qplib_fp.c 78.6 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
/*
 * Broadcom NetXtreme-E RoCE driver.
 *
 * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
 * Broadcom refers to Broadcom Limited and/or its subsidiaries.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * BSD license below:
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS''
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS
 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
 * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
 * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Description: Fast Path Operators
 */

#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/prefetch.h>

#include "roce_hsi.h"

#include "qplib_res.h"
#include "qplib_rcfw.h"
#include "qplib_sp.h"
#include "qplib_fp.h"

static void bnxt_qplib_arm_cq_enable(struct bnxt_qplib_cq *cq);
54
static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp);
55
static void bnxt_qplib_arm_srq(struct bnxt_qplib_srq *srq, u32 arm_type);
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211

static void bnxt_qplib_cancel_phantom_processing(struct bnxt_qplib_qp *qp)
{
	qp->sq.condition = false;
	qp->sq.send_phantom = false;
	qp->sq.single = false;
}

/* Flush list */
static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_cq *scq, *rcq;

	scq = qp->scq;
	rcq = qp->rcq;

	if (!qp->sq.flushed) {
		dev_dbg(&scq->hwq.pdev->dev,
			"QPLIB: FP: Adding to SQ Flush list = %p",
			qp);
		bnxt_qplib_cancel_phantom_processing(qp);
		list_add_tail(&qp->sq_flush, &scq->sqf_head);
		qp->sq.flushed = true;
	}
	if (!qp->srq) {
		if (!qp->rq.flushed) {
			dev_dbg(&rcq->hwq.pdev->dev,
				"QPLIB: FP: Adding to RQ Flush list = %p",
				qp);
			list_add_tail(&qp->rq_flush, &rcq->rqf_head);
			qp->rq.flushed = true;
		}
	}
}

void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp,
				 unsigned long *flags)
	__acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock)
{
	spin_lock_irqsave(&qp->scq->hwq.lock, *flags);
	if (qp->scq == qp->rcq)
		__acquire(&qp->rcq->hwq.lock);
	else
		spin_lock(&qp->rcq->hwq.lock);
}

void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp,
				 unsigned long *flags)
	__releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock)
{
	if (qp->scq == qp->rcq)
		__release(&qp->rcq->hwq.lock);
	else
		spin_unlock(&qp->rcq->hwq.lock);
	spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags);
}

static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp,
						      struct bnxt_qplib_cq *cq)
{
	struct bnxt_qplib_cq *buddy_cq = NULL;

	if (qp->scq == qp->rcq)
		buddy_cq = NULL;
	else if (qp->scq == cq)
		buddy_cq = qp->rcq;
	else
		buddy_cq = qp->scq;
	return buddy_cq;
}

static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp,
				     struct bnxt_qplib_cq *cq)
	__acquires(&buddy_cq->hwq.lock)
{
	struct bnxt_qplib_cq *buddy_cq = NULL;

	buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq);
	if (!buddy_cq)
		__acquire(&cq->hwq.lock);
	else
		spin_lock(&buddy_cq->hwq.lock);
}

static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp,
				       struct bnxt_qplib_cq *cq)
	__releases(&buddy_cq->hwq.lock)
{
	struct bnxt_qplib_cq *buddy_cq = NULL;

	buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq);
	if (!buddy_cq)
		__release(&cq->hwq.lock);
	else
		spin_unlock(&buddy_cq->hwq.lock);
}

void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
{
	unsigned long flags;

	bnxt_qplib_acquire_cq_locks(qp, &flags);
	__bnxt_qplib_add_flush_qp(qp);
	bnxt_qplib_release_cq_locks(qp, &flags);
}

static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp)
{
	if (qp->sq.flushed) {
		qp->sq.flushed = false;
		list_del(&qp->sq_flush);
	}
	if (!qp->srq) {
		if (qp->rq.flushed) {
			qp->rq.flushed = false;
			list_del(&qp->rq_flush);
		}
	}
}

void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp)
{
	unsigned long flags;

	bnxt_qplib_acquire_cq_locks(qp, &flags);
	__clean_cq(qp->scq, (u64)(unsigned long)qp);
	qp->sq.hwq.prod = 0;
	qp->sq.hwq.cons = 0;
	__clean_cq(qp->rcq, (u64)(unsigned long)qp);
	qp->rq.hwq.prod = 0;
	qp->rq.hwq.cons = 0;

	__bnxt_qplib_del_flush_qp(qp);
	bnxt_qplib_release_cq_locks(qp, &flags);
}

static void bnxt_qpn_cqn_sched_task(struct work_struct *work)
{
	struct bnxt_qplib_nq_work *nq_work =
			container_of(work, struct bnxt_qplib_nq_work, work);

	struct bnxt_qplib_cq *cq = nq_work->cq;
	struct bnxt_qplib_nq *nq = nq_work->nq;

	if (cq && nq) {
		spin_lock_bh(&cq->compl_lock);
		if (atomic_read(&cq->arm_state) && nq->cqn_handler) {
			dev_dbg(&nq->pdev->dev,
				"%s:Trigger cq  = %p event nq = %p\n",
				__func__, cq, nq);
			nq->cqn_handler(nq, cq);
		}
		spin_unlock_bh(&cq->compl_lock);
	}
	kfree(nq_work);
}
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279

static void bnxt_qplib_free_qp_hdr_buf(struct bnxt_qplib_res *res,
				       struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_q *rq = &qp->rq;
	struct bnxt_qplib_q *sq = &qp->sq;

	if (qp->rq_hdr_buf)
		dma_free_coherent(&res->pdev->dev,
				  rq->hwq.max_elements * qp->rq_hdr_buf_size,
				  qp->rq_hdr_buf, qp->rq_hdr_buf_map);
	if (qp->sq_hdr_buf)
		dma_free_coherent(&res->pdev->dev,
				  sq->hwq.max_elements * qp->sq_hdr_buf_size,
				  qp->sq_hdr_buf, qp->sq_hdr_buf_map);
	qp->rq_hdr_buf = NULL;
	qp->sq_hdr_buf = NULL;
	qp->rq_hdr_buf_map = 0;
	qp->sq_hdr_buf_map = 0;
	qp->sq_hdr_buf_size = 0;
	qp->rq_hdr_buf_size = 0;
}

static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res,
				       struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_q *rq = &qp->rq;
	struct bnxt_qplib_q *sq = &qp->rq;
	int rc = 0;

	if (qp->sq_hdr_buf_size && sq->hwq.max_elements) {
		qp->sq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
					sq->hwq.max_elements *
					qp->sq_hdr_buf_size,
					&qp->sq_hdr_buf_map, GFP_KERNEL);
		if (!qp->sq_hdr_buf) {
			rc = -ENOMEM;
			dev_err(&res->pdev->dev,
				"QPLIB: Failed to create sq_hdr_buf");
			goto fail;
		}
	}

	if (qp->rq_hdr_buf_size && rq->hwq.max_elements) {
		qp->rq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
						    rq->hwq.max_elements *
						    qp->rq_hdr_buf_size,
						    &qp->rq_hdr_buf_map,
						    GFP_KERNEL);
		if (!qp->rq_hdr_buf) {
			rc = -ENOMEM;
			dev_err(&res->pdev->dev,
				"QPLIB: Failed to create rq_hdr_buf");
			goto fail;
		}
	}
	return 0;

fail:
	bnxt_qplib_free_qp_hdr_buf(res, qp);
	return rc;
}

static void bnxt_qplib_service_nq(unsigned long data)
{
	struct bnxt_qplib_nq *nq = (struct bnxt_qplib_nq *)data;
	struct bnxt_qplib_hwq *hwq = &nq->hwq;
	struct nq_base *nqe, **nq_ptr;
280
	struct bnxt_qplib_cq *cq;
281
	int num_cqne_processed = 0;
282
	int num_srqne_processed = 0;
283 284 285 286 287 288 289 290 291 292 293 294 295 296
	u32 sw_cons, raw_cons;
	u16 type;
	int budget = nq->budget;
	u64 q_handle;

	/* Service the NQ until empty */
	raw_cons = hwq->cons;
	while (budget--) {
		sw_cons = HWQ_CMP(raw_cons, hwq);
		nq_ptr = (struct nq_base **)hwq->pbl_ptr;
		nqe = &nq_ptr[NQE_PG(sw_cons)][NQE_IDX(sw_cons)];
		if (!NQE_CMP_VALID(nqe, raw_cons, hwq->max_elements))
			break;

297 298 299 300 301 302
		/*
		 * The valid test of the entry must be done first before
		 * reading any further.
		 */
		dma_rmb();

303 304 305 306 307 308 309 310 311
		type = le16_to_cpu(nqe->info10_type) & NQ_BASE_TYPE_MASK;
		switch (type) {
		case NQ_BASE_TYPE_CQ_NOTIFICATION:
		{
			struct nq_cn *nqcne = (struct nq_cn *)nqe;

			q_handle = le32_to_cpu(nqcne->cq_handle_low);
			q_handle |= (u64)le32_to_cpu(nqcne->cq_handle_high)
						     << 32;
312 313 314 315 316
			cq = (struct bnxt_qplib_cq *)(unsigned long)q_handle;
			bnxt_qplib_arm_cq_enable(cq);
			spin_lock_bh(&cq->compl_lock);
			atomic_set(&cq->arm_state, 0);
			if (!nq->cqn_handler(nq, (cq)))
317 318 319 320 321
				num_cqne_processed++;
			else
				dev_warn(&nq->pdev->dev,
					 "QPLIB: cqn - type 0x%x not handled",
					 type);
322
			spin_unlock_bh(&cq->compl_lock);
323 324
			break;
		}
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
		case NQ_BASE_TYPE_SRQ_EVENT:
		{
			struct nq_srq_event *nqsrqe =
						(struct nq_srq_event *)nqe;

			q_handle = le32_to_cpu(nqsrqe->srq_handle_low);
			q_handle |= (u64)le32_to_cpu(nqsrqe->srq_handle_high)
				     << 32;
			bnxt_qplib_arm_srq((struct bnxt_qplib_srq *)q_handle,
					   DBR_DBR_TYPE_SRQ_ARMENA);
			if (!nq->srqn_handler(nq,
					      (struct bnxt_qplib_srq *)q_handle,
					      nqsrqe->event))
				num_srqne_processed++;
			else
				dev_warn(&nq->pdev->dev,
					 "QPLIB: SRQ event 0x%x not handled",
					 nqsrqe->event);
			break;
		}
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
		case NQ_BASE_TYPE_DBQ_EVENT:
			break;
		default:
			dev_warn(&nq->pdev->dev,
				 "QPLIB: nqe with type = 0x%x not handled",
				 type);
			break;
		}
		raw_cons++;
	}
	if (hwq->cons != raw_cons) {
		hwq->cons = raw_cons;
		NQ_DB_REARM(nq->bar_reg_iomem, hwq->cons, hwq->max_elements);
	}
}

static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance)
{
	struct bnxt_qplib_nq *nq = dev_instance;
	struct bnxt_qplib_hwq *hwq = &nq->hwq;
	struct nq_base **nq_ptr;
	u32 sw_cons;

	/* Prefetch the NQ element */
	sw_cons = HWQ_CMP(hwq->cons, hwq);
	nq_ptr = (struct nq_base **)nq->hwq.pbl_ptr;
	prefetch(&nq_ptr[NQE_PG(sw_cons)][NQE_IDX(sw_cons)]);

	/* Fan out to CPU affinitized kthreads? */
	tasklet_schedule(&nq->worker);

	return IRQ_HANDLED;
}

void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
{
381 382 383 384
	if (nq->cqn_wq) {
		destroy_workqueue(nq->cqn_wq);
		nq->cqn_wq = NULL;
	}
385 386 387 388 389 390
	/* Make sure the HW is stopped! */
	synchronize_irq(nq->vector);
	tasklet_disable(&nq->worker);
	tasklet_kill(&nq->worker);

	if (nq->requested) {
391
		irq_set_affinity_hint(nq->vector, NULL);
392 393 394 395 396 397 398 399 400 401 402 403 404
		free_irq(nq->vector, nq);
		nq->requested = false;
	}
	if (nq->bar_reg_iomem)
		iounmap(nq->bar_reg_iomem);
	nq->bar_reg_iomem = NULL;

	nq->cqn_handler = NULL;
	nq->srqn_handler = NULL;
	nq->vector = 0;
}

int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
405
			 int nq_idx, int msix_vector, int bar_reg_offset,
406 407 408
			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
					    struct bnxt_qplib_cq *),
			 int (*srqn_handler)(struct bnxt_qplib_nq *nq,
409 410
					     struct bnxt_qplib_srq *,
					     u8 event))
411 412
{
	resource_size_t nq_base;
413
	int rc = -1;
414 415 416

	nq->pdev = pdev;
	nq->vector = msix_vector;
417 418
	if (cqn_handler)
		nq->cqn_handler = cqn_handler;
419

420 421
	if (srqn_handler)
		nq->srqn_handler = srqn_handler;
422 423 424

	tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq);

