-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for *
- * RoCE (RDMA over Converged Ethernet) adapters. *
- * Copyright (C) 2008-2012 Emulex. All rights reserved. *
- * EMULEX and SLI are trademarks of Emulex. *
- * www.emulex.com *
- * *
- * This program is free software; you can redistribute it and/or *
- * modify it under the terms of version 2 of the GNU General *
- * Public License as published by the Free Software Foundation. *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID. See the GNU General Public License for *
- * more details, a copy of which can be found in the file COPYING *
- * included with this package. *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * 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:
+ *
+ * - 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.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT HOLDER 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.
*
* Contact Information:
* linux-drivers@emulex.com
* Emulex
* 3333 Susan Street
* Costa Mesa, CA 92626
- *******************************************************************/
+ */
#include <linux/dma-mapping.h>
#include <rdma/ib_verbs.h>
#include <rdma/iw_cm.h>
#include <rdma/ib_umem.h>
#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
#include "ocrdma.h"
#include "ocrdma_hw.h"
int ocrdma_query_gid(struct ib_device *ibdev, u8 port,
int index, union ib_gid *sgid)
{
+ int ret;
struct ocrdma_dev *dev;
dev = get_ocrdma_dev(ibdev);
if (index >= OCRDMA_MAX_SGID)
return -EINVAL;
- memcpy(sgid, &dev->sgid_tbl[index], sizeof(*sgid));
+ ret = ib_get_cached_gid(ibdev, port, index, sgid, NULL);
+ if (ret == -EAGAIN) {
+ memcpy(sgid, &zgid, sizeof(*sgid));
+ return 0;
+ }
+
+ return ret;
+}
+
+int ocrdma_add_gid(struct ib_device *device,
+ u8 port_num,
+ unsigned int index,
+ const union ib_gid *gid,
+ const struct ib_gid_attr *attr,
+ void **context) {
+ return 0;
+}
+int ocrdma_del_gid(struct ib_device *device,
+ u8 port_num,
+ unsigned int index,
+ void **context) {
return 0;
}
-int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr)
+int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
+ struct ib_udata *uhw)
{
struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
+ if (uhw->inlen || uhw->outlen)
+ return -EINVAL;
+
memset(attr, 0, sizeof *attr);
memcpy(&attr->fw_ver, &dev->attr.fw_ver[0],
min(sizeof(dev->attr.fw_ver), sizeof(attr->fw_ver)));
return 0;
}
+struct net_device *ocrdma_get_netdev(struct ib_device *ibdev, u8 port_num)
+{
+ struct ocrdma_dev *dev;
+ struct net_device *ndev = NULL;
+
+ rcu_read_lock();
+
+ dev = get_ocrdma_dev(ibdev);
+ if (dev)
+ ndev = dev->nic_info.netdev;
+ if (ndev)
+ dev_hold(ndev);
+
+ rcu_read_unlock();
+
+ return ndev;
+}
+
static inline void get_link_speed_and_width(struct ocrdma_dev *dev,
u8 *ib_speed, u8 *ib_width)
{
int status;
u8 speed;
- status = ocrdma_mbx_get_link_speed(dev, &speed);
+ status = ocrdma_mbx_get_link_speed(dev, &speed, NULL);
if (status)
speed = OCRDMA_PHYS_LINK_SPEED_ZERO;
props->port_cap_flags =
IB_PORT_CM_SUP |
IB_PORT_REINIT_SUP |
- IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP | IB_PORT_IP_BASED_GIDS;
+ IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP |
+ IB_PORT_IP_BASED_GIDS;
