* [PATCH V4 1/9] IB/core: Ethernet L2 attributes in verbs/cm structures
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 2/9] IB/CMA: RoCE IP based GID addressing Or Gerlitz
` (7 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
This patch add the support for Ethernet L2 attributes in the
verbs/cm/cma structures.
When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority
in a similar manner that the IB L2 (and the L4 PKEY) attributes are used.
Thus, those attributes were added to the following structures:
* ib_ah_attr - added dmac
* ib_qp_attr - added smac and vlan_id, (sl remains vlan priority)
* ib_wc - added smac, vlan_id
* ib_sa_path_rec - added smac, dmac, vlan_id
* cm_av - added smac and vlan_id
For the path record structure, extra care was taken to avoid the new fields when
packing it into wire format, to avoiding breaking the IB CM and SA wire protocol.
On the active side, the CM fill its internal structures from the path provided
by the ULP, added there taking the ETH L2 attributes and placing them into
the CM Address Handle (struct cm_av).
On the passive side, the CM fills its internal structures from the WC associated
with the REQ message, added there taking the ETH L2 attributes from the WC.
When the HW driver provides the required ETH L2 attributes in the WC, they
set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks
for the presence of these flags, and in their absence does address
resolution from the ib_init_ah_from_wc helper function.
ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters
are mandatory for Ethernet link layer, while they are irrelevant for IB.
Vendor drivers are modified to support the new function signature.
Signed-off-by: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/addr.c | 97 ++++++++++++++++++++++++++-
drivers/infiniband/core/cm.c | 55 +++++++++++++++
drivers/infiniband/core/cma.c | 60 +++++++++++++++--
drivers/infiniband/core/sa_query.c | 12 +++-
drivers/infiniband/core/verbs.c | 45 ++++++++++++-
drivers/infiniband/hw/ehca/ehca_qp.c | 2 +-
drivers/infiniband/hw/ipath/ipath_qp.c | 2 +-
drivers/infiniband/hw/mlx4/qp.c | 9 ++-
drivers/infiniband/hw/mlx5/qp.c | 3 +-
drivers/infiniband/hw/mthca/mthca_qp.c | 3 +-
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 3 +-
drivers/infiniband/hw/qib/qib_qp.c | 2 +-
include/linux/mlx4/device.h | 1 +
include/rdma/ib_addr.h | 42 +++++++++++-
include/rdma/ib_cm.h | 1 +
include/rdma/ib_pack.h | 1 +
include/rdma/ib_sa.h | 3 +
include/rdma/ib_verbs.h | 23 ++++++-
18 files changed, 340 insertions(+), 24 deletions(-)
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index e90f2b2..8172d37 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -86,6 +86,8 @@ int rdma_addr_size(struct sockaddr *addr)
}
EXPORT_SYMBOL(rdma_addr_size);
+static struct rdma_addr_client self;
+
void rdma_addr_register_client(struct rdma_addr_client *client)
{
atomic_set(&client->refcount, 1);
@@ -119,7 +121,8 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
}
EXPORT_SYMBOL(rdma_copy_addr);
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+ u16 *vlan_id)
{
struct net_device *dev;
int ret = -EADDRNOTAVAIL;
@@ -142,6 +145,8 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
return ret;
ret = rdma_copy_addr(dev_addr, dev, NULL);
+ if (vlan_id)
+ *vlan_id = rdma_vlan_dev_vlan_id(dev);
dev_put(dev);
break;
@@ -153,6 +158,8 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
&((struct sockaddr_in6 *) addr)->sin6_addr,
dev, 1)) {
ret = rdma_copy_addr(dev_addr, dev, NULL);
+ if (vlan_id)
+ *vlan_id = rdma_vlan_dev_vlan_id(dev);
break;
}
}
@@ -238,7 +245,7 @@ static int addr4_resolve(struct sockaddr_in *src_in,
src_in->sin_addr.s_addr = fl4.saddr;
if (rt->dst.dev->flags & IFF_LOOPBACK) {
- ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
+ ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL);
if (!ret)
memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
goto put;
@@ -286,7 +293,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
}
if (dst->dev->flags & IFF_LOOPBACK) {
- ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
+ ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL);
if (!ret)
memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
goto put;
@@ -437,6 +444,88 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr)
}
EXPORT_SYMBOL(rdma_addr_cancel);
+struct resolve_cb_context {
+ struct rdma_dev_addr *addr;
+ struct completion comp;
+};
+
+static void resolve_cb(int status, struct sockaddr *src_addr,
+ struct rdma_dev_addr *addr, void *context)
+{
+ memcpy(((struct resolve_cb_context *)context)->addr, addr, sizeof(struct
+ rdma_dev_addr));
+ complete(&((struct resolve_cb_context *)context)->comp);
+}
+
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
+ u16 *vlan_id)
+{
+ int ret = 0;
+ struct rdma_dev_addr dev_addr;
+ struct resolve_cb_context ctx;
+ struct net_device *dev;
+
+ union {
+ struct sockaddr _sockaddr;
+ struct sockaddr_in _sockaddr_in;
+ struct sockaddr_in6 _sockaddr_in6;
+ } sgid_addr, dgid_addr;
+
+
+ ret = rdma_gid2ip(&sgid_addr._sockaddr, sgid);
+ if (ret)
+ return ret;
+
+ ret = rdma_gid2ip(&dgid_addr._sockaddr, dgid);
+ if (ret)
+ return ret;
+
+ memset(&dev_addr, 0, sizeof(dev_addr));
+
+ ctx.addr = &dev_addr;
+ init_completion(&ctx.comp);
+ ret = rdma_resolve_ip(&self, &sgid_addr._sockaddr, &dgid_addr._sockaddr,
+ &dev_addr, 1000, resolve_cb, &ctx);
+ if (ret)
+ return ret;
+
+ wait_for_completion(&ctx.comp);
+
+ memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
+ dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if);
+ if (!dev)
+ return -ENODEV;
+ if (vlan_id)
+ *vlan_id = rdma_vlan_dev_vlan_id(dev);
+ dev_put(dev);
+ return ret;
+}
+EXPORT_SYMBOL(rdma_addr_find_dmac_by_grh);
+
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
+{
+ int ret = 0;
+ struct rdma_dev_addr dev_addr;
+ union {
+ struct sockaddr _sockaddr;
+ struct sockaddr_in _sockaddr_in;
+ struct sockaddr_in6 _sockaddr_in6;
+ } gid_addr;
+
+ ret = rdma_gid2ip(&gid_addr._sockaddr, sgid);
+
+ if (ret)
+ return ret;
+ memset(&dev_addr, 0, sizeof(dev_addr));
+ ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
+ if (ret)
+ return ret;
+
+ memcpy(smac, dev_addr.src_dev_addr, ETH_ALEN);
+ return ret;
+}
+EXPORT_SYMBOL(rdma_addr_find_smac_by_sgid);
+
static int netevent_callback(struct notifier_block *self, unsigned long event,
void *ctx)
{
@@ -461,11 +550,13 @@ static int __init addr_init(void)
return -ENOMEM;
register_netevent_notifier(&nb);
+ rdma_addr_register_client(&self);
return 0;
}
static void __exit addr_cleanup(void)
{
+ rdma_addr_unregister_client(&self);
unregister_netevent_notifier(&nb);
destroy_workqueue(addr_wq);
}
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 784b97c..a67b689 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -47,6 +47,7 @@
#include <linux/sysfs.h>
#include <linux/workqueue.h>
#include <linux/kdev_t.h>
+#include <linux/etherdevice.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_cm.h>
@@ -177,6 +178,8 @@ struct cm_av {
struct ib_ah_attr ah_attr;
u16 pkey_index;
u8 timeout;
+ u8 valid;
+ u8 smac[ETH_ALEN];
};
struct cm_work {
@@ -346,6 +349,23 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
grh, &av->ah_attr);
}
+int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac)
+{
+ struct cm_id_private *cm_id_priv;
+
+ cm_id_priv = container_of(id, struct cm_id_private, id);
+
+ if (smac != NULL)
+ memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac));
+
+ if (alt_smac != NULL)
+ memcpy(cm_id_priv->alt_av.smac, alt_smac,
+ sizeof(cm_id_priv->alt_av.smac));
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_update_cm_av);
+
static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
{
struct cm_device *cm_dev;
@@ -376,6 +396,9 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
ib_init_ah_from_path(cm_dev->ib_device, port->port_num, path,
&av->ah_attr);
av->timeout = path->packet_life_time + 1;
+ memcpy(av->smac, path->smac, sizeof(av->smac));
+
+ av->valid = 1;
return 0;
}
@@ -1557,6 +1580,9 @@ static int cm_req_handler(struct cm_work *work)
cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
+
+ memcpy(work->path[0].dmac, cm_id_priv->av.ah_attr.dmac, ETH_ALEN);
+ work->path[0].vlan_id = cm_id_priv->av.ah_attr.vlan_id;
ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
if (ret) {
ib_get_cached_gid(work->port->cm_dev->ib_device,
@@ -3503,6 +3529,35 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
*qp_attr_mask = IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU |
IB_QP_DEST_QPN | IB_QP_RQ_PSN;
qp_attr->ah_attr = cm_id_priv->av.ah_attr;
+ if (!cm_id_priv->av.valid)
+ return -EINVAL;
+ if (!is_zero_ether_addr(cm_id_priv->av.ah_attr.dmac))
+ *qp_attr_mask |= IB_QP_DEST_EX;
+ if (cm_id_priv->av.ah_attr.vlan_id != 0xffff) {
+ qp_attr->vlan_id = cm_id_priv->av.ah_attr.vlan_id;
+ *qp_attr_mask |= IB_QP_VID;
+ }
+ if (!is_zero_ether_addr(cm_id_priv->av.smac)) {
+ memcpy(qp_attr->smac, cm_id_priv->av.smac,
+ sizeof(qp_attr->smac));
+ *qp_attr_mask |= IB_QP_SMAC;
+ }
+ if (cm_id_priv->alt_av.valid) {
+ if (!is_zero_ether_addr(
+ cm_id_priv->alt_av.ah_attr.dmac))
+ *qp_attr_mask |= IB_QP_ALT_DEST_EX;
+ if (cm_id_priv->alt_av.ah_attr.vlan_id != 0xffff) {
+ qp_attr->alt_vlan_id =
+ cm_id_priv->alt_av.ah_attr.vlan_id;
+ *qp_attr_mask |= IB_QP_ALT_VID;
+ }
+ if (!is_zero_ether_addr(cm_id_priv->alt_av.smac)) {
+ memcpy(qp_attr->alt_smac,
+ cm_id_priv->alt_av.smac,
+ sizeof(qp_attr->alt_smac));
+ *qp_attr_mask |= IB_QP_ALT_SMAC;
+ }
+ }
qp_attr->path_mtu = cm_id_priv->path_mtu;
qp_attr->dest_qp_num = be32_to_cpu(cm_id_priv->remote_qpn);
qp_attr->rq_psn = be32_to_cpu(cm_id_priv->rq_psn);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 3a2c3c3..27acdec 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -362,7 +362,7 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
int ret;
if (addr->sa_family != AF_IB) {
- ret = rdma_translate_ip(addr, dev_addr);
+ ret = rdma_translate_ip(addr, dev_addr, NULL);
} else {
cma_translate_ib((struct sockaddr_ib *) addr, dev_addr);
ret = 0;
@@ -602,6 +602,7 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
+ union ib_gid sgid;
mutex_lock(&id_priv->qp_mutex);
if (!id_priv->id.qp) {
@@ -624,6 +625,20 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
if (ret)
goto out;
+ ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
+ qp_attr.ah_attr.grh.sgid_index, &sgid);
+ if (ret)
+ goto out;
+
+ if (rdma_node_get_transport(id_priv->cma_dev->device->node_type)
+ == RDMA_TRANSPORT_IB &&
+ rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
+ == IB_LINK_LAYER_ETHERNET) {
+ ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+
+ if (ret)
+ goto out;
+ }
if (conn_param)
qp_attr.max_dest_rd_atomic = conn_param->responder_resources;
ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
@@ -724,6 +739,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
else
ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
qp_attr_mask);
+
if (qp_attr->qp_state == IB_QPS_RTR)
qp_attr->rq_psn = id_priv->seq_num;
break;
@@ -1265,6 +1281,15 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
struct rdma_id_private *listen_id, *conn_id;
struct rdma_cm_event event;
int offset, ret;
+ u8 smac[ETH_ALEN];
+ u8 alt_smac[ETH_ALEN];
+ u8 *psmac = smac;
+ u8 *palt_smac = alt_smac;
+ int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==
+ RDMA_TRANSPORT_IB) &&
+ (rdma_port_get_link_layer(cm_id->device,
+ ib_event->param.req_rcvd.port) ==
+ IB_LINK_LAYER_ETHERNET));
listen_id = cm_id->context;
if (!cma_check_req_qp_type(&listen_id->id, ib_event))
@@ -1309,12 +1334,29 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
if (ret)
goto err3;
+ if (is_iboe) {
+ if (ib_event->param.req_rcvd.primary_path != NULL)
+ rdma_addr_find_smac_by_sgid(
+ &ib_event->param.req_rcvd.primary_path->sgid,
+ psmac, NULL);
+ else
+ psmac = NULL;
+ if (ib_event->param.req_rcvd.alternate_path != NULL)
+ rdma_addr_find_smac_by_sgid(
+ &ib_event->param.req_rcvd.alternate_path->sgid,
+ palt_smac, NULL);
+ else
+ palt_smac = NULL;
+ }
/*
* Acquire mutex to prevent user executing rdma_destroy_id()
* while we're accessing the cm_id.