425 426 427 428 429
	/* Have a task to schedule CQ notifiers in post send case */
	nq->cqn_wq  = create_singlethread_workqueue("bnxt_qplib_nq");
	if (!nq->cqn_wq)
		goto fail;

430
	nq->requested = false;
431 432 433
	memset(nq->name, 0, 32);
	sprintf(nq->name, "bnxt_qplib_nq-%d", nq_idx);
	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
434 435 436 437 438
	if (rc) {
		dev_err(&nq->pdev->dev,
			"Failed to request IRQ for NQ: %#x", rc);
		goto fail;
	}
439 440 441 442 443 444 445 446 447 448

	cpumask_clear(&nq->mask);
	cpumask_set_cpu(nq_idx, &nq->mask);
	rc = irq_set_affinity_hint(nq->vector, &nq->mask);
	if (rc) {
		dev_warn(&nq->pdev->dev,
			 "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
			 nq->vector, nq_idx);
	}

449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
	nq->requested = true;
	nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
	nq->bar_reg_off = bar_reg_offset;
	nq_base = pci_resource_start(pdev, nq->bar_reg);
	if (!nq_base) {
		rc = -ENOMEM;
		goto fail;
	}
	nq->bar_reg_iomem = ioremap_nocache(nq_base + nq->bar_reg_off, 4);
	if (!nq->bar_reg_iomem) {
		rc = -ENOMEM;
		goto fail;
	}
	NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);

	return 0;
fail:
	bnxt_qplib_disable_nq(nq);
	return rc;
}

void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq)
{
472
	if (nq->hwq.max_elements) {
473
		bnxt_qplib_free_hwq(nq->pdev, &nq->hwq);
474 475
		nq->hwq.max_elements = 0;
	}
476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
}

int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq)
{
	nq->pdev = pdev;
	if (!nq->hwq.max_elements ||
	    nq->hwq.max_elements > BNXT_QPLIB_NQE_MAX_CNT)
		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;

	if (bnxt_qplib_alloc_init_hwq(nq->pdev, &nq->hwq, NULL, 0,
				      &nq->hwq.max_elements,
				      BNXT_QPLIB_MAX_NQE_ENTRY_SIZE, 0,
				      PAGE_SIZE, HWQ_TYPE_L2_CMPL))
		return -ENOMEM;

	nq->budget = 8;
	return 0;
}

495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
/* SRQ */
static void bnxt_qplib_arm_srq(struct bnxt_qplib_srq *srq, u32 arm_type)
{
	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
	struct dbr_dbr db_msg = { 0 };
	void __iomem *db;
	u32 sw_prod = 0;

	/* Ring DB */
	sw_prod = (arm_type == DBR_DBR_TYPE_SRQ_ARM) ? srq->threshold :
		   HWQ_CMP(srq_hwq->prod, srq_hwq);
	db_msg.index = cpu_to_le32((sw_prod << DBR_DBR_INDEX_SFT) &
				   DBR_DBR_INDEX_MASK);
	db_msg.type_xid = cpu_to_le32(((srq->id << DBR_DBR_XID_SFT) &
					DBR_DBR_XID_MASK) | arm_type);
	db = (arm_type == DBR_DBR_TYPE_SRQ_ARMENA) ?
		srq->dbr_base : srq->dpi->dbr;
	wmb(); /* barrier before db ring */
	__iowrite64_copy(db, &db_msg, sizeof(db_msg) / sizeof(u64));
}

int bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res,
			   struct bnxt_qplib_srq *srq)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_destroy_srq req;
	struct creq_destroy_srq_resp resp;
	u16 cmd_flags = 0;
	int rc;

	RCFW_CMD_PREP(req, DESTROY_SRQ, cmd_flags);

	/* Configure the request */
	req.srq_cid = cpu_to_le32(srq->id);

	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
		return rc;

	bnxt_qplib_free_hwq(res->pdev, &srq->hwq);
	kfree(srq->swq);
	return 0;
}

int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
			  struct bnxt_qplib_srq *srq)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_create_srq req;
	struct creq_create_srq_resp resp;
	struct bnxt_qplib_pbl *pbl;
	u16 cmd_flags = 0;
	int rc, idx;

	srq->hwq.max_elements = srq->max_wqe;
	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &srq->hwq, srq->sglist,
				       srq->nmap, &srq->hwq.max_elements,
				       BNXT_QPLIB_MAX_RQE_ENTRY_SIZE, 0,
				       PAGE_SIZE, HWQ_TYPE_QUEUE);
	if (rc)
		goto exit;

	srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq),
			   GFP_KERNEL);
560 561
	if (!srq->swq) {
		rc = -ENOMEM;
562
		goto fail;
563
	}
564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728

	RCFW_CMD_PREP(req, CREATE_SRQ, cmd_flags);

	/* Configure the request */
	req.dpi = cpu_to_le32(srq->dpi->dpi);
	req.srq_handle = cpu_to_le64(srq);

	req.srq_size = cpu_to_le16((u16)srq->hwq.max_elements);
	pbl = &srq->hwq.pbl[PBL_LVL_0];
	req.pg_size_lvl = cpu_to_le16((((u16)srq->hwq.level &
				      CMDQ_CREATE_SRQ_LVL_MASK) <<
				      CMDQ_CREATE_SRQ_LVL_SFT) |
				      (pbl->pg_size == ROCE_PG_SIZE_4K ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_4K :
				       pbl->pg_size == ROCE_PG_SIZE_8K ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_8K :
				       pbl->pg_size == ROCE_PG_SIZE_64K ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_64K :
				       pbl->pg_size == ROCE_PG_SIZE_2M ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_2M :
				       pbl->pg_size == ROCE_PG_SIZE_8M ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_8M :
				       pbl->pg_size == ROCE_PG_SIZE_1G ?
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_1G :
				       CMDQ_CREATE_SRQ_PG_SIZE_PG_4K));
	req.pbl = cpu_to_le64(pbl->pg_map_arr[0]);
	req.pd_id = cpu_to_le32(srq->pd->id);
	req.eventq_id = cpu_to_le16(srq->eventq_hw_ring_id);

	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
		goto fail;

	spin_lock_init(&srq->lock);
	srq->start_idx = 0;
	srq->last_idx = srq->hwq.max_elements - 1;
	for (idx = 0; idx < srq->hwq.max_elements; idx++)
		srq->swq[idx].next_idx = idx + 1;
	srq->swq[srq->last_idx].next_idx = -1;

	srq->id = le32_to_cpu(resp.xid);
	srq->dbr_base = res->dpi_tbl.dbr_bar_reg_iomem;
	if (srq->threshold)
		bnxt_qplib_arm_srq(srq, DBR_DBR_TYPE_SRQ_ARMENA);
	srq->arm_req = false;

	return 0;
fail:
	bnxt_qplib_free_hwq(res->pdev, &srq->hwq);
	kfree(srq->swq);
exit:
	return rc;
}

int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res,
			  struct bnxt_qplib_srq *srq)
{
	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
	u32 sw_prod, sw_cons, count = 0;

	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
	sw_cons = HWQ_CMP(srq_hwq->cons, srq_hwq);

	count = sw_prod > sw_cons ? sw_prod - sw_cons :
				    srq_hwq->max_elements - sw_cons + sw_prod;
	if (count > srq->threshold) {
		srq->arm_req = false;
		bnxt_qplib_arm_srq(srq, DBR_DBR_TYPE_SRQ_ARM);
	} else {
		/* Deferred arming */
		srq->arm_req = true;
	}

	return 0;
}

int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
			 struct bnxt_qplib_srq *srq)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_query_srq req;
	struct creq_query_srq_resp resp;
	struct bnxt_qplib_rcfw_sbuf *sbuf;
	struct creq_query_srq_resp_sb *sb;
	u16 cmd_flags = 0;
	int rc = 0;

	RCFW_CMD_PREP(req, QUERY_SRQ, cmd_flags);
	req.srq_cid = cpu_to_le32(srq->id);

	/* Configure the request */
	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
	if (!sbuf)
		return -ENOMEM;
	sb = sbuf->sb;
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
					  (void *)sbuf, 0);
	srq->threshold = le16_to_cpu(sb->srq_limit);
	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);

	return rc;
}

int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq,
			     struct bnxt_qplib_swqe *wqe)
{
	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
	struct rq_wqe *srqe, **srqe_ptr;
	struct sq_sge *hw_sge;
	u32 sw_prod, sw_cons, count = 0;
	int i, rc = 0, next;

	spin_lock(&srq_hwq->lock);
	if (srq->start_idx == srq->last_idx) {
		dev_err(&srq_hwq->pdev->dev, "QPLIB: FP: SRQ (0x%x) is full!",
			srq->id);
		rc = -EINVAL;
		spin_unlock(&srq_hwq->lock);
		goto done;
	}
	next = srq->start_idx;
	srq->start_idx = srq->swq[next].next_idx;
	spin_unlock(&srq_hwq->lock);

	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
	srqe_ptr = (struct rq_wqe **)srq_hwq->pbl_ptr;
	srqe = &srqe_ptr[RQE_PG(sw_prod)][RQE_IDX(sw_prod)];
	memset(srqe, 0, BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
	/* Calculate wqe_size16 and data_len */
	for (i = 0, hw_sge = (struct sq_sge *)srqe->data;
	     i < wqe->num_sge; i++, hw_sge++) {
		hw_sge->va_or_pa = cpu_to_le64(wqe->sg_list[i].addr);
		hw_sge->l_key = cpu_to_le32(wqe->sg_list[i].lkey);
		hw_sge->size = cpu_to_le32(wqe->sg_list[i].size);
	}
	srqe->wqe_type = wqe->type;
	srqe->flags = wqe->flags;
	srqe->wqe_size = wqe->num_sge +
			((offsetof(typeof(*srqe), data) + 15) >> 4);
	srqe->wr_id[0] = cpu_to_le32((u32)next);
	srq->swq[next].wr_id = wqe->wr_id;

	srq_hwq->prod++;

	spin_lock(&srq_hwq->lock);
	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
	/* retaining srq_hwq->cons for this logic
	 * actually the lock is only required to
	 * read srq_hwq->cons.
	 */
	sw_cons = HWQ_CMP(srq_hwq->cons, srq_hwq);
	count = sw_prod > sw_cons ? sw_prod - sw_cons :
				    srq_hwq->max_elements - sw_cons + sw_prod;
	spin_unlock(&srq_hwq->lock);
	/* Ring DB */
	bnxt_qplib_arm_srq(srq, DBR_DBR_TYPE_SRQ);
	if (srq->arm_req == true && count > srq->threshold) {
		srq->arm_req = false;
		bnxt_qplib_arm_srq(srq, DBR_DBR_TYPE_SRQ_ARM);
	}
done:
	return rc;
}

729 730 731 732 733
/* QP */
int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_create_qp1 req;
734
	struct creq_create_qp1_resp resp;
735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843
	struct bnxt_qplib_pbl *pbl;
	struct bnxt_qplib_q *sq = &qp->sq;
	struct bnxt_qplib_q *rq = &qp->rq;
	int rc;
	u16 cmd_flags = 0;
	u32 qp_flags = 0;

	RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags);

	/* General */
	req.type = qp->type;
	req.dpi = cpu_to_le32(qp->dpi->dpi);
	req.qp_handle = cpu_to_le64(qp->qp_handle);

	/* SQ */
	sq->hwq.max_elements = sq->max_wqe;
	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &sq->hwq, NULL, 0,
				       &sq->hwq.max_elements,
				       BNXT_QPLIB_MAX_SQE_ENTRY_SIZE, 0,
				       PAGE_SIZE, HWQ_TYPE_QUEUE);
	if (rc)
		goto exit;

	sq->swq = kcalloc(sq->hwq.max_elements, sizeof(*sq->swq), GFP_KERNEL);
	if (!sq->swq) {
		rc = -ENOMEM;
		goto fail_sq;
	}
	pbl = &sq->hwq.pbl[PBL_LVL_0];
	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
	req.sq_pg_size_sq_lvl =
		((sq->hwq.level & CMDQ_CREATE_QP1_SQ_LVL_MASK)
				<<  CMDQ_CREATE_QP1_SQ_LVL_SFT) |
		(pbl->pg_size == ROCE_PG_SIZE_4K ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K :
		 pbl->pg_size == ROCE_PG_SIZE_8K ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8K :
		 pbl->pg_size == ROCE_PG_SIZE_64K ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_64K :
		 pbl->pg_size == ROCE_PG_SIZE_2M ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_2M :
		 pbl->pg_size == ROCE_PG_SIZE_8M ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8M :
		 pbl->pg_size == ROCE_PG_SIZE_1G ?
				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G :
		 CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K);

	if (qp->scq)
		req.scq_cid = cpu_to_le32(qp->scq->id);

	qp_flags |= CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE;

