/* SPDX-License-Identifier: GPL-2.0-only */ /**************************************************************************** * Driver for Solarflare network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. * Copyright 2005-2013 Solarflare Communications Inc. */ /* Common definitions for all Efx net driver code */ #ifndef EFX_NET_DRIVER_H #define EFX_NET_DRIVER_H #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/timer.h> #include <linux/mdio.h> #include <linux/list.h> #include <linux/pci.h> #include <linux/device.h> #include <linux/highmem.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/vmalloc.h> #include <linux/mtd/mtd.h> #include <net/busy_poll.h> #include <net/xdp.h> #include <net/netevent.h> #include "enum.h" #include "bitfield.h" #include "filter.h" /************************************************************************** * * Build definitions * **************************************************************************/ #ifdef DEBUG #define EFX_WARN_ON_ONCE_PARANOID … #define EFX_WARN_ON_PARANOID … #else #define EFX_WARN_ON_ONCE_PARANOID(x) … #define EFX_WARN_ON_PARANOID(x) … #endif /************************************************************************** * * Efx data structures * **************************************************************************/ #define EFX_MAX_CHANNELS … #define EFX_MAX_RX_QUEUES … #define EFX_EXTRA_CHANNEL_IOV … #define EFX_EXTRA_CHANNEL_PTP … #define EFX_EXTRA_CHANNEL_TC … #define EFX_MAX_EXTRA_CHANNELS … /* Checksum generation is a per-queue option in hardware, so each * queue visible to the networking core is backed by two hardware TX * queues. */ #define EFX_MAX_TX_TC … #define EFX_MAX_CORE_TX_QUEUES … #define EFX_TXQ_TYPE_OUTER_CSUM … #define EFX_TXQ_TYPE_INNER_CSUM … #define EFX_TXQ_TYPES … #define EFX_MAX_TXQ_PER_CHANNEL … #define EFX_MAX_TX_QUEUES … /* Maximum possible MTU the driver supports */ #define EFX_MAX_MTU … /* Minimum MTU, from RFC791 (IP) */ #define EFX_MIN_MTU … /* Maximum total header length for TSOv2 */ #define EFX_TSO2_MAX_HDRLEN … /* Size of an RX scatter buffer. Small enough to pack 2 into a 4K page, * and should be a multiple of the cache line size. */ #define EFX_RX_USR_BUF_SIZE … /* If possible, we should ensure cache line alignment at start and end * of every buffer. Otherwise, we just need to ensure 4-byte * alignment of the network header. */ #if NET_IP_ALIGN == 0 #define EFX_RX_BUF_ALIGNMENT … #else #define EFX_RX_BUF_ALIGNMENT … #endif /* Non-standard XDP_PACKET_HEADROOM and tailroom to satisfy XDP_REDIRECT and * still fit two standard MTU size packets into a single 4K page. */ #define EFX_XDP_HEADROOM … #define EFX_XDP_TAILROOM … /* Forward declare Precision Time Protocol (PTP) support structure. */ struct efx_ptp_data; struct hwtstamp_config; struct efx_self_tests; /** * struct efx_buffer - A general-purpose DMA buffer * @addr: host base address of the buffer * @dma_addr: DMA base address of the buffer * @len: Buffer length, in bytes * * The NIC uses these buffers for its interrupt status registers and * MAC stats dumps. */ struct efx_buffer { … }; /** * struct efx_tx_buffer - buffer state for a TX descriptor * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be * freed when descriptor completes * @xdpf: When @flags & %EFX_TX_BUF_XDP, the XDP frame information; its @data * member is the associated buffer to drop a page reference on. * @option: When @flags & %EFX_TX_BUF_OPTION, an EF10-specific option * descriptor. * @dma_addr: DMA address of the fragment. * @flags: Flags for allocation and DMA mapping type * @len: Length of this fragment. * This field is zero when the queue slot is empty. * @unmap_len: Length of this fragment to unmap * @dma_offset: Offset of @dma_addr from the address of the backing DMA mapping. * Only valid if @unmap_len != 0. */ struct efx_tx_buffer { … }; #define EFX_TX_BUF_CONT … #define EFX_TX_BUF_SKB … #define EFX_TX_BUF_MAP_SINGLE … #define EFX_TX_BUF_OPTION … #define EFX_TX_BUF_XDP … #define EFX_TX_BUF_TSO_V3 … #define EFX_TX_BUF_EFV … /** * struct efx_tx_queue - An Efx TX queue * * This is a ring buffer of TX fragments. * Since the TX completion path always executes on the same * CPU and the xmit path can operate on different CPUs, * performance is increased by ensuring that the completion * path and the xmit path operate on different cache lines. * This is particularly important if the xmit path is always * executing on one CPU which is different from the completion * path. There is also a cache line for members which are * read but not written on the fast path. * * @efx: The associated Efx NIC * @queue: DMA queue number * @label: Label for TX completion events. * Is our index within @channel->tx_queue array. * @type: configuration type of this TX queue. A bitmask of %EFX_TXQ_TYPE_* flags. * @tso_version: Version of TSO in use for this queue. * @tso_encap: Is encapsulated TSO supported? Supported in TSOv2 on 8000 series. * @channel: The associated channel * @core_txq: The networking core TX queue structure * @buffer: The software buffer ring * @cb_page: Array of pages of