1/* SPDX-License-Identifier: GPL-2.0 */ 2/* Copyright (c) 2018, Intel Corporation. */ 3 4#ifndef _ICE_TXRX_H_ 5#define _ICE_TXRX_H_ 6 7#include "ice_type.h" 8 9#define ICE_DFLT_IRQ_WORK 256 10#define ICE_RXBUF_3072 3072 11#define ICE_RXBUF_2048 2048 12#define ICE_RXBUF_1664 1664 13#define ICE_RXBUF_1536 1536 14#define ICE_MAX_CHAINED_RX_BUFS 5 15#define ICE_MAX_BUF_TXD 8 16#define ICE_MIN_TX_LEN 17 17#define ICE_MAX_FRAME_LEGACY_RX 8320 18 19/* The size limit for a transmit buffer in a descriptor is (16K - 1). 20 * In order to align with the read requests we will align the value to 21 * the nearest 4K which represents our maximum read request size. 22 */ 23#define ICE_MAX_READ_REQ_SIZE 4096 24#define ICE_MAX_DATA_PER_TXD (16 * 1024 - 1) 25#define ICE_MAX_DATA_PER_TXD_ALIGNED \ 26 (~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD) 27 28#define ICE_MAX_TXQ_PER_TXQG 128 29 30/* Attempt to maximize the headroom available for incoming frames. We use a 2K 31 * buffer for MTUs <= 1500 and need 1536/1534 to store the data for the frame. 32 * This leaves us with 512 bytes of room. From that we need to deduct the 33 * space needed for the shared info and the padding needed to IP align the 34 * frame. 35 * 36 * Note: For cache line sizes 256 or larger this value is going to end 37 * up negative. In these cases we should fall back to the legacy 38 * receive path. 39 */ 40#if (PAGE_SIZE < 8192) 41#define ICE_2K_TOO_SMALL_WITH_PADDING \ 42 ((unsigned int)(NET_SKB_PAD + ICE_RXBUF_1536) > \ 43 SKB_WITH_OVERHEAD(ICE_RXBUF_2048)) 44 45/** 46 * ice_compute_pad - compute the padding 47 * @rx_buf_len: buffer length 48 * 49 * Figure out the size of half page based on given buffer length and 50 * then subtract the skb_shared_info followed by subtraction of the 51 * actual buffer length; this in turn results in the actual space that 52 * is left for padding usage 53 */ 54static inline int ice_compute_pad(int rx_buf_len) 55{ 56 int half_page_size; 57 58 half_page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); 59 return SKB_WITH_OVERHEAD(half_page_size) - rx_buf_len; 60} 61 62/** 63 * ice_skb_pad - determine the padding that we can supply 64 * 65 * Figure out the right Rx buffer size and based on that calculate the 66 * padding 67 */ 68static inline int ice_skb_pad(void) 69{ 70 int rx_buf_len; 71 72 /* If a 2K buffer cannot handle a standard Ethernet frame then 73 * optimize padding for a 3K buffer instead of a 1.5K buffer. 74 * 75 * For a 3K buffer we need to add enough padding to allow for 76 * tailroom due to NET_IP_ALIGN possibly shifting us out of 77 * cache-line alignment. 78 */ 79 if (ICE_2K_TOO_SMALL_WITH_PADDING) 80 rx_buf_len = ICE_RXBUF_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); 81 else 82 rx_buf_len = ICE_RXBUF_1536; 83 84 /* if needed make room for NET_IP_ALIGN */ 85 rx_buf_len -= NET_IP_ALIGN; 86 87 return ice_compute_pad(rx_buf_len); 88} 89 90#define ICE_SKB_PAD ice_skb_pad() 91#else 92#define ICE_2K_TOO_SMALL_WITH_PADDING false 93#define ICE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) 94#endif 95 96/* We are assuming that the cache line is always 64 Bytes here for ice. 97 * In order to make sure that is a correct assumption there is a check in probe 98 * to print a warning if the read from GLPCI_CNF2 tells us that the cache line 99 * size is 128 bytes. We do it this way because we do not want to read the 100 * GLPCI_CNF2 register or a variable containing the value on every pass through 101 * the Tx path. 102 */ 103#define ICE_CACHE_LINE_BYTES 64 104#define ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \ 105 sizeof(struct ice_tx_desc)) 106#define ICE_DESCS_FOR_CTX_DESC 1 107#define ICE_DESCS_FOR_SKB_DATA_PTR 1 108/* Tx descriptors needed, worst case */ 109#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \ 110 ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR) 111#define ICE_DESC_UNUSED(R) \ 112 (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ 113 (R)->next_to_clean - (R)->next_to_use - 1) 114 115#define ICE_RX_DESC_UNUSED(R) \ 116 ((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \ 117 (R)->first_desc - (R)->next_to_use - 1) 118 119#define ICE_RING_QUARTER(R) ((R)->count >> 2) 120 121#define ICE_TX_FLAGS_TSO BIT(0) 122#define ICE_TX_FLAGS_HW_VLAN BIT(1) 123#define ICE_TX_FLAGS_SW_VLAN BIT(2) 124/* Free, was ICE_TX_FLAGS_DUMMY_PKT */ 125#define ICE_TX_FLAGS_TSYN BIT(4) 126#define ICE_TX_FLAGS_IPV4 BIT(5) 127#define ICE_TX_FLAGS_IPV6 BIT(6) 128#define ICE_TX_FLAGS_TUNNEL BIT(7) 129#define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) 130 131#define ICE_XDP_PASS 0 132#define ICE_XDP_CONSUMED BIT(0) 133#define ICE_XDP_TX BIT(1) 134#define ICE_XDP_REDIR BIT(2) 135#define ICE_XDP_EXIT BIT(3) 136#define ICE_SKB_CONSUMED ICE_XDP_CONSUMED 137 138#define ICE_RX_DMA_ATTR \ 139 (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) 140 141#define ICE_ETH_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) 142 143#define ICE_TXD_LAST_DESC_CMD (ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS) 144 145/** 146 * enum ice_tx_buf_type - type of &ice_tx_buf to act on Tx completion 147 * @ICE_TX_BUF_EMPTY: unused OR XSk frame, no action required 148 * @ICE_TX_BUF_DUMMY: dummy Flow Director packet, unmap and kfree() 149 * @ICE_TX_BUF_FRAG: mapped skb OR &xdp_buff frag, only unmap DMA 150 * @ICE_TX_BUF_SKB: &sk_buff, unmap and consume_skb(), update stats 151 * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free(), stats 152 * @ICE_TX_BUF_XDP_XMIT: &xdp_frame, unmap and xdp_return_frame(), stats 153 * @ICE_TX_BUF_XSK_TX: &xdp_buff on XSk queue, xsk_buff_free(), stats 154 */ 155enum ice_tx_buf_type { 156 ICE_TX_BUF_EMPTY = 0U, 157 ICE_TX_BUF_DUMMY, 158 ICE_TX_BUF_FRAG, 159 ICE_TX_BUF_SKB, 160 ICE_TX_BUF_XDP_TX, 161 ICE_TX_BUF_XDP_XMIT, 162 ICE_TX_BUF_XSK_TX, 163}; 164 165struct ice_tx_buf { 166 union { 167 struct ice_tx_desc *next_to_watch; 168 u32 rs_idx; 169 }; 170 union { 171 void *raw_buf; /* used for XDP_TX and FDir rules */ 172 struct sk_buff *skb; /* used for .ndo_start_xmit() */ 173 struct xdp_frame *xdpf; /* used for .ndo_xdp_xmit() */ 174 struct xdp_buff *xdp; /* used for XDP_TX ZC */ 175 }; 176 unsigned int bytecount; 177 union { 178 unsigned int gso_segs; 179 unsigned int nr_frags; /* used for mbuf XDP */ 180 }; 181 u32 tx_flags:12; 182 u32 type:4; /* &ice_tx_buf_type */ 183 u32 vid:16; 184 DEFINE_DMA_UNMAP_LEN(len); 185 DEFINE_DMA_UNMAP_ADDR(dma); 186}; 187 188struct ice_tx_offload_params { 189 u64 cd_qw1; 190 struct ice_tx_ring *tx_ring; 191 u32 td_cmd; 192 u32 td_offset; 193 u32 td_l2tag1; 194 u32 cd_tunnel_params; 195 u16 cd_l2tag2; 196 u8 header_len; 197}; 198 199struct ice_rx_buf { 200 dma_addr_t dma; 201 struct page *page; 202 unsigned int page_offset; 203 unsigned int pgcnt; 204 unsigned int act; 205 unsigned int pagecnt_bias; 206}; 207 208struct ice_q_stats { 209 u64 pkts; 210 u64 bytes; 211}; 212 213struct ice_txq_stats { 214 u64 restart_q; 215 u64 tx_busy; 216 u64 tx_linearize; 217 int prev_pkt; /* negative if no pending Tx descriptors */ 218}; 219 220struct ice_rxq_stats { 221 u64 non_eop_descs; 222 u64 alloc_page_failed; 223 u64 alloc_buf_failed; 224}; 225 226struct ice_ring_stats { 227 struct rcu_head rcu; /* to avoid race on free */ 228 struct ice_q_stats stats; 229 struct u64_stats_sync syncp; 230 union { 231 struct ice_txq_stats tx_stats; 232 struct ice_rxq_stats rx_stats; 233 }; 234}; 235 236enum ice_ring_state_t { 237 ICE_TX_XPS_INIT_DONE, 238 ICE_TX_NBITS, 239}; 240 241/* this enum matches hardware bits and is meant to be used by DYN_CTLN 242 * registers and QINT registers or more generally anywhere in the manual 243 * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any 244 * register but instead is a special value meaning "don't update" ITR0/1/2. 