git: 1d99feddd681 - main - OFED: Various changes from Linux 4.16
- Go to: [ bottom of page ] [ top of archives ] [ this month ]
Date: Wed, 24 Jun 2026 19:51:15 UTC
The branch main has been updated by jhb:
URL: https://cgit.FreeBSD.org/src/commit/?id=1d99feddd681da05dfa9091870403bc9ceb94550
commit 1d99feddd681da05dfa9091870403bc9ceb94550
Author: John Baldwin <jhb@FreeBSD.org>
AuthorDate: 2026-06-24 19:30:56 +0000
Commit: John Baldwin <jhb@FreeBSD.org>
CommitDate: 2026-06-24 19:30:56 +0000
OFED: Various changes from Linux 4.16
This contains changes from the following Linux commits:
c5c4e40e90b5 IB/CM: Change sgid to IB GID when handling CM request
54a6d63f14bd IB/mlx4: Potential buffer overflow in _mlx4_set_path()
56d0a7d9a0f0 IB/core: Depend on IPv6 stack to resolve link local address for RoCEv2
1060f8653414 IB/{core/cm}: Fix generating a return AH for RoCEE
981b5a2384b7 RDMA/cma: Introduce and use helper functions to init work
c42388053758 RDMA/cma: Avoid setting path record type twice
4367ec7fe2dd RDMA/cma: Simplify netdev check
151ed9d70097 IB/core: Refactor to avoid unnecessary check on GID lookup miss
b0dd0d335364 IB/core: Avoid unnecessary type cast
86937fcd6ed2 RDMA/core: Avoid redundant memcpy in rdma_addr_find_l2_eth_by_grh
1c43d5d308f0 IB/core: Avoid exporting module internal ib_find_gid_by_filter()
dbb12562f7c2 IB/{core, ipoib}: Simplify ib_find_gid to search only for IB link layer
f6bdb14267ba IB/{core, umad, cm}: Rename ib_init_ah_from_wc to ib_init_ah_attr_from_wc
4ad6a0245ec8 IB/{core, cm, cma, ipoib}: Rename ib_init_ah_from_path to ib_init_ah_attr_from_path
33f93e1ebcf5 IB/cm: Fix sleeping while spin lock is held
16c72e402867 IB/cm: Refactor to avoid setting path record software only fields
af808ece5ce9 IB/SA: Check dlid before SA agent queries for ClassPortInfo
8d20a1f0ecd5 RDMA/cma: Fix rdma_cm raw IB path setting for RoCE
fe75889f2794 RDMA/{cma, ucma}: Simplify and rename rdma_set_ib_paths
9327c7afdce3 RDMA/cma: Provide a function to set RoCE path record L2 parameters
89838118a515 RDMA/cma: Fix rdma_cm path querying for RoCE
cd2a6e7d384b IB/core: Fix ib_wc structure size to remain in 64 bytes boundary
f2290d6d522d IB/core: Attempt DMAC resolution for only RoCE
a6532e713966 RDMA/core: Clarify rdma_ah_find_type
246d8b184c10 IB/cq: Don't force IB_POLL_DIRECT poll context for ib_process_cq_direct
aaebd377c0e9 IB/core: postpone WR initialization during queue drain
15cbc5197693 RDMA/core: Simplify rdma_addr_get_sgid() to not support RoCE
7a2f64ee4a95 RDMA/ucma: Use rdma cm API to query GID
411460ac50b0 RDMA/cma: Introduce API to read GIDs for multiple transports
2493a57bc10f RDMA/cma: Refactor to access multiple fields of rdma_dev_addr
00db63c128dd RDMA/cma: Check existence of netdevice during port validation
925f7ea7a6ba RDMA/cm: Fix access to uninitialized variable
87daac68f77a IB/core: Map iWarp AH type to undefined in rdma_ah_find_type
87915bf82eea RDMA/verbs: Return proper error code for not supported system call
d3b9e8ad425c RDMA/core: Reduce poll batch for direct cq polling
Parts of 1060f8653414 were already merged into FreeBSD. Cosmetic
changes made in rdma_addr_find_l2_eth_by_grh while merging this change
were just to reduce the diff with Linux to ease merging future
changes.
The merge of 56d0a7d9a0f0 differs slightly from the Linux commit as
FreeBSD was missing the original changes to check for link-local
addresses in ib_resolve_eth_dmac.
The merge of 2493a57bc10f is mostly a cosmetic change to reduce diffs
with upstream as local changes in FreeBSD passed the dev_addr as the
last argument instead of the dev_type and if_index already.
