cxgb4i.c 54.2 KB
Newer Older
1 2 3
/*
 * cxgb4i.c: Chelsio T4 iSCSI driver.
 *
K
Karen Xie 已提交
4
 * Copyright (c) 2010-2015 Chelsio Communications, Inc.
5 6 7 8 9 10 11 12 13 14 15
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation.
 *
 * Written by:	Karen Xie (kxie@chelsio.com)
 *		Rakesh Ranjan (rranjan@chelsio.com)
 */

#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__

16
#include <linux/kernel.h>
17 18 19 20 21 22
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <scsi/scsi_host.h>
#include <net/tcp.h>
#include <net/dst.h>
#include <linux/netdevice.h>
23
#include <net/addrconf.h>
24

25
#include "t4_regs.h"
26 27 28 29 30 31
#include "t4_msg.h"
#include "cxgb4.h"
#include "cxgb4_uld.h"
#include "t4fw_api.h"
#include "l2t.h"
#include "cxgb4i.h"
32
#include "clip_tbl.h"
33 34 35 36 37 38

static unsigned int dbg_level;

#include "../libcxgbi.h"

#define	DRV_MODULE_NAME		"cxgb4i"
39
#define DRV_MODULE_DESC		"Chelsio T4/T5 iSCSI Driver"
K
Karen Xie 已提交
40 41
#define	DRV_MODULE_VERSION	"0.9.5-ko"
#define DRV_MODULE_RELDATE	"Apr. 2015"
42 43 44

static char version[] =
	DRV_MODULE_DESC " " DRV_MODULE_NAME
K
Karen Xie 已提交
45
	" v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
46 47 48 49 50 51 52 53 54

MODULE_AUTHOR("Chelsio Communications, Inc.");
MODULE_DESCRIPTION(DRV_MODULE_DESC);
MODULE_VERSION(DRV_MODULE_VERSION);
MODULE_LICENSE("GPL");

module_param(dbg_level, uint, 0644);
MODULE_PARM_DESC(dbg_level, "Debug flag (default=0)");

55 56
#define CXGB4I_DEFAULT_10G_RCV_WIN (256 * 1024)
static int cxgb4i_rcv_win = -1;
57 58 59
module_param(cxgb4i_rcv_win, int, 0644);
MODULE_PARM_DESC(cxgb4i_rcv_win, "TCP reveive window in bytes");

60 61
#define CXGB4I_DEFAULT_10G_SND_WIN (128 * 1024)
static int cxgb4i_snd_win = -1;
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
module_param(cxgb4i_snd_win, int, 0644);
MODULE_PARM_DESC(cxgb4i_snd_win, "TCP send window in bytes");

static int cxgb4i_rx_credit_thres = 10 * 1024;
module_param(cxgb4i_rx_credit_thres, int, 0644);
MODULE_PARM_DESC(cxgb4i_rx_credit_thres,
		"RX credits return threshold in bytes (default=10KB)");

static unsigned int cxgb4i_max_connect = (8 * 1024);
module_param(cxgb4i_max_connect, uint, 0644);
MODULE_PARM_DESC(cxgb4i_max_connect, "Maximum number of connections");

static unsigned short cxgb4i_sport_base = 20000;
module_param(cxgb4i_sport_base, ushort, 0644);
MODULE_PARM_DESC(cxgb4i_sport_base, "Starting port number (default 20000)");

typedef void (*cxgb4i_cplhandler_func)(struct cxgbi_device *, struct sk_buff *);

static void *t4_uld_add(const struct cxgb4_lld_info *);
static int t4_uld_rx_handler(void *, const __be64 *, const struct pkt_gl *);
static int t4_uld_state_change(void *, enum cxgb4_state state);
83
static inline int send_tx_flowc_wr(struct cxgbi_sock *);
84 85 86

static const struct cxgb4_uld_info cxgb4i_uld_info = {
	.name = DRV_MODULE_NAME,
87
	.nrxq = MAX_ULD_QSETS,
88
	.ntxq = MAX_ULD_QSETS,
89 90
	.rxq_size = 1024,
	.lro = false,
91 92 93 94 95 96 97 98 99 100 101
	.add = t4_uld_add,
	.rx_handler = t4_uld_rx_handler,
	.state_change = t4_uld_state_change,
};

static struct scsi_host_template cxgb4i_host_template = {
	.module		= THIS_MODULE,
	.name		= DRV_MODULE_NAME,
	.proc_name	= DRV_MODULE_NAME,
	.can_queue	= CXGB4I_SCSI_HOST_QDEPTH,
	.queuecommand	= iscsi_queuecommand,
102
	.change_queue_depth = scsi_change_queue_depth,
103 104 105 106 107 108 109 110 111
	.sg_tablesize	= SG_ALL,
	.max_sectors	= 0xFFFF,
	.cmd_per_lun	= ISCSI_DEF_CMD_PER_LUN,
	.eh_abort_handler = iscsi_eh_abort,
	.eh_device_reset_handler = iscsi_eh_device_reset,
	.eh_target_reset_handler = iscsi_eh_recover_target,
	.target_alloc	= iscsi_target_alloc,
	.use_clustering	= DISABLE_CLUSTERING,
	.this_id	= -1,
112
	.track_queue_depth = 1,
113 114 115 116 117 118 119
};

static struct iscsi_transport cxgb4i_iscsi_transport = {
	.owner		= THIS_MODULE,
	.name		= DRV_MODULE_NAME,
	.caps		= CAP_RECOVERY_L0 | CAP_MULTI_R2T | CAP_HDRDGST |
				CAP_DATADGST | CAP_DIGEST_OFFLOAD |
120
				CAP_PADDING_OFFLOAD | CAP_TEXT_NEGO,
121
	.attr_is_visible	= cxgbi_attr_is_visible,
122 123 124 125 126 127 128 129 130 131 132 133
	.get_host_param	= cxgbi_get_host_param,
	.set_host_param	= cxgbi_set_host_param,
	/* session management */
	.create_session	= cxgbi_create_session,
	.destroy_session	= cxgbi_destroy_session,
	.get_session_param = iscsi_session_get_param,
	/* connection management */
	.create_conn	= cxgbi_create_conn,
	.bind_conn		= cxgbi_bind_conn,
	.destroy_conn	= iscsi_tcp_conn_teardown,
	.start_conn		= iscsi_conn_start,
	.stop_conn		= iscsi_conn_stop,
134
	.get_conn_param	= iscsi_conn_get_param,
135 136 137 138 139 140 141 142 143 144 145 146 147 148
	.set_param	= cxgbi_set_conn_param,
	.get_stats	= cxgbi_get_conn_stats,
	/* pdu xmit req from user space */
	.send_pdu	= iscsi_conn_send_pdu,
	/* task */
	.init_task	= iscsi_tcp_task_init,
	.xmit_task	= iscsi_tcp_task_xmit,
	.cleanup_task	= cxgbi_cleanup_task,
	/* pdu */
	.alloc_pdu	= cxgbi_conn_alloc_pdu,
	.init_pdu	= cxgbi_conn_init_pdu,
	.xmit_pdu	= cxgbi_conn_xmit_pdu,
	.parse_pdu_itt	= cxgbi_parse_pdu_itt,
	/* TCP connect/disconnect */
149
	.get_ep_param	= cxgbi_get_ep_param,
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
	.ep_connect	= cxgbi_ep_connect,
	.ep_poll	= cxgbi_ep_poll,
	.ep_disconnect	= cxgbi_ep_disconnect,
	/* Error recovery timeout call */
	.session_recovery_timedout = iscsi_session_recovery_timedout,
};

static struct scsi_transport_template *cxgb4i_stt;

/*
 * CPL (Chelsio Protocol Language) defines a message passing interface between
 * the host driver and Chelsio asic.
 * The section below implments CPLs that related to iscsi tcp connection
 * open/close/abort and data send/receive.
 */
165

166
#define RCV_BUFSIZ_MASK		0x3FFU
167
#define MAX_IMM_TX_PKT_LEN	256
168 169 170 171 172 173 174 175 176 177

static int push_tx_frames(struct cxgbi_sock *, int);

/*
 * is_ofld_imm - check whether a packet can be sent as immediate data
 * @skb: the packet
 *
 * Returns true if a packet can be sent as an offload WR with immediate
 * data.  We currently use the same limit as for Ethernet packets.
 */
178
static inline bool is_ofld_imm(const struct sk_buff *skb)
179
{
180 181 182 183 184 185
	int len = skb->len;

	if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
		len += sizeof(struct fw_ofld_tx_data_wr);

	return len <= MAX_IMM_TX_PKT_LEN;
186 187 188 189 190
}

static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
				struct l2t_entry *e)
{
191
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
192
	int t4 = is_t4(lldi->adapter_type);
193 194 195 196 197 198
	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
	unsigned long long opt0;
	unsigned int opt2;
	unsigned int qid_atid = ((unsigned int)csk->atid) |
				 (((unsigned int)csk->rss_qid) << 14);

199 200 201 202 203 204 205
	opt0 = KEEP_ALIVE_F |
		WND_SCALE_V(wscale) |
		MSS_IDX_V(csk->mss_idx) |
		L2T_IDX_V(((struct l2t_entry *)csk->l2t)->idx) |
		TX_CHAN_V(csk->tx_chan) |
		SMAC_SEL_V(csk->smac_idx) |
		ULP_MODE_V(ULP_MODE_ISCSI) |
206
		RCV_BUFSIZ_V(csk->rcv_win >> 10);
207

