/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
- * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies. All rights reserved.
* Copyright (c) 2004 Voltaire, Inc. All rights reserved.
*
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
- * $Id: mthca_provider.c 1397 2004-12-28 05:09:00Z roland $
+ * $Id: mthca_provider.c 4859 2006-01-09 21:55:10Z roland $
*/
-#include <ib_smi.h>
+#include <rdma/ib_smi.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
#include <linux/mm.h>
#include "mthca_dev.h"
#include "mthca_user.h"
#include "mthca_memfree.h"
+static void init_query_mad(struct ib_smp *mad)
+{
+ mad->base_version = 1;
+ mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
+ mad->class_version = 1;
+ mad->method = IB_MGMT_METHOD_GET;
+}
+
static int mthca_query_device(struct ib_device *ibdev,
struct ib_device_attr *props)
{
struct ib_smp *in_mad = NULL;
struct ib_smp *out_mad = NULL;
int err = -ENOMEM;
- struct mthca_dev* mdev = to_mdev(ibdev);
+ struct mthca_dev *mdev = to_mdev(ibdev);
u8 status;
- in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
if (!in_mad || !out_mad)
goto out;
props->fw_ver = mdev->fw_ver;
- memset(in_mad, 0, sizeof *in_mad);
- in_mad->base_version = 1;
- in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- in_mad->class_version = 1;
- in_mad->method = IB_MGMT_METHOD_GET;
- in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
err = mthca_MAD_IFC(mdev, 1, 1,
1, NULL, NULL, in_mad, out_mad,
props->vendor_id = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
0xffffff;
props->vendor_part_id = be16_to_cpup((__be16 *) (out_mad->data + 30));
- props->hw_ver = be16_to_cpup((__be16 *) (out_mad->data + 32));
+ props->hw_ver = be32_to_cpup((__be32 *) (out_mad->data + 32));
memcpy(&props->sys_image_guid, out_mad->data + 4, 8);
- memcpy(&props->node_guid, out_mad->data + 12, 8);
props->max_mr_size = ~0ull;
+ props->page_size_cap = mdev->limits.page_size_cap;
props->max_qp = mdev->limits.num_qps - mdev->limits.reserved_qps;
- props->max_qp_wr = 0xffff;
+ props->max_qp_wr = mdev->limits.max_wqes;
props->max_sge = mdev->limits.max_sg;
props->max_cq = mdev->limits.num_cqs - mdev->limits.reserved_cqs;
- props->max_cqe = 0xffff;
+ props->max_cqe = mdev->limits.max_cqes;
props->max_mr = mdev->limits.num_mpts - mdev->limits.reserved_mrws;
props->max_pd = mdev->limits.num_pds - mdev->limits.reserved_pds;
props->max_qp_rd_atom = 1 << mdev->qp_table.rdb_shift;
- props->max_qp_init_rd_atom = 1 << mdev->qp_table.rdb_shift;
+ props->max_qp_init_rd_atom = mdev->limits.max_qp_init_rdma;
+ props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp;
+ props->max_srq = mdev->limits.num_srqs - mdev->limits.reserved_srqs;
+ props->max_srq_wr = mdev->limits.max_srq_wqes;
+ props->max_srq_sge = mdev->limits.max_srq_sge;
props->local_ca_ack_delay = mdev->limits.local_ca_ack_delay;
+ props->atomic_cap = mdev->limits.flags & DEV_LIM_FLAG_ATOMIC ?
+ IB_ATOMIC_HCA : IB_ATOMIC_NONE;
+ props->max_pkeys = mdev->limits.pkey_table_len;
+ props->max_mcast_grp = mdev->limits.num_mgms + mdev->limits.num_amgms;
+ props->max_mcast_qp_attach = MTHCA_QP_PER_MGM;
+ props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
+ props->max_mcast_grp;
+ /*
+ * If Sinai memory key optimization is being used, then only
+ * the 8-bit key portion will change. For other HCAs, the
+ * unused index bits will also be used for FMR remapping.
