* [PATCH 0/26] rdma/cm: add support for native IB addressing
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
The following patch series extends the rdma_cm to support native
Infiniband addressing through the use of a new AF_IB address family
and RDMA_PS_IB port space.
It defines a new struct sockaddr_ib that may be used to specify an
IB GID, along with other IB address attributes, such as the pkey and
service ID.
The higher level intent is to support a user space call, rdma_getaddrinfo,
which can return AF_IB addresses to an application. This allows the
rdma_cm to support transport specific features, such as failover and
non-reversible paths, and eliminates the need for the kernel to perform
address and route resolution. (An implementation of rdma_getaddrinfo is included in a separate patch set to the librdmacm.)
This patch series is also available from:
git://git.openfabrics.org/~shefty/rdma-dev.git af_ib
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
Changes from RFC patch series:
Added RDMA_PS_IB for use with AF_IB
drivers/infiniband/core/addr.c | 20 +
drivers/infiniband/core/cma.c | 442 +++++++++++++++++++++++--------
drivers/infiniband/core/sa_query.c | 6
drivers/infiniband/core/ucma.c | 365 ++++++++++++++++++++++---
drivers/infiniband/ulp/iser/iser_verbs.c | 2
include/linux/socket.h | 2
include/rdma/ib.h | 89 ++++++
include/rdma/ib_addr.h | 6
include/rdma/ib_sa.h | 6
include/rdma/rdma_cm.h | 18 +
include/rdma/rdma_user_cm.h | 84 ++++-
net/9p/trans_rdma.c | 3
net/rds/ib.c | 2
net/rds/ib_cm.c | 2
net/rds/iw.c | 2
net/rds/iw_cm.c | 2
net/rds/rdma_transport.c | 3
net/sunrpc/xprtrdma/svc_rdma_transport.c | 3
net/sunrpc/xprtrdma/verbs.c | 2
19 files changed, 863 insertions(+), 196 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 2/26] rdma/cm: fix handling of ipv6 addressing in cma_use_port
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
cma_use_port is coded assuming that the sockaddr is an ipv4 address.
Since ipv6 addressing is supported, and also to support other address
families, make the code more generic in its address handling.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 29 ++++++++++++++++++++++-------
1 files changed, 22 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 875e34e..9041a2b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -643,6 +643,21 @@ static inline int cma_any_addr(struct sockaddr *addr)
return cma_zero_addr(addr) || cma_loopback_addr(addr);
}
+static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst)
+{
+ if (src->sa_family != dst->sa_family)
+ return -1;
+
+ switch (src->sa_family) {
+ case AF_INET:
+ return ((struct sockaddr_in *) src)->sin_addr.s_addr !=
+ ((struct sockaddr_in *) dst)->sin_addr.s_addr;
+ default:
+ return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr,
+ &((struct sockaddr_in6 *) dst)->sin6_addr);
+ }
+}
+
static inline __be16 cma_port(struct sockaddr *addr)
{
if (addr->sa_family == AF_INET)
@@ -2014,13 +2029,13 @@ err1:
static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
{
struct rdma_id_private *cur_id;
- struct sockaddr_in *sin, *cur_sin;
+ struct sockaddr *addr, *cur_addr;
struct rdma_bind_list *bind_list;
struct hlist_node *node;
unsigned short snum;
- sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
- snum = ntohs(sin->sin_port);
+ addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
+ snum = ntohs(cma_port(addr));
if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
@@ -2032,15 +2047,15 @@ static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
* We don't support binding to any address if anyone is bound to
* a specific address on the same port.
*/
- if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr))
+ if (cma_any_addr(addr))
return -EADDRNOTAVAIL;
hlist_for_each_entry(cur_id, node, &bind_list->owners, node) {
- if (cma_any_addr((struct sockaddr *) &cur_id->id.route.addr.src_addr))
+ cur_addr = (struct sockaddr *) &cur_id->id.route.addr.src_addr;
+ if (cma_any_addr(cur_addr))
return -EADDRNOTAVAIL;
- cur_sin = (struct sockaddr_in *) &cur_id->id.route.addr.src_addr;
- if (sin->sin_addr.s_addr == cur_sin->sin_addr.s_addr)
+ if (!cma_addr_cmp(addr, cur_addr))
return -EADDRINUSE;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 1/26] rdma/cm: define native IB address
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma, 'Linux Netdev List'
Define AF_IB and sockaddr_ib to allow the rdma_cm to use native IB
addressing.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
---
include/linux/socket.h | 2 +
include/rdma/ib.h | 89 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 91 insertions(+), 0 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 7b3aae2..966e268 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -181,6 +181,7 @@ struct ucred {
#define AF_PPPOX 24 /* PPPoX sockets */
#define AF_WANPIPE 25 /* Wanpipe API Sockets */
#define AF_LLC 26 /* Linux LLC */
+#define AF_IB 27 /* Native InfiniBand address */
#define AF_CAN 29 /* Controller Area Network */
#define AF_TIPC 30 /* TIPC sockets */
#define AF_BLUETOOTH 31 /* Bluetooth sockets */
@@ -221,6 +222,7 @@ struct ucred {
#define PF_PPPOX AF_PPPOX
#define PF_WANPIPE AF_WANPIPE
#define PF_LLC AF_LLC
+#define PF_IB AF_IB
#define PF_CAN AF_CAN
#define PF_TIPC AF_TIPC
#define PF_BLUETOOTH AF_BLUETOOTH
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
new file mode 100644
index 0000000..cf8f9e7
--- /dev/null
+++ b/include/rdma/ib.h
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2010 Intel Corporation. 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.
+ */
+
+#if !defined(_RDMA_IB_H)
+#define _RDMA_IB_H
+
+#include <linux/types.h>
+
+struct ib_addr {
+ union {
+ __u8 uib_addr8[16];
+ __be16 uib_addr16[8];
+ __be32 uib_addr32[4];
+ __be64 uib_addr64[2];
+ } ib_u;
+#define sib_addr8 ib_u.uib_addr8
+#define sib_addr16 ib_u.uib_addr16
+#define sib_addr32 ib_u.uib_addr32
+#define sib_addr64 ib_u.uib_addr64
+#define sib_raw ib_u.uib_addr8
+#define sib_subnet_prefix ib_u.uib_addr64[0]
+#define sib_interface_id ib_u.uib_addr64[1]
+};
+
+static inline int ib_addr_any(const struct ib_addr *a)
+{
+ return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0);
+}
+
+static inline int ib_addr_loopback(const struct ib_addr *a)
+{
+ return ((a->sib_addr32[0] | a->sib_addr32[1] |
+ a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0);
+}
+
+static inline void ib_addr_set(struct ib_addr *addr,
+ __be32 w1, __be32 w2, __be32 w3, __be32 w4)
+{
+ addr->sib_addr32[0] = w1;
+ addr->sib_addr32[1] = w2;
+ addr->sib_addr32[2] = w3;
+ addr->sib_addr32[3] = w4;
+}
+
+static inline int ib_addr_cmp(const struct ib_addr *a1, const struct ib_addr *a2)
+{
+ return memcmp(a1, a2, sizeof(struct ib_addr));
+}
+
+struct sockaddr_ib {
+ unsigned short int sib_family; /* AF_IB */
+ __be16 sib_pkey;
+ __be32 sib_flowinfo;
+ struct ib_addr sib_addr;
+ __be64 sib_sid;
+ __be64 sib_sid_mask;
+ __u64 sib_scope_id;
+};
+
+#endif /* _RDMA_IB_H */
^ permalink raw reply related
* [PATCH 4/26] ib/addr: add AF_IB support to ip_addr_size
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Add support for AF_IB to ip_addr_size, and rename the function
to account for the change. Give the compiler more control over
whether the call should be inline or not by moving the definition
into the .c file, removing the static inline, and exporting it.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/addr.c | 20 ++++++++++++++++++--
drivers/infiniband/core/cma.c | 12 ++++++------
include/rdma/ib_addr.h | 6 +-----
3 files changed, 25 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index abbb069..f73c5de 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -43,6 +43,7 @@
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <rdma/ib_addr.h>
+#include <rdma/ib.h>
MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("IB Address Translation");
@@ -68,6 +69,21 @@ static LIST_HEAD(req_list);
static DECLARE_DELAYED_WORK(work, process_req);
static struct workqueue_struct *addr_wq;
+int rdma_addr_size(struct sockaddr *addr)
+{
+ switch (addr->sa_family) {
+ case AF_INET:
+ return sizeof(struct sockaddr_in);
+ case AF_INET6:
+ return sizeof(struct sockaddr_in6);
+ case AF_IB:
+ return sizeof(struct sockaddr_ib);
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL(rdma_addr_size);
+
void rdma_addr_register_client(struct rdma_addr_client *client)
{
atomic_set(&client->refcount, 1);
@@ -366,12 +382,12 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
goto err;
}
- memcpy(src_in, src_addr, ip_addr_size(src_addr));
+ memcpy(src_in, src_addr, rdma_addr_size(src_addr));
} else {
src_in->sa_family = dst_addr->sa_family;
}
- memcpy(dst_in, dst_addr, ip_addr_size(dst_addr));
+ memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr));
req->addr = addr;
req->callback = callback;
req->context = context;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 6460fbf..ac57155 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1468,7 +1468,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
dev_id_priv->state = CMA_ADDR_BOUND;
memcpy(&id->route.addr.src_addr, &id_priv->id.route.addr.src_addr,
- ip_addr_size((struct sockaddr *) &id_priv->id.route.addr.src_addr));
+ rdma_addr_size((struct sockaddr *) &id_priv->id.route.addr.src_addr));
cma_attach_to_dev(dev_id_priv, cma_dev);
list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
@@ -1834,7 +1834,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
event.status = status;
} else {
memcpy(&id_priv->id.route.addr.src_addr, src_addr,
- ip_addr_size(src_addr));
+ rdma_addr_size(src_addr));
event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
}
@@ -1924,7 +1924,7 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
return -EINVAL;
atomic_inc(&id_priv->refcount);
- memcpy(&id->route.addr.dst_addr, dst_addr, ip_addr_size(dst_addr));
+ memcpy(&id->route.addr.dst_addr, dst_addr, rdma_addr_size(dst_addr));
if (cma_any_addr(dst_addr))
ret = cma_resolve_loopback(id_priv);
else
@@ -2147,7 +2147,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
goto err1;
}
- memcpy(&id->route.addr.src_addr, addr, ip_addr_size(addr));
+ memcpy(&id->route.addr.src_addr, addr, rdma_addr_size(addr));
ret = cma_get_port(id_priv);
if (ret)
goto err2;
@@ -2807,7 +2807,7 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
if (!mc)
return -ENOMEM;
- memcpy(&mc->addr, addr, ip_addr_size(addr));
+ memcpy(&mc->addr, addr, rdma_addr_size(addr));
mc->context = context;
mc->id_priv = id_priv;
@@ -2842,7 +2842,7 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
id_priv = container_of(id, struct rdma_id_private, id);
spin_lock_irq(&id_priv->lock);
list_for_each_entry(mc, &id_priv->mc_list, list) {
- if (!memcmp(&mc->addr, addr, ip_addr_size(addr))) {
+ if (!memcmp(&mc->addr, addr, rdma_addr_size(addr))) {
list_del(&mc->list);
spin_unlock_irq(&id_priv->lock);
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index fa0d52b..9e06769 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -99,11 +99,7 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr);
int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
const unsigned char *dst_dev_addr);
-static inline int ip_addr_size(struct sockaddr *addr)
-{
- return addr->sa_family == AF_INET6 ?