	/* RQ */
	if (rq->max_wqe) {
		rq->hwq.max_elements = qp->rq.max_wqe;
		rc = bnxt_qplib_alloc_init_hwq(res->pdev, &rq->hwq, NULL, 0,
					       &rq->hwq.max_elements,
					       BNXT_QPLIB_MAX_RQE_ENTRY_SIZE, 0,
					       PAGE_SIZE, HWQ_TYPE_QUEUE);
		if (rc)
			goto fail_sq;

		rq->swq = kcalloc(rq->hwq.max_elements, sizeof(*rq->swq),
				  GFP_KERNEL);
		if (!rq->swq) {
			rc = -ENOMEM;
			goto fail_rq;
		}
		pbl = &rq->hwq.pbl[PBL_LVL_0];
		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
		req.rq_pg_size_rq_lvl =
			((rq->hwq.level & CMDQ_CREATE_QP1_RQ_LVL_MASK) <<
			 CMDQ_CREATE_QP1_RQ_LVL_SFT) |
				(pbl->pg_size == ROCE_PG_SIZE_4K ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K :
				 pbl->pg_size == ROCE_PG_SIZE_8K ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8K :
				 pbl->pg_size == ROCE_PG_SIZE_64K ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_64K :
				 pbl->pg_size == ROCE_PG_SIZE_2M ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_2M :
				 pbl->pg_size == ROCE_PG_SIZE_8M ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8M :
				 pbl->pg_size == ROCE_PG_SIZE_1G ?
					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G :
				 CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K);
		if (qp->rcq)
			req.rcq_cid = cpu_to_le32(qp->rcq->id);
	}

	/* Header buffer - allow hdr_buf pass in */
	rc = bnxt_qplib_alloc_qp_hdr_buf(res, qp);
	if (rc) {
		rc = -ENOMEM;
		goto fail;
	}
	req.qp_flags = cpu_to_le32(qp_flags);
	req.sq_size = cpu_to_le32(sq->hwq.max_elements);
	req.rq_size = cpu_to_le32(rq->hwq.max_elements);

	req.sq_fwo_sq_sge =
		cpu_to_le16((sq->max_sge & CMDQ_CREATE_QP1_SQ_SGE_MASK) <<
			    CMDQ_CREATE_QP1_SQ_SGE_SFT);
	req.rq_fwo_rq_sge =
		cpu_to_le16((rq->max_sge & CMDQ_CREATE_QP1_RQ_SGE_MASK) <<
			    CMDQ_CREATE_QP1_RQ_SGE_SFT);

	req.pd_id = cpu_to_le32(qp->pd->id);

844 845 846
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
847
		goto fail;
848 849

	qp->id = le32_to_cpu(resp.xid);
850
	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
851 852
	rcfw->qp_tbl[qp->id].qp_id = qp->id;
	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872

	return 0;

fail:
	bnxt_qplib_free_qp_hdr_buf(res, qp);
fail_rq:
	bnxt_qplib_free_hwq(res->pdev, &rq->hwq);
	kfree(rq->swq);
fail_sq:
	bnxt_qplib_free_hwq(res->pdev, &sq->hwq);
	kfree(sq->swq);
exit:
	return rc;
}

int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr;
	struct cmdq_create_qp req;
873
	struct creq_create_qp_resp resp;
874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996
	struct bnxt_qplib_pbl *pbl;
	struct sq_psn_search **psn_search_ptr;
	unsigned long int psn_search, poff = 0;
	struct bnxt_qplib_q *sq = &qp->sq;
	struct bnxt_qplib_q *rq = &qp->rq;
	struct bnxt_qplib_hwq *xrrq;
	int i, rc, req_size, psn_sz;
	u16 cmd_flags = 0, max_ssge;
	u32 sw_prod, qp_flags = 0;

	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);

	/* General */
	req.type = qp->type;
	req.dpi = cpu_to_le32(qp->dpi->dpi);
	req.qp_handle = cpu_to_le64(qp->qp_handle);

	/* SQ */
	psn_sz = (qp->type == CMDQ_CREATE_QP_TYPE_RC) ?
		 sizeof(struct sq_psn_search) : 0;
	sq->hwq.max_elements = sq->max_wqe;
	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &sq->hwq, sq->sglist,
				       sq->nmap, &sq->hwq.max_elements,
				       BNXT_QPLIB_MAX_SQE_ENTRY_SIZE,
				       psn_sz,
				       PAGE_SIZE, HWQ_TYPE_QUEUE);
	if (rc)
		goto exit;

	sq->swq = kcalloc(sq->hwq.max_elements, sizeof(*sq->swq), GFP_KERNEL);
	if (!sq->swq) {
		rc = -ENOMEM;
		goto fail_sq;
	}
	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
	if (psn_sz) {
		psn_search_ptr = (struct sq_psn_search **)
				  &hw_sq_send_ptr[get_sqe_pg
					(sq->hwq.max_elements)];
		psn_search = (unsigned long int)
			      &hw_sq_send_ptr[get_sqe_pg(sq->hwq.max_elements)]
			      [get_sqe_idx(sq->hwq.max_elements)];
		if (psn_search & ~PAGE_MASK) {
			/* If the psn_search does not start on a page boundary,
			 * then calculate the offset
			 */
			poff = (psn_search & ~PAGE_MASK) /
				BNXT_QPLIB_MAX_PSNE_ENTRY_SIZE;
		}
		for (i = 0; i < sq->hwq.max_elements; i++)
			sq->swq[i].psn_search =
				&psn_search_ptr[get_psne_pg(i + poff)]
					       [get_psne_idx(i + poff)];
	}
	pbl = &sq->hwq.pbl[PBL_LVL_0];
	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
	req.sq_pg_size_sq_lvl =
		((sq->hwq.level & CMDQ_CREATE_QP_SQ_LVL_MASK)
				 <<  CMDQ_CREATE_QP_SQ_LVL_SFT) |
		(pbl->pg_size == ROCE_PG_SIZE_4K ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K :
		 pbl->pg_size == ROCE_PG_SIZE_8K ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8K :
		 pbl->pg_size == ROCE_PG_SIZE_64K ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_64K :
		 pbl->pg_size == ROCE_PG_SIZE_2M ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_2M :
		 pbl->pg_size == ROCE_PG_SIZE_8M ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8M :
		 pbl->pg_size == ROCE_PG_SIZE_1G ?
				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G :
		 CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K);

	/* initialize all SQ WQEs to LOCAL_INVALID (sq prep for hw fetch) */
	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
	for (sw_prod = 0; sw_prod < sq->hwq.max_elements; sw_prod++) {
		hw_sq_send_hdr = &hw_sq_send_ptr[get_sqe_pg(sw_prod)]
						[get_sqe_idx(sw_prod)];
		hw_sq_send_hdr->wqe_type = SQ_BASE_WQE_TYPE_LOCAL_INVALID;
	}

	if (qp->scq)
		req.scq_cid = cpu_to_le32(qp->scq->id);

	qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_RESERVED_LKEY_ENABLE;
	qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_FR_PMR_ENABLED;
	if (qp->sig_type)
		qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_FORCE_COMPLETION;

	/* RQ */
	if (rq->max_wqe) {
		rq->hwq.max_elements = rq->max_wqe;
		rc = bnxt_qplib_alloc_init_hwq(res->pdev, &rq->hwq, rq->sglist,
					       rq->nmap, &rq->hwq.max_elements,
					       BNXT_QPLIB_MAX_RQE_ENTRY_SIZE, 0,
					       PAGE_SIZE, HWQ_TYPE_QUEUE);
		if (rc)
			goto fail_sq;

		rq->swq = kcalloc(rq->hwq.max_elements, sizeof(*rq->swq),
				  GFP_KERNEL);
		if (!rq->swq) {
			rc = -ENOMEM;
			goto fail_rq;
		}
		pbl = &rq->hwq.pbl[PBL_LVL_0];
		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
		req.rq_pg_size_rq_lvl =
			((rq->hwq.level & CMDQ_CREATE_QP_RQ_LVL_MASK) <<
			 CMDQ_CREATE_QP_RQ_LVL_SFT) |
				(pbl->pg_size == ROCE_PG_SIZE_4K ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K :
				 pbl->pg_size == ROCE_PG_SIZE_8K ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8K :
				 pbl->pg_size == ROCE_PG_SIZE_64K ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_64K :
				 pbl->pg_size == ROCE_PG_SIZE_2M ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_2M :
				 pbl->pg_size == ROCE_PG_SIZE_8M ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8M :
				 pbl->pg_size == ROCE_PG_SIZE_1G ?
					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G :
				 CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K);
997 998 999 1000 1001 1002
	} else {
		/* SRQ */
		if (qp->srq) {
			qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_SRQ_USED;
			req.srq_cid = cpu_to_le32(qp->srq->id);
		}
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
	}

	if (qp->rcq)
		req.rcq_cid = cpu_to_le32(qp->rcq->id);
	req.qp_flags = cpu_to_le32(qp_flags);
	req.sq_size = cpu_to_le32(sq->hwq.max_elements);
	req.rq_size = cpu_to_le32(rq->hwq.max_elements);
	qp->sq_hdr_buf = NULL;
	qp->rq_hdr_buf = NULL;

	rc = bnxt_qplib_alloc_qp_hdr_buf(res, qp);
	if (rc)
		goto fail_rq;

	/* CTRL-22434: Irrespective of the requested SGE count on the SQ
	 * always create the QP with max send sges possible if the requested
	 * inline size is greater than 0.
	 */
	max_ssge = qp->max_inline_data ? 6 : sq->max_sge;
	req.sq_fwo_sq_sge = cpu_to_le16(
				((max_ssge & CMDQ_CREATE_QP_SQ_SGE_MASK)
				 << CMDQ_CREATE_QP_SQ_SGE_SFT) | 0);
	req.rq_fwo_rq_sge = cpu_to_le16(
				((rq->max_sge & CMDQ_CREATE_QP_RQ_SGE_MASK)
				 << CMDQ_CREATE_QP_RQ_SGE_SFT) | 0);
	/* ORRQ and IRRQ */
	if (psn_sz) {
		xrrq = &qp->orrq;
		xrrq->max_elements =
			ORD_LIMIT_TO_ORRQ_SLOTS(qp->max_rd_atomic);
		req_size = xrrq->max_elements *
			   BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE + PAGE_SIZE - 1;
		req_size &= ~(PAGE_SIZE - 1);
		rc = bnxt_qplib_alloc_init_hwq(res->pdev, xrrq, NULL, 0,
					       &xrrq->max_elements,
					       BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE,
					       0, req_size, HWQ_TYPE_CTX);
		if (rc)
			goto fail_buf_free;
		pbl = &xrrq->pbl[PBL_LVL_0];
		req.orrq_addr = cpu_to_le64(pbl->pg_map_arr[0]);

		xrrq = &qp->irrq;
		xrrq->max_elements = IRD_LIMIT_TO_IRRQ_SLOTS(
						qp->max_dest_rd_atomic);
		req_size = xrrq->max_elements *
			   BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE + PAGE_SIZE - 1;
		req_size &= ~(PAGE_SIZE - 1);

		rc = bnxt_qplib_alloc_init_hwq(res->pdev, xrrq, NULL, 0,
					       &xrrq->max_elements,
					       BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE,
					       0, req_size, HWQ_TYPE_CTX);
		if (rc)
			goto fail_orrq;

		pbl = &xrrq->pbl[PBL_LVL_0];
		req.irrq_addr = cpu_to_le64(pbl->pg_map_arr[0]);
	}
	req.pd_id = cpu_to_le32(qp->pd->id);