+ */
+ if (mdev->mthca_flags & MTHCA_FLAG_SINAI_OPT)
+ props->max_map_per_fmr = 255;
+ else
+ props->max_map_per_fmr =
+ (1 << (32 - ilog2(mdev->limits.num_mpts))) - 1;
err = 0;
out:
int err = -ENOMEM;
u8 status;
- in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
if (!in_mad || !out_mad)
goto out;
- memset(in_mad, 0, sizeof *in_mad);
- in_mad->base_version = 1;
- in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- in_mad->class_version = 1;
- in_mad->method = IB_MGMT_METHOD_GET;
- in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
- in_mad->attr_mod = cpu_to_be32(port);
+ memset(props, 0, sizeof *props);
+
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
+ in_mad->attr_mod = cpu_to_be32(port);
err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1,
port, NULL, NULL, in_mad, out_mad,
props->phys_state = out_mad->data[33] >> 4;
props->port_cap_flags = be32_to_cpup((__be32 *) (out_mad->data + 20));
props->gid_tbl_len = to_mdev(ibdev)->limits.gid_table_len;
+ props->max_msg_sz = 0x80000000;
props->pkey_tbl_len = to_mdev(ibdev)->limits.pkey_table_len;
+ props->bad_pkey_cntr = be16_to_cpup((__be16 *) (out_mad->data + 46));
props->qkey_viol_cntr = be16_to_cpup((__be16 *) (out_mad->data + 48));
props->active_width = out_mad->data[31] & 0xf;
props->active_speed = out_mad->data[35] >> 4;
+ props->max_mtu = out_mad->data[41] & 0xf;
+ props->active_mtu = out_mad->data[36] >> 4;
+ props->subnet_timeout = out_mad->data[51] & 0x1f;
+ props->max_vl_num = out_mad->data[37] >> 4;
+ props->init_type_reply = out_mad->data[41] >> 4;
out:
kfree(in_mad);
return err;
}
+static int mthca_modify_device(struct ib_device *ibdev,
+ int mask,
+ struct ib_device_modify *props)
+{
+ if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
+ return -EOPNOTSUPP;
+
+ if (mask & IB_DEVICE_MODIFY_NODE_DESC) {
+ if (mutex_lock_interruptible(&to_mdev(ibdev)->cap_mask_mutex))
+ return -ERESTARTSYS;
+ memcpy(ibdev->node_desc, props->node_desc, 64);
+ mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex);
+ }
+
+ return 0;
+}
+
static int mthca_modify_port(struct ib_device *ibdev,
u8 port, int port_modify_mask,
struct ib_port_modify *props)
int err;
u8 status;
- if (down_interruptible(&to_mdev(ibdev)->cap_mask_mutex))
+ if (mutex_lock_interruptible(&to_mdev(ibdev)->cap_mask_mutex))
return -ERESTARTSYS;
err = mthca_query_port(ibdev, port, &attr);
}
out:
- up(&to_mdev(ibdev)->cap_mask_mutex);
+ mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex);
return err;
}
int err = -ENOMEM;
u8 status;
- in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
if (!in_mad || !out_mad)
goto out;
- memset(in_mad, 0, sizeof *in_mad);
- in_mad->base_version = 1;
- in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- in_mad->class_version = 1;
- in_mad->method = IB_MGMT_METHOD_GET;
- in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE;
- in_mad->attr_mod = cpu_to_be32(index / 32);
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE;
+ in_mad->attr_mod = cpu_to_be32(index / 32);
err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1,
port, NULL, NULL, in_mad, out_mad,
int err = -ENOMEM;
u8 status;
- in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
if (!in_mad || !out_mad)
goto out;
- memset(in_mad, 0, sizeof *in_mad);