Tested by: Wafa Hamzah <wafah@nvidia.com> (mlx5_ib)
Tested by: John Baldwin <jhb@FreeBSD.org> (iw_cxgbe)
Sponsored by: Chelsio Communications
---
sys/dev/mlx4/mlx4_ib/mlx4_ib_qp.c | 2 +
sys/ofed/drivers/infiniband/core/ib_addr.c | 20 +-
sys/ofed/drivers/infiniband/core/ib_cache.c | 16 +-
sys/ofed/drivers/infiniband/core/ib_cm.c | 158 +++++++++------
sys/ofed/drivers/infiniband/core/ib_cma.c | 225 +++++++++++++--------
sys/ofed/drivers/infiniband/core/ib_cq.c | 28 +--
sys/ofed/drivers/infiniband/core/ib_device.c | 16 +-
sys/ofed/drivers/infiniband/core/ib_sa_query.c | 18 +-
sys/ofed/drivers/infiniband/core/ib_ucma.c | 19 +-
sys/ofed/drivers/infiniband/core/ib_user_mad.c | 7 +-
sys/ofed/drivers/infiniband/core/ib_verbs.c | 200 +++++++++---------
sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c | 3 +-
sys/ofed/include/rdma/ib_addr.h | 41 +---
sys/ofed/include/rdma/ib_sa.h | 10 +-
sys/ofed/include/rdma/ib_verbs.h | 36 ++--
sys/ofed/include/rdma/opa_addr.h | 16 ++
sys/ofed/include/rdma/rdma_cm.h | 19 ++
sys/ofed/include/rdma/rdma_cm_ib.h | 8 +-
18 files changed, 475 insertions(+), 367 deletions(-)
diff --git a/sys/dev/mlx4/mlx4_ib/mlx4_ib_qp.c b/sys/dev/mlx4/mlx4_ib/mlx4_ib_qp.c
index e0e6d92436de..c4ab30c8bcb6 100644
--- a/sys/dev/mlx4/mlx4_ib/mlx4_ib_qp.c
+++ b/sys/dev/mlx4/mlx4_ib/mlx4_ib_qp.c
@@ -1416,6 +1416,8 @@ static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct rdma_ah_attr *ah
port,
grh->sgid_index);
+ if (real_sgid_index < 0)
+ return real_sgid_index;
if (real_sgid_index >= dev->dev->caps.gid_table_len[port]) {
pr_err("sgid_index (%u) too large. max is %d\n",
real_sgid_index, dev->dev->caps.gid_table_len[port] - 1);
diff --git a/sys/ofed/drivers/infiniband/core/ib_addr.c b/sys/ofed/drivers/infiniband/core/ib_addr.c
index ecacfd6a43dd..2a00e449ecda 100644
--- a/sys/ofed/drivers/infiniband/core/ib_addr.c
+++ b/sys/ofed/drivers/infiniband/core/ib_addr.c
@@ -877,7 +877,6 @@ 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;
int status;
};
@@ -885,33 +884,28 @@ struct resolve_cb_context {
static void resolve_cb(int status, struct sockaddr *src_addr,
struct rdma_dev_addr *addr, void *context)
{
- if (!status)
- memcpy(((struct resolve_cb_context *)context)->addr,
- addr, sizeof(struct rdma_dev_addr));
((struct resolve_cb_context *)context)->status = status;
complete(&((struct resolve_cb_context *)context)->comp);
}
int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
const union ib_gid *dgid,
- u8 *dmac, if_t dev,
+ u8 *dmac, if_t ndev,
int *hoplimit)
{
- int ret = 0;
struct rdma_dev_addr dev_addr;
struct resolve_cb_context ctx;
-
union rdma_sockaddr sgid_addr, dgid_addr;
+ int ret;
rdma_gid2ip(&sgid_addr._sockaddr, sgid);
rdma_gid2ip(&dgid_addr._sockaddr, dgid);
memset(&dev_addr, 0, sizeof(dev_addr));
- dev_addr.bound_dev_if = if_getindex(dev);
- dev_addr.net = dev_net(dev);
+ dev_addr.bound_dev_if = if_getindex(ndev);
+ dev_addr.net = dev_net(ndev);
- 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);
@@ -925,11 +919,9 @@ int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
return ret;
memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
- if (hoplimit)
- *hoplimit = dev_addr.hoplimit;
- return ret;
+ *hoplimit = dev_addr.hoplimit;
+ return 0;
}
-EXPORT_SYMBOL(rdma_addr_find_l2_eth_by_grh);
int addr_init(void)
{
diff --git a/sys/ofed/drivers/infiniband/core/ib_cache.c b/sys/ofed/drivers/infiniband/core/ib_cache.c
index a11b36f06c86..878b2915f25d 100644
--- a/sys/ofed/drivers/infiniband/core/ib_cache.c
+++ b/sys/ofed/drivers/infiniband/core/ib_cache.c
@@ -579,27 +579,24 @@ static int ib_cache_gid_find_by_filter(struct ib_device *ib_dev,
struct ib_gid_attr attr;
if (table->data_vec[i].props & GID_TABLE_ENTRY_INVALID)
- goto next;
+ continue;
if (memcmp(gid, &table->data_vec[i].gid, sizeof(*gid)))
- goto next;
+ continue;
memcpy(&attr, &table->data_vec[i].attr, sizeof(attr));
- if (filter(gid, &attr, context))
+ if (filter(gid, &attr, context)) {