*/
mutex_lock(&lock);
- if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
+ if (is_iboe)
+ ib_update_cm_av(cm_id, psmac, palt_smac);
+ if (cma_comp(conn_id, RDMA_CM_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);
@@ -1474,7 +1516,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
conn_id->state = RDMA_CM_CONNECT;
- ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr);
+ ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr, NULL);
if (ret) {
mutex_unlock(&conn_id->handler_mutex);
rdma_destroy_id(new_cm_id);
@@ -1855,7 +1897,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
struct cma_work *work;
int ret;
struct net_device *ndev = NULL;
- u16 vid;
+
work = kzalloc(sizeof *work, GFP_KERNEL);
if (!work)
@@ -1879,10 +1921,14 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
goto err2;
}
- vid = rdma_vlan_dev_vlan_id(ndev);
+ route->path_rec->vlan_id = rdma_vlan_dev_vlan_id(ndev);
+ memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN);
+ memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len);
- iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid);
- iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+ iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr,
+ route->path_rec->vlan_id);
+ iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr,
+ route->path_rec->vlan_id);
route->path_rec->hop_limit = 1;
route->path_rec->reversible = 1;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 9838ca4..f820958 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -42,7 +42,7 @@
#include <linux/kref.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
-
+#include <uapi/linux/if_ether.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_cache.h>
#include "sa.h"
@@ -556,6 +556,13 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
ah_attr->grh.hop_limit = rec->hop_limit;
ah_attr->grh.traffic_class = rec->traffic_class;
}
+ if (force_grh) {
+ memcpy(ah_attr->dmac, rec->dmac, ETH_ALEN);
+ ah_attr->vlan_id = rec->vlan_id;
+ } else {
+ ah_attr->vlan_id = 0xffff;
+ }
+
return 0;
}
EXPORT_SYMBOL(ib_init_ah_from_path);
@@ -670,6 +677,9 @@ static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
mad->data, &rec);
+ rec.vlan_id = 0xffff;
+ memset(rec.dmac, 0, ETH_ALEN);
+ memset(rec.smac, 0, ETH_ALEN);
query->callback(status, &rec, query->context);
} else
query->callback(status, NULL, query->context);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index a321df2..baab03d 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -44,6 +44,7 @@
#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>
+#include <rdma/ib_addr.h>
int ib_rate_to_mult(enum ib_rate rate)
{
@@ -189,8 +190,28 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
u32 flow_class;
u16 gid_index;
int ret;
+ int is_eth = (rdma_port_get_link_layer(device, port_num) ==
+ IB_LINK_LAYER_ETHERNET);
memset(ah_attr, 0, sizeof *ah_attr);
+ if (is_eth) {
+ if (!(wc->wc_flags & IB_WC_GRH))
+ return -EPROTOTYPE;
+
+ if (wc->wc_flags & IB_WC_WITH_SMAC &&
+ wc->wc_flags & IB_WC_WITH_VLAN) {
+ memcpy(ah_attr->dmac, wc->smac, ETH_ALEN);
+ ah_attr->vlan_id = wc->vlan_id;
+ } else {
+ ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
+ ah_attr->dmac, &ah_attr->vlan_id);
+ if (ret)
+ return ret;
+ }
+ } else {
+ ah_attr->vlan_id = 0xffff;
+ }
+
ah_attr->dlid = wc->slid;
ah_attr->sl = wc->sl;
ah_attr->src_path_bits = wc->dlid_path_bits;
@@ -473,7 +494,9 @@ EXPORT_SYMBOL(ib_create_qp);
static const struct {
int valid;
enum ib_qp_attr_mask req_param[IB_QPT_MAX];
+ enum ib_qp_attr_mask req_param_add_eth[IB_QPT_MAX];
enum ib_qp_attr_mask opt_param[IB_QPT_MAX];
+ enum ib_qp_attr_mask opt_param_add_eth[IB_QPT_MAX];
} qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
[IB_QPS_RESET] = {
[IB_QPS_RESET] = { .valid = 1 },
@@ -554,6 +577,10 @@ static const struct {
IB_QP_MAX_DEST_RD_ATOMIC |
IB_QP_MIN_RNR_TIMER),
},
+ .req_param_add_eth = {
+ [IB_QPT_RC] = (IB_QP_DEST_EX |
+ IB_QP_SMAC)
+ },
.opt_param = {
[IB_QPT_UD] = (IB_QP_PKEY_INDEX |
IB_QP_QKEY),
@@ -573,7 +600,13 @@ static const struct {
IB_QP_QKEY),
[IB_QPT_GSI] = (IB_QP_PKEY_INDEX |
IB_QP_QKEY),
- }
+ },
+ .opt_param_add_eth = {
+ [IB_QPT_RC] = (IB_QP_ALT_DEST_EX |
+ IB_QP_ALT_SMAC |
+ IB_QP_VID |
+ IB_QP_ALT_VID)
+ }
}
},
[IB_QPS_RTR] = {
@@ -776,7 +809,8 @@ static const struct {
};
int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
- enum ib_qp_type type, enum ib_qp_attr_mask mask)
+ enum ib_qp_type type, enum ib_qp_attr_mask mask,
+ enum rdma_link_layer ll)
{
enum ib_qp_attr_mask req_param, opt_param;
@@ -795,6 +829,13 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
req_param = qp_state_table[cur_state][next_state].req_param[type];
opt_param = qp_state_table[cur_state][next_state].opt_param[type];
+ if (ll == IB_LINK_LAYER_ETHERNET) {
+ req_param |= qp_state_table[cur_state][next_state].
+ req_param_add_eth[type];
+ opt_param |= qp_state_table[cur_state][next_state].
+ opt_param_add_eth[type];
+ }
+
if ((mask & req_param) != req_param)
return 0;
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index 00d6861..2e89356 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -1329,7 +1329,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
qp_new_state = attr_mask & IB_QP_STATE ? attr->qp_state : qp_cur_state;
if (!smi_reset2init &&
!ib_modify_qp_is_ok(qp_cur_state, qp_new_state, ibqp->qp_type,
- attr_mask)) {
+ attr_mask, IB_LINK_LAYER_UNSPECIFIED)) {
ret = -EINVAL;
ehca_err(ibqp->device,
"Invalid qp transition new_state=%x cur_state=%x "
diff --git a/drivers/infiniband/hw/ipath/ipath_qp.c b/drivers/infiniband/hw/ipath/ipath_qp.c
index 0857a9c..face876 100644
--- a/drivers/infiniband/hw/ipath/ipath_qp.c
+++ b/drivers/infiniband/hw/ipath/ipath_qp.c
@@ -463,7 +463,7 @@ int ipath_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
- attr_mask))
+ attr_mask, IB_LINK_LAYER_UNSPECIFIED))
goto inval;
if (attr_mask & IB_QP_AV) {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 4f10af2..da6f5fa 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1561,13 +1561,18 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
struct mlx4_ib_qp *qp = to_mqp(ibqp);
enum ib_qp_state cur_state, new_state;
int err = -EINVAL;
-
+ int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
mutex_lock(&qp->mutex);
cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
- if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+ if (cur_state == new_state && cur_state == IB_QPS_RESET)
+ p = IB_LINK_LAYER_UNSPECIFIED;
+
+ if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
+ attr_mask,
+ rdma_port_get_link_layer(&dev->ib_dev, p))) {
pr_debug("qpn 0x%x: invalid attribute mask specified "
"for transition %d to %d. qp_type %d,"
" attr_mask 0x%x\n",
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 045f8cd..50051a4 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1593,7 +1593,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
- !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+ !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+ IB_LINK_LAYER_UNSPECIFIED))
goto out;
if ((attr_mask & IB_QP_PORT) &&
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 26a6845..e354b2f 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -860,7 +860,8 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
- if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+ if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+ IB_LINK_LAYER_UNSPECIFIED)) {
mthca_dbg(dev, "Bad QP transition (transport %d) "
"%d->%d with attr 0x%08x\n",
qp->transport, cur_state, new_state,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 6e982bb..0607ca7 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1326,7 +1326,8 @@ int ocrdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
new_qps = old_qps;
spin_unlock_irqrestore(&qp->q_lock, flags);
- if (!ib_modify_qp_is_ok(old_qps, new_qps, ibqp->qp_type, attr_mask)) {
+ if (!ib_modify_qp_is_ok(old_qps, new_qps, ibqp->qp_type, attr_mask,
+ IB_LINK_LAYER_UNSPECIFIED)) {
pr_err("%s(%d) invalid attribute mask=0x%x specified for\n"
"qpn=0x%x of type=0x%x old_qps=0x%x, new_qps=0x%x\n",
__func__, dev->id, attr_mask, qp->id, ibqp->qp_type,
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 3cca55b..0cad0c4 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -585,7 +585,7 @@ int qib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
- attr_mask))
+ attr_mask, IB_LINK_LAYER_UNSPECIFIED))
goto inval;
if (attr_mask & IB_QP_AV) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d73423c..4b9162c 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1074,6 +1074,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
u8 *pg, u16 *ratelimit);
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index);
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index f3ac0f2..a071560 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -42,6 +42,7 @@
#include <linux/if_vlan.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_pack.h>
+#include <net/ipv6.h>
struct rdma_addr_client {
atomic_t refcount;
@@ -72,7 +73,8 @@ struct rdma_dev_addr {
* rdma_translate_ip - Translate a local IP address to an RDMA hardware
* address.
*/
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr);
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+ u16 *vlan_id);
/**
* rdma_resolve_ip - Resolve source and destination IP addresses to
@@ -104,6 +106,10 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
int rdma_addr_size(struct sockaddr *addr);
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
+ u16 *vlan_id);
+
static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
{
return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9];
@@ -142,6 +148,40 @@ static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
gid->raw[8] ^= 2;
}
+static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
+{
+ switch (addr->sa_family) {
+ case AF_INET:
+ ipv6_addr_set_v4mapped(((struct sockaddr_in *)
+ addr)->sin_addr.s_addr,
+ (struct in6_addr *)gid);
+ break;
+ case AF_INET6:
+ memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
+static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
+{
+ if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
+ struct sockaddr_in *out_in = (struct sockaddr_in *)out;
+ memset(out_in, 0, sizeof(*out_in));
+ out_in->sin_family = AF_INET;
+ memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4);
+ } else {
+ struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out;
+ memset(out_in, 0, sizeof(*out_in));
+ out_in->sin6_family = AF_INET6;
+ memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
+ }
+ return 0;
+}
+
static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
{
return dev->priv_flags & IFF_802_1Q_VLAN ?
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 0e3ff30..f29e3a2 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -601,4 +601,5 @@ struct ib_cm_sidr_rep_param {
int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
struct ib_cm_sidr_rep_param *param);
+int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac);
#endif /* IB_CM_H */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index b37fe3b..b1f7592 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -34,6 +34,7 @@
#define IB_PACK_H
#include <rdma/ib_verbs.h>
+#include <uapi/linux/if_ether.h>
enum {
IB_LRH_BYTES = 8,
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 125f871..7e071a6 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -154,6 +154,9 @@ struct ib_sa_path_rec {
u8 packet_life_time_selector;
u8 packet_life_time;
u8 preference;
+ u8 smac[ETH_ALEN];
+ u8 dmac[ETH_ALEN];
+ u16 vlan_id;
};
#define IB_SA_MCMEMBER_REC_MGID IB_SA_COMP_MASK( 0)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e393171..c8a61f8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -48,6 +48,7 @@
#include <linux/rwsem.h>
#include <linux/scatterlist.h>
#include <linux/workqueue.h>
+#include <uapi/linux/if_ether.h>
#include <linux/atomic.h>
#include <asm/uaccess.h>
@@ -470,6 +471,8 @@ struct ib_ah_attr {
u8 static_rate;
u8 ah_flags;
u8 port_num;
+ u8 dmac[ETH_ALEN];
+ u16 vlan_id;
};
enum ib_wc_status {
@@ -522,6 +525,8 @@ enum ib_wc_flags {
IB_WC_WITH_IMM = (1<<1),
IB_WC_WITH_INVALIDATE = (1<<2),
IB_WC_IP_CSUM_OK = (1<<3),
+ IB_WC_WITH_SMAC = (1<<4),
+ IB_WC_WITH_VLAN = (1<<5),
};
struct ib_wc {
@@ -542,6 +547,8 @@ struct ib_wc {
u8 sl;
u8 dlid_path_bits;
u8 port_num; /* valid only for DR SMPs on switches */
+ u8 smac[ETH_ALEN];
+ u16 vlan_id;
};
enum ib_cq_notify_flags {
@@ -719,7 +726,13 @@ enum ib_qp_attr_mask {
IB_QP_MAX_DEST_RD_ATOMIC = (1<<17),
IB_QP_PATH_MIG_STATE = (1<<18),
IB_QP_CAP = (1<<19),
- IB_QP_DEST_QPN = (1<<20)
+ IB_QP_DEST_QPN = (1<<20),
+ IB_QP_DEST_EX = (1<<21),
+ IB_QP_ALT_DEST_EX = (1<<22),
+ IB_QP_SMAC = (1<<23),
+ IB_QP_ALT_SMAC = (1<<24),
+ IB_QP_VID = (1<<25),
+ IB_QP_ALT_VID = (1<<26),
};
enum ib_qp_state {
@@ -769,6 +782,10 @@ struct ib_qp_attr {
u8 rnr_retry;
u8 alt_port_num;
u8 alt_timeout;
+ u8 smac[ETH_ALEN];
+ u8 alt_smac[ETH_ALEN];
+ u16 vlan_id;
+ u16 alt_vlan_id;
};
enum ib_wr_opcode {
@@ -1485,6 +1502,7 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
* @next_state: Next QP state
* @type: QP type
* @mask: Mask of supplied QP attributes
+ * @ll : link layer of port
*
* This function is a helper function that a low-level driver's
* modify_qp method can use to validate the consumer's input. It
@@ -1493,7 +1511,8 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
* and that the attribute mask supplied is allowed for the transition.
*/
int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
- enum ib_qp_type type, enum ib_qp_attr_mask mask);
+ enum ib_qp_type type, enum ib_qp_attr_mask mask,
+ enum rdma_link_layer ll);
int ib_register_event_handler (struct ib_event_handler *event_handler);
int ib_unregister_event_handler(struct ib_event_handler *event_handler);
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 2/9] IB/CMA: RoCE IP based GID addressing
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-09-10 14:41 ` [PATCH V4 1/9] IB/core: Ethernet L2 attributes in verbs/cm structures Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 3/9] IB/mlx4: Use RoCE IP based GIDs in the port GID table Or Gerlitz
` (6 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Currently, the IB core and specifically the RDMA-CM assumes that
RoCE (IBoE) gids encode related Ethernet netdevice interface
MAC address and possibly VLAN id.
Change gids to be treated as they encode interface IP address.
Since Ethernet layer 2 address parameters are not longer encoded
within gids, had to extend the Infiniband address structures (e.g.
ib_ah_attr) with layer 2 address parameters, namely mac and vlan.
Signed-off-by: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 22 +++++++++--------
drivers/infiniband/core/ucma.c | 18 +++-----------
include/rdma/ib_addr.h | 50 +++++++++------------------------------
3 files changed, 28 insertions(+), 62 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 27acdec..2497031 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -386,7 +386,9 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv)
return -EINVAL;
mutex_lock(&lock);
- iboe_addr_get_sgid(dev_addr, &iboe_gid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &iboe_gid);
+
memcpy(&gid, dev_addr->src_dev_addr +
rdma_addr_gid_offset(dev_addr), sizeof gid);
list_for_each_entry(cma_dev, &dev_list, list) {
@@ -1925,10 +1927,10 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN);
memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len);
- iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr,
- route->path_rec->vlan_id);
- iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr,
- route->path_rec->vlan_id);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &route->path_rec->sgid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr,
+ &route->path_rec->dgid);
route->path_rec->hop_limit = 1;
route->path_rec->reversible = 1;
@@ -2095,6 +2097,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
RDMA_CM_ADDR_RESOLVED))
goto out;
+ memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
if (!status && !id_priv->cma_dev)
status = cma_acquire_dev(id_priv);
@@ -2104,10 +2107,8 @@ static void addr_handler(int status, struct sockaddr *src_addr,
goto out;
event.event = RDMA_CM_EVENT_ADDR_ERROR;
event.status = status;
- } else {
- memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
+ } else
event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
- }
if (id_priv->id.event_handler(&id_priv->id, &event)) {
cma_exch(id_priv, RDMA_CM_DESTROYING);
@@ -2588,6 +2589,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
if (ret)
goto err1;
+ memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
if (!cma_any_addr(addr)) {
ret = cma_translate_addr(addr, &id->route.addr.dev_addr);
if (ret)
@@ -2598,7 +2600,6 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
goto err1;
}
- memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) {
if (addr->sa_family == AF_INET)
id_priv->afonly = 1;
@@ -3327,7 +3328,8 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
err = -EINVAL;
goto out2;
}
- iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &mc->multicast.ib->rec.port_gid);
work->id = id_priv;
work->mc = mc;
INIT_WORK(&work->work, iboe_mcast_work_handler);
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index b0f189b..7e7da86 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -655,24 +655,14 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
struct rdma_route *route)
{
- struct rdma_dev_addr *dev_addr;
- struct net_device *dev;
- u16 vid = 0;
resp->num_paths = route->num_paths;
switch (route->num_paths) {
case 0:
- dev_addr = &route->addr.dev_addr;
- dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
- if (dev) {
- vid = rdma_vlan_dev_vlan_id(dev);
- dev_put(dev);
- }
-
- iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
- dev_addr->dst_dev_addr, vid);
- iboe_addr_get_sgid(dev_addr,
- (union ib_gid *) &resp->ib_route[0].sgid);
+ rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
+ (union ib_gid *)&resp->ib_route[0].dgid);
+ rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
+ (union ib_gid *)&resp->ib_route[0].sgid);
resp->ib_route[0].pkey = cpu_to_be16(0xffff);
break;
case 2:
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index a071560..53f81fb 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -38,8 +38,12 @@
#include <linux/in6.h>
#include <linux/if_arp.h>
#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
#include <linux/socket.h>
#include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_pack.h>
#include <net/ipv6.h>
@@ -132,20 +136,10 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
}
-static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
+static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
{
- memset(gid->raw, 0, 16);
- *((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
- if (vid < 0x1000) {
- gid->raw[12] = vid & 0xff;
- gid->raw[11] = vid >> 8;
- } else {
- gid->raw[12] = 0xfe;
- gid->raw[11] = 0xff;
- }
- memcpy(gid->raw + 13, mac + 3, 3);
- memcpy(gid->raw + 8, mac, 3);
- gid->raw[8] ^= 2;
+ return dev->priv_flags & IFF_802_1Q_VLAN ?