- sizeof(struct sockaddr_in6) : sizeof(struct sockaddr_in);
-}
+int rdma_addr_size(struct sockaddr *addr);
static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
{
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 5/26] rdma/cm: update port reservation to support AF_IB
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Update the port reservation code path to support AF_IB addresses.
Define a new port space, RDMA_PS_IB, for AF_IB addressing.
The AF_IB port space is a 64-bit service id (SID), which the
user can control through the use of a mask. The rdma_cm
will assign values to the unmasked portions of the SID
when an rdma_cm_id is bound to an AF_IB address.
Because the IB spec divides the SID range into several regions,
a SID/mask combination may fall into one of the existing
port space ranges as defined by the RDMA CM IP Annex. We need
to coordinate port reservation between RDMA_PS_IB and
RDMA_PS_TCP/RDMA_PS_UDP.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 69 +++++++++++++++++++++++++++++++++++++----
include/rdma/rdma_cm.h | 6 ++++
2 files changed, 68 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index ac57155..1328a8e 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -657,18 +657,29 @@ static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst)
case AF_INET:
return ((struct sockaddr_in *) src)->sin_addr.s_addr !=
((struct sockaddr_in *) dst)->sin_addr.s_addr;
- default:
+ case AF_INET6:
return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr,
&((struct sockaddr_in6 *) dst)->sin6_addr);
+ default:
+ return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr,
+ &((struct sockaddr_ib *) dst)->sib_addr);
}
}
-static inline __be16 cma_port(struct sockaddr *addr)
+/* AF_IB must be using the RDMA CM IP Annex */
+static __be16 cma_port(struct sockaddr *addr)
{
- if (addr->sa_family == AF_INET)
+ switch (addr->sa_family) {
+ case AF_INET:
return ((struct sockaddr_in *) addr)->sin_port;
- else
+ case AF_INET6:
return ((struct sockaddr_in6 *) addr)->sin6_port;
+ case AF_IB:
+ return htons((u16) (be64_to_cpu(((struct sockaddr_ib *) addr)->sib_sid) &
+ be64_to_cpu(((struct sockaddr_ib *) addr)->sib_sid_mask)));
+ default:
+ return 0;
+ }
}
static inline int cma_any_port(struct sockaddr *addr)
@@ -1945,10 +1956,29 @@ EXPORT_SYMBOL(rdma_resolve_addr);
static void cma_bind_port(struct rdma_bind_list *bind_list,
struct rdma_id_private *id_priv)
{
- struct sockaddr_in *sin;
+ struct sockaddr *addr;
+ struct sockaddr_ib *sib;
+ u64 sid, mask;
+ __be16 port;
- sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
- sin->sin_port = htons(bind_list->port);
+ addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
+ port = htons(bind_list->port);
+
+ switch (addr->sa_family) {
+ case AF_INET:
+ ((struct sockaddr_in *) addr)->sin_port = port;
+ break;
+ case AF_INET6:
+ ((struct sockaddr_in6 *) addr)->sin6_port = port;
+ break;
+ case AF_IB:
+ sib = (struct sockaddr_ib *) addr;
+ sid = be64_to_cpu(sib->sib_sid);
+ mask = be64_to_cpu(sib->sib_sid_mask);
+ sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port));
+ sib->sib_sid_mask = cpu_to_be64(~0ULL);
+ break;
+ }
id_priv->bind_list = bind_list;
hlist_add_head(&id_priv->node, &bind_list->owners);
}
@@ -2068,6 +2098,26 @@ static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
return 0;
}
+static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv)
+{
+ struct sockaddr_ib *sib;
+ u64 mask, sid;
+
+ sib = (struct sockaddr_ib *) &id_priv->id.route.addr.src_addr;
+ mask = be64_to_cpu(sib->sib_sid_mask);
+ sid = be64_to_cpu(sib->sib_sid);
+
+ if (mask != RDMA_IB_IP_PS_MASK && mask != ~0ULL)
+ return NULL;
+
+ if ((sid & RDMA_IB_IP_PS_MASK) == RDMA_IB_IP_PS_TCP)
+ return &tcp_ps;
+ else if ((sid & RDMA_IB_IP_PS_MASK) == RDMA_IB_IP_PS_UDP)
+ return &udp_ps;
+ else
+ return NULL;
+}
+
static int cma_get_port(struct rdma_id_private *id_priv)
{
struct idr *ps;
@@ -2086,6 +2136,11 @@ static int cma_get_port(struct rdma_id_private *id_priv)
case RDMA_PS_IPOIB:
ps = &ipoib_ps;
break;
+ case RDMA_PS_IB:
+ ps = cma_select_ib_ps(id_priv);
+ if (!ps)
+ return -EINVAL;
+ break;
default:
return -EPROTONOSUPPORT;
}
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index c6b2962..8c27b6e 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -65,11 +65,17 @@ enum rdma_cm_event_type {
enum rdma_port_space {
RDMA_PS_SDP = 0x0001,
RDMA_PS_IPOIB = 0x0002,
+ RDMA_PS_IB = 0x0003,
RDMA_PS_TCP = 0x0106,
RDMA_PS_UDP = 0x0111,
RDMA_PS_SCTP = 0x0183
};
+#define RDMA_IB_IP_PS_MASK 0xFFFFFFFFFFFF0000ULL
+#define RDMA_IB_IP_PORT_MASK 0x000000000000FFFFULL
+#define RDMA_IB_IP_PS_TCP 0x0000000001060000ULL
+#define RDMA_IB_IP_PS_UDP 0x0000000001110000ULL
+
struct rdma_addr {
struct sockaddr_storage src_addr;
struct sockaddr_storage dst_addr;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 3/26] rdma/cm: include AF_IB in loopback and any address checks
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Enhance checks for loopback and any address to support AF_IB
in addition to AF_INET and AF_INT6. This will allow future
patches to use AF_IB when binding and resolving addresses.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 35 ++++++++++++++++++++---------------
1 files changed, 20 insertions(+), 15 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 9041a2b..6460fbf 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -46,6 +46,7 @@
#include <rdma/rdma_cm.h>
#include <rdma/rdma_cm_ib.h>
+#include <rdma/ib.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_cm.h>
#include <rdma/ib_sa.h>
@@ -616,26 +617,30 @@ EXPORT_SYMBOL(rdma_init_qp_attr);
static inline int cma_zero_addr(struct sockaddr *addr)
{
- struct in6_addr *ip6;
-
- if (addr->sa_family == AF_INET)
- return ipv4_is_zeronet(
- ((struct sockaddr_in *)addr)->sin_addr.s_addr);
- else {
- ip6 = &((struct sockaddr_in6 *) addr)->sin6_addr;
- return (ip6->s6_addr32[0] | ip6->s6_addr32[1] |
- ip6->s6_addr32[2] | ip6->s6_addr32[3]) == 0;
+ switch (addr->sa_family) {
+ case AF_INET:
+ return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr);
+ case AF_INET6:
+ return ipv6_addr_any(&((struct sockaddr_in6 *) addr)->sin6_addr);
+ case AF_IB:
+ return ib_addr_any(&((struct sockaddr_ib *) addr)->sib_addr);
+ default:
+ return 0;
}
}
static inline int cma_loopback_addr(struct sockaddr *addr)
{
- if (addr->sa_family == AF_INET)
- return ipv4_is_loopback(
- ((struct sockaddr_in *) addr)->sin_addr.s_addr);
- else
- return ipv6_addr_loopback(
- &((struct sockaddr_in6 *) addr)->sin6_addr);
+ switch (addr->sa_family) {
+ case AF_INET:
+ return ipv4_is_loopback(((struct sockaddr_in *) addr)->sin_addr.s_addr);
+ case AF_INET6:
+ return ipv6_addr_loopback(&((struct sockaddr_in6 *) addr)->sin6_addr);
+ case AF_IB:
+ return ib_addr_loopback(&((struct sockaddr_ib *) addr)->sib_addr);
+ default:
+ return 0;
+ }
}
static inline int cma_any_addr(struct sockaddr *addr)
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 6/26] rdma/cm: specify QP type when creating an ID
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA, 'Andy Grover',
bfields-uC3wQj2KruNg9hUCZPvPmw, neilb-l3A5Bk7waGM,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
v9fs-developer-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f
rdma/cm: specify QP type when creating an ID
From: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
The rdma_cm infers the QP type from the port space selected by the
user. In order to support RDMA_PS_IB, we need to know which
QP type the user intends to support in order to perform the
correction operation, such as sending a REQ versus SIDR.