- in_mad->base_version = 1;
- in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- in_mad->class_version = 1;
- in_mad->method = IB_MGMT_METHOD_GET;
- in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
- in_mad->attr_mod = cpu_to_be32(port);
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
+ in_mad->attr_mod = cpu_to_be32(port);
err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1,
port, NULL, NULL, in_mad, out_mad,
memcpy(gid->raw, out_mad->data + 8, 8);
- memset(in_mad, 0, sizeof *in_mad);
- in_mad->base_version = 1;
- in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- in_mad->class_version = 1;
- in_mad->method = IB_MGMT_METHOD_GET;
- in_mad->attr_id = IB_SMP_ATTR_GUID_INFO;
- in_mad->attr_mod = cpu_to_be32(index / 8);
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_GUID_INFO;
+ in_mad->attr_mod = cpu_to_be32(index / 8);
err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1,
port, NULL, NULL, in_mad, out_mad,
goto out;
}
- memcpy(gid->raw + 8, out_mad->data + (index % 8) * 16, 8);
+ memcpy(gid->raw + 8, out_mad->data + (index % 8) * 8, 8);
out:
kfree(in_mad);
return 0;
}
+static struct ib_srq *mthca_create_srq(struct ib_pd *pd,
+ struct ib_srq_init_attr *init_attr,
+ struct ib_udata *udata)
+{
+ struct mthca_create_srq ucmd;
+ struct mthca_ucontext *context = NULL;
+ struct mthca_srq *srq;
+ int err;
+
+ srq = kmalloc(sizeof *srq, GFP_KERNEL);
+ if (!srq)
+ return ERR_PTR(-ENOMEM);
+
+ if (pd->uobject) {
+ context = to_mucontext(pd->uobject->context);
+
+ if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) {
+ err = -EFAULT;
+ goto err_free;
+ }
+
+ err = mthca_map_user_db(to_mdev(pd->device), &context->uar,
+ context->db_tab, ucmd.db_index,
+ ucmd.db_page);
+
+ if (err)
+ goto err_free;
+
+ srq->mr.ibmr.lkey = ucmd.lkey;
+ srq->db_index = ucmd.db_index;
+ }
+
+ err = mthca_alloc_srq(to_mdev(pd->device), to_mpd(pd),
+ &init_attr->attr, srq);
+
+ if (err && pd->uobject)
+ mthca_unmap_user_db(to_mdev(pd->device), &context->uar,
+ context->db_tab, ucmd.db_index);
+
+ if (err)
+ goto err_free;
+
+ if (context && ib_copy_to_udata(udata, &srq->srqn, sizeof (__u32))) {
+ mthca_free_srq(to_mdev(pd->device), srq);
+ err = -EFAULT;
+ goto err_free;
+ }
+
+ return &srq->ibsrq;
+
+err_free:
+ kfree(srq);
+
+ return ERR_PTR(err);
+}
+
+static int mthca_destroy_srq(struct ib_srq *srq)
+{
+ struct mthca_ucontext *context;
+
+ if (srq->uobject) {
+ context = to_mucontext(srq->uobject->context);
+
+ mthca_unmap_user_db(to_mdev(srq->device), &context->uar,
+ context->db_tab, to_msrq(srq)->db_index);
+ }
+
+ mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
+ kfree(srq);
+
+ return 0;
+}
+
static struct ib_qp *mthca_create_qp(struct ib_pd *pd,
struct ib_qp_init_attr *init_attr,
struct ib_udata *udata)
struct mthca_qp *qp;
int err;
+ if (init_attr->create_flags)
+ return ERR_PTR(-EINVAL);
+
switch (init_attr->qp_type) {
case IB_QPT_RC:
case IB_QPT_UC:
if (pd->uobject) {
context = to_mucontext(pd->uobject->context);
- if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd))
+ if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) {
+ kfree(qp);
return ERR_PTR(-EFAULT);
+ }
err = mthca_map_user_db(to_mdev(pd->device), &context->uar,
context->db_tab,
