void *
cfs_cpt_vzalloc(struct cfs_cpt_table *cptab, int cpt, size_t nr_bytes)
{
/* vzalloc_node() sets __GFP_FS by default but no current Kernel
* exported entry-point allows for both a NUMA node specification
* and a custom allocation flags mask. This may be an issue since
* __GFP_FS usage can cause some deadlock situations in our code,
* like when memory reclaim started, within the same context of a
* thread doing FS operations, that can also attempt conflicting FS
* operations, ...
*/
return vzalloc_node(nr_bytes, cfs_cpt_spread_node(cptab, cpt));
}
static void *__meminit alloc_page_ext(size_t size, int nid)
{
gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
void *addr = NULL;
addr = alloc_pages_exact_nid(nid, size, flags);
if (addr) {
kmemleak_alloc(addr, size, 1, flags);
return addr;
}
addr = vzalloc_node(size, nid);
return addr;
}
static void *__meminit alloc_page_cgroup(size_t size, int nid)
{
gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
void *addr = NULL;
addr = alloc_pages_exact_nid(nid, size, flags);
if (addr) {
kmemleak_alloc(addr, size, 1, flags);
return addr;
}
if (node_state(nid, N_HIGH_MEMORY))
addr = vzalloc_node(size, nid);
else
addr = vzalloc(size);
return addr;
}
static int netvsc_init_buf(struct hv_device *device)
{
int ret = 0;
unsigned long t;
struct netvsc_device *net_device;
struct nvsp_message *init_packet;
struct net_device *ndev;
int node;
net_device = get_outbound_net_device(device);
if (!net_device)
return -ENODEV;
ndev = net_device->ndev;
node = cpu_to_node(device->channel->target_cpu);
net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node);
if (!net_device->recv_buf)
net_device->recv_buf = vzalloc(net_device->recv_buf_size);
if (!net_device->recv_buf) {
netdev_err(ndev, "unable to allocate receive "
"buffer of size %d\n", net_device->recv_buf_size);
ret = -ENOMEM;
goto cleanup;
}
/*
* Establish the gpadl handle for this buffer on this
* channel. Note: This call uses the vmbus connection rather
* than the channel to establish the gpadl handle.
*/
ret = vmbus_establish_gpadl(device->channel, net_device->recv_buf,
net_device->recv_buf_size,
&net_device->recv_buf_gpadl_handle);
if (ret != 0) {
netdev_err(ndev,
"unable to establish receive buffer's gpadl\n");
goto cleanup;
}
/* Notify the NetVsp of the gpadl handle */
init_packet = &net_device->channel_init_pkt;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_RECV_BUF;
init_packet->msg.v1_msg.send_recv_buf.
gpadl_handle = net_device->recv_buf_gpadl_handle;
init_packet->msg.v1_msg.
send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;
/* Send the gpadl notification request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret != 0) {
netdev_err(ndev,
"unable to send receive buffer's gpadl to netvsp\n");
goto cleanup;
}
t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
BUG_ON(t == 0);
/* Check the response */
if (init_packet->msg.v1_msg.
send_recv_buf_complete.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "Unable to complete receive buffer "
"initialization with NetVsp - status %d\n",
init_packet->msg.v1_msg.
send_recv_buf_complete.status);
ret = -EINVAL;
goto cleanup;
}
/* Parse the response */
net_device->recv_section_cnt = init_packet->msg.
v1_msg.send_recv_buf_complete.num_sections;
net_device->recv_section = kmemdup(
init_packet->msg.v1_msg.send_recv_buf_complete.sections,
net_device->recv_section_cnt *
sizeof(struct nvsp_1_receive_buffer_section),
GFP_KERNEL);
if (net_device->recv_section == NULL) {
ret = -EINVAL;
goto cleanup;
}
/*
* For 1st release, there should only be 1 section that represents the
* entire receive buffer
*/
if (net_device->recv_section_cnt != 1 ||
net_device->recv_section->offset != 0) {
ret = -EINVAL;
goto cleanup;
}
/* Now setup the send buffer.
*/
net_device->send_buf = vzalloc_node(net_device->send_buf_size, node);
if (!net_device->send_buf)
net_device->send_buf = vzalloc(net_device->send_buf_size);
if (!net_device->send_buf) {
netdev_err(ndev, "unable to allocate send "
"buffer of size %d\n", net_device->send_buf_size);
ret = -ENOMEM;
goto cleanup;
}
/* Establish the gpadl handle for this buffer on this
* channel. Note: This call uses the vmbus connection rather
* than the channel to establish the gpadl handle.