+ vlan_dev_vlan_id(dev) : 0xffff;
}
static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
@@ -182,25 +176,20 @@ static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
return 0;
}
-static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
-{
- return dev->priv_flags & IFF_802_1Q_VLAN ?
- vlan_dev_vlan_id(dev) : 0xffff;
-}
-
static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
union ib_gid *gid)
{
struct net_device *dev;
- u16 vid = 0xffff;
+ struct in_device *ip4;
dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
if (dev) {
- vid = rdma_vlan_dev_vlan_id(dev);
+ ip4 = (struct in_device *)dev->ip_ptr;
+ if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
+ ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
+ (struct in6_addr *)gid);
dev_put(dev);
}
-
- iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
}
static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -284,13 +273,6 @@ static inline int rdma_link_local_addr(struct in6_addr *addr)
return 0;
}
-static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
-{
- memcpy(mac, &addr->s6_addr[8], 3);
- memcpy(mac + 3, &addr->s6_addr[13], 3);
- mac[0] ^= 2;
-}
-
static inline int rdma_is_multicast_addr(struct in6_addr *addr)
{
return addr->s6_addr[0] == 0xff;
@@ -306,14 +288,6 @@ static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
mac[i] = addr->s6_addr[i + 10];
}
-static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
-{
- u16 vid;
-
- vid = dgid->raw[11] << 8 | dgid->raw[12];
- return vid < 0x1000 ? vid : 0xffff;
-}
-
static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
{
return dev->priv_flags & IFF_802_1Q_VLAN ?
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 3/9] IB/mlx4: Use RoCE IP based GIDs in the port GID table
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-09-10 14:41 ` [PATCH V4 1/9] IB/core: Ethernet L2 attributes in verbs/cm structures Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 2/9] IB/CMA: RoCE IP based GID addressing Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 4/9] IB/mlx4: Handle Ethernet L2 parameters for IP based GID addressing Or Gerlitz
` (5 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Currently, the mlx4 driver set RoCE (IBoE) gids to encode related
Ethernet netdevice interface MAC address and possibly VLAN id.
Change this scheme such that gids encode interface IP addresses
(both IP4 and IPv6).
This requires learning which are the IP addresses which are of use
by a netdevice associated with the HCA port, formatting them to gids
and adding them to the port gid table. Further, events of add and
delete address are caught to maintain the gid table accordingly.
Associated IP addresses may belong to a master of an Ethernet netdevice
on top of that port so this should be considered when building and
maintaining the gid table.
Signed-off-by: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/main.c | 474 ++++++++++++++++++++++++----------
drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 +
2 files changed, 334 insertions(+), 143 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index d6c5a73..7a29ad5 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -39,6 +39,8 @@
#include <linux/inetdevice.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_user_verbs.h>
@@ -790,7 +792,6 @@ static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
union ib_gid *gid)
{
- u8 mac[6];
struct net_device *ndev;
int ret = 0;
@@ -804,11 +805,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
spin_unlock(&mdev->iboe.lock);
if (ndev) {
- rdma_get_mcast_mac((struct in6_addr *)gid, mac);
- rtnl_lock();
- dev_mc_add(mdev->iboe.netdevs[mqp->port - 1], mac);
ret = 1;
- rtnl_unlock();
dev_put(ndev);
}
@@ -1031,6 +1028,8 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
struct mlx4_ib_qp *mqp = to_mqp(ibqp);
u64 reg_id;
struct mlx4_ib_steering *ib_steering = NULL;
+ enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+ MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
if (mdev->dev->caps.steering_mode ==
MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1042,7 +1041,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
!!(mqp->flags &
MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
- MLX4_PROT_IB_IPV6, ®_id);
+ prot, ®_id);
if (err)
goto err_malloc;
@@ -1061,7 +1060,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
err_add:
mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
- MLX4_PROT_IB_IPV6, reg_id);
+ prot, reg_id);
err_malloc:
kfree(ib_steering);
@@ -1089,10 +1088,11 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
int err;
struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
struct mlx4_ib_qp *mqp = to_mqp(ibqp);
- u8 mac[6];
struct net_device *ndev;
struct mlx4_ib_gid_entry *ge;
u64 reg_id = 0;
+ enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+ MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
if (mdev->dev->caps.steering_mode ==
MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1115,7 +1115,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
}
err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
- MLX4_PROT_IB_IPV6, reg_id);
+ prot, reg_id);
if (err)
return err;
@@ -1127,13 +1127,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
if (ndev)
dev_hold(ndev);
spin_unlock(&mdev->iboe.lock);
- rdma_get_mcast_mac((struct in6_addr *)gid, mac);
- if (ndev) {
- rtnl_lock();
- dev_mc_del(mdev->iboe.netdevs[ge->port - 1], mac);
- rtnl_unlock();
+ if (ndev)
dev_put(ndev);
- }
list_del(&ge->list);
kfree(ge);
} else
@@ -1229,20 +1224,6 @@ static struct device_attribute *mlx4_class_attributes[] = {
&dev_attr_board_id
};
-static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, struct net_device *dev)
-{
- memcpy(eui, dev->dev_addr, 3);
- memcpy(eui + 5, dev->dev_addr + 3, 3);
- if (vlan_id < 0x1000) {
- eui[3] = vlan_id >> 8;
- eui[4] = vlan_id & 0xff;
- } else {
- eui[3] = 0xff;
- eui[4] = 0xfe;
- }
- eui[0] ^= 2;
-}
-
static void update_gids_task(struct work_struct *work)
{
struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
@@ -1265,161 +1246,318 @@ static void update_gids_task(struct work_struct *work)
MLX4_CMD_WRAPPED);
if (err)
pr_warn("set port command failed\n");
- else {
- memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
+ else
mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
- }
mlx4_free_cmd_mailbox(dev, mailbox);
kfree(gw);
}
-static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear)
+static void reset_gids_task(struct work_struct *work)
{
- struct net_device *ndev = dev->iboe.netdevs[port - 1];
- struct update_gid_work *work;
- struct net_device *tmp;
+ struct update_gid_work *gw =
+ container_of(work, struct update_gid_work, work);
+ struct mlx4_cmd_mailbox *mailbox;
+ union ib_gid *gids;
+ int err;
int i;
- u8 *hits;
- int ret;
- union ib_gid gid;
- int free;
- int found;
- int need_update = 0;
- u16 vid;
+ struct mlx4_dev *dev = gw->dev->dev;
- work = kzalloc(sizeof *work, GFP_ATOMIC);
- if (!work)
- return -ENOMEM;
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ pr_warn("reset gid table failed\n");
+ goto free;
+ }
- hits = kzalloc(128, GFP_ATOMIC);
- if (!hits) {
- ret = -ENOMEM;
- goto out;
+ gids = mailbox->buf;
+ memcpy(gids, gw->gids, sizeof(gw->gids));
+
+ for (i = 1; i < gw->dev->num_ports + 1; i++) {
+ if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) ==
+ IB_LINK_LAYER_ETHERNET) {
+ err = mlx4_cmd(dev, mailbox->dma,
+ MLX4_SET_PORT_GID_TABLE << 8 | i,
+ 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+ if (err)
+ pr_warn(KERN_WARNING
+ "set port %d command failed\n", i);
+ }
}
- rcu_read_lock();
- for_each_netdev_rcu(&init_net, tmp) {
- if (ndev && (tmp == ndev || rdma_vlan_dev_real_dev(tmp) == ndev)) {
- gid.global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
- vid = rdma_vlan_dev_vlan_id(tmp);
- mlx4_addrconf_ifid_eui48(&gid.raw[8], vid, ndev);
- found = 0;
- free = -1;
- for (i = 0; i < 128; ++i) {
- if (free < 0 &&
- !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
- free = i;
- if (!memcmp(&dev->iboe.gid_table[port - 1][i], &gid, sizeof gid)) {
- hits[i] = 1;
- found = 1;
- break;
- }
- }
+ mlx4_free_cmd_mailbox(dev, mailbox);
+free:
+ kfree(gw);
+}
- if (!found) {
- if (tmp == ndev &&
- (memcmp(&dev->iboe.gid_table[port - 1][0],
- &gid, sizeof gid) ||
- !memcmp(&dev->iboe.gid_table[port - 1][0],
- &zgid, sizeof gid))) {
- dev->iboe.gid_table[port - 1][0] = gid;
- ++need_update;
- hits[0] = 1;
- } else if (free >= 0) {
- dev->iboe.gid_table[port - 1][free] = gid;
- hits[free] = 1;
- ++need_update;
- }
+static int update_gid_table(struct mlx4_ib_dev *dev, int port,
+ union ib_gid *gid, int clear)
+{
+ struct update_gid_work *work;
+ int i;
+ int need_update = 0;
+ int free = -1;
+ int found = -1;
+ int max_gids;
+
+ max_gids = dev->dev->caps.gid_table_len[port];
+ for (i = 0; i < max_gids; ++i) {
+ if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
+ sizeof(*gid)))
+ found = i;
+
+ if (clear) {
+ if (found >= 0) {
+ need_update = 1;
+ dev->iboe.gid_table[port - 1][found] = zgid;
+ break;
}
+ } else {
+ if (found >= 0)
+ break;
+
+ if (free < 0 &&
+ !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid,
+ sizeof(*gid)))
+ free = i;
}
}
- rcu_read_unlock();
- for (i = 0; i < 128; ++i)
- if (!hits[i]) {
- if (memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
- ++need_update;
- dev->iboe.gid_table[port - 1][i] = zgid;
- }
+ if (found == -1 && !clear && free >= 0) {
+ dev->iboe.gid_table[port - 1][free] = *gid;
+ need_update = 1;
+ }
- if (need_update) {
- memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof work->gids);
- INIT_WORK(&work->work, update_gids_task);
- work->port = port;
- work->dev = dev;
- queue_work(wq, &work->work);
- } else
- kfree(work);
+ if (!need_update)
+ return 0;
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return -ENOMEM;
+
+ memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof(work->gids));
+ INIT_WORK(&work->work, update_gids_task);
+ work->port = port;
+ work->dev = dev;
+ queue_work(wq, &work->work);
- kfree(hits);
return 0;
+}
-out:
- kfree(work);
- return ret;
+static int reset_gid_table(struct mlx4_ib_dev *dev)
+{
+ struct update_gid_work *work;
+
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return -ENOMEM;
+ memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table));
+ memset(work->gids, 0, sizeof(work->gids));
+ INIT_WORK(&work->work, reset_gids_task);
+ work->dev = dev;
+ queue_work(wq, &work->work);
+ return 0;
}
-static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event)
+static int mlx4_ib_addr_event(int event, struct net_device *event_netdev,
+ struct mlx4_ib_dev *ibdev, union ib_gid *gid)
{
- switch (event) {
- case NETDEV_UP:
- case NETDEV_CHANGEADDR:
- update_ipv6_gids(dev, port, 0);
- break;
+ struct mlx4_ib_iboe *iboe;
+ int port = 0;
+ struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
+ rdma_vlan_dev_real_dev(event_netdev) :
+ event_netdev;
+
+ if (event != NETDEV_DOWN && event != NETDEV_UP)
+ return 0;
+
+ if ((real_dev != event_netdev) &&
+ (event == NETDEV_DOWN) &&
+ rdma_link_local_addr((struct in6_addr *)gid))
+ return 0;
+
+ iboe = &ibdev->iboe;
+ spin_lock(&iboe->lock);
+
+ for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+ if ((netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->masters[port - 1])) ||
+ (!netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->netdevs[port - 1])))
+ update_gid_table(ibdev, port, gid,
+ event == NETDEV_DOWN);
+
+ spin_unlock(&iboe->lock);
+ return 0;
- case NETDEV_DOWN:
- update_ipv6_gids(dev, port, 1);
- dev->iboe.netdevs[port - 1] = NULL;
- }
}
-static void netdev_added(struct mlx4_ib_dev *dev, int port)
+static u8 mlx4_ib_get_dev_port(struct net_device *dev,
+ struct mlx4_ib_dev *ibdev)
{
- update_ipv6_gids(dev, port, 0);
+ u8 port = 0;
+ struct mlx4_ib_iboe *iboe;
+ struct net_device *real_dev = rdma_vlan_dev_real_dev(dev) ?