found = true;
-
-next:
- if (found)
+ if (index)
+ *index = i;
break;
+ }
}
read_unlock_irqrestore(&table->rwlock, flags);
if (!found)
return -ENOENT;
-
- if (index)
- *index = i;
return 0;
}
@@ -899,7 +896,6 @@ int ib_find_gid_by_filter(struct ib_device *device,
port_num, filter,
context, index);
}
-EXPORT_SYMBOL(ib_find_gid_by_filter);
int ib_get_cached_pkey(struct ib_device *device,
u8 port_num,
diff --git a/sys/ofed/drivers/infiniband/core/ib_cm.c b/sys/ofed/drivers/infiniband/core/ib_cm.c
index be29881c73c9..215849d0ae18 100644
--- a/sys/ofed/drivers/infiniband/core/ib_cm.c
+++ b/sys/ofed/drivers/infiniband/core/ib_cm.c
@@ -474,9 +474,9 @@ static int cm_init_av_for_lap(struct cm_port *port, struct ib_wc *wc,
* used for sending any responses. If initialization is successful,
* than new ah_attr is used by overwriting old one.
*/
- ret = ib_init_ah_from_wc(port->cm_dev->ib_device,
- port->port_num, wc,
- grh, &new_ah_attr);
+ ret = ib_init_ah_attr_from_wc(port->cm_dev->ib_device,
+ port->port_num, wc,
+ grh, &new_ah_attr);
if (ret)
return ret;
@@ -489,8 +489,9 @@ static int cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
{
av->port = port;
av->pkey_index = wc->pkey_index;
- return ib_init_ah_from_wc(port->cm_dev->ib_device, port->port_num, wc,
- grh, &av->ah_attr);
+ return ib_init_ah_attr_from_wc(port->cm_dev->ib_device,
+ port->port_num, wc,
+ grh, &av->ah_attr);
}
static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
@@ -526,8 +527,8 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
return ret;
av->port = port;
- ret = ib_init_ah_from_path(cm_dev->ib_device, port->port_num,
- path, &av->ah_attr);
+ ret = ib_init_ah_attr_from_path(cm_dev->ib_device, port->port_num,
+ path, &av->ah_attr);
if (ret)
return ret;
@@ -1588,6 +1589,37 @@ static u16 cm_get_bth_pkey(struct cm_work *work)
return pkey;
}
+/**
+ * Convert OPA SGID to IB SGID
+ * ULPs (such as IPoIB) do not understand OPA GIDs and will
+ * reject them as the local_gid will not match the sgid. Therefore,
+ * change the pathrec's SGID to an IB SGID.
+ *
+ * @work: Work completion
+ * @path: Path record
+ */
+static void cm_opa_to_ib_sgid(struct cm_work *work,
+ struct sa_path_rec *path)
+{
+ struct ib_device *dev = work->port->cm_dev->ib_device;
+ struct ib_gid_attr gid_attr;
+ u8 port_num = work->port->port_num;
+
+ if (rdma_cap_opa_ah(dev, port_num) &&
+ (ib_is_opa_gid(&path->sgid))) {
+ union ib_gid sgid;
+
+ if (ib_get_cached_gid(dev, port_num, 0,
+ &sgid, &gid_attr)) {
+ dev_warn(&dev->dev,
+ "Error updating sgid in CM request\n");
+ return;
+ }
+
+ path->sgid = sgid;
+ }
+}
+
static void cm_format_req_event(struct cm_work *work,
struct cm_id_private *cm_id_priv,
struct ib_cm_id *listen_id)
@@ -1601,10 +1633,13 @@ static void cm_format_req_event(struct cm_work *work,
param->bth_pkey = cm_get_bth_pkey(work);
param->port = cm_id_priv->av.port->port_num;
param->primary_path = &work->path[0];
- if (cm_req_has_alt_path(req_msg))
+ cm_opa_to_ib_sgid(work, param->primary_path);
+ if (cm_req_has_alt_path(req_msg)) {
param->alternate_path = &work->path[1];
- else
+ cm_opa_to_ib_sgid(work, param->alternate_path);
+ } else {
param->alternate_path = NULL;
+ }
param->remote_ca_guid = req_msg->local_ca_guid;
param->remote_qkey = be32_to_cpu(req_msg->local_qkey);
param->remote_qpn = be32_to_cpu(cm_req_get_local_qpn(req_msg));
@@ -1891,56 +1926,50 @@ static int cm_req_handler(struct cm_work *work)
work->port->port_num,
grh->sgid_index,
&gid, &gid_attr);
- if (!ret) {
- if (gid_attr.ndev) {
- work->path[0].rec_type =
- sa_conv_gid_to_pathrec_type(gid_attr.gid_type);
- sa_path_set_ifindex(&work->path[0],
- if_getindex(gid_attr.ndev));
- sa_path_set_ndev(&work->path[0],
- dev_net(gid_attr.ndev));
- dev_put(gid_attr.ndev);
- } else {
- cm_path_set_rec_type(work->port->cm_dev->ib_device,
- work->port->port_num,
- &work->path[0],
- &req_msg->primary_local_gid);
- }
- if (cm_req_has_alt_path(req_msg))
