* [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE)
@ 2020-05-26 10:32 Leon Romanovsky
2020-05-26 10:33 ` [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason Leon Romanovsky
2020-05-27 19:14 ` [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Jason Gunthorpe
0 siblings, 2 replies; 5+ messages in thread
From: Leon Romanovsky @ 2020-05-26 10:32 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: rds-devel, Bart Van Assche, Chaitanya Kulkarni, linux-rdma,
netdev, Santosh Shilimkar, linux-kernel, linux-nvme,
Christoph Hellwig, Leon Romanovsky, target-devel, Danil Kipnis,
Jakub Kicinski, Jack Wang, David S. Miller, Sagi Grimberg
From: Leon Romanovsky <leonro@mellanox.com>
Changelog:
v3:
* Rebased on top of ebd6e96b33a2 RDMA/ipoib: Remove can_sleep parameter from iboib_mcast_alloc
* Updated rdma_reject patch to include newly added RTR ulp
* Remove empty hunks added by rebase
* Changed signature of rdma_reject so kernel users will provide reason by themselves
* Squashed UAPI patch to other patches which add functionality
* Removed define of the IBTA reason from UAPI
v2: https://lore.kernel.org/linux-rdma/20200413141538.935574-1-leon@kernel.org/
* Rebased on latest rdma-next and removed already accepted patches.
* Updated all rdma_reject in-kernel users to provide reject reason.
v1: Dropped field_avail patch in favor of mass conversion to use function
which already exists in the kernel code.
https://lore.kernel.org/lkml/20200310091438.248429-1-leon@kernel.org
v0: https://lore.kernel.org/lkml/20200305150105.207959-1-leon@kernel.org
Enhanced Connection Established or ECE is new negotiation scheme
introduced in IBTA v1.4 to exchange extra information about nodes
capabilities and later negotiate them at the connection establishment
phase.
The RDMA-CM messages (REQ, REP, SIDR_REQ and SIDR_REP) were extended
to carry two fields, one new and another gained new functionality:
* VendorID is a new field that indicates that common subset of vendor
option bits are supported as indicated by that VendorID.
* AttributeModifier already exists, but overloaded to indicate which
vendor options are supported by this VendorID.
This is kernel part of such functionality which is responsible to get data
from librdmacm and properly create and handle RDMA-CM messages.
Thanks
Leon Romanovsky (6):
RDMA/cm: Add Enhanced Connection Establishment (ECE) bits
RDMA/ucma: Extend ucma_connect to receive ECE parameters
RDMA/ucma: Deliver ECE parameters through UCMA events
RDMA/cm: Send and receive ECE parameter over the wire
RDMA/cma: Connect ECE to rdma_accept
RDMA/cma: Provide ECE reject reason
drivers/infiniband/core/cm.c | 39 ++++++++++++++---
drivers/infiniband/core/cma.c | 57 ++++++++++++++++++++++---
drivers/infiniband/core/cma_priv.h | 1 +
drivers/infiniband/core/ucma.c | 49 +++++++++++++++++----
drivers/infiniband/ulp/isert/ib_isert.c | 4 +-
drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 +-
drivers/infiniband/ulp/srpt/ib_srpt.c | 3 +-
drivers/nvme/target/rdma.c | 3 +-
include/rdma/ib_cm.h | 9 +++-
include/rdma/ibta_vol1_c12.h | 6 +++
include/rdma/rdma_cm.h | 9 +++-
include/uapi/rdma/rdma_user_cm.h | 11 ++++-
net/rds/ib_cm.c | 4 +-
13 files changed, 170 insertions(+), 27 deletions(-)
--
2.26.2
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason
2020-05-26 10:32 [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Leon Romanovsky
@ 2020-05-26 10:33 ` Leon Romanovsky
2020-05-26 11:36 ` Leon Romanovsky
2020-05-27 19:14 ` [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Jason Gunthorpe
1 sibling, 1 reply; 5+ messages in thread
From: Leon Romanovsky @ 2020-05-26 10:33 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: rds-devel, Bart Van Assche, Chaitanya Kulkarni, linux-rdma,
netdev, Santosh Shilimkar, linux-nvme, Christoph Hellwig,
Leon Romanovsky, target-devel, Danil Kipnis, Jakub Kicinski,
Jack Wang, David S. Miller, Sagi Grimberg
From: Leon Romanovsky <leonro@mellanox.com>
IBTA declares "vendor option not supported" reject reason in REJ
messages if passive side doesn't want to accept proposed ECE options.
