Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 299 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
new file mode 100644
index 000000000..57d39ee00
--- /dev/null
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -0,0 +1,299 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
+
+/* Linux PRO/1000 Ethernet Driver main header file */
+
+#ifndef _IGBVF_H_
+#define _IGBVF_H_
+
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+
+#include "vf.h"
+
+/* Forward declarations */
+struct igbvf_info;
+struct igbvf_adapter;
+
+/* Interrupt defines */
+#define IGBVF_START_ITR		488 /* ~8000 ints/sec */
+#define IGBVF_4K_ITR		980
+#define IGBVF_20K_ITR		196
+#define IGBVF_70K_ITR		56
+
+enum latency_range {
+	lowest_latency = 0,
+	low_latency = 1,
+	bulk_latency = 2,
+	latency_invalid = 255
+};
+
+/* Interrupt modes, as used by the IntMode parameter */
+#define IGBVF_INT_MODE_LEGACY	0
+#define IGBVF_INT_MODE_MSI	1
+#define IGBVF_INT_MODE_MSIX	2
+
+/* Tx/Rx descriptor defines */
+#define IGBVF_DEFAULT_TXD	256
+#define IGBVF_MAX_TXD		4096
+#define IGBVF_MIN_TXD		80
+
+#define IGBVF_DEFAULT_RXD	256
+#define IGBVF_MAX_RXD		4096
+#define IGBVF_MIN_RXD		80
+
+#define IGBVF_MIN_ITR_USECS	10 /* 100000 irq/sec */
+#define IGBVF_MAX_ITR_USECS	10000 /* 100    irq/sec */
+
+/* RX descriptor control thresholds.
+ * PTHRESH - MAC will consider prefetch if it has fewer than this number of
+ *	   descriptors available in its onboard memory.
+ *	   Setting this to 0 disables RX descriptor prefetch.
+ * HTHRESH - MAC will only prefetch if there are at least this many descriptors
+ *	   available in host memory.
+ *	   If PTHRESH is 0, this should also be 0.
+ * WTHRESH - RX descriptor writeback threshold - MAC will delay writing back
+ *	   descriptors until either it has this many to write back, or the
+ *	   ITR timer expires.
+ */
+#define IGBVF_RX_PTHRESH	16
+#define IGBVF_RX_HTHRESH	8
+#define IGBVF_RX_WTHRESH	1
+
+/* this is the size past which hardware will drop packets when setting LPE=0 */
+#define MAXIMUM_ETHERNET_VLAN_SIZE	1522
+
+#define IGBVF_FC_PAUSE_TIME	0x0680 /* 858 usec */
+
+/* How many Tx Descriptors do we need to call netif_wake_queue ? */
+#define IGBVF_TX_QUEUE_WAKE	32
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IGBVF_RX_BUFFER_WRITE	16 /* Must be power of 2 */
+
+#define AUTO_ALL_MODES		0
+#define IGBVF_EEPROM_APME	0x0400
+
+#define IGBVF_MNG_VLAN_NONE	(-1)
+
+#define IGBVF_MAX_MAC_FILTERS	3
+
+/* Number of packet split data buffers (not including the header buffer) */
+#define PS_PAGE_BUFFERS		(MAX_PS_BUFFERS - 1)
+
+enum igbvf_boards {
+	board_vf,
+	board_i350_vf,
+};
+
+struct igbvf_queue_stats {
+	u64 packets;
+	u64 bytes;
+};
+
+/* wrappers around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct igbvf_buffer {
+	dma_addr_t dma;
+	struct sk_buff *skb;
+	union {
+		/* Tx */
+		struct {
+			unsigned long time_stamp;
+			union e1000_adv_tx_desc *next_to_watch;
+			u16 length;
+			u16 mapped_as_page;
+		};
+		/* Rx */
+		struct {
+			struct page *page;
+			u64 page_dma;
+			unsigned int page_offset;
+		};
+	};
+};
+
+union igbvf_desc {
+	union e1000_adv_rx_desc rx_desc;
+	union e1000_adv_tx_desc tx_desc;
+	struct e1000_adv_tx_context_desc tx_context_desc;
+};
+
+struct igbvf_ring {
+	struct igbvf_adapter *adapter;  /* backlink */
+	union igbvf_desc *desc;	/* pointer to ring memory  */
+	dma_addr_t dma;		/* phys address of ring    */
+	unsigned int size;	/* length of ring in bytes */
+	unsigned int count;	/* number of desc. in ring */
+
+	u16 next_to_use;
+	u16 next_to_clean;
+
+	u16 head;
+	u16 tail;
+
+	/* array of buffer information structs */
+	struct igbvf_buffer *buffer_info;
+	struct napi_struct napi;
+
