STRUCT NFP_NET(9)

📦 version 7.3.1, in nixpkgs unstable

💖 struct nfp_net(9) 💖

okay so bestie, welcome to the struct nfp_net page — this is the NFP network device structure and it lives in the Kernel API Manual. it's a big one, grab a snack 🍓

✨ SYNOPSIS ✨

like, here's the whole vibe, every field, exactly as it is:

struct nfp_net {
    struct nfp_net_dp dp;
    const struct nfp_dev_info *dev_info;
    struct nfp_net_fw_version fw_ver;
    u32 id;
    u32 cap;
    u32 cap_w1;
    u32 max_mtu;
    u8 rss_hfunc;
    u32 rss_cfg;
    u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
    u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
    struct xdp_attachment_info xdp;
    struct xdp_attachment_info xdp_hw;
    unsigned int max_tx_rings;
    unsigned int max_rx_rings;
    int stride_tx;
    int stride_rx;
    unsigned int max_r_vecs;
    struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
    struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
    irq_handler_t lsc_handler;
    char lsc_name[IFNAMSIZ + 8];
    irq_handler_t exn_handler;
    char exn_name[IFNAMSIZ + 8];
    irq_handler_t shared_handler;
    char shared_name[IFNAMSIZ + 8];
    bool link_up;
    spinlock_t link_status_lock;
    spinlock_t reconfig_lock;
    u32 reconfig_posted;
    bool reconfig_timer_active;
    bool reconfig_sync_present;
    struct timer_list reconfig_timer;
    u32 reconfig_in_progress_update;
    struct semaphore bar_lock;
    bool rx_coalesce_adapt_on;
    bool tx_coalesce_adapt_on;
    u32 rx_coalesce_usecs;
    u32 rx_coalesce_max_frames;
    u32 tx_coalesce_usecs;
    u32 tx_coalesce_max_frames;
    u8 __iomem *qcp_cfg;
    u8 __iomem *tx_bar;
    u8 __iomem *rx_bar;
  #ifdef CONFIG_NFP_NET_IPSEC;
    struct xarray xa_ipsec;
  #endif;
    struct nfp_net_tlv_caps tlv_caps;
    unsigned int ktls_tx_conn_cnt;
    unsigned int ktls_rx_conn_cnt;
    atomic64_t ktls_conn_id_gen;
    atomic_t ktls_no_space;
    atomic_t ktls_rx_resync_req;
    atomic_t ktls_rx_resync_ign;
    atomic_t ktls_rx_resync_sent;
    struct {
      struct sk_buff_head queue;
      wait_queue_head_t wq;
      struct workqueue_struct *workq;
      struct work_struct wait_work;
      struct work_struct runq_work;
      u16 tag;
    } mbox_cmsg;
    struct dentry *debugfs_dir;
    struct list_head vnic_list;
    struct pci_dev *pdev;
    struct nfp_app *app;
    bool vnic_no_name;
    struct nfp_port *port;
    struct {
      spinlock_t lock;
      struct list_head list;
      struct work_struct work;
    } mbox_amsg;
    struct {
      u16 count;
      struct list_head list;
    } fs;
    void *app_priv;
 };

🌸 MEMBERS 🌸

okay, deep breath, we're going field by field and honestly? every single one ate 💅