+ rdma_vlan_dev_real_dev(dev) : dev;
+
+ iboe = &ibdev->iboe;
+ spin_lock(&iboe->lock);
+
+ for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+ if ((netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->masters[port - 1])) ||
+ (!netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->netdevs[port - 1])))
+ break;
+
+ spin_unlock(&iboe->lock);
+
+ if ((port == 0) || (port > MLX4_MAX_PORTS))
+ return 0;
+ else
+ return port;
}
-static void netdev_removed(struct mlx4_ib_dev *dev, int port)
+static int mlx4_ib_inet_event(struct notifier_block *this, unsigned long event,
+ void *ptr)
{
- update_ipv6_gids(dev, port, 1);
+ struct mlx4_ib_dev *ibdev;
+ struct in_ifaddr *ifa = ptr;
+ union ib_gid gid;
+ struct net_device *event_netdev = ifa->ifa_dev->dev;
+
+ ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet);
+
+ mlx4_ib_addr_event(event, event_netdev, ibdev, &gid);
+ return NOTIFY_DONE;
}
-static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event,
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct mlx4_ib_dev *ibdev;
- struct net_device *oldnd;
+ struct inet6_ifaddr *ifa = ptr;
+ union ib_gid *gid = (union ib_gid *)&ifa->addr;
+ struct net_device *event_netdev = ifa->idev->dev;
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet6);
+
+ mlx4_ib_addr_event(event, event_netdev, ibdev, gid);
+ return NOTIFY_DONE;
+}
+#endif
+
+static void mlx4_ib_get_dev_addr(struct net_device *dev,
+ struct mlx4_ib_dev *ibdev, u8 port)
+{
+ struct in_device *in_dev;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct inet6_dev *in6_dev;
+ union ib_gid *pgid;
+ struct inet6_ifaddr *ifp;
+#endif
+ union ib_gid gid;
+
+
+ if ((port == 0) || (port > MLX4_MAX_PORTS))
+ return;
+
+ /* IPv4 gids */
+ in_dev = in_dev_get(dev);
+ if (in_dev) {
+ for_ifa(in_dev) {
+ /*ifa->ifa_address;*/
+ ipv6_addr_set_v4mapped(ifa->ifa_address,
+ (struct in6_addr *)&gid);
+ update_gid_table(ibdev, port, &gid, 0);
+ }
+ endfor_ifa(in_dev);
+ in_dev_put(in_dev);
+ }
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ /* IPv6 gids */
+ in6_dev = in6_dev_get(dev);
+ if (in6_dev) {
+ read_lock_bh(&in6_dev->lock);
+ list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
+ pgid = (union ib_gid *)&ifp->addr;
+ update_gid_table(ibdev, port, pgid, 0);
+ }
+ read_unlock_bh(&in6_dev->lock);
+ in6_dev_put(in6_dev);
+ }
+#endif
+}
+
+static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
+{
+ struct net_device *dev;
+
+ if (reset_gid_table(ibdev))
+ return -1;
+
+ read_lock(&dev_base_lock);
+
+ for_each_netdev(&init_net, dev) {
+ u8 port = mlx4_ib_get_dev_port(dev, ibdev);
+ if (port)
+ mlx4_ib_get_dev_addr(dev, ibdev, port);
+ }
+
+ read_unlock(&dev_base_lock);
+
+ return 0;
+}
+
+static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
+{
struct mlx4_ib_iboe *iboe;
int port;
- if (!net_eq(dev_net(dev), &init_net))
- return NOTIFY_DONE;
-
- ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
iboe = &ibdev->iboe;
spin_lock(&iboe->lock);
mlx4_foreach_ib_transport_port(port, ibdev->dev) {
- oldnd = iboe->netdevs[port - 1];
+ struct net_device *old_master = iboe->masters[port - 1];
+ struct net_device *curr_master;
iboe->netdevs[port - 1] =
mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
- if (oldnd != iboe->netdevs[port - 1]) {
- if (iboe->netdevs[port - 1])
- netdev_added(ibdev, port);
- else
- netdev_removed(ibdev, port);
+
+ if (iboe->netdevs[port - 1] &&
+ netif_is_bond_slave(iboe->netdevs[port - 1])) {
+ rtnl_lock();
+ iboe->masters[port - 1] = netdev_master_upper_dev_get(
+ iboe->netdevs[port - 1]);
+ rtnl_unlock();
}
- }
+ curr_master = iboe->masters[port - 1];
- if (dev == iboe->netdevs[0] ||
- (iboe->netdevs[0] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[0]))
- handle_en_event(ibdev, 1, event);
- else if (dev == iboe->netdevs[1]
- || (iboe->netdevs[1] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[1]))
- handle_en_event(ibdev, 2, event);
+ /* if bonding is used it is possible that we add it to masters
+ only after IP address is assigned to the net bonding
+ interface */
+ if (curr_master && (old_master != curr_master))
+ mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+ }
spin_unlock(&iboe->lock);
+}
+
+static int mlx4_ib_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct mlx4_ib_dev *ibdev;
+
+ if (!net_eq(dev_net(dev), &init_net))
+ return NOTIFY_DONE;
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
+ mlx4_ib_scan_netdevs(ibdev);
return NOTIFY_DONE;
}
@@ -1725,11 +1863,35 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
if (mlx4_ib_init_sriov(ibdev))
goto err_mad;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) {
- iboe->nb.notifier_call = mlx4_ib_netdev_event;
- err = register_netdevice_notifier(&iboe->nb);
- if (err)
- goto err_sriov;
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) {
+ if (!iboe->nb.notifier_call) {
+ iboe->nb.notifier_call = mlx4_ib_netdev_event;
+ err = register_netdevice_notifier(&iboe->nb);
+ if (err) {
+ iboe->nb.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+ if (!iboe->nb_inet.notifier_call) {
+ iboe->nb_inet.notifier_call = mlx4_ib_inet_event;
+ err = register_inetaddr_notifier(&iboe->nb_inet);
+ if (err) {
+ iboe->nb_inet.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ if (!iboe->nb_inet6.notifier_call) {
+ iboe->nb_inet6.notifier_call = mlx4_ib_inet6_event;
+ err = register_inet6addr_notifier(&iboe->nb_inet6);
+ if (err) {
+ iboe->nb_inet6.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+#endif
+ mlx4_ib_scan_netdevs(ibdev);
+ mlx4_ib_init_gid_table(ibdev);
}
for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
@@ -1755,11 +1917,25 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
return ibdev;
err_notif:
- if (unregister_netdevice_notifier(&ibdev->iboe.nb))
- pr_warn("failure unregistering notifier\n");
+ if (ibdev->iboe.nb.notifier_call) {
+ if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb.notifier_call = NULL;
+ }
+ if (ibdev->iboe.nb_inet.notifier_call) {
+ if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet.notifier_call = NULL;
+ }
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ if (ibdev->iboe.nb_inet6.notifier_call) {
+ if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet6.notifier_call = NULL;
+ }
+#endif
flush_workqueue(wq);
-err_sriov:
mlx4_ib_close_sriov(ibdev);
err_mad:
@@ -1801,6 +1977,18 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
pr_warn("failure unregistering notifier\n");
ibdev->iboe.nb.notifier_call = NULL;
}
+ if (ibdev->iboe.nb_inet.notifier_call) {
+ if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet.notifier_call = NULL;
+ }
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ if (ibdev->iboe.nb_inet6.notifier_call) {
+ if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet6.notifier_call = NULL;
+ }
+#endif
iounmap(ibdev->uar_map);
for (p = 0; p < ibdev->num_ports; ++p)
if (ibdev->counters[p] != -1)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 036b663..133f41f 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -428,7 +428,10 @@ struct mlx4_ib_sriov {
struct mlx4_ib_iboe {
spinlock_t lock;
struct net_device *netdevs[MLX4_MAX_PORTS];
+ struct net_device *masters[MLX4_MAX_PORTS];
struct notifier_block nb;
+ struct notifier_block nb_inet;
+ struct notifier_block nb_inet6;
union ib_gid gid_table[MLX4_MAX_PORTS][128];
};
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 4/9] IB/mlx4: Handle Ethernet L2 parameters for IP based GID addressing
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (2 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 3/9] IB/mlx4: Use RoCE IP based GIDs in the port GID table Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 5/9] IB/ocrdma: Populate GID table with IP based gids Or Gerlitz
` (4 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
IP based RoCE gids don't store Ethernet L2 parameters, MAC and VLAN.
Hence, we need to extract them now from the CQE and place in struct
ib_wc (to be used for cases were they were taken from the gid).
Also, when modifying a QP or building address handle, instead of
parsing the dgid to get the MAC and VLAN, take them from the
address handle attributes.
Signed-off-by: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/ah.c | 40 +++---------
drivers/infiniband/hw/mlx4/cq.c | 9 +++
drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 -
drivers/infiniband/hw/mlx4/qp.c | 105 ++++++++++++++++++++++-------
drivers/net/ethernet/mellanox/mlx4/port.c | 20 ++++++
include/linux/mlx4/cq.h | 15 +++-
6 files changed, 130 insertions(+), 62 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index a251bec..170dca6 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -39,25 +39,6 @@
#include "mlx4_ib.h"
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
- u8 *mac, int *is_mcast, u8 port)
-{
- struct in6_addr in6;
-
- *is_mcast = 0;
-
- memcpy(&in6, ah_attr->grh.dgid.raw, sizeof in6);
- if (rdma_link_local_addr(&in6))
- rdma_get_ll_mac(&in6, mac);
- else if (rdma_is_multicast_addr(&in6)) {
- rdma_get_mcast_mac(&in6, mac);
- *is_mcast = 1;
- } else
- return -EINVAL;
-
- return 0;
-}
-
static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
struct mlx4_ib_ah *ah)
{
@@ -92,21 +73,18 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
{
struct mlx4_ib_dev *ibdev = to_mdev(pd->device);
struct mlx4_dev *dev = ibdev->dev;
- union ib_gid sgid;
- u8 mac[6];
- int err;
int is_mcast;
+ struct in6_addr in6;
u16 vlan_tag;
- err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num);
- if (err)
- return ERR_PTR(err);
-
- memcpy(ah->av.eth.mac, mac, 6);
- err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid);
- if (err)
- return ERR_PTR(err);
- vlan_tag = rdma_get_vlan_id(&sgid);
+ memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+ if (rdma_is_multicast_addr(&in6)) {
+ is_mcast = 1;
+ rdma_get_mcast_mac(&in6, ah->av.eth.mac);
+ } else {
+ memcpy(ah->av.eth.mac, ah_attr->dmac, ETH_ALEN);
+ }
+ vlan_tag = ah_attr->vlan_id;
if (vlan_tag < 0x1000)
vlan_tag |= (ah_attr->sl & 7) << 13;
ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index d5e60f4..5f6113b 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -793,6 +793,15 @@ repoll:
wc->sl = be16_to_cpu(cqe->sl_vid) >> 13;
else
wc->sl = be16_to_cpu(cqe->sl_vid) >> 12;
+ if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) {
+ wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+ MLX4_CQE_VID_MASK;
+ } else {
+ wc->vlan_id = 0xffff;
+ }
+ wc->wc_flags |= IB_WC_WITH_VLAN;
+ memcpy(wc->smac, cqe->smac, ETH_ALEN);
+ wc->wc_flags |= IB_WC_WITH_SMAC;
}
return 0;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 133f41f..c06f571 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -678,9 +678,6 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
union ib_gid *gid, int netw_view);
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
- u8 *mac, int *is_mcast, u8 port);
-
static inline bool mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
{
u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index da6f5fa..e0c2186 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -90,6 +90,21 @@ enum {
MLX4_RAW_QP_MSGMAX = 31,
};
+#ifndef ETH_ALEN
+#define ETH_ALEN 6
+#endif
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+ u64 mac = 0;
+ int i;
+
+ for (i = 0; i < ETH_ALEN; i++) {
+ mac <<= 8;
+ mac |= addr[i];
+ }
+ return mac;
+}
+
static const __be32 mlx4_ib_opcode[] = {
[IB_WR_SEND] = cpu_to_be32(MLX4_OPCODE_SEND),
[IB_WR_LSO] = cpu_to_be32(MLX4_OPCODE_LSO),
@@ -1144,16 +1159,15 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
}
-static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
- struct mlx4_qp_path *path, u8 port)
+static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
+ u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
+ u8 port)
{
- int err;
int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
IB_LINK_LAYER_ETHERNET;
- u8 mac[6];
- int is_mcast;
- u16 vlan_tag;
int vidx;
+ int smac_index;
+
path->grh_mylmc = ah->src_path_bits & 0x7f;
path->rlid = cpu_to_be16(ah->dlid);
@@ -1188,22 +1202,27 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
if (!(ah->ah_flags & IB_AH_GRH))
return -1;
- err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
- if (err)
- return err;
-
- memcpy(path->dmac, mac, 6);
+ memcpy(path->dmac, ah->dmac, ETH_ALEN);
path->ackto = MLX4_IB_LINK_TYPE_ETH;
- /* use index 0 into MAC table for IBoE */
- path->grh_mylmc &= 0x80;
+ /* find the index into MAC table for IBoE */
+ if (!is_zero_ether_addr((const u8 *)&smac)) {
+ if (mlx4_find_cached_mac(dev->dev, port, smac,
+ &smac_index))
+ return -ENOENT;
+ } else {
+ smac_index = 0;
+ }
+
+ path->grh_mylmc &= 0x80 | smac_index;
- vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+ path->feup |= MLX4_FEUP_FORCE_ETH_UP;
if (vlan_tag < 0x1000) {
if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
return -ENOENT;
path->vlan_index = vidx;
path->fl = 1 << 6;
+ path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
}
} else
path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
@@ -1212,6 +1231,28 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
return 0;
}
+static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
+ enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_qp_path *path, u8 port)
+{
+ return _mlx4_set_path(dev, &qp->ah_attr,
+ mlx4_mac_to_u64((u8 *)qp->smac),
+ (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
+ path, port);
+}
+
+static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
+ const struct ib_qp_attr *qp,
+ enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_qp_path *path, u8 port)
+{
+ return _mlx4_set_path(dev, &qp->alt_ah_attr,
+ mlx4_mac_to_u64((u8 *)qp->alt_smac),
+ (qp_attr_mask & IB_QP_ALT_VID) ?
+ qp->alt_vlan_id : 0xffff,
+ path, port);
+}
+
static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
{
struct mlx4_ib_gid_entry *ge, *tmp;
@@ -1329,7 +1370,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
}
if (attr_mask & IB_QP_AV) {
- if (mlx4_set_path(dev, &attr->ah_attr, &context->pri_path,
+ if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path,
attr_mask & IB_QP_PORT ?
attr->port_num : qp->port))
goto out;
@@ -1352,8 +1393,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
dev->dev->caps.pkey_table_len[attr->alt_port_num])
goto out;
- if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
- attr->alt_port_num))
+ if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path,
+ attr->alt_port_num))
goto out;
context->alt_path.pkey_index = attr->alt_pkey_index;
@@ -1464,6 +1505,17 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
MLX4_IB_LINK_TYPE_ETH;
+ if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+ int is_eth = rdma_port_get_link_layer(
+ &dev->ib_dev, qp->port) ==
+ IB_LINK_LAYER_ETHERNET;
+ if (is_eth) {
+ context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
+ optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
+ }
+ }
+
+
if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD &&
attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
sqd_event = 1;
@@ -1561,18 +1613,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
struct mlx4_ib_qp *qp = to_mqp(ibqp);
enum ib_qp_state cur_state, new_state;
int err = -EINVAL;
- int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ int ll;
mutex_lock(&qp->mutex);
cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
- if (cur_state == new_state && cur_state == IB_QPS_RESET)
- p = IB_LINK_LAYER_UNSPECIFIED;
+ if (cur_state == new_state && cur_state == IB_QPS_RESET) {
+ ll = IB_LINK_LAYER_UNSPECIFIED;
+ } else {
+ int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ ll = rdma_port_get_link_layer(&dev->ib_dev, port);
+ }
if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
- attr_mask,
- rdma_port_get_link_layer(&dev->ib_dev, p))) {
+ attr_mask, ll)) {
pr_debug("qpn 0x%x: invalid attribute mask specified "
"for transition %d to %d. qp_type %d,"
" attr_mask 0x%x\n",
@@ -1789,8 +1844,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
return err;
}
- vlan = rdma_get_vlan_id(&sgid);
- is_vlan = vlan < 0x1000;
+ if (ah->av.eth.vlan != 0xffff) {
+ vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
+ is_vlan = 1;
+ }
}
ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 946e0af..fbe76f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -123,6 +123,26 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
return err;
}
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
+{
+ struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+ struct mlx4_mac_table *table = &info->mac_table;
+ int i;
+
+ for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+ if (!table->refs[i])
+ continue;
+
+ if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
+ *idx = i;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
+
int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
{
struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h
index 98fa492..e186299 100644
--- a/include/linux/mlx4/cq.h
+++ b/include/linux/mlx4/cq.h
@@ -34,6 +34,7 @@
#define MLX4_CQ_H
#include <linux/types.h>
+#include <uapi/linux/if_ether.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
@@ -43,10 +44,15 @@ struct mlx4_cqe {
__be32 immed_rss_invalid;
__be32 g_mlpath_rqpn;
__be16 sl_vid;
- __be16 rlid;
- __be16 status;
- u8 ipv6_ext_mask;
- u8 badfcs_enc;
+ union {
+ struct {
+ __be16 rlid;
+ __be16 status;
+ u8 ipv6_ext_mask;
+ u8 badfcs_enc;
+ };
+ u8 smac[ETH_ALEN];
+ };
__be32 byte_cnt;
__be16 wqe_index;
__be16 checksum;
@@ -83,6 +89,7 @@ struct mlx4_ts_cqe {
enum {
MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29,
MLX4_CQE_QPN_MASK = 0xffffff,
+ MLX4_CQE_VID_MASK = 0xfff,
};
enum {
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 5/9] IB/ocrdma: Populate GID table with IP based gids
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (3 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 4/9] IB/mlx4: Handle Ethernet L2 parameters for IP based GID addressing Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 6/9] IB/ocrdma: Handle Ethernet L2 parameters for IP based GID addressing Or Gerlitz
` (3 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Naresh Gottumukkala, Or Gerlitz
From: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
This patch is similar in spirit to the "IB/mlx4: Use RoCE IP based GIDs
in the port GID table" patch for this series.
Changes to inet4 and inet6 addresses for the host are monitored and if the
address is associated with an ocrdma device then a gid is added or deleted
from the device's gid table. The gid format will be a IPv4 to IPv6 mapped or
the IPv6 address.