*/
ret = vmbus_establish_gpadl(device->channel, net_device->send_buf,
net_device->send_buf_size,
&net_device->send_buf_gpadl_handle);
if (ret != 0) {
netdev_err(ndev,
"unable to establish send buffer's gpadl\n");
goto cleanup;
}
/* Notify the NetVsp of the gpadl handle */
init_packet = &net_device->channel_init_pkt;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
init_packet->msg.v1_msg.send_send_buf.gpadl_handle =
net_device->send_buf_gpadl_handle;
init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID;
/* Send the gpadl notification request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret != 0) {
netdev_err(ndev,
"unable to send send buffer's gpadl to netvsp\n");
goto cleanup;
}
t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
BUG_ON(t == 0);
/* Check the response */
if (init_packet->msg.v1_msg.
send_send_buf_complete.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "Unable to complete send buffer "
"initialization with NetVsp - status %d\n",
init_packet->msg.v1_msg.
send_send_buf_complete.status);
ret = -EINVAL;
goto cleanup;
}
/* Parse the response */
net_device->send_section_size = init_packet->msg.
v1_msg.send_send_buf_complete.section_size;
/* Section count is simply the size divided by the section size.
*/
net_device->send_section_cnt =
net_device->send_buf_size/net_device->send_section_size;
dev_info(&device->device, "Send section size: %d, Section count:%d\n",
net_device->send_section_size, net_device->send_section_cnt);
/* Setup state for managing the send buffer. */
net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
BITS_PER_LONG);
net_device->send_section_map =
kzalloc(net_device->map_words * sizeof(ulong), GFP_KERNEL);
if (net_device->send_section_map == NULL) {
ret = -ENOMEM;
goto cleanup;
}
goto exit;
cleanup:
netvsc_destroy_buf(net_device);
exit:
return ret;
}
/*
* This needs to be very careful to not leave IS_ERR pointers around for
* cleanup to trip over.
*/
static int rds_ib_setup_qp(struct rds_connection *conn)
{
struct rds_ib_connection *ic = conn->c_transport_data;
struct ib_device *dev = ic->i_cm_id->device;
struct ib_qp_init_attr attr;
struct ib_cq_init_attr cq_attr = {};
struct rds_ib_device *rds_ibdev;
int ret, fr_queue_space;
/*
* It's normal to see a null device if an incoming connection races
* with device removal, so we don't print a warning.
*/
rds_ibdev = rds_ib_get_client_data(dev);
if (!rds_ibdev)
return -EOPNOTSUPP;
/* The fr_queue_space is currently set to 512, to add extra space on
* completion queue and send queue. This extra space is used for FRMR
* registration and invalidation work requests
*/
fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
/* add the conn now so that connection establishment has the dev */
rds_ib_add_conn(rds_ibdev, conn);
if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1)
rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1);
if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1)
rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1);
/* Protection domain and memory range */
ic->i_pd = rds_ibdev->pd;
cq_attr.cqe = ic->i_send_ring.w_nr + fr_queue_space + 1;
ic->i_send_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_send,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_send_cq)) {
ret = PTR_ERR(ic->i_send_cq);
ic->i_send_cq = NULL;
rdsdebug("ib_create_cq send failed: %d\n", ret);
goto out;
}
cq_attr.cqe = ic->i_recv_ring.w_nr;
ic->i_recv_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_recv,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_recv_cq)) {
ret = PTR_ERR(ic->i_recv_cq);
ic->i_recv_cq = NULL;
rdsdebug("ib_create_cq recv failed: %d\n", ret);
goto out;
}
ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
if (ret) {
rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
goto out;
}
ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
if (ret) {
rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
goto out;
}
/* XXX negotiate max send/recv with remote? */
memset(&attr, 0, sizeof(attr));
attr.event_handler = rds_ib_qp_event_handler;
attr.qp_context = conn;
/* + 1 to allow for the single ack message */
attr.cap.max_send_wr = ic->i_send_ring.w_nr + fr_queue_space + 1;
attr.cap.max_recv_wr = ic->i_recv_ring.w_nr + 1;
attr.cap.max_send_sge = rds_ibdev->max_sge;
attr.cap.max_recv_sge = RDS_IB_RECV_SGE;
attr.sq_sig_type = IB_SIGNAL_REQ_WR;
attr.qp_type = IB_QPT_RC;
attr.send_cq = ic->i_send_cq;
attr.recv_cq = ic->i_recv_cq;
atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
/*
* XXX this can fail if max_*_wr is too large? Are we supposed
* to back off until we get a value that the hardware can support?