copy buffers. Carved up according to * %EFX_TX_CB_ORDER into %EFX_TX_CB_SIZE-sized chunks. * @txd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. * @piobuf: PIO buffer region for this TX queue (shared with its partner). * Size of the region is efx_piobuf_size. * @piobuf_offset: Buffer offset to be specified in PIO descriptors * @initialised: Has hardware queue been initialised? * @timestamping: Is timestamping enabled for this channel? * @xdp_tx: Is this an XDP tx queue? * @read_count: Current read pointer. * This is the number of buffers that have been removed from both rings. * @old_write_count: The value of @write_count when last checked. * This is here for performance reasons. The xmit path will * only get the up-to-date value of @write_count if this * variable indicates that the queue is empty. This is to * avoid cache-line ping-pong between the xmit path and the * completion path. * @merge_events: Number of TX merged completion events * @completed_timestamp_major: Top part of the most recent tx timestamp. * @completed_timestamp_minor: Low part of the most recent tx timestamp. * @insert_count: Current insert pointer * This is the number of buffers that have been added to the * software ring. * @write_count: Current write pointer * This is the number of buffers that have been added to the * hardware ring. * @packet_write_count: Completable write pointer * This is the write pointer of the last packet written. * Normally this will equal @write_count, but as option descriptors * don't produce completion events, they won't update this. * Filled in iff @efx->type->option_descriptors; only used for PIO. * Thus, this is only written and used on EF10. * @old_read_count: The value of read_count when last checked. * This is here for performance reasons. The xmit path will * only get the up-to-date value of read_count if this * variable indicates that the queue is full. This is to * avoid cache-line ping-pong between the xmit path and the * completion path. * @tso_bursts: Number of times TSO xmit invoked by kernel * @tso_long_headers: Number of packets with headers too long for standard * blocks * @tso_packets: Number of packets via the TSO xmit path * @tso_fallbacks: Number of times TSO fallback used * @pushes: Number of times the TX push feature has been used * @pio_packets: Number of times the TX PIO feature has been used * @xmit_pending: Are any packets waiting to be pushed to the NIC * @cb_packets: Number of times the TX copybreak feature has been used * @notify_count: Count of notified descriptors to the NIC * @empty_read_count: If the completion path has seen the queue as empty * and the transmission path has not yet checked this, the value of * @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0. */ struct efx_tx_queue { … }; #define EFX_TX_CB_ORDER … #define EFX_TX_CB_SIZE … /** * struct efx_rx_buffer - An Efx RX data buffer * @dma_addr: DMA base address of the buffer * @page: The associated page buffer. * Will be %NULL if the buffer slot is currently free. * @page_offset: If pending: offset in @page of DMA base address. * If completed: offset in @page of Ethernet header. * @len: If pending: length for DMA descriptor. * If completed: received length, excluding hash prefix. * @flags: Flags for buffer and packet state. These are only set on the * first buffer of a scattered packet. */ struct efx_rx_buffer { … }; #define EFX_RX_BUF_LAST_IN_PAGE … #define EFX_RX_PKT_CSUMMED … #define EFX_RX_PKT_DISCARD … #define EFX_RX_PKT_TCP … #define EFX_RX_PKT_PREFIX_LEN … #define EFX_RX_PKT_CSUM_LEVEL … /** * struct efx_rx_page_state - Page-based rx buffer state * * Inserted at the start of every page allocated for receive buffers. * Used to facilitate sharing dma mappings between recycled rx buffers * and those passed up to the kernel. * * @dma_addr: The dma address of this page. */ struct efx_rx_page_state { … }; /** * struct efx_rx_queue - An Efx RX queue * @efx: The associated Efx NIC * @core_index: Index of network core RX queue. Will be >= 0 iff this * is associated with a real RX queue. * @buffer: The software buffer ring * @rxd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. * @refill_enabled: Enable refill whenever fill level is low * @flush_pending: Set when a RX flush is pending. Has the same lifetime as * @rxq_flush_pending. * @grant_credits: Posted RX descriptors need to be granted to the MAE with * %MC_CMD_MAE_COUNTERS_STREAM_GIVE_CREDITS. For %EFX_EXTRA_CHANNEL_TC, * and only supported on EF100. * @added_count: Number of buffers added to the receive queue. * @notified_count: Number of buffers given to NIC (<= @added_count). * @granted_count: Number of buffers granted to the MAE (<= @notified_count). * @removed_count: Number of buffers removed from the receive queue. * @scatter_n: Used by NIC specific receive code. * @scatter_len: Used by NIC specific receive code. * @page_ring: The ring to store DMA mapped pages for reuse. * @page_add: Counter to calculate the write pointer for the recycle ring. * @page_remove: Counter to calculate the read pointer for the recycle