OpenCloudOS-Kernel/drivers/infiniband/core/netlink.c

277 lines
6.9 KiB
C
Raw Normal View History

/*
* Copyright (c) 2010 Voltaire 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.
*/
#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__
#include <linux/export.h>
#include <net/netlink.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <rdma/rdma_netlink.h>
#include "core_priv.h"
#include "core_priv.h"
static DEFINE_MUTEX(rdma_nl_mutex);
static struct sock *nls;
static struct {
const struct ibnl_client_cbs *cb_table;
} rdma_nl_types[RDMA_NL_NUM_CLIENTS];
int ibnl_chk_listeners(unsigned int group)
{
if (netlink_has_listeners(nls, group) == 0)
return -1;
return 0;
}
static bool is_nl_msg_valid(unsigned int type, unsigned int op)
{
static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS - 1] = {
RDMA_NL_RDMA_CM_NUM_OPS,
RDMA_NL_IWPM_NUM_OPS,
0,
RDMA_NL_LS_NUM_OPS,
0 };
/*
* This BUILD_BUG_ON is intended to catch addition of new
* RDMA netlink protocol without updating the array above.
*/
BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6);
if (type > RDMA_NL_NUM_CLIENTS - 1)
return false;
return (op < max_num_ops[type - 1]) ? true : false;
}
static bool is_nl_valid(unsigned int type, unsigned int op)
{
if (!is_nl_msg_valid(type, op) ||
!rdma_nl_types[type].cb_table ||
!rdma_nl_types[type].cb_table[op].dump)
return false;
return true;
}
void rdma_nl_register(unsigned int index,
const struct ibnl_client_cbs cb_table[])
{
mutex_lock(&rdma_nl_mutex);
if (!is_nl_msg_valid(index, 0)) {
/*
* All clients are not interesting in success/failure of
* this call. They want to see the print to error log and
* continue their initialization. Print warning for them,
* because it is programmer's error to be here.
*/
mutex_unlock(&rdma_nl_mutex);
WARN(true,
"The not-valid %u index was supplied to RDMA netlink\n",
index);
return;
}
if (rdma_nl_types[index].cb_table) {
mutex_unlock(&rdma_nl_mutex);
WARN(true,
"The %u index is already registered in RDMA netlink\n",
index);
return;
}
rdma_nl_types[index].cb_table = cb_table;
mutex_unlock(&rdma_nl_mutex);
}
EXPORT_SYMBOL(rdma_nl_register);
void rdma_nl_unregister(unsigned int index)
{
mutex_lock(&rdma_nl_mutex);
rdma_nl_types[index].cb_table = NULL;
mutex_unlock(&rdma_nl_mutex);
}
EXPORT_SYMBOL(rdma_nl_unregister);
void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
RDMA/core: Add support for iWARP Port Mapper user space service This patch adds iWARP Port Mapper (IWPM) Version 2 support. The iWARP Port Mapper implementation is based on the port mapper specification section in the Sockets Direct Protocol paper - http://www.rdmaconsortium.org/home/draft-pinkerton-iwarp-sdp-v1.0.pdf Existing iWARP RDMA providers use the same IP address as the native TCP/IP stack when creating RDMA connections. They need a mechanism to claim the TCP ports used for RDMA connections to prevent TCP port collisions when other host applications use TCP ports. The iWARP Port Mapper provides a standard mechanism to accomplish this. Without this service it is possible for RDMA application to bind/listen on the same port which is already being used by native TCP host application. If that happens the incoming TCP connection data can be passed to the RDMA stack with error. The iWARP Port Mapper solution doesn't contain any changes to the existing network stack in the kernel space. All the changes are contained with the infiniband tree and also in user space. The iWARP Port Mapper service is implemented as a user space daemon process. Source for the IWPM service is located at http://git.openfabrics.org/git?p=~tnikolova/libiwpm-1.0.0/.git;a=summary The iWARP driver (port mapper client) sends to the IWPM service the local IP address and TCP port it has received from the RDMA application, when starting a connection. The IWPM service performs a socket bind from user space to get an available TCP port, called a mapped port, and communicates it back to the client. In that sense, the IWPM service is used to map the TCP port, which the RDMA application uses to any port available from the host TCP port space. The mapped ports are used in iWARP RDMA connections to avoid collisions with native TCP stack which is aware that these ports are taken. When an RDMA connection using a mapped port is terminated, the client notifies the IWPM service, which then releases the TCP port. The message exchange between the IWPM service and the iWARP drivers (between user space and kernel space) is implemented using netlink sockets. 1) Netlink interface functions are added: ibnl_unicast() and ibnl_mulitcast() for sending netlink messages to user space 2) The signature of the existing ibnl_put_msg() is changed to be more generic 3) Two netlink clients are added: RDMA_NL_NES, RDMA_NL_C4IW corresponding to the two iWarp drivers - nes and cxgb4 which use the IWPM service 4) Enums are added to enumerate the attributes in the netlink messages, which are exchanged between the user space IWPM service and the iWARP drivers Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: PJ Waskiewicz <pj.waskiewicz@solidfire.com> [ Fold in range checking fixes and nlh_next removal as suggested by Dan Carpenter and Steve Wise. Fix sparse endianness in hash. - Roland ] Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-03-27 06:07:35 +08:00
