From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/net/ethernet/chelsio/cxgb3/adapter.h | 334 +++++++++++++++++++++++++++ 1 file changed, 334 insertions(+) create mode 100644 drivers/net/ethernet/chelsio/cxgb3/adapter.h (limited to 'drivers/net/ethernet/chelsio/cxgb3/adapter.h') diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h new file mode 100644 index 000000000..6d682b7c7 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h @@ -0,0 +1,334 @@ +/* + * Copyright (c) 2003-2008 Chelsio, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* This file should not be included directly. Include common.h instead. */ + +#ifndef __T3_ADAPTER_H__ +#define __T3_ADAPTER_H__ + +#include +#include +#include +#include +#include +#include +#include +#include "t3cdev.h" +#include + +struct adapter; +struct sge_qset; +struct port_info; + +enum mac_idx_types { + LAN_MAC_IDX = 0, + SAN_MAC_IDX, + + MAX_MAC_IDX +}; + +struct iscsi_config { + __u8 mac_addr[ETH_ALEN]; + __u32 flags; + int (*send)(struct port_info *pi, struct sk_buff **skb); + int (*recv)(struct port_info *pi, struct sk_buff *skb); +}; + +struct port_info { + struct adapter *adapter; + struct sge_qset *qs; + u8 port_id; + u8 nqsets; + u8 first_qset; + struct cphy phy; + struct cmac mac; + struct link_config link_config; + int activity; + __be32 iscsi_ipv4addr; + struct iscsi_config iscsic; + + int link_fault; /* link fault was detected */ +}; + +enum { /* adapter flags */ + FULL_INIT_DONE = (1 << 0), + USING_MSI = (1 << 1), + USING_MSIX = (1 << 2), + QUEUES_BOUND = (1 << 3), + TP_PARITY_INIT = (1 << 4), + NAPI_INIT = (1 << 5), +}; + +struct fl_pg_chunk { + struct page *page; + void *va; + unsigned int offset; + unsigned long *p_cnt; + dma_addr_t mapping; +}; + +struct rx_desc; +struct rx_sw_desc; + +struct sge_fl { /* SGE per free-buffer list state */ + unsigned int buf_size; /* size of each Rx buffer */ + unsigned int credits; /* # of available Rx buffers */ + unsigned int pend_cred; /* new buffers since last FL DB ring */ + unsigned int size; /* capacity of free list */ + unsigned int cidx; /* consumer index */ + unsigned int pidx; /* producer index */ + unsigned int gen; /* free list generation */ + struct fl_pg_chunk pg_chunk;/* page chunk cache */ + unsigned int use_pages; /* whether FL uses pages or sk_buffs */ + unsigned int order; /* order of page allocations */ + unsigned int alloc_size; /* size of allocated buffer */ + struct rx_desc *desc; /* address of HW Rx descriptor ring */ + struct rx_sw_desc *sdesc; /* address of SW Rx descriptor ring */ + dma_addr_t phys_addr; /* physical address of HW ring start */ + unsigned int cntxt_id; /* SGE context id for the free list */ + unsigned long empty; /* # of times queue ran out of buffers */ + unsigned long alloc_failed; /* # of times buffer allocation failed */ +}; + +/* + * Bundle size for grouping offload RX packets for delivery to the stack. + * Don't make this too big as we do prefetch on each packet in a bundle. + */ +# define RX_BUNDLE_SIZE 8 + +struct rsp_desc; + +struct sge_rspq { /* state for an SGE response queue */ + unsigned int credits; /* # of pending response credits */ + unsigned int size; /* capacity of response queue */ + unsigned int cidx; /* consumer index */ + unsigned int gen; /* current generation bit */ + unsigned int polling; /* is the queue serviced through NAPI? */ + unsigned int holdoff_tmr; /* interrupt holdoff timer in 100ns */ + unsigned int