ring. * @page_recycle_count: The number of pages that have been recycled. * @page_recycle_failed: The number of pages that couldn't be recycled because * the kernel still held a reference to them. * @page_recycle_full: The number of pages that were released because the * recycle ring was full. * @page_ptr_mask: The number of pages in the RX recycle ring minus 1. * @max_fill: RX descriptor maximum fill level (<= ring size) * @fast_fill_trigger: RX descriptor fill level that will trigger a fast fill * (<= @max_fill) * @min_fill: RX descriptor minimum non-zero fill level. * This records the minimum fill level observed when a ring * refill was triggered. * @recycle_count: RX buffer recycle counter. * @slow_fill: Timer used to defer efx_nic_generate_fill_event(). * @grant_work: workitem used to grant credits to the MAE if @grant_credits * @xdp_rxq_info: XDP specific RX queue information. * @xdp_rxq_info_valid: Is xdp_rxq_info valid data?. */ struct efx_rx_queue { … }; enum efx_sync_events_state { … }; /** * struct efx_channel - An Efx channel * * A channel comprises an event queue, at least one TX queue, at least * one RX queue, and an associated tasklet for processing the event * queue. * * @efx: Associated Efx NIC * @channel: Channel instance number * @type: Channel type definition * @eventq_init: Event queue initialised flag * @enabled: Channel enabled indicator * @irq: IRQ number (MSI and MSI-X only) * @irq_moderation_us: IRQ moderation value (in microseconds) * @napi_dev: Net device used with NAPI * @napi_str: NAPI control structure * @state: state for NAPI vs busy polling * @state_lock: lock protecting @state * @eventq: Event queue buffer * @eventq_mask: Event queue pointer mask * @eventq_read_ptr: Event queue read pointer * @event_test_cpu: Last CPU to handle interrupt or test event for this channel * @irq_count: Number of IRQs since last adaptive moderation decision * @irq_mod_score: IRQ moderation score * @rfs_filter_count: number of accelerated RFS filters currently in place; * equals the count of @rps_flow_id slots filled * @rfs_last_expiry: value of jiffies last time some accelerated RFS filters * were checked for expiry * @rfs_expire_index: next accelerated RFS filter ID to check for expiry * @n_rfs_succeeded: number of successful accelerated RFS filter insertions * @n_rfs_failed: number of failed accelerated RFS filter insertions * @filter_work: Work item for efx_filter_rfs_expire() * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS, * indexed by filter ID * @n_rx_tobe_disc: Count of RX_TOBE_DISC errors * @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors * @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors * @n_rx_mcast_mismatch: Count of unmatched multicast frames * @n_rx_frm_trunc: Count of RX_FRM_TRUNC errors * @n_rx_overlength: Count of RX_OVERLENGTH errors * @n_skbuff_leaks: Count of skbuffs leaked due to RX overrun * @n_rx_nodesc_trunc: Number of RX packets truncated and then dropped due to * lack of descriptors * @n_rx_merge_events: Number of RX merged completion events * @n_rx_merge_packets: Number of RX packets completed by merged events * @n_rx_xdp_drops: Count of RX packets intentionally dropped due to XDP * @n_rx_xdp_bad_drops: Count of RX packets dropped due to XDP errors * @n_rx_xdp_tx: Count of RX packets retransmitted due to XDP * @n_rx_xdp_redirect: Count of RX packets redirected to a different NIC by XDP * @n_rx_mport_bad: Count of RX packets dropped because their ingress mport was * not recognised * @rx_pkt_n_frags: Number of fragments in next packet to be delivered by * __efx_rx_packet(), or zero if there is none * @rx_pkt_index: Ring index of first buffer for next packet to be delivered * by __efx_rx_packet(), if @rx_pkt_n_frags != 0 * @rx_list: list of SKBs from current RX, awaiting processing * @rx_queue: RX queue for this channel * @tx_queue: TX queues for this channel * @tx_queue_by_type: pointers into @tx_queue, or %NULL, indexed by txq type * @sync_events_state: Current state of sync events on this channel * @sync_timestamp_major: Major part of the last ptp sync event * @sync_timestamp_minor: Minor part of the last ptp sync event */ struct efx_channel { … }; /** * struct efx_msi_context - Context for each MSI * @efx: The associated NIC * @index: Index of the channel/IRQ * @name: Name of the channel/IRQ * * Unlike &struct efx_channel, this is never reallocated and is always * safe for the IRQ handler to access. */ struct efx_msi_context { … }; /** * struct efx_channel_type - distinguishes traffic and extra channels * @handle_no_channel: Handle failure to allocate an extra channel * @pre_probe: Set up extra state prior to initialisation * @start: called early in efx_start_channels() * @stop: called early in efx_stop_channels() * @post_remove: Tear down extra state after finalisation, if allocated. * May be called on channels that have not been probed. * @get_name: Generate the channel's name (used for its IRQ handler) * @copy: Copy the channel state prior to reallocation. May be %NULL if * reallocation is not supported. * @receive_skb: Handle an