int len, int client, int op, int flags)
{
unsigned char *prev_tail;
prev_tail = skb_tail_pointer(skb);
*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
RDMA/core: Add support for iWARP Port Mapper user space service This patch adds iWARP Port Mapper (IWPM) Version 2 support. The iWARP Port Mapper implementation is based on the port mapper specification section in the Sockets Direct Protocol paper - http://www.rdmaconsortium.org/home/draft-pinkerton-iwarp-sdp-v1.0.pdf Existing iWARP RDMA providers use the same IP address as the native TCP/IP stack when creating RDMA connections. They need a mechanism to claim the TCP ports used for RDMA connections to prevent TCP port collisions when other host applications use TCP ports. The iWARP Port Mapper provides a standard mechanism to accomplish this. Without this service it is possible for RDMA application to bind/listen on the same port which is already being used by native TCP host application. If that happens the incoming TCP connection data can be passed to the RDMA stack with error. The iWARP Port Mapper solution doesn't contain any changes to the existing network stack in the kernel space. All the changes are contained with the infiniband tree and also in user space. The iWARP Port Mapper service is implemented as a user space daemon process. Source for the IWPM service is located at http://git.openfabrics.org/git?p=~tnikolova/libiwpm-1.0.0/.git;a=summary The iWARP driver (port mapper client) sends to the IWPM service the local IP address and TCP port it has received from the RDMA application, when starting a connection. The IWPM service performs a socket bind from user space to get an available TCP port, called a mapped port, and communicates it back to the client. In that sense, the IWPM service is used to map the TCP port, which the RDMA application uses to any port available from the host TCP port space. The mapped ports are used in iWARP RDMA connections to avoid collisions with native TCP stack which is aware that these ports are taken. When an RDMA connection using a mapped port is terminated, the client notifies the IWPM service, which then releases the TCP port. The message exchange between the IWPM service and the iWARP drivers (between user space and kernel space) is implemented using netlink sockets. 1) Netlink interface functions are added: ibnl_unicast() and ibnl_mulitcast() for sending netlink messages to user space 2) The signature of the existing ibnl_put_msg() is changed to be more generic 3) Two netlink clients are added: RDMA_NL_NES, RDMA_NL_C4IW corresponding to the two iWarp drivers - nes and cxgb4 which use the IWPM service 4) Enums are added to enumerate the attributes in the netlink messages, which are exchanged between the user space IWPM service and the iWARP drivers Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: PJ Waskiewicz <pj.waskiewicz@solidfire.com> [ Fold in range checking fixes and nlh_next removal as suggested by Dan Carpenter and Steve Wise. Fix sparse endianness in hash. - Roland ] Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-03-27 06:07:35 +08:00
len, flags);
if (!*nlh)
goto out_nlmsg_trim;
(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
return nlmsg_data(*nlh);
out_nlmsg_trim:
nlmsg_trim(skb, prev_tail);
return NULL;
}
EXPORT_SYMBOL(ibnl_put_msg);
int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
int len, void *data, int type)
{
unsigned char *prev_tail;
prev_tail = skb_tail_pointer(skb);
if (nla_put(skb, type, len, data))
goto nla_put_failure;
nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail;
return 0;
nla_put_failure:
nlmsg_trim(skb, prev_tail - nlh->nlmsg_len);
return -EMSGSIZE;
}
EXPORT_SYMBOL(ibnl_put_attr);
static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
int type = nlh->nlmsg_type;
unsigned int index = RDMA_NL_GET_CLIENT(type);
unsigned int op = RDMA_NL_GET_OP(type);
struct netlink_callback cb = {};
struct netlink_dump_control c = {};
if (!is_nl_valid(index, op))
return -EINVAL;
/*
* For response or local service set_timeout request,
* there is no need to use netlink_dump_start.
*/
if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
(index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
cb.skb = skb;
cb.nlh = nlh;
cb.dump = rdma_nl_types[index].cb_table[op].dump;
return cb.dump(skb, &cb);
}
c.dump = rdma_nl_types[index].cb_table[op].dump;
return netlink_dump_start(nls, skb, nlh, &c);
}
static void ibnl_rcv_reply_skb(struct sk_buff *skb)
{
struct nlmsghdr *nlh;
int msglen;
/*
* Process responses until there is no more message or the first
* request. Generally speaking, it is not recommended to mix responses
* with requests.
