qp.c

/*
 * Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
 *
 * 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
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - 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.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */
#include "iw_cxgb4.h"

static int ocqp_support = 1;
module_param(ocqp_support, int, 0644);
MODULE_PARM_DESC(ocqp_support, "Support on-chip SQs (default=1)");

static void set_state(struct c4iw_qp *qhp, enum c4iw_qp_state state)
{
	unsigned long flag;
	spin_lock_irqsave(&qhp->lock, flag);
	qhp->attr.state = state;
	spin_unlock_irqrestore(&qhp->lock, flag);
}

static void dealloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
{
	c4iw_ocqp_pool_free(rdev, sq->dma_addr, sq->memsize);
}

static void dealloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
{
	dma_free_coherent(&(rdev->lldi.pdev->dev), sq->memsize, sq->queue,
			  pci_unmap_addr(sq, mapping));
}

static void dealloc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
{
	if (t4_sq_onchip(sq))
		dealloc_oc_sq(rdev, sq);
	else
		dealloc_host_sq(rdev, sq);
}

static int alloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
{
	if (!ocqp_support || !t4_ocqp_supported())
		return -ENOSYS;
	sq->dma_addr = c4iw_ocqp_pool_alloc(rdev, sq->memsize);
	if (!sq->dma_addr)
		return -ENOMEM;
	sq->phys_addr = rdev->oc_mw_pa + sq->dma_addr -
			rdev->lldi.vr->ocq.start;
	sq->queue = (__force union t4_wr *)(rdev->oc_mw_kva + sq->dma_addr -
					    rdev->lldi.vr->ocq.start);
	sq->flags |= T4_SQ_ONCHIP;
	return 0;
}

static int alloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
{
	sq->queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev), sq->memsize,
				       &(sq->dma_addr), GFP_KERNEL);
	if (!sq->queue)
		return -ENOMEM;
	sq->phys_addr = virt_to_phys(sq->queue);
	pci_unmap_addr_set(sq, mapping, sq->dma_addr);
	return 0;
}

static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
		      struct c4iw_dev_ucontext *uctx)
{
	/*
	 * uP clears EQ contexts when the connection exits rdma mode,
	 * so no need to post a RESET WR for these EQs.
	 */
	dma_free_coherent(&(rdev->lldi.pdev->dev),
			  wq->rq.memsize, wq->rq.queue,
			  dma_unmap_addr(&wq->rq, mapping));
	dealloc_sq(rdev, &wq->sq);
	c4iw_rqtpool_free(rdev, wq->rq.rqt_hwaddr, wq->rq.rqt_size);
	kfree(wq->rq.sw_rq);
	kfree(wq->sq.sw_sq);
	c4iw_put_qpid(rdev, wq->rq.qid, uctx);
	c4iw_put_qpid(rdev, wq->sq.qid, uctx);
	return 0;
}

static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
		     struct t4_cq *rcq, struct t4_cq *scq,
		     struct c4iw_dev_ucontext *uctx)
{
	int user = (uctx != &rdev->uctx);
	struct fw_ri_res_wr *res_wr;
	struct fw_ri_res *res;
	int wr_len;
	struct c4iw_wr_wait wr_wait;
	struct sk_buff *skb;
	int ret;
	int eqsize;

	wq->sq.qid = c4iw_get_qpid(rdev, uctx);
	if (!wq->sq.qid)
		return -ENOMEM;

	wq->rq.qid = c4iw_get_qpid(rdev, uctx);
	if (!wq->rq.qid)
		goto err1;

	if (!user) {
		wq->sq.sw_sq = kzalloc(wq->sq.size * sizeof *wq->sq.sw_sq,
				 GFP_KERNEL);
		if (!wq->sq.sw_sq)
			goto err2;

		wq->rq.sw_rq = kzalloc(wq->rq.size * sizeof *wq->rq.sw_rq,
				 GFP_KERNEL);
		if (!wq->rq.sw_rq)
			goto err3;
	}

	/*
	 * RQT must be a power of 2.
	 */
	wq->rq.rqt_size = roundup_pow_of_two(wq->rq.size);
	wq->rq.rqt_hwaddr = c4iw_rqtpool_alloc(rdev, wq->rq.rqt_size);
	if (!wq->rq.rqt_hwaddr)
		goto err4;

	if (user) {
		if (alloc_oc_sq(rdev, &wq->sq) && alloc_host_sq(rdev, &wq->sq))
			goto err5;
	} else
		if (alloc_host_sq(rdev, &wq->sq))
			goto err5;
	memset(wq->sq.queue, 0, wq->sq.memsize);
	dma_unmap_addr_set(&wq->sq, mapping, wq->sq.dma_addr);

	wq->rq.queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev),
					  wq->rq.memsize, &(wq->rq.dma_addr),
					  GFP_KERNEL);
	if (!wq->rq.queue)
		goto err6;
	PDBG("%s sq base va 0x%p pa 0x%llx rq base va 0x%p pa 0x%llx\n",
		__func__, wq->sq.queue,
		(unsigned long long)virt_to_phys(wq->sq.queue),
		wq->rq.queue,
		(unsigned long long)virt_to_phys(wq->rq.queue));
	memset(wq->rq.queue, 0, wq->rq.memsize);
	dma_unmap_addr_set(&wq->rq, mapping, wq->rq.dma_addr);

	wq->db = rdev->lldi.db_reg;
	wq->gts = rdev->lldi.gts_reg;
	if (user) {
		wq->sq.udb = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
					(wq->sq.qid << rdev->qpshift);
		wq->sq.udb &= PAGE_MASK;
		wq->rq.udb = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
					(wq->rq.qid << rdev->qpshift);
		wq->rq.udb &= PAGE_MASK;
	}
	wq->rdev = rdev;
	wq->rq.msn = 1;

	/* build fw_ri_res_wr */
	wr_len = sizeof *res_wr + 2 * sizeof *res;

	skb = alloc_skb(wr_len, GFP_KERNEL);
	if (!skb) {
		ret = -ENOMEM;
		goto err7;
	}
	set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);

	res_wr = (struct fw_ri_res_wr *)__skb_put(skb, wr_len);
	memset(res_wr, 0, wr_len);
	res_wr->op_nres = cpu_to_be32(
			FW_WR_OP(FW_RI_RES_WR) |
			V_FW_RI_RES_WR_NRES(2) |