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, 239 insertions, 0 deletions

diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
new file mode 100644
index 000000000..9b9f2e44f
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ */
+
+#ifndef _QEDI_ISCSI_H_
+#define _QEDI_ISCSI_H_
+
+#include <linux/socket.h>
+#include <linux/completion.h>
+#include "qedi.h"
+
+#define ISCSI_MAX_SESS_PER_HBA	4096
+
+#define DEF_KA_TIMEOUT		7200000
+#define DEF_KA_INTERVAL		10000
+#define DEF_KA_MAX_PROBE_COUNT	10
+#define DEF_TOS			0
+#define DEF_TTL			0xfe
+#define DEF_SND_SEQ_SCALE	0
+#define DEF_RCV_BUF		0xffff
+#define DEF_SND_BUF		0xffff
+#define DEF_SEED		0
+#define DEF_MAX_RT_TIME		8000
+#define DEF_MAX_DA_COUNT        2
+#define DEF_SWS_TIMER		1000
+#define DEF_MAX_CWND		2
+#define DEF_PATH_MTU		1500
+#define DEF_MSS			1460
+#define DEF_LL2_MTU		1560
+#define JUMBO_MTU		9000
+
+#define MIN_MTU         576 /* rfc 793 */
+#define IPV4_HDR_LEN    20
+#define IPV6_HDR_LEN    40
+#define TCP_HDR_LEN     20
+#define TCP_OPTION_LEN  12
+#define VLAN_LEN         4
+
+enum {
+	EP_STATE_IDLE                   = 0x0,
+	EP_STATE_ACQRCONN_START         = 0x1,
+	EP_STATE_ACQRCONN_COMPL         = 0x2,
+	EP_STATE_OFLDCONN_START         = 0x4,
+	EP_STATE_OFLDCONN_COMPL         = 0x8,
+	EP_STATE_DISCONN_START          = 0x10,
+	EP_STATE_DISCONN_COMPL          = 0x20,
+	EP_STATE_CLEANUP_START          = 0x40,
+	EP_STATE_CLEANUP_CMPL           = 0x80,
+	EP_STATE_TCP_FIN_RCVD           = 0x100,
+	EP_STATE_TCP_RST_RCVD           = 0x200,
+	EP_STATE_LOGOUT_SENT            = 0x400,
+	EP_STATE_LOGOUT_RESP_RCVD       = 0x800,
+	EP_STATE_CLEANUP_FAILED         = 0x1000,
+	EP_STATE_OFLDCONN_FAILED        = 0x2000,
+	EP_STATE_CONNECT_FAILED         = 0x4000,
+	EP_STATE_DISCONN_TIMEDOUT       = 0x8000,
+	EP_STATE_OFLDCONN_NONE          = 0x10000,
+};
+
+struct qedi_conn;
+
+struct qedi_endpoint {
+	struct qedi_ctx *qedi;
+	u32 dst_addr[4];
+	u32 src_addr[4];
+	u16 src_port;
+	u16 dst_port;
+	u16 vlan_id;
+	u16 pmtu;
+	u8 src_mac[ETH_ALEN];
+	u8 dst_mac[ETH_ALEN];
+	u8 ip_type;
+	int state;
+	wait_queue_head_t ofld_wait;
+	wait_queue_head_t tcp_ofld_wait;
+	u32 iscsi_cid;
+	/* identifier of the connection from qed */
+	u32 handle;
+	u32 fw_cid;
+	void __iomem *p_doorbell;
+	struct iscsi_db_data db_data;
+
+	/* Send queue management */
+	struct iscsi_wqe *sq;
+	dma_addr_t sq_dma;
+
+	u16 sq_prod_idx;
+	u16 fw_sq_prod_idx;
+	u16 sq_con_idx;
+	u32 sq_mem_size;
+
+	void *sq_pbl;
+	dma_addr_t sq_pbl_dma;
+	u32 sq_pbl_size;
+	struct qedi_conn *conn;
+	struct work_struct offload_work;
+};
+
+#define QEDI_SQ_WQES_MIN	16
+
+struct qedi_io_bdt {
+	struct scsi_sge *sge_tbl;
+	dma_addr_t sge_tbl_dma;
+	u16 sge_valid;
+};
+
+/**
+ * struct generic_pdu_resc - login pdu resource structure
+ *
+ * @req_buf:            driver buffer used to stage payload associated with
+ *                      the login request
+ * @req_dma_addr:       dma address for iscsi login request payload buffer
+ * @req_buf_size:       actual login request payload length
+ * @req_wr_ptr:         pointer into login request buffer when next data is
+ *                      to be written
+ * @resp_hdr:           iscsi header where iscsi login response header is to