+	char name[IFNAMSIZ + 5];
+	u32 eims_value;
+	u32 itr_val;
+	enum latency_range itr_range;
+	u16 itr_register;
+	int set_itr;
+
+	struct sk_buff *rx_skb_top;
+
+	struct igbvf_queue_stats stats;
+};
+
+/* board specific private data structure */
+struct igbvf_adapter {
+	struct timer_list watchdog_timer;
+	struct timer_list blink_timer;
+
+	struct work_struct reset_task;
+	struct work_struct watchdog_task;
+
+	const struct igbvf_info *ei;
+
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	u32 bd_number;
+	u32 rx_buffer_len;
+	u32 polling_interval;
+	u16 mng_vlan_id;
+	u16 link_speed;
+	u16 link_duplex;
+
+	spinlock_t tx_queue_lock; /* prevent concurrent tail updates */
+
+	/* track device up/down/testing state */
+	unsigned long state;
+
+	/* Interrupt Throttle Rate */
+	u32 requested_itr; /* ints/sec or adaptive */
+	u32 current_itr; /* Actual ITR register value, not ints/sec */
+
+	/* Tx */
+	struct igbvf_ring *tx_ring /* One per active queue */
+	____cacheline_aligned_in_smp;
+
+	unsigned int restart_queue;
+	u32 txd_cmd;
+
+	u32 tx_int_delay;
+	u32 tx_abs_int_delay;
+
+	unsigned int total_tx_bytes;
+	unsigned int total_tx_packets;
+	unsigned int total_rx_bytes;
+	unsigned int total_rx_packets;
+
+	/* Tx stats */
+	u32 tx_timeout_count;
+	u32 tx_fifo_head;
+	u32 tx_head_addr;
+	u32 tx_fifo_size;
+	u32 tx_dma_failed;
+
+	/* Rx */
+	struct igbvf_ring *rx_ring;
+
+	u32 rx_int_delay;
+	u32 rx_abs_int_delay;
+
+	/* Rx stats */
+	u64 hw_csum_err;
+	u64 hw_csum_good;
+	u64 rx_hdr_split;
+	u32 alloc_rx_buff_failed;
+	u32 rx_dma_failed;
+
+	unsigned int rx_ps_hdr_size;
+	u32 max_frame_size;
+	u32 min_frame_size;
+
+	/* OS defined structs */
+	struct net_device *netdev;
+	struct pci_dev *pdev;
+	spinlock_t stats_lock; /* prevent concurrent stats updates */
+
+	/* structs defined in e1000_hw.h */
+	struct e1000_hw hw;
+
+	/* The VF counters don't clear on read so we have to get a base
+	 * count on driver start up and always subtract that base on
+	 * the first update, thus the flag..
+	 */
+	struct e1000_vf_stats stats;
+	u64 zero_base;
+
+	struct igbvf_ring test_tx_ring;
+	struct igbvf_ring test_rx_ring;
+	u32 test_icr;
+
+	u32 msg_enable;
+	struct msix_entry *msix_entries;
+	int int_mode;
+	u32 eims_enable_mask;
+	u32 eims_other;
+	u32 int_counter0;
+	u32 int_counter1;
+
+	u32 eeprom_wol;
+	u32 wol;
+	u32 pba;
+
+	bool fc_autoneg;
+
+	unsigned long led_status;
+
+	unsigned int flags;
+	unsigned long last_reset;
+};
+
+struct igbvf_info {
+	enum e1000_mac_type	mac;
+	unsigned int		flags;
+	u32			pba;
+	void			(*init_ops)(struct e1000_hw *);
+	s32			(*get_variants)(struct igbvf_adapter *);
+};
+
+/* hardware capability, feature, and workaround flags */
+#define IGBVF_FLAG_RX_CSUM_DISABLED	BIT(0)
+#define IGBVF_FLAG_RX_LB_VLAN_BSWAP	BIT(1)
+#define IGBVF_RX_DESC_ADV(R, i)     \
+	(&((((R).desc))[i].rx_desc))
+#define IGBVF_TX_DESC_ADV(R, i)     \
+	(&((((R).desc))[i].tx_desc))
+#define IGBVF_TX_CTXTDESC_ADV(R, i) \
+	(&((((R).desc))[i].tx_context_desc))
+
+enum igbvf_state_t {
+	__IGBVF_TESTING,
+	__IGBVF_RESETTING,
+	__IGBVF_DOWN
+};
+
+extern char igbvf_driver_name[];
+
+void igbvf_check_options(struct igbvf_adapter *);
+void igbvf_set_ethtool_ops(struct net_device *);
+
+int igbvf_up(struct igbvf_adapter *);
+void igbvf_down(struct igbvf_adapter *);
+void igbvf_reinit_locked(struct igbvf_adapter *);
+int igbvf_setup_rx_resources(struct igbvf_adapter *, struct igbvf_ring *);
+int igbvf_setup_tx_resources(struct igbvf_adapter *, struct igbvf_ring *);
+void igbvf_free_rx_resources(struct igbvf_ring *);
+void igbvf_free_tx_resources(struct igbvf_ring *);
+void igbvf_update_stats(struct igbvf_adapter *);
+
+extern unsigned int copybreak;
+
+#endif /* _IGBVF_H_ */