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, 108 insertions, 21 deletions

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 8b380fc13314..08b283347d9c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -19,12 +19,21 @@
 				(ETH_FCS_LEN + ETH_HLEN + VLAN_HLEN))
 
 struct enetc_tx_swbd {
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdp_frame;
+	};
 	dma_addr_t dma;
+	struct page *page;	/* valid only if is_xdp_tx */
+	u16 page_offset;	/* valid only if is_xdp_tx */
 	u16 len;
+	enum dma_data_direction dir;
 	u8 is_dma_page:1;
 	u8 check_wb:1;
-	u8 do_tstamp:1;
+	u8 do_twostep_tstamp:1;
+	u8 is_eof:1;
+	u8 is_xdp_tx:1;
+	u8 is_xdp_redirect:1;
 };
 
 #define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
@@ -32,21 +41,45 @@ struct enetc_tx_swbd {
 #define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
 #define ENETC_RXB_DMA_SIZE	\
 	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD)
+#define ENETC_RXB_DMA_SIZE_XDP	\
+	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - XDP_PACKET_HEADROOM)
 
 struct enetc_rx_swbd {
 	dma_addr_t dma;
 	struct page *page;
 	u16 page_offset;
+	enum dma_data_direction dir;
+	u16 len;
 };
 
+/* ENETC overhead: optional extension BD + 1 BD gap */
+#define ENETC_TXBDS_NEEDED(val)	((val) + 2)
+/* max # of chained Tx BDs is 15, including head and extension BD */
+#define ENETC_MAX_SKB_FRAGS	13
+#define ENETC_TXBDS_MAX_NEEDED	ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1)
+
 struct enetc_ring_stats {
 	unsigned int packets;
 	unsigned int bytes;
 	unsigned int rx_alloc_errs;
+	unsigned int xdp_drops;
+	unsigned int xdp_tx;
+	unsigned int xdp_tx_drops;
+	unsigned int xdp_redirect;
+	unsigned int xdp_redirect_failures;
+	unsigned int xdp_redirect_sg;
+	unsigned int recycles;
+	unsigned int recycle_failures;
+};
+
+struct enetc_xdp_data {
+	struct xdp_rxq_info rxq;
+	struct bpf_prog *prog;
+	int xdp_tx_in_flight;
 };
 
-#define ENETC_RX_RING_DEFAULT_SIZE	512
-#define ENETC_TX_RING_DEFAULT_SIZE	256
+#define ENETC_RX_RING_DEFAULT_SIZE	2048
+#define ENETC_TX_RING_DEFAULT_SIZE	2048
 #define ENETC_DEFAULT_TX_WORK		(ENETC_TX_RING_DEFAULT_SIZE / 2)
 
 struct enetc_bdr {
@@ -71,6 +104,9 @@ struct enetc_bdr {
 	};
 	void __iomem *idr; /* Interrupt Detect Register pointer */
 
+	int buffer_offset;
+	struct enetc_xdp_data xdp;
+
 	struct enetc_ring_stats stats;
 
 	dma_addr_t bd_dma_base;
@@ -92,18 +128,28 @@ static inline int enetc_bd_unused(struct enetc_bdr *bdr)
 	return bdr->bd_count + bdr->next_to_clean - bdr->next_to_use - 1;
 }
 
+static inline int enetc_swbd_unused(struct enetc_bdr *bdr)
+{
+	if (bdr->next_to_clean > bdr->next_to_alloc)
+		return bdr->next_to_clean - bdr->next_to_alloc - 1;
+
+	return bdr->bd_count + bdr->next_to_clean - bdr->next_to_alloc - 1;
+}
+
 /* Control BD ring */
 #define ENETC_CBDR_DEFAULT_SIZE	64
 struct enetc_cbdr {
 	void *bd_base; /* points to Rx or Tx BD ring */
 	void __iomem *pir;
 	void __iomem *cir;
+	void __iomem *mr; /* mode register */
 
 	int bd_count; /* # of BDs */
 	int next_to_use;
 	int next_to_clean;
 
 	dma_addr_t bd_dma_base;
+	struct device *dma_dev;
 };
 
 #define ENETC_TXBD(BDR, i) (&(((union enetc_tx_bd *)((BDR).bd_base))[i]))
@@ -119,19 +165,26 @@ static inline union enetc_rx_bd *enetc_rxbd(struct enetc_bdr *rx_ring, int i)
 	return &(((union enetc_rx_bd *)rx_ring->bd_base)[hw_idx]);
 }
 