return ERR_PTR(err);
}
- init_attr->cap.max_inline_data = 0;
init_attr->cap.max_send_wr = qp->sq.max;
init_attr->cap.max_recv_wr = qp->rq.max;
init_attr->cap.max_send_sge = qp->sq.max_gs;
init_attr->cap.max_recv_sge = qp->rq.max_gs;
+ init_attr->cap.max_inline_data = qp->max_inline_data;
return &qp->ibqp;
}
}
static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
+ int comp_vector,
struct ib_ucontext *context,
struct ib_udata *udata)
{
int nent;
int err;
+ if (entries < 1 || entries > to_mdev(ibdev)->limits.max_cqes)
+ return ERR_PTR(-EINVAL);
+
if (context) {
if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd))
return ERR_PTR(-EFAULT);
}
if (context) {
- cq->mr.ibmr.lkey = ucmd.lkey;
- cq->set_ci_db_index = ucmd.set_db_index;
- cq->arm_db_index = ucmd.arm_db_index;
+ cq->buf.mr.ibmr.lkey = ucmd.lkey;
+ cq->set_ci_db_index = ucmd.set_db_index;
+ cq->arm_db_index = ucmd.arm_db_index;
}
for (nent = 1; nent <= entries; nent <<= 1)
goto err_free;
}
+ cq->resize_buf = NULL;
+
return &cq->ibcq;
err_free:
return ERR_PTR(err);
}
+static int mthca_alloc_resize_buf(struct mthca_dev *dev, struct mthca_cq *cq,
+ int entries)
+{
+ int ret;
+
+ spin_lock_irq(&cq->lock);
+ if (cq->resize_buf) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC);
+ if (!cq->resize_buf) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ cq->resize_buf->state = CQ_RESIZE_ALLOC;
+
+ ret = 0;
+
+unlock:
+ spin_unlock_irq(&cq->lock);
+
+ if (ret)
+ return ret;
+
+ ret = mthca_alloc_cq_buf(dev, &cq->resize_buf->buf, entries);
+ if (ret) {
+ spin_lock_irq(&cq->lock);
+ kfree(cq->resize_buf);
+ cq->resize_buf = NULL;
+ spin_unlock_irq(&cq->lock);
+ return ret;
+ }
+
+ cq->resize_buf->cqe = entries - 1;
+
+ spin_lock_irq(&cq->lock);
+ cq->resize_buf->state = CQ_RESIZE_READY;
+ spin_unlock_irq(&cq->lock);
+
+ return 0;
+}
+
+static int mthca_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
+{
+ struct mthca_dev *dev = to_mdev(ibcq->device);
+ struct mthca_cq *cq = to_mcq(ibcq);
+ struct mthca_resize_cq ucmd;
+ u32 lkey;
+ u8 status;
+ int ret;
+
+ if (entries < 1 || entries > dev->limits.max_cqes)
+ return -EINVAL;
+
+ mutex_lock(&cq->mutex);
+
+ entries = roundup_pow_of_two(entries + 1);
+ if (entries == ibcq->cqe + 1) {
+ ret = 0;
+ goto out;
+ }
+
+ if (cq->is_kernel) {
+ ret = mthca_alloc_resize_buf(dev, cq, entries);
+ if (ret)
+ goto out;
+ lkey = cq->resize_buf->buf.mr.ibmr.lkey;
+ } else {
+ if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ lkey = ucmd.lkey;
+ }
+
+ ret = mthca_RESIZE_CQ(dev, cq->cqn, lkey, ilog2(entries), &status);
+ if (status)
+ ret = -EINVAL;
+
+ if (ret) {
+ if (cq->resize_buf) {
+ mthca_free_cq_buf(dev, &cq->resize_buf->buf,
+ cq->resize_buf->cqe);
+ kfree(cq->resize_buf);
+ spin_lock_irq(&cq->lock);
+ cq->resize_buf = NULL;
+ spin_unlock_irq(&cq->lock);
+ }
+ goto out;
+ }
+
+ if (cq->is_kernel) {
+ struct mthca_cq_buf tbuf;
+ int tcqe;
+
+ spin_lock_irq(&cq->lock);
+ if (cq->resize_buf->state == CQ_RESIZE_READY) {
+ mthca_cq_resize_copy_cqes(cq);
+ tbuf = cq->buf;
+ tcqe = cq->ibcq.cqe;
+ cq->buf = cq->resize_buf->buf;
+ cq->ibcq.cqe = cq->resize_buf->cqe;
+ } else {
+ tbuf = cq->resize_buf->buf;
+ tcqe = cq->resize_buf->cqe;
+ }
+
+ kfree(cq->resize_buf);
+ cq->resize_buf = NULL;