208 209 210
	opt2 = RX_CHANNEL_V(0) |
		RSS_QUEUE_VALID_F |
		RSS_QUEUE_V(csk->rss_qid);
211

212 213 214 215 216 217
	if (is_t4(lldi->adapter_type)) {
		struct cpl_act_open_req *req =
				(struct cpl_act_open_req *)skb->head;

		INIT_TP_WR(req, 0);
		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
218
					qid_atid));
219 220 221 222 223
		req->local_port = csk->saddr.sin_port;
		req->peer_port = csk->daddr.sin_port;
		req->local_ip = csk->saddr.sin_addr.s_addr;
		req->peer_ip = csk->daddr.sin_addr.s_addr;
		req->opt0 = cpu_to_be64(opt0);
224 225 226
		req->params = cpu_to_be32(cxgb4_select_ntuple(
					csk->cdev->ports[csk->port_id],
					csk->l2t));
227
		opt2 |= RX_FC_VALID_F;
228
		req->opt2 = cpu_to_be32(opt2);
229

230 231 232 233 234 235 236 237
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
			"csk t4 0x%p, %pI4:%u-%pI4:%u, atid %d, qid %u.\n",
			csk, &req->local_ip, ntohs(req->local_port),
			&req->peer_ip, ntohs(req->peer_port),
			csk->atid, csk->rss_qid);
	} else {
		struct cpl_t5_act_open_req *req =
				(struct cpl_t5_act_open_req *)skb->head;
238
		u32 isn = (prandom_u32() & ~7UL) - 1;
239 240 241 242 243 244 245 246 247

		INIT_TP_WR(req, 0);
		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
					qid_atid));
		req->local_port = csk->saddr.sin_port;
		req->peer_port = csk->daddr.sin_port;
		req->local_ip = csk->saddr.sin_addr.s_addr;
		req->peer_ip = csk->daddr.sin_addr.s_addr;
		req->opt0 = cpu_to_be64(opt0);
248
		req->params = cpu_to_be64(FILTER_TUPLE_V(
249 250 251
				cxgb4_select_ntuple(
					csk->cdev->ports[csk->port_id],
					csk->l2t)));
252 253 254 255
		req->rsvd = cpu_to_be32(isn);
		opt2 |= T5_ISS_VALID;
		opt2 |= T5_OPT_2_VALID_F;

256 257 258 259 260 261 262 263 264 265
		req->opt2 = cpu_to_be32(opt2);

		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
			"csk t5 0x%p, %pI4:%u-%pI4:%u, atid %d, qid %u.\n",
			csk, &req->local_ip, ntohs(req->local_port),
			&req->peer_ip, ntohs(req->peer_port),
			csk->atid, csk->rss_qid);
	}

	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);
266 267 268 269 270 271 272 273

	pr_info_ipaddr("t%d csk 0x%p,%u,0x%lx,%u, rss_qid %u.\n",
		       (&csk->saddr), (&csk->daddr), t4 ? 4 : 5, csk,
		       csk->state, csk->flags, csk->atid, csk->rss_qid);

	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
}

274
#if IS_ENABLED(CONFIG_IPV6)
275 276 277 278 279 280 281 282 283 284 285
static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
			       struct l2t_entry *e)
{
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
	int t4 = is_t4(lldi->adapter_type);
	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
	unsigned long long opt0;
	unsigned int opt2;
	unsigned int qid_atid = ((unsigned int)csk->atid) |
				 (((unsigned int)csk->rss_qid) << 14);

286 287 288 289 290 291 292
	opt0 = KEEP_ALIVE_F |
		WND_SCALE_V(wscale) |
		MSS_IDX_V(csk->mss_idx) |
		L2T_IDX_V(((struct l2t_entry *)csk->l2t)->idx) |
		TX_CHAN_V(csk->tx_chan) |
		SMAC_SEL_V(csk->smac_idx) |
		ULP_MODE_V(ULP_MODE_ISCSI) |
293
		RCV_BUFSIZ_V(csk->rcv_win >> 10);
294

295 296 297 298
	opt2 = RX_CHANNEL_V(0) |
		RSS_QUEUE_VALID_F |
		RX_FC_DISABLE_F |
		RSS_QUEUE_V(csk->rss_qid);
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318

	if (t4) {
		struct cpl_act_open_req6 *req =
			    (struct cpl_act_open_req6 *)skb->head;

		INIT_TP_WR(req, 0);
		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
							    qid_atid));
		req->local_port = csk->saddr6.sin6_port;
		req->peer_port = csk->daddr6.sin6_port;

		req->local_ip_hi = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr);
		req->local_ip_lo = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr +
								    8);
		req->peer_ip_hi = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr);
		req->peer_ip_lo = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr +
								    8);

		req->opt0 = cpu_to_be64(opt0);

319
		opt2 |= RX_FC_VALID_F;
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
		req->opt2 = cpu_to_be32(opt2);

		req->params = cpu_to_be32(cxgb4_select_ntuple(
					  csk->cdev->ports[csk->port_id],
					  csk->l2t));
	} else {
		struct cpl_t5_act_open_req6 *req =
				(struct cpl_t5_act_open_req6 *)skb->head;

		INIT_TP_WR(req, 0);
		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
							    qid_atid));
		req->local_port = csk->saddr6.sin6_port;
		req->peer_port = csk->daddr6.sin6_port;
		req->local_ip_hi = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr);
		req->local_ip_lo = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr +
									8);
		req->peer_ip_hi = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr);
		req->peer_ip_lo = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr +
									8);
		req->opt0 = cpu_to_be64(opt0);

342
		opt2 |= T5_OPT_2_VALID_F;
343 344
		req->opt2 = cpu_to_be32(opt2);

345
		req->params = cpu_to_be64(FILTER_TUPLE_V(cxgb4_select_ntuple(
346 347 348 349 350 351 352 353 354 355 356 357
					  csk->cdev->ports[csk->port_id],
					  csk->l2t)));
	}

	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);

	pr_info("t%d csk 0x%p,%u,0x%lx,%u, [%pI6]:%u-[%pI6]:%u, rss_qid %u.\n",
		t4 ? 4 : 5, csk, csk->state, csk->flags, csk->atid,
		&csk->saddr6.sin6_addr, ntohs(csk->saddr.sin_port),
		&csk->daddr6.sin6_addr, ntohs(csk->daddr.sin_port),
		csk->rss_qid);

358 359
	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
}
360
#endif
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401

static void send_close_req(struct cxgbi_sock *csk)
{
	struct sk_buff *skb = csk->cpl_close;
	struct cpl_close_con_req *req = (struct cpl_close_con_req *)skb->head;
	unsigned int tid = csk->tid;

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx, tid %u.\n",
		csk, csk->state, csk->flags, csk->tid);
	csk->cpl_close = NULL;
	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
	INIT_TP_WR(req, tid);
	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid));
	req->rsvd = 0;

	cxgbi_sock_skb_entail(csk, skb);
	if (csk->state >= CTP_ESTABLISHED)
		push_tx_frames(csk, 1);
}

static void abort_arp_failure(void *handle, struct sk_buff *skb)
{
	struct cxgbi_sock *csk = (struct cxgbi_sock *)handle;
	struct cpl_abort_req *req;

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx, tid %u, abort.\n",
		csk, csk->state, csk->flags, csk->tid);
	req = (struct cpl_abort_req *)skb->data;
	req->cmd = CPL_ABORT_NO_RST;
	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
}

static void send_abort_req(struct cxgbi_sock *csk)
{
	struct cpl_abort_req *req;
	struct sk_buff *skb = csk->cpl_abort_req;

	if (unlikely(csk->state == CTP_ABORTING) || !skb || !csk->cdev)
		return;
402 403 404 405 406 407

	if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
		send_tx_flowc_wr(csk);
		cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
	}

408 409 410 411 412 413
	cxgbi_sock_set_state(csk, CTP_ABORTING);
	cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_PENDING);
	cxgbi_sock_purge_write_queue(csk);

	csk->cpl_abort_req = NULL;
	req = (struct cpl_abort_req *)skb->head;
414
	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
	req->cmd = CPL_ABORT_SEND_RST;
	t4_set_arp_err_handler(skb, csk, abort_arp_failure);
	INIT_TP_WR(req, csk->tid);
	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, csk->tid));
	req->rsvd0 = htonl(csk->snd_nxt);
	req->rsvd1 = !cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT);

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx,%u, snd_nxt %u, 0x%x.\n",
		csk, csk->state, csk->flags, csk->tid, csk->snd_nxt,
		req->rsvd1);

	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
}

static void send_abort_rpl(struct cxgbi_sock *csk, int rst_status)
{
	struct sk_buff *skb = csk->cpl_abort_rpl;
	struct cpl_abort_rpl *rpl = (struct cpl_abort_rpl *)skb->head;

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx,%u, status %d.\n",
		csk, csk->state, csk->flags, csk->tid, rst_status);

	csk->cpl_abort_rpl = NULL;
440
	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
	INIT_TP_WR(rpl, csk->tid);
	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, csk->tid));
	rpl->cmd = rst_status;
	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
}

/*
 * CPL connection rx data ack: host ->
 * Send RX credits through an RX_DATA_ACK CPL message. Returns the number of
 * credits sent.
 */
static u32 send_rx_credits(struct cxgbi_sock *csk, u32 credits)
{
	struct sk_buff *skb;
	struct cpl_rx_data_ack *req;