- work->path[1].rec_type = work->path[0].rec_type;
- cm_format_paths_from_req(req_msg, &work->path[0],
- &work->path[1]);
- if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
- sa_path_set_dmac(&work->path[0],
- cm_id_priv->av.ah_attr.roce.dmac);
- work->path[0].hop_limit = grh->hop_limit;
- ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av,
- cm_id_priv);
- }
if (ret) {
- int err = ib_get_cached_gid(work->port->cm_dev->ib_device,
- work->port->port_num, 0,
- &work->path[0].sgid,
- &gid_attr);
- if (!err && gid_attr.ndev) {
- work->path[0].rec_type =
- sa_conv_gid_to_pathrec_type(gid_attr.gid_type);
- sa_path_set_ifindex(&work->path[0],
- if_getindex(gid_attr.ndev));
- sa_path_set_ndev(&work->path[0],
- dev_net(gid_attr.ndev));
- dev_put(gid_attr.ndev);
- } else {
- cm_path_set_rec_type(work->port->cm_dev->ib_device,
- work->port->port_num,
- &work->path[0],
- &req_msg->primary_local_gid);
- }
- if (cm_req_has_alt_path(req_msg))
- work->path[1].rec_type = work->path[0].rec_type;
- ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
- &work->path[0].sgid, sizeof work->path[0].sgid,
- NULL, 0);
+ ib_send_cm_rej(cm_id, IB_CM_REJ_UNSUPPORTED, NULL, 0, NULL, 0);
+ goto rejected;
+ }
+
+ if (gid_attr.ndev) {
+ work->path[0].rec_type =
+ sa_conv_gid_to_pathrec_type(gid_attr.gid_type);
+ sa_path_set_ifindex(&work->path[0],
+ if_getindex(gid_attr.ndev));
+ sa_path_set_ndev(&work->path[0],
+ dev_net(gid_attr.ndev));
+ dev_put(gid_attr.ndev);
+ } else {
+ cm_path_set_rec_type(work->port->cm_dev->ib_device,
+ work->port->port_num,
+ &work->path[0],
+ &req_msg->primary_local_gid);
+ }
+ if (cm_req_has_alt_path(req_msg))
+ work->path[1].rec_type = work->path[0].rec_type;
+ cm_format_paths_from_req(req_msg, &work->path[0],
+ &work->path[1]);
+ if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
+ sa_path_set_dmac(&work->path[0],
+ cm_id_priv->av.ah_attr.roce.dmac);
+ work->path[0].hop_limit = grh->hop_limit;
+ ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av,
+ cm_id_priv);
+ if (ret) {
+ int err;
+
+ err = ib_get_cached_gid(work->port->cm_dev->ib_device,
+ work->port->port_num, 0,
+ &work->path[0].sgid,
+ NULL);
+ if (err)
+ ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
+ NULL, 0, NULL, 0);
+ else
+ ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
+ &work->path[0].sgid,
+ sizeof(work->path[0].sgid),
+ NULL, 0);
goto rejected;
}
if (cm_req_has_alt_path(req_msg)) {
@@ -1949,7 +1978,7 @@ static int cm_req_handler(struct cm_work *work)
if (ret) {
ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
&work->path[0].sgid,
- sizeof work->path[0].sgid, NULL, 0);
+ sizeof(work->path[0].sgid), NULL, 0);
goto rejected;
}
}
@@ -3123,6 +3152,12 @@ static int cm_lap_handler(struct cm_work *work)
if (!cm_id_priv)
return -EINVAL;
+ ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
+ work->mad_recv_wc->recv_buf.grh,
+ &cm_id_priv->av);
+ if (ret)
+ goto deref;
+
param = &work->cm_event.param.lap_rcvd;
memset(&work->path[0], 0, sizeof(work->path[1]));
cm_path_set_rec_type(work->port->cm_dev->ib_device,
@@ -3169,11 +3204,6 @@ static int cm_lap_handler(struct cm_work *work)
cm_id_priv->id.lap_state = IB_CM_LAP_RCVD;
cm_id_priv->tid = lap_msg->hdr.tid;
- ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
- work->mad_recv_wc->recv_buf.grh,
- &cm_id_priv->av);
- if (ret)
- goto unlock;
ret = cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av,
cm_id_priv);
if (ret)
diff --git a/sys/ofed/drivers/infiniband/core/ib_cma.c b/sys/ofed/drivers/infiniband/core/ib_cma.c
index 33a4189804e1..09c1d266d6f8 100644
--- a/sys/ofed/drivers/infiniband/core/ib_cma.c
+++ b/sys/ofed/drivers/infiniband/core/ib_cma.c
@@ -648,10 +648,12 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
static inline int cma_validate_port(struct ib_device *device, u8 port,
enum ib_gid_type gid_type,
union ib_gid *gid,
- const struct rdma_dev_addr *dev_addr)
+ struct rdma_id_private *id_priv)