1064 1065 1066
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
1067
		goto fail;
1068 1069

	qp->id = le32_to_cpu(resp.xid);
1070
	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
1071 1072 1073 1074
	INIT_LIST_HEAD(&qp->sq_flush);
	INIT_LIST_HEAD(&qp->rq_flush);
	rcfw->qp_tbl[qp->id].qp_id = qp->id;
	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
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 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 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

	return 0;

fail:
	if (qp->irrq.max_elements)
		bnxt_qplib_free_hwq(res->pdev, &qp->irrq);
fail_orrq:
	if (qp->orrq.max_elements)
		bnxt_qplib_free_hwq(res->pdev, &qp->orrq);
fail_buf_free:
	bnxt_qplib_free_qp_hdr_buf(res, qp);
fail_rq:
	bnxt_qplib_free_hwq(res->pdev, &rq->hwq);
	kfree(rq->swq);
fail_sq:
	bnxt_qplib_free_hwq(res->pdev, &sq->hwq);
	kfree(sq->swq);
exit:
	return rc;
}

static void __modify_flags_from_init_state(struct bnxt_qplib_qp *qp)
{
	switch (qp->state) {
	case CMDQ_MODIFY_QP_NEW_STATE_RTR:
		/* INIT->RTR, configure the path_mtu to the default
		 * 2048 if not being requested
		 */
		if (!(qp->modify_flags &
		    CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU)) {
			qp->modify_flags |=
				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
			qp->path_mtu =
				CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
		}
		qp->modify_flags &=
			~CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
		/* Bono FW require the max_dest_rd_atomic to be >= 1 */
		if (qp->max_dest_rd_atomic < 1)
			qp->max_dest_rd_atomic = 1;
		qp->modify_flags &= ~CMDQ_MODIFY_QP_MODIFY_MASK_SRC_MAC;
		/* Bono FW 20.6.5 requires SGID_INDEX configuration */
		if (!(qp->modify_flags &
		    CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX)) {
			qp->modify_flags |=
				CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX;
			qp->ah.sgid_index = 0;
		}
		break;
	default:
		break;
	}
}

static void __modify_flags_from_rtr_state(struct bnxt_qplib_qp *qp)
{
	switch (qp->state) {
	case CMDQ_MODIFY_QP_NEW_STATE_RTS:
		/* Bono FW requires the max_rd_atomic to be >= 1 */
		if (qp->max_rd_atomic < 1)
			qp->max_rd_atomic = 1;
		/* Bono FW does not allow PKEY_INDEX,
		 * DGID, FLOW_LABEL, SGID_INDEX, HOP_LIMIT,
		 * TRAFFIC_CLASS, DEST_MAC, PATH_MTU, RQ_PSN,
		 * MIN_RNR_TIMER, MAX_DEST_RD_ATOMIC, DEST_QP_ID
		 * modification
		 */
		qp->modify_flags &=
			~(CMDQ_MODIFY_QP_MODIFY_MASK_PKEY |
			  CMDQ_MODIFY_QP_MODIFY_MASK_DGID |
			  CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL |
			  CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX |
			  CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT |
			  CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS |
			  CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC |
			  CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU |
			  CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN |
			  CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER |
			  CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC |
			  CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID);
		break;
	default:
		break;
	}
}

static void __filter_modify_flags(struct bnxt_qplib_qp *qp)
{
	switch (qp->cur_qp_state) {
	case CMDQ_MODIFY_QP_NEW_STATE_RESET:
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_INIT:
		__modify_flags_from_init_state(qp);
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_RTR:
		__modify_flags_from_rtr_state(qp);
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_RTS:
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_SQD:
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_SQE:
		break;
	case CMDQ_MODIFY_QP_NEW_STATE_ERR:
		break;
	default:
		break;
	}
}

int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_modify_qp req;
1189
	struct creq_modify_qp_resp resp;
1190 1191 1192
	u16 cmd_flags = 0, pkey;
	u32 temp32[4];
	u32 bmask;
1193
	int rc;
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 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 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

	RCFW_CMD_PREP(req, MODIFY_QP, cmd_flags);

	/* Filter out the qp_attr_mask based on the state->new transition */
	__filter_modify_flags(qp);
	bmask = qp->modify_flags;
	req.modify_mask = cpu_to_le32(qp->modify_flags);
	req.qp_cid = cpu_to_le32(qp->id);
	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_STATE) {
		req.network_type_en_sqd_async_notify_new_state =
				(qp->state & CMDQ_MODIFY_QP_NEW_STATE_MASK) |
				(qp->en_sqd_async_notify ?
					CMDQ_MODIFY_QP_EN_SQD_ASYNC_NOTIFY : 0);
	}
	req.network_type_en_sqd_async_notify_new_state |= qp->nw_type;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS)
		req.access = qp->access;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_PKEY) {
		if (!bnxt_qplib_get_pkey(res, &res->pkey_tbl,
					 qp->pkey_index, &pkey))
			req.pkey = cpu_to_le16(pkey);
	}
	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_QKEY)
		req.qkey = cpu_to_le32(qp->qkey);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DGID) {
		memcpy(temp32, qp->ah.dgid.data, sizeof(struct bnxt_qplib_gid));
		req.dgid[0] = cpu_to_le32(temp32[0]);
		req.dgid[1] = cpu_to_le32(temp32[1]);
		req.dgid[2] = cpu_to_le32(temp32[2]);
		req.dgid[3] = cpu_to_le32(temp32[3]);
	}
	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL)
		req.flow_label = cpu_to_le32(qp->ah.flow_label);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX)
		req.sgid_index = cpu_to_le16(res->sgid_tbl.hw_id
					     [qp->ah.sgid_index]);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT)
		req.hop_limit = qp->ah.hop_limit;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS)
		req.traffic_class = qp->ah.traffic_class;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC)
		memcpy(req.dest_mac, qp->ah.dmac, 6);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU)
		req.path_mtu = qp->path_mtu;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT)
		req.timeout = qp->timeout;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT)
		req.retry_cnt = qp->retry_cnt;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY)
		req.rnr_retry = qp->rnr_retry;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER)
		req.min_rnr_timer = qp->min_rnr_timer;

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN)
		req.rq_psn = cpu_to_le32(qp->rq.psn);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN)
		req.sq_psn = cpu_to_le32(qp->sq.psn);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC)
		req.max_rd_atomic =
			ORD_LIMIT_TO_ORRQ_SLOTS(qp->max_rd_atomic);

	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC)
		req.max_dest_rd_atomic =
			IRD_LIMIT_TO_IRRQ_SLOTS(qp->max_dest_rd_atomic);

	req.sq_size = cpu_to_le32(qp->sq.hwq.max_elements);
	req.rq_size = cpu_to_le32(qp->rq.hwq.max_elements);
	req.sq_sge = cpu_to_le16(qp->sq.max_sge);
	req.rq_sge = cpu_to_le16(qp->rq.max_sge);
	req.max_inline_data = cpu_to_le32(qp->max_inline_data);
	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID)
		req.dest_qp_id = cpu_to_le32(qp->dest_qpn);

	req.vlan_pcp_vlan_dei_vlan_id = cpu_to_le16(qp->vlan_id);

1283 1284 1285 1286
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
		return rc;
1287 1288 1289 1290 1291 1292 1293 1294
	qp->cur_qp_state = qp->state;
	return 0;
}

int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_query_qp req;
1295 1296
	struct creq_query_qp_resp resp;
	struct bnxt_qplib_rcfw_sbuf *sbuf;
1297 1298 1299
	struct creq_query_qp_resp_sb *sb;
	u16 cmd_flags = 0;
	u32 temp32[4];
1300
	int i, rc = 0;
1301 1302 1303

	RCFW_CMD_PREP(req, QUERY_QP, cmd_flags);

1304 1305 1306 1307 1308
	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
	if (!sbuf)
		return -ENOMEM;
	sb = sbuf->sb;

1309 1310
	req.qp_cid = cpu_to_le32(qp->id);
	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
1311 1312 1313 1314
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
					  (void *)sbuf, 0);
	if (rc)
		goto bail;
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
	/* Extract the context from the side buffer */
	qp->state = sb->en_sqd_async_notify_state &
			CREQ_QUERY_QP_RESP_SB_STATE_MASK;
	qp->en_sqd_async_notify = sb->en_sqd_async_notify_state &
				  CREQ_QUERY_QP_RESP_SB_EN_SQD_ASYNC_NOTIFY ?
				  true : false;
	qp->access = sb->access;
	qp->pkey_index = le16_to_cpu(sb->pkey);
	qp->qkey = le32_to_cpu(sb->qkey);

	temp32[0] = le32_to_cpu(sb->dgid[0]);
	temp32[1] = le32_to_cpu(sb->dgid[1]);
	temp32[2] = le32_to_cpu(sb->dgid[2]);
	temp32[3] = le32_to_cpu(sb->dgid[3]);
	memcpy(qp->ah.dgid.data, temp32, sizeof(qp->ah.dgid.data));

	qp->ah.flow_label = le32_to_cpu(sb->flow_label);

	qp->ah.sgid_index = 0;
	for (i = 0; i < res->sgid_tbl.max; i++) {
		if (res->sgid_tbl.hw_id[i] == le16_to_cpu(sb->sgid_index)) {
			qp->ah.sgid_index = i;
			break;
		}
	}
	if (i == res->sgid_tbl.max)
		dev_warn(&res->pdev->dev, "QPLIB: SGID not found??");

	qp->ah.hop_limit = sb->hop_limit;
	qp->ah.traffic_class = sb->traffic_class;
	memcpy(qp->ah.dmac, sb->dest_mac, 6);
	qp->ah.vlan_id = (le16_to_cpu(sb->path_mtu_dest_vlan_id) &
				CREQ_QUERY_QP_RESP_SB_VLAN_ID_MASK) >>
				CREQ_QUERY_QP_RESP_SB_VLAN_ID_SFT;
	qp->path_mtu = (le16_to_cpu(sb->path_mtu_dest_vlan_id) &
				    CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK) >>
				    CREQ_QUERY_QP_RESP_SB_PATH_MTU_SFT;
	qp->timeout = sb->timeout;
	qp->retry_cnt = sb->retry_cnt;
	qp->rnr_retry = sb->rnr_retry;
	qp->min_rnr_timer = sb->min_rnr_timer;
	qp->rq.psn = le32_to_cpu(sb->rq_psn);
	qp->max_rd_atomic = ORRQ_SLOTS_TO_ORD_LIMIT(sb->max_rd_atomic);
	qp->sq.psn = le32_to_cpu(sb->sq_psn);
	qp->max_dest_rd_atomic =
			IRRQ_SLOTS_TO_IRD_LIMIT(sb->max_dest_rd_atomic);
	qp->sq.max_wqe = qp->sq.hwq.max_elements;
	qp->rq.max_wqe = qp->rq.hwq.max_elements;
	qp->sq.max_sge = le16_to_cpu(sb->sq_sge);
	qp->rq.max_sge = le16_to_cpu(sb->rq_sge);
	qp->max_inline_data = le32_to_cpu(sb->max_inline_data);
	qp->dest_qpn = le32_to_cpu(sb->dest_qp_id);
	memcpy(qp->smac, sb->src_mac, 6);
	qp->vlan_id = le16_to_cpu(sb->vlan_pcp_vlan_dei_vlan_id);
1369 1370 1371
bail:
	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
	return rc;
1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
}

static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp)
{
	struct bnxt_qplib_hwq *cq_hwq = &cq->hwq;
	struct cq_base *hw_cqe, **hw_cqe_ptr;
	int i;

	for (i = 0; i < cq_hwq->max_elements; i++) {
		hw_cqe_ptr = (struct cq_base **)cq_hwq->pbl_ptr;
		hw_cqe = &hw_cqe_ptr[CQE_PG(i)][CQE_IDX(i)];
		if (!CQE_CMP_VALID(hw_cqe, i, cq_hwq->max_elements))
			continue;
1385 1386 1387 1388 1389
		/*
		 * The valid test of the entry must be done first before
		 * reading any further.
		 */
		dma_rmb();
1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420
		switch (hw_cqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK) {
		case CQ_BASE_CQE_TYPE_REQ:
		case CQ_BASE_CQE_TYPE_TERMINAL:
		{
			struct cq_req *cqe = (struct cq_req *)hw_cqe;

			if (qp == le64_to_cpu(cqe->qp_handle))
				cqe->qp_handle = 0;
			break;
		}
		case CQ_BASE_CQE_TYPE_RES_RC:
		case CQ_BASE_CQE_TYPE_RES_UD:
		case CQ_BASE_CQE_TYPE_RES_RAWETH_QP1:
		{
			struct cq_res_rc *cqe = (struct cq_res_rc *)hw_cqe;

			if (qp == le64_to_cpu(cqe->qp_handle))
				cqe->qp_handle = 0;
			break;
		}
		default:
			break;
		}
	}
}

int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
			  struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_destroy_qp req;
1421
	struct creq_destroy_qp_resp resp;
1422 1423
	unsigned long flags;
	u16 cmd_flags = 0;
1424
	int rc;
1425

1426 1427 1428
	rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID;
	rcfw->qp_tbl[qp->id].qp_handle = NULL;

1429 1430 1431
	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);

	req.qp_cid = cpu_to_le32(qp->id);
1432 1433
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
1434 1435 1436
	if (rc) {
		rcfw->qp_tbl[qp->id].qp_id = qp->id;
		rcfw->qp_tbl[qp->id].qp_handle = qp;
1437
		return rc;
1438
	}
1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542

	/* Must walk the associated CQs to nullified the QP ptr */
	spin_lock_irqsave(&qp->scq->hwq.lock, flags);