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
		"csk 0x%p,%u,0x%lx,%u, credit %u.\n",
		csk, csk->state, csk->flags, csk->tid, credits);

461
	skb = alloc_wr(sizeof(*req), 0, GFP_ATOMIC);
462 463 464 465 466 467 468 469 470 471
	if (!skb) {
		pr_info("csk 0x%p, credit %u, OOM.\n", csk, credits);
		return 0;
	}
	req = (struct cpl_rx_data_ack *)skb->head;

	set_wr_txq(skb, CPL_PRIORITY_ACK, csk->port_id);
	INIT_TP_WR(req, csk->tid);
	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK,
				      csk->tid));
472 473
	req->credit_dack = cpu_to_be32(RX_CREDITS_V(credits)
				       | RX_FORCE_ACK_F);
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
	return credits;
}

/*
 * sgl_len - calculates the size of an SGL of the given capacity
 * @n: the number of SGL entries
 * Calculates the number of flits needed for a scatter/gather list that
 * can hold the given number of entries.
 */
static inline unsigned int sgl_len(unsigned int n)
{
	n--;
	return (3 * n) / 2 + (n & 1) + 2;
}

/*
 * calc_tx_flits_ofld - calculate # of flits for an offload packet
 * @skb: the packet
 *
 * Returns the number of flits needed for the given offload packet.
 * These packets are already fully constructed and no additional headers
 * will be added.
 */
static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
{
	unsigned int flits, cnt;

	if (is_ofld_imm(skb))
		return DIV_ROUND_UP(skb->len, 8);
	flits = skb_transport_offset(skb) / 8;
	cnt = skb_shinfo(skb)->nr_frags;
506
	if (skb_tail_pointer(skb) != skb_transport_header(skb))
507 508 509 510
		cnt++;
	return flits + sgl_len(cnt);
}

511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532
#define FLOWC_WR_NPARAMS_MIN	9
static inline int tx_flowc_wr_credits(int *nparamsp, int *flowclenp)
{
	int nparams, flowclen16, flowclen;

	nparams = FLOWC_WR_NPARAMS_MIN;
	flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]);
	flowclen16 = DIV_ROUND_UP(flowclen, 16);
	flowclen = flowclen16 * 16;
	/*
	 * Return the number of 16-byte credits used by the FlowC request.
	 * Pass back the nparams and actual FlowC length if requested.
	 */
	if (nparamsp)
		*nparamsp = nparams;
	if (flowclenp)
		*flowclenp = flowclen;

	return flowclen16;
}

static inline int send_tx_flowc_wr(struct cxgbi_sock *csk)
533 534 535
{
	struct sk_buff *skb;
	struct fw_flowc_wr *flowc;
536
	int nparams, flowclen16, flowclen;
537

538
	flowclen16 = tx_flowc_wr_credits(&nparams, &flowclen);
539
	skb = alloc_wr(flowclen, 0, GFP_ATOMIC);
540 541
	flowc = (struct fw_flowc_wr *)skb->head;
	flowc->op_to_nparams =
542
		htonl(FW_WR_OP_V(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS_V(nparams));
543
	flowc->flowid_len16 =
544
		htonl(FW_WR_LEN16_V(flowclen16) | FW_WR_FLOWID_V(csk->tid));
545
	flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
546
	flowc->mnemval[0].val = htonl(csk->cdev->pfvf);
547 548 549 550 551 552 553 554 555 556 557
	flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
	flowc->mnemval[1].val = htonl(csk->tx_chan);
	flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT;
	flowc->mnemval[2].val = htonl(csk->tx_chan);
	flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID;
	flowc->mnemval[3].val = htonl(csk->rss_qid);
	flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT;
	flowc->mnemval[4].val = htonl(csk->snd_nxt);
	flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
	flowc->mnemval[5].val = htonl(csk->rcv_nxt);
	flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
558
	flowc->mnemval[6].val = htonl(csk->snd_win);
559 560 561 562
	flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
	flowc->mnemval[7].val = htonl(csk->advmss);
	flowc->mnemval[8].mnemonic = 0;
	flowc->mnemval[8].val = 0;
563 564 565
	flowc->mnemval[8].mnemonic = FW_FLOWC_MNEM_TXDATAPLEN_MAX;
	flowc->mnemval[8].val = 16384;

566
	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
567 568 569 570

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p, tid 0x%x, %u,%u,%u,%u,%u,%u,%u.\n",
		csk, csk->tid, 0, csk->tx_chan, csk->rss_qid,
571
		csk->snd_nxt, csk->rcv_nxt, csk->snd_win,
572 573 574
		csk->advmss);

	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
575 576

	return flowclen16;
577 578 579 580 581 582 583
}

static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb,
				   int dlen, int len, u32 credits, int compl)
{
	struct fw_ofld_tx_data_wr *req;
	unsigned int submode = cxgbi_skcb_ulp_mode(skb) & 3;
584
	unsigned int wr_ulp_mode = 0, val;
585
	bool imm = is_ofld_imm(skb);
586 587 588

	req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req));

589
	if (imm) {
590 591 592 593 594
		req->op_to_immdlen = htonl(FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
					FW_WR_COMPL_F |
					FW_WR_IMMDLEN_V(dlen));
		req->flowid_len16 = htonl(FW_WR_FLOWID_V(csk->tid) |
						FW_WR_LEN16_V(credits));
595 596
	} else {
		req->op_to_immdlen =
597 598 599
			cpu_to_be32(FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
					FW_WR_COMPL_F |
					FW_WR_IMMDLEN_V(0));
600
		req->flowid_len16 =
601 602
			cpu_to_be32(FW_WR_FLOWID_V(csk->tid) |
					FW_WR_LEN16_V(credits));
603 604
	}
	if (submode)
605 606 607
		wr_ulp_mode = FW_OFLD_TX_DATA_WR_ULPMODE_V(ULP2_MODE_ISCSI) |
				FW_OFLD_TX_DATA_WR_ULPSUBMODE_V(submode);
	val = skb_peek(&csk->write_queue) ? 0 : 1;
K
Karen Xie 已提交
608
	req->tunnel_to_proxy = htonl(wr_ulp_mode |
609
				     FW_OFLD_TX_DATA_WR_SHOVE_V(val));
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637
	req->plen = htonl(len);
	if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT))
		cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
}

static void arp_failure_skb_discard(void *handle, struct sk_buff *skb)
{
	kfree_skb(skb);
}

static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
{
	int total_size = 0;
	struct sk_buff *skb;

	if (unlikely(csk->state < CTP_ESTABLISHED ||
		csk->state == CTP_CLOSE_WAIT_1 || csk->state >= CTP_ABORTING)) {
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK |
			 1 << CXGBI_DBG_PDU_TX,
			"csk 0x%p,%u,0x%lx,%u, in closing state.\n",
			csk, csk->state, csk->flags, csk->tid);
		return 0;
	}

	while (csk->wr_cred && (skb = skb_peek(&csk->write_queue)) != NULL) {
		int dlen = skb->len;
		int len = skb->len;
		unsigned int credits_needed;
638
		int flowclen16 = 0;
639 640 641

		skb_reset_transport_header(skb);
		if (is_ofld_imm(skb))
642
			credits_needed = DIV_ROUND_UP(dlen, 16);
643
		else
644 645 646 647 648 649 650
			credits_needed = DIV_ROUND_UP(
						8 * calc_tx_flits_ofld(skb),
						16);

		if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
			credits_needed += DIV_ROUND_UP(
					sizeof(struct fw_ofld_tx_data_wr),
651 652
					16);

653 654 655 656 657 658 659 660 661 662 663
		/*
		 * Assumes the initial credits is large enough to support
		 * fw_flowc_wr plus largest possible first payload
		 */
		if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
			flowclen16 = send_tx_flowc_wr(csk);
			csk->wr_cred -= flowclen16;
			csk->wr_una_cred += flowclen16;
			cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
		}

664 665 666 667 668 669 670 671
		if (csk->wr_cred < credits_needed) {
			log_debug(1 << CXGBI_DBG_PDU_TX,
				"csk 0x%p, skb %u/%u, wr %d < %u.\n",
				csk, skb->len, skb->data_len,
				credits_needed, csk->wr_cred);
			break;
		}
		__skb_unlink(skb, &csk->write_queue);
672
		set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
673
		skb->csum = credits_needed + flowclen16;
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
		csk->wr_cred -= credits_needed;
		csk->wr_una_cred += credits_needed;
		cxgbi_sock_enqueue_wr(csk, skb);

		log_debug(1 << CXGBI_DBG_PDU_TX,
			"csk 0x%p, skb %u/%u, wr %d, left %u, unack %u.\n",
			csk, skb->len, skb->data_len, credits_needed,
			csk->wr_cred, csk->wr_una_cred);

		if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR))) {
			len += cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
			make_tx_data_wr(csk, skb, dlen, len, credits_needed,
					req_completion);
			csk->snd_nxt += len;
			cxgbi_skcb_clear_flag(skb, SKCBF_TX_NEED_HDR);
689 690 691 692 693
		} else if (cxgbi_skcb_test_flag(skb, SKCBF_TX_FLAG_COMPL) &&
			   (csk->wr_una_cred >= (csk->wr_max_cred / 2))) {
			struct cpl_close_con_req *req =
				(struct cpl_close_con_req *)skb->data;
			req->wr.wr_hi |= htonl(FW_WR_COMPL_F);
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
		}
		total_size += skb->truesize;
		t4_set_arp_err_handler(skb, csk, arp_failure_skb_discard);