props->gid_tbl_len = OCRDMA_MAX_SGID;
props->pkey_tbl_len = 1;
props->bad_pkey_cntr = 0;
if (dev->pd_mgr->pd_prealloc_valid) {
status = ocrdma_get_pd_num(dev, pd);
- return (status == 0) ? pd : ERR_PTR(status);
+ if (status == 0) {
+ return pd;
+ } else {
+ kfree(pd);
+ return ERR_PTR(status);
+ }
}
retry:
(void) ocrdma_mbx_dealloc_lkey(dev, mr->hwmr.fr_mr, mr->hwmr.lkey);
+ kfree(mr->pages);
ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
/* it could be user registered memory. */
return status;
}
-struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
+struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
+ const struct ib_cq_init_attr *attr,
struct ib_ucontext *ib_ctx,
struct ib_udata *udata)
{
+ int entries = attr->cqe;
struct ocrdma_cq *cq;
struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
struct ocrdma_ucontext *uctx = NULL;
int status;
struct ocrdma_create_cq_ureq ureq;
+ if (attr->flags)
+ return ERR_PTR(-EINVAL);
+
if (udata) {
if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
return ERR_PTR(-EFAULT);
{
struct ocrdma_ewqe_ud_hdr *ud_hdr =
(struct ocrdma_ewqe_ud_hdr *)(hdr + 1);
- struct ocrdma_ah *ah = get_ocrdma_ah(wr->wr.ud.ah);
+ struct ocrdma_ah *ah = get_ocrdma_ah(ud_wr(wr)->ah);
- ud_hdr->rsvd_dest_qpn = wr->wr.ud.remote_qpn;
+ ud_hdr->rsvd_dest_qpn = ud_wr(wr)->remote_qpn;
if (qp->qp_type == IB_QPT_GSI)
ud_hdr->qkey = qp->qkey;
else
- ud_hdr->qkey = wr->wr.ud.remote_qkey;
+ ud_hdr->qkey = ud_wr(wr)->remote_qkey;
ud_hdr->rsvd_ahid = ah->id;
if (ah->av->valid & OCRDMA_AV_VLAN_VALID)
hdr->cw |= (OCRDMA_FLAG_AH_VLAN_PR << OCRDMA_WQE_FLAGS_SHIFT);
status = ocrdma_build_inline_sges(qp, hdr, sge, wr, wqe_size);
if (status)
return status;
- ext_rw->addr_lo = wr->wr.rdma.remote_addr;
- ext_rw->addr_hi = upper_32_bits(wr->wr.rdma.remote_addr);
- ext_rw->lrkey = wr->wr.rdma.rkey;
+ ext_rw->addr_lo = rdma_wr(wr)->remote_addr;
+ ext_rw->addr_hi = upper_32_bits(rdma_wr(wr)->remote_addr);
+ ext_rw->lrkey = rdma_wr(wr)->rkey;
ext_rw->len = hdr->total_len;
return 0;
}
hdr->cw |= (OCRDMA_READ << OCRDMA_WQE_OPCODE_SHIFT);
hdr->cw |= (OCRDMA_TYPE_LKEY << OCRDMA_WQE_TYPE_SHIFT);
- ext_rw->addr_lo = wr->wr.rdma.remote_addr;
- ext_rw->addr_hi = upper_32_bits(wr->wr.rdma.remote_addr);
- ext_rw->lrkey = wr->wr.rdma.rkey;
+ ext_rw->addr_lo = rdma_wr(wr)->remote_addr;
+ ext_rw->addr_hi = upper_32_bits(rdma_wr(wr)->remote_addr);
+ ext_rw->lrkey = rdma_wr(wr)->rkey;
ext_rw->len = hdr->total_len;
}
-static void build_frmr_pbes(struct ib_send_wr *wr, struct ocrdma_pbl *pbl_tbl,
- struct ocrdma_hw_mr *hwmr)
-{
- int i;
- u64 buf_addr = 0;
- int num_pbes;
- struct ocrdma_pbe *pbe;
-
- pbe = (struct ocrdma_pbe *)pbl_tbl->va;
- num_pbes = 0;
-
- /* go through the OS phy regions & fill hw pbe entries into pbls. */
- for (i = 0; i < wr->wr.fast_reg.page_list_len; i++) {
- /* number of pbes can be more for one OS buf, when
- * buffers are of different sizes.
- * split the ib_buf to one or more pbes.
- */
- buf_addr = wr->wr.fast_reg.page_list->page_list[i];
- pbe->pa_lo = cpu_to_le32((u32) (buf_addr & PAGE_MASK));
- pbe->pa_hi = cpu_to_le32((u32) upper_32_bits(buf_addr));
- num_pbes += 1;
- pbe++;
-
- /* if the pbl is full storing the pbes,
- * move to next pbl.