Modify rdma_create_id to allow the user to specify the QP type,
and use it to make our selections of datagram versus connected
mode.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 35 ++++++++++++++----------------
drivers/infiniband/core/ucma.c | 27 ++++++++++++++++++++---
drivers/infiniband/ulp/iser/iser_verbs.c | 2 +-
include/rdma/rdma_cm.h | 5 +++-
net/9p/trans_rdma.c | 3 ++-
net/rds/ib.c | 2 +-
net/rds/ib_cm.c | 2 +-
net/rds/iw.c | 2 +-
net/rds/iw_cm.c | 2 +-
net/rds/rdma_transport.c | 3 ++-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 3 ++-
net/sunrpc/xprtrdma/verbs.c | 2 +-
12 files changed, 55 insertions(+), 33 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 1328a8e..ccf47c6 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -271,11 +271,6 @@ static inline void sdp_set_ip_ver(struct sdp_hh *hh, u8 ip_ver)
hh->ip_version = (ip_ver << 4) | (hh->ip_version & 0xF);
}
-static inline int cma_is_ud_ps(enum rdma_port_space ps)
-{
- return (ps == RDMA_PS_UDP || ps == RDMA_PS_IPOIB);
-}
-
static void cma_attach_to_dev(struct rdma_id_private *id_priv,
struct cma_device *cma_dev)
{
@@ -366,7 +361,8 @@ static int cma_has_cm_dev(struct rdma_id_private *id_priv)
}
struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
- void *context, enum rdma_port_space ps)
+ void *context, enum rdma_port_space ps,
+ enum ib_qp_type qp_type)
{
struct rdma_id_private *id_priv;
@@ -378,6 +374,7 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
id_priv->id.context = context;
id_priv->id.event_handler = event_handler;
id_priv->id.ps = ps;
+ id_priv->id.qp_type = qp_type;
spin_lock_init(&id_priv->lock);
mutex_init(&id_priv->qp_mutex);
init_completion(&id_priv->comp);
@@ -445,7 +442,7 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
if (IS_ERR(qp))
return PTR_ERR(qp);
- if (cma_is_ud_ps(id_priv->id.ps))
+ if (id->qp_type == IB_QPT_UD)
ret = cma_init_ud_qp(id_priv, qp);
else
ret = cma_init_conn_qp(id_priv, qp);
@@ -567,7 +564,7 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
qp_attr->port_num = id_priv->id.port_num;
*qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT;
- if (cma_is_ud_ps(id_priv->id.ps)) {
+ if (id_priv->id.qp_type == IB_QPT_UD) {
ret = cma_set_qkey(id_priv);
if (ret)
return ret;
@@ -590,7 +587,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
id_priv = container_of(id, struct rdma_id_private, id);
switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
case RDMA_TRANSPORT_IB:
- if (!id_priv->cm_id.ib || cma_is_ud_ps(id_priv->id.ps))
+ if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD))
ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask);
else
ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
@@ -1035,7 +1032,7 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id,
goto err;
id = rdma_create_id(listen_id->event_handler, listen_id->context,
- listen_id->ps);
+ listen_id->ps, ib_event->param.req_rcvd.qp_type);
if (IS_ERR(id))
goto err;
@@ -1086,7 +1083,7 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id,
int ret;
id = rdma_create_id(listen_id->event_handler, listen_id->context,
- listen_id->ps);
+ listen_id->ps, IB_QPT_UD);
if (IS_ERR(id))
return NULL;
@@ -1141,7 +1138,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
memset(&event, 0, sizeof event);
offset = cma_user_data_offset(listen_id->id.ps);
event.event = RDMA_CM_EVENT_CONNECT_REQUEST;
- if (cma_is_ud_ps(listen_id->id.ps)) {
+ if (listen_id->id.qp_type == IB_QPT_UD) {
conn_id = cma_new_udp_id(&listen_id->id, ib_event);
event.param.ud.private_data = ib_event->private_data + offset;
event.param.ud.private_data_len =
@@ -1174,8 +1171,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
* while we're accessing the cm_id.
*/
mutex_lock(&lock);
- if (cma_comp(conn_id, CMA_CONNECT) &&
- !cma_is_ud_ps(conn_id->id.ps))
+ if (cma_comp(conn_id, CMA_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
mutex_unlock(&lock);
mutex_unlock(&conn_id->handler_mutex);
@@ -1328,7 +1324,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
/* Create a new RDMA id for the new IW CM ID */
new_cm_id = rdma_create_id(listen_id->id.event_handler,
listen_id->id.context,
- RDMA_PS_TCP);
+ RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(new_cm_id)) {
ret = -ENOMEM;
goto out;
@@ -1471,7 +1467,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
struct rdma_cm_id *id;
int ret;
- id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps);
+ id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
+ id_priv->id.qp_type);
if (IS_ERR(id))
return;
@@ -2510,7 +2507,7 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
switch (rdma_node_get_transport(id->device->node_type)) {
case RDMA_TRANSPORT_IB:
- if (cma_is_ud_ps(id->ps))
+ if (id->qp_type == IB_QPT_UD)
ret = cma_resolve_ib_udp(id_priv, conn_param);
else
ret = cma_connect_ib(id_priv, conn_param);
@@ -2623,7 +2620,7 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
switch (rdma_node_get_transport(id->device->node_type)) {
case RDMA_TRANSPORT_IB:
- if (cma_is_ud_ps(id->ps))
+ if (id->qp_type == IB_QPT_UD)
ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS,
conn_param->private_data,
conn_param->private_data_len);
@@ -2684,7 +2681,7 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
switch (rdma_node_get_transport(id->device->node_type)) {
case RDMA_TRANSPORT_IB:
- if (cma_is_ud_ps(id->ps))
+ if (id->qp_type == IB_QPT_UD)
ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT,
private_data, private_data_len);
else
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index b2e16c3..9feb18b 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -349,13 +349,28 @@ done:
return ret;
}
-static ssize_t ucma_create_id(struct ucma_file *file,
- const char __user *inbuf,
- int in_len, int out_len)
+static int ucma_get_qp_type(struct rdma_ucm_create_id *cmd, enum ib_qp_type *qp_type)
+{
+ switch (cmd->ps) {
+ case RDMA_PS_TCP:
+ *qp_type = IB_QPT_RC;
+ return 0;
+ case RDMA_PS_UDP:
+ case RDMA_PS_IPOIB:
+ *qp_type = IB_QPT_UD;
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
+static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
+ int in_len, int out_len)
{
struct rdma_ucm_create_id cmd;
struct rdma_ucm_create_id_resp resp;
struct ucma_context *ctx;
+ enum ib_qp_type qp_type;
int ret;
if (out_len < sizeof(resp))
@@ -364,6 +379,10 @@ static ssize_t ucma_create_id(struct ucma_file *file,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
+ ret = ucma_get_qp_type(&cmd, &qp_type);
+ if (ret)
+ return ret;
+
mutex_lock(&file->mut);
ctx = ucma_alloc_ctx(file);
mutex_unlock(&file->mut);
@@ -371,7 +390,7 @@ static ssize_t ucma_create_id(struct ucma_file *file,
return -ENOMEM;
ctx->uid = cmd.uid;
- ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps);
+ ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type);
if (IS_ERR(ctx->cm_id)) {
ret = PTR_ERR(ctx->cm_id);
goto err1;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 8579f32..5b8411b 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -522,7 +522,7 @@ int iser_connect(struct iser_conn *ib_conn,
ib_conn->cma_id = rdma_create_id(iser_cma_handler,
(void *)ib_conn,
- RDMA_PS_TCP);
+ RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(ib_conn->cma_id)) {
err = PTR_ERR(ib_conn->cma_id);
iser_err("rdma_create_id failed: %d\n", err);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 8c27b6e..68e73d1 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -137,6 +137,7 @@ struct rdma_cm_id {
rdma_cm_event_handler event_handler;
struct rdma_route route;
enum rdma_port_space ps;
+ enum ib_qp_type qp_type;
u8 port_num;
};
@@ -147,9 +148,11 @@ struct rdma_cm_id {
* returned rdma_id.
* @context: User specified context associated with the id.
* @ps: RDMA port space.
+ * @qp_type: type of queue pair associated with the id.
*/
struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
- void *context, enum rdma_port_space ps);
+ void *context, enum rdma_port_space ps,
+ enum ib_qp_type qp_type);
/**
* rdma_destroy_id - Destroys an RDMA identifier.
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 2c95a89..34e89f8 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -585,7 +585,8 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
return -ENOMEM;
/* Create the RDMA CM ID */
- rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP);
+ rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP,
+ IB_QPT_RC);
if (IS_ERR(rdma->cm_id))
goto error;
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 3b89923..a6b3925 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -223,7 +223,7 @@ static int rds_ib_laddr_check(__be32 addr)
/* Create a CMA ID and try to bind it. This catches both
* IB and iWARP capable NICs.