{
- const int dev_type = dev_addr->dev_type;
- if_t ndev;
+ struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
+ int bound_if_index = dev_addr->bound_dev_if;
+ int dev_type = dev_addr->dev_type;
+ if_t ndev = NULL;
int ret = -ENODEV;
if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port))
@@ -661,9 +663,10 @@ static inline int cma_validate_port(struct ib_device *device, u8 port,
return ret;
if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) {
- ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
+ ndev = dev_get_by_index(dev_addr->net, bound_if_index);
+ if (!ndev)
+ return ret;
} else {
- ndev = NULL;
gid_type = IB_GID_TYPE_IB;
}
@@ -707,7 +710,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
ret = cma_validate_port(cma_dev->device, port,
rdma_protocol_ib(cma_dev->device, port) ?
IB_GID_TYPE_IB :
- listen_id_priv->gid_type, gidp, dev_addr);
+ listen_id_priv->gid_type, gidp, id_priv);
if (!ret) {
id_priv->id.port_num = port;
goto out;
@@ -729,7 +732,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
rdma_protocol_ib(cma_dev->device, port) ?
IB_GID_TYPE_IB :
cma_dev->default_gid_type[port - 1],
- gidp, dev_addr);
+ gidp, id_priv);
if (!ret) {
id_priv->id.port_num = port;
goto out;
@@ -2333,6 +2336,33 @@ __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr)
}
EXPORT_SYMBOL(rdma_get_service_id);
+void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid,
+ union ib_gid *dgid)
+{
+ struct rdma_addr *addr = &cm_id->route.addr;
+
+ if (!cm_id->device) {
+ if (sgid)
+ memset(sgid, 0, sizeof(*sgid));
+ if (dgid)
+ memset(dgid, 0, sizeof(*dgid));
+ return;
+ }
+
+ if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) {
+ if (sgid)
+ rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid);
+ if (dgid)
+ rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid);
+ } else {
+ if (sgid)
+ rdma_addr_get_sgid(&addr->dev_addr, sgid);
+ if (dgid)
+ rdma_addr_get_dgid(&addr->dev_addr, dgid);
+ }
+}
+EXPORT_SYMBOL(rdma_read_gids);
+
static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
{
struct rdma_id_private *id_priv = iw_id->context;
@@ -2713,6 +2743,26 @@ out:
kfree(work);
}
+static void cma_init_resolve_route_work(struct cma_work *work,
+ struct rdma_id_private *id_priv)
+{
+ work->id = id_priv;
+ INIT_WORK(&work->work, cma_work_handler);
+ work->old_state = RDMA_CM_ROUTE_QUERY;
+ work->new_state = RDMA_CM_ROUTE_RESOLVED;
+ work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
+}
+
+static void cma_init_resolve_addr_work(struct cma_work *work,
+ struct rdma_id_private *id_priv)
+{
+ work->id = id_priv;
+ INIT_WORK(&work->work, cma_work_handler);
+ work->old_state = RDMA_CM_ADDR_QUERY;
+ work->new_state = RDMA_CM_ADDR_RESOLVED;
+ work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
+}
+
static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms)
{
struct rdma_route *route = &id_priv->id.route;
@@ -2723,11 +2773,7 @@ static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms)
if (!work)
return -ENOMEM;
- work->id = id_priv;
- INIT_WORK(&work->work, cma_work_handler);
- work->old_state = RDMA_CM_ROUTE_QUERY;
- work->new_state = RDMA_CM_ROUTE_RESOLVED;
- work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
+ cma_init_resolve_route_work(work, id_priv);
route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL);
if (!route->path_rec) {
@@ -2748,10 +2794,63 @@ err1:
return ret;
}
-int rdma_set_ib_paths(struct rdma_cm_id *id,
- struct sa_path_rec *path_rec, int num_paths)
+static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type,
+ unsigned long supported_gids,
+ enum ib_gid_type default_gid)
+{
+ if ((network_type == RDMA_NETWORK_IPV4 ||
+ network_type == RDMA_NETWORK_IPV6) &&
+ test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids))
+ return IB_GID_TYPE_ROCE_UDP_ENCAP;
+
+ return default_gid;
+}
+
+/*
+ * cma_iboe_set_path_rec_l2_fields() is helper function which sets
+ * path record type based on GID type.