Due to the fact that ECE is managed by userspace, there is a need to let
users to provide such rejected reason.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/core/cma.c | 9 ++++-----
drivers/infiniband/core/ucma.c | 15 ++++++++++++++-
drivers/infiniband/ulp/isert/ib_isert.c | 4 ++--
drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 +-
drivers/infiniband/ulp/srpt/ib_srpt.c | 3 ++-
drivers/nvme/target/rdma.c | 3 ++-
include/rdma/rdma_cm.h | 2 +-
include/uapi/rdma/rdma_user_cm.h | 3 ++-
net/rds/ib_cm.c | 4 +++-
9 files changed, 31 insertions(+), 14 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index d449afe5557b..8026ee56546a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4196,7 +4196,7 @@ int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
return 0;
reject:
cma_modify_qp_err(id_priv);
- rdma_reject(id, NULL, 0);
+ rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED);
return ret;
}
EXPORT_SYMBOL(__rdma_accept);
@@ -4236,7 +4236,7 @@ int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event)
EXPORT_SYMBOL(rdma_notify);
int rdma_reject(struct rdma_cm_id *id, const void *private_data,
- u8 private_data_len)
+ u8 private_data_len, u8 reason)
{
struct rdma_id_private *id_priv;
int ret;
@@ -4251,9 +4251,8 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
private_data, private_data_len);
} else {
trace_cm_send_rej(id_priv);
- ret = ib_send_cm_rej(id_priv->cm_id.ib,
- IB_CM_REJ_CONSUMER_DEFINED, NULL,
- 0, private_data, private_data_len);
+ ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0,
+ private_data, private_data_len);
}
} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
ret = iw_cm_reject(id_priv->cm_id.iw,
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 6b27b210b890..5b87eee8ccc8 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -52,6 +52,7 @@
#include <rdma/rdma_cm_ib.h>
#include <rdma/ib_addr.h>
#include <rdma/ib.h>
+#include <rdma/ib_cm.h>
#include <rdma/rdma_netlink.h>
#include "core_priv.h"
@@ -1181,12 +1182,24 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
+ if (!cmd.reason)
+ cmd.reason = IB_CM_REJ_CONSUMER_DEFINED;
+
+ switch (cmd.reason) {
+ case IB_CM_REJ_CONSUMER_DEFINED:
+ case IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED:
+ break;
+ default:
+ return -EINVAL;
+ }
+
ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
mutex_lock(&ctx->mutex);
- ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len);
+ ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len,
+ cmd.reason);
mutex_unlock(&ctx->mutex);
ucma_put_ctx(ctx);
return ret;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index a1a035270cab..7bc598d7a15c 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -502,7 +502,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
if (!np->enabled) {
spin_unlock_bh(&np->np_thread_lock);
isert_dbg("iscsi_np is not enabled, reject connect request\n");
- return rdma_reject(cma_id, NULL, 0);
+ return rdma_reject(cma_id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED);
}
spin_unlock_bh(&np->np_thread_lock);
@@ -553,7 +553,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
isert_free_login_buf(isert_conn);
out:
kfree(isert_conn);
- rdma_reject(cma_id, NULL, 0);
+ rdma_reject(cma_id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED);
return ret;
}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 5ef8988ee75b..67d164ff5aaa 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1576,7 +1576,7 @@ static int rtrs_rdma_do_reject(struct rdma_cm_id *cm_id, int errno)
.errno = cpu_to_le16(errno),
};
- err = rdma_reject(cm_id, &msg, sizeof(msg));
+ err = rdma_reject(cm_id, &msg, sizeof(msg), IB_CM_REJ_CONSUMER_DEFINED);
if (err)
pr_err("rdma_reject(), err: %d\n", err);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index a294630f2100..cdc8c239d6c0 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2497,7 +2497,8 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
SRP_BUF_FORMAT_INDIRECT);
if (rdma_cm_id)
- rdma_reject(rdma_cm_id, rej, sizeof(*rej));
+ rdma_reject(rdma_cm_id, rej, sizeof(*rej),
+ IB_CM_REJ_CONSUMER_DEFINED);
else
ib_send_cm_rej(ib_cm_id, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0,
rej, sizeof(*rej));
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index fd47de0e4e4e..30a0a9adaddd 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1138,7 +1138,8 @@ static int nvmet_rdma_cm_reject(struct rdma_cm_id *cm_id,
rej.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
rej.sts = cpu_to_le16(status);
- return rdma_reject(cm_id, (void *)&rej, sizeof(rej));
+ return rdma_reject(cm_id, (void *)&rej, sizeof(rej),
+ IB_CM_REJ_CONSUMER_DEFINED);
}
static struct nvmet_rdma_queue *
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 7ac91677660f..939d7abe026f 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -320,7 +320,7 @@ int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event);
* rdma_reject - Called to reject a connection request or response.