	__clean_cq(qp->scq, (u64)(unsigned long)qp);

	if (qp->rcq && qp->rcq != qp->scq) {
		spin_lock(&qp->rcq->hwq.lock);
		__clean_cq(qp->rcq, (u64)(unsigned long)qp);
		spin_unlock(&qp->rcq->hwq.lock);
	}

	spin_unlock_irqrestore(&qp->scq->hwq.lock, flags);

	bnxt_qplib_free_qp_hdr_buf(res, qp);
	bnxt_qplib_free_hwq(res->pdev, &qp->sq.hwq);
	kfree(qp->sq.swq);

	bnxt_qplib_free_hwq(res->pdev, &qp->rq.hwq);
	kfree(qp->rq.swq);

	if (qp->irrq.max_elements)
		bnxt_qplib_free_hwq(res->pdev, &qp->irrq);
	if (qp->orrq.max_elements)
		bnxt_qplib_free_hwq(res->pdev, &qp->orrq);

	return 0;
}

void *bnxt_qplib_get_qp1_sq_buf(struct bnxt_qplib_qp *qp,
				struct bnxt_qplib_sge *sge)
{
	struct bnxt_qplib_q *sq = &qp->sq;
	u32 sw_prod;

	memset(sge, 0, sizeof(*sge));

	if (qp->sq_hdr_buf) {
		sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
		sge->addr = (dma_addr_t)(qp->sq_hdr_buf_map +
					 sw_prod * qp->sq_hdr_buf_size);
		sge->lkey = 0xFFFFFFFF;
		sge->size = qp->sq_hdr_buf_size;
		return qp->sq_hdr_buf + sw_prod * sge->size;
	}
	return NULL;
}

u32 bnxt_qplib_get_rq_prod_index(struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_q *rq = &qp->rq;

	return HWQ_CMP(rq->hwq.prod, &rq->hwq);
}

dma_addr_t bnxt_qplib_get_qp_buf_from_index(struct bnxt_qplib_qp *qp, u32 index)
{
	return (qp->rq_hdr_buf_map + index * qp->rq_hdr_buf_size);
}

void *bnxt_qplib_get_qp1_rq_buf(struct bnxt_qplib_qp *qp,
				struct bnxt_qplib_sge *sge)
{
	struct bnxt_qplib_q *rq = &qp->rq;
	u32 sw_prod;

	memset(sge, 0, sizeof(*sge));

	if (qp->rq_hdr_buf) {
		sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
		sge->addr = (dma_addr_t)(qp->rq_hdr_buf_map +
					 sw_prod * qp->rq_hdr_buf_size);
		sge->lkey = 0xFFFFFFFF;
		sge->size = qp->rq_hdr_buf_size;
		return qp->rq_hdr_buf + sw_prod * sge->size;
	}
	return NULL;
}

void bnxt_qplib_post_send_db(struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_q *sq = &qp->sq;
	struct dbr_dbr db_msg = { 0 };
	u32 sw_prod;

	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);

	db_msg.index = cpu_to_le32((sw_prod << DBR_DBR_INDEX_SFT) &
				   DBR_DBR_INDEX_MASK);
	db_msg.type_xid =
		cpu_to_le32(((qp->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
			    DBR_DBR_TYPE_SQ);
	/* Flush all the WQE writes to HW */
	wmb();
	__iowrite64_copy(qp->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
}

int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
			 struct bnxt_qplib_swqe *wqe)
{
	struct bnxt_qplib_q *sq = &qp->sq;
	struct bnxt_qplib_swq *swq;
	struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr;
	struct sq_sge *hw_sge;
1543 1544
	struct bnxt_qplib_nq_work *nq_work = NULL;
	bool sch_handler = false;
1545 1546 1547 1548 1549 1550
	u32 sw_prod;
	u8 wqe_size16;
	int i, rc = 0, data_len = 0, pkt_num = 0;
	__le32 temp32;

	if (qp->state != CMDQ_MODIFY_QP_NEW_STATE_RTS) {
1551 1552 1553 1554 1555 1556 1557
		if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
			sch_handler = true;
			dev_dbg(&sq->hwq.pdev->dev,
				"%s Error QP. Scheduling for poll_cq\n",
				__func__);
			goto queue_err;
		}
1558
	}
1559 1560 1561 1562 1563 1564

	if (bnxt_qplib_queue_full(sq)) {
		dev_err(&sq->hwq.pdev->dev,
			"QPLIB: prod = %#x cons = %#x qdepth = %#x delta = %#x",
			sq->hwq.prod, sq->hwq.cons, sq->hwq.max_elements,
			sq->q_full_delta);
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
		rc = -ENOMEM;
		goto done;
	}
	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
	swq = &sq->swq[sw_prod];
	swq->wr_id = wqe->wr_id;
	swq->type = wqe->type;
	swq->flags = wqe->flags;
	if (qp->sig_type)
		swq->flags |= SQ_SEND_FLAGS_SIGNAL_COMP;
	swq->start_psn = sq->psn & BTH_PSN_MASK;

	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
	hw_sq_send_hdr = &hw_sq_send_ptr[get_sqe_pg(sw_prod)]
					[get_sqe_idx(sw_prod)];

	memset(hw_sq_send_hdr, 0, BNXT_QPLIB_MAX_SQE_ENTRY_SIZE);

	if (wqe->flags & BNXT_QPLIB_SWQE_FLAGS_INLINE) {
		/* Copy the inline data */
		if (wqe->inline_len > BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH) {
			dev_warn(&sq->hwq.pdev->dev,
				 "QPLIB: Inline data length > 96 detected");
			data_len = BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH;
		} else {
			data_len = wqe->inline_len;
		}
		memcpy(hw_sq_send_hdr->data, wqe->inline_data, data_len);
		wqe_size16 = (data_len + 15) >> 4;
	} else {
		for (i = 0, hw_sge = (struct sq_sge *)hw_sq_send_hdr->data;
		     i < wqe->num_sge; i++, hw_sge++) {
			hw_sge->va_or_pa = cpu_to_le64(wqe->sg_list[i].addr);
			hw_sge->l_key = cpu_to_le32(wqe->sg_list[i].lkey);
			hw_sge->size = cpu_to_le32(wqe->sg_list[i].size);
			data_len += wqe->sg_list[i].size;
		}
		/* Each SGE entry = 1 WQE size16 */
		wqe_size16 = wqe->num_sge;
1604 1605 1606 1607 1608
		/* HW requires wqe size has room for atleast one SGE even if
		 * none was supplied by ULP
		 */
		if (!wqe->num_sge)
			wqe_size16++;
1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
	}

	/* Specifics */
	switch (wqe->type) {
	case BNXT_QPLIB_SWQE_TYPE_SEND:
		if (qp->type == CMDQ_CREATE_QP1_TYPE_GSI) {
			/* Assemble info for Raw Ethertype QPs */
			struct sq_send_raweth_qp1 *sqe =
				(struct sq_send_raweth_qp1 *)hw_sq_send_hdr;

			sqe->wqe_type = wqe->type;
			sqe->flags = wqe->flags;
			sqe->wqe_size = wqe_size16 +
				((offsetof(typeof(*sqe), data) + 15) >> 4);
			sqe->cfa_action = cpu_to_le16(wqe->rawqp1.cfa_action);
			sqe->lflags = cpu_to_le16(wqe->rawqp1.lflags);
			sqe->length = cpu_to_le32(data_len);
			sqe->cfa_meta = cpu_to_le32((wqe->rawqp1.cfa_meta &
				SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_MASK) <<
				SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_SFT);

			break;
		}
1632
		/* fall thru */
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 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776
	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM:
	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV:
	{
		struct sq_send *sqe = (struct sq_send *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->wqe_size = wqe_size16 +
				((offsetof(typeof(*sqe), data) + 15) >> 4);
		sqe->inv_key_or_imm_data = cpu_to_le32(
						wqe->send.inv_key);
		if (qp->type == CMDQ_CREATE_QP_TYPE_UD) {
			sqe->q_key = cpu_to_le32(wqe->send.q_key);
			sqe->dst_qp = cpu_to_le32(
					wqe->send.dst_qp & SQ_SEND_DST_QP_MASK);
			sqe->length = cpu_to_le32(data_len);
			sqe->avid = cpu_to_le32(wqe->send.avid &
						SQ_SEND_AVID_MASK);
			sq->psn = (sq->psn + 1) & BTH_PSN_MASK;
		} else {
			sqe->length = cpu_to_le32(data_len);
			sqe->dst_qp = 0;
			sqe->avid = 0;
			if (qp->mtu)
				pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
			if (!pkt_num)
				pkt_num = 1;
			sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
		}
		break;
	}
	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE:
	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM:
	case BNXT_QPLIB_SWQE_TYPE_RDMA_READ:
	{
		struct sq_rdma *sqe = (struct sq_rdma *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->wqe_size = wqe_size16 +
				((offsetof(typeof(*sqe), data) + 15) >> 4);
		sqe->imm_data = cpu_to_le32(wqe->rdma.inv_key);
		sqe->length = cpu_to_le32((u32)data_len);
		sqe->remote_va = cpu_to_le64(wqe->rdma.remote_va);
		sqe->remote_key = cpu_to_le32(wqe->rdma.r_key);
		if (qp->mtu)
			pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
		if (!pkt_num)
			pkt_num = 1;
		sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
		break;
	}
	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP:
	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_FETCH_AND_ADD:
	{
		struct sq_atomic *sqe = (struct sq_atomic *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->remote_key = cpu_to_le32(wqe->atomic.r_key);
		sqe->remote_va = cpu_to_le64(wqe->atomic.remote_va);
		sqe->swap_data = cpu_to_le64(wqe->atomic.swap_data);
		sqe->cmp_data = cpu_to_le64(wqe->atomic.cmp_data);
		if (qp->mtu)
			pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
		if (!pkt_num)
			pkt_num = 1;
		sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
		break;
	}
	case BNXT_QPLIB_SWQE_TYPE_LOCAL_INV:
	{
		struct sq_localinvalidate *sqe =
				(struct sq_localinvalidate *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->inv_l_key = cpu_to_le32(wqe->local_inv.inv_l_key);

		break;
	}
	case BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR:
	{
		struct sq_fr_pmr *sqe = (struct sq_fr_pmr *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->access_cntl = wqe->frmr.access_cntl |
				   SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE;
		sqe->zero_based_page_size_log =
			(wqe->frmr.pg_sz_log & SQ_FR_PMR_PAGE_SIZE_LOG_MASK) <<
			SQ_FR_PMR_PAGE_SIZE_LOG_SFT |
			(wqe->frmr.zero_based ? SQ_FR_PMR_ZERO_BASED : 0);
		sqe->l_key = cpu_to_le32(wqe->frmr.l_key);
		temp32 = cpu_to_le32(wqe->frmr.length);
		memcpy(sqe->length, &temp32, sizeof(wqe->frmr.length));
		sqe->numlevels_pbl_page_size_log =
			((wqe->frmr.pbl_pg_sz_log <<
					SQ_FR_PMR_PBL_PAGE_SIZE_LOG_SFT) &
					SQ_FR_PMR_PBL_PAGE_SIZE_LOG_MASK) |
			((wqe->frmr.levels << SQ_FR_PMR_NUMLEVELS_SFT) &
					SQ_FR_PMR_NUMLEVELS_MASK);

		for (i = 0; i < wqe->frmr.page_list_len; i++)
			wqe->frmr.pbl_ptr[i] = cpu_to_le64(
						wqe->frmr.page_list[i] |
						PTU_PTE_VALID);
		sqe->pblptr = cpu_to_le64(wqe->frmr.pbl_dma_ptr);
		sqe->va = cpu_to_le64(wqe->frmr.va);

		break;
	}
	case BNXT_QPLIB_SWQE_TYPE_BIND_MW:
	{
		struct sq_bind *sqe = (struct sq_bind *)hw_sq_send_hdr;

		sqe->wqe_type = wqe->type;
		sqe->flags = wqe->flags;
		sqe->access_cntl = wqe->bind.access_cntl;
		sqe->mw_type_zero_based = wqe->bind.mw_type |
			(wqe->bind.zero_based ? SQ_BIND_ZERO_BASED : 0);
		sqe->parent_l_key = cpu_to_le32(wqe->bind.parent_l_key);
		sqe->l_key = cpu_to_le32(wqe->bind.r_key);
		sqe->va = cpu_to_le64(wqe->bind.va);
		temp32 = cpu_to_le32(wqe->bind.length);
		memcpy(&sqe->length, &temp32, sizeof(wqe->bind.length));
		break;
	}
	default:
		/* Bad wqe, return error */
		rc = -EINVAL;
		goto done;
	}
	swq->next_psn = sq->psn & BTH_PSN_MASK;
	if (swq->psn_search) {
		swq->psn_search->opcode_start_psn = cpu_to_le32(
			((swq->start_psn << SQ_PSN_SEARCH_START_PSN_SFT) &
			 SQ_PSN_SEARCH_START_PSN_MASK) |
			((wqe->type << SQ_PSN_SEARCH_OPCODE_SFT) &
			 SQ_PSN_SEARCH_OPCODE_MASK));
		swq->psn_search->flags_next_psn = cpu_to_le32(
			((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
			 SQ_PSN_SEARCH_NEXT_PSN_MASK));
	}
1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788
queue_err:
	if (sch_handler) {
		/* Store the ULP info in the software structures */
		sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
		swq = &sq->swq[sw_prod];
		swq->wr_id = wqe->wr_id;
		swq->type = wqe->type;
		swq->flags = wqe->flags;
		if (qp->sig_type)
			swq->flags |= SQ_SEND_FLAGS_SIGNAL_COMP;
		swq->start_psn = sq->psn & BTH_PSN_MASK;
	}
1789
	sq->hwq.prod++;
1790 1791
	qp->wqe_cnt++;

1792
done:
1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
	if (sch_handler) {
		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
		if (nq_work) {
			nq_work->cq = qp->scq;
			nq_work->nq = qp->scq->nq;
			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
			queue_work(qp->scq->nq->cqn_wq, &nq_work->work);
		} else {
			dev_err(&sq->hwq.pdev->dev,
				"QPLIB: FP: Failed to allocate SQ nq_work!");
			rc = -ENOMEM;
		}
	}
1806 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
	return rc;
}

void bnxt_qplib_post_recv_db(struct bnxt_qplib_qp *qp)
{
	struct bnxt_qplib_q *rq = &qp->rq;
	struct dbr_dbr db_msg = { 0 };
	u32 sw_prod;