skb ready to be passed to netif_receive_skb() * @receive_raw: Handle an RX buffer ready to be passed to __efx_rx_packet() * @want_txqs: Determine whether this channel should have TX queues * created. If %NULL, TX queues are not created. * @keep_eventq: Flag for whether event queue should be kept initialised * while the device is stopped * @want_pio: Flag for whether PIO buffers should be linked to this * channel's TX queues. */ struct efx_channel_type { … }; enum efx_led_mode { … }; #define STRING_TABLE_LOOKUP(val, member) … extern const char *const efx_loopback_mode_names[]; extern const unsigned int efx_loopback_mode_max; #define LOOPBACK_MODE(efx) … enum efx_int_mode { … }; #define EFX_INT_MODE_USE_MSI(x) … enum nic_state { … }; static inline bool efx_net_active(enum nic_state state) { … } static inline bool efx_frozen(enum nic_state state) { … } static inline bool efx_recovering(enum nic_state state) { … } static inline enum nic_state efx_freeze(enum nic_state state) { … } static inline enum nic_state efx_thaw(enum nic_state state) { … } static inline enum nic_state efx_recover(enum nic_state state) { … } static inline enum nic_state efx_recovered(enum nic_state state) { … } /* Forward declaration */ struct efx_nic; /* Pseudo bit-mask flow control field */ #define EFX_FC_RX … #define EFX_FC_TX … #define EFX_FC_AUTO … /** * struct efx_link_state - Current state of the link * @up: Link is up * @fd: Link is full-duplex * @fc: Actual flow control flags * @speed: Link speed (Mbps) */ struct efx_link_state { … }; static inline bool efx_link_state_equal(const struct efx_link_state *left, const struct efx_link_state *right) { … } /** * enum efx_phy_mode - PHY operating mode flags * @PHY_MODE_NORMAL: on and should pass traffic * @PHY_MODE_TX_DISABLED: on with TX disabled * @PHY_MODE_LOW_POWER: set to low power through MDIO * @PHY_MODE_OFF: switched off through external control * @PHY_MODE_SPECIAL: on but will not pass traffic */ enum efx_phy_mode { … }; static inline bool efx_phy_mode_disabled(enum efx_phy_mode mode) { … } /** * struct efx_hw_stat_desc - Description of a hardware statistic * @name: Name of the statistic as visible through ethtool, or %NULL if * it should not be exposed * @dma_width: Width in bits (0 for non-DMA statistics) * @offset: Offset within stats (ignored for non-DMA statistics) */ struct efx_hw_stat_desc { … }; struct vfdi_status; /* The reserved RSS context value */ #define EFX_MCDI_RSS_CONTEXT_INVALID … /** * struct efx_rss_context_priv - driver private data for an RSS context * @context_id: the RSS_CONTEXT_ID returned by MC firmware, or * %EFX_MCDI_RSS_CONTEXT_INVALID if this context is not present on the NIC. * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled */ struct efx_rss_context_priv { … }; /** * struct efx_rss_context - an RSS context * @priv: hardware-specific state * @rx_hash_key: Toeplitz hash key for this RSS context * @indir_table: Indirection table for this RSS context */ struct efx_rss_context { … }; #ifdef CONFIG_RFS_ACCEL /* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING * is used to test if filter does or will exist. */ #define EFX_ARFS_FILTER_ID_PENDING … #define EFX_ARFS_FILTER_ID_ERROR … #define EFX_ARFS_FILTER_ID_REMOVING … /** * struct efx_arfs_rule - record of an ARFS filter and its IDs * @node: linkage into hash table * @spec: details of the filter (used as key for hash table). Use efx->type to * determine which member to use. * @rxq_index: channel to which the filter will steer traffic. * @arfs_id: filter ID which was returned to ARFS * @filter_id: index in software filter table. May be * %EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet, * %EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or * %EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter. */ struct efx_arfs_rule { … }; /* Size chosen so that the table is one page (4kB) */ #define EFX_ARFS_HASH_TABLE_SIZE … /** * struct efx_async_filter_insertion - Request to asynchronously insert a filter * @net_dev: Reference to the netdevice * @spec: The filter to insert * @work: Workitem for this request * @rxq_index: Identifies the channel for which this request was made * @flow_id: Identifies the kernel-side flow for which this request was made */ struct efx_async_filter_insertion { … }; /* Maximum number of ARFS workitems that may be in flight on an efx_nic */ #define EFX_RPS_MAX_IN_FLIGHT … #endif /* CONFIG_RFS_ACCEL */ enum efx_xdp_tx_queues_mode { … }; struct efx_mae; /** * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) * @pci_dev: The PCI device * @node: List node for maintaning primary/secondary function lists * @primary: &struct efx_nic instance for the primary function of this * controller. May be the same structure, and may be %NULL if no * primary function is bound. Serialised by rtnl_lock. * @secondary_list: List of &struct efx_nic instances for the secondary PCI * functions of the controller, if this is for the primary function. * Serialised by rtnl_lock. * @type: Controller type attributes * @legacy_irq: IRQ number * @workqueue: Workqueue