1/* Broadcom NetXtreme-C/E network driver. 2 * 3 * Copyright (c) 2016-2017 Broadcom Limited 4 * 5 * This program is free software; you can redistribute it and/or modify 6 * it under the terms of the GNU General Public License as published by 7 * the Free Software Foundation. 8 */ 9#include <linux/pci.h> 10#include <linux/netdevice.h> 11#include <linux/etherdevice.h> 12#include <linux/rtnetlink.h> 13#include <linux/jhash.h> 14#include <net/pkt_cls.h> 15 16#include "bnxt_hsi.h" 17#include "bnxt.h" 18#include "bnxt_vfr.h" 19#include "bnxt_devlink.h" 20#include "bnxt_tc.h" 21 22#ifdef CONFIG_BNXT_SRIOV 23 24#define CFA_HANDLE_INVALID 0xffff 25#define VF_IDX_INVALID 0xffff 26 27static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx, 28 u16 *tx_cfa_action, u16 *rx_cfa_code) 29{ 30 struct hwrm_cfa_vfr_alloc_output *resp = bp->hwrm_cmd_resp_addr; 31 struct hwrm_cfa_vfr_alloc_input req = { 0 }; 32 int rc; 33 34 bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_ALLOC, -1, -1); 35 req.vf_id = cpu_to_le16(vf_idx); 36 sprintf(req.vfr_name, "vfr%d", vf_idx); 37 38 mutex_lock(&bp->hwrm_cmd_lock); 39 rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); 40 if (!rc) { 41 *tx_cfa_action = le16_to_cpu(resp->tx_cfa_action); 42 *rx_cfa_code = le16_to_cpu(resp->rx_cfa_code); 43 netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x", 44 *tx_cfa_action, *rx_cfa_code); 45 } else { 46 netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); 47 } 48 49 mutex_unlock(&bp->hwrm_cmd_lock); 50 return rc; 51} 52 53static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx) 54{ 55 struct hwrm_cfa_vfr_free_input req = { 0 }; 56 int rc; 57 58 bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_FREE, -1, -1); 59 sprintf(req.vfr_name, "vfr%d", vf_idx); 60 61 rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); 62 if (rc) 63 netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); 64 return rc; 65} 66 67static int bnxt_hwrm_vfr_qcfg(struct bnxt *bp, struct bnxt_vf_rep *vf_rep, 68 u16 *max_mtu) 69{ 70 struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr; 71 struct hwrm_func_qcfg_input req = {0}; 72 u16 mtu; 73 int rc; 74 75 bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1); 76 req.fid = cpu_to_le16(bp->pf.vf[vf_rep->vf_idx].fw_fid); 77 78 mutex_lock(&bp->hwrm_cmd_lock); 79 80 rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); 81 if (!rc) { 82 mtu = le16_to_cpu(resp->max_mtu_configured); 83 if (!mtu) 84 *max_mtu = BNXT_MAX_MTU; 85 else 86 *max_mtu = mtu; 87 } 88 mutex_unlock(&bp->hwrm_cmd_lock); 89 return rc; 90} 91 92static int bnxt_vf_rep_open(struct net_device *dev) 93{ 94 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 95 struct bnxt *bp = vf_rep->bp; 96 97 /* Enable link and TX only if the parent PF is open. */ 98 if (netif_running(bp->dev)) { 99 netif_carrier_on(dev); 100 netif_tx_start_all_queues(dev); 101 } 102 return 0; 103} 104 105static int bnxt_vf_rep_close(struct net_device *dev) 106{ 107 netif_carrier_off(dev); 108 netif_tx_disable(dev); 109 110 return 0; 111} 112 113static netdev_tx_t bnxt_vf_rep_xmit(struct sk_buff *skb, 114 struct net_device *dev) 115{ 116 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 117 int rc, len = skb->len; 118 119 skb_dst_drop(skb); 120 dst_hold((struct dst_entry *)vf_rep->dst); 121 skb_dst_set(skb, (struct dst_entry *)vf_rep->dst); 122 skb->dev = vf_rep->dst->u.port_info.lower_dev; 123 124 rc = dev_queue_xmit(skb); 125 if (!rc) { 126 vf_rep->tx_stats.packets++; 127 vf_rep->tx_stats.bytes += len; 128 } 129 return rc; 130} 131 132static void 