		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_TX,
			"csk 0x%p,%u,0x%lx,%u, skb 0x%p, %u.\n",
			csk, csk->state, csk->flags, csk->tid, skb, len);

		cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
	}
	return total_size;
}

static inline void free_atid(struct cxgbi_sock *csk)
{
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);

	if (cxgbi_sock_flag(csk, CTPF_HAS_ATID)) {
		cxgb4_free_atid(lldi->tids, csk->atid);
		cxgbi_sock_clear_flag(csk, CTPF_HAS_ATID);
		cxgbi_sock_put(csk);
	}
}

static void do_act_establish(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_act_establish *req = (struct cpl_act_establish *)skb->data;
	unsigned short tcp_opt = ntohs(req->tcp_opt);
	unsigned int tid = GET_TID(req);
724
	unsigned int atid = TID_TID_G(ntohl(req->tos_atid));
725 726 727 728 729 730 731 732 733 734
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;
	u32 rcv_isn = be32_to_cpu(req->rcv_isn);

	csk = lookup_atid(t, atid);
	if (unlikely(!csk)) {
		pr_err("NO conn. for atid %u, cdev 0x%p.\n", atid, cdev);
		goto rel_skb;
	}

735 736 737 738 739 740
	if (csk->atid != atid) {
		pr_err("bad conn atid %u, csk 0x%p,%u,0x%lx,tid %u, atid %u.\n",
			atid, csk, csk->state, csk->flags, csk->tid, csk->atid);
		goto rel_skb;
	}

741 742 743 744 745
	pr_info_ipaddr("atid 0x%x, tid 0x%x, csk 0x%p,%u,0x%lx, isn %u.\n",
		       (&csk->saddr), (&csk->daddr),
		       atid, tid, csk, csk->state, csk->flags, rcv_isn);

	module_put(THIS_MODULE);
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768

	cxgbi_sock_get(csk);
	csk->tid = tid;
	cxgb4_insert_tid(lldi->tids, csk, tid);
	cxgbi_sock_set_flag(csk, CTPF_HAS_TID);

	free_atid(csk);

	spin_lock_bh(&csk->lock);
	if (unlikely(csk->state != CTP_ACTIVE_OPEN))
		pr_info("csk 0x%p,%u,0x%lx,%u, got EST.\n",
			csk, csk->state, csk->flags, csk->tid);

	if (csk->retry_timer.function) {
		del_timer(&csk->retry_timer);
		csk->retry_timer.function = NULL;
	}

	csk->copied_seq = csk->rcv_wup = csk->rcv_nxt = rcv_isn;
	/*
	 * Causes the first RX_DATA_ACK to supply any Rx credits we couldn't
	 * pass through opt0.
	 */
769 770
	if (csk->rcv_win > (RCV_BUFSIZ_MASK << 10))
		csk->rcv_wup -= csk->rcv_win - (RCV_BUFSIZ_MASK << 10);
771

772 773
	csk->advmss = lldi->mtus[TCPOPT_MSS_G(tcp_opt)] - 40;
	if (TCPOPT_TSTAMP_G(tcp_opt))
774 775 776 777 778 779
		csk->advmss -= 12;
	if (csk->advmss < 128)
		csk->advmss = 128;

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p, mss_idx %u, advmss %u.\n",
780
			csk, TCPOPT_MSS_G(tcp_opt), csk->advmss);
781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816

	cxgbi_sock_established(csk, ntohl(req->snd_isn), ntohs(req->tcp_opt));

	if (unlikely(cxgbi_sock_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED)))
		send_abort_req(csk);
	else {
		if (skb_queue_len(&csk->write_queue))
			push_tx_frames(csk, 0);
		cxgbi_conn_tx_open(csk);
	}
	spin_unlock_bh(&csk->lock);

rel_skb:
	__kfree_skb(skb);
}

static int act_open_rpl_status_to_errno(int status)
{
	switch (status) {
	case CPL_ERR_CONN_RESET:
		return -ECONNREFUSED;
	case CPL_ERR_ARP_MISS:
		return -EHOSTUNREACH;
	case CPL_ERR_CONN_TIMEDOUT:
		return -ETIMEDOUT;
	case CPL_ERR_TCAM_FULL:
		return -ENOMEM;
	case CPL_ERR_CONN_EXIST:
		return -EADDRINUSE;
	default:
		return -EIO;
	}
}

static void csk_act_open_retry_timer(unsigned long data)
{
817
	struct sk_buff *skb = NULL;
818
	struct cxgbi_sock *csk = (struct cxgbi_sock *)data;
819
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
820 821 822
	void (*send_act_open_func)(struct cxgbi_sock *, struct sk_buff *,
				   struct l2t_entry *);
	int t4 = is_t4(lldi->adapter_type), size, size6;
823 824 825 826 827 828 829

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx,%u.\n",
		csk, csk->state, csk->flags, csk->tid);

	cxgbi_sock_get(csk);
	spin_lock_bh(&csk->lock);
830 831 832 833 834 835 836 837 838 839 840 841

	if (t4) {
		size = sizeof(struct cpl_act_open_req);
		size6 = sizeof(struct cpl_act_open_req6);
	} else {
		size = sizeof(struct cpl_t5_act_open_req);
		size6 = sizeof(struct cpl_t5_act_open_req6);
	}

	if (csk->csk_family == AF_INET) {
		send_act_open_func = send_act_open_req;
		skb = alloc_wr(size, 0, GFP_ATOMIC);
842
#if IS_ENABLED(CONFIG_IPV6)
843 844 845
	} else {
		send_act_open_func = send_act_open_req6;
		skb = alloc_wr(size6, 0, GFP_ATOMIC);
846
#endif
847 848
	}

849 850 851 852 853
	if (!skb)
		cxgbi_sock_fail_act_open(csk, -ENOMEM);
	else {
		skb->sk = (struct sock *)csk;
		t4_set_arp_err_handler(skb, csk,
854 855
				       cxgbi_sock_act_open_req_arp_failure);
		send_act_open_func(csk, skb, csk->l2t);
856
	}
857

858 859
	spin_unlock_bh(&csk->lock);
	cxgbi_sock_put(csk);
860

861 862
}

863 864 865 866 867 868 869
static inline bool is_neg_adv(unsigned int status)
{
	return status == CPL_ERR_RTX_NEG_ADVICE ||
		status == CPL_ERR_KEEPALV_NEG_ADVICE ||
		status == CPL_ERR_PERSIST_NEG_ADVICE;
}

870 871 872 873 874 875
static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_act_open_rpl *rpl = (struct cpl_act_open_rpl *)skb->data;
	unsigned int tid = GET_TID(rpl);
	unsigned int atid =
876 877
		TID_TID_G(AOPEN_ATID_G(be32_to_cpu(rpl->atid_status)));
	unsigned int status = AOPEN_STATUS_G(be32_to_cpu(rpl->atid_status));
878 879 880 881 882 883 884 885 886
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_atid(t, atid);
	if (unlikely(!csk)) {
		pr_err("NO matching conn. atid %u, tid %u.\n", atid, tid);
		goto rel_skb;
	}

887 888 889
	pr_info_ipaddr("tid %u/%u, status %u.\n"
		       "csk 0x%p,%u,0x%lx. ", (&csk->saddr), (&csk->daddr),
		       atid, tid, status, csk, csk->state, csk->flags);
890

891
	if (is_neg_adv(status))
892 893
		goto rel_skb;

894 895
	module_put(THIS_MODULE);

896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930
	if (status && status != CPL_ERR_TCAM_FULL &&
	    status != CPL_ERR_CONN_EXIST &&
	    status != CPL_ERR_ARP_MISS)
		cxgb4_remove_tid(lldi->tids, csk->port_id, GET_TID(rpl));

	cxgbi_sock_get(csk);
	spin_lock_bh(&csk->lock);

	if (status == CPL_ERR_CONN_EXIST &&
	    csk->retry_timer.function != csk_act_open_retry_timer) {
		csk->retry_timer.function = csk_act_open_retry_timer;
		mod_timer(&csk->retry_timer, jiffies + HZ / 2);
	} else
		cxgbi_sock_fail_act_open(csk,
					act_open_rpl_status_to_errno(status));

	spin_unlock_bh(&csk->lock);
	cxgbi_sock_put(csk);
rel_skb:
	__kfree_skb(skb);
}

static void do_peer_close(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_peer_close *req = (struct cpl_peer_close *)skb->data;
	unsigned int tid = GET_TID(req);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (unlikely(!csk)) {
		pr_err("can't find connection for tid %u.\n", tid);
		goto rel_skb;
	}
931 932 933
	pr_info_ipaddr("csk 0x%p,%u,0x%lx,%u.\n",
		       (&csk->saddr), (&csk->daddr),
		       csk, csk->state, csk->flags, csk->tid);
934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
	cxgbi_sock_rcv_peer_close(csk);
rel_skb:
	__kfree_skb(skb);
}