-static inline union enetc_rx_bd *enetc_rxbd_next(struct enetc_bdr *rx_ring,
-						 union enetc_rx_bd *rxbd,
-						 int i)
+static inline void enetc_rxbd_next(struct enetc_bdr *rx_ring,
+				   union enetc_rx_bd **old_rxbd, int *old_index)
 {
-	rxbd++;
+	union enetc_rx_bd *new_rxbd = *old_rxbd;
+	int new_index = *old_index;
+
+	new_rxbd++;
+
 #ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 	if (rx_ring->ext_en)
-		rxbd++;
+		new_rxbd++;
 #endif
-	if (unlikely(++i == rx_ring->bd_count))
-		rxbd = rx_ring->bd_base;
 
-	return rxbd;
+	if (unlikely(++new_index == rx_ring->bd_count)) {
+		new_rxbd = rx_ring->bd_base;
+		new_index = 0;
+	}
+
+	*old_rxbd = new_rxbd;
+	*old_index = new_index;
 }
 
 static inline union enetc_rx_bd *enetc_rxbd_ext(union enetc_rx_bd *rxbd)
@@ -184,6 +237,22 @@ static inline bool enetc_si_is_pf(struct enetc_si *si)
 	return !!(si->hw.port);
 }
 
+static inline int enetc_pf_to_port(struct pci_dev *pf_pdev)
+{
+	switch (pf_pdev->devfn) {
+	case 0:
+		return 0;
+	case 1:
+		return 1;
+	case 2:
+		return 2;
+	case 6:
+		return 3;
+	default:
+		return -1;
+	}
+}
+
 #define ENETC_MAX_NUM_TXQS	8
 #define ENETC_INT_NAME_MAX	(IFNAMSIZ + 8)
 
@@ -218,12 +287,20 @@ struct psfp_cap {
 	u32 max_psfp_meter;
 };
 
+#define ENETC_F_TX_TSTAMP_MASK	0xff
 /* TODO: more hardware offloads */
 enum enetc_active_offloads {
-	ENETC_F_RX_TSTAMP	= BIT(0),
-	ENETC_F_TX_TSTAMP	= BIT(1),
-	ENETC_F_QBV             = BIT(2),
-	ENETC_F_QCI		= BIT(3),
+	/* 8 bits reserved for TX timestamp types (hwtstamp_tx_types) */
+	ENETC_F_TX_TSTAMP		= BIT(0),
+	ENETC_F_TX_ONESTEP_SYNC_TSTAMP	= BIT(1),
+
+	ENETC_F_RX_TSTAMP		= BIT(8),
+	ENETC_F_QBV			= BIT(9),
+	ENETC_F_QCI			= BIT(10),
+};
+
+enum enetc_flags_bit {
+	ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS = 0,
 };
 
 /* interrupt coalescing modes */
@@ -252,10 +329,11 @@ struct enetc_ndev_priv {
 	u16 rx_bd_count, tx_bd_count;
 
 	u16 msg_enable;
-	int active_offloads;
+	enum enetc_active_offloads active_offloads;
 
 	u32 speed; /* store speed for compare update pspeed */
 
+	struct enetc_bdr **xdp_tx_ring;
 	struct enetc_bdr *tx_ring[16];
 	struct enetc_bdr *rx_ring[16];
 
@@ -266,6 +344,13 @@ struct enetc_ndev_priv {
 	struct phylink *phylink;
 	int ic_mode;
 	u32 tx_ictt;
+
+	struct bpf_prog *xdp_prog;
+
+	unsigned long flags;
+
+	struct work_struct	tx_onestep_tstamp;
+	struct sk_buff_head	tx_skbs;
 };
 
 /* Messaging */
@@ -305,15 +390,17 @@ int enetc_set_features(struct net_device *ndev,
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd);
 int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		   void *type_data);
+int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp);
+int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
+		   struct xdp_frame **frames, u32 flags);
 
 /* ethtool */
 void enetc_set_ethtool_ops(struct net_device *ndev);
 
 /* control buffer descriptor ring (CBDR) */
-int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
-void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
-void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr);
-void enetc_clear_cbdr(struct enetc_hw *hw);
+int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count,
+		     struct enetc_cbdr *cbdr);
+void enetc_teardown_cbdr(struct enetc_cbdr *cbdr);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);