*/
ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
if (ret) {
rdsdebug("rdma_create_qp failed: %d\n", ret);
goto out;
}
ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
ic->i_send_ring.w_nr *
sizeof(struct rds_header),
&ic->i_send_hdrs_dma, GFP_KERNEL);
if (!ic->i_send_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent send failed\n");
goto out;
}
ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
ic->i_recv_ring.w_nr *
sizeof(struct rds_header),
&ic->i_recv_hdrs_dma, GFP_KERNEL);
if (!ic->i_recv_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent recv failed\n");
goto out;
}
ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
&ic->i_ack_dma, GFP_KERNEL);
if (!ic->i_ack) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent ack failed\n");
goto out;
}
ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
ibdev_to_node(dev));
if (!ic->i_sends) {
ret = -ENOMEM;
rdsdebug("send allocation failed\n");
goto out;
}
ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
ibdev_to_node(dev));
if (!ic->i_recvs) {
ret = -ENOMEM;
rdsdebug("recv allocation failed\n");
goto out;
}
rds_ib_recv_init_ack(ic);
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
out:
rds_ib_dev_put(rds_ibdev);
return ret;
}
static int rds_ib_setup_qp(struct rds_connection *conn)
{
struct rds_ib_connection *ic = conn->c_transport_data;
struct ib_device *dev = ic->i_cm_id->device;
struct ib_qp_init_attr attr;
struct rds_ib_device *rds_ibdev;
int ret;
rds_ibdev = rds_ib_get_client_data(dev);
if (!rds_ibdev)
return -EOPNOTSUPP;
rds_ib_add_conn(rds_ibdev, conn);
if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1)
rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1);
if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1)
rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1);
ic->i_pd = rds_ibdev->pd;
ic->i_mr = rds_ibdev->mr;
ic->i_send_cq = ib_create_cq(dev, rds_ib_send_cq_comp_handler,
rds_ib_cq_event_handler, conn,
ic->i_send_ring.w_nr + 1, 0);
if (IS_ERR(ic->i_send_cq)) {
ret = PTR_ERR(ic->i_send_cq);
ic->i_send_cq = NULL;
rdsdebug("ib_create_cq send failed: %d\n", ret);
goto out;
}
ic->i_recv_cq = ib_create_cq(dev, rds_ib_recv_cq_comp_handler,
rds_ib_cq_event_handler, conn,
ic->i_recv_ring.w_nr, 0);
if (IS_ERR(ic->i_recv_cq)) {
ret = PTR_ERR(ic->i_recv_cq);
ic->i_recv_cq = NULL;
rdsdebug("ib_create_cq recv failed: %d\n", ret);
goto out;
}
ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
if (ret) {
rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
goto out;
}
ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
if (ret) {
rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
goto out;
}
memset(&attr, 0, sizeof(attr));
attr.event_handler = rds_ib_qp_event_handler;
attr.qp_context = conn;
attr.cap.max_send_wr = ic->i_send_ring.w_nr + 1;
attr.cap.max_recv_wr = ic->i_recv_ring.w_nr + 1;
attr.cap.max_send_sge = rds_ibdev->max_sge;
attr.cap.max_recv_sge = RDS_IB_RECV_SGE;
attr.sq_sig_type = IB_SIGNAL_REQ_WR;
attr.qp_type = IB_QPT_RC;
attr.send_cq = ic->i_send_cq;
attr.recv_cq = ic->i_recv_cq;
ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
if (ret) {
rdsdebug("rdma_create_qp failed: %d\n", ret);
goto out;
}
ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
ic->i_send_ring.w_nr *
sizeof(struct rds_header),
&ic->i_send_hdrs_dma, GFP_KERNEL);
if (!ic->i_send_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent send failed\n");
goto out;
}
ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
ic->i_recv_ring.w_nr *
sizeof(struct rds_header),
&ic->i_recv_hdrs_dma, GFP_KERNEL);
if (!ic->i_recv_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent recv failed\n");
goto out;
}
ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
&ic->i_ack_dma, GFP_KERNEL);
