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, 315 insertions, 0 deletions

diff --git a/include/net/macsec.h b/include/net/macsec.h
new file mode 100644
index 000000000..5b9c61c4d
--- /dev/null
+++ b/include/net/macsec.h
@@ -0,0 +1,315 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * MACsec netdev header, used for h/w accelerated implementations.
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ */
+#ifndef _NET_MACSEC_H_
+#define _NET_MACSEC_H_
+
+#include <linux/u64_stats_sync.h>
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/if_macsec.h>
+
+#define MACSEC_DEFAULT_PN_LEN 4
+#define MACSEC_XPN_PN_LEN 8
+
+#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
+
+#define MACSEC_SCI_LEN 8
+#define MACSEC_PORT_ES (htons(0x0001))
+
+#define MACSEC_TCI_VERSION 0x80
+#define MACSEC_TCI_ES      0x40 /* end station */
+#define MACSEC_TCI_SC      0x20 /* SCI present */
+#define MACSEC_TCI_SCB     0x10 /* epon */
+#define MACSEC_TCI_E       0x08 /* encryption */
+#define MACSEC_TCI_C       0x04 /* changed text */
+#define MACSEC_AN_MASK     0x03 /* association number */
+#define MACSEC_TCI_CONFID  (MACSEC_TCI_E | MACSEC_TCI_C)
+
+#define MACSEC_DEFAULT_ICV_LEN 16
+
+typedef u64 __bitwise sci_t;
+typedef u32 __bitwise ssci_t;
+
+struct metadata_dst;
+
+typedef union salt {
+	struct {
+		u32 ssci;
+		u64 pn;
+	} __packed;
+	u8 bytes[MACSEC_SALT_LEN];
+} __packed salt_t;
+
+typedef union pn {
+	struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+		u32 lower;
+		u32 upper;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+		u32 upper;
+		u32 lower;
+#else
+#error	"Please fix <asm/byteorder.h>"
+#endif
+	};
+	u64 full64;
+} pn_t;
+
+/**
+ * struct macsec_key - SA key
+ * @id: user-provided key identifier
+ * @tfm: crypto struct, key storage
+ * @salt: salt used to generate IV in XPN cipher suites
+ */
+struct macsec_key {
+	u8 id[MACSEC_KEYID_LEN];
+	struct crypto_aead *tfm;
+	salt_t salt;
+};
+
+struct macsec_rx_sc_stats {
+	__u64 InOctetsValidated;
+	__u64 InOctetsDecrypted;
+	__u64 InPktsUnchecked;
+	__u64 InPktsDelayed;
+	__u64 InPktsOK;
+	__u64 InPktsInvalid;
+	__u64 InPktsLate;
+	__u64 InPktsNotValid;
+	__u64 InPktsNotUsingSA;
+	__u64 InPktsUnusedSA;
+};
+
+struct macsec_rx_sa_stats {
+	__u32 InPktsOK;
+	__u32 InPktsInvalid;
+	__u32 InPktsNotValid;
+	__u32 InPktsNotUsingSA;
+	__u32 InPktsUnusedSA;
+};
+
+struct macsec_tx_sa_stats {
+	__u32 OutPktsProtected;
+	__u32 OutPktsEncrypted;
+};
+
+struct macsec_tx_sc_stats {
+	__u64 OutPktsProtected;
+	__u64 OutPktsEncrypted;
+	__u64 OutOctetsProtected;
+	__u64 OutOctetsEncrypted;
+};
+
+struct macsec_dev_stats {
+	__u64 OutPktsUntagged;
+	__u64 InPktsUntagged;
+	__u64 OutPktsTooLong;
+	__u64 InPktsNoTag;
+	__u64 InPktsBadTag;
+	__u64 InPktsUnknownSCI;
+	__u64 InPktsNoSCI;
+	__u64 InPktsOverrun;
+};
+
+/**
+ * struct macsec_rx_sa - receive secure association
+ * @active:
+ * @next_pn: packet number expected for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @ssci: short secure channel identifier
+ * @stats: per-SA stats
+ */
+struct macsec_rx_sa {
+	struct macsec_key key;
+	ssci_t ssci;
+	spinlock_t lock;
+	union {
+		pn_t next_pn_halves;
+		u64 next_pn;
+	};
+	refcount_t refcnt;
+	bool active;
+	struct macsec_rx_sa_stats __percpu *stats;
+	struct macsec_rx_sc *sc;
+	struct rcu_head rcu;
+};
+
+struct pcpu_rx_sc_stats {
+	struct macsec_rx_sc_stats stats;
+	struct u64_stats_sync syncp;
+};
+
+struct pcpu_tx_sc_stats {
+	struct macsec_tx_sc_stats stats;
+	struct u64_stats_sync syncp;
+};
+
+/**
+ * struct macsec_rx_sc - receive secure channel
+ * @sci: secure channel identifier for this SC
+ * @active: channel is active
+ * @sa: array of secure associations
+ * @stats: per-SC stats
+ */
+struct macsec_rx_sc {
+	struct macsec_rx_sc __rcu *next;
+	sci_t sci;
+	bool active;
+	struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
+	struct pcpu_rx_sc_stats __percpu *stats;
+	refcount_t refcnt;
+	struct rcu_head rcu_head;
+};
+
+/**
+ * struct macsec_tx_sa - transmit secure association
+ * @active:
+ * @next_pn: packet number to use for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @ssci: short secure channel identifier