+ spin_unlock_irq(&cq->lock);
+
+ mthca_free_cq_buf(dev, &tbuf, tcqe);
+ } else
+ ibcq->cqe = entries - 1;
+
+out:
+ mutex_unlock(&cq->mutex);
+
+ return ret;
+}
+
static int mthca_destroy_cq(struct ib_cq *cq)
{
if (cq->uobject) {
return ERR_PTR(err);
}
+ mr->umem = NULL;
+
return &mr->ibmr;
}
struct mthca_mr *mr;
u64 *page_list;
u64 total_size;
- u64 mask;
+ unsigned long mask;
int shift;
int npages;
int err;
int i, j, n;
- /* First check that we have enough alignment */
- if ((*iova_start & ~PAGE_MASK) != (buffer_list[0].addr & ~PAGE_MASK))
- return ERR_PTR(-EINVAL);
-
- if (num_phys_buf > 1 &&
- ((buffer_list[0].addr + buffer_list[0].size) & ~PAGE_MASK))
- return ERR_PTR(-EINVAL);
-
- mask = 0;
+ mask = buffer_list[0].addr ^ *iova_start;
total_size = 0;
for (i = 0; i < num_phys_buf; ++i) {
- if (i != 0 && buffer_list[i].addr & ~PAGE_MASK)
- return ERR_PTR(-EINVAL);
- if (i != 0 && i != num_phys_buf - 1 &&
- (buffer_list[i].size & ~PAGE_MASK))
- return ERR_PTR(-EINVAL);
+ if (i != 0)
+ mask |= buffer_list[i].addr;
+ if (i != num_phys_buf - 1)
+ mask |= buffer_list[i].addr + buffer_list[i].size;
total_size += buffer_list[i].size;
- if (i > 0)
- mask |= buffer_list[i].addr;
}
- /* Find largest page shift we can use to cover buffers */
- for (shift = PAGE_SHIFT; shift < 31; ++shift)
- if (num_phys_buf > 1) {
- if ((1ULL << shift) & mask)
- break;
- } else {
- if (1ULL << shift >=
- buffer_list[0].size +
- (buffer_list[0].addr & ((1ULL << shift) - 1)))
- break;
- }
+ if (mask & ~PAGE_MASK)
+ return ERR_PTR(-EINVAL);
+
+ shift = __ffs(mask | 1 << 31);
buffer_list[0].size += buffer_list[0].addr & ((1ULL << shift) - 1);
buffer_list[0].addr &= ~0ull << shift;
}
kfree(page_list);
+ mr->umem = NULL;
+
return &mr->ibmr;
}
-static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, struct ib_umem *region,
- int acc, struct ib_udata *udata)
+static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+ u64 virt, int acc, struct ib_udata *udata)
{
struct mthca_dev *dev = to_mdev(pd->device);
struct ib_umem_chunk *chunk;
int shift, n, len;
int i, j, k;
int err = 0;
-
- shift = ffs(region->page_size) - 1;
+ int write_mtt_size;
mr = kmalloc(sizeof *mr, GFP_KERNEL);
if (!mr)
return ERR_PTR(-ENOMEM);
+ mr->umem = ib_umem_get(pd->uobject->context, start, length, acc);
+ if (IS_ERR(mr->umem)) {
+ err = PTR_ERR(mr->umem);
+ goto err;
+ }
+
+ shift = ffs(mr->umem->page_size) - 1;
+
n = 0;
- list_for_each_entry(chunk, ®ion->chunk_list, list)
+ list_for_each_entry(chunk, &mr->umem->chunk_list, list)
n += chunk->nents;
mr->mtt = mthca_alloc_mtt(dev, n);
if (IS_ERR(mr->mtt)) {
err = PTR_ERR(mr->mtt);
- goto err;
+ goto err_umem;
}
pages = (u64 *) __get_free_page(GFP_KERNEL);
i = n = 0;
- list_for_each_entry(chunk, ®ion->chunk_list, list)
+ write_mtt_size = min(mthca_write_mtt_size(dev), (int) (PAGE_SIZE / sizeof *pages));
+
+ list_for_each_entry(chunk, &mr->umem->chunk_list, list)
for (j = 0; j < chunk->nmap; ++j) {
len = sg_dma_len(&chunk->page_list[j]) >> shift;
for (k = 0; k < len; ++k) {
pages[i++] = sg_dma_address(&chunk->page_list[j]) +
- region->page_size * k;
+ mr->umem->page_size * k;
/*
- * Be friendly to WRITE_MTT command
- * and leave two empty slots for the
- * index and reserved fields of the
- * mailbox.