133bnxt_vf_rep_get_stats64(struct net_device *dev, 134 struct rtnl_link_stats64 *stats) 135{ 136 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 137 138 stats->rx_packets = vf_rep->rx_stats.packets; 139 stats->rx_bytes = vf_rep->rx_stats.bytes; 140 stats->tx_packets = vf_rep->tx_stats.packets; 141 stats->tx_bytes = vf_rep->tx_stats.bytes; 142} 143 144static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type, 145 void *type_data, 146 void *cb_priv) 147{ 148 struct bnxt_vf_rep *vf_rep = cb_priv; 149 struct bnxt *bp = vf_rep->bp; 150 int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid; 151 152 if (!bnxt_tc_flower_enabled(vf_rep->bp) || 153 !tc_cls_can_offload_and_chain0(bp->dev, type_data)) 154 return -EOPNOTSUPP; 155 156 switch (type) { 157 case TC_SETUP_CLSFLOWER: 158 return bnxt_tc_setup_flower(bp, vf_fid, type_data); 159 default: 160 return -EOPNOTSUPP; 161 } 162} 163 164static LIST_HEAD(bnxt_vf_block_cb_list); 165 166static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, 167 void *type_data) 168{ 169 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 170 171 switch (type) { 172 case TC_SETUP_BLOCK: 173 return flow_block_cb_setup_simple(type_data, 174 &bnxt_vf_block_cb_list, 175 bnxt_vf_rep_setup_tc_block_cb, 176 vf_rep, vf_rep, true); 177 default: 178 return -EOPNOTSUPP; 179 } 180} 181 182struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code) 183{ 184 u16 vf_idx; 185 186 if (cfa_code && bp->cfa_code_map && BNXT_PF(bp)) { 187 vf_idx = bp->cfa_code_map[cfa_code]; 188 if (vf_idx != VF_IDX_INVALID) 189 return bp->vf_reps[vf_idx]->dev; 190 } 191 return NULL; 192} 193 194void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb) 195{ 196 struct bnxt_vf_rep *vf_rep = netdev_priv(skb->dev); 197 198 vf_rep->rx_stats.bytes += skb->len; 199 vf_rep->rx_stats.packets++; 200 201 netif_receive_skb(skb); 202} 203 204static int bnxt_vf_rep_get_phys_port_name(struct net_device *dev, char *buf, 205 size_t len) 206{ 207 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 208 struct pci_dev *pf_pdev = vf_rep->bp->pdev; 209 int rc; 210 211 rc = snprintf(buf, len, "pf%dvf%d", PCI_FUNC(pf_pdev->devfn), 212 vf_rep->vf_idx); 213 if (rc >= len) 214 return -EOPNOTSUPP; 215 return 0; 216} 217 218static void bnxt_vf_rep_get_drvinfo(struct net_device *dev, 219 struct ethtool_drvinfo *info) 220{ 221 strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); 222} 223 224static int bnxt_vf_rep_get_port_parent_id(struct net_device *dev, 225 struct netdev_phys_item_id *ppid) 226{ 227 struct bnxt_vf_rep *vf_rep = netdev_priv(dev); 228 229 /* as only PORT_PARENT_ID is supported currently use common code 230 * between PF and VF-rep for now. 231 */ 232 return bnxt_get_port_parent_id(vf_rep->bp->dev, ppid); 233} 234 235static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = { 236 .get_drvinfo = bnxt_vf_rep_get_drvinfo 237}; 238 239static const struct net_device_ops bnxt_vf_rep_netdev_ops = { 240 .ndo_open = bnxt_vf_rep_open, 241 .ndo_stop = bnxt_vf_rep_close, 242 .ndo_start_xmit = bnxt_vf_rep_xmit, 243 .ndo_get_stats64 = bnxt_vf_rep_get_stats64, 244 .ndo_setup_tc = bnxt_vf_rep_setup_tc, 245 .ndo_get_port_parent_id = bnxt_vf_rep_get_port_parent_id, 246 .ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name 247}; 248 249bool bnxt_dev_is_vf_rep(struct net_device *dev) 250{ 251 return dev->netdev_ops == &bnxt_vf_rep_netdev_ops; 252} 253 254/* Called when the parent PF interface is closed: 255 * As the mode transition from SWITCHDEV to LEGACY 256 * happens under the rtnl_lock() this routine is safe 257 * under the rtnl_lock() 258 */ 259void bnxt_vf_reps_close(struct bnxt *bp) 260{ 261 struct bnxt_vf_rep *vf_rep; 262 u16 num_vfs, i; 263 264 if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) 265 return; 266 267 num_vfs = pci_num_vf(bp->pdev); 268 for (i = 0; i < num_vfs; i++) { 269 vf_rep = bp->vf_reps[i]; 270 if (netif_running(vf_rep->dev)) 271 bnxt_vf_rep_close(vf_rep->dev); 272 } 273} 274 275/* Called when the parent PF interface is opened (re-opened): 276 * As the mode transition from SWITCHDEV to LEGACY 277 * happen under the rtnl_lock() this routine is safe 278 * under the rtnl_lock() 279 */ 280void bnxt_vf_reps_open(struct bnxt *bp) 281{ 282 int i; 283 284 if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) 285 return; 286 287 for (i = 0; i < pci_num_vf(bp->pdev); i++) 288 bnxt_vf_rep_open(bp->vf_reps[i]->dev); 289} 290 291static void __bnxt_vf_reps_destroy(struct bnxt *bp) 292{ 293 u16 num_vfs = pci_num_vf(bp->pdev); 294 struct bnxt_vf_rep *vf_rep; 295 int i; 296 297 for (i = 0; i < num_vfs; i++) { 298 vf_rep = bp->vf_reps[i]; 299 if (vf_rep) { 300 dst_release((struct dst_entry *)vf_rep->dst); 301 302 if (vf_rep->tx_cfa_action != CFA_HANDLE_INVALID) 303 hwrm_cfa_vfr_free(bp, vf_rep->vf_idx); 304 305 if (vf_rep->dev) { 306 /* if register_netdev failed, then netdev_ops 307 * would have been set to NULL 308 */ 309 if (vf_rep->dev->netdev_ops) 310 unregister_netdev(vf_rep->dev); 311 free_netdev(vf_rep->dev); 312 } 313 } 314 } 315 316 kfree(bp->vf_reps); 317 bp->vf_reps = NULL; 318} 319 320void bnxt_vf_reps_destroy(struct bnxt *bp) 321{ 322 bool closed = false; 323 324 if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) 325 return; 326 327 if (!bp->vf_reps) 328 return; 329 330 /* Ensure that parent PF's and VF-reps' RX/TX has been quiesced 331 * before proceeding with VF-rep cleanup. 332 */ 333 rtnl_lock(); 334 if (netif_running(bp->dev)) { 335 bnxt_close_nic(bp, false, false); 336 closed = true; 337 } 338 /* un-publish cfa_code_map so that RX path can't see it anymore */ 339 kfree(bp->cfa_code_map); 340 bp->cfa_code_map = NULL; 341 bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY; 342 343 if (closed) 344 bnxt_open_nic(bp, false, false); 345 rtnl_unlock(); 346 347 /* Need to call vf_reps_destroy() outside of rntl_lock 348 * as unregister_netdev takes rtnl_lock 349 */ 350 __bnxt_vf_reps_destroy(bp); 351} 352 353/* Use the OUI of the PF's perm addr and report the same mac addr 354 * for the same VF-rep each time 355 */ 356static void bnxt_vf_rep_eth_addr_gen(u8 *src_mac, u16 vf_idx, u8 *mac) 357{ 358 u32 addr; 359 360 ether_addr_copy(mac, src_mac); 361 362 addr = jhash(src_mac, ETH_ALEN, 0) + vf_idx; 363 mac[3] = (u8)(addr & 0xFF); 364 mac[4] = (u8)((addr >> 8) & 0xFF); 365 mac[5] = (u8)((addr >> 16) & 0xFF); 366} 367 368static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep, 369 struct net_device *dev) 370{ 371 struct net_device *pf_dev = bp->dev; 372 u16 max_mtu; 373 374 dev->netdev_ops = &bnxt_vf_rep_netdev_ops; 375 dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops; 376 /* Just inherit all the featues of the parent PF as the VF-R 377 * uses the RX/TX rings of the parent PF 378 */ 379 dev->hw_features = pf_dev->hw_features; 380 dev->gso_partial_features = pf_dev->gso_partial_features; 381 dev->vlan_features = pf_dev->vlan_features; 382 dev->hw_enc_features = pf_dev->hw_enc_features; 383 dev->features |= pf_dev->features; 384 bnxt_vf_rep_eth_addr_gen(bp->pf.mac_addr, vf_rep->vf_idx, 385 dev->perm_addr); 386 ether_addr_copy(dev->dev_addr, dev->perm_addr); 387 /* Set VF-Rep's max-mtu to the corresponding VF's max-mtu */ 388 if (!bnxt_hwrm_vfr_qcfg(bp, vf_rep, &max_mtu)) 389 dev->max_mtu = max_mtu; 390 dev->min_mtu = ETH_ZLEN; 391} 392 393static int bnxt_vf_reps_create(struct bnxt *bp) 394{ 395 u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev); 396 struct bnxt_vf_rep *vf_rep; 397 struct net_device *dev; 398 int rc, i; 399 400 if (!