+ * @stats: per-SA stats
+ */
+struct macsec_tx_sa {
+	struct macsec_key key;
+	ssci_t ssci;
+	spinlock_t lock;
+	union {
+		pn_t next_pn_halves;
+		u64 next_pn;
+	};
+	refcount_t refcnt;
+	bool active;
+	struct macsec_tx_sa_stats __percpu *stats;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct macsec_tx_sc - transmit secure channel
+ * @active:
+ * @encoding_sa: association number of the SA currently in use
+ * @encrypt: encrypt packets on transmit, or authenticate only
+ * @send_sci: always include the SCI in the SecTAG
+ * @end_station:
+ * @scb: single copy broadcast flag
+ * @sa: array of secure associations
+ * @stats: stats for this TXSC
+ * @md_dst: MACsec offload metadata dst
+ */
+struct macsec_tx_sc {
+	bool active;
+	u8 encoding_sa;
+	bool encrypt;
+	bool send_sci;
+	bool end_station;
+	bool scb;
+	struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
+	struct pcpu_tx_sc_stats __percpu *stats;
+	struct metadata_dst *md_dst;
+};
+
+/**
+ * struct macsec_secy - MACsec Security Entity
+ * @netdev: netdevice for this SecY
+ * @n_rx_sc: number of receive secure channels configured on this SecY
+ * @sci: secure channel identifier used for tx
+ * @key_len: length of keys used by the cipher suite
+ * @icv_len: length of ICV used by the cipher suite
+ * @validate_frames: validation mode
+ * @xpn: enable XPN for this SecY
+ * @operational: MAC_Operational flag
+ * @protect_frames: enable protection for this SecY
+ * @replay_protect: enable packet number checks on receive
+ * @replay_window: size of the replay window
+ * @tx_sc: transmit secure channel
+ * @rx_sc: linked list of receive secure channels
+ */
+struct macsec_secy {
+	struct net_device *netdev;
+	unsigned int n_rx_sc;
+	sci_t sci;
+	u16 key_len;
+	u16 icv_len;
+	enum macsec_validation_type validate_frames;
+	bool xpn;
+	bool operational;
+	bool protect_frames;
+	bool replay_protect;
+	u32 replay_window;
+	struct macsec_tx_sc tx_sc;
+	struct macsec_rx_sc __rcu *rx_sc;
+};
+
+/**
+ * struct macsec_context - MACsec context for hardware offloading
+ */
+struct macsec_context {
+	union {
+		struct net_device *netdev;
+		struct phy_device *phydev;
+	};
+	enum macsec_offload offload;
+
+	struct macsec_secy *secy;
+	struct macsec_rx_sc *rx_sc;
+	struct {
+		unsigned char assoc_num;
+		u8 key[MACSEC_MAX_KEY_LEN];
+		union {
+			struct macsec_rx_sa *rx_sa;
+			struct macsec_tx_sa *tx_sa;
+		};
+	} sa;
+	union {
+		struct macsec_tx_sc_stats *tx_sc_stats;
+		struct macsec_tx_sa_stats *tx_sa_stats;
+		struct macsec_rx_sc_stats *rx_sc_stats;
+		struct macsec_rx_sa_stats *rx_sa_stats;
+		struct macsec_dev_stats  *dev_stats;
+	} stats;
+};
+
+/**
+ * struct macsec_ops - MACsec offloading operations
+ */
+struct macsec_ops {
+	/* Device wide */
+	int (*mdo_dev_open)(struct macsec_context *ctx);
+	int (*mdo_dev_stop)(struct macsec_context *ctx);
+	/* SecY */
+	int (*mdo_add_secy)(struct macsec_context *ctx);
+	int (*mdo_upd_secy)(struct macsec_context *ctx);
+	int (*mdo_del_secy)(struct macsec_context *ctx);
+	/* Security channels */
+	int (*mdo_add_rxsc)(struct macsec_context *ctx);
+	int (*mdo_upd_rxsc)(struct macsec_context *ctx);
+	int (*mdo_del_rxsc)(struct macsec_context *ctx);
+	/* Security associations */
+	int (*mdo_add_rxsa)(struct macsec_context *ctx);
+	int (*mdo_upd_rxsa)(struct macsec_context *ctx);
+	int (*mdo_del_rxsa)(struct macsec_context *ctx);
+	int (*mdo_add_txsa)(struct macsec_context *ctx);
+	int (*mdo_upd_txsa)(struct macsec_context *ctx);
+	int (*mdo_del_txsa)(struct macsec_context *ctx);
+	/* Statistics */
+	int (*mdo_get_dev_stats)(struct macsec_context *ctx);
+	int (*mdo_get_tx_sc_stats)(struct macsec_context *ctx);
+	int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx);
+	int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx);
+	int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx);
+};
+
+void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
+static inline bool macsec_send_sci(const struct macsec_secy *secy)
+{
+	const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
+
+	return tx_sc->send_sci ||
+		(secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb);
+}
+
+#endif /* _NET_MACSEC_H_ */