*/
while (skb->len >= nlmsg_total_size(0)) {
nlh = nlmsg_hdr(skb);
if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
return;
/* Handle response only */
if (nlh->nlmsg_flags & NLM_F_REQUEST)
return;
ibnl_rcv_msg(skb, nlh, NULL);
msglen = NLMSG_ALIGN(nlh->nlmsg_len);
if (msglen > skb->len)
msglen = skb->len;
skb_pull(skb, msglen);
}
}
static void ibnl_rcv(struct sk_buff *skb)
{
mutex_lock(&rdma_nl_mutex);
ibnl_rcv_reply_skb(skb);
netlink_rcv_skb(skb, &ibnl_rcv_msg);
mutex_unlock(&rdma_nl_mutex);
}
RDMA/core: Add support for iWARP Port Mapper user space service This patch adds iWARP Port Mapper (IWPM) Version 2 support. The iWARP Port Mapper implementation is based on the port mapper specification section in the Sockets Direct Protocol paper - http://www.rdmaconsortium.org/home/draft-pinkerton-iwarp-sdp-v1.0.pdf Existing iWARP RDMA providers use the same IP address as the native TCP/IP stack when creating RDMA connections. They need a mechanism to claim the TCP ports used for RDMA connections to prevent TCP port collisions when other host applications use TCP ports. The iWARP Port Mapper provides a standard mechanism to accomplish this. Without this service it is possible for RDMA application to bind/listen on the same port which is already being used by native TCP host application. If that happens the incoming TCP connection data can be passed to the RDMA stack with error. The iWARP Port Mapper solution doesn't contain any changes to the existing network stack in the kernel space. All the changes are contained with the infiniband tree and also in user space. The iWARP Port Mapper service is implemented as a user space daemon process. Source for the IWPM service is located at http://git.openfabrics.org/git?p=~tnikolova/libiwpm-1.0.0/.git;a=summary The iWARP driver (port mapper client) sends to the IWPM service the local IP address and TCP port it has received from the RDMA application, when starting a connection. The IWPM service performs a socket bind from user space to get an available TCP port, called a mapped port, and communicates it back to the client. In that sense, the IWPM service is used to map the TCP port, which the RDMA application uses to any port available from the host TCP port space. The mapped ports are used in iWARP RDMA connections to avoid collisions with native TCP stack which is aware that these ports are taken. When an RDMA connection using a mapped port is terminated, the client notifies the IWPM service, which then releases the TCP port. The message exchange between the IWPM service and the iWARP drivers (between user space and kernel space) is implemented using netlink sockets. 1) Netlink interface functions are added: ibnl_unicast() and ibnl_mulitcast() for sending netlink messages to user space 2) The signature of the existing ibnl_put_msg() is changed to be more generic 3) Two netlink clients are added: RDMA_NL_NES, RDMA_NL_C4IW corresponding to the two iWarp drivers - nes and cxgb4 which use the IWPM service 4) Enums are added to enumerate the attributes in the netlink messages, which are exchanged between the user space IWPM service and the iWARP drivers Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: PJ Waskiewicz <pj.waskiewicz@solidfire.com> [ Fold in range checking fixes and nlh_next removal as suggested by Dan Carpenter and Steve Wise. Fix sparse endianness in hash. - Roland ] Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-03-27 06:07:35 +08:00
int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
__u32 pid)
{
int err;
err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
return (err < 0) ? err : 0;
RDMA/core: Add support for iWARP Port Mapper user space service This patch adds iWARP Port Mapper (IWPM) Version 2 support. The iWARP Port Mapper implementation is based on the port mapper specification section in the Sockets Direct Protocol paper - http://www.rdmaconsortium.org/home/draft-pinkerton-iwarp-sdp-v1.0.pdf Existing iWARP RDMA providers use the same IP address as the native TCP/IP stack when creating RDMA connections. They need a mechanism to claim the TCP ports used for RDMA connections to prevent TCP port collisions when other host applications use TCP ports. The iWARP Port Mapper provides a standard mechanism to accomplish this. Without this service it is possible for RDMA application to bind/listen on the same port which is already being used by native TCP host application. If that happens the incoming TCP connection data can be passed to the RDMA stack with error. The iWARP Port Mapper solution doesn't contain any changes to the existing network stack in the kernel space. All the changes are contained with the infiniband tree and also in user space. The iWARP Port Mapper service is implemented as a user space daemon process. Source for the IWPM service is located at http://git.openfabrics.org/git?p=~tnikolova/libiwpm-1.0.0/.git;a=summary The iWARP driver (port mapper client) sends to the IWPM service the local IP address and TCP port it has received from the RDMA application, when starting a connection. The IWPM service performs a socket bind from user space to get an available TCP port, called a mapped port, and communicates it back to the client. In that sense, the IWPM service is used to map the TCP port, which the RDMA application uses to any port available from the host TCP port space. The mapped ports are used in iWARP RDMA connections to avoid collisions with native TCP stack which is aware that these ports are taken. When an RDMA connection using a mapped port is terminated, the client notifies the IWPM service, which then releases the TCP port. The message exchange between the IWPM service and the iWARP drivers (between user space and kernel space) is implemented using netlink sockets. 