  • dp — the datapath structure. like the whole main-character of data movement.
  • dev_info — NFP ASIC params. the hardware's little ID card.
  • fw_ver — firmware version. good to know what we're working with fr fr.
  • id — vNIC id within the PF (it's 0 for VFs, no cap).
  • cap — capabilities advertised by the Firmware. the flex list.
  • cap_w1 — extended capabilities word advertised by the Firmware. slay, more flex.
  • max_mtu — maximum support MTU advertised by the Firmware. (yes, "support", that's what it says, don't come for me 😭)
  • rss_hfunc — RSS selected hash function.
  • rss_cfg — RSS configuration.
  • rss_key — RSS secret key. 🤫
  • rss_itbl — RSS indirection table.
  • xdp — information about the driver XDP program.
  • xdp_hw — information about the HW XDP program.
  • max_tx_rings — maximum number of TX rings supported by the Firmware.
  • max_rx_rings — maximum number of RX rings supported by the Firmware.
  • stride_tx — queue controller TX queue spacing.
  • stride_rx — queue controller RX queue spacing.
  • max_r_vecs — number of allocated interrupt vectors for RX/TX.
  • r_vecs — pre-allocated array of ring vectors.
  • irq_entries — pre-allocated array of MSI-X entries.
  • lsc_handler — handler for Link State Change interrupt.
  • lsc_name — name for Link State Change interrupt.
  • exn_handler — handler for Exception interrupt.
  • exn_name — name for Exception interrupt.
  • shared_handler — handler for shared interrupts.
  • shared_name — name for shared interrupt.
  • link_up — is the link up? (the eternal question 💀)
  • link_status_lock — protects link_* and ensures atomicity with BAR reading.
  • reconfig_lock — protects reconfig_posted, reconfig_timer_active, reconfig_sync_present and HW reconfiguration request regs/machinery from async requests (sync must take bar_lock). lowkey a lot of responsibility ngl.
  • reconfig_posted — pending reconfig bits coming from async sources.
  • reconfig_timer_active — timer for reading reconfiguration results is pending.
  • reconfig_sync_present — some thread is performing synchronous reconfig.
  • reconfig_timer — timer for async reading of reconfig results.
  • reconfig_in_progress_update — update FW is processing now (debug only). 🔍
  • bar_lock — vNIC config BAR access lock, protects: update, mailbox area, crypto TLV.
  • rx_coalesce_adapt_on — is RX interrupt moderation adaptive?
  • tx_coalesce_adapt_on — is TX interrupt moderation adaptive?
  • rx_coalesce_usecs — RX interrupt moderation usecs delay parameter.
  • rx_coalesce_max_frames — RX interrupt moderation frame count parameter.
  • tx_coalesce_usecs — TX interrupt moderation usecs delay parameter.
  • tx_coalesce_max_frames — TX interrupt moderation frame count parameter.
  • qcp_cfg — pointer to QCP queue used for configuration notification.
  • tx_bar — pointer to mapped TX queues.
  • rx_bar — pointer to mapped FL/RX queues.
  • xa_ipsec — IPsec xarray SA data. (only a thing when CONFIG_NFP_NET_IPSEC is on, iykyk)
  • tlv_caps — parsed TLV capabilities.
  • ktls_tx_conn_cnt — number of offloaded kTLS TX connections.
  • ktls_rx_conn_cnt — number of offloaded kTLS RX connections.
  • ktls_conn_id_gen — trivial generator for kTLS connection ids (for TX).
  • ktls_no_space — counter of firmware rejecting kTLS connection due to lack of space. rude of it, honestly.
  • ktls_rx_resync_req — counter of TLS RX resync requested.
  • ktls_rx_resync_ign — counter of TLS RX resync requests ignored.
  • ktls_rx_resync_sent — counter of TLS RX resync completed.
  • mbox_cmsg — Common Control Message via vNIC mailbox state.
    • mbox_cmsg.queue — CCM mbox queue of pending messages.
    • mbox_cmsg.wq — CCM mbox wait queue of waiting processes.
    • mbox_cmsg.workq — CCM mbox work queue for wait_work and runq_work.
    • mbox_cmsg.wait_work — CCM mbox posted msg reconfig wait work.
    • mbox_cmsg.runq_work — CCM mbox posted msg queue runner work.
    • mbox_cmsg.tag — CCM mbox message tag allocator.
  • debugfs_dir — device directory in debugfs.
  • vnic_list — entry on device vNIC list.
  • pdev — backpointer to PCI device.
  • app — APP handle if available.
  • vnic_no_name — for non-port PF vNIC make ndo_get_phys_port_name return -EOPNOTSUPP to keep backwards compatibility (set by app). yes that's the whole sentence, it's important 🫶
  • port — pointer to nfp_port structure if vNIC is a port.
  • mbox_amsg — asynchronously processed message via mailbox.
    • mbox_amsg.lock — protect message list.
    • mbox_amsg.list — list of message to process.
    • mbox_amsg.work — work to process message asynchronously.
  • fs — flow steering.
    • fs.count — flow count.
    • fs.list — list of flows.
  • app_priv — APP private data for this vNIC.

🦋 SEE ALSO 🦋

go read these next bestie, they're all in the kernel file ./drivers/net/ethernet/netronome/nfp/nfp_net.h, and also:

and that's the page!! 💜 this one's from ./drivers/net/ethernet/netrono... (they truncated it, not me 🙈), dated October 2026 — ty for reading bestie, go forth and slay those rings ✨🎀🌈
📦 where this page comes from