+ * Be friendly to write_mtt and pass it chunks
+ * of appropriate size.
*/
- if (i == PAGE_SIZE / sizeof (u64) - 2) {
- err = mthca_write_mtt(dev, mr->mtt,
- n, pages, i);
+ if (i == write_mtt_size) {
+ err = mthca_write_mtt(dev, mr->mtt, n, pages, i);
if (err)
goto mtt_done;
n += i;
if (err)
goto err_mtt;
- err = mthca_mr_alloc(dev, to_mpd(pd)->pd_num, shift, region->virt_base,
- region->length, convert_access(acc), mr);
+ err = mthca_mr_alloc(dev, to_mpd(pd)->pd_num, shift, virt, length,
+ convert_access(acc), mr);
if (err)
goto err_mtt;
err_mtt:
mthca_free_mtt(dev, mr->mtt);
+err_umem:
+ ib_umem_release(mr->umem);
+
err:
kfree(mr);
return ERR_PTR(err);
static int mthca_dereg_mr(struct ib_mr *mr)
{
struct mthca_mr *mmr = to_mmr(mr);
+
mthca_free_mr(to_mdev(mr->device), mmr);
+ if (mmr->umem)
+ ib_umem_release(mmr->umem);
kfree(mmr);
+
return 0;
}
return 0;
}
-static ssize_t show_rev(struct class_device *cdev, char *buf)
+static ssize_t show_rev(struct device *device, struct device_attribute *attr,
+ char *buf)
{
- struct mthca_dev *dev = container_of(cdev, struct mthca_dev, ib_dev.class_dev);
+ struct mthca_dev *dev =
+ container_of(device, struct mthca_dev, ib_dev.dev);
return sprintf(buf, "%x\n", dev->rev_id);
}
-static ssize_t show_fw_ver(struct class_device *cdev, char *buf)
+static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
+ char *buf)
{
- struct mthca_dev *dev = container_of(cdev, struct mthca_dev, ib_dev.class_dev);
- return sprintf(buf, "%x.%x.%x\n", (int) (dev->fw_ver >> 32),
+ struct mthca_dev *dev =
+ container_of(device, struct mthca_dev, ib_dev.dev);
+ return sprintf(buf, "%d.%d.%d\n", (int) (dev->fw_ver >> 32),
(int) (dev->fw_ver >> 16) & 0xffff,
(int) dev->fw_ver & 0xffff);
}
-static ssize_t show_hca(struct class_device *cdev, char *buf)
+static ssize_t show_hca(struct device *device, struct device_attribute *attr,
+ char *buf)
{
- struct mthca_dev *dev = container_of(cdev, struct mthca_dev, ib_dev.class_dev);
+ struct mthca_dev *dev =
+ container_of(device, struct mthca_dev, ib_dev.dev);
switch (dev->pdev->device) {
case PCI_DEVICE_ID_MELLANOX_TAVOR:
return sprintf(buf, "MT23108\n");
}
}
-static CLASS_DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
-static CLASS_DEVICE_ATTR(fw_ver, S_IRUGO, show_fw_ver, NULL);
-static CLASS_DEVICE_ATTR(hca_type, S_IRUGO, show_hca, NULL);
+static ssize_t show_board(struct device *device, struct device_attribute *attr,
+ char *buf)
+{
+ struct mthca_dev *dev =
+ container_of(device, struct mthca_dev, ib_dev.dev);