*/
- cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP);
+ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(cm_id))
return PTR_ERR(cm_id);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 647cb8f..c8d4343 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -539,7 +539,7 @@ int rds_ib_conn_connect(struct rds_connection *conn)
/* XXX I wonder what affect the port space has */
/* delegate cm event handler to rdma_transport */
ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
- RDMA_PS_TCP);
+ RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(ic->i_cm_id)) {
ret = PTR_ERR(ic->i_cm_id);
ic->i_cm_id = NULL;
diff --git a/net/rds/iw.c b/net/rds/iw.c
index b28fa85..bcce00e 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -225,7 +225,7 @@ static int rds_iw_laddr_check(__be32 addr)
/* Create a CMA ID and try to bind it. This catches both
* IB and iWARP capable NICs.
*/
- cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP);
+ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(cm_id))
return PTR_ERR(cm_id);
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index 394cf6b..d05cfad 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -518,7 +518,7 @@ int rds_iw_conn_connect(struct rds_connection *conn)
/* XXX I wonder what affect the port space has */
/* delegate cm event handler to rdma_transport */
ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
- RDMA_PS_TCP);
+ RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(ic->i_cm_id)) {
ret = PTR_ERR(ic->i_cm_id);
ic->i_cm_id = NULL;
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 9ece910..e55bf7d 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -129,7 +129,8 @@ static int __init rds_rdma_listen_init(void)
struct rdma_cm_id *cm_id;
int ret;
- cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP);
+ cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP,
+ IB_QPT_RC);
if (IS_ERR(cm_id)) {
ret = PTR_ERR(cm_id);
printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3fa5751..963b269 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -684,7 +684,8 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
return ERR_PTR(-ENOMEM);
xprt = &cma_xprt->sc_xprt;
- listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP);
+ listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
+ IB_QPT_RC);
if (IS_ERR(listen_id)) {
ret = PTR_ERR(listen_id);
dprintk("svcrdma: rdma_create_id failed = %d\n", ret);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 2209aa8..bb271be 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -377,7 +377,7 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt,
init_completion(&ia->ri_done);
- id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP);
+ id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(id)) {
rc = PTR_ERR(id);
dprintk("RPC: %s: rdma_create_id() failed %i\n",
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 7/26] rdma/ucm: add support for RDMA_PS_IB when creating an ID
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
In order to support RDMA_PS_IB, we need to know the qp type
to associated with the rdma cm id. Receive the qp type from
user space using currently reserved fields. Previous kernels
do not support RDMA_PS_IB, so we only read out the qp type
data if PS_IB has been selected. This avoids issues reading
uninitialized data from existing applications.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 3 +++
include/rdma/rdma_user_cm.h | 3 ++-
2 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 9feb18b..7a59039 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -359,6 +359,9 @@ static int ucma_get_qp_type(struct rdma_ucm_create_id *cmd, enum ib_qp_type *qp_
case RDMA_PS_IPOIB:
*qp_type = IB_QPT_UD;
return 0;
+ case RDMA_PS_IB:
+ *qp_type = cmd->qp_type;
+ return 0;
default:
return -EINVAL;
}
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index 1d16502..d88c23c 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -77,7 +77,8 @@ struct rdma_ucm_create_id {
__u64 uid;
__u64 response;
__u16 ps;
- __u8 reserved[6];
+ __u8 qp_type;
+ __u8 reserved[5];
};
struct rdma_ucm_create_id_resp {
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 11/26] rdma/cm: do not modify sa_family when setting loopback address
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
cma_resolve_loopback is called after an rdma_cm_id has been
bound to a specific sa_family and port. Once the
source sa_family for the id has been set, do not modify it.
Only the actual IP address portion of the source address
needs to be set.
As part of this fix, we can simplify setting the source address
by moving the loopback address assignment from cma_resolve_loopback
to cma_bind_loopback. cma_bind_loopback is only invoked when
the source address is the loopback address.
Finally, add loopback support for AF_IB as part of the change.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 31 ++++++++++++++++++-------------
1 files changed, 18 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b724eac..224b817 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1775,6 +1775,23 @@ err:
}
EXPORT_SYMBOL(rdma_resolve_route);
+static void cma_set_loopback(struct sockaddr *addr)
+{
+ switch (addr->sa_family) {
+ case AF_INET:
+ ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ break;
+ case AF_INET6:
+ ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr,
+ 0, 0, 0, htonl(1));
+ break;
+ default:
+ ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr,
+ 0, 0, 0, htonl(1));
+ break;
+ }
+}
+
static int cma_bind_loopback(struct rdma_id_private *id_priv)
{
struct cma_device *cma_dev;
@@ -1815,6 +1832,7 @@ port_found:
ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey);
id_priv->id.port_num = p;
cma_attach_to_dev(id_priv, cma_dev);
+ cma_set_loopback((struct sockaddr *) &id_priv->id.route.addr.src_addr);
out:
mutex_unlock(&lock);
return ret;
@@ -1869,7 +1887,6 @@ out:
static int cma_resolve_loopback(struct rdma_id_private *id_priv)
{
struct cma_work *work;
- struct sockaddr *src, *dst;
union ib_gid gid;
int ret;
@@ -1886,18 +1903,6 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);
- src = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
- if (cma_zero_addr(src)) {
- dst = (struct sockaddr *) &id_priv->id.route.addr.dst_addr;
- if ((src->sa_family = dst->sa_family) == AF_INET) {
- ((struct sockaddr_in *) src)->sin_addr.s_addr =
- ((struct sockaddr_in *) dst)->sin_addr.s_addr;
- } else {
- ipv6_addr_copy(&((struct sockaddr_in6 *) src)->sin6_addr,
- &((struct sockaddr_in6 *) dst)->sin6_addr);
- }
- }
-
work->id = id_priv;
INIT_WORK(&work->work, cma_work_handler);
work->old_state = CMA_ADDR_QUERY;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 8/26] rdma/ucm: change event handling based on port space
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
The rdma_ucm handles events differently based on the port space
of the associated rdma_cm_id. In order to support RDMA_PS_IB,
fix the handling based on the qp type.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7a59039..723fe83 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -258,7 +258,7 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
ucma_set_event_context(ctx, event, uevent);
uevent->resp.event = event->event;
uevent->resp.status = event->status;
- if (cm_id->ps == RDMA_PS_UDP || cm_id->ps == RDMA_PS_IPOIB)
+ if (cm_id->qp_type == IB_QPT_UD)
ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud);
else
ucma_copy_conn_event(&uevent->resp.param.conn,
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 21/26] rdma/cm: export cma_get_service_id
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Allow the rdma_ucm to query the IB service ID formed or
allocated by the rdma_cm by exporting the cma_get_service_id
functionality.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 19 ++++++++++---------
include/rdma/rdma_cm.h | 7 +++++++
2 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 8e22119..e0bdb80 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1255,13 +1255,14 @@ out:
return ret;
}
-static __be64 cma_get_service_id(enum rdma_port_space ps, struct sockaddr *addr)
+__be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr)
{
if (addr->sa_family == AF_IB)
return ((struct sockaddr_ib *) addr)->sib_sid;
- return cpu_to_be64(((u64)ps << 16) + be16_to_cpu(cma_port(addr)));
+ return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr)));
}
+EXPORT_SYMBOL(rdma_get_service_id);
static void cma_set_compare_data(enum rdma_port_space ps, struct sockaddr *addr,
struct ib_cm_compare_data *compare)
@@ -1477,7 +1478,7 @@ static int cma_ib_listen(struct rdma_id_private *id_priv)
return PTR_ERR(id_priv->cm_id.ib);
addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
- svc_id = cma_get_service_id(id_priv->id.ps, addr);
+ svc_id = rdma_get_service_id(&id_priv->id, addr);
if (cma_any_addr(addr))
ret = ib_cm_listen(id_priv->cm_id.ib, svc_id, 0, NULL);
else {
@@ -1659,8 +1660,8 @@ static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
path_rec.numb_path = 1;
path_rec.reversible = 1;
- path_rec.service_id = cma_get_service_id(id_priv->id.ps,
- (struct sockaddr *) &addr->dst_addr);
+ path_rec.service_id = rdma_get_service_id(&id_priv->id,
+ (struct sockaddr *) &addr->dst_addr);
comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
@@ -2509,8 +2510,8 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
}
req.path = route->path_rec;
- req.service_id = cma_get_service_id(id_priv->id.ps,
- (struct sockaddr *) &route->addr.dst_addr);
+ req.service_id = rdma_get_service_id(&id_priv->id,
+ (struct sockaddr *) &route->addr.dst_addr);
req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8);
req.max_cm_retries = CMA_MAX_CM_RETRIES;
@@ -2560,8 +2561,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
if (route->num_paths == 2)
req.alternate_path = &route->path_rec[1];
- req.service_id = cma_get_service_id(id_priv->id.ps,
- (struct sockaddr *) &route->addr.dst_addr);
+ req.service_id = rdma_get_service_id(&id_priv->id,
+ (struct sockaddr *) &route->addr.dst_addr);
req.qp_num = id_priv->qp_num;
req.qp_type = IB_QPT_RC;
req.starting_psn = id_priv->seq_num;
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 68e73d1..e74de96 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -339,4 +339,11 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr);
*/
void rdma_set_service_type(struct rdma_cm_id *id, int tos);
+/**
+ * rdma_get_service_id - Return the IB service ID for a specified address.