if (!ic->i_ack) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent ack failed\n");
goto out;
}
ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
ibdev_to_node(dev));
if (!ic->i_sends) {
ret = -ENOMEM;
rdsdebug("send allocation failed\n");
goto out;
}
ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
ibdev_to_node(dev));
if (!ic->i_recvs) {
ret = -ENOMEM;
rdsdebug("recv allocation failed\n");
goto out;
}
rds_ib_recv_init_ack(ic);
rdsdebug("conn %p pd %p mr %p cq %p %p\n", conn, ic->i_pd, ic->i_mr,
ic->i_send_cq, ic->i_recv_cq);
out:
rds_ib_dev_put(rds_ibdev);
return ret;
}
/**
* rvt_create_srq - create a shared receive queue
* @ibpd: the protection domain of the SRQ to create
* @srq_init_attr: the attributes of the SRQ
* @udata: data from libibverbs when creating a user SRQ
*
* Return: Allocated srq object
*/
struct ib_srq *rvt_create_srq(struct ib_pd *ibpd,
struct ib_srq_init_attr *srq_init_attr,
struct ib_udata *udata)
{
struct rvt_dev_info *dev = ib_to_rvt(ibpd->device);
struct rvt_ucontext *ucontext = rdma_udata_to_drv_context(
udata, struct rvt_ucontext, ibucontext);
struct rvt_srq *srq;
u32 sz;
struct ib_srq *ret;
if (srq_init_attr->srq_type != IB_SRQT_BASIC)
return ERR_PTR(-EOPNOTSUPP);
if (srq_init_attr->attr.max_sge == 0 ||
srq_init_attr->attr.max_sge > dev->dparms.props.max_srq_sge ||
srq_init_attr->attr.max_wr == 0 ||
srq_init_attr->attr.max_wr > dev->dparms.props.max_srq_wr)
return ERR_PTR(-EINVAL);
srq = kzalloc_node(sizeof(*srq), GFP_KERNEL, dev->dparms.node);
if (!srq)
return ERR_PTR(-ENOMEM);
/*
* Need to use vmalloc() if we want to support large #s of entries.
*/
srq->rq.size = srq_init_attr->attr.max_wr + 1;
srq->rq.max_sge = srq_init_attr->attr.max_sge;
sz = sizeof(struct ib_sge) * srq->rq.max_sge +
sizeof(struct rvt_rwqe);
srq->rq.wq = udata ?
vmalloc_user(sizeof(struct rvt_rwq) + srq->rq.size * sz) :
vzalloc_node(sizeof(struct rvt_rwq) + srq->rq.size * sz,
dev->dparms.node);
if (!srq->rq.wq) {
ret = ERR_PTR(-ENOMEM);
goto bail_srq;
}
/*
* Return the address of the RWQ as the offset to mmap.
* See rvt_mmap() for details.
*/
if (udata && udata->outlen >= sizeof(__u64)) {
int err;
u32 s = sizeof(struct rvt_rwq) + srq->rq.size * sz;
srq->ip =
rvt_create_mmap_info(dev, s, &ucontext->ibucontext,
srq->rq.wq);
if (!srq->ip) {
ret = ERR_PTR(-ENOMEM);
goto bail_wq;
}
err = ib_copy_to_udata(udata, &srq->ip->offset,
sizeof(srq->ip->offset));
if (err) {
ret = ERR_PTR(err);
goto bail_ip;
}
}
/*
* ib_create_srq() will initialize srq->ibsrq.
*/
spin_lock_init(&srq->rq.lock);
srq->limit = srq_init_attr->attr.srq_limit;
spin_lock(&dev->n_srqs_lock);
if (dev->n_srqs_allocated == dev->dparms.props.max_srq) {
spin_unlock(&dev->n_srqs_lock);
ret = ERR_PTR(-ENOMEM);
goto bail_ip;
}
dev->n_srqs_allocated++;
spin_unlock(&dev->n_srqs_lock);
if (srq->ip) {
spin_lock_irq(&dev->pending_lock);
list_add(&srq->ip->pending_mmaps, &dev->pending_mmaps);
spin_unlock_irq(&dev->pending_lock);
}
return &srq->ibsrq;
bail_ip:
kfree(srq->ip);
bail_wq:
vfree(srq->rq.wq);
bail_srq:
kfree(srq);
return ret;
}
/**
* rvt_modify_srq - modify a shared receive queue
* @ibsrq: the SRQ to modify
* @attr: the new attributes of the SRQ
* @attr_mask: indicates which attributes to modify
* @udata: user data for libibverbs.so
*
* Return: 0 on success
*/
int rvt_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
enum ib_srq_attr_mask attr_mask,
struct ib_udata *udata)
{
struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
struct rvt_dev_info *dev = ib_to_rvt(ibsrq->device);
struct rvt_rwq *wq;
int ret = 0;
if (attr_mask & IB_SRQ_MAX_WR) {
struct rvt_rwq *owq;
struct rvt_rwqe *p;
u32 sz, size, n, head, tail;
/* Check that the requested sizes are below the limits. */
if ((attr->max_wr > dev->dparms.props.max_srq_wr) ||
((attr_mask & IB_SRQ_LIMIT) ?