- */
- if (num_pbes == (hwmr->pbl_size/sizeof(u64))) {
- pbl_tbl++;
- pbe = (struct ocrdma_pbe *)pbl_tbl->va;
- }
- }
- return;
-}
-
static int get_encoded_page_size(int pg_sz)
{
/* Max size is 256M 4096 << 16 */
return i;
}
-
-static int ocrdma_build_fr(struct ocrdma_qp *qp, struct ocrdma_hdr_wqe *hdr,
- struct ib_send_wr *wr)
+static int ocrdma_build_reg(struct ocrdma_qp *qp,
+ struct ocrdma_hdr_wqe *hdr,
+ struct ib_reg_wr *wr)
{
u64 fbo;
struct ocrdma_ewqe_fr *fast_reg = (struct ocrdma_ewqe_fr *)(hdr + 1);
- struct ocrdma_mr *mr;
- struct ocrdma_dev *dev = get_ocrdma_dev(qp->ibqp.device);
+ struct ocrdma_mr *mr = get_ocrdma_mr(wr->mr);
+ struct ocrdma_pbl *pbl_tbl = mr->hwmr.pbl_table;
+ struct ocrdma_pbe *pbe;
u32 wqe_size = sizeof(*fast_reg) + sizeof(*hdr);
+ int num_pbes = 0, i;
wqe_size = roundup(wqe_size, OCRDMA_WQE_ALIGN_BYTES);
- if (wr->wr.fast_reg.page_list_len > dev->attr.max_pages_per_frmr)
- return -EINVAL;
-
hdr->cw |= (OCRDMA_FR_MR << OCRDMA_WQE_OPCODE_SHIFT);
hdr->cw |= ((wqe_size / OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT);
- if (wr->wr.fast_reg.page_list_len == 0)
- BUG();
- if (wr->wr.fast_reg.access_flags & IB_ACCESS_LOCAL_WRITE)
+ if (wr->access & IB_ACCESS_LOCAL_WRITE)
hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_LOCAL_WR;
- if (wr->wr.fast_reg.access_flags & IB_ACCESS_REMOTE_WRITE)
+ if (wr->access & IB_ACCESS_REMOTE_WRITE)
hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_WR;
- if (wr->wr.fast_reg.access_flags & IB_ACCESS_REMOTE_READ)
+ if (wr->access & IB_ACCESS_REMOTE_READ)
hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_RD;
- hdr->lkey = wr->wr.fast_reg.rkey;
- hdr->total_len = wr->wr.fast_reg.length;
+ hdr->lkey = wr->key;
+ hdr->total_len = mr->ibmr.length;
- fbo = wr->wr.fast_reg.iova_start -
- (wr->wr.fast_reg.page_list->page_list[0] & PAGE_MASK);
+ fbo = mr->ibmr.iova - mr->pages[0];
- fast_reg->va_hi = upper_32_bits(wr->wr.fast_reg.iova_start);
- fast_reg->va_lo = (u32) (wr->wr.fast_reg.iova_start & 0xffffffff);
+ fast_reg->va_hi = upper_32_bits(mr->ibmr.iova);
+ fast_reg->va_lo = (u32) (mr->ibmr.iova & 0xffffffff);
fast_reg->fbo_hi = upper_32_bits(fbo);
fast_reg->fbo_lo = (u32) fbo & 0xffffffff;
- fast_reg->num_sges = wr->wr.fast_reg.page_list_len;
- fast_reg->size_sge =
- get_encoded_page_size(1 << wr->wr.fast_reg.page_shift);
- mr = (struct ocrdma_mr *) (unsigned long)
- dev->stag_arr[(hdr->lkey >> 8) & (OCRDMA_MAX_STAG - 1)];
- build_frmr_pbes(wr, mr->hwmr.pbl_table, &mr->hwmr);
+ fast_reg->num_sges = mr->npages;
+ fast_reg->size_sge = get_encoded_page_size(mr->ibmr.page_size);
+
+ pbe = pbl_tbl->va;
+ for (i = 0; i < mr->npages; i++) {
+ u64 buf_addr = mr->pages[i];
+
+ pbe->pa_lo = cpu_to_le32((u32) (buf_addr & PAGE_MASK));
+ pbe->pa_hi = cpu_to_le32((u32) upper_32_bits(buf_addr));
+ num_pbes += 1;
+ pbe++;
+
+ /* if the pbl is full storing the pbes,
+ * move to next pbl.