+ * @id: Communication identifier associated with the address.
+ * @addr: Address for the service ID.
+ */
+__be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr);
+
#endif /* RDMA_CM_H */
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 17/26] rdma/cm: only listen on IB devices when using AF_IB
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
If an rdma_cm_id is bound to AF_IB, with a wild card address,
only listen on IB devices.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b3188fc..8e22119 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1534,6 +1534,10 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
struct rdma_cm_id *id;
int ret;
+ if (id_priv->id.route.addr.src_addr.ss_family == AF_IB &&
+ rdma_node_get_transport(cma_dev->device->node_type) != RDMA_TRANSPORT_IB)
+ return;
+
id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
id_priv->id.qp_type);
if (IS_ERR(id))
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 9/26] rdma/cm: set qkey for port space IB
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Include RDMA_PS_IB checks when setting the qkey for UD QPs.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index ccf47c6..84909b9 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -303,6 +303,7 @@ static int cma_set_qkey(struct rdma_id_private *id_priv)
switch (id_priv->id.ps) {
case RDMA_PS_UDP:
+ case RDMA_PS_IB:
id_priv->qkey = RDMA_UDP_QKEY;
break;
case RDMA_PS_IPOIB:
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 13/26] rdma/cm: add support for AF_IB to rdma_resolve_addr
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Allow the user to specify the remote address using AF_IB format.
When AF_IB is used, the remote address simply needs to be recorded,
and no resolution using ARP is done. The local address may still
need to be resolved however.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 107 +++++++++++++++++++++++++++++++++++++++--
1 files changed, 101 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 7179409..5c956be 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -346,6 +346,61 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv)
return ret;
}
+/*
+ * Select the source IB device and address to reach the destination IB address.
+ */
+static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
+{
+ struct cma_device *cma_dev, *cur_dev;
+ struct sockaddr_ib *addr;
+ union ib_gid gid, sgid, *dgid;
+ u16 pkey, index;
+ u8 port, p;
+ int i;
+
+ cma_dev = NULL;
+ addr = (struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr;
+ dgid = (union ib_gid *) &addr->sib_addr;
+ pkey = ntohs(addr->sib_pkey);
+
+ list_for_each_entry(cur_dev, &dev_list, list) {
+ if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
+ continue;
+
+ for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
+ if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index))
+ continue;
+
+ for (i = 0; !ib_get_cached_gid(cur_dev->device, p, i, &gid); i++) {
+ if (!memcmp(&gid, dgid, sizeof(gid))) {
+ cma_dev = cur_dev;
+ sgid = gid;
+ port = p;
+ goto found;
+ }
+
+ if (!cma_dev && (gid.global.subnet_prefix ==
+ dgid->global.subnet_prefix)) {
+ cma_dev = cur_dev;
+ sgid = gid;
+ port = p;
+ }
+ }
+ }
+ }
+
+ if (!cma_dev)
+ return -ENODEV;
+
+found:
+ cma_attach_to_dev(id_priv, cma_dev);
+ id_priv->id.port_num = port;
+ addr = (struct sockaddr_ib *) &id_priv->id.route.addr.src_addr;
+ memcpy(&addr->sib_addr, &sgid, sizeof sgid);
+ cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr);
+ return 0;
+}
+
static void cma_deref_id(struct rdma_id_private *id_priv)
{
if (atomic_dec_and_test(&id_priv->refcount))
@@ -1929,14 +1984,48 @@ err:
return ret;
}
+static int cma_resolve_ib_addr(struct rdma_id_private *id_priv)
+{
+ struct cma_work *work;
+ int ret;
+
+ work = kzalloc(sizeof *work, GFP_KERNEL);
+ if (!work)
+ return -ENOMEM;
+
+ if (!id_priv->cma_dev) {
+ ret = cma_resolve_ib_dev(id_priv);
+ if (ret)
+ goto err;
+ }
+
+ rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)
+ &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr));
+
+ work->id = id_priv;
+ INIT_WORK(&work->work, cma_work_handler);
+ work->old_state = CMA_ADDR_QUERY;
+ work->new_state = CMA_ADDR_RESOLVED;
+ work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
+ queue_work(cma_wq, &work->work);
+ return 0;
+err:
+ kfree(work);
+ return ret;
+}
+
static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
struct sockaddr *dst_addr)
{
if (!src_addr || !src_addr->sa_family) {
src_addr = (struct sockaddr *) &id->route.addr.src_addr;
- if ((src_addr->sa_family = dst_addr->sa_family) == AF_INET6) {
+ src_addr->sa_family = dst_addr->sa_family;
+ if (dst_addr->sa_family == AF_INET6) {
((struct sockaddr_in6 *) src_addr)->sin6_scope_id =
((struct sockaddr_in6 *) dst_addr)->sin6_scope_id;
+ } else if (dst_addr->sa_family == AF_IB) {
+ ((struct sockaddr_ib *) src_addr)->sib_pkey =
+ ((struct sockaddr_ib *) dst_addr)->sib_pkey;
}
}
return rdma_bind_addr(id, src_addr);
@@ -1960,12 +2049,18 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
atomic_inc(&id_priv->refcount);
memcpy(&id->route.addr.dst_addr, dst_addr, rdma_addr_size(dst_addr));
- if (cma_any_addr(dst_addr))
+ if (cma_any_addr(dst_addr)) {
ret = cma_resolve_loopback(id_priv);
- else
- ret = rdma_resolve_ip(&addr_client, (struct sockaddr *) &id->route.addr.src_addr,
- dst_addr, &id->route.addr.dev_addr,
- timeout_ms, addr_handler, id_priv);
+ } else {
+ if (dst_addr->sa_family == AF_IB) {
+ ret = cma_resolve_ib_addr(id_priv);
+ } else {
+ ret = rdma_resolve_ip(&addr_client,
+ (struct sockaddr *) &id->route.addr.src_addr,
+ dst_addr, &id->route.addr.dev_addr,
+ timeout_ms, addr_handler, id_priv);
+ }
+ }
if (ret)
goto err;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 12/26] rdma/cm: restrict AF_IB loopback to binding to IB devices only
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
If a user specifies AF_IB as the source address for a loopback
connection, limit the resolution to IB devices only.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 30 ++++++++++++++++++++++--------
1 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 224b817..7179409 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1794,26 +1794,40 @@ static void cma_set_loopback(struct sockaddr *addr)
static int cma_bind_loopback(struct rdma_id_private *id_priv)
{
- struct cma_device *cma_dev;
+ struct cma_device *cma_dev, *cur_dev;
+ struct sockaddr *addr;
struct ib_port_attr port_attr;
union ib_gid gid;
u16 pkey;
int ret;
u8 p;
+ cma_dev = NULL;
+ addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
mutex_lock(&lock);
- if (list_empty(&dev_list)) {
+ list_for_each_entry(cur_dev, &dev_list, list) {
+ if (addr->sa_family == AF_IB &&
+ rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
+ continue;
+
+ if (!cma_dev)
+ cma_dev = cur_dev;
+
+ for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
+ if (!ib_query_port(cur_dev->device, p, &port_attr) &&
+ port_attr.state == IB_PORT_ACTIVE) {
+ cma_dev = cur_dev;
+ goto port_found;
+ }
+ }
+ }
+
+ if (!cma_dev) {
ret = -ENODEV;
goto out;
}
- list_for_each_entry(cma_dev, &dev_list, list)
- for (p = 1; p <= cma_dev->device->phys_port_cnt; ++p)
- if (!ib_query_port(cma_dev->device, p, &port_attr) &&
- port_attr.state == IB_PORT_ACTIVE)
- goto port_found;
p = 1;
- cma_dev = list_entry(dev_list.next, struct cma_device, list);
port_found:
ret = ib_get_cached_gid(cma_dev->device, p, 0, &gid);
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 10/26] rdma/cm: Allow user to specify AF_IB when binding
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Modify rdma_bind_addr to allow the user to specify AF_IB when
binding to a device. AF_IB indicates that the user is not
mapping an IP address to the native IB addressing. (The mapping
may have already been done, or is not needed.)