(bp->flags & BNXT_FLAG_DSN_VALID)) 401 return -ENODEV; 402 403 bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL); 404 if (!bp->vf_reps) 405 return -ENOMEM; 406 407 /* storage for cfa_code to vf-idx mapping */ 408 cfa_code_map = kmalloc_array(MAX_CFA_CODE, sizeof(*bp->cfa_code_map), 409 GFP_KERNEL); 410 if (!cfa_code_map) { 411 rc = -ENOMEM; 412 goto err; 413 } 414 for (i = 0; i < MAX_CFA_CODE; i++) 415 cfa_code_map[i] = VF_IDX_INVALID; 416 417 for (i = 0; i < num_vfs; i++) { 418 dev = alloc_etherdev(sizeof(*vf_rep)); 419 if (!dev) { 420 rc = -ENOMEM; 421 goto err; 422 } 423 424 vf_rep = netdev_priv(dev); 425 bp->vf_reps[i] = vf_rep; 426 vf_rep->dev = dev; 427 vf_rep->bp = bp; 428 vf_rep->vf_idx = i; 429 vf_rep->tx_cfa_action = CFA_HANDLE_INVALID; 430 431 /* get cfa handles from FW */ 432 rc = hwrm_cfa_vfr_alloc(bp, vf_rep->vf_idx, 433 &vf_rep->tx_cfa_action, 434 &vf_rep->rx_cfa_code); 435 if (rc) { 436 rc = -ENOLINK; 437 goto err; 438 } 439 cfa_code_map[vf_rep->rx_cfa_code] = vf_rep->vf_idx; 440 441 vf_rep->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, 442 GFP_KERNEL); 443 if (!vf_rep->dst) { 444 rc = -ENOMEM; 445 goto err; 446 } 447 /* only cfa_action is needed to mux a packet while TXing */ 448 vf_rep->dst->u.port_info.port_id = vf_rep->tx_cfa_action; 449 vf_rep->dst->u.port_info.lower_dev = bp->dev; 450 451 bnxt_vf_rep_netdev_init(bp, vf_rep, dev); 452 rc = register_netdev(dev); 453 if (rc) { 454 /* no need for unregister_netdev in cleanup */ 455 dev->netdev_ops = NULL; 456 goto err; 457 } 458 } 459 460 /* publish cfa_code_map only after all VF-reps have been initialized */ 461 bp->cfa_code_map = cfa_code_map; 462 bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; 463 netif_keep_dst(bp->dev); 464 return 0; 465 466err: 467 netdev_info(bp->dev, "%s error=%d\n", __func__, rc); 468 kfree(cfa_code_map); 469 __bnxt_vf_reps_destroy(bp); 470 return rc; 471} 472 473/* Devlink related routines */ 474int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode) 475{ 476 struct bnxt *bp = bnxt_get_bp_from_dl(devlink); 477 478 *mode = bp->eswitch_mode; 479 return 0; 480} 481 482int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, 483 struct netlink_ext_ack *extack) 484{ 485 struct bnxt *bp = bnxt_get_bp_from_dl(devlink); 486 int rc = 0; 487 488 mutex_lock(&bp->sriov_lock); 489 if (bp->eswitch_mode == mode) { 490 netdev_info(bp->dev, "already in %s eswitch mode\n", 491 mode == DEVLINK_ESWITCH_MODE_LEGACY ? 492 "legacy" : "switchdev"); 493 rc = -EINVAL; 494 goto done; 495 } 496 497 switch (mode) { 498 case DEVLINK_ESWITCH_MODE_LEGACY: 499 bnxt_vf_reps_destroy(bp); 500 break; 501 502 case DEVLINK_ESWITCH_MODE_SWITCHDEV: 503 if (bp->hwrm_spec_code < 0x10803) { 504 netdev_warn(bp->dev, "FW does not support SRIOV E-Switch SWITCHDEV mode\n"); 505 rc = -ENOTSUPP; 506 goto done; 507 } 508 509 if (pci_num_vf(bp->pdev) == 0) { 510 netdev_info(bp->dev, "Enable VFs before setting switchdev mode\n"); 511 rc = -EPERM; 512 goto done; 513 } 514 rc = bnxt_vf_reps_create(bp); 515 break; 516 517 default: 518 rc = -EINVAL; 519 goto done; 520 } 521done: 522 mutex_unlock(&bp->sriov_lock); 523 return rc; 524} 525 526#endif 527