Cc: Naresh Gottumukkala <bgottumukkala-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/ocrdma/ocrdma_main.c | 138 ++++++++-------------------
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 2 +-
2 files changed, 41 insertions(+), 99 deletions(-)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 56e0049..c3fca6e 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -67,46 +67,24 @@ void ocrdma_get_guid(struct ocrdma_dev *dev, u8 *guid)
guid[7] = mac_addr[5];
}
-static void ocrdma_build_sgid_mac(union ib_gid *sgid, unsigned char *mac_addr,
- bool is_vlan, u16 vlan_id)
-{
- sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
- sgid->raw[8] = mac_addr[0] ^ 2;
- sgid->raw[9] = mac_addr[1];
- sgid->raw[10] = mac_addr[2];
- if (is_vlan) {
- sgid->raw[11] = vlan_id >> 8;
- sgid->raw[12] = vlan_id & 0xff;
- } else {
- sgid->raw[11] = 0xff;
- sgid->raw[12] = 0xfe;
- }
- sgid->raw[13] = mac_addr[3];
- sgid->raw[14] = mac_addr[4];
- sgid->raw[15] = mac_addr[5];
-}
-
-static bool ocrdma_add_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
- bool is_vlan, u16 vlan_id)
+static bool ocrdma_add_sgid(struct ocrdma_dev *dev, union ib_gid *new_sgid)
{
int i;
- union ib_gid new_sgid;
unsigned long flags;
memset(&ocrdma_zero_sgid, 0, sizeof(union ib_gid));
- ocrdma_build_sgid_mac(&new_sgid, mac_addr, is_vlan, vlan_id);
spin_lock_irqsave(&dev->sgid_lock, flags);
for (i = 0; i < OCRDMA_MAX_SGID; i++) {
if (!memcmp(&dev->sgid_tbl[i], &ocrdma_zero_sgid,
sizeof(union ib_gid))) {
/* found free entry */
- memcpy(&dev->sgid_tbl[i], &new_sgid,
+ memcpy(&dev->sgid_tbl[i], new_sgid,
sizeof(union ib_gid));
spin_unlock_irqrestore(&dev->sgid_lock, flags);
return true;
- } else if (!memcmp(&dev->sgid_tbl[i], &new_sgid,
+ } else if (!memcmp(&dev->sgid_tbl[i], new_sgid,
sizeof(union ib_gid))) {
/* entry already present, no addition is required. */
spin_unlock_irqrestore(&dev->sgid_lock, flags);
@@ -117,20 +95,17 @@ static bool ocrdma_add_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
return false;
}
-static bool ocrdma_del_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
- bool is_vlan, u16 vlan_id)
+static bool ocrdma_del_sgid(struct ocrdma_dev *dev, union ib_gid *sgid)
{
int found = false;
int i;
- union ib_gid sgid;
unsigned long flags;
- ocrdma_build_sgid_mac(&sgid, mac_addr, is_vlan, vlan_id);
spin_lock_irqsave(&dev->sgid_lock, flags);
/* first is default sgid, which cannot be deleted. */
for (i = 1; i < OCRDMA_MAX_SGID; i++) {
- if (!memcmp(&dev->sgid_tbl[i], &sgid, sizeof(union ib_gid))) {
+ if (!memcmp(&dev->sgid_tbl[i], sgid, sizeof(union ib_gid))) {
/* found matching entry */
memset(&dev->sgid_tbl[i], 0, sizeof(union ib_gid));
found = true;
@@ -141,75 +116,18 @@ static bool ocrdma_del_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
return found;
}
-static void ocrdma_add_default_sgid(struct ocrdma_dev *dev)
-{
- /* GID Index 0 - Invariant manufacturer-assigned EUI-64 */
- union ib_gid *sgid = &dev->sgid_tbl[0];
-
- sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
- ocrdma_get_guid(dev, &sgid->raw[8]);
-}
-
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
-static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev)
-{
- struct net_device *netdev, *tmp;
- u16 vlan_id;
- bool is_vlan;
-
- netdev = dev->nic_info.netdev;
-
- rcu_read_lock();
- for_each_netdev_rcu(&init_net, tmp) {
- if (netdev == tmp || vlan_dev_real_dev(tmp) == netdev) {
- if (!netif_running(tmp) || !netif_oper_up(tmp))
- continue;
- if (netdev != tmp) {
- vlan_id = vlan_dev_vlan_id(tmp);
- is_vlan = true;
- } else {
- is_vlan = false;
- vlan_id = 0;
- tmp = netdev;
- }
- ocrdma_add_sgid(dev, tmp->dev_addr, is_vlan, vlan_id);
- }
- }
- rcu_read_unlock();
-}
-#else
-static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev)
-{
-
-}
-#endif /* VLAN */
-
-static int ocrdma_build_sgid_tbl(struct ocrdma_dev *dev)
+static int ocrdma_addr_event(unsigned long event, struct net_device *netdev,
+ union ib_gid *gid)
{
- ocrdma_add_default_sgid(dev);
- ocrdma_add_vlan_sgids(dev);
- return 0;
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-
-static int ocrdma_inet6addr_event(struct notifier_block *notifier,
- unsigned long event, void *ptr)
-{
- struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
- struct net_device *netdev = ifa->idev->dev;
struct ib_event gid_event;
struct ocrdma_dev *dev;
bool found = false;
bool updated = false;
bool is_vlan = false;
- u16 vid = 0;
is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN;
- if (is_vlan) {
- vid = vlan_dev_vlan_id(netdev);
+ if (is_vlan)
netdev = vlan_dev_real_dev(netdev);
- }
rcu_read_lock();
list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) {
@@ -222,16 +140,14 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier,
if (!found)
return NOTIFY_DONE;
- if (!rdma_link_local_addr((struct in6_addr *)&ifa->addr))
- return NOTIFY_DONE;
mutex_lock(&dev->dev_lock);
switch (event) {
case NETDEV_UP:
- updated = ocrdma_add_sgid(dev, netdev->dev_addr, is_vlan, vid);
+ updated = ocrdma_add_sgid(dev, gid);
break;
case NETDEV_DOWN:
- updated = ocrdma_del_sgid(dev, netdev->dev_addr, is_vlan, vid);
+ updated = ocrdma_del_sgid(dev, gid);
break;
default:
break;
@@ -247,6 +163,32 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier,
return NOTIFY_OK;
}
+static int ocrdma_inetaddr_event(struct notifier_block *notifier,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = ptr;
+ union ib_gid gid;
+ struct net_device *netdev = ifa->ifa_dev->dev;
+
+ ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+ return ocrdma_addr_event(event, netdev, &gid);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+static int ocrdma_inet6addr_event(struct notifier_block *notifier,
+ unsigned long event, void *ptr)
+{
+ struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+ union ib_gid *gid = (union ib_gid *)&ifa->addr;
+ struct net_device *netdev = ifa->idev->dev;
+ return ocrdma_addr_event(event, netdev, gid);
+}
+
+static struct notifier_block ocrdma_inetaddr_notifier = {
+ .notifier_call = ocrdma_inetaddr_event
+};
+
static struct notifier_block ocrdma_inet6addr_notifier = {
.notifier_call = ocrdma_inet6addr_event
};
@@ -423,10 +365,6 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info)
if (status)
goto alloc_err;
- status = ocrdma_build_sgid_tbl(dev);
- if (status)
- goto alloc_err;
-
status = ocrdma_register_device(dev);
if (status)
goto alloc_err;
@@ -552,6 +490,10 @@ static int __init ocrdma_init_module(void)
{
int status;
+ status = register_inetaddr_notifier(&ocrdma_inetaddr_notifier);
+ if (status)
+ return status;
+
#if IS_ENABLED(CONFIG_IPV6)
status = register_inet6addr_notifier(&ocrdma_inet6addr_notifier);
if (status)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 0607ca7..b95253e 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1327,7 +1327,7 @@ int ocrdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
spin_unlock_irqrestore(&qp->q_lock, flags);
if (!ib_modify_qp_is_ok(old_qps, new_qps, ibqp->qp_type, attr_mask,
- IB_LINK_LAYER_UNSPECIFIED)) {
+ IB_LINK_LAYER_ETHERNET)) {
pr_err("%s(%d) invalid attribute mask=0x%x specified for\n"
"qpn=0x%x of type=0x%x old_qps=0x%x, new_qps=0x%x\n",
__func__, dev->id, attr_mask, qp->id, ibqp->qp_type,
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 6/9] IB/ocrdma: Handle Ethernet L2 parameters for IP based GID addressing
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (4 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 5/9] IB/ocrdma: Populate GID table with IP based gids Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 7/9] IB/core: Add RoCE IP based addressing extensions for uverbs Or Gerlitz
` (2 subsequent siblings)
8 siblings, 0 replies; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Naresh Gottumukkala, Or Gerlitz
From: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
This patch is similar in spirit to the "IB/mlx4: Handle Ethernet L2 parameters for
IP based GID addressing" from series. It handles the fact that IP based RoCE gids
don't store Ethernet L2 parameters, MAC and VLAN.
When building an address handle, instead of parsing the dgid to
get the MAC and VLAN, take them from the address handle attributes.
Cc: Naresh Gottumukkala <bgottumukkala-laKkSmNT4hbQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/ocrdma/ocrdma.h | 12 ++++++++++++
drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 5 +++--
drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 21 ++-------------------
drivers/infiniband/hw/ocrdma/ocrdma_hw.h | 1 -
4 files changed, 17 insertions(+), 22 deletions(-)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index adc11d1..d544292 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -422,5 +422,17 @@ static inline int is_cqe_wr_imm(struct ocrdma_cqe *cqe)
OCRDMA_CQE_WRITE_IMM) ? 1 : 0;
}
+static inline int ocrdma_resolve_dmac(struct ocrdma_dev *dev,
+ struct ib_ah_attr *ah_attr, u8 *mac_addr)
+{
+ struct in6_addr in6;
+
+ memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+ if (rdma_is_multicast_addr(&in6))
+ rdma_get_mcast_mac(&in6, mac_addr);
+ else
+ memcpy(mac_addr, ah_attr->dmac, ETH_ALEN);
+ return 0;
+}
#endif
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index ee499d9..bbb7962 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -49,7 +49,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
ah->sgid_index = attr->grh.sgid_index;
- vlan_tag = rdma_get_vlan_id(&attr->grh.dgid);
+ vlan_tag = attr->vlan_id;
if (!vlan_tag || (vlan_tag > 0xFFF))
vlan_tag = dev->pvid;
if (vlan_tag && (vlan_tag < 0x1000)) {
@@ -64,7 +64,8 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
eth_sz = sizeof(struct ocrdma_eth_basic);
}
memcpy(ð.smac[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
- status = ocrdma_resolve_dgid(dev, &attr->grh.dgid, ð.dmac[0]);
+ memcpy(ð.dmac[0], attr->dmac, ETH_ALEN);
+ status = ocrdma_resolve_dmac(dev, attr, ð.dmac[0]);
if (status)
return status;
status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 4ed8235..69c82b1 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -2076,23 +2076,6 @@ mbx_err:
return status;
}
-int ocrdma_resolve_dgid(struct ocrdma_dev *dev, union ib_gid *dgid,
- u8 *mac_addr)
-{
- struct in6_addr in6;
-
- memcpy(&in6, dgid, sizeof in6);
- if (rdma_is_multicast_addr(&in6)) {
- rdma_get_mcast_mac(&in6, mac_addr);
- } else if (rdma_link_local_addr(&in6)) {
- rdma_get_ll_mac(&in6, mac_addr);
- } else {
- pr_err("%s() fail to resolve mac_addr.\n", __func__);
- return -EINVAL;
- }
- return 0;
-}
-
static int ocrdma_set_av_params(struct ocrdma_qp *qp,
struct ocrdma_modify_qp *cmd,
struct ib_qp_attr *attrs)
@@ -2126,14 +2109,14 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp,
qp->sgid_idx = ah_attr->grh.sgid_index;
memcpy(&cmd->params.sgid[0], &sgid.raw[0], sizeof(cmd->params.sgid));
- ocrdma_resolve_dgid(qp->dev, &ah_attr->grh.dgid, &mac_addr[0]);
+ ocrdma_resolve_dmac(qp->dev, ah_attr, &mac_addr[0]);
cmd->params.dmac_b0_to_b3 = mac_addr[0] | (mac_addr[1] << 8) |
(mac_addr[2] << 16) | (mac_addr[3] << 24);
/* convert them to LE format. */
ocrdma_cpu_to_le32(&cmd->params.dgid[0], sizeof(cmd->params.dgid));
ocrdma_cpu_to_le32(&cmd->params.sgid[0], sizeof(cmd->params.sgid));
cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8);
- vlan_id = rdma_get_vlan_id(&sgid);
+ vlan_id = ah_attr->vlan_id;
if (vlan_id && (vlan_id < 0x1000)) {
cmd->params.vlan_dmac_b4_to_b5 |=
vlan_id << OCRDMA_QP_PARAMS_VLAN_SHIFT;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
index f2a89d4..82fe332 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
@@ -94,7 +94,6 @@ void ocrdma_ring_cq_db(struct ocrdma_dev *, u16 cq_id, bool armed,
int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed);
int ocrdma_query_config(struct ocrdma_dev *,
struct ocrdma_mbx_query_config *config);
-int ocrdma_resolve_dgid(struct ocrdma_dev *, union ib_gid *dgid, u8 *mac_addr);
int ocrdma_mbx_alloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);
int ocrdma_mbx_dealloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 7/9] IB/core: Add RoCE IP based addressing extensions for uverbs
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (5 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 6/9] IB/ocrdma: Handle Ethernet L2 parameters for IP based GID addressing Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
[not found] ` <1378824099-22150-8-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-09-10 14:41 ` [PATCH V4 8/9] IB/core: Add RoCE IP based addressing extensions for rdma_ucm Or Gerlitz
2013-09-10 14:41 ` [PATCH V4 9/9] IB/mlx4: Enable mlx4_ib support for MODIFY_QP_EX Or Gerlitz
8 siblings, 1 reply; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Add uverbs support for RoCE (IBoE) IP based addressing extensions
towards user space libraries.
Under ip based gid addressing, for RC QPs, QP attributes should contain the
Ethernet L2 destination. Until now, indicatings GID was sufficient. When
using ip encoded in gids, the QP attributes should contain extended destination,
indicating vlan and dmac as well. This is done via a new struct ib_uverbs_qp_dest_ex.
This new structure is contained in a new struct ib_uverbs_modify_qp_ex that is
used by MODIFY_QP_EX command. In order to make those changes seamlessly, those
extended structures were added in the bottom of the current structures.
The new command also gets smac/alt_smac/vlan_id/alt_vlan_id. Those parameters
are fixed in the QP context in order to enhance security.
The extended dest is used a a pointer rather than as a inline fixed field
in the sake of future scalability.
Also, when the gid encodes ip address, the AH attributes should contain also
dmac. Therefore, ib_uverbs_create_ah was extended to contain those fields.
When creating an AH, the user indicates the exact L2 ethernet destination
parameters. This is done by a new CREATE_AH_EX command that uses a new struct
ib_uverbs_create_ah_ex.
struct ib_user_path_rec was extended too, to contain source and destination
MAC and VLAN ID, this structure is of use by the rdma_ucm driver.
