_LEN		128
 
-#define MT_MAX_NON_AQL_PKT  16
-#define MT_TXQ_FREE_THR     32
+#define MT_MAX_NON_AQL_PKT	16
+#define MT_TXQ_FREE_THR		32
+
+#define MT76_TOKEN_FREE_THR	64
 
 struct mt76_dev;
 struct mt76_phy;
@@ -169,7 +171,8 @@ struct mt76_mcu_ops {
 };
 
 struct mt76_queue_ops {
-	int (*init)(struct mt76_dev *dev);
+	int (*init)(struct mt76_dev *dev,
+		    int (*poll)(struct napi_struct *napi, int budget));
 
 	int (*alloc)(struct mt76_dev *dev, struct mt76_queue *q,
 		     int idx, int n_desc, int bufsize,
@@ -190,13 +193,18 @@ struct mt76_queue_ops {
 	void (*tx_cleanup)(struct mt76_dev *dev, struct mt76_queue *q,
 			   bool flush);
 
+	void (*rx_cleanup)(struct mt76_dev *dev, struct mt76_queue *q);
+
 	void (*kick)(struct mt76_dev *dev, struct mt76_queue *q);
+
+	void (*reset_q)(struct mt76_dev *dev, struct mt76_queue *q);
 };
 
 enum mt76_wcid_flags {
 	MT_WCID_FLAG_CHECK_PS,
 	MT_WCID_FLAG_PS,
 	MT_WCID_FLAG_4ADDR,
+	MT_WCID_FLAG_HDR_TRANS,
 };
 
 #define MT76_N_WCIDS 288
@@ -222,6 +230,7 @@ struct mt76_wcid {
 
 	u16 idx;
 	u8 hw_key_idx;
+	u8 hw_key_idx2;
 
 	u8 sta:1;
 	u8 ext_phy:1;
@@ -324,6 +333,8 @@ struct mt76_driver_ops {
 	u32 drv_flags;
 	u32 survey_flags;
 	u16 txwi_size;
+	u16 token_size;
+	u8 mcs_rates;
 
 	void (*update_survey)(struct mt76_dev *dev);
 
@@ -491,15 +502,16 @@ struct mt76_rx_status {
 		u16 wcid_idx;
 	};
 
-	unsigned long reorder_time;
+	u32 reorder_time;
 
 	u32 ampdu_ref;
+	u32 timestamp;
 
 	u8 iv[6];
 
 	u8 ext_phy:1;
 	u8 aggr:1;
-	u8 tid;
+	u8 qos_ctl;
 	u16 seqno;
 
 	u16 freq;
@@ -507,6 +519,7 @@ struct mt76_rx_status {
 	u8 enc_flags;
 	u8 encoding:2, bw:3, he_ru:3;
 	u8 he_gi:2, he_dcm:1;
+	u8 amsdu:1, first_amsdu:1, last_amsdu:1;
 	u8 rate_idx;
 	u8 nss;
 	u8 band;
@@ -529,7 +542,7 @@ struct mt76_testmode_data {
 	struct sk_buff *tx_skb;
 
 	u32 tx_count;
-	u16 tx_msdu_len;
+	u16 tx_mpdu_len;
 
 	u8 tx_rate_mode;
 	u8 tx_rate_idx;
@@ -600,6 +613,12 @@ struct mt76_phy {
 
 	struct delayed_work mac_work;
 	u8 mac_work_count;
+
+	struct {
+		struct sk_buff *head;
+		struct sk_buff **tail;
+		u16 seqno;
+	} rx_amsdu[__MT_RXQ_MAX];
 };
 
 struct mt76_dev {
@@ -628,6 +647,7 @@ struct mt76_dev {
 	struct mt76_mcu mcu;
 
 	struct net_device napi_dev;
+	struct net_device tx_napi_dev;
 	spinlock_t rx_lock;
 	struct napi_struct napi[__MT_RXQ_MAX];
 	struct sk_buff_head rx_skb[__MT_RXQ_MAX];
@@ -641,6 +661,10 @@ struct mt76_dev {
 	struct mt76_worker tx_worker;
 	struct napi_struct tx_napi;
 
+	spinlock_t token_lock;
+	struct idr token;
+	int token_count;
+
 	wait_queue_head_t tx_wait;
 	struct sk_buff_head status_list;
 
@@ -695,6 +719,13 @@ struct mt76_dev {
 	};
 };
 
+struct mt76_power_limits {
+	s8 cck[4];
+	s8 ofdm[8];
+	s8 mcs[4][10];
+	s8 ru[7][12];
+};
+
 enum mt76_phy_type {
 	MT_PHY_TYPE_CCK,
 	MT_PHY_TYPE_OFDM,
@@ -778,13 +809,15 @@ static inline u16 mt76_rev(struct mt76_dev *dev)
 #define mt76xx_chip(dev) mt76_chip(&((dev)->mt76))
 #define mt76xx_rev(dev) mt76_rev(&((dev)->mt76))
 