static void do_close_con_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_close_con_rpl *rpl = (struct cpl_close_con_rpl *)skb->data;
	unsigned int tid = GET_TID(rpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (unlikely(!csk)) {
		pr_err("can't find connection for tid %u.\n", tid);
		goto rel_skb;
	}
952 953 954
	pr_info_ipaddr("csk 0x%p,%u,0x%lx,%u.\n",
		       (&csk->saddr), (&csk->daddr),
		       csk, csk->state, csk->flags, csk->tid);
955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992
	cxgbi_sock_rcv_close_conn_rpl(csk, ntohl(rpl->snd_nxt));
rel_skb:
	__kfree_skb(skb);
}

static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason,
								int *need_rst)
{
	switch (abort_reason) {
	case CPL_ERR_BAD_SYN: /* fall through */
	case CPL_ERR_CONN_RESET:
		return csk->state > CTP_ESTABLISHED ?
			-EPIPE : -ECONNRESET;
	case CPL_ERR_XMIT_TIMEDOUT:
	case CPL_ERR_PERSIST_TIMEDOUT:
	case CPL_ERR_FINWAIT2_TIMEDOUT:
	case CPL_ERR_KEEPALIVE_TIMEDOUT:
		return -ETIMEDOUT;
	default:
		return -EIO;
	}
}

static void do_abort_req_rss(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_abort_req_rss *req = (struct cpl_abort_req_rss *)skb->data;
	unsigned int tid = GET_TID(req);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;
	int rst_status = CPL_ABORT_NO_RST;

	csk = lookup_tid(t, tid);
	if (unlikely(!csk)) {
		pr_err("can't find connection for tid %u.\n", tid);
		goto rel_skb;
	}

993 994 995
	pr_info_ipaddr("csk 0x%p,%u,0x%lx,%u, status %u.\n",
		       (&csk->saddr), (&csk->daddr),
		       csk, csk->state, csk->flags, csk->tid, req->status);
996

997
	if (is_neg_adv(req->status))
998 999 1000 1001 1002
		goto rel_skb;

	cxgbi_sock_get(csk);
	spin_lock_bh(&csk->lock);

A
Anish Bhatt 已提交
1003 1004 1005 1006 1007
	cxgbi_sock_clear_flag(csk, CTPF_ABORT_REQ_RCVD);

	if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
		send_tx_flowc_wr(csk);
		cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
1008 1009
	}

A
Anish Bhatt 已提交
1010 1011 1012
	cxgbi_sock_set_flag(csk, CTPF_ABORT_REQ_RCVD);
	cxgbi_sock_set_state(csk, CTP_ABORTING);

1013 1014 1015 1016 1017 1018
	send_abort_rpl(csk, rst_status);

	if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) {
		csk->err = abort_status_to_errno(csk, req->status, &rst_status);
		cxgbi_sock_closed(csk);
	}
A
Anish Bhatt 已提交
1019

1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037
	spin_unlock_bh(&csk->lock);
	cxgbi_sock_put(csk);
rel_skb:
	__kfree_skb(skb);
}

static void do_abort_rpl_rss(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_abort_rpl_rss *rpl = (struct cpl_abort_rpl_rss *)skb->data;
	unsigned int tid = GET_TID(rpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (!csk)
		goto rel_skb;

1038 1039 1040 1041
	if (csk)
		pr_info_ipaddr("csk 0x%p,%u,0x%lx,%u, status %u.\n",
			       (&csk->saddr), (&csk->daddr), csk,
			       csk->state, csk->flags, csk->tid, rpl->status);
1042 1043 1044 1045 1046 1047 1048 1049 1050

	if (rpl->status == CPL_ERR_ABORT_FAILED)
		goto rel_skb;

	cxgbi_sock_rcv_abort_rpl(csk);
rel_skb:
	__kfree_skb(skb);
}

K
Karen Xie 已提交
1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
static void do_rx_data(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_rx_data *cpl = (struct cpl_rx_data *)skb->data;
	unsigned int tid = GET_TID(cpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (!csk) {
		pr_err("can't find connection for tid %u.\n", tid);
	} else {
		/* not expecting this, reset the connection. */
		pr_err("csk 0x%p, tid %u, rcv cpl_rx_data.\n", csk, tid);
		spin_lock_bh(&csk->lock);
		send_abort_req(csk);
		spin_unlock_bh(&csk->lock);
	}
	__kfree_skb(skb);
}

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
static void do_rx_iscsi_hdr(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)skb->data;
	unsigned short pdu_len_ddp = be16_to_cpu(cpl->pdu_len_ddp);
	unsigned int tid = GET_TID(cpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (unlikely(!csk)) {
		pr_err("can't find conn. for tid %u.\n", tid);
		goto rel_skb;
	}

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
		"csk 0x%p,%u,0x%lx, tid %u, skb 0x%p,%u, 0x%x.\n",
		csk, csk->state, csk->flags, csk->tid, skb, skb->len,
		pdu_len_ddp);

	spin_lock_bh(&csk->lock);

	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
			"csk 0x%p,%u,0x%lx,%u, bad state.\n",
			csk, csk->state, csk->flags, csk->tid);
		if (csk->state != CTP_ABORTING)
			goto abort_conn;
		else
			goto discard;
	}

	cxgbi_skcb_tcp_seq(skb) = ntohl(cpl->seq);
1105 1106
	cxgbi_skcb_flags(skb) = 0;

1107 1108 1109 1110 1111 1112
	skb_reset_transport_header(skb);
	__skb_pull(skb, sizeof(*cpl));
	__pskb_trim(skb, ntohs(cpl->len));

	if (!csk->skb_ulp_lhdr) {
		unsigned char *bhs;
1113
		unsigned int hlen, dlen, plen;
1114 1115 1116 1117 1118

		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
			"csk 0x%p,%u,0x%lx, tid %u, skb 0x%p header.\n",
			csk, csk->state, csk->flags, csk->tid, skb);
		csk->skb_ulp_lhdr = skb;
1119
		cxgbi_skcb_set_flag(skb, SKCBF_RX_HDR);
1120

1121
		if (cxgbi_skcb_tcp_seq(skb) != csk->rcv_nxt) {
1122
			pr_info("tid %u, CPL_ISCSI_HDR, bad seq, 0x%x/0x%x.\n",
1123
				csk->tid, cxgbi_skcb_tcp_seq(skb),
1124 1125 1126 1127
				csk->rcv_nxt);
			goto abort_conn;
		}

1128
		bhs = skb->data;
1129 1130 1131
		hlen = ntohs(cpl->len);
		dlen = ntohl(*(unsigned int *)(bhs + 4)) & 0xFFFFFF;

1132
		plen = ISCSI_PDU_LEN_G(pdu_len_ddp);
1133 1134 1135 1136
		if (is_t4(lldi->adapter_type))
			plen -= 40;

		if ((hlen + dlen) != plen) {
1137 1138
			pr_info("tid 0x%x, CPL_ISCSI_HDR, pdu len "
				"mismatch %u != %u + %u, seq 0x%x.\n",
1139 1140
				csk->tid, plen, hlen, dlen,
				cxgbi_skcb_tcp_seq(skb));
1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155
			goto abort_conn;
		}

		cxgbi_skcb_rx_pdulen(skb) = (hlen + dlen + 3) & (~0x3);
		if (dlen)
			cxgbi_skcb_rx_pdulen(skb) += csk->dcrc_len;
		csk->rcv_nxt += cxgbi_skcb_rx_pdulen(skb);

		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
			"csk 0x%p, skb 0x%p, 0x%x,%u+%u,0x%x,0x%x.\n",
			csk, skb, *bhs, hlen, dlen,
			ntohl(*((unsigned int *)(bhs + 16))),
			ntohl(*((unsigned int *)(bhs + 24))));

	} else {
1156
		struct sk_buff *lskb = csk->skb_ulp_lhdr;
1157

1158
		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA);
1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
			"csk 0x%p,%u,0x%lx, skb 0x%p data, 0x%p.\n",
			csk, csk->state, csk->flags, skb, lskb);
	}

	__skb_queue_tail(&csk->receive_queue, skb);
	spin_unlock_bh(&csk->lock);
	return;

abort_conn:
	send_abort_req(csk);
discard:
	spin_unlock_bh(&csk->lock);
rel_skb:
	__kfree_skb(skb);
}

static void do_rx_data_ddp(struct cxgbi_device *cdev,
				  struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct sk_buff *lskb;
	struct cpl_rx_data_ddp *rpl = (struct cpl_rx_data_ddp *)skb->data;
	unsigned int tid = GET_TID(rpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;
	unsigned int status = ntohl(rpl->ddpvld);

	csk = lookup_tid(t, tid);
	if (unlikely(!csk)) {
		pr_err("can't find connection for tid %u.\n", tid);
		goto rel_skb;
	}

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
		"csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p.\n",
		csk, csk->state, csk->flags, skb, status, csk->skb_ulp_lhdr);

	spin_lock_bh(&csk->lock);