	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
	db_msg.index = cpu_to_le32((sw_prod << DBR_DBR_INDEX_SFT) &
				   DBR_DBR_INDEX_MASK);
	db_msg.type_xid =
		cpu_to_le32(((qp->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
			    DBR_DBR_TYPE_RQ);

	/* Flush the writes to HW Rx WQE before the ringing Rx DB */
	wmb();
	__iowrite64_copy(qp->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
}

int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
			 struct bnxt_qplib_swqe *wqe)
{
	struct bnxt_qplib_q *rq = &qp->rq;
	struct rq_wqe *rqe, **rqe_ptr;
	struct sq_sge *hw_sge;
1833 1834
	struct bnxt_qplib_nq_work *nq_work = NULL;
	bool sch_handler = false;
1835 1836 1837 1838
	u32 sw_prod;
	int i, rc = 0;

	if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
1839 1840 1841 1842 1843
		sch_handler = true;
		dev_dbg(&rq->hwq.pdev->dev,
			"%s Error QP. Scheduling for poll_cq\n",
			__func__);
		goto queue_err;
1844
	}
1845
	if (bnxt_qplib_queue_full(rq)) {
1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869
		dev_err(&rq->hwq.pdev->dev,
			"QPLIB: FP: QP (0x%x) RQ is full!", qp->id);
		rc = -EINVAL;
		goto done;
	}
	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
	rq->swq[sw_prod].wr_id = wqe->wr_id;

	rqe_ptr = (struct rq_wqe **)rq->hwq.pbl_ptr;
	rqe = &rqe_ptr[RQE_PG(sw_prod)][RQE_IDX(sw_prod)];

	memset(rqe, 0, BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);

	/* Calculate wqe_size16 and data_len */
	for (i = 0, hw_sge = (struct sq_sge *)rqe->data;
	     i < wqe->num_sge; i++, hw_sge++) {
		hw_sge->va_or_pa = cpu_to_le64(wqe->sg_list[i].addr);
		hw_sge->l_key = cpu_to_le32(wqe->sg_list[i].lkey);
		hw_sge->size = cpu_to_le32(wqe->sg_list[i].size);
	}
	rqe->wqe_type = wqe->type;
	rqe->flags = wqe->flags;
	rqe->wqe_size = wqe->num_sge +
			((offsetof(typeof(*rqe), data) + 15) >> 4);
1870 1871 1872 1873 1874
	/* HW requires wqe size has room for atleast one SGE even if none
	 * was supplied by ULP
	 */
	if (!wqe->num_sge)
		rqe->wqe_size++;
1875 1876 1877 1878

	/* Supply the rqe->wr_id index to the wr_id_tbl for now */
	rqe->wr_id[0] = cpu_to_le32(sw_prod);

1879 1880 1881 1882 1883 1884 1885
queue_err:
	if (sch_handler) {
		/* Store the ULP info in the software structures */
		sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
		rq->swq[sw_prod].wr_id = wqe->wr_id;
	}

1886
	rq->hwq.prod++;
1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899
	if (sch_handler) {
		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
		if (nq_work) {
			nq_work->cq = qp->rcq;
			nq_work->nq = qp->rcq->nq;
			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
			queue_work(qp->rcq->nq->cqn_wq, &nq_work->work);
		} else {
			dev_err(&rq->hwq.pdev->dev,
				"QPLIB: FP: Failed to allocate RQ nq_work!");
			rc = -ENOMEM;
		}
	}
1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940
done:
	return rc;
}

/* CQ */

/* Spinlock must be held */
static void bnxt_qplib_arm_cq_enable(struct bnxt_qplib_cq *cq)
{
	struct dbr_dbr db_msg = { 0 };

	db_msg.type_xid =
		cpu_to_le32(((cq->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
			    DBR_DBR_TYPE_CQ_ARMENA);
	/* Flush memory writes before enabling the CQ */
	wmb();
	__iowrite64_copy(cq->dbr_base, &db_msg, sizeof(db_msg) / sizeof(u64));
}

static void bnxt_qplib_arm_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
{
	struct bnxt_qplib_hwq *cq_hwq = &cq->hwq;
	struct dbr_dbr db_msg = { 0 };
	u32 sw_cons;

	/* Ring DB */
	sw_cons = HWQ_CMP(cq_hwq->cons, cq_hwq);
	db_msg.index = cpu_to_le32((sw_cons << DBR_DBR_INDEX_SFT) &
				    DBR_DBR_INDEX_MASK);
	db_msg.type_xid =
		cpu_to_le32(((cq->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
			    arm_type);
	/* flush memory writes before arming the CQ */
	wmb();
	__iowrite64_copy(cq->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
}

int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_create_cq req;
1941
	struct creq_create_cq_resp resp;
1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982
	struct bnxt_qplib_pbl *pbl;
	u16 cmd_flags = 0;
	int rc;

	cq->hwq.max_elements = cq->max_wqe;
	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &cq->hwq, cq->sghead,
				       cq->nmap, &cq->hwq.max_elements,
				       BNXT_QPLIB_MAX_CQE_ENTRY_SIZE, 0,
				       PAGE_SIZE, HWQ_TYPE_QUEUE);
	if (rc)
		goto exit;

	RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags);

	if (!cq->dpi) {
		dev_err(&rcfw->pdev->dev,
			"QPLIB: FP: CREATE_CQ failed due to NULL DPI");
		return -EINVAL;
	}
	req.dpi = cpu_to_le32(cq->dpi->dpi);
	req.cq_handle = cpu_to_le64(cq->cq_handle);

	req.cq_size = cpu_to_le32(cq->hwq.max_elements);
	pbl = &cq->hwq.pbl[PBL_LVL_0];
	req.pg_size_lvl = cpu_to_le32(
	    ((cq->hwq.level & CMDQ_CREATE_CQ_LVL_MASK) <<
						CMDQ_CREATE_CQ_LVL_SFT) |
	    (pbl->pg_size == ROCE_PG_SIZE_4K ? CMDQ_CREATE_CQ_PG_SIZE_PG_4K :
	     pbl->pg_size == ROCE_PG_SIZE_8K ? CMDQ_CREATE_CQ_PG_SIZE_PG_8K :
	     pbl->pg_size == ROCE_PG_SIZE_64K ? CMDQ_CREATE_CQ_PG_SIZE_PG_64K :
	     pbl->pg_size == ROCE_PG_SIZE_2M ? CMDQ_CREATE_CQ_PG_SIZE_PG_2M :
	     pbl->pg_size == ROCE_PG_SIZE_8M ? CMDQ_CREATE_CQ_PG_SIZE_PG_8M :
	     pbl->pg_size == ROCE_PG_SIZE_1G ? CMDQ_CREATE_CQ_PG_SIZE_PG_1G :
	     CMDQ_CREATE_CQ_PG_SIZE_PG_4K));

	req.pbl = cpu_to_le64(pbl->pg_map_arr[0]);

	req.cq_fco_cnq_id = cpu_to_le32(
			(cq->cnq_hw_ring_id & CMDQ_CREATE_CQ_CNQ_ID_MASK) <<
			 CMDQ_CREATE_CQ_CNQ_ID_SFT);

1983 1984 1985
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
1986
		goto fail;
1987 1988

	cq->id = le32_to_cpu(resp.xid);
1989 1990 1991
	cq->dbr_base = res->dpi_tbl.dbr_bar_reg_iomem;
	cq->period = BNXT_QPLIB_QUEUE_START_PERIOD;
	init_waitqueue_head(&cq->waitq);
1992 1993 1994
	INIT_LIST_HEAD(&cq->sqf_head);
	INIT_LIST_HEAD(&cq->rqf_head);
	spin_lock_init(&cq->compl_lock);
1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008

	bnxt_qplib_arm_cq_enable(cq);
	return 0;

fail:
	bnxt_qplib_free_hwq(res->pdev, &cq->hwq);
exit:
	return rc;
}

int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
{
	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
	struct cmdq_destroy_cq req;
2009
	struct creq_destroy_cq_resp resp;
2010
	u16 cmd_flags = 0;
2011
	int rc;
2012 2013 2014 2015

	RCFW_CMD_PREP(req, DESTROY_CQ, cmd_flags);

	req.cq_cid = cpu_to_le32(cq->id);
2016 2017 2018 2019
	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
					  (void *)&resp, NULL, 0);
	if (rc)
		return rc;
2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
	bnxt_qplib_free_hwq(res->pdev, &cq->hwq);
	return 0;
}

static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp,
		      struct bnxt_qplib_cqe **pcqe, int *budget)
{
	u32 sw_prod, sw_cons;
	struct bnxt_qplib_cqe *cqe;
	int rc = 0;

	/* Now complete all outstanding SQEs with FLUSHED_ERR */
	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
	cqe = *pcqe;
	while (*budget) {
		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
		if (sw_cons == sw_prod) {
			break;
		}
2039 2040 2041 2042 2043
		/* Skip the FENCE WQE completions */
		if (sq->swq[sw_cons].wr_id == BNXT_QPLIB_FENCE_WRID) {
			bnxt_qplib_cancel_phantom_processing(qp);
			goto skip_compl;
		}
2044 2045 2046 2047 2048 2049 2050 2051 2052
		memset(cqe, 0, sizeof(*cqe));
		cqe->status = CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR;
		cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
		cqe->qp_handle = (u64)(unsigned long)qp;
		cqe->wr_id = sq->swq[sw_cons].wr_id;
		cqe->src_qp = qp->id;
		cqe->type = sq->swq[sw_cons].type;
		cqe++;
		(*budget)--;
2053
skip_compl:
2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064
		sq->hwq.cons++;
	}
	*pcqe = cqe;
	if (!(*budget) && HWQ_CMP(sq->hwq.cons, &sq->hwq) != sw_prod)
		/* Out of budget */
		rc = -EAGAIN;

	return rc;
}

static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp,
2065
		      struct bnxt_qplib_cqe **pcqe, int *budget)
2066 2067 2068 2069
{
	struct bnxt_qplib_cqe *cqe;
	u32 sw_prod, sw_cons;
	int rc = 0;
2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082
	int opcode = 0;

	switch (qp->type) {
	case CMDQ_CREATE_QP1_TYPE_GSI:
		opcode = CQ_BASE_CQE_TYPE_RES_RAWETH_QP1;
		break;
	case CMDQ_CREATE_QP_TYPE_RC:
		opcode = CQ_BASE_CQE_TYPE_RES_RC;
		break;
	case CMDQ_CREATE_QP_TYPE_UD:
		opcode = CQ_BASE_CQE_TYPE_RES_UD;
		break;
	}
2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108

	/* Flush the rest of the RQ */
	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
	cqe = *pcqe;
	while (*budget) {
		sw_cons = HWQ_CMP(rq->hwq.cons, &rq->hwq);
		if (sw_cons == sw_prod)
			break;
		memset(cqe, 0, sizeof(*cqe));
		cqe->status =
		    CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR;
		cqe->opcode = opcode;
		cqe->qp_handle = (unsigned long)qp;
		cqe->wr_id = rq->swq[sw_cons].wr_id;
		cqe++;
		(*budget)--;
		rq->hwq.cons++;
	}
	*pcqe = cqe;
	if (!*budget && HWQ_CMP(rq->hwq.cons, &rq->hwq) != sw_prod)
		/* Out of budget */
		rc = -EAGAIN;

	return rc;
}

2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123
void bnxt_qplib_mark_qp_error(void *qp_handle)
{
	struct bnxt_qplib_qp *qp = qp_handle;

	if (!qp)
		return;

	/* Must block new posting of SQ and RQ */
	qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
	bnxt_qplib_cancel_phantom_processing(qp);

	/* Add qp to flush list of the CQ */
	__bnxt_qplib_add_flush_qp(qp);
}

2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172
/* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive)
 *       CQE is track from sw_cq_cons to max_element but valid only if VALID=1
 */
static int do_wa9060(struct bnxt_qplib_qp *qp, struct bnxt_qplib_cq *cq,
		     u32 cq_cons, u32 sw_sq_cons, u32 cqe_sq_cons)
{
	struct bnxt_qplib_q *sq = &qp->sq;
	struct bnxt_qplib_swq *swq;
	u32 peek_sw_cq_cons, peek_raw_cq_cons, peek_sq_cons_idx;
	struct cq_base *peek_hwcqe, **peek_hw_cqe_ptr;
	struct cq_req *peek_req_hwcqe;
	struct bnxt_qplib_qp *peek_qp;
	struct bnxt_qplib_q *peek_sq;
	int i, rc = 0;

	/* Normal mode */
	/* Check for the psn_search marking before completing */
	swq = &sq->swq[sw_sq_cons];
	if (swq->psn_search &&
	    le32_to_cpu(swq->psn_search->flags_next_psn) & 0x80000000) {
		/* Unmark */
		swq->psn_search->flags_next_psn = cpu_to_le32
			(le32_to_cpu(swq->psn_search->flags_next_psn)
				     & ~0x80000000);
		dev_dbg(&cq->hwq.pdev->dev,
			"FP: Process Req cq_cons=0x%x qp=0x%x sq cons sw=0x%x cqe=0x%x marked!\n",
			cq_cons, qp->id, sw_sq_cons, cqe_sq_cons);
		sq->condition = true;
		sq->send_phantom = true;