attr->srq_limit : srq->limit) > attr->max_wr)
return -EINVAL;
sz = sizeof(struct rvt_rwqe) +
srq->rq.max_sge * sizeof(struct ib_sge);
size = attr->max_wr + 1;
wq = udata ?
vmalloc_user(sizeof(struct rvt_rwq) + size * sz) :
vzalloc_node(sizeof(struct rvt_rwq) + size * sz,
dev->dparms.node);
if (!wq)
return -ENOMEM;
/* Check that we can write the offset to mmap. */
if (udata && udata->inlen >= sizeof(__u64)) {
__u64 offset_addr;
__u64 offset = 0;
ret = ib_copy_from_udata(&offset_addr, udata,
sizeof(offset_addr));
if (ret)
goto bail_free;
udata->outbuf = (void __user *)
(unsigned long)offset_addr;
ret = ib_copy_to_udata(udata, &offset,
sizeof(offset));
if (ret)
goto bail_free;
}
spin_lock_irq(&srq->rq.lock);
/*
* validate head and tail pointer values and compute
* the number of remaining WQEs.
*/
owq = srq->rq.wq;
head = owq->head;
tail = owq->tail;
if (head >= srq->rq.size || tail >= srq->rq.size) {
ret = -EINVAL;
goto bail_unlock;
}
n = head;
if (n < tail)
n += srq->rq.size - tail;
else
n -= tail;
if (size <= n) {
ret = -EINVAL;
goto bail_unlock;
}
n = 0;
p = wq->wq;
while (tail != head) {
struct rvt_rwqe *wqe;
int i;
wqe = rvt_get_rwqe_ptr(&srq->rq, tail);
p->wr_id = wqe->wr_id;
p->num_sge = wqe->num_sge;
for (i = 0; i < wqe->num_sge; i++)
p->sg_list[i] = wqe->sg_list[i];
n++;
p = (struct rvt_rwqe *)((char *)p + sz);
if (++tail >= srq->rq.size)
tail = 0;
}
srq->rq.wq = wq;
srq->rq.size = size;
wq->head = n;
wq->tail = 0;
if (attr_mask & IB_SRQ_LIMIT)
srq->limit = attr->srq_limit;
spin_unlock_irq(&srq->rq.lock);
vfree(owq);
if (srq->ip) {
struct rvt_mmap_info *ip = srq->ip;
struct rvt_dev_info *dev = ib_to_rvt(srq->ibsrq.device);
u32 s = sizeof(struct rvt_rwq) + size * sz;
rvt_update_mmap_info(dev, ip, s, wq);
/*
* Return the offset to mmap.
* See rvt_mmap() for details.
*/
if (udata && udata->inlen >= sizeof(__u64)) {
ret = ib_copy_to_udata(udata, &ip->offset,
sizeof(ip->offset));
if (ret)
return ret;
}
/*
* Put user mapping info onto the pending list
* unless it already is on the list.
*/
spin_lock_irq(&dev->pending_lock);
if (list_empty(&ip->pending_mmaps))
list_add(&ip->pending_mmaps,
&dev->pending_mmaps);
spin_unlock_irq(&dev->pending_lock);
}
} else if (attr_mask & IB_SRQ_LIMIT) {
spin_lock_irq(&srq->rq.lock);
if (attr->srq_limit >= srq->rq.size)
ret = -EINVAL;
else
srq->limit = attr->srq_limit;
spin_unlock_irq(&srq->rq.lock);
}
return ret;
bail_unlock:
spin_unlock_irq(&srq->rq.lock);
bail_free:
vfree(wq);
return ret;
}