	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
			"csk 0x%p,%u,0x%lx,%u, bad state.\n",
			csk, csk->state, csk->flags, csk->tid);
		if (csk->state != CTP_ABORTING)
			goto abort_conn;
		else
			goto discard;
	}

	if (!csk->skb_ulp_lhdr) {
		pr_err("tid 0x%x, rcv RX_DATA_DDP w/o pdu bhs.\n", csk->tid);
		goto abort_conn;
	}

	lskb = csk->skb_ulp_lhdr;
	csk->skb_ulp_lhdr = NULL;

	cxgbi_skcb_rx_ddigest(lskb) = ntohl(rpl->ulp_crc);

	if (ntohs(rpl->len) != cxgbi_skcb_rx_pdulen(lskb))
		pr_info("tid 0x%x, RX_DATA_DDP pdulen %u != %u.\n",
			csk->tid, ntohs(rpl->len), cxgbi_skcb_rx_pdulen(lskb));

	if (status & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) {
1224 1225
		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n",
			csk, lskb, status, cxgbi_skcb_flags(lskb));
1226 1227 1228
		cxgbi_skcb_set_flag(lskb, SKCBF_RX_HCRC_ERR);
	}
	if (status & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) {
1229 1230
		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n",
			csk, lskb, status, cxgbi_skcb_flags(lskb));
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DCRC_ERR);
	}
	if (status & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) {
		log_debug(1 << CXGBI_DBG_PDU_RX,
			"csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n",
			csk, lskb, status);
		cxgbi_skcb_set_flag(lskb, SKCBF_RX_PAD_ERR);
	}
	if ((status & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) &&
		!cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA)) {
		log_debug(1 << CXGBI_DBG_PDU_RX,
			"csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n",
			csk, lskb, status);
		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA_DDPD);
	}
	log_debug(1 << CXGBI_DBG_PDU_RX,
		"csk 0x%p, lskb 0x%p, f 0x%lx.\n",
		csk, lskb, cxgbi_skcb_flags(lskb));

1250
	cxgbi_skcb_set_flag(lskb, SKCBF_RX_STATUS);
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308
	cxgbi_conn_pdu_ready(csk);
	spin_unlock_bh(&csk->lock);
	goto rel_skb;

abort_conn:
	send_abort_req(csk);
discard:
	spin_unlock_bh(&csk->lock);
rel_skb:
	__kfree_skb(skb);
}

static void do_fw4_ack(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cxgbi_sock *csk;
	struct cpl_fw4_ack *rpl = (struct cpl_fw4_ack *)skb->data;
	unsigned int tid = GET_TID(rpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;

	csk = lookup_tid(t, tid);
	if (unlikely(!csk))
		pr_err("can't find connection for tid %u.\n", tid);
	else {
		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
			"csk 0x%p,%u,0x%lx,%u.\n",
			csk, csk->state, csk->flags, csk->tid);
		cxgbi_sock_rcv_wr_ack(csk, rpl->credits, ntohl(rpl->snd_una),
					rpl->seq_vld);
	}
	__kfree_skb(skb);
}

static void do_set_tcb_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
{
	struct cpl_set_tcb_rpl *rpl = (struct cpl_set_tcb_rpl *)skb->data;
	unsigned int tid = GET_TID(rpl);
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct tid_info *t = lldi->tids;
	struct cxgbi_sock *csk;

	csk = lookup_tid(t, tid);
	if (!csk)
		pr_err("can't find conn. for tid %u.\n", tid);

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,%lx,%u, status 0x%x.\n",
		csk, csk->state, csk->flags, csk->tid, rpl->status);

	if (rpl->status != CPL_ERR_NONE)
		pr_err("csk 0x%p,%u, SET_TCB_RPL status %u.\n",
			csk, tid, rpl->status);

	__kfree_skb(skb);
}

static int alloc_cpls(struct cxgbi_sock *csk)
{
1309 1310
	csk->cpl_close = alloc_wr(sizeof(struct cpl_close_con_req),
					0, GFP_KERNEL);
1311 1312 1313
	if (!csk->cpl_close)
		return -ENOMEM;

1314 1315
	csk->cpl_abort_req = alloc_wr(sizeof(struct cpl_abort_req),
					0, GFP_KERNEL);
1316 1317 1318
	if (!csk->cpl_abort_req)
		goto free_cpls;

1319 1320
	csk->cpl_abort_rpl = alloc_wr(sizeof(struct cpl_abort_rpl),
					0, GFP_KERNEL);
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
	if (!csk->cpl_abort_rpl)
		goto free_cpls;
	return 0;

free_cpls:
	cxgbi_sock_free_cpl_skbs(csk);
	return -ENOMEM;
}

static inline void l2t_put(struct cxgbi_sock *csk)
{
	if (csk->l2t) {
		cxgb4_l2t_release(csk->l2t);
		csk->l2t = NULL;
		cxgbi_sock_put(csk);
	}
}

static void release_offload_resources(struct cxgbi_sock *csk)
{
	struct cxgb4_lld_info *lldi;
1342 1343 1344
#if IS_ENABLED(CONFIG_IPV6)
	struct net_device *ndev = csk->cdev->ports[csk->port_id];
#endif
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx,%u.\n",
		csk, csk->state, csk->flags, csk->tid);

	cxgbi_sock_free_cpl_skbs(csk);
	if (csk->wr_cred != csk->wr_max_cred) {
		cxgbi_sock_purge_wr_queue(csk);
		cxgbi_sock_reset_wr_list(csk);
	}

	l2t_put(csk);
1357 1358 1359 1360 1361 1362
#if IS_ENABLED(CONFIG_IPV6)
	if (csk->csk_family == AF_INET6)
		cxgb4_clip_release(ndev,
				   (const u32 *)&csk->saddr6.sin6_addr, 1);
#endif

1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
	if (cxgbi_sock_flag(csk, CTPF_HAS_ATID))
		free_atid(csk);
	else if (cxgbi_sock_flag(csk, CTPF_HAS_TID)) {
		lldi = cxgbi_cdev_priv(csk->cdev);
		cxgb4_remove_tid(lldi->tids, 0, csk->tid);
		cxgbi_sock_clear_flag(csk, CTPF_HAS_TID);
		cxgbi_sock_put(csk);
	}
	csk->dst = NULL;
	csk->cdev = NULL;
}

static int init_act_open(struct cxgbi_sock *csk)
{
	struct cxgbi_device *cdev = csk->cdev;
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct net_device *ndev = cdev->ports[csk->port_id];
	struct sk_buff *skb = NULL;
1381 1382
	struct neighbour *n = NULL;
	void *daddr;
1383
	unsigned int step;
1384 1385
	unsigned int size, size6;
	int t4 = is_t4(lldi->adapter_type);
1386 1387
	unsigned int linkspeed;
	unsigned int rcv_winf, snd_winf;
1388 1389 1390 1391 1392

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p,%u,0x%lx,%u.\n",
		csk, csk->state, csk->flags, csk->tid);

1393 1394
	if (csk->csk_family == AF_INET)
		daddr = &csk->daddr.sin_addr.s_addr;
1395 1396
#if IS_ENABLED(CONFIG_IPV6)
	else if (csk->csk_family == AF_INET6)
1397
		daddr = &csk->daddr6.sin6_addr;
1398 1399 1400 1401 1402
#endif
	else {
		pr_err("address family 0x%x not supported\n", csk->csk_family);
		goto rel_resource;
	}
1403 1404 1405 1406 1407 1408 1409 1410

	n = dst_neigh_lookup(csk->dst, daddr);

	if (!n) {
		pr_err("%s, can't get neighbour of csk->dst.\n", ndev->name);
		goto rel_resource;
	}

1411 1412 1413
	csk->atid = cxgb4_alloc_atid(lldi->tids, csk);
	if (csk->atid < 0) {
		pr_err("%s, NO atid available.\n", ndev->name);
1414
		goto rel_resource_without_clip;
1415 1416 1417 1418
	}
	cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
	cxgbi_sock_get(csk);

1419
	csk->l2t = cxgb4_l2t_get(lldi->l2t, n, ndev, 0);
1420 1421
	if (!csk->l2t) {
		pr_err("%s, cannot alloc l2t.\n", ndev->name);
1422
		goto rel_resource_without_clip;
1423 1424 1425
	}
	cxgbi_sock_get(csk);

1426 1427 1428 1429 1430
#if IS_ENABLED(CONFIG_IPV6)
	if (csk->csk_family == AF_INET6)
		cxgb4_clip_get(ndev, (const u32 *)&csk->saddr6.sin6_addr, 1);
#endif

1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
	if (t4) {
		size = sizeof(struct cpl_act_open_req);
		size6 = sizeof(struct cpl_act_open_req6);
	} else {
		size = sizeof(struct cpl_t5_act_open_req);
		size6 = sizeof(struct cpl_t5_act_open_req6);
	}

	if (csk->csk_family == AF_INET)
		skb = alloc_wr(size, 0, GFP_NOIO);
1441
#if IS_ENABLED(CONFIG_IPV6)
1442 1443
	else
		skb = alloc_wr(size6, 0, GFP_NOIO);
1444
#endif
1445