		/* TODO: Only ARM if the previous SQE is ARMALL */
		bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ_ARMALL);

		rc = -EAGAIN;
		goto out;
	}
	if (sq->condition) {
		/* Peek at the completions */
		peek_raw_cq_cons = cq->hwq.cons;
		peek_sw_cq_cons = cq_cons;
		i = cq->hwq.max_elements;
		while (i--) {
			peek_sw_cq_cons = HWQ_CMP((peek_sw_cq_cons), &cq->hwq);
			peek_hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr;
			peek_hwcqe = &peek_hw_cqe_ptr[CQE_PG(peek_sw_cq_cons)]
						     [CQE_IDX(peek_sw_cq_cons)];
			/* If the next hwcqe is VALID */
			if (CQE_CMP_VALID(peek_hwcqe, peek_raw_cq_cons,
					  cq->hwq.max_elements)) {
2173 2174 2175 2176 2177
			/*
			 * The valid test of the entry must be done first before
			 * reading any further.
			 */
				dma_rmb();
2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225
				/* If the next hwcqe is a REQ */
				if ((peek_hwcqe->cqe_type_toggle &
				    CQ_BASE_CQE_TYPE_MASK) ==
				    CQ_BASE_CQE_TYPE_REQ) {
					peek_req_hwcqe = (struct cq_req *)
							 peek_hwcqe;
					peek_qp = (struct bnxt_qplib_qp *)
						((unsigned long)
						 le64_to_cpu
						 (peek_req_hwcqe->qp_handle));
					peek_sq = &peek_qp->sq;
					peek_sq_cons_idx = HWQ_CMP(le16_to_cpu(
						peek_req_hwcqe->sq_cons_idx) - 1
						, &sq->hwq);
					/* If the hwcqe's sq's wr_id matches */
					if (peek_sq == sq &&
					    sq->swq[peek_sq_cons_idx].wr_id ==
					    BNXT_QPLIB_FENCE_WRID) {
						/*
						 *  Unbreak only if the phantom
						 *  comes back
						 */
						dev_dbg(&cq->hwq.pdev->dev,
							"FP:Got Phantom CQE");
						sq->condition = false;
						sq->single = true;
						rc = 0;
						goto out;
					}
				}
				/* Valid but not the phantom, so keep looping */
			} else {
				/* Not valid yet, just exit and wait */
				rc = -EINVAL;
				goto out;
			}
			peek_sw_cq_cons++;
			peek_raw_cq_cons++;
		}
		dev_err(&cq->hwq.pdev->dev,
			"Should not have come here! cq_cons=0x%x qp=0x%x sq cons sw=0x%x hw=0x%x",
			cq_cons, qp->id, sw_sq_cons, cqe_sq_cons);
		rc = -EINVAL;
	}
out:
	return rc;
}

2226 2227
static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
				     struct cq_req *hwcqe,
2228 2229
				     struct bnxt_qplib_cqe **pcqe, int *budget,
				     u32 cq_cons, struct bnxt_qplib_qp **lib_qp)
2230 2231 2232 2233
{
	struct bnxt_qplib_qp *qp;
	struct bnxt_qplib_q *sq;
	struct bnxt_qplib_cqe *cqe;
2234 2235
	u32 sw_sq_cons, cqe_sq_cons;
	struct bnxt_qplib_swq *swq;
2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246
	int rc = 0;

	qp = (struct bnxt_qplib_qp *)((unsigned long)
				      le64_to_cpu(hwcqe->qp_handle));
	if (!qp) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: Process Req qp is NULL");
		return -EINVAL;
	}
	sq = &qp->sq;

2247 2248
	cqe_sq_cons = HWQ_CMP(le16_to_cpu(hwcqe->sq_cons_idx), &sq->hwq);
	if (cqe_sq_cons > sq->hwq.max_elements) {
2249 2250 2251 2252
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: CQ Process req reported ");
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: sq_cons_idx 0x%x which exceeded max 0x%x",
2253
			cqe_sq_cons, sq->hwq.max_elements);
2254 2255 2256
		return -EINVAL;
	}

2257 2258 2259 2260 2261
	if (qp->sq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		goto done;
	}
2262 2263
	/* Require to walk the sq's swq to fabricate CQEs for all previously
	 * signaled SWQEs due to CQE aggregation from the current sq cons
2264
	 * to the cqe_sq_cons
2265 2266 2267
	 */
	cqe = *pcqe;
	while (*budget) {
2268 2269 2270
		sw_sq_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
		if (sw_sq_cons == cqe_sq_cons)
			/* Done */
2271
			break;
2272 2273

		swq = &sq->swq[sw_sq_cons];
2274 2275 2276 2277
		memset(cqe, 0, sizeof(*cqe));
		cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
		cqe->qp_handle = (u64)(unsigned long)qp;
		cqe->src_qp = qp->id;
2278 2279 2280 2281
		cqe->wr_id = swq->wr_id;
		if (cqe->wr_id == BNXT_QPLIB_FENCE_WRID)
			goto skip;
		cqe->type = swq->type;
2282 2283 2284 2285 2286

		/* For the last CQE, check for status.  For errors, regardless
		 * of the request being signaled or not, it must complete with
		 * the hwcqe error status
		 */
2287
		if (HWQ_CMP((sw_sq_cons + 1), &sq->hwq) == cqe_sq_cons &&
2288 2289 2290 2291 2292 2293
		    hwcqe->status != CQ_REQ_STATUS_OK) {
			cqe->status = hwcqe->status;
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Processed Req ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id[%d] = 0x%llx with status 0x%x",
2294
				sw_sq_cons, cqe->wr_id, cqe->status);
2295 2296
			cqe++;
			(*budget)--;
2297 2298 2299
			bnxt_qplib_lock_buddy_cq(qp, cq);
			bnxt_qplib_mark_qp_error(qp);
			bnxt_qplib_unlock_buddy_cq(qp, cq);
2300
		} else {
2301 2302 2303 2304 2305 2306 2307
			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
				/* Before we complete, do WA 9060 */
				if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
					      cqe_sq_cons)) {
					*lib_qp = qp;
					goto out;
				}
2308 2309 2310 2311 2312
				cqe->status = CQ_REQ_STATUS_OK;
				cqe++;
				(*budget)--;
			}
		}
2313
skip:
2314
		sq->hwq.cons++;
2315 2316
		if (sq->single)
			break;
2317
	}
2318
out:
2319
	*pcqe = cqe;
2320
	if (HWQ_CMP(sq->hwq.cons, &sq->hwq) != cqe_sq_cons) {
2321 2322 2323 2324
		/* Out of budget */
		rc = -EAGAIN;
		goto done;
	}
2325 2326 2327 2328 2329
	/*
	 * Back to normal completion mode only after it has completed all of
	 * the WC for this CQE
	 */
	sq->single = false;
2330 2331 2332 2333
done:
	return rc;
}

2334 2335 2336 2337 2338 2339 2340 2341 2342 2343
static void bnxt_qplib_release_srqe(struct bnxt_qplib_srq *srq, u32 tag)
{
	spin_lock(&srq->hwq.lock);
	srq->swq[srq->last_idx].next_idx = (int)tag;
	srq->last_idx = (int)tag;
	srq->swq[srq->last_idx].next_idx = -1;
	srq->hwq.cons++; /* Support for SRQE counter */
	spin_unlock(&srq->hwq.lock);
}

2344 2345 2346 2347 2348 2349 2350
static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq,
					struct cq_res_rc *hwcqe,
					struct bnxt_qplib_cqe **pcqe,
					int *budget)
{
	struct bnxt_qplib_qp *qp;
	struct bnxt_qplib_q *rq;
2351
	struct bnxt_qplib_srq *srq;
2352 2353 2354 2355 2356 2357 2358 2359 2360 2361
	struct bnxt_qplib_cqe *cqe;
	u32 wr_id_idx;
	int rc = 0;

	qp = (struct bnxt_qplib_qp *)((unsigned long)
				      le64_to_cpu(hwcqe->qp_handle));
	if (!qp) {
		dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq RC qp is NULL");
		return -EINVAL;
	}
2362 2363 2364 2365 2366 2367
	if (qp->rq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		goto done;
	}

2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378
	cqe = *pcqe;
	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
	cqe->length = le32_to_cpu(hwcqe->length);
	cqe->invrkey = le32_to_cpu(hwcqe->imm_data_or_inv_r_key);
	cqe->mr_handle = le64_to_cpu(hwcqe->mr_handle);
	cqe->flags = le16_to_cpu(hwcqe->flags);
	cqe->status = hwcqe->status;
	cqe->qp_handle = (u64)(unsigned long)qp;

	wr_id_idx = le32_to_cpu(hwcqe->srq_or_rq_wr_id) &
				CQ_RES_RC_SRQ_OR_RQ_WR_ID_MASK;
2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410
	if (cqe->flags & CQ_RES_RC_FLAGS_SRQ_SRQ) {
		srq = qp->srq;
		if (!srq)
			return -EINVAL;
		if (wr_id_idx > srq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process RC ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id idx 0x%x exceeded SRQ max 0x%x",
				wr_id_idx, srq->hwq.max_elements);
			return -EINVAL;
		}
		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
		bnxt_qplib_release_srqe(srq, wr_id_idx);
		cqe++;
		(*budget)--;
		*pcqe = cqe;
	} else {
		rq = &qp->rq;
		if (wr_id_idx > rq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process RC ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id idx 0x%x exceeded RQ max 0x%x",
				wr_id_idx, rq->hwq.max_elements);
			return -EINVAL;
		}
		cqe->wr_id = rq->swq[wr_id_idx].wr_id;
		cqe++;
		(*budget)--;
		rq->hwq.cons++;
		*pcqe = cqe;
2411

2412 2413 2414 2415 2416 2417 2418
		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
			/* Add qp to flush list of the CQ */
			bnxt_qplib_lock_buddy_cq(qp, cq);
			__bnxt_qplib_add_flush_qp(qp);
			bnxt_qplib_unlock_buddy_cq(qp, cq);
		}
2419
	}
2420 2421

done:
2422 2423 2424 2425 2426 2427 2428 2429 2430 2431
	return rc;
}

static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq,
					struct cq_res_ud *hwcqe,
					struct bnxt_qplib_cqe **pcqe,
					int *budget)
{
	struct bnxt_qplib_qp *qp;
	struct bnxt_qplib_q *rq;
2432
	struct bnxt_qplib_srq *srq;
2433 2434 2435 2436 2437 2438 2439 2440 2441 2442
	struct bnxt_qplib_cqe *cqe;
	u32 wr_id_idx;
	int rc = 0;

	qp = (struct bnxt_qplib_qp *)((unsigned long)
				      le64_to_cpu(hwcqe->qp_handle));
	if (!qp) {
		dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq UD qp is NULL");
		return -EINVAL;
	}
2443 2444 2445 2446 2447
	if (qp->rq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		goto done;
	}
2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462
	cqe = *pcqe;
	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
	cqe->length = le32_to_cpu(hwcqe->length);
	cqe->invrkey = le32_to_cpu(hwcqe->imm_data);
	cqe->flags = le16_to_cpu(hwcqe->flags);
	cqe->status = hwcqe->status;
	cqe->qp_handle = (u64)(unsigned long)qp;
	memcpy(cqe->smac, hwcqe->src_mac, 6);
	wr_id_idx = le32_to_cpu(hwcqe->src_qp_high_srq_or_rq_wr_id)
				& CQ_RES_UD_SRQ_OR_RQ_WR_ID_MASK;
	cqe->src_qp = le16_to_cpu(hwcqe->src_qp_low) |
				  ((le32_to_cpu(
				  hwcqe->src_qp_high_srq_or_rq_wr_id) &
				 CQ_RES_UD_SRC_QP_HIGH_MASK) >> 8);

2463 2464 2465 2466
	if (cqe->flags & CQ_RES_RC_FLAGS_SRQ_SRQ) {
		srq = qp->srq;
		if (!srq)
			return -EINVAL;
2467

2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496
		if (wr_id_idx > srq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process UD ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id idx 0x%x exceeded SRQ max 0x%x",
				wr_id_idx, srq->hwq.max_elements);
			return -EINVAL;
		}
		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
		bnxt_qplib_release_srqe(srq, wr_id_idx);
		cqe++;
		(*budget)--;
		*pcqe = cqe;
	} else {
		rq = &qp->rq;
		if (wr_id_idx > rq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process UD ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id idx 0x%x exceeded RQ max 0x%x",
				wr_id_idx, rq->hwq.max_elements);
			return -EINVAL;
		}

		cqe->wr_id = rq->swq[wr_id_idx].wr_id;
		cqe++;
		(*budget)--;
		rq->hwq.cons++;
		*pcqe = cqe;
2497