for port reconfigures and the HW monitor. * Work items do not hold and must not acquire RTNL. * @workqueue_name: Name of workqueue * @reset_work: Scheduled reset workitem * @membase_phys: Memory BAR value as physical address * @membase: Memory BAR value * @vi_stride: step between per-VI registers / memory regions * @interrupt_mode: Interrupt mode * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds * @timer_max_ns: Interrupt timer maximum value, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues * @irqs_hooked: Channel interrupts are hooked * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues * @irq_rx_moderation_us: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags * @state: Device state number (%STATE_*). Serialised by the rtnl_lock. * @reset_pending: Bitmask for pending resets * @tx_queue: TX DMA queues * @rx_queue: RX DMA queues * @channel: Channels * @msi_context: Context for each MSI * @extra_channel_types: Types of extra (non-traffic) channels that * should be allocated for this NIC * @mae: Details of the Match Action Engine * @xdp_tx_queue_count: Number of entries in %xdp_tx_queues. * @xdp_tx_queues: Array of pointers to tx queues used for XDP transmit. * @xdp_txq_queues_mode: XDP TX queues sharing strategy. * @rxq_entries: Size of receive queues requested by user. * @txq_entries: Size of transmit queues requested by user. * @txq_stop_thresh: TX queue fill level at or above which we stop it. * @txq_wake_thresh: TX queue fill level at or below which we wake it. * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches * @sram_lim_qw: Qword address limit of SRAM * @n_channels: Number of channels in use * @n_rx_channels: Number of channels used for RX (= number of RX queues) * @n_tx_channels: Number of channels used for TX * @n_extra_tx_channels: Number of extra channels with TX queues * @tx_queues_per_channel: number of TX queues probed on each channel * @n_xdp_channels: Number of channels used for XDP TX * @xdp_channel_offset: Offset of zeroth channel used for XPD TX. * @xdp_tx_per_channel: Max number of TX queues on an XDP TX channel. * @rx_ip_align: RX DMA address offset to have IP header aligned in * in accordance with NET_IP_ALIGN * @rx_dma_len: Current maximum RX DMA length * @rx_buffer_order: Order (log2) of number of pages for each RX buffer * @rx_buffer_truesize: Amortised allocation size of an RX buffer, * for use in sk_buff::truesize * @rx_prefix_size: Size of RX prefix before packet data * @rx_packet_hash_offset: Offset of RX flow hash from start of packet data * (valid only if @rx_prefix_size != 0; always negative) * @rx_packet_len_offset: Offset of RX packet length from start of packet data * (valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative) * @rx_packet_ts_offset: Offset of timestamp from start of packet data * (valid only if channel->sync_timestamps_enabled; always negative) * @rx_scatter: Scatter mode enabled for receives * @rss_context: Main RSS context. * @vport_id: The function's vport ID, only relevant for PFs * @int_error_count: Number of internal errors seen recently * @int_error_expire: Time at which error count will be expired * @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot * @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will * acknowledge but do nothing else. * @irq_status: Interrupt status buffer * @irq_zero_count: Number of legacy IRQs seen with queue flags == 0 * @irq_level: IRQ level/index for IRQs not triggered by an event queue * @selftest_work: Work item for asynchronous self-test * @mtd_list: List of MTDs attached to the NIC * @nic_data: Hardware dependent state * @mcdi: Management-Controller-to-Driver Interface state * @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode, * efx_monitor() and efx_reconfigure_port() * @port_enabled: Port enabled indicator. * Serialises efx_stop_all(), efx_start_all(), efx_monitor() and * efx_mac_work() with kernel interfaces. Safe to read under any * one of the rtnl_lock, mac_lock, or netif_tx_lock, but all three must * be held to modify it. * @port_initialized: Port initialized? * @net_dev: Operating system network device. Consider holding the rtnl lock * @fixed_features: Features which cannot be turned off * @num_mac_stats: Number of MAC stats reported by firmware (MAC_STATS_NUM_STATS * field of %MC_CMD_GET_CAPABILITIES_V4 response, or %MC_CMD_MAC_NSTATS) * @stats_buffer: DMA buffer for statistics * @phy_type: PHY type * @phy_data: PHY private data (including PHY-specific stats) * @mdio: PHY MDIO interface * @mdio_bus: PHY MDIO bus ID (only used by Siena) * @phy_mode: PHY operating mode. Serialised by @mac_lock. * @link_advertising: Autonegotiation advertising flags * @fec_config: Forward Error Correction configuration flags. For bit positions * see &enum ethtool_fec_config_bits. * @link_state: Current state of the link * @n_link_state_changes: Number of times the link has changed state * @wanted_fc: Wanted flow control flags * @fc_disable: When non-zero flow control is disabled. Typically used to * ensure that network back pressure doesn't delay dma queue