AF_IB is restricted to the RDMA_PS_IB port space.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 22 ++++++++++++++++++----
1 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 84909b9..b724eac 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -320,6 +320,13 @@ static int cma_set_qkey(struct rdma_id_private *id_priv)
return ret;
}
+static void cma_translate_ib(struct sockaddr_ib *addr, struct rdma_dev_addr *dev_addr)
+{
+ dev_addr->dev_type = ARPHRD_INFINIBAND;
+ rdma_addr_set_sgid(dev_addr, (union ib_gid *) &addr->sib_addr);
+ ib_addr_set_pkey(dev_addr, ntohs(addr->sib_pkey));
+}
+
static int cma_acquire_dev(struct rdma_id_private *id_priv)
{
struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
@@ -2177,7 +2184,9 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
struct rdma_id_private *id_priv;
int ret;
- if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6)
+ if ((addr->sa_family != AF_INET && addr->sa_family != AF_INET6 &&
+ addr->sa_family != AF_IB) ||
+ (addr->sa_family == AF_IB && id->ps != RDMA_PS_IB))
return -EAFNOSUPPORT;
id_priv = container_of(id, struct rdma_id_private, id);
@@ -2189,9 +2198,14 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
goto err1;
if (!cma_any_addr(addr)) {
- ret = rdma_translate_ip(addr, &id->route.addr.dev_addr);
- if (ret)
- goto err1;
+ if (addr->sa_family == AF_IB) {
+ cma_translate_ib((struct sockaddr_ib *) addr,
+ &id->route.addr.dev_addr);
+ } else {
+ ret = rdma_translate_ip(addr, &id->route.addr.dev_addr);
+ if (ret)
+ goto err1;
+ }
mutex_lock(&lock);
ret = cma_acquire_dev(id_priv);
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 15/26] rdma/cm: fixup white space
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Fix a white space issue that bug me.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index cc35872..0432eca 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1655,7 +1655,7 @@ static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
path_rec.numb_path = 1;
path_rec.reversible = 1;
path_rec.service_id = cma_get_service_id(id_priv->id.ps,
- (struct sockaddr *) &addr->dst_addr);
+ (struct sockaddr *) &addr->dst_addr);
comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 16/26] rdma/cm: expose private data when using AF_IB
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
If the source or destination address is AF_IB, then do not
reserve a portion of the private data in the IB CM REQ or SIDR
REQ messages for the cma header. Instead, all private data
should be exported to the user. When AF_IB is used, the
rdma cm does not have sufficient information to fill in the
cma header. Additionally, this will be necessary to support
any IB connection through the rdma cm interface,
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 34 ++++++++++++++++++----------------
1 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0432eca..b3188fc 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -820,6 +820,7 @@ static inline int cma_user_data_offset(enum rdma_port_space ps)
{
switch (ps) {
case RDMA_PS_SDP:
+ case RDMA_PS_IB:
return 0;
default:
return sizeof(struct cma_hdr);
@@ -2349,19 +2350,19 @@ err1:
}
EXPORT_SYMBOL(rdma_bind_addr);
-static int cma_format_hdr(void *hdr, enum rdma_port_space ps,
- struct rdma_route *route)
+static int cma_format_hdr(void *hdr, struct rdma_cm_id *id)
{
struct cma_hdr *cma_hdr;
struct sdp_hh *sdp_hdr;
- if (route->addr.src_addr.ss_family == AF_INET) {
+ if (id->route.addr.src_addr.ss_family == AF_INET &&
+ id->route.addr.dst_addr.ss_family == AF_INET) {
struct sockaddr_in *src4, *dst4;
- src4 = (struct sockaddr_in *) &route->addr.src_addr;
- dst4 = (struct sockaddr_in *) &route->addr.dst_addr;
+ src4 = (struct sockaddr_in *) &id->route.addr.src_addr;
+ dst4 = (struct sockaddr_in *) &id->route.addr.dst_addr;
- switch (ps) {
+ switch (id->ps) {
case RDMA_PS_SDP:
sdp_hdr = hdr;
if (sdp_get_majv(sdp_hdr->sdp_version) != SDP_MAJ_VERSION)
@@ -2380,13 +2381,14 @@ static int cma_format_hdr(void *hdr, enum rdma_port_space ps,
cma_hdr->port = src4->sin_port;
break;
}
- } else {
+ } else if (id->route.addr.src_addr.ss_family == AF_INET6 &&
+ id->route.addr.dst_addr.ss_family == AF_INET6) {
struct sockaddr_in6 *src6, *dst6;
- src6 = (struct sockaddr_in6 *) &route->addr.src_addr;
- dst6 = (struct sockaddr_in6 *) &route->addr.dst_addr;
+ src6 = (struct sockaddr_in6 *) &id->route.addr.src_addr;
+ dst6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr;
- switch (ps) {
+ switch (id->ps) {
case RDMA_PS_SDP:
sdp_hdr = hdr;
if (sdp_get_majv(sdp_hdr->sdp_version) != SDP_MAJ_VERSION)
@@ -2478,20 +2480,20 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
{
struct ib_cm_sidr_req_param req;
struct rdma_route *route;
- int ret;
+ int offset, ret;
- req.private_data_len = sizeof(struct cma_hdr) +
- conn_param->private_data_len;
+ offset = cma_user_data_offset(id_priv->id.ps);
+ req.private_data_len = offset + conn_param->private_data_len;
req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
if (!req.private_data)
return -ENOMEM;
if (conn_param->private_data && conn_param->private_data_len)
- memcpy((void *) req.private_data + sizeof(struct cma_hdr),
+ memcpy((void *) req.private_data + offset,
conn_param->private_data, conn_param->private_data_len);
route = &id_priv->id.route;
- ret = cma_format_hdr((void *) req.private_data, id_priv->id.ps, route);
+ ret = cma_format_hdr((void *) req.private_data, &id_priv->id);
if (ret)
goto out;
@@ -2545,7 +2547,7 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
}
route = &id_priv->id.route;
- ret = cma_format_hdr(private_data, id_priv->id.ps, route);
+ ret = cma_format_hdr(private_data, &id_priv->id);
if (ret)
goto out;
req.private_data = private_data;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 18/26] rdma/ucm: support querying for AF_IB addresses
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
The sockaddr structure for AF_IB is larger than sockaddr_in6.
The rdma cm user space ABI uses the latter to exchange address
information between user space and the kernel.
To support querying for larger addresses, define a new query
command that exchanges data using sockaddr_storage, rather
than sockaddr_in6. Unlike the existing query_route command,
the new command only returns address information. Route
(i.e. path record) data is separated.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 76 +++++++++++++++++++++++++++++++++++++++-
include/rdma/rdma_user_cm.h | 22 ++++++++++--
2 files changed, 93 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 723fe83..2b6b51a 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -44,6 +44,7 @@
#include <rdma/ib_marshall.h>
#include <rdma/rdma_cm.h>
#include <rdma/rdma_cm_ib.h>
+#include <rdma/ib_addr.h>
MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access");
@@ -608,7 +609,7 @@ static ssize_t ucma_query_route(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
{
- struct rdma_ucm_query_route cmd;
+ struct rdma_ucm_query cmd;
struct rdma_ucm_query_route_resp resp;
struct ucma_context *ctx;
struct sockaddr *addr;
@@ -655,6 +656,76 @@ out:
return ret;
}
+static void ucma_query_device_addr(struct rdma_cm_id *cm_id,
+ struct rdma_ucm_query_addr_resp *resp)
+{
+ if (!cm_id->device)
+ return;
+
+ resp->node_guid = (__force __u64) cm_id->device->node_guid;
+ resp->port_num = cm_id->port_num;
+ resp->pkey = (__force __u16) cpu_to_be16(
+ ib_addr_get_pkey(&cm_id->route.addr.dev_addr));
+}
+
+static ssize_t ucma_query_addr(struct ucma_context *ctx,
+ void __user *response, int out_len)
+{
+ struct rdma_ucm_query_addr_resp resp;
+ struct sockaddr *addr;
+ int ret = 0;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ memset(&resp, 0, sizeof resp);
+
+ addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr;
+ resp.src_size = rdma_addr_size(addr);
+ memcpy(&resp.src_addr, addr, resp.src_size);
+
+ addr = (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr;
+ resp.dst_size = rdma_addr_size(addr);
+ memcpy(&resp.dst_addr, addr, resp.dst_size);
+
+ ucma_query_device_addr(ctx->cm_id, &resp);
+
+ if (copy_to_user(response, &resp, sizeof(resp)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
+static ssize_t ucma_query(struct ucma_file *file,
+ const char __user *inbuf,
+ int in_len, int out_len)
+{
+ struct rdma_ucm_query cmd;
+ struct ucma_context *ctx;
+ void __user *response;
+ int ret;
+
+ if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
+ return -EFAULT;
+
+ response = (void __user *)(unsigned long) cmd.response;
+ ctx = ucma_get_ctx(file, cmd.id);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ switch (cmd.option) {
+ case RDMA_USER_CM_QUERY_ADDR:
+ ret = ucma_query_addr(ctx, response, out_len);
+ break;
+ default:
+ ret = -ENOSYS;
+ break;
+ }
+
+ ucma_put_ctx(ctx);
+ return ret;
+}
+
static void ucma_copy_conn_param(struct rdma_conn_param *dst,
struct rdma_ucm_conn_param *src)
{
@@ -1173,7 +1244,8 @@ static ssize_t (*ucma_cmd_table[])(struct ucma_file *file,
[RDMA_USER_CM_CMD_NOTIFY] = ucma_notify,
[RDMA_USER_CM_CMD_JOIN_MCAST] = ucma_join_multicast,
[RDMA_USER_CM_CMD_LEAVE_MCAST] = ucma_leave_multicast,
- [RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id
+ [RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id,
+ [RDMA_USER_CM_CMD_QUERY] = ucma_query
};
static ssize_t ucma_write(struct file *filp, const char __user *buf,
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index d88c23c..9687b2f 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -61,7 +61,8 @@ enum {
RDMA_USER_CM_CMD_NOTIFY,
RDMA_USER_CM_CMD_JOIN_MCAST,
RDMA_USER_CM_CMD_LEAVE_MCAST,
- RDMA_USER_CM_CMD_MIGRATE_ID
+ RDMA_USER_CM_CMD_MIGRATE_ID,
+ RDMA_USER_CM_CMD_QUERY
};
/*
@@ -113,10 +114,14 @@ struct rdma_ucm_resolve_route {
__u32 timeout_ms;
};
-struct rdma_ucm_query_route {
+enum {
+ RDMA_USER_CM_QUERY_ADDR
+};
+
+struct rdma_ucm_query {
__u64 response;
__u32 id;
- __u32 reserved;
+ __u32 option;
};
struct rdma_ucm_query_route_resp {
@@ -129,6 +134,17 @@ struct rdma_ucm_query_route_resp {
__u8 reserved[3];
};
+struct rdma_ucm_query_addr_resp {
+ __u64 node_guid;
+ __u8 port_num;
+ __u8 reserved;
+ __u16 pkey;
+ __u16 src_size;
+ __u16 dst_size;
+ struct sockaddr_storage src_addr;
+ struct sockaddr_storage dst_addr;
+};
+
struct rdma_ucm_conn_param {
__u32 qp_num;
__u32 reserved;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 14/26] rdma/cm: add support for AF_IB to cma_get_service_id
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
cma_get_service_id forms the service ID based on the port space
and port number of the rdma_cm_id. Extend the call to support
AF_IB, which contains the service ID directly. This will
be needed to support any arbitrary SID.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 5c956be..cc35872 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1256,6 +1256,9 @@ out:
static __be64 cma_get_service_id(enum rdma_port_space ps, struct sockaddr *addr)
{
+ if (addr->sa_family == AF_IB)
+ return ((struct sockaddr_ib *) addr)->sib_sid;
+
return cpu_to_be64(((u64)ps << 16) + be16_to_cpu(cma_port(addr)));
}
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 19/26] ib/sa: export function to pack a path record into wire format
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Allow converting from struct ib_sa_path_rec to the IB defined
SA path record wire format. This will be used to report path
data from the rdma cm into user space.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/sa_query.c | 6 ++++++
include/rdma/ib_sa.h | 6 ++++++
2 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7e1ffd8..54ec971 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -610,6 +610,12 @@ void ib_sa_unpack_path(void *attribute, struct ib_sa_path_rec *rec)
}
EXPORT_SYMBOL(ib_sa_unpack_path);
+void ib_sa_pack_path(struct ib_sa_path_rec *rec, void *attribute)
+{
+ ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table), rec, attribute);
+}
+EXPORT_SYMBOL(ib_sa_pack_path);
+
static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
int status,
struct ib_sa_mad *mad)
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 1082afa..86aa772 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -385,4 +385,10 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
*/
void ib_sa_unpack_path(void *attribute, struct ib_sa_path_rec *rec);
+/**
+ * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec
+ * to IB MAD wire format.
