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, 84 insertions, 8 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index e553b9a1f785..b6cd43eda7ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -26,10 +26,21 @@
 
 struct stmmac_resources {
 	void __iomem *addr;
-	const char *mac;
+	u8 mac[ETH_ALEN];
 	int wol_irq;
 	int lpi_irq;
 	int irq;
+	int sfty_ce_irq;
+	int sfty_ue_irq;
+	int rx_irq[MTL_MAX_RX_QUEUES];
+	int tx_irq[MTL_MAX_TX_QUEUES];
+};
+
+enum stmmac_txbuf_type {
+	STMMAC_TXBUF_T_SKB,
+	STMMAC_TXBUF_T_XDP_TX,
+	STMMAC_TXBUF_T_XDP_NDO,
+	STMMAC_TXBUF_T_XSK_TX,
 };
 
 struct stmmac_tx_info {
@@ -38,6 +49,7 @@ struct stmmac_tx_info {
 	unsigned len;
 	bool last_segment;
 	bool is_jumbo;
+	enum stmmac_txbuf_type buf_type;
 };
 
 #define STMMAC_TBS_AVAIL	BIT(0)
@@ -53,8 +65,13 @@ struct stmmac_tx_queue {
 	struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
 	struct dma_edesc *dma_entx;
 	struct dma_desc *dma_tx;
-	struct sk_buff **tx_skbuff;
+	union {
+		struct sk_buff **tx_skbuff;
+		struct xdp_frame **xdpf;
+	};
 	struct stmmac_tx_info *tx_skbuff_dma;
+	struct xsk_buff_pool *xsk_pool;
+	u32 xsk_frames_done;
 	unsigned int cur_tx;
 	unsigned int dirty_tx;
 	dma_addr_t dma_tx_phy;
@@ -63,15 +80,23 @@ struct stmmac_tx_queue {
 };
 
 struct stmmac_rx_buffer {
-	struct page *page;
+	union {
+		struct {
+			struct page *page;
+			dma_addr_t addr;
+			__u32 page_offset;
+		};
+		struct xdp_buff *xdp;
+	};
 	struct page *sec_page;
-	dma_addr_t addr;
 	dma_addr_t sec_addr;
 };
 
 struct stmmac_rx_queue {
 	u32 rx_count_frames;
 	u32 queue_index;
+	struct xdp_rxq_info xdp_rxq;
+	struct xsk_buff_pool *xsk_pool;
 	struct page_pool *page_pool;
 	struct stmmac_rx_buffer *buf_pool;
 	struct stmmac_priv *priv_data;
@@ -79,6 +104,7 @@ struct stmmac_rx_queue {
 	struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
 	unsigned int cur_rx;
 	unsigned int dirty_rx;
+	unsigned int buf_alloc_num;
 	u32 rx_zeroc_thresh;
 	dma_addr_t dma_rx_phy;
 	u32 rx_tail_addr;
@@ -93,6 +119,7 @@ struct stmmac_rx_queue {
 struct stmmac_channel {
 	struct napi_struct rx_napi ____cacheline_aligned_in_smp;
 	struct napi_struct tx_napi ____cacheline_aligned_in_smp;
+	struct napi_struct rxtx_napi ____cacheline_aligned_in_smp;
 	struct stmmac_priv *priv_data;
 	spinlock_t lock;
 	u32 index;
@@ -147,20 +174,21 @@ struct stmmac_flow_entry {
 
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
-	u32 tx_coal_frames;
-	u32 tx_coal_timer;
-	u32 rx_coal_frames;
+	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
+	u32 tx_coal_timer[MTL_MAX_TX_QUEUES];
+	u32 rx_coal_frames[MTL_MAX_TX_QUEUES];
 
 	int tx_coalesce;
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
 	bool tso;
 	int sph;
+	int sph_cap;
 	u32 sarc_type;
 
 	unsigned int dma_buf_sz;
 	unsigned int rx_copybreak;
-	u32 rx_riwt;
+	u32 rx_riwt[MTL_MAX_TX_QUEUES];
 	int hwts_rx_en;
 
 	void __iomem *ioaddr;
@@ -222,9 +250,24 @@ struct stmmac_priv {
 	int use_riwt;
 	int irq_wake;
 	spinlock_t ptp_lock;
+	/* Protects auxiliary snapshot registers from concurrent access. */
+	struct mutex aux_ts_lock;
+
 	void __iomem *mmcaddr;
 	void __iomem *ptpaddr;
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	int sfty_ce_irq;
+	int sfty_ue_irq;
+	int rx_irq[MTL_MAX_RX_QUEUES];
+	int tx_irq[MTL_MAX_TX_QUEUES];
+	/*irq name */
+	char int_name_mac[IFNAMSIZ + 9];
+	char int_name_wol[IFNAMSIZ + 9];
+	char int_name_lpi[IFNAMSIZ + 9];
+	char int_name_sfty_ce[IFNAMSIZ + 10];
+	char int_name_sfty_ue[IFNAMSIZ + 10];
+	char int_name_rx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 14];
+	char int_name_tx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 18];
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dbgfs_dir;
@@ -234,6 +277,12 @@ struct stmmac_priv {
 	struct workqueue_struct *wq;
 	struct work_struct service_task;
 
+	/* Workqueue for handling FPE hand-shaking */
+	unsigned long fpe_task_state;
+	struct workqueue_struct *fpe_wq;
+	struct work_struct fpe_task;
+	char wq_name[IFNAMSIZ + 4];
+
 	/* TC Handling */
 	unsigned int tc_entries_max;
 	unsigned int tc_off_max;
@@ -246,6 +295,10 @@ struct stmmac_priv {
 
 	/* Receive Side Scaling */
 	struct stmmac_rss rss;
+
+	/* XDP BPF Program */
+	unsigned long *af_xdp_zc_qps;
+	struct bpf_prog *xdp_prog;
 };
 
 enum stmmac_state {
@@ -262,6 +315,8 @@ void stmmac_set_ethtool_ops(struct net_device *netdev);
 
 void stmmac_ptp_register(struct stmmac_priv *priv);
 void stmmac_ptp_unregister(struct stmmac_priv *priv);
+int stmmac_open(struct net_device *dev);
+int stmmac_release(struct net_device *dev);
 int stmmac_resume(struct device *dev);
 int stmmac_suspend(struct device *dev);
 int stmmac_dvr_remove(struct device *dev);
@@ -272,6 +327,27 @@ void stmmac_disable_eee_mode(struct stmmac_priv *priv);
 bool stmmac_eee_init(struct stmmac_priv *priv);
 int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt);
 int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size);
+int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled);
+void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable);
+
+static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
+{
+	return !!priv->xdp_prog;
+}
+
+static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
+{
+	if (stmmac_xdp_is_enabled(priv))
+		return XDP_PACKET_HEADROOM;
+
+	return 0;
+}
+
+void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue);
+void stmmac_enable_rx_queue(struct stmmac_priv *priv, u32 queue);
+void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue);
+void stmmac_enable_tx_queue(struct stmmac_priv *priv, u32 queue);
+int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags);
 
 #if IS_ENABLED(CONFIG_STMMAC_SELFTESTS)
 void stmmac_selftest_run(struct net_device *dev,