- 根目录:
- drivers
- infiniband
- hw
- mlx4
- mad.c
/*
* Copyright (c) 2007 Cisco Systems, 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 <rdma/ib_mad.h>
#include <rdma/ib_smi.h>
#include <linux/mlx4/cmd.h>
#include <linux/gfp.h>
#include <rdma/ib_pma.h>
#include "mlx4_ib.h"
enum {
MLX4_IB_VENDOR_CLASS1 = 0x9,
MLX4_IB_VENDOR_CLASS2 = 0xa
};
int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey,
int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
void *in_mad, void *response_mad)
{
struct mlx4_cmd_mailbox *inmailbox, *outmailbox;
void *inbox;
int err;
u32 in_modifier = port;
u8 op_modifier = 0;
inmailbox = mlx4_alloc_cmd_mailbox(dev->dev);
if (IS_ERR(inmailbox))
return PTR_ERR(inmailbox);
inbox = inmailbox->buf;
outmailbox = mlx4_alloc_cmd_mailbox(dev->dev);
if (IS_ERR(outmailbox)) {
mlx4_free_cmd_mailbox(dev->dev, inmailbox);
return PTR_ERR(outmailbox);
}
memcpy(inbox, in_mad, 256);
/*
* Key check traps can't be generated unless we have in_wc to
* tell us where to send the trap.
*/
if (ignore_mkey || !in_wc)
op_modifier |= 0x1;
if (ignore_bkey || !in_wc)
op_modifier |= 0x2;
if (in_wc) {
struct {
__be32 my_qpn;
u32 reserved1;
__be32 rqpn;
u8 sl;
u8 g_path;
u16 reserved2[2];
__be16 pkey;
u32 reserved3[11];
u8 grh[40];
} *ext_info;
memset(inbox + 256, 0, 256);
ext_info = inbox + 256;
ext_info->my_qpn = cpu_to_be32(in_wc->qp->qp_num);
ext_info->rqpn = cpu_to_be32(in_wc->src_qp);
ext_info->sl = in_wc->sl << 4;
ext_info->g_path = in_wc->dlid_path_bits |
(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
ext_info->pkey = cpu_to_be16(in_wc->pkey_index);
if (in_grh)
memcpy(ext_info->grh, in_grh, 40);
op_modifier |= 0x4;
in_modifier |= in_wc->slid << 16;
}
err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma,
in_modifier, op_modifier,
MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
MLX4_CMD_NATIVE);
if (!err)
memcpy(response_mad, outmailbox->buf, 256);
mlx4_free_cmd_mailbox(dev->dev, inmailbox);
mlx4_free_cmd_mailbox(dev->dev, outmailbox);
return err;
}
static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
{
struct ib_ah *new_ah;
struct ib_ah_attr ah_attr;
if (!dev->send_agent[port_num - 1][0])
return;
memset(&ah_attr, 0, sizeof ah_attr);
ah_attr.dlid = lid;
ah_attr.sl = sl;
ah_attr.port_num = port_num;
new_ah = ib_create_ah(dev->send_agent[port_num - 1][0]->qp->pd,
&ah_attr);
if (IS_ERR(new_ah))
return;
spin_lock(&dev->sm_lock);
if (dev->sm_ah[port_num - 1])
ib_destroy_ah(dev->sm_ah[port_num - 1]);
dev->sm_ah[port_num - 1] = new_ah;
spin_unlock(&dev->sm_lock);
}
/*
* Snoop SM MADs for port info and P_Key table sets, so we can
* synthesize LID change and P_Key change events.
*/
static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
u16 prev_lid)
{
struct ib_event event;
if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
mad->mad_hdr.method == IB_MGMT_METHOD_SET) {
if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO) {
struct ib_port_info *pinfo =
(struct ib_port_info *) ((struct ib_smp *) mad)->data;
u16 lid = be16_to_cpu(pinfo->lid);
update_sm_ah(to_mdev(ibdev), port_num,
be16_to_cpu(pinfo->sm_lid),
pinfo->neighbormtu_mastersmsl & 0xf);
event.device = ibdev;
event.element.port_num = port_num;
if (pinfo->clientrereg_resv_subnetto & 0x80) {
event.event = IB_EVENT_CLIENT_REREGISTER;
ib_dispatch_event(&event);
}
if (prev_lid != lid) {
event.event = IB_EVENT_LID_CHANGE;
ib_dispatch_event(&event);
}
}
if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PKEY_TABLE) {
event.device = ibdev;
event.event = IB_EVENT_PKEY_CHANGE;
event.element.port_num = port_num;
ib_dispatch_event(&event);
}
}
}
static void node_desc_override(struct ib_device *dev,
struct ib_mad *mad)
{
if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP &&
mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {
spin_lock(&to_mdev(dev)->sm_lock);
memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64);
spin_unlock(&to_mdev(dev)->sm_lock);
}
}
static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *mad)
{
int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
struct ib_mad_send_buf *send_buf;
struct ib_mad_agent *agent = dev->send_agent[port_num - 1][qpn];
int ret;
if (agent) {
send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
IB_MGMT_MAD_DATA, GFP_ATOMIC);
if (IS_ERR(send_buf))
return;
/*
* We rely here on the fact that MLX QPs don't use the
* address handle after the send is posted (this is
* wrong following the IB spec strictly, but we know
* it's OK for our devices).
