uverbs_cmd.c

来自「LINUX 2.6.17.4的源码」· C语言 代码 · 共 2,020 行 · 第 1/4 页

	if (copy_from_user(&cmd, buf, sizeof cmd))
		return -EFAULT;

	attr      = kmalloc(sizeof *attr, GFP_KERNEL);
	init_attr = kmalloc(sizeof *init_attr, GFP_KERNEL);
	if (!attr || !init_attr) {
		ret = -ENOMEM;
		goto out;
	}

	mutex_lock(&ib_uverbs_idr_mutex);

	qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle);
	if (qp && qp->uobject->context == file->ucontext)
		ret = ib_query_qp(qp, attr, cmd.attr_mask, init_attr);
	else
		ret = -EINVAL;

	mutex_unlock(&ib_uverbs_idr_mutex);

	if (ret)
		goto out;

	memset(&resp, 0, sizeof resp);

	resp.qp_state               = attr->qp_state;
	resp.cur_qp_state           = attr->cur_qp_state;
	resp.path_mtu               = attr->path_mtu;
	resp.path_mig_state         = attr->path_mig_state;
	resp.qkey                   = attr->qkey;
	resp.rq_psn                 = attr->rq_psn;
	resp.sq_psn                 = attr->sq_psn;
	resp.dest_qp_num            = attr->dest_qp_num;
	resp.qp_access_flags        = attr->qp_access_flags;
	resp.pkey_index             = attr->pkey_index;
	resp.alt_pkey_index         = attr->alt_pkey_index;
	resp.en_sqd_async_notify    = attr->en_sqd_async_notify;
	resp.max_rd_atomic          = attr->max_rd_atomic;
	resp.max_dest_rd_atomic     = attr->max_dest_rd_atomic;
	resp.min_rnr_timer          = attr->min_rnr_timer;
	resp.port_num               = attr->port_num;
	resp.timeout                = attr->timeout;
	resp.retry_cnt              = attr->retry_cnt;
	resp.rnr_retry              = attr->rnr_retry;
	resp.alt_port_num           = attr->alt_port_num;
	resp.alt_timeout            = attr->alt_timeout;

	memcpy(resp.dest.dgid, attr->ah_attr.grh.dgid.raw, 16);
	resp.dest.flow_label        = attr->ah_attr.grh.flow_label;
	resp.dest.sgid_index        = attr->ah_attr.grh.sgid_index;
	resp.dest.hop_limit         = attr->ah_attr.grh.hop_limit;
	resp.dest.traffic_class     = attr->ah_attr.grh.traffic_class;
	resp.dest.dlid              = attr->ah_attr.dlid;
	resp.dest.sl                = attr->ah_attr.sl;
	resp.dest.src_path_bits     = attr->ah_attr.src_path_bits;
	resp.dest.static_rate       = attr->ah_attr.static_rate;
	resp.dest.is_global         = !!(attr->ah_attr.ah_flags & IB_AH_GRH);
	resp.dest.port_num          = attr->ah_attr.port_num;

	memcpy(resp.alt_dest.dgid, attr->alt_ah_attr.grh.dgid.raw, 16);
	resp.alt_dest.flow_label    = attr->alt_ah_attr.grh.flow_label;
	resp.alt_dest.sgid_index    = attr->alt_ah_attr.grh.sgid_index;
	resp.alt_dest.hop_limit     = attr->alt_ah_attr.grh.hop_limit;
	resp.alt_dest.traffic_class = attr->alt_ah_attr.grh.traffic_class;
	resp.alt_dest.dlid          = attr->alt_ah_attr.dlid;
	resp.alt_dest.sl            = attr->alt_ah_attr.sl;
	resp.alt_dest.src_path_bits = attr->alt_ah_attr.src_path_bits;
	resp.alt_dest.static_rate   = attr->alt_ah_attr.static_rate;
	resp.alt_dest.is_global     = !!(attr->alt_ah_attr.ah_flags & IB_AH_GRH);
	resp.alt_dest.port_num      = attr->alt_ah_attr.port_num;

	resp.max_send_wr            = init_attr->cap.max_send_wr;
	resp.max_recv_wr            = init_attr->cap.max_recv_wr;
	resp.max_send_sge           = init_attr->cap.max_send_sge;
	resp.max_recv_sge           = init_attr->cap.max_recv_sge;
	resp.max_inline_data        = init_attr->cap.max_inline_data;
	resp.sq_sig_all             = init_attr->sq_sig_type == IB_SIGNAL_ALL_WR;

	if (copy_to_user((void __user *) (unsigned long) cmd.response,
			 &resp, sizeof resp))
		ret = -EFAULT;

out:
	kfree(attr);
	kfree(init_attr);