245 */ 246enum ice_dyn_idx_t { 247 ICE_IDX_ITR0 = 0, 248 ICE_IDX_ITR1 = 1, 249 ICE_IDX_ITR2 = 2, 250 ICE_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ 251}; 252 253/* Header split modes defined by DTYPE field of Rx RLAN context */ 254enum ice_rx_dtype { 255 ICE_RX_DTYPE_NO_SPLIT = 0, 256 ICE_RX_DTYPE_HEADER_SPLIT = 1, 257 ICE_RX_DTYPE_SPLIT_ALWAYS = 2, 258}; 259 260/* indices into GLINT_ITR registers */ 261#define ICE_RX_ITR ICE_IDX_ITR0 262#define ICE_TX_ITR ICE_IDX_ITR1 263#define ICE_ITR_8K 124 264#define ICE_ITR_20K 50 265#define ICE_ITR_MAX 8160 /* 0x1FE0 */ 266#define ICE_DFLT_TX_ITR ICE_ITR_20K 267#define ICE_DFLT_RX_ITR ICE_ITR_20K 268enum ice_dynamic_itr { 269 ITR_STATIC = 0, 270 ITR_DYNAMIC = 1 271}; 272 273#define ITR_IS_DYNAMIC(rc) ((rc)->itr_mode == ITR_DYNAMIC) 274#define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */ 275#define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S) 276#define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */ 277#define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK) 278 279#define ICE_DFLT_INTRL 0 280#define ICE_MAX_INTRL 236 281 282#define ICE_IN_WB_ON_ITR_MODE 255 283/* Sets WB_ON_ITR and assumes INTENA bit is already cleared, which allows 284 * setting the MSK_M bit to tell hardware to ignore the INTENA_M bit. Also, 285 * set the write-back latency to the usecs passed in. 286 */ 287#define ICE_GLINT_DYN_CTL_WB_ON_ITR(usecs, itr_idx) \ 288 ((((usecs) << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)) & \ 289 GLINT_DYN_CTL_INTERVAL_M) | \ 290 (((itr_idx) << GLINT_DYN_CTL_ITR_INDX_S) & \ 291 GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | \ 292 GLINT_DYN_CTL_WB_ON_ITR_M) 293 294/* Legacy or Advanced Mode Queue */ 295#define ICE_TX_ADVANCED 0 296#define ICE_TX_LEGACY 1 297 298/* descriptor ring, associated with a VSI */ 299struct ice_rx_ring { 300 /* CL1 - 1st cacheline starts here */ 301 struct ice_rx_ring *next; /* pointer to next ring in q_vector */ 302 void *desc; /* Descriptor ring memory */ 303 struct device *dev; /* Used for DMA mapping */ 304 struct net_device *netdev; /* netdev ring maps to */ 305 struct ice_vsi *vsi; /* Backreference to associated VSI */ 306 struct ice_q_vector *q_vector; /* Backreference to associated vector */ 307 u8 __iomem *tail; 308 u16 q_index; /* Queue number of ring */ 309 310 u16 count; /* Number of descriptors */ 311 u16 reg_idx; /* HW register index of the ring */ 312 u16 next_to_alloc; 313 /* CL2 - 2nd cacheline starts here */ 314 union { 315 struct ice_rx_buf *rx_buf; 316 struct xdp_buff **xdp_buf; 317 }; 318 struct xdp_buff xdp; 319 /* CL3 - 3rd cacheline starts here */ 320 struct bpf_prog *xdp_prog; 321 u16 rx_offset; 322 323 /* used in interrupt processing */ 324 u16 next_to_use; 325 u16 next_to_clean; 326 u16 first_desc; 327 328 /* stats structs */ 329 struct ice_ring_stats *ring_stats; 330 331 struct rcu_head rcu; /* to avoid race on free */ 332 /* CL4 - 4th cacheline starts here */ 333 struct ice_channel *ch; 334 struct ice_tx_ring *xdp_ring; 335 struct xsk_buff_pool *xsk_pool; 336 u32 nr_frags; 337 dma_addr_t dma; /* physical address of ring */ 338 u64 cached_phctime; 339 u16 rx_buf_len; 340 u8 dcb_tc; /* Traffic class of ring */ 341 u8 ptp_rx; 342#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) 343#define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) 344 u8 flags; 345 /* CL5 - 5th cacheline starts here */ 346 struct xdp_rxq_info xdp_rxq; 347} ____cacheline_internodealigned_in_smp; 348 349struct ice_tx_ring { 350 /* CL1 - 1st cacheline starts here */ 351 struct ice_tx_ring *next; /* pointer to next ring in q_vector */ 352 void *desc; /* Descriptor ring memory */ 353 struct device *dev; /* Used for DMA mapping */ 354 u8 __iomem *tail; 355 struct ice_tx_buf *tx_buf; 356 struct ice_q_vector *q_vector; /* Backreference to associated vector */ 357 struct net_device *netdev; /* netdev ring maps to */ 358 struct ice_vsi *vsi; /* Backreference to associated