+ * It also sets up other L2 fields which includes destination mac address
+ * netdev ifindex, of the path record.
+ * It returns the netdev of the bound interface for this path record entry.
+ */
+static if_t
+cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv)
+{
+ struct rdma_route *route = &id_priv->id.route;
+ enum ib_gid_type gid_type = IB_GID_TYPE_ROCE;
+ struct rdma_addr *addr = &route->addr;
+ unsigned long supported_gids;
+ if_t ndev;
+
+ if (!addr->dev_addr.bound_dev_if)
+ return NULL;
+
+ ndev = dev_get_by_index(addr->dev_addr.net,
+ addr->dev_addr.bound_dev_if);
+ if (!ndev)
+ return NULL;
+
+ supported_gids = roce_gid_type_mask_support(id_priv->id.device,
+ id_priv->id.port_num);
+ gid_type = cma_route_gid_type(addr->dev_addr.network,
+ supported_gids,
+ id_priv->gid_type);
+ /* Use the hint from IP Stack to select GID Type */
+ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network))
+ gid_type = ib_network_to_gid_type(addr->dev_addr.network);
+ route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type);
+
+ sa_path_set_ndev(route->path_rec, addr->dev_addr.net);
+ sa_path_set_ifindex(route->path_rec, if_getindex(ndev));
+ sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr);
+ return ndev;
+}
+
+int rdma_set_ib_path(struct rdma_cm_id *id,
+ struct sa_path_rec *path_rec)
{
struct rdma_id_private *id_priv;
+ if_t ndev;
int ret;
id_priv = container_of(id, struct rdma_id_private, id);
@@ -2759,20 +2858,33 @@ int rdma_set_ib_paths(struct rdma_cm_id *id,
RDMA_CM_ROUTE_RESOLVED))
return -EINVAL;
- id->route.path_rec = kmemdup(path_rec, sizeof *path_rec * num_paths,
+ id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec),
GFP_KERNEL);
if (!id->route.path_rec) {
ret = -ENOMEM;
goto err;
}
- id->route.num_paths = num_paths;
+ if (rdma_protocol_roce(id->device, id->port_num)) {
+ ndev = cma_iboe_set_path_rec_l2_fields(id_priv);
+ if (!ndev) {
+ ret = -ENODEV;
+ goto err_free;
+ }
+ dev_put(ndev);
+ }
+
+ id->route.num_paths = 1;
return 0;
+
+err_free:
+ kfree(id->route.path_rec);
+ id->route.path_rec = NULL;
err:
cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED);
return ret;
}
-EXPORT_SYMBOL(rdma_set_ib_paths);
+EXPORT_SYMBOL(rdma_set_ib_path);
static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms)
{
@@ -2782,11 +2894,7 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms)
if (!work)
return -ENOMEM;
- work->id = id_priv;
- INIT_WORK(&work->work, cma_work_handler);
- work->old_state = RDMA_CM_ROUTE_QUERY;
- work->new_state = RDMA_CM_ROUTE_RESOLVED;
- work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
+ cma_init_resolve_route_work(work, id_priv);
queue_work(cma_wq, &work->work);
return 0;
}
@@ -2800,26 +2908,14 @@ static int iboe_tos_to_sl(if_t ndev, int tos)
return sl;
}
-static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type,
- unsigned long supported_gids,
- enum ib_gid_type default_gid)
-{
- if ((network_type == RDMA_NETWORK_IPV4 ||
- network_type == RDMA_NETWORK_IPV6) &&
- test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids))
- return IB_GID_TYPE_ROCE_UDP_ENCAP;
-
- return default_gid;
-}
-
static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
{
struct rdma_route *route = &id_priv->id.route;
struct rdma_addr *addr = &route->addr;
struct cma_work *work;
int ret;
- if_t ndev = NULL;
- enum ib_gid_type gid_type = IB_GID_TYPE_IB;
+ if_t ndev;
+
u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num -
rdma_start_port(id_priv->cma_dev->device)];
u8 tos = id_priv->tos_set ? id_priv->tos : default_roce_tos;
@@ -2829,9 +2925,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
if (!work)
return -ENOMEM;
- work->id = id_priv;
- INIT_WORK(&work->work, cma_work_handler);
-
route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL);
if (!route->path_rec) {
ret = -ENOMEM;
@@ -2840,43 +2933,17 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
route->num_paths = 1;
- if (addr->dev_addr.bound_dev_if) {
- unsigned long supported_gids;
-
- ndev = dev_get_by_index(addr->dev_addr.net,
- addr->dev_addr.bound_dev_if);
- if (!ndev) {
- ret = -ENODEV;
- goto err2;
- }
-
- supported_gids = roce_gid_type_mask_support(id_priv->id.device,
- id_priv->id.port_num);
- gid_type = cma_route_gid_type(addr->dev_addr.network,