-#define mt76_init_queues(dev)		(dev)->mt76.queue_ops->init(&((dev)->mt76))
+#define mt76_init_queues(dev, ...)		(dev)->mt76.queue_ops->init(&((dev)->mt76), __VA_ARGS__)
 #define mt76_queue_alloc(dev, ...)	(dev)->mt76.queue_ops->alloc(&((dev)->mt76), __VA_ARGS__)
 #define mt76_tx_queue_skb_raw(dev, ...)	(dev)->mt76.queue_ops->tx_queue_skb_raw(&((dev)->mt76), __VA_ARGS__)
 #define mt76_tx_queue_skb(dev, ...)	(dev)->mt76.queue_ops->tx_queue_skb(&((dev)->mt76), __VA_ARGS__)
 #define mt76_queue_rx_reset(dev, ...)	(dev)->mt76.queue_ops->rx_reset(&((dev)->mt76), __VA_ARGS__)
-#define mt76_queue_tx_cleanup(dev, ...)        (dev)->mt76.queue_ops->tx_cleanup(&((dev)->mt76), __VA_ARGS__)
+#define mt76_queue_tx_cleanup(dev, ...)	(dev)->mt76.queue_ops->tx_cleanup(&((dev)->mt76), __VA_ARGS__)
+#define mt76_queue_rx_cleanup(dev, ...)	(dev)->mt76.queue_ops->rx_cleanup(&((dev)->mt76), __VA_ARGS__)
 #define mt76_queue_kick(dev, ...)	(dev)->mt76.queue_ops->kick(&((dev)->mt76), __VA_ARGS__)
+#define mt76_queue_reset(dev, ...)	(dev)->mt76.queue_ops->reset_q(&((dev)->mt76), __VA_ARGS__)
 
 #define mt76_for_each_q_rx(dev, i)	\
 	for (i = 0; i < ARRAY_SIZE((dev)->q_rx) && \
@@ -811,6 +844,7 @@ void mt76_seq_puts_array(struct seq_file *file, const char *str,
 
 int mt76_eeprom_init(struct mt76_dev *dev, int len);
 void mt76_eeprom_override(struct mt76_phy *phy);
+int mt76_get_of_eeprom(struct mt76_dev *dev, void *data, int offset, int len);
 
 struct mt76_queue *
 mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc,
@@ -988,6 +1022,7 @@ void mt76_stop_tx_queues(struct mt76_phy *phy, struct ieee80211_sta *sta,
 void mt76_tx_check_agg_ssn(struct ieee80211_sta *sta, struct sk_buff *skb);
 void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid);
 void mt76_txq_schedule_all(struct mt76_phy *phy);
+void mt76_tx_worker_run(struct mt76_dev *dev);
 void mt76_tx_worker(struct mt76_worker *w);
 void mt76_release_buffered_frames(struct ieee80211_hw *hw,
 				  struct ieee80211_sta *sta,
@@ -1056,6 +1091,7 @@ int mt76_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 int mt76_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *skb,
 		       struct netlink_callback *cb, void *data, int len);
 int mt76_testmode_set_state(struct mt76_phy *phy, enum mt76_testmode_state state);
+int mt76_testmode_alloc_skb(struct mt76_phy *phy, u32 len);
 
 static inline void mt76_testmode_reset(struct mt76_phy *phy, bool disable)
 {
@@ -1176,4 +1212,45 @@ mt76_mcu_skb_send_msg(struct mt76_dev *dev, struct sk_buff *skb, int cmd,
 
 void mt76_set_irq_mask(struct mt76_dev *dev, u32 addr, u32 clear, u32 set);
 
+s8 mt76_get_rate_power_limits(struct mt76_phy *phy,
+			      struct ieee80211_channel *chan,
+			      struct mt76_power_limits *dest,
+			      s8 target_power);
+
+struct mt76_txwi_cache *
+mt76_token_release(struct mt76_dev *dev, int token, bool *wake);
+int mt76_token_consume(struct mt76_dev *dev, struct mt76_txwi_cache **ptxwi);
+void __mt76_set_tx_blocked(struct mt76_dev *dev, bool blocked);
+
+static inline void mt76_set_tx_blocked(struct mt76_dev *dev, bool blocked)
+{
+	spin_lock_bh(&dev->token_lock);
+	__mt76_set_tx_blocked(dev, blocked);
+	spin_unlock_bh(&dev->token_lock);
+}
+
+static inline int
+mt76_token_get(struct mt76_dev *dev, struct mt76_txwi_cache **ptxwi)
+{
+	int token;
+
+	spin_lock_bh(&dev->token_lock);
+	token = idr_alloc(&dev->token, *ptxwi, 0, dev->drv->token_size,
+			  GFP_ATOMIC);
+	spin_unlock_bh(&dev->token_lock);
+
+	return token;
+}
+
+static inline struct mt76_txwi_cache *
+mt76_token_put(struct mt76_dev *dev, int token)
+{
+	struct mt76_txwi_cache *txwi;
+
+	spin_lock_bh(&dev->token_lock);
+	txwi = idr_remove(&dev->token, token);
+	spin_unlock_bh(&dev->token_lock);
+
+	return txwi;
+}
 #endif