+ */
+void ib_sa_pack_path(struct ib_sa_path_rec *rec, void *attribute);
+
#endif /* IB_SA_H */
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 20/26] rdma/ucm: support querying when IB paths are not reversible
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
The current query_route call can return up to two path records.
The assumption being that one is the primary path, with optional
support for an alternate path. In both cases, the paths are
assumed to be reversible and are used to send CM MADs.
With the ability to manually set IB path data, the rdma cm
can eventually be capable of using up to 6 paths per
connection:
forward primary, reverse primary,
forward alternate, reverse alternate,
reversible primary path for CM MADs
reversible alternate path for CM MADs.
(It is unclear at this time if IB routing will complicate this.)
In order to handle more flexible routing topologies, add a new
command to report any number of paths.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 35 +++++++++++++++++++++++++++++++++++
include/rdma/rdma_user_cm.h | 9 ++++++++-
2 files changed, 43 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 2b6b51a..5d8d68e 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -696,6 +696,38 @@ static ssize_t ucma_query_addr(struct ucma_context *ctx,
return ret;
}
+static ssize_t ucma_query_path(struct ucma_context *ctx,
+ void __user *response, int out_len)
+{
+ struct rdma_ucm_query_path_resp *resp;
+ int i, ret = 0;
+
+ if (out_len < sizeof(*resp))
+ return -ENOSPC;
+
+ resp = kzalloc(out_len, GFP_KERNEL);
+ if (!resp)
+ return -ENOMEM;
+
+ resp->num_paths = ctx->cm_id->route.num_paths;
+ for (i = 0, out_len -= sizeof(*resp);
+ i < resp->num_paths && out_len > sizeof(struct ib_path_rec_data);
+ i++, out_len -= sizeof(struct ib_path_rec_data)) {
+
+ resp->path_data[i].flags = IB_PATH_GMP | IB_PATH_PRIMARY |
+ IB_PATH_BIDIRECTIONAL;
+ ib_sa_pack_path(&ctx->cm_id->route.path_rec[i],
+ &resp->path_data[i].path_rec);
+ }
+
+ if (copy_to_user(response, resp,
+ sizeof(*resp) + (i * sizeof(struct ib_path_rec_data))))
+ ret = -EFAULT;
+
+ kfree(resp);
+ return ret;
+}
+
static ssize_t ucma_query(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
@@ -717,6 +749,9 @@ static ssize_t ucma_query(struct ucma_file *file,
case RDMA_USER_CM_QUERY_ADDR:
ret = ucma_query_addr(ctx, response, out_len);
break;
+ case RDMA_USER_CM_QUERY_PATH:
+ ret = ucma_query_path(ctx, response, out_len);
+ break;
default:
ret = -ENOSYS;
break;
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index 9687b2f..7784203 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -115,7 +115,8 @@ struct rdma_ucm_resolve_route {
};
enum {
- RDMA_USER_CM_QUERY_ADDR
+ RDMA_USER_CM_QUERY_ADDR,
+ RDMA_USER_CM_QUERY_PATH
};
struct rdma_ucm_query {
@@ -145,6 +146,12 @@ struct rdma_ucm_query_addr_resp {
struct sockaddr_storage dst_addr;
};
+struct rdma_ucm_query_path_resp {
+ __u32 num_paths;
+ __u32 reserved;
+ struct ib_path_rec_data path_data[0];
+};
+
struct rdma_ucm_conn_param {
__u32 qp_num;
__u32 reserved;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 23/26] rdma/ucm: name changes to indicate only IP addresses supported
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Several commands into the RDMA CM from user space are
restricted to supporting addresses which fit into a sockaddr_in6
structure: bind address, resolve address, and join multicast.
With the addition of AF_IB, we need to support addresses
which are larger than sockaddr_in6. This will be done by
adding new commands that exchange address information using
sockaddr_storage. However, to support existing applications,
we maintain the current commands and structures, but rename
them to indicate that they only support IPv4 and v6 addresses.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 60 ++++++++++++++++++++--------------------
include/rdma/rdma_user_cm.h | 12 ++++----
2 files changed, 36 insertions(+), 36 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 82eb1ac..6456502 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -517,10 +517,10 @@ static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
return ret;
}
-static ssize_t ucma_bind_addr(struct ucma_file *file, const char __user *inbuf,
+static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
- struct rdma_ucm_bind_addr cmd;
+ struct rdma_ucm_bind_ip cmd;
struct ucma_context *ctx;
int ret;
@@ -536,11 +536,11 @@ static ssize_t ucma_bind_addr(struct ucma_file *file, const char __user *inbuf,
return ret;
}
-static ssize_t ucma_resolve_addr(struct ucma_file *file,
- const char __user *inbuf,
- int in_len, int out_len)
+static ssize_t ucma_resolve_ip(struct ucma_file *file,
+ const char __user *inbuf,
+ int in_len, int out_len)
{
- struct rdma_ucm_resolve_addr cmd;
+ struct rdma_ucm_resolve_ip cmd;
struct ucma_context *ctx;
int ret;
@@ -1110,11 +1110,11 @@ static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf,
return ret;
}
-static ssize_t ucma_join_multicast(struct ucma_file *file,
- const char __user *inbuf,
- int in_len, int out_len)
+static ssize_t ucma_join_ip_multicast(struct ucma_file *file,
+ const char __user *inbuf,
+ int in_len, int out_len)
{
- struct rdma_ucm_join_mcast cmd;
+ struct rdma_ucm_join_ip_mcast cmd;
struct rdma_ucm_create_id_resp resp;
struct ucma_context *ctx;
struct ucma_multicast *mc;
@@ -1311,26 +1311,26 @@ file_put:
static ssize_t (*ucma_cmd_table[])(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len) = {
- [RDMA_USER_CM_CMD_CREATE_ID] = ucma_create_id,
- [RDMA_USER_CM_CMD_DESTROY_ID] = ucma_destroy_id,
- [RDMA_USER_CM_CMD_BIND_ADDR] = ucma_bind_addr,
- [RDMA_USER_CM_CMD_RESOLVE_ADDR] = ucma_resolve_addr,
- [RDMA_USER_CM_CMD_RESOLVE_ROUTE]= ucma_resolve_route,
- [RDMA_USER_CM_CMD_QUERY_ROUTE] = ucma_query_route,
- [RDMA_USER_CM_CMD_CONNECT] = ucma_connect,
- [RDMA_USER_CM_CMD_LISTEN] = ucma_listen,
- [RDMA_USER_CM_CMD_ACCEPT] = ucma_accept,
- [RDMA_USER_CM_CMD_REJECT] = ucma_reject,
- [RDMA_USER_CM_CMD_DISCONNECT] = ucma_disconnect,
- [RDMA_USER_CM_CMD_INIT_QP_ATTR] = ucma_init_qp_attr,
- [RDMA_USER_CM_CMD_GET_EVENT] = ucma_get_event,
- [RDMA_USER_CM_CMD_GET_OPTION] = NULL,
- [RDMA_USER_CM_CMD_SET_OPTION] = ucma_set_option,
- [RDMA_USER_CM_CMD_NOTIFY] = ucma_notify,
- [RDMA_USER_CM_CMD_JOIN_MCAST] = ucma_join_multicast,
- [RDMA_USER_CM_CMD_LEAVE_MCAST] = ucma_leave_multicast,
- [RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id,
- [RDMA_USER_CM_CMD_QUERY] = ucma_query
+ [RDMA_USER_CM_CMD_CREATE_ID] = ucma_create_id,
+ [RDMA_USER_CM_CMD_DESTROY_ID] = ucma_destroy_id,
+ [RDMA_USER_CM_CMD_BIND_IP] = ucma_bind_ip,
+ [RDMA_USER_CM_CMD_RESOLVE_IP] = ucma_resolve_ip,
+ [RDMA_USER_CM_CMD_RESOLVE_ROUTE] = ucma_resolve_route,
+ [RDMA_USER_CM_CMD_QUERY_ROUTE] = ucma_query_route,
+ [RDMA_USER_CM_CMD_CONNECT] = ucma_connect,
+ [RDMA_USER_CM_CMD_LISTEN] = ucma_listen,
+ [RDMA_USER_CM_CMD_ACCEPT] = ucma_accept,
+ [RDMA_USER_CM_CMD_REJECT] = ucma_reject,
+ [RDMA_USER_CM_CMD_DISCONNECT] = ucma_disconnect,
+ [RDMA_USER_CM_CMD_INIT_QP_ATTR] = ucma_init_qp_attr,
+ [RDMA_USER_CM_CMD_GET_EVENT] = ucma_get_event,
+ [RDMA_USER_CM_CMD_GET_OPTION] = NULL,