- supported_gids,
- id_priv->gid_type);
- route->path_rec->rec_type =
- sa_conv_gid_to_pathrec_type(gid_type);
- sa_path_set_ndev(route->path_rec, if_getvnet(ndev));
- sa_path_set_ifindex(route->path_rec, if_getindex(ndev));
- }
+ ndev = cma_iboe_set_path_rec_l2_fields(id_priv);
if (!ndev) {
ret = -ENODEV;
goto err2;
}
- sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr);
-
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);
- /* Use the hint from IP Stack to select GID Type */
- if (gid_type < ib_network_to_gid_type(addr->dev_addr.network))
- gid_type = ib_network_to_gid_type(addr->dev_addr.network);
- route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type);
-
if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB)
/* TODO: get the hoplimit from the inet/inet6 device */
route->path_rec->hop_limit = addr->dev_addr.hoplimit;
@@ -2898,11 +2965,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
goto err2;
}
- work->old_state = RDMA_CM_ROUTE_QUERY;
- work->new_state = RDMA_CM_ROUTE_RESOLVED;
- work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
- work->event.status = 0;
-
+ cma_init_resolve_route_work(work, id_priv);
queue_work(cma_wq, &work->work);
return 0;
@@ -3076,11 +3139,7 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);
- work->id = id_priv;
- INIT_WORK(&work->work, cma_work_handler);
- work->old_state = RDMA_CM_ADDR_QUERY;
- work->new_state = RDMA_CM_ADDR_RESOLVED;
- work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
+ cma_init_resolve_addr_work(work, id_priv);
queue_work(cma_wq, &work->work);
return 0;
err:
@@ -3106,11 +3165,7 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv)
rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)
&(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr));
- work->id = id_priv;
- INIT_WORK(&work->work, cma_work_handler);
- work->old_state = RDMA_CM_ADDR_QUERY;
- work->new_state = RDMA_CM_ADDR_RESOLVED;
- work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
+ cma_init_resolve_addr_work(work, id_priv);
queue_work(cma_wq, &work->work);
return 0;
err:
@@ -3745,10 +3800,10 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
event.status = ret;
break;
}
- ret = ib_init_ah_from_path(id_priv->id.device,
- id_priv->id.port_num,
- id_priv->id.route.path_rec,
- &event.param.ud.ah_attr);
+ ret = ib_init_ah_attr_from_path(id_priv->id.device,
+ id_priv->id.port_num,
+ id_priv->id.route.path_rec,
+ &event.param.ud.ah_attr);
if (ret) {
event.event = RDMA_CM_EVENT_ADDR_ERROR;
event.status = ret;
diff --git a/sys/ofed/drivers/infiniband/core/ib_cq.c b/sys/ofed/drivers/infiniband/core/ib_cq.c
index 9b100619cde7..d5c498e65509 100644
--- a/sys/ofed/drivers/infiniband/core/ib_cq.c
+++ b/sys/ofed/drivers/infiniband/core/ib_cq.c
@@ -41,6 +41,7 @@
/* # of WCs to poll for with a single call to ib_poll_cq */
#define IB_POLL_BATCH 16
+#define IB_POLL_BATCH_DIRECT 8
/* # of WCs to iterate over before yielding */
#define IB_POLL_BUDGET_WORKQUEUE 65536
@@ -48,7 +49,8 @@
#define IB_POLL_FLAGS \
(IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS)
-static int __ib_process_cq(struct ib_cq *cq, int budget)
+static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
+ int batch)
{
int i, n, completed = 0;
@@ -57,10 +59,10 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
* want to bound this call, thus we need unsigned
* minimum here.
*/
- while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH,
- budget - completed), cq->wc)) > 0) {
+ while ((n = ib_poll_cq(cq, min_t(u32, batch,
+ budget - completed), wcs)) > 0) {
for (i = 0; i < n; i++) {
- struct ib_wc *wc = &cq->wc[i];
+ struct ib_wc *wc = &wcs[i];
if (wc->wr_cqe)
wc->wr_cqe->done(cq, wc);
@@ -70,8 +72,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
completed += n;
- if (n != IB_POLL_BATCH ||
- (budget != -1 && completed >= budget))
+ if (n != batch || (budget != -1 && completed >= budget))
break;
}
@@ -83,18 +84,20 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
* @cq: CQ to process
* @budget: number of CQEs to poll for
*
- * This function is used to process all outstanding CQ entries on a
- * %IB_POLL_DIRECT CQ. It does not offload CQ processing to a different
- * context and does not ask for completion interrupts from the HCA.