+ return sprintf(buf, "%.*s\n", MTHCA_BOARD_ID_LEN, dev->board_id);
+}
+
+static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
+static DEVICE_ATTR(fw_ver, S_IRUGO, show_fw_ver, NULL);
+static DEVICE_ATTR(hca_type, S_IRUGO, show_hca, NULL);
+static DEVICE_ATTR(board_id, S_IRUGO, show_board, NULL);
-static struct class_device_attribute *mthca_class_attributes[] = {
- &class_device_attr_hw_rev,
- &class_device_attr_fw_ver,
- &class_device_attr_hca_type
+static struct device_attribute *mthca_dev_attributes[] = {
+ &dev_attr_hw_rev,
+ &dev_attr_fw_ver,
+ &dev_attr_hca_type,
+ &dev_attr_board_id
};
+static int mthca_init_node_data(struct mthca_dev *dev)
+{
+ struct ib_smp *in_mad = NULL;
+ struct ib_smp *out_mad = NULL;
+ int err = -ENOMEM;
+ u8 status;
+
+ in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
+ out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
+ if (!in_mad || !out_mad)
+ goto out;
+
+ init_query_mad(in_mad);
+ in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
+
+ err = mthca_MAD_IFC(dev, 1, 1,
+ 1, NULL, NULL, in_mad, out_mad,
+ &status);
+ if (err)
+ goto out;
+ if (status) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ memcpy(dev->ib_dev.node_desc, out_mad->data, 64);
+
+ in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+
+ err = mthca_MAD_IFC(dev, 1, 1,
+ 1, NULL, NULL, in_mad, out_mad,
+ &status);
+ if (err)
+ goto out;
+ if (status) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (mthca_is_memfree(dev))
+ dev->rev_id = be32_to_cpup((__be32 *) (out_mad->data + 32));
+ memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8);
+
+out:
+ kfree(in_mad);
+ kfree(out_mad);
+ return err;
+}
+
int mthca_register_device(struct mthca_dev *dev)
{
int ret;
int i;
+ ret = mthca_init_node_data(dev);
+ if (ret)
+ return ret;
+
strlcpy(dev->ib_dev.name, "mthca%d", IB_DEVICE_NAME_MAX);
dev->ib_dev.owner = THIS_MODULE;
- dev->ib_dev.node_type = IB_NODE_CA;
+ dev->ib_dev.uverbs_abi_ver = MTHCA_UVERBS_ABI_VERSION;
+ dev->ib_dev.uverbs_cmd_mask =
+ (1ull << IB_USER_VERBS_CMD_GET_CONTEXT) |
+ (1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) |
+ (1ull << IB_USER_VERBS_CMD_QUERY_PORT) |
+ (1ull << IB_USER_VERBS_CMD_ALLOC_PD) |
+ (1ull << IB_USER_VERBS_CMD_DEALLOC_PD) |
+ (1ull << IB_USER_VERBS_CMD_REG_MR) |
+ (1ull << IB_USER_VERBS_CMD_DEREG_MR) |
+ (1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
+ (1ull << IB_USER_VERBS_CMD_CREATE_CQ) |
+ (1ull << IB_USER_VERBS_CMD_RESIZE_CQ) |
+ (1ull << IB_USER_VERBS_CMD_DESTROY_CQ) |
+ (1ull << IB_USER_VERBS_CMD_CREATE_QP) |
+ (1ull << IB_USER_VERBS_CMD_QUERY_QP) |