flushes. * Serialised by the rtnl lock. * @mac_work: Work item for changing MAC promiscuity and multicast hash * @loopback_mode: Loopback status * @loopback_modes: Supported loopback mode bitmask * @loopback_selftest: Offline self-test private state * @xdp_prog: Current XDP programme for this interface * @filter_sem: Filter table rw_semaphore, protects existence of @filter_state * @filter_state: Architecture-dependent filter table state * @rps_mutex: Protects RPS state of all channels * @rps_slot_map: bitmap of in-flight entries in @rps_slot * @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work() * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and * @rps_next_id). * @rps_hash_table: Mapping between ARFS filters and their various IDs * @rps_next_id: next arfs_id for an ARFS filter * @active_queues: Count of RX and TX queues that haven't been flushed and drained. * @rxq_flush_pending: Count of number of receive queues that need to be flushed. * Decremented when the efx_flush_rx_queue() is called. * @rxq_flush_outstanding: Count of number of RX flushes started but not yet * completed (either success or failure). Not used when MCDI is used to * flush receive queues. * @flush_wq: wait queue used by efx_nic_flush_queues() to wait for flush completions. * @vf_count: Number of VFs intended to be enabled. * @vf_init_count: Number of VFs that have been fully initialised. * @vi_scale: log2 number of vnics per VF. * @vf_reps_lock: Protects vf_reps list * @vf_reps: local VF reps * @ptp_data: PTP state data * @ptp_warned: has this NIC seen and warned about unexpected PTP events? * @vpd_sn: Serial number read from VPD * @xdp_rxq_info_failed: Have any of the rx queues failed to initialise their * xdp_rxq_info structures? * @netdev_notifier: Netdevice notifier. * @netevent_notifier: Netevent notifier (for neighbour updates). * @tc: state for TC offload (EF100). * @devlink: reference to devlink structure owned by this device * @dl_port: devlink port associated with the PF * @mem_bar: The BAR that is mapped into membase. * @reg_base: Offset from the start of the bar to the function control window. * @monitor_work: Hardware monitor workitem * @biu_lock: BIU (bus interface unit) lock * @last_irq_cpu: Last CPU to handle a possible test interrupt. This * field is used by efx_test_interrupts() to verify that an * interrupt has occurred. * @stats_lock: Statistics update lock. Must be held when calling * efx_nic_type::{update,start,stop}_stats. * @n_rx_noskb_drops: Count of RX packets dropped due to failure to allocate an skb * * This is stored in the private area of the &struct net_device. */ struct efx_nic { … }; /** * struct efx_probe_data - State after hardware probe * @pci_dev: The PCI device * @efx: Efx NIC details */ struct efx_probe_data { … }; static inline struct efx_nic *efx_netdev_priv(struct net_device *dev) { … } static inline int efx_dev_registered(struct efx_nic *efx) { … } static inline unsigned int efx_port_num(struct efx_nic *efx) { … } struct efx_mtd_partition { … }; struct efx_udp_tunnel { … }; /** * struct efx_nic_type - Efx device type definition * @mem_bar: Get the memory BAR * @mem_map_size: Get memory BAR mapped size * @probe: Probe the controller * @remove: Free resources allocated by probe() * @init: Initialise the controller * @dimension_resources: Dimension controller resources (buffer table, * and VIs once the available interrupt resources are clear) * @fini: Shut down the controller * @monitor: Periodic function for polling link state and hardware monitor * @map_reset_reason: Map ethtool reset reason to a reset method * @map_reset_flags: Map ethtool reset flags to a reset method, if possible * @reset: Reset the controller hardware and possibly the PHY. This will * be called while the controller is uninitialised. * @probe_port: Probe the MAC and PHY * @remove_port: Free resources allocated by probe_port() * @handle_global_event: Handle a "global" event (may be %NULL) * @fini_dmaq: Flush and finalise DMA queues (RX and TX queues) * @prepare_flr: Prepare for an FLR * @finish_flr: Clean up after an FLR * @describe_stats: Describe statistics for ethtool * @update_stats: Update statistics not provided by event handling. * Either argument may be %NULL. * @update_stats_atomic: Update statistics while in atomic context, if that * is more limiting than @update_stats. Otherwise, leave %NULL and * driver core will call @update_stats. * @start_stats: Start the regular fetching of statistics * @pull_stats: Pull stats from the NIC and wait until they arrive. * @stop_stats: Stop the regular fetching of statistics * @push_irq_moderation: Apply interrupt moderation value * @reconfigure_port: Push loopback/power/txdis changes to the MAC and PHY * @prepare_enable_fc_tx: Prepare MAC to enable pause frame TX (may be %NULL) * @reconfigure_mac: Push MAC address, MTU, flow control and filter settings * to the hardware. Serialised by the mac_lock. * @check_mac_fault: Check MAC fault state. True if fault present. * @get_wol: Get WoL configuration from driver state * @set_wol: Push WoL configuration