+ */
+ if (num_pbes == (mr->hwmr.pbl_size/sizeof(u64))) {
+ pbl_tbl++;
+ pbe = (struct ocrdma_pbe *)pbl_tbl->va;
+ }
+ }
+
return 0;
}
OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT;
hdr->lkey = wr->ex.invalidate_rkey;
break;
- case IB_WR_FAST_REG_MR:
- status = ocrdma_build_fr(qp, hdr, wr);
+ case IB_WR_REG_MR:
+ status = ocrdma_build_reg(qp, hdr, reg_wr(wr));
break;
default:
status = -EINVAL;
ibwc->opcode = IB_WC_SEND;
break;
case OCRDMA_FR_MR:
- ibwc->opcode = IB_WC_FAST_REG_MR;
+ ibwc->opcode = IB_WC_REG_MR;
break;
case OCRDMA_LKEY_INV:
ibwc->opcode = IB_WC_LOCAL_INV;
}
stop_cqe:
cq->getp = cur_getp;
- if (cq->deferred_arm) {
- ocrdma_ring_cq_db(dev, cq->id, true, cq->deferred_sol,
- polled_hw_cqes);
+ if (cq->deferred_arm || polled_hw_cqes) {
+ ocrdma_ring_cq_db(dev, cq->id, cq->deferred_arm,
+ cq->deferred_sol, polled_hw_cqes);
cq->deferred_arm = false;
cq->deferred_sol = false;
- } else {
- /* We need to pop the CQE. No need to arm */
- ocrdma_ring_cq_db(dev, cq->id, false, cq->deferred_sol,
- polled_hw_cqes);
- cq->deferred_sol = false;
}
return i;
return 0;
}
-struct ib_mr *ocrdma_alloc_frmr(struct ib_pd *ibpd, int max_page_list_len)
+struct ib_mr *ocrdma_alloc_mr(struct ib_pd *ibpd,
+ enum ib_mr_type mr_type,
+ u32 max_num_sg)
{
int status;
struct ocrdma_mr *mr;
struct ocrdma_pd *pd = get_ocrdma_pd(ibpd);
struct ocrdma_dev *dev = get_ocrdma_dev(ibpd->device);
- if (max_page_list_len > dev->attr.max_pages_per_frmr)
+ if (mr_type != IB_MR_TYPE_MEM_REG)
+ return ERR_PTR(-EINVAL);
+
+ if (max_num_sg > dev->attr.max_pages_per_frmr)
return ERR_PTR(-EINVAL);
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
return ERR_PTR(-ENOMEM);
- status = ocrdma_get_pbl_info(dev, mr, max_page_list_len);
+ mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+ if (!mr->pages) {
+ status = -ENOMEM;
+ goto pl_err;
+ }
+
+ status = ocrdma_get_pbl_info(dev, mr, max_num_sg);
if (status)
goto pbl_err;
mr->hwmr.fr_mr = 1;
mbx_err:
ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
pbl_err:
+ kfree(mr->pages);
+pl_err:
kfree(mr);
return ERR_PTR(-ENOMEM);
}
-struct ib_fast_reg_page_list *ocrdma_alloc_frmr_page_list(struct ib_device
- *ibdev,
- int page_list_len)
-{
- struct ib_fast_reg_page_list *frmr_list;
- int size;
-
- size = sizeof(*frmr_list) + (page_list_len * sizeof(u64));
- frmr_list = kzalloc(size, GFP_KERNEL);
- if (!frmr_list)
- return ERR_PTR(-ENOMEM);
- frmr_list->page_list = (u64 *)(frmr_list + 1);
- return frmr_list;
-}
-
-void ocrdma_free_frmr_page_list(struct ib_fast_reg_page_list *page_list)
-{
- kfree(page_list);
-}
-
#define MAX_KERNEL_PBE_SIZE 65536
static inline int count_kernel_pbes(struct ib_phys_buf *buf_list,
int buf_cnt, u32 *pbe_size)
kfree(mr);
return ERR_PTR(status);
}
+
+static int ocrdma_set_page(struct ib_mr *ibmr, u64 addr)
+{
+ struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+ if (unlikely(mr->npages == mr->hwmr.num_pbes))
+ return -ENOMEM;
+
+ mr->pages[mr->npages++] = addr;
+
+ return 0;
+}
+
+int ocrdma_map_mr_sg(struct ib_mr *ibmr,
+ struct scatterlist *sg,
+ int sg_nents)
+{
+ struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+ mr->npages = 0;
+
+ return ib_sg_to_pages(ibmr, sg, sg_nents, ocrdma_set_page);
+}
Code Review / kvmfornfv.git / blobdiff