+ *                      be recreated
+ * @resp_buf:           buffer to stage login response payload
+ * @resp_dma_addr:      login response payload buffer dma address
+ * @resp_buf_size:      login response paylod length
+ * @resp_wr_ptr:        pointer into login response buffer when next data is
+ *                      to be written
+ * @req_bd_tbl:         iscsi login request payload BD table
+ * @req_bd_dma:         login request BD table dma address
+ * @resp_bd_tbl:        iscsi login response payload BD table
+ * @resp_bd_dma:        login request BD table dma address
+ *
+ * following structure defines buffer info for generic pdus such as iSCSI Login,
+ *      Logout and NOP
+ */
+struct generic_pdu_resc {
+	char *req_buf;
+	dma_addr_t req_dma_addr;
+	u32 req_buf_size;
+	char *req_wr_ptr;
+	struct iscsi_hdr resp_hdr;
+	char *resp_buf;
+	dma_addr_t resp_dma_addr;
+	u32 resp_buf_size;
+	char *resp_wr_ptr;
+	char *req_bd_tbl;
+	dma_addr_t req_bd_dma;
+	char *resp_bd_tbl;
+	dma_addr_t resp_bd_dma;
+};
+
+struct qedi_conn {
+	struct iscsi_cls_conn *cls_conn;
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *ep;
+	struct iscsi_endpoint *iscsi_ep;
+	struct list_head active_cmd_list;
+	spinlock_t list_lock;		/* internal conn lock */
+	u32 active_cmd_count;
+	u32 cmd_cleanup_req;
+	atomic_t cmd_cleanup_cmpl;
+
+	u32 iscsi_conn_id;
+	int itt;
+	int abrt_conn;
+#define QEDI_CID_RESERVED	0x5AFF
+	u32 fw_cid;
+	/*
+	 * Buffer for login negotiation process
+	 */
+	struct generic_pdu_resc gen_pdu;
+
+	struct list_head tmf_work_list;
+	wait_queue_head_t wait_queue;
+	spinlock_t tmf_work_lock;	/* tmf work lock */
+	bool ep_disconnect_starting;
+	int fw_cleanup_works;
+};
+
+struct qedi_cmd {
+	struct list_head io_cmd;
+	bool io_cmd_in_list;
+	struct iscsi_hdr hdr;
+	struct qedi_conn *conn;
+	struct scsi_cmnd *scsi_cmd;
+	struct scatterlist *sg;
+	struct qedi_io_bdt io_tbl;
+	struct iscsi_task_context request;
+	unsigned char *sense_buffer;
+	dma_addr_t sense_buffer_dma;
+	u16 task_id;
+
+	/* field populated for tmf work queue */
+	struct iscsi_task *task;
+	struct work_struct tmf_work;
+	int state;
+#define CLEANUP_WAIT	1
+#define CLEANUP_RECV	2
+#define CLEANUP_WAIT_FAILED	3
+#define CLEANUP_NOT_REQUIRED	4
+#define LUN_RESET_RESPONSE_RECEIVED	5
+#define RESPONSE_RECEIVED	6
+
+	int type;
+#define TYPEIO		1
+#define TYPERESET	2
+
+	struct qedi_work_map *list_tmf_work;
+	/* slowpath management */
+	bool use_slowpath;
+
+	struct iscsi_tm_rsp *tmf_resp_buf;
+	struct qedi_work cqe_work;
+};
+
+struct qedi_work_map {
+	struct list_head list;
+	struct qedi_cmd *qedi_cmd;
+	struct iscsi_task *ctask;
+	int rtid;
+
+	int state;
+#define QEDI_WORK_QUEUED	1
+#define QEDI_WORK_SCHEDULED	2
+#define QEDI_WORK_EXIT		3
+
+	struct work_struct *ptr_tmf_work;
+};
+
+struct qedi_boot_target {
+	char ip_addr[64];
+	char iscsi_name[255];
+	u32 ipv6_en;
+};
+
+#define qedi_set_itt(task_id, itt) ((u32)(((task_id) & 0xffff) | ((itt) << 16)))
+#define qedi_get_itt(cqe) (cqe.iscsi_hdr.cmd.itt >> 16)
+
+#define QEDI_OFLD_WAIT_STATE(q) ((q)->state == EP_STATE_OFLDCONN_FAILED || \
+				(q)->state == EP_STATE_OFLDCONN_COMPL)
+
+#endif /* _QEDI_ISCSI_H_ */