to the NIC * @resume_wol: Synchronise WoL state between driver and MC (e.g. after resume) * @get_fec_stats: Get standard FEC statistics. * @test_chip: Test registers. This is expected to reset the NIC. * @test_nvram: Test validity of NVRAM contents * @mcdi_request: Send an MCDI request with the given header and SDU. * The SDU length may be any value from 0 up to the protocol- * defined maximum, but its buffer will be padded to a multiple * of 4 bytes. * @mcdi_poll_response: Test whether an MCDI response is available. * @mcdi_read_response: Read the MCDI response PDU. The offset will * be a multiple of 4. The length may not be, but the buffer * will be padded so it is safe to round up. * @mcdi_poll_reboot: Test whether the MCDI has rebooted. If so, * return an appropriate error code for aborting any current * request; otherwise return 0. * @irq_enable_master: Enable IRQs on the NIC. Each event queue must * be separately enabled after this. * @irq_test_generate: Generate a test IRQ * @irq_disable_non_ev: Disable non-event IRQs on the NIC. Each event * queue must be separately disabled before this. * @irq_handle_msi: Handle MSI for a channel. The @dev_id argument is * a pointer to the &struct efx_msi_context for the channel. * @irq_handle_legacy: Handle legacy interrupt. The @dev_id argument * is a pointer to the &struct efx_nic. * @tx_probe: Allocate resources for TX queue (and select TXQ type) * @tx_init: Initialise TX queue on the NIC * @tx_remove: Free resources for TX queue * @tx_write: Write TX descriptors and doorbell * @tx_enqueue: Add an SKB to TX queue * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC * @rx_pull_rss_config: Read RSS hash key and indirection table back from the NIC * @rx_push_rss_context_config: Write RSS hash key and indirection table for * user RSS context to the NIC * @rx_pull_rss_context_config: Read RSS hash key and indirection table for user * RSS context back from the NIC * @rx_probe: Allocate resources for RX queue * @rx_init: Initialise RX queue on the NIC * @rx_remove: Free resources for RX queue * @rx_write: Write RX descriptors and doorbell * @rx_defer_refill: Generate a refill reminder event * @rx_packet: Receive the queued RX buffer on a channel * @rx_buf_hash_valid: Determine whether the RX prefix contains a valid hash * @ev_probe: Allocate resources for event queue * @ev_init: Initialise event queue on the NIC * @ev_fini: Deinitialise event queue on the NIC * @ev_remove: Free resources for event queue * @ev_process: Process events for a queue, up to the given NAPI quota * @ev_read_ack: Acknowledge read events on a queue, rearming its IRQ * @ev_test_generate: Generate a test event * @filter_table_probe: Probe filter capabilities and set up filter software state * @filter_table_restore: Restore filters removed from hardware * @filter_table_remove: Remove filters from hardware and tear down software state * @filter_update_rx_scatter: Update filters after change to rx scatter setting * @filter_insert: add or replace a filter * @filter_remove_safe: remove a filter by ID, carefully * @filter_get_safe: retrieve a filter by ID, carefully * @filter_clear_rx: Remove all RX filters whose priority is less than or * equal to the given priority and is not %EFX_FILTER_PRI_AUTO * @filter_count_rx_used: Get the number of filters in use at a given priority * @filter_get_rx_id_limit: Get maximum value of a filter id, plus 1 * @filter_get_rx_ids: Get list of RX filters at a given priority * @filter_rfs_expire_one: Consider expiring a filter inserted for RFS. * This must check whether the specified table entry is used by RFS * and that rps_may_expire_flow() returns true for it. * @mtd_probe: Probe and add MTD partitions associated with this net device, * using efx_mtd_add() * @mtd_rename: Set an MTD partition name using the net device name * @mtd_read: Read from an MTD partition * @mtd_erase: Erase part of an MTD partition * @mtd_write: Write to an MTD partition * @mtd_sync: Wait for write-back to complete on MTD partition. This * also notifies the driver that a writer has finished using this * partition. * @ptp_write_host_time: Send host time to MC as part of sync protocol * @ptp_set_ts_sync_events: Enable or disable sync events for inline RX * timestamping, possibly only temporarily for the purposes of a reset. * @ptp_set_ts_config: Set hardware timestamp configuration. The flags * and tx_type will already have been validated but this operation * must validate and update rx_filter. * @get_phys_port_id: Get the underlying physical port id. * @set_mac_address: Set the MAC address of the device * @tso_versions: Returns mask of firmware-assisted TSO versions supported. * If %NULL, then device does not support any TSO version. * @udp_tnl_push_ports: Push the list of UDP tunnel ports to the NIC if required. * @udp_tnl_has_port: Check if a port has been added as UDP tunnel * @print_additional_fwver: Dump NIC-specific additional FW version info * @sensor_event: Handle a sensor event from MCDI * @rx_recycle_ring_size: Size of the RX recycle ring * @revision: Hardware