1446 1447 1448 1449 1450 1451 1452 1453 1454
	if (!skb)
		goto rel_resource;
	skb->sk = (struct sock *)csk;
	t4_set_arp_err_handler(skb, csk, cxgbi_sock_act_open_req_arp_failure);

	if (!csk->mtu)
		csk->mtu = dst_mtu(csk->dst);
	cxgb4_best_mtu(lldi->mtus, csk->mtu, &csk->mss_idx);
	csk->tx_chan = cxgb4_port_chan(ndev);
1455 1456
	csk->smac_idx = cxgb4_tp_smt_idx(lldi->adapter_type,
					 cxgb4_port_viid(ndev));
1457 1458 1459 1460
	step = lldi->ntxq / lldi->nchan;
	csk->txq_idx = cxgb4_port_idx(ndev) * step;
	step = lldi->nrxq / lldi->nchan;
	csk->rss_qid = lldi->rxq_ids[cxgb4_port_idx(ndev) * step];
1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475
	linkspeed = ((struct port_info *)netdev_priv(ndev))->link_cfg.speed;
	csk->snd_win = cxgb4i_snd_win;
	csk->rcv_win = cxgb4i_rcv_win;
	if (cxgb4i_rcv_win <= 0) {
		csk->rcv_win = CXGB4I_DEFAULT_10G_RCV_WIN;
		rcv_winf = linkspeed / SPEED_10000;
		if (rcv_winf)
			csk->rcv_win *= rcv_winf;
	}
	if (cxgb4i_snd_win <= 0) {
		csk->snd_win = CXGB4I_DEFAULT_10G_SND_WIN;
		snd_winf = linkspeed / SPEED_10000;
		if (snd_winf)
			csk->snd_win *= snd_winf;
	}
1476 1477 1478
	csk->wr_cred = lldi->wr_cred -
		       DIV_ROUND_UP(sizeof(struct cpl_abort_req), 16);
	csk->wr_max_cred = csk->wr_cred;
1479 1480 1481 1482
	csk->wr_una_cred = 0;
	cxgbi_sock_reset_wr_list(csk);
	csk->err = 0;

1483 1484 1485 1486 1487 1488 1489
	pr_info_ipaddr("csk 0x%p,%u,0x%lx,%u,%u,%u, mtu %u,%u, smac %u.\n",
		       (&csk->saddr), (&csk->daddr), csk, csk->state,
		       csk->flags, csk->tx_chan, csk->txq_idx, csk->rss_qid,
		       csk->mtu, csk->mss_idx, csk->smac_idx);

	/* must wait for either a act_open_rpl or act_open_establish */
	try_module_get(THIS_MODULE);
1490
	cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN);
1491 1492
	if (csk->csk_family == AF_INET)
		send_act_open_req(csk, skb, csk->l2t);
1493
#if IS_ENABLED(CONFIG_IPV6)
1494 1495
	else
		send_act_open_req6(csk, skb, csk->l2t);
1496
#endif
1497
	neigh_release(n);
1498

1499 1500 1501
	return 0;

rel_resource:
1502 1503 1504 1505 1506 1507
#if IS_ENABLED(CONFIG_IPV6)
	if (csk->csk_family == AF_INET6)
		cxgb4_clip_release(ndev,
				   (const u32 *)&csk->saddr6.sin6_addr, 1);
#endif
rel_resource_without_clip:
1508 1509
	if (n)
		neigh_release(n);
1510 1511 1512 1513 1514
	if (skb)
		__kfree_skb(skb);
	return -EINVAL;
}

1515
static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
1516 1517 1518 1519 1520 1521 1522 1523
	[CPL_ACT_ESTABLISH] = do_act_establish,
	[CPL_ACT_OPEN_RPL] = do_act_open_rpl,
	[CPL_PEER_CLOSE] = do_peer_close,
	[CPL_ABORT_REQ_RSS] = do_abort_req_rss,
	[CPL_ABORT_RPL_RSS] = do_abort_rpl_rss,
	[CPL_CLOSE_CON_RPL] = do_close_con_rpl,
	[CPL_FW4_ACK] = do_fw4_ack,
	[CPL_ISCSI_HDR] = do_rx_iscsi_hdr,
1524
	[CPL_ISCSI_DATA] = do_rx_iscsi_hdr,
1525 1526
	[CPL_SET_TCB_RPL] = do_set_tcb_rpl,
	[CPL_RX_DATA_DDP] = do_rx_data_ddp,
1527
	[CPL_RX_ISCSI_DDP] = do_rx_data_ddp,
K
Karen Xie 已提交
1528
	[CPL_RX_DATA] = do_rx_data,
1529 1530
};

1531
static int cxgb4i_ofld_init(struct cxgbi_device *cdev)
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554
{
	int rc;

	if (cxgb4i_max_connect > CXGB4I_MAX_CONN)
		cxgb4i_max_connect = CXGB4I_MAX_CONN;

	rc = cxgbi_device_portmap_create(cdev, cxgb4i_sport_base,
					cxgb4i_max_connect);
	if (rc < 0)
		return rc;

	cdev->csk_release_offload_resources = release_offload_resources;
	cdev->csk_push_tx_frames = push_tx_frames;
	cdev->csk_send_abort_req = send_abort_req;
	cdev->csk_send_close_req = send_close_req;
	cdev->csk_send_rx_credits = send_rx_credits;
	cdev->csk_alloc_cpls = alloc_cpls;
	cdev->csk_init_act_open = init_act_open;

	pr_info("cdev 0x%p, offload up, added.\n", cdev);
	return 0;
}

1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663
static inline void
ulp_mem_io_set_hdr(struct cxgbi_device *cdev,
		   struct ulp_mem_io *req,
		   unsigned int wr_len, unsigned int dlen,
		   unsigned int pm_addr,
		   int tid)
{
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct ulptx_idata *idata = (struct ulptx_idata *)(req + 1);

	INIT_ULPTX_WR(req, wr_len, 0, tid);
	req->wr.wr_hi = htonl(FW_WR_OP_V(FW_ULPTX_WR) |
		FW_WR_ATOMIC_V(0));
	req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) |
		ULP_MEMIO_ORDER_V(is_t4(lldi->adapter_type)) |
		T5_ULP_MEMIO_IMM_V(!is_t4(lldi->adapter_type)));
	req->dlen = htonl(ULP_MEMIO_DATA_LEN_V(dlen >> 5));
	req->lock_addr = htonl(ULP_MEMIO_ADDR_V(pm_addr >> 5));
	req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16));

	idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
	idata->len = htonl(dlen);
}

static struct sk_buff *
ddp_ppod_init_idata(struct cxgbi_device *cdev,
		    struct cxgbi_ppm *ppm,
		    unsigned int idx, unsigned int npods,
		    unsigned int tid)
{
	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit;
	unsigned int dlen = npods << PPOD_SIZE_SHIFT;
	unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) +
				sizeof(struct ulptx_idata) + dlen, 16);
	struct sk_buff *skb = alloc_wr(wr_len, 0, GFP_ATOMIC);

	if (!skb) {
		pr_err("%s: %s idx %u, npods %u, OOM.\n",
		       __func__, ppm->ndev->name, idx, npods);
		return NULL;
	}

	ulp_mem_io_set_hdr(cdev, (struct ulp_mem_io *)skb->head, wr_len, dlen,
			   pm_addr, tid);

	return skb;
}

static int ddp_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk,
				struct cxgbi_task_tag_info *ttinfo,
				unsigned int idx, unsigned int npods,
				struct scatterlist **sg_pp,
				unsigned int *sg_off)
{
	struct cxgbi_device *cdev = csk->cdev;
	struct sk_buff *skb = ddp_ppod_init_idata(cdev, ppm, idx, npods,
						  csk->tid);
	struct ulp_mem_io *req;
	struct ulptx_idata *idata;
	struct cxgbi_pagepod *ppod;
	int i;

	if (!skb)
		return -ENOMEM;

	req = (struct ulp_mem_io *)skb->head;
	idata = (struct ulptx_idata *)(req + 1);
	ppod = (struct cxgbi_pagepod *)(idata + 1);

	for (i = 0; i < npods; i++, ppod++)
		cxgbi_ddp_set_one_ppod(ppod, ttinfo, sg_pp, sg_off);

	cxgbi_skcb_set_flag(skb, SKCBF_TX_MEM_WRITE);
	cxgbi_skcb_set_flag(skb, SKCBF_TX_FLAG_COMPL);
	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);

	spin_lock_bh(&csk->lock);
	cxgbi_sock_skb_entail(csk, skb);
	spin_unlock_bh(&csk->lock);

	return 0;
}

static int ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk,
		       struct cxgbi_task_tag_info *ttinfo)
{
	unsigned int pidx = ttinfo->idx;
	unsigned int npods = ttinfo->npods;
	unsigned int i, cnt;
	int err = 0;
	struct scatterlist *sg = ttinfo->sgl;
	unsigned int offset = 0;

	ttinfo->cid = csk->port_id;

	for (i = 0; i < npods; i += cnt, pidx += cnt) {
		cnt = npods - i;

		if (cnt > ULPMEM_IDATA_MAX_NPPODS)
			cnt = ULPMEM_IDATA_MAX_NPPODS;
		err = ddp_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt,
					   &sg, &offset);
		if (err < 0)
			break;
	}

	return err;
}

1664 1665 1666 1667 1668 1669
static int ddp_setup_conn_pgidx(struct cxgbi_sock *csk, unsigned int tid,
				int pg_idx, bool reply)
{
	struct sk_buff *skb;
	struct cpl_set_tcb_field *req;

1670
	if (!pg_idx || pg_idx >= DDP_PGIDX_MAX)
1671 1672
		return 0;

1673
	skb = alloc_wr(sizeof(*req), 0, GFP_KERNEL);
1674 1675 1676
	if (!skb)
		return -ENOMEM;

1677
	/*  set up ulp page size */
1678 1679 1680
	req = (struct cpl_set_tcb_field *)skb->head;
	INIT_TP_WR(req, csk->tid);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid));
1681
	req->reply_ctrl = htons(NO_REPLY_V(reply) | QUEUENO_V(csk->rss_qid));
1682 1683 1684
	req->word_cookie = htons(0);
	req->mask = cpu_to_be64(0x3 << 8);
	req->val = cpu_to_be64(pg_idx << 8);
1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699
	set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id);