2498 2499 2500 2501 2502 2503 2504
		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
			/* Add qp to flush list of the CQ */
			bnxt_qplib_lock_buddy_cq(qp, cq);
			__bnxt_qplib_add_flush_qp(qp);
			bnxt_qplib_unlock_buddy_cq(qp, cq);
		}
2505
	}
2506
done:
2507 2508 2509
	return rc;
}

2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528
bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq)
{
	struct cq_base *hw_cqe, **hw_cqe_ptr;
	unsigned long flags;
	u32 sw_cons, raw_cons;
	bool rc = true;

	spin_lock_irqsave(&cq->hwq.lock, flags);
	raw_cons = cq->hwq.cons;
	sw_cons = HWQ_CMP(raw_cons, &cq->hwq);
	hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr;
	hw_cqe = &hw_cqe_ptr[CQE_PG(sw_cons)][CQE_IDX(sw_cons)];

	 /* Check for Valid bit. If the CQE is valid, return false */
	rc = !CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements);
	spin_unlock_irqrestore(&cq->hwq.lock, flags);
	return rc;
}

2529 2530 2531 2532 2533 2534 2535
static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq,
						struct cq_res_raweth_qp1 *hwcqe,
						struct bnxt_qplib_cqe **pcqe,
						int *budget)
{
	struct bnxt_qplib_qp *qp;
	struct bnxt_qplib_q *rq;
2536
	struct bnxt_qplib_srq *srq;
2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547
	struct bnxt_qplib_cqe *cqe;
	u32 wr_id_idx;
	int rc = 0;

	qp = (struct bnxt_qplib_qp *)((unsigned long)
				      le64_to_cpu(hwcqe->qp_handle));
	if (!qp) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: process_cq Raw/QP1 qp is NULL");
		return -EINVAL;
	}
2548 2549 2550 2551 2552
	if (qp->rq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		goto done;
	}
2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572
	cqe = *pcqe;
	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
	cqe->flags = le16_to_cpu(hwcqe->flags);
	cqe->qp_handle = (u64)(unsigned long)qp;

	wr_id_idx =
		le32_to_cpu(hwcqe->raweth_qp1_payload_offset_srq_or_rq_wr_id)
				& CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_MASK;
	cqe->src_qp = qp->id;
	if (qp->id == 1 && !cqe->length) {
		/* Add workaround for the length misdetection */
		cqe->length = 296;
	} else {
		cqe->length = le16_to_cpu(hwcqe->length);
	}
	cqe->pkey_index = qp->pkey_index;
	memcpy(cqe->smac, qp->smac, 6);

	cqe->raweth_qp1_flags = le16_to_cpu(hwcqe->raweth_qp1_flags);
	cqe->raweth_qp1_flags2 = le32_to_cpu(hwcqe->raweth_qp1_flags2);
2573
	cqe->raweth_qp1_metadata = le32_to_cpu(hwcqe->raweth_qp1_metadata);
2574

2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609
	if (cqe->flags & CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ) {
		srq = qp->srq;
		if (!srq) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: SRQ used but not defined??");
			return -EINVAL;
		}
		if (wr_id_idx > srq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process Raw/QP1 ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: wr_id idx 0x%x exceeded SRQ max 0x%x",
				wr_id_idx, srq->hwq.max_elements);
			return -EINVAL;
		}
		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
		bnxt_qplib_release_srqe(srq, wr_id_idx);
		cqe++;
		(*budget)--;
		*pcqe = cqe;
	} else {
		rq = &qp->rq;
		if (wr_id_idx > rq->hwq.max_elements) {
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: FP: CQ Process Raw/QP1 RQ wr_id ");
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: ix 0x%x exceeded RQ max 0x%x",
				wr_id_idx, rq->hwq.max_elements);
			return -EINVAL;
		}
		cqe->wr_id = rq->swq[wr_id_idx].wr_id;
		cqe++;
		(*budget)--;
		rq->hwq.cons++;
		*pcqe = cqe;
2610

2611 2612 2613 2614 2615 2616 2617
		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
			/* Add qp to flush list of the CQ */
			bnxt_qplib_lock_buddy_cq(qp, cq);
			__bnxt_qplib_add_flush_qp(qp);
			bnxt_qplib_unlock_buddy_cq(qp, cq);
		}
2618
	}
2619 2620

done:
2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647
	return rc;
}

static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
					  struct cq_terminal *hwcqe,
					  struct bnxt_qplib_cqe **pcqe,
					  int *budget)
{
	struct bnxt_qplib_qp *qp;
	struct bnxt_qplib_q *sq, *rq;
	struct bnxt_qplib_cqe *cqe;
	u32 sw_cons = 0, cqe_cons;
	int rc = 0;

	/* Check the Status */
	if (hwcqe->status != CQ_TERMINAL_STATUS_OK)
		dev_warn(&cq->hwq.pdev->dev,
			 "QPLIB: FP: CQ Process Terminal Error status = 0x%x",
			 hwcqe->status);

	qp = (struct bnxt_qplib_qp *)((unsigned long)
				      le64_to_cpu(hwcqe->qp_handle));
	if (!qp) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: CQ Process terminal qp is NULL");
		return -EINVAL;
	}
2648

2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666
	/* Must block new posting of SQ and RQ */
	qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;

	sq = &qp->sq;
	rq = &qp->rq;

	cqe_cons = le16_to_cpu(hwcqe->sq_cons_idx);
	if (cqe_cons == 0xFFFF)
		goto do_rq;

	if (cqe_cons > sq->hwq.max_elements) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: CQ Process terminal reported ");
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: sq_cons_idx 0x%x which exceeded max 0x%x",
			cqe_cons, sq->hwq.max_elements);
		goto do_rq;
	}
2667 2668 2669 2670 2671 2672

	if (qp->sq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		goto sq_done;
	}
2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716

	/* Terminal CQE can also include aggregated successful CQEs prior.
	 * So we must complete all CQEs from the current sq's cons to the
	 * cq_cons with status OK
	 */
	cqe = *pcqe;
	while (*budget) {
		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
		if (sw_cons == cqe_cons)
			break;
		if (sq->swq[sw_cons].flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
			memset(cqe, 0, sizeof(*cqe));
			cqe->status = CQ_REQ_STATUS_OK;
			cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
			cqe->qp_handle = (u64)(unsigned long)qp;
			cqe->src_qp = qp->id;
			cqe->wr_id = sq->swq[sw_cons].wr_id;
			cqe->type = sq->swq[sw_cons].type;
			cqe++;
			(*budget)--;
		}
		sq->hwq.cons++;
	}
	*pcqe = cqe;
	if (!(*budget) && sw_cons != cqe_cons) {
		/* Out of budget */
		rc = -EAGAIN;
		goto sq_done;
	}
sq_done:
	if (rc)
		return rc;
do_rq:
	cqe_cons = le16_to_cpu(hwcqe->rq_cons_idx);
	if (cqe_cons == 0xFFFF) {
		goto done;
	} else if (cqe_cons > rq->hwq.max_elements) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: CQ Processed terminal ");
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: reported rq_cons_idx 0x%x exceeds max 0x%x",
			cqe_cons, rq->hwq.max_elements);
		goto done;
	}
2717 2718 2719 2720 2721 2722 2723 2724

	if (qp->rq.flushed) {
		dev_dbg(&cq->hwq.pdev->dev,
			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
		rc = 0;
		goto done;
	}

2725 2726 2727 2728 2729
	/* Terminal CQE requires all posted RQEs to complete with FLUSHED_ERR
	 * from the current rq->cons to the rq->prod regardless what the
	 * rq->cons the terminal CQE indicates
	 */

2730 2731 2732 2733
	/* Add qp to flush list of the CQ */
	bnxt_qplib_lock_buddy_cq(qp, cq);
	__bnxt_qplib_add_flush_qp(qp);
	bnxt_qplib_unlock_buddy_cq(qp, cq);
2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753
done:
	return rc;
}

static int bnxt_qplib_cq_process_cutoff(struct bnxt_qplib_cq *cq,
					struct cq_cutoff *hwcqe)
{
	/* Check the Status */
	if (hwcqe->status != CQ_CUTOFF_STATUS_OK) {
		dev_err(&cq->hwq.pdev->dev,
			"QPLIB: FP: CQ Process Cutoff Error status = 0x%x",
			hwcqe->status);
		return -EINVAL;
	}
	clear_bit(CQ_FLAGS_RESIZE_IN_PROG, &cq->flags);
	wake_up_interruptible(&cq->waitq);

	return 0;
}

2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780
int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq,
				  struct bnxt_qplib_cqe *cqe,
				  int num_cqes)
{
	struct bnxt_qplib_qp *qp = NULL;
	u32 budget = num_cqes;
	unsigned long flags;

	spin_lock_irqsave(&cq->hwq.lock, flags);
	list_for_each_entry(qp, &cq->sqf_head, sq_flush) {
		dev_dbg(&cq->hwq.pdev->dev,
			"QPLIB: FP: Flushing SQ QP= %p",
			qp);
		__flush_sq(&qp->sq, qp, &cqe, &budget);
	}

	list_for_each_entry(qp, &cq->rqf_head, rq_flush) {
		dev_dbg(&cq->hwq.pdev->dev,
			"QPLIB: FP: Flushing RQ QP= %p",
			qp);
		__flush_rq(&qp->rq, qp, &cqe, &budget);
	}
	spin_unlock_irqrestore(&cq->hwq.lock, flags);

	return num_cqes - budget;
}

2781
int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe,
2782
		       int num_cqes, struct bnxt_qplib_qp **lib_qp)
2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801
{
	struct cq_base *hw_cqe, **hw_cqe_ptr;
	unsigned long flags;
	u32 sw_cons, raw_cons;
	int budget, rc = 0;

	spin_lock_irqsave(&cq->hwq.lock, flags);
	raw_cons = cq->hwq.cons;
	budget = num_cqes;

	while (budget) {
		sw_cons = HWQ_CMP(raw_cons, &cq->hwq);
		hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr;
		hw_cqe = &hw_cqe_ptr[CQE_PG(sw_cons)][CQE_IDX(sw_cons)];

		/* Check for Valid bit */
		if (!CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements))
			break;

2802 2803 2804 2805 2806
		/*
		 * The valid test of the entry must be done first before
		 * reading any further.
		 */
		dma_rmb();
2807 2808 2809 2810 2811
		/* From the device's respective CQE format to qplib_wc*/
		switch (hw_cqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK) {
		case CQ_BASE_CQE_TYPE_REQ:
			rc = bnxt_qplib_cq_process_req(cq,
						       (struct cq_req *)hw_cqe,
2812 2813
						       &cqe, &budget,
						       sw_cons, lib_qp);
2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875
			break;
		case CQ_BASE_CQE_TYPE_RES_RC:
			rc = bnxt_qplib_cq_process_res_rc(cq,
							  (struct cq_res_rc *)
							  hw_cqe, &cqe,
							  &budget);
			break;
		case CQ_BASE_CQE_TYPE_RES_UD:
			rc = bnxt_qplib_cq_process_res_ud
					(cq, (struct cq_res_ud *)hw_cqe, &cqe,
					 &budget);
			break;
		case CQ_BASE_CQE_TYPE_RES_RAWETH_QP1:
			rc = bnxt_qplib_cq_process_res_raweth_qp1
					(cq, (struct cq_res_raweth_qp1 *)
					 hw_cqe, &cqe, &budget);
			break;
		case CQ_BASE_CQE_TYPE_TERMINAL:
			rc = bnxt_qplib_cq_process_terminal
					(cq, (struct cq_terminal *)hw_cqe,
					 &cqe, &budget);
			break;
		case CQ_BASE_CQE_TYPE_CUT_OFF:
			bnxt_qplib_cq_process_cutoff
					(cq, (struct cq_cutoff *)hw_cqe);
			/* Done processing this CQ */
			goto exit;
		default:
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: process_cq unknown type 0x%lx",
				hw_cqe->cqe_type_toggle &
				CQ_BASE_CQE_TYPE_MASK);
			rc = -EINVAL;
			break;
		}
		if (rc < 0) {
			if (rc == -EAGAIN)
				break;
			/* Error while processing the CQE, just skip to the
			 * next one
			 */
			dev_err(&cq->hwq.pdev->dev,
				"QPLIB: process_cqe error rc = 0x%x", rc);
		}
		raw_cons++;
	}
	if (cq->hwq.cons != raw_cons) {
		cq->hwq.cons = raw_cons;
		bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ);
	}
exit:
	spin_unlock_irqrestore(&cq->hwq.lock, flags);
	return num_cqes - budget;
}

void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
{
	unsigned long flags;

	spin_lock_irqsave(&cq->hwq.lock, flags);
	if (arm_type)
		bnxt_qplib_arm_cq(cq, arm_type);
2876 2877
	/* Using cq->arm_state variable to track whether to issue cq handler */
	atomic_set(&cq->arm_state, 1);
2878 2879
	spin_unlock_irqrestore(&cq->hwq.lock, flags);
}
2880 2881 2882 2883 2884 2885 2886

void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp)
{
	flush_workqueue(qp->scq->nq->cqn_wq);
	if (qp->scq != qp->rcq)
		flush_workqueue(qp->rcq->nq->cqn_wq);
}