next_holdoff; /* holdoff time for next interrupt */ + unsigned int rx_recycle_buf; /* whether recycling occurred + within current sop-eop */ + struct rsp_desc *desc; /* address of HW response ring */ + dma_addr_t phys_addr; /* physical address of the ring */ + unsigned int cntxt_id; /* SGE context id for the response q */ + spinlock_t lock; /* guards response processing */ + struct sk_buff_head rx_queue; /* offload packet receive queue */ + struct sk_buff *pg_skb; /* used to build frag list in napi handler */ + + unsigned long offload_pkts; + unsigned long offload_bundles; + unsigned long eth_pkts; /* # of ethernet packets */ + unsigned long pure_rsps; /* # of pure (non-data) responses */ + unsigned long imm_data; /* responses with immediate data */ + unsigned long rx_drops; /* # of packets dropped due to no mem */ + unsigned long async_notif; /* # of asynchronous notification events */ + unsigned long empty; /* # of times queue ran out of credits */ + unsigned long nomem; /* # of responses deferred due to no mem */ + unsigned long unhandled_irqs; /* # of spurious intrs */ + unsigned long starved; + unsigned long restarted; +}; + +struct tx_desc; +struct tx_sw_desc; + +struct sge_txq { /* state for an SGE Tx queue */ + unsigned long flags; /* HW DMA fetch status */ + unsigned int in_use; /* # of in-use Tx descriptors */ + unsigned int size; /* # of descriptors */ + unsigned int processed; /* total # of descs HW has processed */ + unsigned int cleaned; /* total # of descs SW has reclaimed */ + unsigned int stop_thres; /* SW TX queue suspend threshold */ + unsigned int cidx; /* consumer index */ + unsigned int pidx; /* producer index */ + unsigned int gen; /* current value of generation bit */ + unsigned int unacked; /* Tx descriptors used since last COMPL */ + struct tx_desc *desc; /* address of HW Tx descriptor ring */ + struct tx_sw_desc *sdesc; /* address of SW Tx descriptor ring */ + spinlock_t lock; /* guards enqueueing of new packets */ + unsigned int token; /* WR token */ + dma_addr_t phys_addr; /* physical address of the ring */ + struct sk_buff_head sendq; /* List of backpressured offload packets */ + struct work_struct qresume_task; /* restarts the queue */ + unsigned int cntxt_id; /* SGE context id for the Tx q */ + unsigned long stops; /* # of times q has been stopped */ + unsigned long restarts; /* # of queue restarts */ +}; + +enum { /* per port SGE statistics */ + SGE_PSTAT_TSO, /* # of TSO requests */ + SGE_PSTAT_RX_CSUM_GOOD, /* # of successful RX csum offloads */ + SGE_PSTAT_TX_CSUM, /* # of TX checksum offloads */ + SGE_PSTAT_VLANEX, /* # of VLAN tag extractions */ + SGE_PSTAT_VLANINS, /* # of VLAN tag insertions */ + + SGE_PSTAT_MAX /* must be last */ +}; + +struct napi_gro_fraginfo; + +struct sge_qset { /* an SGE queue set */ + struct adapter *adap; + struct napi_struct napi; + struct sge_rspq rspq; + struct sge_fl fl[SGE_RXQ_PER_SET]; + struct sge_txq txq[SGE_TXQ_PER_SET]; + int nomem; + void *lro_va; + struct net_device *netdev; + struct netdev_queue *tx_q; /* associated netdev TX queue */ + unsigned long txq_stopped; /* which Tx queues are stopped */ + struct timer_list tx_reclaim_timer; /* reclaims TX buffers */ + struct timer_list rx_reclaim_timer; /* reclaims RX buffers */ + unsigned long port_stats[SGE_PSTAT_MAX]; +} ____cacheline_aligned; + +struct sge { + struct sge_qset qs[SGE_QSETS]; + spinlock_t reg_lock; /* guards non-atomic SGE registers (eg context) */ +}; + +struct adapter { + struct t3cdev tdev; + struct list_head adapter_list; + void __iomem *regs; + struct pci_dev *pdev; + unsigned long registered_device_map; + unsigned long open_device_map; + unsigned long flags; + + const char *name; + int msg_enable; + unsigned int mmio_len; + + struct adapter_params params; + unsigned int slow_intr_mask; + unsigned long irq_stats[IRQ_NUM_STATS]; + + int msix_nvectors; + struct { + unsigned short vec; + char desc[22]; + } msix_info[SGE_QSETS + 1]; + + /* T3 modules */ + struct sge sge; + struct mc7 pmrx; + struct mc7 pmtx; + struct mc7 cm; + struct mc5 mc5; + + struct net_device *port[MAX_NPORTS]; + unsigned int check_task_cnt; + struct delayed_work adap_check_task; + struct work_struct ext_intr_handler_task; + struct work_struct fatal_error_handler_task; + struct work_struct link_fault_handler_task; + + struct work_struct db_full_task; + struct work_struct db_empty_task; + struct work_struct db_drop_task; + + struct dentry *debugfs_root; + + struct mutex mdio_lock; + spinlock_t stats_lock; + spinlock_t work_lock; + + struct sk_buff *nofail_skb; +}; + +static inline u32 t3_read_reg(struct adapter *adapter, u32 reg_addr) +{ + u32 val = readl(adapter->regs + reg_addr); + + CH_DBG(adapter, MMIO, "read register 0x%x value 0x%x\n", reg_addr, val); + return val; +} + +static inline void t3_write_reg(struct adapter *adapter, u32 reg_addr, u32 val) +{ + CH_DBG(adapter, MMIO, "setting register 0x%x to 0x%x\n", reg_addr, val); + writel(val, adapter->regs + reg_addr); +} + +static inline struct port_info *adap2pinfo(struct adapter *adap, int idx) +{ + return netdev_priv(adap->port[idx]); +} + +static inline int phy2portid(struct cphy *phy) +{ + struct adapter *adap = phy->adapter; + struct port_info *port0 = adap2pinfo(adap, 0); + + return &port0->phy == phy ? 0 : 1; +} + +#define OFFLOAD_DEVMAP_BIT 15 + +#define tdev2adap(d) container_of(d, struct adapter, tdev) + +static inline int offload_running(struct adapter *adapter) +{ + return test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map); +} + +int t3_offload_tx(struct t3cdev *tdev, struct sk_buff *skb); + +void t3_os_ext_intr_handler(struct adapter *adapter); +void t3_os_link_changed(struct adapter *adapter, int port_id, int link_status, + int speed, int duplex, int fc); +void t3_os_phymod_changed(struct adapter *adap, int port_id); +void t3_os_link_fault(struct adapter *adapter, int port_id, int state); +void t3_os_link_fault_handler(struct adapter *adapter, int port_id); + +void t3_sge_start(struct adapter *adap); +void t3_sge_stop_dma(struct adapter *adap); +void t3_sge_stop(struct adapter *adap); +void t3_start_sge_timers(struct adapter *adap); +void t3_stop_sge_timers(struct adapter *adap); +void t3_free_sge_resources(struct adapter *adap); +void t3_sge_err_intr_handler(struct adapter *adapter); +irq_handler_t t3_intr_handler(struct adapter *adap, int polling); +netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev); +int t3_mgmt_tx(struct adapter *adap, struct sk_buff *skb); +void t3_update_qset_coalesce(struct sge_qset *qs, const struct qset_params *p); +int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, + int irq_vec_idx, const struct qset_params *p, + int ntxq, struct net_device *dev, + struct netdev_queue *netdevq); +extern struct workqueue_struct *cxgb3_wq; + +int t3_get_edc_fw(struct cphy *phy, int edc_idx, int size); + +#endif /* __T3_ADAPTER_H__ */ -- cgit v1.2.3