+ [RDMA_USER_CM_CMD_SET_OPTION] = ucma_set_option,
+ [RDMA_USER_CM_CMD_NOTIFY] = ucma_notify,
+ [RDMA_USER_CM_CMD_JOIN_IP_MCAST] = ucma_join_ip_multicast,
+ [RDMA_USER_CM_CMD_LEAVE_MCAST] = ucma_leave_multicast,
+ [RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id,
+ [RDMA_USER_CM_CMD_QUERY] = ucma_query
};
static ssize_t ucma_write(struct file *filp, const char __user *buf,
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index 95bb515..c1e0ac9 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -45,8 +45,8 @@
enum {
RDMA_USER_CM_CMD_CREATE_ID,
RDMA_USER_CM_CMD_DESTROY_ID,
- RDMA_USER_CM_CMD_BIND_ADDR,
- RDMA_USER_CM_CMD_RESOLVE_ADDR,
+ RDMA_USER_CM_CMD_BIND_IP,
+ RDMA_USER_CM_CMD_RESOLVE_IP,
RDMA_USER_CM_CMD_RESOLVE_ROUTE,
RDMA_USER_CM_CMD_QUERY_ROUTE,
RDMA_USER_CM_CMD_CONNECT,
@@ -59,7 +59,7 @@ enum {
RDMA_USER_CM_CMD_GET_OPTION,
RDMA_USER_CM_CMD_SET_OPTION,
RDMA_USER_CM_CMD_NOTIFY,
- RDMA_USER_CM_CMD_JOIN_MCAST,
+ RDMA_USER_CM_CMD_JOIN_IP_MCAST,
RDMA_USER_CM_CMD_LEAVE_MCAST,
RDMA_USER_CM_CMD_MIGRATE_ID,
RDMA_USER_CM_CMD_QUERY
@@ -96,13 +96,13 @@ struct rdma_ucm_destroy_id_resp {
__u32 events_reported;
};
-struct rdma_ucm_bind_addr {
+struct rdma_ucm_bind_ip {
__u64 response;
struct sockaddr_in6 addr;
__u32 id;
};
-struct rdma_ucm_resolve_addr {
+struct rdma_ucm_resolve_ip {
struct sockaddr_in6 src_addr;
struct sockaddr_in6 dst_addr;
__u32 id;
@@ -216,7 +216,7 @@ struct rdma_ucm_notify {
__u32 event;
};
-struct rdma_ucm_join_mcast {
+struct rdma_ucm_join_ip_mcast {
__u64 response; /* rdma_ucm_create_id_resp */
__u64 uid;
struct sockaddr_in6 addr;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 22/26] rdma/ucm: add ability to query GID addresses
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Part of address resolution is mapping IP addresses to IB GIDs.
With the changes to support querying larger addresses and more
path records, also provide a way to query IB GIDs after
resolution completes.
This optimizes querying for IB GIDs
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 50 ++++++++++++++++++++++++++++++++++++++++
include/rdma/rdma_user_cm.h | 3 ++
2 files changed, 52 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 5d8d68e..82eb1ac 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -45,6 +45,7 @@
#include <rdma/rdma_cm.h>
#include <rdma/rdma_cm_ib.h>
#include <rdma/ib_addr.h>
+#include <rdma/ib.h>
MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access");
@@ -728,6 +729,52 @@ static ssize_t ucma_query_path(struct ucma_context *ctx,
return ret;
}
+static ssize_t ucma_query_gid(struct ucma_context *ctx,
+ void __user *response, int out_len)
+{
+ struct rdma_ucm_query_addr_resp resp;
+ struct sockaddr_ib *addr;
+ int ret = 0;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ memset(&resp, 0, sizeof resp);
+
+ ucma_query_device_addr(ctx->cm_id, &resp);
+
+ addr = (struct sockaddr_ib *) &resp.src_addr;
+ resp.src_size = sizeof(*addr);
+ if (ctx->cm_id->route.addr.src_addr.ss_family == AF_IB) {
+ memcpy(addr, &ctx->cm_id->route.addr.src_addr, resp.src_size);
+ } else {
+ addr->sib_family = AF_IB;
+ addr->sib_pkey = (__force __be16) resp.pkey;
+ rdma_addr_get_sgid(&ctx->cm_id->route.addr.dev_addr,
+ (union ib_gid *) &addr->sib_addr);
+ addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *)
+ &ctx->cm_id->route.addr.src_addr);
+ }
+
+ addr = (struct sockaddr_ib *) &resp.dst_addr;
+ resp.dst_size = sizeof(*addr);
+ if (ctx->cm_id->route.addr.dst_addr.ss_family == AF_IB) {
+ memcpy(addr, &ctx->cm_id->route.addr.dst_addr, resp.dst_size);
+ } else {
+ addr->sib_family = AF_IB;
+ addr->sib_pkey = (__force __be16) resp.pkey;
+ rdma_addr_get_dgid(&ctx->cm_id->route.addr.dev_addr,
+ (union ib_gid *) &addr->sib_addr);
+ addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *)
+ &ctx->cm_id->route.addr.dst_addr);
+ }
+
+ if (copy_to_user(response, &resp, sizeof(resp)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
static ssize_t ucma_query(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
@@ -752,6 +799,9 @@ static ssize_t ucma_query(struct ucma_file *file,
case RDMA_USER_CM_QUERY_PATH:
ret = ucma_query_path(ctx, response, out_len);
break;
+ case RDMA_USER_CM_QUERY_GID:
+ ret = ucma_query_gid(ctx, response, out_len);
+ break;
default:
ret = -ENOSYS;
break;
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index 7784203..95bb515 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -116,7 +116,8 @@ struct rdma_ucm_resolve_route {
enum {
RDMA_USER_CM_QUERY_ADDR,
- RDMA_USER_CM_QUERY_PATH
+ RDMA_USER_CM_QUERY_PATH,
+ RDMA_USER_CM_QUERY_GID
};
struct rdma_ucm_query {
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 24/26] rdma/ucm: allow user space to bind to AF_IB
From: Sean Hefty @ 2010-04-01 17:08 UTC (permalink / raw)
To: Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA
Support user space binding to addresses using AF_IB. Since
sockaddr_ib is larger than sockaddr_in6, we need to define
a larger structure when binding using AF_IB. This time we
use sockaddr_storage to cover future cases.
Signed-off-by: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 27 ++++++++++++++++++++++++++-
include/rdma/rdma_user_cm.h | 10 +++++++++-
2 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 6456502..aa50080 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -536,6 +536,30 @@ static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf,
return ret;
}
+static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf,
+ int in_len, int out_len)
+{
+ struct rdma_ucm_bind cmd;
+ struct sockaddr *addr;
+ struct ucma_context *ctx;
+ int ret;
+
+ if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
+ return -EFAULT;
+
+ addr = (struct sockaddr *) &cmd.addr;
+ if (cmd.reserved || !cmd.addr_size || (cmd.addr_size != rdma_addr_size(addr)))
+ return -EINVAL;
+
+ ctx = ucma_get_ctx(file, cmd.id);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ ret = rdma_bind_addr(ctx->cm_id, addr);
+ ucma_put_ctx(ctx);
+ return ret;
+}
+
static ssize_t ucma_resolve_ip(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
@@ -1330,7 +1354,8 @@ static ssize_t (*ucma_cmd_table[])(struct ucma_file *file,
[RDMA_USER_CM_CMD_JOIN_IP_MCAST] = ucma_join_ip_multicast,
[RDMA_USER_CM_CMD_LEAVE_MCAST] = ucma_leave_multicast,
[RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id,
- [RDMA_USER_CM_CMD_QUERY] = ucma_query
+ [RDMA_USER_CM_CMD_QUERY] = ucma_query,
+ [RDMA_USER_CM_CMD_BIND] = ucma_bind
};
static ssize_t ucma_write(struct file *filp, const char __user *buf,
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index c1e0ac9..375f2a9 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -62,7 +62,8 @@ enum {
RDMA_USER_CM_CMD_JOIN_IP_MCAST,
RDMA_USER_CM_CMD_LEAVE_MCAST,
RDMA_USER_CM_CMD_MIGRATE_ID,
- RDMA_USER_CM_CMD_QUERY
+ RDMA_USER_CM_CMD_QUERY,
+ RDMA_USER_CM_CMD_BIND
};
/*
@@ -102,6 +103,13 @@ struct rdma_ucm_bind_ip {
__u32 id;
};
+struct rdma_ucm_bind {
+ __u32 id;
+ __u16 addr_size;
+ __u16 reserved;
+ struct sockaddr_storage addr;
+};
+
struct rdma_ucm_resolve_ip {
struct sockaddr_in6 src_addr;
struct sockaddr_in6 dst_addr;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox