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, 63 insertions, 48 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 17101c45cbcd..e35db3ff583b 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -36,6 +36,7 @@
 #include <linux/bpf.h>
 #include <linux/avf/virtchnl.h>
 #include <linux/cpu_rmap.h>
+#include <linux/dim.h>
 #include <net/devlink.h>
 #include <net/ipv6.h>
 #include <net/xdp_sock.h>
@@ -44,6 +45,9 @@
 #include <net/gre.h>
 #include <net/udp_tunnel.h>
 #include <net/vxlan.h>
+#if IS_ENABLED(CONFIG_DCB)
+#include <scsi/iscsi_proto.h>
+#endif /* CONFIG_DCB */
 #include "ice_devids.h"
 #include "ice_type.h"
 #include "ice_txrx.h"
@@ -73,7 +77,7 @@
 #define ICE_MIN_LAN_TXRX_MSIX	1
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
-#define ICE_FDIR_MSIX		1
+#define ICE_FDIR_MSIX		2
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -84,9 +88,12 @@
 #define ICE_MAX_LG_RSS_QS	256
 #define ICE_RES_VALID_BIT	0x8000
 #define ICE_RES_MISC_VEC_ID	(ICE_RES_VALID_BIT - 1)
+/* All VF control VSIs share the same IRQ, so assign a unique ID for them */
+#define ICE_RES_VF_CTRL_VEC_ID	(ICE_RES_MISC_VEC_ID - 1)
 #define ICE_INVAL_Q_INDEX	0xffff
 #define ICE_INVAL_VFID		256
 
+#define ICE_MAX_RXQS_PER_TC		256	/* Used when setting VSI context per TC Rx queues */
 #define ICE_MAX_RESET_WAIT		20
 
 #define ICE_VSIQF_HKEY_ARRAY_SIZE	((VSIQF_HKEY_MAX_INDEX + 1) *	4)
@@ -190,53 +197,58 @@ struct ice_sw {
 	u8 dflt_vsi_ena:1;	/* true if above dflt_vsi is enabled */
 };
 
-enum ice_state {
-	__ICE_TESTING,
-	__ICE_DOWN,
-	__ICE_NEEDS_RESTART,
-	__ICE_PREPARED_FOR_RESET,	/* set by driver when prepared */
-	__ICE_RESET_OICR_RECV,		/* set by driver after rcv reset OICR */
-	__ICE_PFR_REQ,			/* set by driver and peers */
-	__ICE_CORER_REQ,		/* set by driver and peers */
-	__ICE_GLOBR_REQ,		/* set by driver and peers */
-	__ICE_CORER_RECV,		/* set by OICR handler */
-	__ICE_GLOBR_RECV,		/* set by OICR handler */
-	__ICE_EMPR_RECV,		/* set by OICR handler */
-	__ICE_SUSPENDED,		/* set on module remove path */
-	__ICE_RESET_FAILED,		/* set by reset/rebuild */
+enum ice_pf_state {
+	ICE_TESTING,
+	ICE_DOWN,
+	ICE_NEEDS_RESTART,
+	ICE_PREPARED_FOR_RESET,	/* set by driver when prepared */
+	ICE_RESET_OICR_RECV,		/* set by driver after rcv reset OICR */
+	ICE_PFR_REQ,			/* set by driver and peers */
+	ICE_CORER_REQ,		/* set by driver and peers */
+	ICE_GLOBR_REQ,		/* set by driver and peers */
+	ICE_CORER_RECV,		/* set by OICR handler */
+	ICE_GLOBR_RECV,		/* set by OICR handler */
+	ICE_EMPR_RECV,		/* set by OICR handler */
+	ICE_SUSPENDED,		/* set on module remove path */
+	ICE_RESET_FAILED,		/* set by reset/rebuild */
 	/* When checking for the PF to be in a nominal operating state, the
 	 * bits that are grouped at the beginning of the list need to be
-	 * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
+	 * checked. Bits occurring before ICE_STATE_NOMINAL_CHECK_BITS will
 	 * be checked. If you need to add a bit into consideration for nominal
 	 * operating state, it must be added before
-	 * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position
+	 * ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position
 	 * without appropriate consideration.
 	 */
-	__ICE_STATE_NOMINAL_CHECK_BITS,
-	__ICE_ADMINQ_EVENT_PENDING,
-	__ICE_MAILBOXQ_EVENT_PENDING,
-	__ICE_MDD_EVENT_PENDING,
-	__ICE_VFLR_EVENT_PENDING,
-	__ICE_FLTR_OVERFLOW_PROMISC,
-	__ICE_VF_DIS,
-	__ICE_CFG_BUSY,
-	__ICE_SERVICE_SCHED,
-	__ICE_SERVICE_DIS,
-	__ICE_FD_FLUSH_REQ,
-	__ICE_OICR_INTR_DIS,		/* Global OICR interrupt disabled */
-	__ICE_MDD_VF_PRINT_PENDING,	/* set when MDD event handle */
-	__ICE_VF_RESETS_DISABLED,	/* disable resets during ice_remove */
-	__ICE_LINK_DEFAULT_OVERRIDE_PENDING,
-	__ICE_PHY_INIT_COMPLETE,
-	__ICE_STATE_NBITS		/* must be last */
+	ICE_STATE_NOMINAL_CHECK_BITS,
+	ICE_ADMINQ_EVENT_PENDING,
+	ICE_MAILBOXQ_EVENT_PENDING,
+	ICE_MDD_EVENT_PENDING,
+	ICE_VFLR_EVENT_PENDING,
+	ICE_FLTR_OVERFLOW_PROMISC,
+	ICE_VF_DIS,
+	ICE_CFG_BUSY,
+	ICE_SERVICE_SCHED,
+	ICE_SERVICE_DIS,
+	ICE_FD_FLUSH_REQ,
+	ICE_OICR_INTR_DIS,		/* Global OICR interrupt disabled */
+	ICE_MDD_VF_PRINT_PENDING,	/* set when MDD event handle */
+	ICE_VF_RESETS_DISABLED,	/* disable resets during ice_remove */
+	ICE_LINK_DEFAULT_OVERRIDE_PENDING,
+	ICE_PHY_INIT_COMPLETE,
+	ICE_FD_VF_FLUSH_CTX,		/* set at FD Rx IRQ or timeout */
+	ICE_STATE_NBITS		/* must be last */
 };
 