	return ret ? ret : in_len;
}

ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
			    const char __user *buf, int in_len,
			    int out_len)
{
	struct ib_uverbs_modify_qp cmd;
	struct ib_qp              *qp;
	struct ib_qp_attr         *attr;
	int                        ret;

	if (copy_from_user(&cmd, buf, sizeof cmd))
		return -EFAULT;

	attr = kmalloc(sizeof *attr, GFP_KERNEL);
	if (!attr)
		return -ENOMEM;

	mutex_lock(&ib_uverbs_idr_mutex);

	qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle);
	if (!qp || qp->uobject->context != file->ucontext) {
		ret = -EINVAL;
		goto out;
	}

	attr->qp_state 		  = cmd.qp_state;
	attr->cur_qp_state 	  = cmd.cur_qp_state;
	attr->path_mtu 		  = cmd.path_mtu;
	attr->path_mig_state 	  = cmd.path_mig_state;
	attr->qkey 		  = cmd.qkey;
	attr->rq_psn 		  = cmd.rq_psn;
	attr->sq_psn 		  = cmd.sq_psn;
	attr->dest_qp_num 	  = cmd.dest_qp_num;
	attr->qp_access_flags 	  = cmd.qp_access_flags;
	attr->pkey_index 	  = cmd.pkey_index;
	attr->alt_pkey_index 	  = cmd.alt_pkey_index;
	attr->en_sqd_async_notify = cmd.en_sqd_async_notify;
	attr->max_rd_atomic 	  = cmd.max_rd_atomic;
	attr->max_dest_rd_atomic  = cmd.max_dest_rd_atomic;
	attr->min_rnr_timer 	  = cmd.min_rnr_timer;
	attr->port_num 		  = cmd.port_num;
	attr->timeout 		  = cmd.timeout;
	attr->retry_cnt 	  = cmd.retry_cnt;
	attr->rnr_retry 	  = cmd.rnr_retry;
	attr->alt_port_num 	  = cmd.alt_port_num;
	attr->alt_timeout 	  = cmd.alt_timeout;

	memcpy(attr->ah_attr.grh.dgid.raw, cmd.dest.dgid, 16);
	attr->ah_attr.grh.flow_label        = cmd.dest.flow_label;
	attr->ah_attr.grh.sgid_index        = cmd.dest.sgid_index;
	attr->ah_attr.grh.hop_limit         = cmd.dest.hop_limit;
	attr->ah_attr.grh.traffic_class     = cmd.dest.traffic_class;
	attr->ah_attr.dlid 	    	    = cmd.dest.dlid;
	attr->ah_attr.sl   	    	    = cmd.dest.sl;
	attr->ah_attr.src_path_bits 	    = cmd.dest.src_path_bits;
	attr->ah_attr.static_rate   	    = cmd.dest.static_rate;
	attr->ah_attr.ah_flags 	    	    = cmd.dest.is_global ? IB_AH_GRH : 0;
	attr->ah_attr.port_num 	    	    = cmd.dest.port_num;

	memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd.alt_dest.dgid, 16);
	attr->alt_ah_attr.grh.flow_label    = cmd.alt_dest.flow_label;
	attr->alt_ah_attr.grh.sgid_index    = cmd.alt_dest.sgid_index;
	attr->alt_ah_attr.grh.hop_limit     = cmd.alt_dest.hop_limit;
	attr->alt_ah_attr.grh.traffic_class = cmd.alt_dest.traffic_class;
	attr->alt_ah_attr.dlid 	    	    = cmd.alt_dest.dlid;
	attr->alt_ah_attr.sl   	    	    = cmd.alt_dest.sl;
	attr->alt_ah_attr.src_path_bits     = cmd.alt_dest.src_path_bits;
	attr->alt_ah_attr.static_rate       = cmd.alt_dest.static_rate;
	attr->alt_ah_attr.ah_flags 	    = cmd.alt_dest.is_global ? IB_AH_GRH : 0;
	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;

	ret = ib_modify_qp(qp, attr, cmd.attr_mask);
	if (ret)
		goto out;

	ret = in_len;

out:
	mutex_unlock(&ib_uverbs_idr_mutex);
	kfree(attr);

	return ret;
}

ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
			     const char __user *buf, int in_len,
			     int out_len)
{
	struct ib_uverbs_destroy_qp      cmd;
	struct ib_uverbs_destroy_qp_resp resp;
	struct ib_qp               	*qp;
	struct ib_uqp_object        	*uobj;
	int                        	 ret = -EINVAL;

	if (copy_from_user(&cmd, buf, sizeof cmd))
		return -EFAULT;

	memset(&resp, 0, sizeof resp);

	mutex_lock(&ib_uverbs_idr_mutex);

	qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle);
	if (!qp || qp->uobject->context != file->ucontext)
		goto out;