Signed-off-by: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/uverbs.h | 2 +
drivers/infiniband/core/uverbs_cmd.c | 359 ++++++++++++++++++++++-------
drivers/infiniband/core/uverbs_main.c | 4 +-
drivers/infiniband/core/uverbs_marshall.c | 128 ++++++++++-
include/rdma/ib_marshall.h | 12 +
include/uapi/rdma/ib_user_sa.h | 34 +++-
include/uapi/rdma/ib_user_verbs.h | 160 +++++++++++++-
7 files changed, 608 insertions(+), 91 deletions(-)
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index d040b87..b0fcb0b 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -202,11 +202,13 @@ IB_UVERBS_DECLARE_CMD(create_qp);
IB_UVERBS_DECLARE_CMD(open_qp);
IB_UVERBS_DECLARE_CMD(query_qp);
IB_UVERBS_DECLARE_CMD(modify_qp);
+IB_UVERBS_DECLARE_CMD(modify_qp_ex);
IB_UVERBS_DECLARE_CMD(destroy_qp);
IB_UVERBS_DECLARE_CMD(post_send);
IB_UVERBS_DECLARE_CMD(post_recv);
IB_UVERBS_DECLARE_CMD(post_srq_recv);
IB_UVERBS_DECLARE_CMD(create_ah);
+IB_UVERBS_DECLARE_CMD(create_ah_ex);
IB_UVERBS_DECLARE_CMD(destroy_ah);
IB_UVERBS_DECLARE_CMD(attach_mcast);
IB_UVERBS_DECLARE_CMD(detach_mcast);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index f2b81b9..9a0c5d7 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1900,6 +1900,60 @@ static int modify_qp_mask(enum ib_qp_type qp_type, int mask)
}
}
+static void ib_uverbs_modify_qp_assign(struct ib_uverbs_modify_qp *cmd,
+ struct ib_qp_attr *attr,
+ struct ib_uverbs_qp_dest *dest,
+ struct ib_uverbs_qp_dest *alt_dest) {
+ attr->qp_state = cmd->qp_state;
+ attr->cur_qp_state = cmd->cur_qp_state;
+ attr->path_mtu = cmd->path_mtu;
+ attr->path_mig_state = cmd->path_mig_state;
+ attr->qkey = cmd->qkey;
+ attr->rq_psn = cmd->rq_psn;
+ attr->sq_psn = cmd->sq_psn;
+ attr->dest_qp_num = cmd->dest_qp_num;
+ attr->qp_access_flags = cmd->qp_access_flags;
+ attr->pkey_index = cmd->pkey_index;
+ attr->alt_pkey_index = cmd->alt_pkey_index;
+ attr->en_sqd_async_notify = cmd->en_sqd_async_notify;
+ attr->max_rd_atomic = cmd->max_rd_atomic;
+ attr->max_dest_rd_atomic = cmd->max_dest_rd_atomic;
+ attr->min_rnr_timer = cmd->min_rnr_timer;
+ attr->port_num = cmd->port_num;
+ attr->timeout = cmd->timeout;
+ attr->retry_cnt = cmd->retry_cnt;
+ attr->rnr_retry = cmd->rnr_retry;
+ attr->alt_port_num = cmd->alt_port_num;
+ attr->alt_timeout = cmd->alt_timeout;
+
+ memcpy(attr->ah_attr.grh.dgid.raw, dest->dgid, 16);
+ attr->ah_attr.grh.flow_label = dest->flow_label;
+ attr->ah_attr.grh.sgid_index = dest->sgid_index;
+ attr->ah_attr.grh.hop_limit = dest->hop_limit;
+ attr->ah_attr.grh.traffic_class = dest->traffic_class;
+ attr->ah_attr.dlid = dest->dlid;
+ attr->ah_attr.sl = dest->sl;
+ attr->ah_attr.src_path_bits = dest->src_path_bits;
+ attr->ah_attr.static_rate = dest->static_rate;
+ attr->ah_attr.ah_flags = dest->is_global ?
+ IB_AH_GRH : 0;
+ attr->ah_attr.port_num = dest->port_num;
+
+ memcpy(attr->alt_ah_attr.grh.dgid.raw, alt_dest->dgid, 16);
+ attr->alt_ah_attr.grh.flow_label = alt_dest->flow_label;
+ attr->alt_ah_attr.grh.sgid_index = alt_dest->sgid_index;
+ attr->alt_ah_attr.grh.hop_limit = alt_dest->hop_limit;
+ attr->alt_ah_attr.grh.traffic_class = alt_dest->traffic_class;
+ attr->alt_ah_attr.dlid = alt_dest->dlid;
+ attr->alt_ah_attr.sl = alt_dest->sl;
+ attr->alt_ah_attr.src_path_bits = alt_dest->src_path_bits;
+ attr->alt_ah_attr.static_rate = alt_dest->static_rate;
+ attr->alt_ah_attr.ah_flags = alt_dest->is_global
+ ? IB_AH_GRH : 0;
+ attr->alt_ah_attr.port_num = alt_dest->port_num;
+}
+
+
ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len)
@@ -1926,51 +1980,13 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
goto out;
}
- attr->qp_state = cmd.qp_state;
- attr->cur_qp_state = cmd.cur_qp_state;
- attr->path_mtu = cmd.path_mtu;
- attr->path_mig_state = cmd.path_mig_state;
- attr->qkey = cmd.qkey;
- attr->rq_psn = cmd.rq_psn;
- attr->sq_psn = cmd.sq_psn;
- attr->dest_qp_num = cmd.dest_qp_num;
- attr->qp_access_flags = cmd.qp_access_flags;
- attr->pkey_index = cmd.pkey_index;
- attr->alt_pkey_index = cmd.alt_pkey_index;
- attr->en_sqd_async_notify = cmd.en_sqd_async_notify;
- attr->max_rd_atomic = cmd.max_rd_atomic;
- attr->max_dest_rd_atomic = cmd.max_dest_rd_atomic;
- attr->min_rnr_timer = cmd.min_rnr_timer;
- attr->port_num = cmd.port_num;
- attr->timeout = cmd.timeout;
- attr->retry_cnt = cmd.retry_cnt;
- attr->rnr_retry = cmd.rnr_retry;
- attr->alt_port_num = cmd.alt_port_num;
- attr->alt_timeout = cmd.alt_timeout;
-
- memcpy(attr->ah_attr.grh.dgid.raw, cmd.dest.dgid, 16);
- attr->ah_attr.grh.flow_label = cmd.dest.flow_label;
- attr->ah_attr.grh.sgid_index = cmd.dest.sgid_index;
- attr->ah_attr.grh.hop_limit = cmd.dest.hop_limit;
- attr->ah_attr.grh.traffic_class = cmd.dest.traffic_class;
- attr->ah_attr.dlid = cmd.dest.dlid;
- attr->ah_attr.sl = cmd.dest.sl;
- attr->ah_attr.src_path_bits = cmd.dest.src_path_bits;
- attr->ah_attr.static_rate = cmd.dest.static_rate;
- attr->ah_attr.ah_flags = cmd.dest.is_global ? IB_AH_GRH : 0;
- attr->ah_attr.port_num = cmd.dest.port_num;
-
- memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd.alt_dest.dgid, 16);
- attr->alt_ah_attr.grh.flow_label = cmd.alt_dest.flow_label;
- attr->alt_ah_attr.grh.sgid_index = cmd.alt_dest.sgid_index;
- attr->alt_ah_attr.grh.hop_limit = cmd.alt_dest.hop_limit;
- attr->alt_ah_attr.grh.traffic_class = cmd.alt_dest.traffic_class;
- attr->alt_ah_attr.dlid = cmd.alt_dest.dlid;
- attr->alt_ah_attr.sl = cmd.alt_dest.sl;
- attr->alt_ah_attr.src_path_bits = cmd.alt_dest.src_path_bits;
- attr->alt_ah_attr.static_rate = cmd.alt_dest.static_rate;
- attr->alt_ah_attr.ah_flags = cmd.alt_dest.is_global ? IB_AH_GRH : 0;
- attr->alt_ah_attr.port_num = cmd.alt_dest.port_num;
+ ib_uverbs_modify_qp_assign(&cmd, attr, &cmd.dest, &cmd.alt_dest);
+ memset(attr->ah_attr.dmac, 0, sizeof(attr->ah_attr.dmac));
+ attr->vlan_id = 0xFFFF;
+ memset(attr->smac, 0, sizeof(attr->smac));
+ memset(attr->alt_ah_attr.dmac, 0, sizeof(attr->alt_ah_attr.dmac));
+ attr->alt_vlan_id = 0xFFFF;
+ memset(attr->alt_smac, 0, sizeof(attr->alt_smac));
if (qp->real_qp == qp) {
ret = qp->device->modify_qp(qp, attr,
@@ -1992,6 +2008,111 @@ out:
return ret;
}
+ssize_t ib_uverbs_modify_qp_ex(struct ib_uverbs_file *file,
+ const char __user *buf, int in_len,
+ int out_len)
+{
+ struct ib_uverbs_modify_qp_ex cmd;
+ struct ib_uverbs_qp_dest_ex dest_ex;
+ struct ib_uverbs_qp_dest_ex alt_dest_ex;
+ struct ib_uverbs_qp_dest *dest;
+ struct ib_uverbs_qp_dest *alt_dest;
+ struct ib_udata udata;
+ struct ib_qp *qp;
+ struct ib_qp_attr *attr;
+ int ret;
+
+ if (copy_from_user(&cmd, buf, sizeof(cmd)))
+ return -EFAULT;
+
+ INIT_UDATA(&udata, buf + sizeof(cmd), NULL, in_len - sizeof(cmd),
+ out_len);
+
+ attr = kmalloc(sizeof(*attr), GFP_KERNEL);
+ if (!attr)
+ return -ENOMEM;
+
+ qp = idr_read_qp(cmd.qp_handle, file->ucontext);
+ if (!qp) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!(cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_DEST_EX) ||
+ copy_from_user(&dest_ex, cmd.dest_ex, sizeof(dest_ex)))
+ dest = &cmd.dest;
+ else
+ dest = (struct ib_uverbs_qp_dest *)&dest_ex;
+
+
+ if (!(cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_ALT_DEST_EX) ||
+ copy_from_user(&alt_dest_ex, cmd.alt_dest_ex, sizeof(alt_dest_ex)))
+ alt_dest = &cmd.alt_dest;
+ else
+ alt_dest = (struct ib_uverbs_qp_dest *)&alt_dest_ex;
+
+ ib_uverbs_modify_qp_assign((struct ib_uverbs_modify_qp *)((void *)&cmd +
+ offsetof(
+ struct ib_uverbs_modify_qp_ex, dest)), attr,
+ dest,
+ alt_dest);
+
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_DEST_EX &&
+ dest_ex.comp_mask & IB_UVERBS_QP_DEST_ATTR_DMAC)
+ memcpy(attr->ah_attr.dmac, dest_ex.dmac,
+ sizeof(attr->ah_attr.dmac));
+ else
+ memset(attr->ah_attr.dmac, 0,
+ sizeof(attr->ah_attr.dmac));
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_VID)
+ attr->vlan_id = cmd.vid;
+ else
+ attr->vlan_id = 0xFFFF;
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_SMAC)
+ memcpy(attr->smac, cmd.smac,
+ sizeof(attr->smac));
+ else
+ memset(attr->smac, 0,
+ sizeof(attr->smac));
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_ALT_DEST_EX &&
+ alt_dest_ex.comp_mask & IB_UVERBS_QP_DEST_ATTR_DMAC)
+ memcpy(attr->alt_ah_attr.dmac, alt_dest_ex.dmac,
+ sizeof(attr->alt_ah_attr.dmac));
+ else
+ memset(attr->alt_ah_attr.dmac, 0,
+ sizeof(attr->alt_ah_attr.dmac));
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_ALT_VID)
+ attr->alt_vlan_id = cmd.alt_vid;
+ else
+ attr->alt_vlan_id = 0xFFFF;
+ if (cmd.comp_mask & IB_UVERBS_MODIFY_QP_EX_ALT_SMAC)
+ memcpy(attr->alt_smac, cmd.alt_smac,
+ sizeof(attr->alt_smac));
+ else
+ memset(attr->alt_smac, 0,
+ sizeof(attr->alt_smac));
+
+
+ if (qp->real_qp == qp) {
+ ret = qp->device->modify_qp(qp, attr,
+ modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
+ } else {
+ ret = ib_modify_qp(qp, attr,
+ modify_qp_mask(qp->qp_type, cmd.attr_mask));
+ }
+
+ put_qp_read(qp);
+
+ if (ret)
+ goto out;
+
+ ret = in_len;
+
+out:
+ kfree(attr);
+
+ return ret;
+}
ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len)
@@ -2389,48 +2510,46 @@ out:
return ret ? ret : in_len;
}
-ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
- const char __user *buf, int in_len,
- int out_len)
+static struct ib_uobject *ib_uverbs_create_ah_assign(
+ struct ib_uverbs_create_ah_ex *cmd,
+ struct ib_uverbs_ah_attr_ex *src_attr,
+ struct ib_uverbs_file *file)
{
- struct ib_uverbs_create_ah cmd;
- struct ib_uverbs_create_ah_resp resp;
- struct ib_uobject *uobj;
struct ib_pd *pd;
struct ib_ah *ah;
struct ib_ah_attr attr;
- int ret;
-
- if (out_len < sizeof resp)
- return -ENOSPC;
-
- if (copy_from_user(&cmd, buf, sizeof cmd))
- return -EFAULT;
+ struct ib_uobject *uobj;
+ long ret;
- uobj = kmalloc(sizeof *uobj, GFP_KERNEL);
+ uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
if (!uobj)
- return -ENOMEM;
+ return (void *)-ENOMEM;
- init_uobj(uobj, cmd.user_handle, file->ucontext, &ah_lock_class);
+ init_uobj(uobj, cmd->user_handle, file->ucontext, &ah_lock_class);
down_write(&uobj->mutex);
- pd = idr_read_pd(cmd.pd_handle, file->ucontext);
+ pd = idr_read_pd(cmd->pd_handle, file->ucontext);
if (!pd) {
ret = -EINVAL;
goto err;
}
- attr.dlid = cmd.attr.dlid;
- attr.sl = cmd.attr.sl;
- attr.src_path_bits = cmd.attr.src_path_bits;
- attr.static_rate = cmd.attr.static_rate;
- attr.ah_flags = cmd.attr.is_global ? IB_AH_GRH : 0;
- attr.port_num = cmd.attr.port_num;
- attr.grh.flow_label = cmd.attr.grh.flow_label;
- attr.grh.sgid_index = cmd.attr.grh.sgid_index;
- attr.grh.hop_limit = cmd.attr.grh.hop_limit;
- attr.grh.traffic_class = cmd.attr.grh.traffic_class;
- memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
+ attr.dlid = src_attr->dlid;
+ attr.sl = src_attr->sl;
+ attr.src_path_bits = src_attr->src_path_bits;
+ attr.static_rate = src_attr->static_rate;
+ attr.ah_flags = src_attr->is_global ? IB_AH_GRH : 0;
+ attr.port_num = src_attr->port_num;
+ attr.grh.flow_label = src_attr->grh.flow_label;
+ attr.grh.sgid_index = src_attr->grh.sgid_index;
+ attr.grh.hop_limit = src_attr->grh.hop_limit;
+ attr.grh.traffic_class = src_attr->grh.traffic_class;
+ memcpy(attr.grh.dgid.raw, src_attr->grh.dgid, 16);
+
+ if (src_attr->comp_mask & IB_UVERBS_AH_ATTR_DMAC)
+ memcpy(attr.dmac, src_attr->dmac, sizeof(attr.dmac));
+ else
+ memset(attr.dmac, 0, sizeof(attr.dmac));
ah = ib_create_ah(pd, &attr);
if (IS_ERR(ah)) {
@@ -2439,22 +2558,61 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
}
ah->uobject = uobj;
+
uobj->object = ah;
ret = idr_add_uobj(&ib_uverbs_ah_idr, uobj);
if (ret)
goto err_destroy;
+ put_pd_read(pd);
+
+ return uobj;
+
+err_destroy:
+ ib_destroy_ah(ah);
+err_put:
+ put_pd_read(pd);
+err:
+ put_uobj_write(uobj);
+ return (void *)ret;
+}
+
+ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
+ const char __user *buf, int in_len,
+ int out_len)
+{
+ struct ib_uverbs_create_ah_ex cmd_ex;
+ struct ib_uverbs_create_ah *cmd = (struct ib_uverbs_create_ah *)
+ ((void *)&cmd_ex +
+ sizeof(cmd_ex.comp_mask));
+ struct ib_uverbs_ah_attr_ex attr_ex;
+ struct ib_uverbs_create_ah_resp resp;
+ struct ib_uobject *uobj;
+ int ret;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ cmd_ex.comp_mask = 0;
+ if (copy_from_user(cmd, buf, sizeof(*cmd)))
+ return -EFAULT;
+
+ attr_ex.comp_mask = 0;
+ memcpy(&attr_ex, &cmd->attr, sizeof(cmd->attr));
+
+ uobj = ib_uverbs_create_ah_assign(&cmd_ex, &attr_ex, file);
+ if (IS_ERR(uobj))
+ return (ssize_t)uobj;
+
resp.ah_handle = uobj->id;
- if (copy_to_user((void __user *) (unsigned long) cmd.response,
+ if (copy_to_user((void __user *)(unsigned long) cmd->response,
&resp, sizeof resp)) {
ret = -EFAULT;
goto err_copy;
}
- put_pd_read(pd);
-
mutex_lock(&file->mutex);
list_add_tail(&uobj->list, &file->ucontext->ah_list);
mutex_unlock(&file->mutex);
@@ -2467,15 +2625,54 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
err_copy:
idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
+ ib_destroy_ah(uobj->object);
+ put_uobj_write(uobj);
-err_destroy:
- ib_destroy_ah(ah);
+ return ret;
+}
-err_put:
- put_pd_read(pd);
+ssize_t ib_uverbs_create_ah_ex(struct ib_uverbs_file *file,
+ const char __user *buf, int in_len,
+ int out_len)
+{
+ struct ib_uverbs_create_ah_ex cmd_ex;
+ struct ib_uverbs_create_ah_resp resp;
+ struct ib_uobject *uobj;
+ int ret;
-err:
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ if (copy_from_user(&cmd_ex, buf, sizeof(cmd_ex)))
+ return -EFAULT;
+
+ uobj = ib_uverbs_create_ah_assign(&cmd_ex, &cmd_ex.attr, file);
+ if (IS_ERR(uobj))
+ return (ssize_t)uobj;
+
+ resp.ah_handle = uobj->id;
+
+ if (copy_to_user((void __user *)(unsigned long)cmd_ex.response,
+ &resp, sizeof(resp))) {
+ ret = -EFAULT;
+ goto err_copy;
+ }
+
+ mutex_lock(&file->mutex);
+ list_add_tail(&uobj->list, &file->ucontext->ah_list);
+ mutex_unlock(&file->mutex);
+
+ uobj->live = 1;
+
+ up_write(&uobj->mutex);
+
+ return in_len;
+
+err_copy:
+ idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
+ ib_destroy_ah(uobj->object);
put_uobj_write(uobj);
+
return ret;