*/
spin_lock(&dev->sm_lock);
memcpy(send_buf->mad, mad, sizeof *mad);
if ((send_buf->ah = dev->sm_ah[port_num - 1]))
ret = ib_post_send_mad(send_buf, NULL);
else
ret = -EINVAL;
spin_unlock(&dev->sm_lock);
if (ret)
ib_free_send_mad(send_buf);
}
}
static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
struct ib_wc *in_wc, struct ib_grh *in_grh,
struct ib_mad *in_mad, struct ib_mad *out_mad)
{
u16 slid, prev_lid = 0;
int err;
struct ib_port_attr pattr;
slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
forward_trap(to_mdev(ibdev), port_num, in_mad);
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
}
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_TRAP_REPRESS)
return IB_MAD_RESULT_SUCCESS;
/*
* Don't process SMInfo queries -- the SMA can't handle them.
*/
if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO)
return IB_MAD_RESULT_SUCCESS;
} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
in_mad->mad_hdr.mgmt_class == MLX4_IB_VENDOR_CLASS1 ||
in_mad->mad_hdr.mgmt_class == MLX4_IB_VENDOR_CLASS2 ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_CONG_MGMT) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET)
return IB_MAD_RESULT_SUCCESS;
} else
return IB_MAD_RESULT_SUCCESS;
if ((in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
!ib_query_port(ibdev, port_num, &pattr))
prev_lid = pattr.lid;
err = mlx4_MAD_IFC(to_mdev(ibdev),
mad_flags & IB_MAD_IGNORE_MKEY,
mad_flags & IB_MAD_IGNORE_BKEY,
port_num, in_wc, in_grh, in_mad, out_mad);
if (err)
return IB_MAD_RESULT_FAILURE;
if (!out_mad->mad_hdr.status) {
smp_snoop(ibdev, port_num, in_mad, prev_lid);
node_desc_override(ibdev, out_mad);
}
/* set return bit in status of directed route responses */
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
/* no response for trap repress */
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}
static void edit_counter(struct mlx4_counter *cnt,
struct ib_pma_portcounters *pma_cnt)
{
pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2));
pma_cnt->port_rcv_data = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2));
pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames));
pma_cnt->port_rcv_packets = cpu_to_be32(be64_to_cpu(cnt->rx_frames));
}
static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
struct ib_wc *in_wc, struct ib_grh *in_grh,
struct ib_mad *in_mad, struct ib_mad *out_mad)
{
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_ib_dev *dev = to_mdev(ibdev);
int err;
u32 inmod = dev->counters[port_num - 1] & 0xffff;
u8 mode;
if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
return -EINVAL;
mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
if (IS_ERR(mailbox))
return IB_MAD_RESULT_FAILURE;
err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0,
MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
MLX4_CMD_WRAPPED);
if (err)
err = IB_MAD_RESULT_FAILURE;
else {
memset(out_mad->data, 0, sizeof out_mad->data);
mode = ((struct mlx4_counter *)mailbox->buf)->counter_mode;
switch (mode & 0xf) {
case 0:
edit_counter(mailbox->buf,
(void *)(out_mad->data + 40));
err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
break;
default:
err = IB_MAD_RESULT_FAILURE;
}
}
mlx4_free_cmd_mailbox(dev->dev, mailbox);
return err;
}
int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
struct ib_wc *in_wc, struct ib_grh *in_grh,
struct ib_mad *in_mad, struct ib_mad *out_mad)
{
switch (rdma_port_get_link_layer(ibdev, port_num)) {
case IB_LINK_LAYER_INFINIBAND:
return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
in_grh, in_mad, out_mad);
case IB_LINK_LAYER_ETHERNET:
return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
in_grh, in_mad, out_mad);
default:
return -EINVAL;
}
}
static void send_handler(struct ib_mad_agent *agent,
struct ib_mad_send_wc *mad_send_wc)
{
ib_free_send_mad(mad_send_wc->send_buf);
}
int mlx4_ib_mad_init(struct mlx4_ib_dev *dev)
{
struct ib_mad_agent *agent;
int p, q;
int ret;
enum rdma_link_layer ll;
for (p = 0; p < dev->num_ports; ++p) {
ll = rdma_port_get_link_layer(&dev->ib_dev, p + 1);
for (q = 0; q <= 1; ++q) {
if (ll == IB_LINK_LAYER_INFINIBAND) {
agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
q ? IB_QPT_GSI : IB_QPT_SMI,
NULL, 0, send_handler,
NULL, NULL);
if (IS_ERR(agent)) {
ret = PTR_ERR(agent);
goto err;
}
dev->send_agent[p][q] = agent;
} else
dev->send_agent[p][q] = NULL;
}
}
return 0;
err:
for (p = 0; p < dev->num_ports; ++p)
for (q = 0; q <= 1; ++q)
if (dev->send_agent[p][q])
ib_unregister_mad_agent(dev->send_agent[p][q]);
return ret;
}
void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
{
struct ib_mad_agent *agent;
int p, q;
for (p = 0; p < dev->num_ports; ++p) {
for (q = 0; q <= 1; ++q) {
agent = dev->send_agent[p][q];
if (agent) {
dev->send_agent[p][q] = NULL;
ib_unregister_mad_agent(agent);
}
}
if (dev->sm_ah[p])
ib_destroy_ah(dev->sm_ah[p]);
}
}