	uobj = container_of(qp->uobject, struct ib_uqp_object, uevent.uobject);

	if (!list_empty(&uobj->mcast_list)) {
		ret = -EBUSY;
		goto out;
	}

	ret = ib_destroy_qp(qp);
	if (ret)
		goto out;

	idr_remove(&ib_uverbs_qp_idr, cmd.qp_handle);

	mutex_lock(&file->mutex);
	list_del(&uobj->uevent.uobject.list);
	mutex_unlock(&file->mutex);

	ib_uverbs_release_uevent(file, &uobj->uevent);

	resp.events_reported = uobj->uevent.events_reported;

	kfree(uobj);

	if (copy_to_user((void __user *) (unsigned long) cmd.response,
			 &resp, sizeof resp))
		ret = -EFAULT;

out:
	mutex_unlock(&ib_uverbs_idr_mutex);

	return ret ? ret : in_len;
}

ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
			    const char __user *buf, int in_len,
			    int out_len)
{
	struct ib_uverbs_post_send      cmd;
	struct ib_uverbs_post_send_resp resp;
	struct ib_uverbs_send_wr       *user_wr;
	struct ib_send_wr              *wr = NULL, *last, *next, *bad_wr;
	struct ib_qp                   *qp;
	int                             i, sg_ind;
	ssize_t                         ret = -EINVAL;

	if (copy_from_user(&cmd, buf, sizeof cmd))
		return -EFAULT;

	if (in_len < sizeof cmd + cmd.wqe_size * cmd.wr_count +
	    cmd.sge_count * sizeof (struct ib_uverbs_sge))
		return -EINVAL;

	if (cmd.wqe_size < sizeof (struct ib_uverbs_send_wr))
		return -EINVAL;

	user_wr = kmalloc(cmd.wqe_size, GFP_KERNEL);
	if (!user_wr)
		return -ENOMEM;

	mutex_lock(&ib_uverbs_idr_mutex);

	qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle);
	if (!qp || qp->uobject->context != file->ucontext)
		goto out;

	sg_ind = 0;
	last = NULL;
	for (i = 0; i < cmd.wr_count; ++i) {
		if (copy_from_user(user_wr,
				   buf + sizeof cmd + i * cmd.wqe_size,
				   cmd.wqe_size)) {
			ret = -EFAULT;
			goto out;
		}

		if (user_wr->num_sge + sg_ind > cmd.sge_count) {
			ret = -EINVAL;
			goto out;
		}

		next = kmalloc(ALIGN(sizeof *next, sizeof (struct ib_sge)) +
			       user_wr->num_sge * sizeof (struct ib_sge),
			       GFP_KERNEL);
		if (!next) {
			ret = -ENOMEM;
			goto out;
		}

		if (!last)
			wr = next;
		else
			last->next = next;
		last = next;

		next->next       = NULL;
		next->wr_id      = user_wr->wr_id;
		next->num_sge    = user_wr->num_sge;
		next->opcode     = user_wr->opcode;
		next->send_flags = user_wr->send_flags;
		next->imm_data   = (__be32 __force) user_wr->imm_data;

		if (qp->qp_type == IB_QPT_UD) {
			next->wr.ud.ah = idr_find(&ib_uverbs_ah_idr,
						  user_wr->wr.ud.ah);
			if (!next->wr.ud.ah) {
				ret = -EINVAL;
				goto out;
			}
			next->wr.ud.remote_qpn  = user_wr->wr.ud.remote_qpn;
			next->wr.ud.remote_qkey = user_wr->wr.ud.remote_qkey;
		} else {
			switch (next->opcode) {
			case IB_WR_RDMA_WRITE:
			case IB_WR_RDMA_WRITE_WITH_IMM:
			case IB_WR_RDMA_READ:
				next->wr.rdma.remote_addr =
					user_wr->wr.rdma.remote_addr;
				next->wr.rdma.rkey        =
					user_wr->wr.rdma.rkey;
				break;
			case IB_WR_ATOMIC_CMP_AND_SWP:
			case IB_WR_ATOMIC_FETCH_AND_ADD:
				next->wr.atomic.remote_addr =
					user_wr->wr.atomic.remote_addr;
				next->wr.atomic.compare_add =
					user_wr->wr.atomic.compare_add;
				next->wr.atomic.swap = user_wr->wr.atomic.swap;
				next->wr.atomic.rkey = user_wr->wr.atomic.rkey;
				break;
			default:
				break;
			}
		}

		if (next->num_sge) {
			next->sg_list = (void *) next +
				ALIGN(sizeof *next, sizeof (struct ib_sge));
			if (copy_from_user(next->sg_list,
					   buf + sizeof cmd +
					   cmd.wr_count * cmd.wqe_size +
					   sg_ind * sizeof (struct ib_sge),
					   next->num_sge * sizeof (struct ib_sge))) {
				ret = -EFAULT;
				goto out;
			}
			sg_ind += next->num_sge;
		} else
			next->sg_list = NULL;
	}