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p, tid 0x%x, pg_idx %u.\n", csk, csk->tid, pg_idx);

	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
	return 0;
}

static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid,
				 int hcrc, int dcrc, int reply)
{
	struct sk_buff *skb;
	struct cpl_set_tcb_field *req;

1700 1701
	if (!hcrc && !dcrc)
		return 0;
1702

1703
	skb = alloc_wr(sizeof(*req), 0, GFP_KERNEL);
1704 1705 1706 1707 1708
	if (!skb)
		return -ENOMEM;

	csk->hcrc_len = (hcrc ? 4 : 0);
	csk->dcrc_len = (dcrc ? 4 : 0);
1709
	/*  set up ulp submode */
1710 1711 1712
	req = (struct cpl_set_tcb_field *)skb->head;
	INIT_TP_WR(req, tid);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid));
1713
	req->reply_ctrl = htons(NO_REPLY_V(reply) | QUEUENO_V(csk->rss_qid));
1714 1715 1716 1717
	req->word_cookie = htons(0);
	req->mask = cpu_to_be64(0x3 << 4);
	req->val = cpu_to_be64(((hcrc ? ULP_CRC_HEADER : 0) |
				(dcrc ? ULP_CRC_DATA : 0)) << 4);
1718 1719 1720 1721 1722 1723 1724 1725 1726
	set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id);

	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
		"csk 0x%p, tid 0x%x, crc %d,%d.\n", csk, csk->tid, hcrc, dcrc);

	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
	return 0;
}

1727 1728 1729 1730 1731 1732
static struct cxgbi_ppm *cdev2ppm(struct cxgbi_device *cdev)
{
	return (struct cxgbi_ppm *)(*((struct cxgb4_lld_info *)
				       (cxgbi_cdev_priv(cdev)))->iscsi_ppm);
}

1733 1734
static int cxgb4i_ddp_init(struct cxgbi_device *cdev)
{
1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757
	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
	struct net_device *ndev = cdev->ports[0];
	struct cxgbi_tag_format tformat;
	unsigned int ppmax;
	int i;

	if (!lldi->vr->iscsi.size) {
		pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name);
		return -EACCES;
	}

	cdev->flags |= CXGBI_FLAG_USE_PPOD_OFLDQ;
	ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT;

	memset(&tformat, 0, sizeof(struct cxgbi_tag_format));
	for (i = 0; i < 4; i++)
		tformat.pgsz_order[i] = (lldi->iscsi_pgsz_order >> (i << 3))
					 & 0xF;
	cxgbi_tagmask_check(lldi->iscsi_tagmask, &tformat);

	cxgbi_ddp_ppm_setup(lldi->iscsi_ppm, cdev, &tformat, ppmax,
			    lldi->iscsi_llimit, lldi->vr->iscsi.start, 2);

1758 1759
	cdev->csk_ddp_setup_digest = ddp_setup_conn_digest;
	cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx;
1760 1761 1762 1763 1764 1765 1766
	cdev->csk_ddp_set_map = ddp_set_map;
	cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
				  lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN);
	cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
				  lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN);
	cdev->cdev2ppm = cdev2ppm;

1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801
	return 0;
}

static void *t4_uld_add(const struct cxgb4_lld_info *lldi)
{
	struct cxgbi_device *cdev;
	struct port_info *pi;
	int i, rc;

	cdev = cxgbi_device_register(sizeof(*lldi), lldi->nports);
	if (!cdev) {
		pr_info("t4 device 0x%p, register failed.\n", lldi);
		return NULL;
	}
	pr_info("0x%p,0x%x, ports %u,%s, chan %u, q %u,%u, wr %u.\n",
		cdev, lldi->adapter_type, lldi->nports,
		lldi->ports[0]->name, lldi->nchan, lldi->ntxq,
		lldi->nrxq, lldi->wr_cred);
	for (i = 0; i < lldi->nrxq; i++)
		log_debug(1 << CXGBI_DBG_DEV,
			"t4 0x%p, rxq id #%d: %u.\n",
			cdev, i, lldi->rxq_ids[i]);

	memcpy(cxgbi_cdev_priv(cdev), lldi, sizeof(*lldi));
	cdev->flags = CXGBI_FLAG_DEV_T4;
	cdev->pdev = lldi->pdev;
	cdev->ports = lldi->ports;
	cdev->nports = lldi->nports;
	cdev->mtus = lldi->mtus;
	cdev->nmtus = NMTUS;
	cdev->rx_credit_thres = cxgb4i_rx_credit_thres;
	cdev->skb_tx_rsvd = CXGB4I_TX_HEADER_LEN;
	cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr);
	cdev->itp = &cxgb4i_iscsi_transport;

1802 1803
	cdev->pfvf = FW_VIID_PFN_G(cxgb4_port_viid(lldi->ports[0]))
			<< FW_VIID_PFN_S;
1804 1805 1806
	pr_info("cdev 0x%p,%s, pfvf %u.\n",
		cdev, lldi->ports[0]->name, cdev->pfvf);

1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845
	rc = cxgb4i_ddp_init(cdev);
	if (rc) {
		pr_info("t4 0x%p ddp init failed.\n", cdev);
		goto err_out;
	}
	rc = cxgb4i_ofld_init(cdev);
	if (rc) {
		pr_info("t4 0x%p ofld init failed.\n", cdev);
		goto err_out;
	}

	rc = cxgbi_hbas_add(cdev, CXGB4I_MAX_LUN, CXGBI_MAX_CONN,
				&cxgb4i_host_template, cxgb4i_stt);
	if (rc)
		goto err_out;

	for (i = 0; i < cdev->nports; i++) {
		pi = netdev_priv(lldi->ports[i]);
		cdev->hbas[i]->port_id = pi->port_id;
	}
	return cdev;

err_out:
	cxgbi_device_unregister(cdev);
	return ERR_PTR(-ENOMEM);
}

#define RX_PULL_LEN	128
static int t4_uld_rx_handler(void *handle, const __be64 *rsp,
				const struct pkt_gl *pgl)
{
	const struct cpl_act_establish *rpl;
	struct sk_buff *skb;
	unsigned int opc;
	struct cxgbi_device *cdev = handle;

	if (pgl == NULL) {
		unsigned int len = 64 - sizeof(struct rsp_ctrl) - 8;

1846
		skb = alloc_wr(len, 0, GFP_ATOMIC);
1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896
		if (!skb)
			goto nomem;
		skb_copy_to_linear_data(skb, &rsp[1], len);
	} else {
		if (unlikely(*(u8 *)rsp != *(u8 *)pgl->va)) {
			pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n",
				pgl->va, be64_to_cpu(*rsp),
				be64_to_cpu(*(u64 *)pgl->va),
				pgl->tot_len);
			return 0;
		}
		skb = cxgb4_pktgl_to_skb(pgl, RX_PULL_LEN, RX_PULL_LEN);
		if (unlikely(!skb))
			goto nomem;
	}

	rpl = (struct cpl_act_establish *)skb->data;
	opc = rpl->ot.opcode;
	log_debug(1 << CXGBI_DBG_TOE,
		"cdev %p, opcode 0x%x(0x%x,0x%x), skb %p.\n",
		 cdev, opc, rpl->ot.opcode_tid, ntohl(rpl->ot.opcode_tid), skb);
	if (cxgb4i_cplhandlers[opc])
		cxgb4i_cplhandlers[opc](cdev, skb);
	else {
		pr_err("No handler for opcode 0x%x.\n", opc);
		__kfree_skb(skb);
	}
	return 0;
nomem:
	log_debug(1 << CXGBI_DBG_TOE, "OOM bailing out.\n");
	return 1;
}

static int t4_uld_state_change(void *handle, enum cxgb4_state state)
{
	struct cxgbi_device *cdev = handle;

	switch (state) {
	case CXGB4_STATE_UP:
		pr_info("cdev 0x%p, UP.\n", cdev);
		break;
	case CXGB4_STATE_START_RECOVERY:
		pr_info("cdev 0x%p, RECOVERY.\n", cdev);
		/* close all connections */
		break;
	case CXGB4_STATE_DOWN:
		pr_info("cdev 0x%p, DOWN.\n", cdev);
		break;
	case CXGB4_STATE_DETACH:
		pr_info("cdev 0x%p, DETACH.\n", cdev);
1897
		cxgbi_device_unregister(cdev);
1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915
		break;
	default:
		pr_info("cdev 0x%p, unknown state %d.\n", cdev, state);
		break;
	}
	return 0;
}

static int __init cxgb4i_init_module(void)
{
	int rc;

	printk(KERN_INFO "%s", version);

	rc = cxgbi_iscsi_init(&cxgb4i_iscsi_transport, &cxgb4i_stt);
	if (rc < 0)
		return rc;
	cxgb4_register_uld(CXGB4_ULD_ISCSI, &cxgb4i_uld_info);
1916

1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928
	return 0;
}

static void __exit cxgb4i_exit_module(void)
{
	cxgb4_unregister_uld(CXGB4_ULD_ISCSI);
	cxgbi_device_unregister_all(CXGBI_FLAG_DEV_T4);
	cxgbi_iscsi_cleanup(&cxgb4i_iscsi_transport, &cxgb4i_stt);
}

module_init(cxgb4i_init_module);
module_exit(cxgb4i_exit_module);