}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 75ad86c..f1cc3f0 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -116,7 +116,9 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
[IB_USER_VERBS_CMD_CREATE_XSRQ] = ib_uverbs_create_xsrq,
[IB_USER_VERBS_CMD_OPEN_QP] = ib_uverbs_open_qp,
[IB_USER_VERBS_CMD_CREATE_FLOW] = ib_uverbs_create_flow,
- [IB_USER_VERBS_CMD_DESTROY_FLOW] = ib_uverbs_destroy_flow
+ [IB_USER_VERBS_CMD_DESTROY_FLOW] = ib_uverbs_destroy_flow,
+ [IB_USER_VERBS_CMD_MODIFY_QP_EX] = ib_uverbs_modify_qp_ex,
+ [IB_USER_VERBS_CMD_CREATE_AH_EX] = ib_uverbs_create_ah_ex
};
static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c
index e7bee46..7f7a7e2 100644
--- a/drivers/infiniband/core/uverbs_marshall.c
+++ b/drivers/infiniband/core/uverbs_marshall.c
@@ -31,6 +31,7 @@
*/
#include <linux/export.h>
+#include <linux/etherdevice.h>
#include <rdma/ib_marshall.h>
void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
@@ -52,6 +53,17 @@ void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
}
EXPORT_SYMBOL(ib_copy_ah_attr_to_user);
+void ib_copy_ah_attr_to_user_ex(struct ib_uverbs_ah_attr_ex *dst,
+ struct ib_ah_attr *src)
+{
+ dst->comp_mask = 0;
+ ib_copy_ah_attr_to_user((struct ib_uverbs_ah_attr *)
+ dst, src);
+ dst->comp_mask |= IB_UVERBS_AH_ATTR_DMAC;
+ memcpy(dst->dmac, src->dmac, sizeof(dst->dmac));
+}
+EXPORT_SYMBOL(ib_copy_ah_attr_to_user_ex);
+
void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
struct ib_qp_attr *src)
{
@@ -65,15 +77,15 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
dst->dest_qp_num = src->dest_qp_num;
dst->qp_access_flags = src->qp_access_flags;
+ ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
+ ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr);
+
dst->max_send_wr = src->cap.max_send_wr;
dst->max_recv_wr = src->cap.max_recv_wr;
dst->max_send_sge = src->cap.max_send_sge;
dst->max_recv_sge = src->cap.max_recv_sge;
dst->max_inline_data = src->cap.max_inline_data;
- ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
- ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr);
-
dst->pkey_index = src->pkey_index;
dst->alt_pkey_index = src->alt_pkey_index;
dst->en_sqd_async_notify = src->en_sqd_async_notify;
@@ -91,6 +103,63 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
}
EXPORT_SYMBOL(ib_copy_qp_attr_to_user);
+void ib_copy_qp_attr_to_user_ex(struct ib_uverbs_qp_attr_ex *dst,
+ struct ib_qp_attr *src)
+{
+ struct ib_uverbs_ah_attr_ex ah_attr_ex;
+ struct ib_uverbs_ah_attr_ex alt_ah_attr_ex;
+
+ ib_copy_qp_attr_to_user((struct ib_uverbs_qp_attr *)
+ dst, src);
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_AH_EX &&
+ !is_zero_ether_addr(src->ah_attr.dmac)) {
+ ib_copy_ah_attr_to_user_ex(&ah_attr_ex, &src->ah_attr);
+ if (dst->ah_attr_ex == NULL ||
+ copy_to_user(dst->ah_attr_ex, &ah_attr_ex,
+ sizeof(ah_attr_ex)))
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_AH_EX;
+ } else {
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_AH_EX;
+ }
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_ALT_AH_EX &&
+ !is_zero_ether_addr(src->alt_ah_attr.dmac)) {
+ ib_copy_ah_attr_to_user_ex(&alt_ah_attr_ex, &src->alt_ah_attr);
+ if (dst->alt_ah_attr_ex == NULL ||
+ copy_to_user(dst->alt_ah_attr_ex, &alt_ah_attr_ex,
+ sizeof(alt_ah_attr_ex)))
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_AH_EX;
+ } else {
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_AH_EX;
+ }
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_SMAC &&
+ !is_zero_ether_addr(src->smac))
+ memcpy(dst->smac, src->smac, sizeof(dst->smac));
+ else
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_SMAC;
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_ALT_SMAC &&
+ !is_zero_ether_addr(src->alt_smac))
+ memcpy(dst->alt_smac, src->alt_smac, sizeof(dst->alt_smac));
+ else
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_ALT_SMAC;
+
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_SMAC &&
+ src->vlan_id != 0xFFFF)
+ dst->vlan_id = src->vlan_id;
+ else
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_VID;
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_VID &&
+ src->vlan_id != 0xFFFF)
+ dst->vlan_id = src->vlan_id;
+ else
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_VID;
+ if (dst->comp_mask & IB_UVERBS_QP_ATTR_ALT_VID &&
+ src->alt_vlan_id != 0xFFFF)
+ dst->alt_vlan_id = src->alt_vlan_id;
+ else
+ dst->comp_mask &= ~IB_UVERBS_QP_ATTR_VID;
+}
+EXPORT_SYMBOL(ib_copy_qp_attr_to_user_ex);
+
void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
struct ib_sa_path_rec *src)
{
@@ -117,11 +186,26 @@ void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
}
EXPORT_SYMBOL(ib_copy_path_rec_to_user);
-void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst,
- struct ib_user_path_rec *src)
+void ib_copy_path_rec_to_user_ex(struct ib_user_path_rec_ex *dst,
+ struct ib_sa_path_rec *src)
{
- memcpy(dst->dgid.raw, src->dgid, sizeof dst->dgid);
- memcpy(dst->sgid.raw, src->sgid, sizeof dst->sgid);
+ ib_copy_path_rec_to_user((struct ib_user_path_rec *)dst, src);
+
+ dst->comp_mask = IB_USER_PATH_REC_ATTR_DMAC |
+ IB_USER_PATH_REC_ATTR_SMAC |
+ IB_USER_PATH_REC_ATTR_VID;
+
+ memcpy(dst->dmac, src->dmac, sizeof(dst->dmac));
+ memcpy(dst->smac, src->smac, sizeof(dst->smac));
+ dst->vlan_id = src->vlan_id;
+}
+EXPORT_SYMBOL(ib_copy_path_rec_to_user_ex);
+
+static void ib_copy_path_rec_from_user_assign(struct ib_sa_path_rec *dst,
+ struct ib_user_path_rec *src)
+{
+ memcpy(dst->dgid.raw, src->dgid, sizeof(dst->dgid));
+ memcpy(dst->sgid.raw, src->sgid, sizeof(dst->sgid));
dst->dlid = src->dlid;
dst->slid = src->slid;
@@ -141,4 +225,34 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst,
dst->preference = src->preference;
dst->packet_life_time_selector = src->packet_life_time_selector;
}
+
+void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst,
+ struct ib_user_path_rec *src) {
+ memset(dst->dmac, 0, sizeof(dst->dmac));
+ memset(dst->smac, 0, sizeof(dst->smac));
+ dst->vlan_id = 0xFFFF;
+
+ ib_copy_path_rec_from_user_assign(dst, src);
+}
EXPORT_SYMBOL(ib_copy_path_rec_from_user);
+
+void ib_copy_path_rec_from_user_ex(struct ib_sa_path_rec *dst,
+ struct ib_user_path_rec_ex *src) {
+ if (src->comp_mask & IB_USER_PATH_REC_ATTR_DMAC)
+ memcpy(dst->dmac, src->dmac, sizeof(dst->dmac));
+ else
+ memset(dst->dmac, 0, sizeof(dst->dmac));
+
+ if (src->comp_mask & IB_USER_PATH_REC_ATTR_SMAC)
+ memcpy(dst->smac, src->smac, sizeof(dst->smac));
+ else
+ memset(dst->smac, 0, sizeof(dst->smac));
+
+ if (src->comp_mask & IB_USER_PATH_REC_ATTR_VID)
+ dst->vlan_id = src->vlan_id;
+ else
+ dst->vlan_id = 0xFFFF;
+
+ ib_copy_path_rec_from_user_assign(dst, (struct ib_user_path_rec *)src);
+}
+EXPORT_SYMBOL(ib_copy_path_rec_from_user_ex);
diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h
index db03720..11ab3a8 100644
--- a/include/rdma/ib_marshall.h
+++ b/include/rdma/ib_marshall.h
@@ -41,13 +41,25 @@
void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
struct ib_qp_attr *src);
+void ib_copy_qp_attr_to_user_ex(struct ib_uverbs_qp_attr_ex *dst,
+ struct ib_qp_attr *src);
+
void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
struct ib_ah_attr *src);
+void ib_copy_ah_attr_to_user_ex(struct ib_uverbs_ah_attr_ex *dst,
+ struct ib_ah_attr *src);
+
void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
struct ib_sa_path_rec *src);
+void ib_copy_path_rec_to_user_ex(struct ib_user_path_rec_ex *dst,
+ struct ib_sa_path_rec *src);
+
void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst,
struct ib_user_path_rec *src);
+void ib_copy_path_rec_from_user_ex(struct ib_sa_path_rec *dst,
+ struct ib_user_path_rec_ex *src);
+
#endif /* IB_USER_MARSHALL_H */
diff --git a/include/uapi/rdma/ib_user_sa.h b/include/uapi/rdma/ib_user_sa.h
index cfc7c9b..8a24e10 100644
--- a/include/uapi/rdma/ib_user_sa.h
+++ b/include/uapi/rdma/ib_user_sa.h
@@ -48,7 +48,13 @@ enum {
struct ib_path_rec_data {
__u32 flags;
__u32 reserved;
- __u32 path_rec[16];
+ __u32 path_rec[20];
+};
+
+enum ibv_kern_path_rec_attr_mask {
+ IB_USER_PATH_REC_ATTR_DMAC = 1ULL << 0,
+ IB_USER_PATH_REC_ATTR_SMAC = 1ULL << 1,
+ IB_USER_PATH_REC_ATTR_VID = 1ULL << 2
};
struct ib_user_path_rec {
@@ -73,4 +79,30 @@ struct ib_user_path_rec {
__u8 preference;
};
+struct ib_user_path_rec_ex {
+ __u8 dgid[16];
+ __u8 sgid[16];
+ __be16 dlid;
+ __be16 slid;
+ __u32 raw_traffic;
+ __be32 flow_label;
+ __u32 reversible;
+ __u32 mtu;
+ __be16 pkey;
+ __u8 hop_limit;
+ __u8 traffic_class;
+ __u8 numb_path;
+ __u8 sl;
+ __u8 mtu_selector;
+ __u8 rate_selector;
+ __u8 rate;
+ __u8 packet_life_time_selector;
+ __u8 packet_life_time;
+ __u8 preference;
+ __u32 comp_mask;
+ __u8 smac[ETH_ALEN];
+ __u8 dmac[ETH_ALEN];
+ u16 vlan_id;
+};
+
#endif /* IB_USER_SA_H */
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 0b233c5..f1939cf 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -37,6 +37,7 @@
#define IB_USER_VERBS_H
#include <linux/types.h>
+#include <linux/if_ether.h>
/*
* Increment this value if any changes that break userspace ABI
@@ -88,7 +89,9 @@ enum {
IB_USER_VERBS_CMD_CREATE_XSRQ,
IB_USER_VERBS_CMD_OPEN_QP,
IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
- IB_USER_VERBS_CMD_DESTROY_FLOW
+ IB_USER_VERBS_CMD_DESTROY_FLOW,
+ IB_USER_VERBS_CMD_MODIFY_QP_EX,
+ IB_USER_VERBS_CMD_CREATE_AH_EX
};
/*
@@ -394,6 +397,24 @@ struct ib_uverbs_ah_attr {
__u8 reserved;
};
+enum ib_uverbs_ah_attr_mask {
+ IB_UVERBS_AH_ATTR_DMAC,
+ IB_UVERBS_AH_ATTR_VID
+};
+
+struct ib_uverbs_ah_attr_ex {
+ struct ib_uverbs_global_route grh;
+ __u16 dlid;
+ __u8 sl;
+ __u8 src_path_bits;
+ __u8 static_rate;
+ __u8 is_global;
+ __u8 port_num;
+ __u8 reserved;
+ __u32 comp_mask;
+ __u8 dmac[ETH_ALEN];
+};
+
struct ib_uverbs_qp_attr {
__u32 qp_attr_mask;
__u32 qp_state;
@@ -432,6 +453,65 @@ struct ib_uverbs_qp_attr {
__u8 reserved[5];
};
+enum ib_uverbs_qh_attr_mask {
+ IB_UVERBS_QP_ATTR_AH_EX = 1 << 0,
+ IB_UVERBS_QP_ATTR_ALT_AH_EX = 1 << 1,
+ IB_UVERBS_QP_ATTR_SMAC = 1 << 2,
+ IB_UVERBS_QP_ATTR_ALT_SMAC = 1 << 3,
+ IB_UVERBS_QP_ATTR_VID = 1 << 4,
+ IB_UVERBS_QP_ATTR_ALT_VID = 1 << 5,
+};
+
+struct ib_uverbs_qp_attr_ex {
+ __u32 qp_attr_mask;
+ __u32 qp_state;
+ __u32 cur_qp_state;
+ __u32 path_mtu;
+ __u32 path_mig_state;
+ __u32 qkey;
+ __u32 rq_psn;
+ __u32 sq_psn;
+ __u32 dest_qp_num;
+ __u32 qp_access_flags;
+
+ /* deprecated for extension */
+ struct ib_uverbs_ah_attr ah_attr;
+ /* deprecated for extension */
+ struct ib_uverbs_ah_attr alt_ah_attr;
+
+ /* ib_qp_cap */
+ __u32 max_send_wr;
+ __u32 max_recv_wr;
+ __u32 max_send_sge;
+ __u32 max_recv_sge;
+ __u32 max_inline_data;
+
+ __u16 pkey_index;
+ __u16 alt_pkey_index;
+ __u8 en_sqd_async_notify;
+ __u8 sq_draining;
+ __u8 max_rd_atomic;
+ __u8 max_dest_rd_atomic;
+ __u8 min_rnr_timer;
+ __u8 port_num;
+ __u8 timeout;
+ __u8 retry_cnt;
+ __u8 rnr_retry;
+ __u8 alt_port_num;
+ __u8 alt_timeout;
+ __u8 reserved[5];
+
+ __u32 comp_mask;
+ /* represents: struct ib_uverbs_ah_attr_ex * __user */
+ void __user *ah_attr_ex;
+ /* represents: struct ib_uverbs_ah_attr_ex * __user */
+ void __user *alt_ah_attr_ex;
+ __u8 smac[ETH_ALEN];
+ __u8 alt_smac[ETH_ALEN];
+ __u16 vlan_id;
+ __u16 alt_vlan_id;
+};
+
struct ib_uverbs_create_qp {
__u64 response;
__u64 user_handle;
@@ -492,6 +572,27 @@ struct ib_uverbs_qp_dest {
__u8 port_num;
};
+enum ib_uverbs_qp_dest_attr_mask {
+ IB_UVERBS_QP_DEST_ATTR_DMAC = 1ULL << 0
+};
+
+struct ib_uverbs_qp_dest_ex {
+ __u8 dgid[16];
+ __u32 flow_label;
+ __u16 dlid;
+ __u16 reserved;
+ __u8 sgid_index;
+ __u8 hop_limit;
+ __u8 traffic_class;
+ __u8 sl;
+ __u8 src_path_bits;
+ __u8 static_rate;
+ __u8 is_global;
+ __u8 port_num;
+ __u32 comp_mask;
+ __u8 dmac[ETH_ALEN];
+};
+
struct ib_uverbs_query_qp {
__u64 response;
__u32 qp_handle;
@@ -563,6 +664,54 @@ struct ib_uverbs_modify_qp {
__u64 driver_data[0];
};
+enum ib_uverbs_modify_qp_ex_comp_mask {
+ IB_UVERBS_MODIFY_QP_EX_SMAC = (1ULL << 0),
+ IB_UVERBS_MODIFY_QP_EX_ALT_SMAC = (1ULL << 1),
+ IB_UVERBS_MODIFY_QP_EX_VID = (1ULL << 2),
+ IB_UVERBS_MODIFY_QP_EX_ALT_VID = (1ULL << 3),
+ IB_UVERBS_MODIFY_QP_EX_DEST_EX = (1ULL << 4),
+ IB_UVERBS_MODIFY_QP_EX_ALT_DEST_EX = (1ULL << 5)
+};
+
+struct ib_uverbs_modify_qp_ex {
+ __u32 comp_mask;
+ struct ib_uverbs_qp_dest dest;
+ struct ib_uverbs_qp_dest alt_dest;
+ __u32 qp_handle;
+ __u32 attr_mask;
+ __u32 qkey;
+ __u32 rq_psn;
+ __u32 sq_psn;
+ __u32 dest_qp_num;
+ __u32 qp_access_flags;
+ __u16 pkey_index;
+ __u16 alt_pkey_index;
+ __u8 qp_state;
+ __u8 cur_qp_state;
+ __u8 path_mtu;
+ __u8 path_mig_state;
+ __u8 en_sqd_async_notify;
+ __u8 max_rd_atomic;
+ __u8 max_dest_rd_atomic;
+ __u8 min_rnr_timer;
+ __u8 port_num;
+ __u8 timeout;
+ __u8 retry_cnt;
+ __u8 rnr_retry;
+ __u8 alt_port_num;
+ __u8 alt_timeout;
+ __u8 reserved[2];
+ __u8 smac[ETH_ALEN];
+ __u8 alt_smac[ETH_ALEN];
+ __u16 vid;
+ __u16 alt_vid;
+ /* represents: struct ib_uverbs_qp_dest_ex * __user */
+ void __user *dest_ex;
+ /* represents: struct ib_uverbs_qp_dest_ex * __user */
+ void __user *alt_dest_ex;
+ __u64 driver_data[0];
+};
+
struct ib_uverbs_modify_qp_resp {
};
@@ -672,6 +821,15 @@ struct ib_uverbs_create_ah {
struct ib_uverbs_ah_attr attr;
};
+struct ib_uverbs_create_ah_ex {
+ __u32 comp_mask;
+ __u64 response;
+ __u64 user_handle;
+ __u32 pd_handle;
+ __u32 reserved;
+ struct ib_uverbs_ah_attr_ex attr;
+};
+
struct ib_uverbs_create_ah_resp {
__u32 ah_handle;
};
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 8/9] IB/core: Add RoCE IP based addressing extensions for rdma_ucm
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (6 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 7/9] IB/core: Add RoCE IP based addressing extensions for uverbs Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
[not found] ` <1378824099-22150-9-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-09-10 14:41 ` [PATCH V4 9/9] IB/mlx4: Enable mlx4_ib support for MODIFY_QP_EX Or Gerlitz
8 siblings, 1 reply; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Add rdma_ucm support for RoCE (IBoE) IP based addressing extensions
towards librdmacm
Extend INIT_QP_ATTR and QUERY_ROUTE ucma commands.