1) Netlink interface functions are added: ibnl_unicast() and ibnl_mulitcast() for sending netlink messages to user space 2) The signature of the existing ibnl_put_msg() is changed to be more generic 3) Two netlink clients are added: RDMA_NL_NES, RDMA_NL_C4IW corresponding to the two iWarp drivers - nes and cxgb4 which use the IWPM service 4) Enums are added to enumerate the attributes in the netlink messages, which are exchanged between the user space IWPM service and the iWARP drivers Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: PJ Waskiewicz <pj.waskiewicz@solidfire.com> [ Fold in range checking fixes and nlh_next removal as suggested by Dan Carpenter and Steve Wise. Fix sparse endianness in hash. - Roland ] Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-03-27 06:07:35 +08:00
}
EXPORT_SYMBOL(ibnl_unicast);
int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
__u32 pid)
{
int err;
err = netlink_unicast(nls, skb, pid, 0);
return (err < 0) ? err : 0;
}
EXPORT_SYMBOL(ibnl_unicast_wait);
RDMA/core: Add support for iWARP Port Mapper user space service This patch adds iWARP Port Mapper (IWPM) Version 2 support. The iWARP Port Mapper implementation is based on the port mapper specification section in the Sockets Direct Protocol paper - http://www.rdmaconsortium.org/home/draft-pinkerton-iwarp-sdp-v1.0.pdf Existing iWARP RDMA providers use the same IP address as the native TCP/IP stack when creating RDMA connections. They need a mechanism to claim the TCP ports used for RDMA connections to prevent TCP port collisions when other host applications use TCP ports. The iWARP Port Mapper provides a standard mechanism to accomplish this. Without this service it is possible for RDMA application to bind/listen on the same port which is already being used by native TCP host application. If that happens the incoming TCP connection data can be passed to the RDMA stack with error. The iWARP Port Mapper solution doesn't contain any changes to the existing network stack in the kernel space. All the changes are contained with the infiniband tree and also in user space. The iWARP Port Mapper service is implemented as a user space daemon process. Source for the IWPM service is located at http://git.openfabrics.org/git?p=~tnikolova/libiwpm-1.0.0/.git;a=summary The iWARP driver (port mapper client) sends to the IWPM service the local IP address and TCP port it has received from the RDMA application, when starting a connection. The IWPM service performs a socket bind from user space to get an available TCP port, called a mapped port, and communicates it back to the client. In that sense, the IWPM service is used to map the TCP port, which the RDMA application uses to any port available from the host TCP port space. The mapped ports are used in iWARP RDMA connections to avoid collisions with native TCP stack which is aware that these ports are taken. When an RDMA connection using a mapped port is terminated, the client notifies the IWPM service, which then releases the TCP port. The message exchange between the IWPM service and the iWARP drivers (between user space and kernel space) is implemented using netlink sockets. 1) Netlink interface functions are added: ibnl_unicast() and ibnl_mulitcast() for sending netlink messages to user space 2) The signature of the existing ibnl_put_msg() is changed to be more generic 3) Two netlink clients are added: RDMA_NL_NES, RDMA_NL_C4IW corresponding to the two iWarp drivers - nes and cxgb4 which use the IWPM service 4) Enums are added to enumerate the attributes in the netlink messages, which are exchanged between the user space IWPM service and the iWARP drivers Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Steve Wise <swise@opengridcomputing.com> Reviewed-by: PJ Waskiewicz <pj.waskiewicz@solidfire.com> [ Fold in range checking fixes and nlh_next removal as suggested by Dan Carpenter and Steve Wise. Fix sparse endianness in hash. - Roland ] Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-03-27 06:07:35 +08:00
int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
unsigned int group, gfp_t flags)
{
return nlmsg_multicast(nls, skb, 0, group, flags);
}
EXPORT_SYMBOL(ibnl_multicast);
int __init rdma_nl_init(void)
{
struct netlink_kernel_cfg cfg = {
.input = ibnl_rcv,
};
nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
if (!nls)
return -ENOMEM;
nls->sk_sndtimeo = 10 * HZ;
return 0;
}
void rdma_nl_exit(void)
{
int idx;
for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
rdma_nl_unregister(idx);
netlink_kernel_release(nls);
}