architecture revision * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address * @buf_tbl_base: Buffer table base address * @evq_ptr_tbl_base: Event queue pointer table base address * @evq_rptr_tbl_base: Event queue read-pointer table base address * @max_dma_mask: Maximum possible DMA mask * @rx_prefix_size: Size of RX prefix before packet data * @rx_hash_offset: Offset of RX flow hash within prefix * @rx_ts_offset: Offset of timestamp within prefix * @rx_buffer_padding: Size of padding at end of RX packet * @can_rx_scatter: NIC is able to scatter packets to multiple buffers * @always_rx_scatter: NIC will always scatter packets to multiple buffers * @option_descriptors: NIC supports TX option descriptors * @min_interrupt_mode: Lowest capability interrupt mode supported * from &enum efx_int_mode. * @timer_period_max: Maximum period of interrupt timer (in ticks) * @offload_features: net_device feature flags for protocol offload * features implemented in hardware * @mcdi_max_ver: Maximum MCDI version supported * @hwtstamp_filters: Mask of hardware timestamp filter types supported */ struct efx_nic_type { … }; /************************************************************************** * * Prototypes and inline functions * *************************************************************************/ static inline struct efx_channel * efx_get_channel(struct efx_nic *efx, unsigned index) { … } /* Iterate over all used channels */ #define efx_for_each_channel(_channel, _efx) … /* Iterate over all used channels in reverse */ #define efx_for_each_channel_rev(_channel, _efx) … static inline struct efx_channel * efx_get_tx_channel(struct efx_nic *efx, unsigned int index) { … } static inline struct efx_channel * efx_get_xdp_channel(struct efx_nic *efx, unsigned int index) { … } static inline bool efx_channel_is_xdp_tx(struct efx_channel *channel) { … } static inline bool efx_channel_has_tx_queues(struct efx_channel *channel) { … } static inline unsigned int efx_channel_num_tx_queues(struct efx_channel *channel) { … } static inline struct efx_tx_queue * efx_channel_get_tx_queue(struct efx_channel *channel, unsigned int type) { … } static inline struct efx_tx_queue * efx_get_tx_queue(struct efx_nic *efx, unsigned int index, unsigned int type) { … } /* Iterate over all TX queues belonging to a channel */ #define efx_for_each_channel_tx_queue(_tx_queue, _channel) … static inline bool efx_channel_has_rx_queue(struct efx_channel *channel) { … } static inline struct efx_rx_queue * efx_channel_get_rx_queue(struct efx_channel *channel) { … } /* Iterate over all RX queues belonging to a channel */ #define efx_for_each_channel_rx_queue(_rx_queue, _channel) … static inline struct efx_channel * efx_rx_queue_channel(struct efx_rx_queue *rx_queue) { … } static inline int efx_rx_queue_index(struct efx_rx_queue *rx_queue) { … } /* Returns a pointer to the specified receive buffer in the RX * descriptor queue. */ static inline struct efx_rx_buffer *efx_rx_buffer(struct efx_rx_queue *rx_queue, unsigned int index) { … } static inline struct efx_rx_buffer * efx_rx_buf_next(struct efx_rx_queue *rx_queue, struct efx_rx_buffer *rx_buf) { … } /** * EFX_MAX_FRAME_LEN - calculate maximum frame length * * This calculates the maximum frame length that will be used for a * given MTU. The frame length will be equal to the MTU plus a * constant amount of header space and padding. This is the quantity * that the net driver will program into the MAC as the maximum frame * length. * * The 10G MAC requires 8-byte alignment on the frame * length, so we round up to the nearest 8. * * Re-clocking by the XGXS on RX can reduce an IPG to 32 bits (half an * XGMII cycle). If the frame length reaches the maximum value in the * same cycle, the XMAC can miss the IPG altogether. We work around * this by adding a further 16 bytes. */ #define EFX_FRAME_PAD … #define EFX_MAX_FRAME_LEN(mtu) … static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb) { … } static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb) { … } /* Get the max fill level of the TX queues on this channel */ static inline unsigned int efx_channel_tx_fill_level(struct efx_channel *channel) { … } /* Conservative approximation of efx_channel_tx_fill_level using cached value */ static inline unsigned int efx_channel_tx_old_fill_level(struct efx_channel *channel) { … } /* Get all supported features. * If a feature is not fixed, it is present in hw_features. * If a feature is fixed, it does not present in hw_features, but * always in features. */ static inline netdev_features_t efx_supported_features(const struct efx_nic *efx) { … } /* Get the current TX queue insert index. */ static inline unsigned int efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue) { … } /* Get a TX buffer. */ static inline struct efx_tx_buffer * __efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue) { … } /* Get a TX buffer, checking it's not currently in use. */ static inline struct efx_tx_buffer * efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue) { … } #endif /* EFX_NET_DRIVER_H */