	resp.bad_wr = 0;
	ret = qp->device->post_send(qp, wr, &bad_wr);
	if (ret)
		for (next = wr; next; next = next->next) {
			++resp.bad_wr;
			if (next == bad_wr)
				break;
		}

	if (copy_to_user((void __user *) (unsigned long) cmd.response,
			 &resp, sizeof resp))
		ret = -EFAULT;

out:
	mutex_unlock(&ib_uverbs_idr_mutex);

	while (wr) {
		next = wr->next;
		kfree(wr);
		wr = next;
	}

	kfree(user_wr);

	return ret ? ret : in_len;
}

static struct ib_recv_wr *ib_uverbs_unmarshall_recv(const char __user *buf,
						    int in_len,
						    u32 wr_count,
						    u32 sge_count,
						    u32 wqe_size)
{
	struct ib_uverbs_recv_wr *user_wr;
	struct ib_recv_wr        *wr = NULL, *last, *next;
	int                       sg_ind;
	int                       i;
	int                       ret;

	if (in_len < wqe_size * wr_count +
	    sge_count * sizeof (struct ib_uverbs_sge))
		return ERR_PTR(-EINVAL);

	if (wqe_size < sizeof (struct ib_uverbs_recv_wr))
		return ERR_PTR(-EINVAL);

	user_wr = kmalloc(wqe_size, GFP_KERNEL);
	if (!user_wr)
		return ERR_PTR(-ENOMEM);

	sg_ind = 0;
	last = NULL;
	for (i = 0; i < wr_count; ++i) {
		if (copy_from_user(user_wr, buf + i * wqe_size,
				   wqe_size)) {
			ret = -EFAULT;
			goto err;
		}

		if (user_wr->num_sge + sg_ind > sge_count) {
			ret = -EINVAL;
			goto err;
		}

		next = kmalloc(ALIGN(sizeof *next, sizeof (struct ib_sge)) +
			       user_wr->num_sge * sizeof (struct ib_sge),
			       GFP_KERNEL);
		if (!next) {
			ret = -ENOMEM;
			goto err;
		}

		if (!last)
			wr = next;
		else
			last->next = next;
		last = next;

		next->next       = NULL;
		next->wr_id      = user_wr->wr_id;
		next->num_sge    = user_wr->num_sge;

		if (next->num_sge) {
			next->sg_list = (void *) next +
				ALIGN(sizeof *next, sizeof (struct ib_sge));
			if (copy_from_user(next->sg_list,
					   buf + wr_count * wqe_size +
					   sg_ind * sizeof (struct ib_sge),
					   next->num_sge * sizeof (struct ib_sge))) {
				ret = -EFAULT;
				goto err;
			}
			sg_ind += next->num_sge;
		} else
			next->sg_list = NULL;
	}

	kfree(user_wr);
	return wr;

err:
	kfree(user_wr);

	while (wr) {
		next = wr->next;
		kfree(wr);
		wr = next;
	}

	return ERR_PTR(ret);
}

ssize_t ib_uverbs_post_recv(struct ib_uverbs_file *file,
			    const char __user *buf, int in_len,
			    int out_len)
{
	struct ib_uverbs_post_recv      cmd;
	struct ib_uverbs_post_recv_resp resp;
	struct ib_recv_wr              *wr, *next, *bad_wr;
	struct ib_qp                   *qp;
	ssize_t                         ret = -EINVAL;

	if (copy_from_user(&cmd, buf, sizeof cmd))
		return -EFAULT;

	wr = ib_uverbs_unmarshall_recv(buf + sizeof cmd,
				       in_len - sizeof cmd, cmd.wr_count,
				       cmd.sge_count, cmd.wqe_size);
	if (IS_ERR(wr))
		return PTR_ERR(wr);

	mutex_lock(&ib_uverbs_idr_mutex);

	qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle);
	if (!qp || qp->uobject->context != file->ucontext)
		goto out;

	resp.bad_wr = 0;
	ret = qp->device->post_recv(qp, wr, &bad_wr);
	if (ret)
		for (next = wr; next; next = next->next) {
			++resp.bad_wr;
			if (next == bad_wr)
				break;
		}


	if (copy_to_user((void __user *) (unsigned long) cmd.response,
			 &resp, sizeof resp))
		ret = -EFAULT;

out:
	mutex_unlock(&ib_uverbs_idr_mutex);

	while (wr) {
		next = wr->next;
		kfree(wr);
		wr = next;
	}

	return ret ? ret : in_len;
}