-enum ice_vsi_flags {
-	ICE_VSI_FLAG_UMAC_FLTR_CHANGED,
-	ICE_VSI_FLAG_MMAC_FLTR_CHANGED,
-	ICE_VSI_FLAG_VLAN_FLTR_CHANGED,
-	ICE_VSI_FLAG_PROMISC_CHANGED,
-	ICE_VSI_FLAG_NBITS		/* must be last */
+enum ice_vsi_state {
+	ICE_VSI_DOWN,
+	ICE_VSI_NEEDS_RESTART,
+	ICE_VSI_NETDEV_ALLOCD,
+	ICE_VSI_NETDEV_REGISTERED,
+	ICE_VSI_UMAC_FLTR_CHANGED,
+	ICE_VSI_MMAC_FLTR_CHANGED,
+	ICE_VSI_VLAN_FLTR_CHANGED,
+	ICE_VSI_PROMISC_CHANGED,
+	ICE_VSI_STATE_NBITS		/* must be last */
 };
 
 /* struct that defines a VSI, associated with a dev */
@@ -252,14 +264,12 @@ struct ice_vsi {
 	irqreturn_t (*irq_handler)(int irq, void *data);
 
 	u64 tx_linearize;
-	DECLARE_BITMAP(state, __ICE_STATE_NBITS);
-	DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS);
+	DECLARE_BITMAP(state, ICE_VSI_STATE_NBITS);
 	unsigned int current_netdev_flags;
 	u32 tx_restart;
 	u32 tx_busy;
 	u32 rx_buf_failed;
 	u32 rx_page_failed;
-	u32 rx_gro_dropped;
 	u16 num_q_vectors;
 	u16 base_vector;		/* IRQ base for OS reserved vectors */
 	enum ice_vsi_type type;
@@ -342,7 +352,7 @@ struct ice_q_vector {
 	u16 reg_idx;
 	u8 num_ring_rx;			/* total number of Rx rings in vector */
 	u8 num_ring_tx;			/* total number of Tx rings in vector */
-	u8 itr_countdown;		/* when 0 should adjust adaptive ITR */
+	u8 wb_on_itr:1;			/* if true, WB on ITR is enabled */
 	/* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
 	 * value to the device
 	 */
@@ -357,6 +367,8 @@ struct ice_q_vector {
 	struct irq_affinity_notify affinity_notify;
 
 	char name[ICE_INT_NAME_STR_LEN];
+
+	u16 total_events;	/* net_dim(): number of interrupts processed */
 } ____cacheline_internodealigned_in_smp;
 
 enum ice_pf_flags {
@@ -414,7 +426,8 @@ struct ice_pf {
 	u16 num_msix_per_vf;
 	/* used to ratelimit the MDD event logging */
 	unsigned long last_printed_mdd_jiffies;
-	DECLARE_BITMAP(state, __ICE_STATE_NBITS);
+	DECLARE_BITMAP(malvfs, ICE_MAX_VF_COUNT);
+	DECLARE_BITMAP(state, ICE_STATE_NBITS);
 	DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS);
 	unsigned long *avail_txqs;	/* bitmap to track PF Tx queue usage */
 	unsigned long *avail_rxqs;	/* bitmap to track PF Rx queue usage */
@@ -499,7 +512,7 @@ ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
 	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
 	      (itr << GLINT_DYN_CTL_ITR_INDX_S);
 	if (vsi)
-		if (test_bit(__ICE_DOWN, vsi->state))
+		if (test_bit(ICE_VSI_DOWN, vsi->state))
 			return;
 	wr32(hw, GLINT_DYN_CTL(vector), val);
 }
@@ -616,8 +629,10 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi);
 int
 ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	     u32 flags);
-int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
-int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
+int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size);
+int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size);
+int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed);
+int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);