VSI */ 359 /* CL2 - 2nd cacheline starts here */ 360 dma_addr_t dma; /* physical address of ring */ 361 struct xsk_buff_pool *xsk_pool; 362 u16 next_to_use; 363 u16 next_to_clean; 364 u16 q_handle; /* Queue handle per TC */ 365 u16 reg_idx; /* HW register index of the ring */ 366 u16 count; /* Number of descriptors */ 367 u16 q_index; /* Queue number of ring */ 368 u16 xdp_tx_active; 369 /* stats structs */ 370 struct ice_ring_stats *ring_stats; 371 /* CL3 - 3rd cacheline starts here */ 372 struct rcu_head rcu; /* to avoid race on free */ 373 DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ 374 struct ice_channel *ch; 375 struct ice_ptp_tx *tx_tstamps; 376 spinlock_t tx_lock; 377 u32 txq_teid; /* Added Tx queue TEID */ 378 /* CL4 - 4th cacheline starts here */ 379#define ICE_TX_FLAGS_RING_XDP BIT(0) 380#define ICE_TX_FLAGS_RING_VLAN_L2TAG1 BIT(1) 381#define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) 382 u8 flags; 383 u8 dcb_tc; /* Traffic class of ring */ 384 u8 ptp_tx; 385} ____cacheline_internodealigned_in_smp; 386 387static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) 388{ 389 return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB); 390} 391 392static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring) 393{ 394 ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB; 395} 396 397static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring) 398{ 399 ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB; 400} 401 402static inline bool ice_ring_ch_enabled(struct ice_tx_ring *ring) 403{ 404 return !!ring->ch; 405} 406 407static inline bool ice_ring_is_xdp(struct ice_tx_ring *ring) 408{ 409 return !!(ring->flags & ICE_TX_FLAGS_RING_XDP); 410} 411 412enum ice_container_type { 413 ICE_RX_CONTAINER, 414 ICE_TX_CONTAINER, 415}; 416 417struct ice_ring_container { 418 /* head of linked-list of rings */ 419 union { 420 struct ice_rx_ring *rx_ring; 421 struct ice_tx_ring *tx_ring; 422 }; 423 struct dim dim; /* data for net_dim algorithm */ 424 u16 itr_idx; /* index in the interrupt vector */ 425 /* this matches the maximum number of ITR bits, but in usec 426 * values, so it is shifted left one bit (bit zero is ignored) 427 */ 428 union { 429 struct { 430 u16 itr_setting:13; 431 u16 itr_reserved:2; 432 u16 itr_mode:1; 433 }; 434 u16 itr_settings; 435 }; 436 enum ice_container_type type; 437}; 438 439struct ice_coalesce_stored { 440 u16 itr_tx; 441 u16 itr_rx; 442 u8 intrl; 443 u8 tx_valid; 444 u8 rx_valid; 445}; 446 447/* iterator for handling rings in ring container */ 448#define ice_for_each_rx_ring(pos, head) \ 449 for (pos = (head).rx_ring; pos; pos = pos->next) 450 451#define ice_for_each_tx_ring(pos, head) \ 452 for (pos = (head).tx_ring; pos; pos = pos->next) 453 454static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) 455{ 456#if (PAGE_SIZE < 8192) 457 if (ring->rx_buf_len > (PAGE_SIZE / 2)) 458 return 1; 459#endif 460 return 0; 461} 462 463#define ice_rx_pg_size(_ring) (PAGE_SIZE << ice_rx_pg_order(_ring)) 464 465union ice_32b_rx_flex_desc; 466 467bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count); 468netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); 469u16 470ice_select_queue(struct net_device *dev, struct sk_buff *skb, 471 struct net_device *sb_dev); 472void ice_clean_tx_ring(struct ice_tx_ring *tx_ring); 473void ice_clean_rx_ring(struct ice_rx_ring *rx_ring); 474int ice_setup_tx_ring(struct ice_tx_ring *tx_ring); 475int ice_setup_rx_ring(struct ice_rx_ring *rx_ring); 476void ice_free_tx_ring(struct ice_tx_ring *tx_ring); 477void ice_free_rx_ring(struct ice_rx_ring *rx_ring); 478int ice_napi_poll(struct napi_struct *napi, int budget); 479int 480ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, 481 u8 *raw_packet); 482int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget); 483void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring); 484#endif /* _ICE_TXRX_H_ */ 485