+ * This function is used to process all outstanding CQ entries.
+ * It does not offload CQ processing to a different context and does
+ * not ask for completion interrupts from the HCA.
+ * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger
+ * concurrent processing.
*
* Note: do not pass -1 as %budget unless it is guaranteed that the number
* of completions that will be processed is small.
*/
int ib_process_cq_direct(struct ib_cq *cq, int budget)
{
- WARN_ON_ONCE(cq->poll_ctx != IB_POLL_DIRECT);
+ struct ib_wc wcs[IB_POLL_BATCH_DIRECT];
- return __ib_process_cq(cq, budget);
+ return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT);
}
EXPORT_SYMBOL(ib_process_cq_direct);
@@ -108,7 +111,8 @@ static void ib_cq_poll_work(struct work_struct *work)
struct ib_cq *cq = container_of(work, struct ib_cq, work);
int completed;
- completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE);
+ completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc,
+ IB_POLL_BATCH);
if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
queue_work(ib_comp_wq, &cq->work);
diff --git a/sys/ofed/drivers/infiniband/core/ib_device.c b/sys/ofed/drivers/infiniband/core/ib_device.c
index 7aae715657fb..9c45149a7877 100644
--- a/sys/ofed/drivers/infiniband/core/ib_device.c
+++ b/sys/ofed/drivers/infiniband/core/ib_device.c
@@ -857,32 +857,22 @@ EXPORT_SYMBOL(ib_modify_port);
/**
* ib_find_gid - Returns the port number and GID table index where
- * a specified GID value occurs.
+ * a specified GID value occurs. Its searches only for IB link layer.
* @device: The device to query.
* @gid: The GID value to search for.
- * @gid_type: Type of GID.
* @ndev: The ndev related to the GID to search for.
* @port_num: The port number of the device where the GID value was found.
* @index: The index into the GID table where the GID was found. This
* parameter may be NULL.
*/
int ib_find_gid(struct ib_device *device, union ib_gid *gid,
- enum ib_gid_type gid_type, if_t ndev,
- u8 *port_num, u16 *index)
+ if_t ndev, u8 *port_num, u16 *index)
{
union ib_gid tmp_gid;
int ret, port, i;
for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) {
- if (rdma_cap_roce_gid_table(device, port)) {
- if (!ib_find_cached_gid_by_port(device, gid, gid_type, port,
- ndev, index)) {
- *port_num = port;
- return 0;
- }
- }
-
- if (gid_type != IB_GID_TYPE_IB)
+ if (rdma_cap_roce_gid_table(device, port))
continue;
for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) {
diff --git a/sys/ofed/drivers/infiniband/core/ib_sa_query.c b/sys/ofed/drivers/infiniband/core/ib_sa_query.c
index c8e1af4bd2f2..65d132fe7f7a 100644
--- a/sys/ofed/drivers/infiniband/core/ib_sa_query.c
+++ b/sys/ofed/drivers/infiniband/core/ib_sa_query.c
@@ -790,9 +790,9 @@ static u8 get_src_path_mask(struct ib_device *device, u8 port_num)
return src_path_mask;
}
-int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
- struct sa_path_rec *rec,
- struct rdma_ah_attr *ah_attr)
+int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num,
+ struct sa_path_rec *rec,
+ struct rdma_ah_attr *ah_attr)
{
int ret;
u16 gid_index;
@@ -897,10 +897,11 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
return 0;
}
-EXPORT_SYMBOL(ib_init_ah_from_path);
+EXPORT_SYMBOL(ib_init_ah_attr_from_path);
static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
{
+ struct rdma_ah_attr ah_attr;
unsigned long flags;
spin_lock_irqsave(&query->port->ah_lock, flags);
@@ -912,6 +913,15 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
query->sm_ah = query->port->sm_ah;
spin_unlock_irqrestore(&query->port->ah_lock, flags);
+ /*
+ * Always check if sm_ah has valid dlid assigned,
+ * before querying for class port info
+ */
+ if ((rdma_query_ah(query->sm_ah->ah, &ah_attr) < 0) ||
+ !rdma_is_valid_unicast_lid(&ah_attr)) {
+ kref_put(&query->sm_ah->ref, free_sm_ah);
+ return -EAGAIN;
+ }
query->mad_buf = ib_create_send_mad(query->port->agent, 1,
query->sm_ah->pkey_index,
0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
diff --git a/sys/ofed/drivers/infiniband/core/ib_ucma.c b/sys/ofed/drivers/infiniband/core/ib_ucma.c
index 4d17b8285012..66b8875082db 100644
*** 784 LINES SKIPPED ***