+ (1ull << IB_USER_VERBS_CMD_MODIFY_QP) |
+ (1ull << IB_USER_VERBS_CMD_DESTROY_QP) |
+ (1ull << IB_USER_VERBS_CMD_ATTACH_MCAST) |
+ (1ull << IB_USER_VERBS_CMD_DETACH_MCAST);
+ dev->ib_dev.node_type = RDMA_NODE_IB_CA;
dev->ib_dev.phys_port_cnt = dev->limits.num_ports;
+ dev->ib_dev.num_comp_vectors = 1;
dev->ib_dev.dma_device = &dev->pdev->dev;
- dev->ib_dev.class_dev.dev = &dev->pdev->dev;
dev->ib_dev.query_device = mthca_query_device;
dev->ib_dev.query_port = mthca_query_port;
+ dev->ib_dev.modify_device = mthca_modify_device;
dev->ib_dev.modify_port = mthca_modify_port;
dev->ib_dev.query_pkey = mthca_query_pkey;
dev->ib_dev.query_gid = mthca_query_gid;
dev->ib_dev.alloc_pd = mthca_alloc_pd;
dev->ib_dev.dealloc_pd = mthca_dealloc_pd;
dev->ib_dev.create_ah = mthca_ah_create;
+ dev->ib_dev.query_ah = mthca_ah_query;
dev->ib_dev.destroy_ah = mthca_ah_destroy;
+
+ if (dev->mthca_flags & MTHCA_FLAG_SRQ) {
+ dev->ib_dev.create_srq = mthca_create_srq;
+ dev->ib_dev.modify_srq = mthca_modify_srq;
+ dev->ib_dev.query_srq = mthca_query_srq;
+ dev->ib_dev.destroy_srq = mthca_destroy_srq;
+ dev->ib_dev.uverbs_cmd_mask |=
+ (1ull << IB_USER_VERBS_CMD_CREATE_SRQ) |
+ (1ull << IB_USER_VERBS_CMD_MODIFY_SRQ) |
+ (1ull << IB_USER_VERBS_CMD_QUERY_SRQ) |
+ (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ);
+
+ if (mthca_is_memfree(dev))
+ dev->ib_dev.post_srq_recv = mthca_arbel_post_srq_recv;
+ else
+ dev->ib_dev.post_srq_recv = mthca_tavor_post_srq_recv;
+ }
+
dev->ib_dev.create_qp = mthca_create_qp;
dev->ib_dev.modify_qp = mthca_modify_qp;
+ dev->ib_dev.query_qp = mthca_query_qp;
dev->ib_dev.destroy_qp = mthca_destroy_qp;
dev->ib_dev.create_cq = mthca_create_cq;
+ dev->ib_dev.resize_cq = mthca_resize_cq;
dev->ib_dev.destroy_cq = mthca_destroy_cq;
dev->ib_dev.poll_cq = mthca_poll_cq;
dev->ib_dev.get_dma_mr = mthca_get_dma_mr;
dev->ib_dev.post_recv = mthca_tavor_post_receive;
}
- init_MUTEX(&dev->cap_mask_mutex);
+ mutex_init(&dev->cap_mask_mutex);
ret = ib_register_device(&dev->ib_dev);
if (ret)
return ret;
- for (i = 0; i < ARRAY_SIZE(mthca_class_attributes); ++i) {
- ret = class_device_create_file(&dev->ib_dev.class_dev,
- mthca_class_attributes[i]);
+ for (i = 0; i < ARRAY_SIZE(mthca_dev_attributes); ++i) {
+ ret = device_create_file(&dev->ib_dev.dev,
+ mthca_dev_attributes[i]);
if (ret) {
ib_unregister_device(&dev->ib_dev);
return ret;
}
}
+ mthca_start_catas_poll(dev);
+
return 0;
}
void mthca_unregister_device(struct mthca_dev *dev)
{
+ mthca_stop_catas_poll(dev);
ib_unregister_device(&dev->ib_dev);
}