INIT_QP_ATTR_EX uses struct ib_uverbs_qp_attr_ex
QUERY_ROUTE_EX uses struct rdma_ucm_query_route_resp_ex which in turn
uses ib_user_path_rec_ex
Signed-off-by: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 175 ++++++++++++++++++++++++++++++++++++-
include/uapi/rdma/rdma_user_cm.h | 29 ++++++-
2 files changed, 198 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7e7da86..4d59e88 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -652,6 +652,35 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
}
}
+static void ucma_copy_ib_route_ex(struct rdma_ucm_query_route_resp_ex *resp,
+ struct rdma_route *route)
+{
+ struct rdma_dev_addr *dev_addr;
+
+ resp->num_paths = route->num_paths;
+ switch (route->num_paths) {
+ case 0:
+ dev_addr = &route->addr.dev_addr;
+ rdma_addr_get_dgid(dev_addr,
+ (union ib_gid *)&resp->ib_route[0].dgid);
+ rdma_addr_get_sgid(dev_addr,
+ (union ib_gid *)&resp->ib_route[0].sgid);
+ resp->ib_route[0].pkey =
+ cpu_to_be16(ib_addr_get_pkey(dev_addr));
+ break;
+ case 2:
+ ib_copy_path_rec_to_user_ex(&resp->ib_route[1],
+ &route->path_rec[1]);
+ /* fall through */
+ case 1:
+ ib_copy_path_rec_to_user_ex(&resp->ib_route[0],
+ &route->path_rec[0]);
+ break;
+ default:
+ break;
+ }
+}
+
static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
struct rdma_route *route)
{
@@ -678,14 +707,39 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
}
}
-static void ucma_copy_iw_route(struct rdma_ucm_query_route_resp *resp,
+static void ucma_copy_iboe_route_ex(struct rdma_ucm_query_route_resp_ex *resp,
+ struct rdma_route *route)
+{
+ resp->num_paths = route->num_paths;
+ switch (route->num_paths) {
+ case 0:
+ rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
+ (union ib_gid *)&resp->ib_route[0].dgid);
+ rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
+ (union ib_gid *)&resp->ib_route[0].sgid);
+ resp->ib_route[0].pkey = cpu_to_be16(0xffff);
+ break;
+ case 2:
+ ib_copy_path_rec_to_user_ex(&resp->ib_route[1],
+ &route->path_rec[1]);
+ /* fall through */
+ case 1:
+ ib_copy_path_rec_to_user_ex(&resp->ib_route[0],
+ &route->path_rec[0]);
+ break;
+ default:
+ break;
+ }
+}
+
+static void ucma_copy_iw_route(struct ib_user_path_rec *resp_path,
struct rdma_route *route)
{
struct rdma_dev_addr *dev_addr;
dev_addr = &route->addr.dev_addr;
- rdma_addr_get_dgid(dev_addr, (union ib_gid *) &resp->ib_route[0].dgid);
- rdma_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid);
+ rdma_addr_get_dgid(dev_addr, (union ib_gid *)&resp_path->dgid);
+ rdma_addr_get_sgid(dev_addr, (union ib_gid *)&resp_path->sgid);
}
static ssize_t ucma_query_route(struct ucma_file *file,
@@ -737,7 +791,74 @@ static ssize_t ucma_query_route(struct ucma_file *file,
}
break;
case RDMA_TRANSPORT_IWARP:
- ucma_copy_iw_route(&resp, &ctx->cm_id->route);
+ ucma_copy_iw_route(&resp.ib_route[0], &ctx->cm_id->route);
+ break;
+ default:
+ break;
+ }
+
+out:
+ if (copy_to_user((void __user *)(unsigned long)cmd.response,
+ &resp, sizeof(resp)))
+ ret = -EFAULT;
+
+ ucma_put_ctx(ctx);
+ return ret;
+}
+
+static ssize_t ucma_query_route_ex(struct ucma_file *file,
+ const char __user *inbuf,
+ int in_len, int out_len)
+{
+ struct rdma_ucm_query_route_ex cmd;
+ struct rdma_ucm_query_route_resp_ex resp;
+ struct ucma_context *ctx;
+ struct sockaddr *addr;
+ int ret = 0;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
+ return -EFAULT;
+
+ ctx = ucma_get_ctx(file, cmd.id);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ memset(&resp, 0, sizeof(resp));
+ addr = (struct sockaddr *)&ctx->cm_id->route.addr.src_addr;
+ memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ?
+ sizeof(struct sockaddr_in) :
+ sizeof(struct sockaddr_in6));
+ addr = (struct sockaddr *)&ctx->cm_id->route.addr.dst_addr;
+ memcpy(&resp.dst_addr, addr, addr->sa_family == AF_INET ?
+ sizeof(struct sockaddr_in) :
+ sizeof(struct sockaddr_in6));
+ if (!ctx->cm_id->device)
+ goto out;
+
+ resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid;
+ resp.port_num = ctx->cm_id->port_num;
+ switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) {
+ case RDMA_TRANSPORT_IB:
+ switch (rdma_port_get_link_layer(ctx->cm_id->device,
+ ctx->cm_id->port_num)) {
+ case IB_LINK_LAYER_INFINIBAND:
+ ucma_copy_ib_route_ex(&resp, &ctx->cm_id->route);
+ break;
+ case IB_LINK_LAYER_ETHERNET:
+ ucma_copy_iboe_route_ex(&resp, &ctx->cm_id->route);
+ break;
+ default:
+ break;
+ }
+ break;
+ case RDMA_TRANSPORT_IWARP:
+ ucma_copy_iw_route((struct ib_user_path_rec *)
+ ((void *)&resp.ib_route[0] +
+ sizeof(resp.ib_route[0].comp_mask)),
+ &ctx->cm_id->route);
break;
default:
break;
@@ -1071,6 +1192,48 @@ out:
return ret;
}
+static ssize_t ucma_init_qp_attr_ex(struct ucma_file *file,
+ const char __user *inbuf,
+ int in_len, int out_len)
+{
+ struct rdma_ucm_init_qp_attr_ex cmd;
+ struct ib_uverbs_qp_attr_ex resp;
+ struct ucma_context *ctx;
+ struct ib_qp_attr qp_attr;
+ int ret;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
+ return -EFAULT;
+
+ if (copy_from_user(&resp, (void __user *)(unsigned long)cmd.response,
+ sizeof(resp)))
+ return -EFAULT;
+
+ ctx = ucma_get_ctx(file, cmd.id);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ resp.comp_mask = cmd.comp_mask;
+ resp.qp_attr_mask = 0;
+ memset(&qp_attr, 0, sizeof(qp_attr));
+ qp_attr.qp_state = cmd.qp_state;
+ ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask);
+ if (ret)
+ goto out;
+
+ ib_copy_qp_attr_to_user_ex(&resp, &qp_attr);
+ if (copy_to_user((void __user *)(unsigned long)cmd.response,
+ &resp, sizeof(resp)))
+ ret = -EFAULT;
+
+out:
+ ucma_put_ctx(ctx);
+ return ret;
+}
+
static int ucma_set_option_id(struct ucma_context *ctx, int optname,
void *optval, size_t optlen)
{
@@ -1474,7 +1637,9 @@ static ssize_t (*ucma_cmd_table[])(struct ucma_file *file,
[RDMA_USER_CM_CMD_QUERY] = ucma_query,
[RDMA_USER_CM_CMD_BIND] = ucma_bind,
[RDMA_USER_CM_CMD_RESOLVE_ADDR] = ucma_resolve_addr,
- [RDMA_USER_CM_CMD_JOIN_MCAST] = ucma_join_multicast
+ [RDMA_USER_CM_CMD_JOIN_MCAST] = ucma_join_multicast,
+ [RDMA_USER_CM_CMD_QUERY_ROUTE_EX] = ucma_query_route_ex,
+ [RDMA_USER_CM_CMD_INIT_QP_ATTR_EX] = ucma_init_qp_attr_ex
};
static ssize_t ucma_write(struct file *filp, const char __user *buf,
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
index 99b80ab..ceb7f1f 100644
--- a/include/uapi/rdma/rdma_user_cm.h
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -65,7 +65,9 @@ enum {
RDMA_USER_CM_CMD_QUERY,
RDMA_USER_CM_CMD_BIND,
RDMA_USER_CM_CMD_RESOLVE_ADDR,
- RDMA_USER_CM_CMD_JOIN_MCAST
+ RDMA_USER_CM_CMD_JOIN_MCAST,
+ RDMA_USER_CM_CMD_QUERY_ROUTE_EX,
+ RDMA_USER_CM_CMD_INIT_QP_ATTR_EX
};
/*
@@ -146,6 +148,13 @@ struct rdma_ucm_query {
__u32 option;
};
+struct rdma_ucm_query_route_ex {
+ __u32 comp_mask;
+ __u64 response;
+ __u32 id;
+ __u32 reserved;
+};
+
struct rdma_ucm_query_route_resp {
__u64 node_guid;
struct ib_user_path_rec ib_route[2];
@@ -173,6 +182,16 @@ struct rdma_ucm_query_path_resp {
struct ib_path_rec_data path_data[0];
};
+struct rdma_ucm_query_route_resp_ex {
+ __u64 node_guid;
+ struct ib_user_path_rec_ex ib_route[2];
+ struct sockaddr_in6 src_addr;
+ struct sockaddr_in6 dst_addr;
+ __u32 num_paths;
+ __u8 port_num;
+ __u8 reserved[3];
+};
+
struct rdma_ucm_conn_param {
__u32 qp_num;
__u32 qkey;
@@ -231,6 +250,14 @@ struct rdma_ucm_init_qp_attr {
__u32 qp_state;
};
+struct rdma_ucm_init_qp_attr_ex {
+ __u32 comp_mask;
+ __u32 reserved;
+ __u64 response;
+ __u32 id;
+ __u32 qp_state;
+};
+
struct rdma_ucm_notify {
__u32 id;
__u32 event;
--
1.7.1
--
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 [flat|nested] 31+ messages in thread
* [PATCH V4 9/9] IB/mlx4: Enable mlx4_ib support for MODIFY_QP_EX
[not found] ` <1378824099-22150-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (7 preceding siblings ...)
2013-09-10 14:41 ` [PATCH V4 8/9] IB/core: Add RoCE IP based addressing extensions for rdma_ucm Or Gerlitz
@ 2013-09-10 14:41 ` Or Gerlitz
[not found] ` <1378824099-22150-10-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
8 siblings, 1 reply; 31+ messages in thread
From: Or Gerlitz @ 2013-09-10 14:41 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, monis-VPRAkNaXOzVWk0Htik3J/w,
matanb-VPRAkNaXOzVWk0Htik3J/w, Or Gerlitz
From: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
mlx4_ib driver should indicate that it supports
MODIFY_QP_EX user verbs extended command.
Signed-off-by: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/main.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 7a29ad5..77c87d0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1755,7 +1755,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
(1ull << IB_USER_VERBS_CMD_QUERY_SRQ) |
(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ) |
(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) |
- (1ull << IB_USER_VERBS_CMD_OPEN_QP);
+ (1ull << IB_USER_VERBS_CMD_OPEN_QP) |
+ (1ull << IB_USER_VERBS_CMD_MODIFY_QP_EX);
ibdev->ib_dev.query_device = mlx4_ib_query_device;
ibdev->ib_dev.query_port = mlx4_ib_query_port;
--
1.7.1
--
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 [flat|nested] 31+ messages in thread