*/
int rdma_reject(struct rdma_cm_id *id, const void *private_data,
- u8 private_data_len);
+ u8 private_data_len, u8 reason);
/**
* rdma_disconnect - This function disconnects the associated QP and
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
index 6b883dde7064..ed5a514305c1 100644
--- a/include/uapi/rdma/rdma_user_cm.h
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -238,7 +238,8 @@ struct rdma_ucm_accept {
struct rdma_ucm_reject {
__u32 id;
__u8 private_data_len;
- __u8 reserved[3];
+ __u8 reason;
+ __u8 reserved[2];
__u8 private_data[RDMA_MAX_PRIVATE_DATA];
};
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c71f4328d138..0fec4171564e 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -37,6 +37,7 @@
#include <linux/vmalloc.h>
#include <linux/ratelimit.h>
#include <net/addrconf.h>
+#include <rdma/ib_cm.h>
#include "rds_single_path.h"
#include "rds.h"
@@ -927,7 +928,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
if (conn)
mutex_unlock(&conn->c_cm_lock);
if (err)
- rdma_reject(cm_id, &err, sizeof(int));
+ rdma_reject(cm_id, &err, sizeof(int),
+ IB_CM_REJ_CONSUMER_DEFINED);
return destroy;
}
--
2.26.2
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason
2020-05-26 10:33 ` [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason Leon Romanovsky
@ 2020-05-26 11:36 ` Leon Romanovsky
2020-05-26 12:07 ` Leon Romanovsky
0 siblings, 1 reply; 5+ messages in thread
From: Leon Romanovsky @ 2020-05-26 11:36 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: rds-devel, Bart Van Assche, Chaitanya Kulkarni, linux-rdma,
netdev, Santosh Shilimkar, linux-nvme, Christoph Hellwig,
target-devel, Danil Kipnis, Jakub Kicinski, Jack Wang,
David S. Miller, Sagi Grimberg
On Tue, May 26, 2020 at 01:33:04PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> IBTA declares "vendor option not supported" reject reason in REJ
> messages if passive side doesn't want to accept proposed ECE options.
>
> Due to the fact that ECE is managed by userspace, there is a need to let
> users to provide such rejected reason.
>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> ---
> drivers/infiniband/core/cma.c | 9 ++++-----
> drivers/infiniband/core/ucma.c | 15 ++++++++++++++-
> drivers/infiniband/ulp/isert/ib_isert.c | 4 ++--
> drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 +-
> drivers/infiniband/ulp/srpt/ib_srpt.c | 3 ++-
> drivers/nvme/target/rdma.c | 3 ++-
> include/rdma/rdma_cm.h | 2 +-
> include/uapi/rdma/rdma_user_cm.h | 3 ++-
> net/rds/ib_cm.c | 4 +++-
> 9 files changed, 31 insertions(+), 14 deletions(-)
For some reason didn't get the failure in CI, this small fixup is
needed.
commit af02a4a50ec0d18fe9bfb86b96411dfb42054f97 (HEAD -> rdma-next)
Author: Leon Romanovsky <leon@kernel.org>
Date: Tue May 26 14:34:34 2020 +0300
fixup! RDMA/cma: Provide ECE reject reason
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 30a0a9adaddd..d84765f66d49 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -18,6 +18,7 @@
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
+#include <rdma/ib_cm.h>
#include <rdma/rdma_cm.h>
#include <rdma/rw.h>
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason
2020-05-26 11:36 ` Leon Romanovsky
@ 2020-05-26 12:07 ` Leon Romanovsky
0 siblings, 0 replies; 5+ messages in thread
From: Leon Romanovsky @ 2020-05-26 12:07 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: rds-devel, Bart Van Assche, Chaitanya Kulkarni, linux-rdma,
netdev, Santosh Shilimkar, linux-nvme, Christoph Hellwig,
target-devel, Danil Kipnis, Jakub Kicinski, Jack Wang,
David S. Miller, Sagi Grimberg
On Tue, May 26, 2020 at 02:36:28PM +0300, Leon Romanovsky wrote:
> On Tue, May 26, 2020 at 01:33:04PM +0300, Leon Romanovsky wrote:
> > From: Leon Romanovsky <leonro@mellanox.com>
> >
> > IBTA declares "vendor option not supported" reject reason in REJ
> > messages if passive side doesn't want to accept proposed ECE options.
> >
> > Due to the fact that ECE is managed by userspace, there is a need to let
> > users to provide such rejected reason.
> >
> > Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> > ---
> > drivers/infiniband/core/cma.c | 9 ++++-----
> > drivers/infiniband/core/ucma.c | 15 ++++++++++++++-
> > drivers/infiniband/ulp/isert/ib_isert.c | 4 ++--
> > drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 +-
> > drivers/infiniband/ulp/srpt/ib_srpt.c | 3 ++-
> > drivers/nvme/target/rdma.c | 3 ++-
> > include/rdma/rdma_cm.h | 2 +-
> > include/uapi/rdma/rdma_user_cm.h | 3 ++-
> > net/rds/ib_cm.c | 4 +++-
> > 9 files changed, 31 insertions(+), 14 deletions(-)
>
> For some reason didn't get the failure in CI, this small fixup is
> needed.
>
> commit af02a4a50ec0d18fe9bfb86b96411dfb42054f97 (HEAD -> rdma-next)
> Author: Leon Romanovsky <leon@kernel.org>
> Date: Tue May 26 14:34:34 2020 +0300
>
> fixup! RDMA/cma: Provide ECE reject reason
>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
>
> diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
> index 30a0a9adaddd..d84765f66d49 100644
> --- a/drivers/nvme/target/rdma.c
> +++ b/drivers/nvme/target/rdma.c
> @@ -18,6 +18,7 @@
> #include <asm/unaligned.h>
>
> #include <rdma/ib_verbs.h>
> +#include <rdma/ib_cm.h>
> #include <rdma/rdma_cm.h>
> #include <rdma/rw.h>
>
and this one:
commit 4c489c296115d1c795f24cd4aad741058671fe50 (HEAD -> rdma-next)
Author: Leon Romanovsky <leon@kernel.org>
Date: Tue May 26 15:01:19 2020 +0300
fixup! RDMA/cma: Provide ECE reject reason
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 7bc598d7a15c..b7df38ee8ae0 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -15,6 +15,7 @@
#include <linux/in.h>
#include <linux/in6.h>
#include <rdma/ib_verbs.h>
+#include <rdma/ib_cm.h>
#include <rdma/rdma_cm.h>
#include <target/target_core_base.h>
#include <target/target_core_fabric.h>
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 67d164ff5aaa..0d9241f5d9e6 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -15,6 +15,7 @@
#include "rtrs-srv.h"
#include "rtrs-log.h"
+#include <rdma/ib_cm.h>
MODULE_DESCRIPTION("RDMA Transport Server");
MODULE_LICENSE("GPL");
(END)
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE)
2020-05-26 10:32 [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Leon Romanovsky
2020-05-26 10:33 ` [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason Leon Romanovsky
@ 2020-05-27 19:14 ` Jason Gunthorpe
1 sibling, 0 replies; 5+ messages in thread
From: Jason Gunthorpe @ 2020-05-27 19:14 UTC (permalink / raw)
To: Leon Romanovsky
Cc: rds-devel, Bart Van Assche, Chaitanya Kulkarni, linux-rdma,
netdev, Santosh Shilimkar, linux-kernel, linux-nvme,
David S. Miller, Leon Romanovsky, Doug Ledford, target-devel,
Danil Kipnis, Jakub Kicinski, Jack Wang, Christoph Hellwig,
Sagi Grimberg
On Tue, May 26, 2020 at 01:32:58PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> Changelog:
> v3:
> * Rebased on top of ebd6e96b33a2 RDMA/ipoib: Remove can_sleep parameter from iboib_mcast_alloc
> * Updated rdma_reject patch to include newly added RTR ulp
> * Remove empty hunks added by rebase
> * Changed signature of rdma_reject so kernel users will provide reason by themselves
> * Squashed UAPI patch to other patches which add functionality
> * Removed define of the IBTA reason from UAPI
> v2: https://lore.kernel.org/linux-rdma/20200413141538.935574-1-leon@kernel.org/
> * Rebased on latest rdma-next and removed already accepted patches.
> * Updated all rdma_reject in-kernel users to provide reject reason.
> v1: Dropped field_avail patch in favor of mass conversion to use function
> which already exists in the kernel code.
> https://lore.kernel.org/lkml/20200310091438.248429-1-leon@kernel.org
> v0: https://lore.kernel.org/lkml/20200305150105.207959-1-leon@kernel.org
>
> Enhanced Connection Established or ECE is new negotiation scheme
> introduced in IBTA v1.4 to exchange extra information about nodes
> capabilities and later negotiate them at the connection establishment
> phase.
>
> The RDMA-CM messages (REQ, REP, SIDR_REQ and SIDR_REP) were extended
> to carry two fields, one new and another gained new functionality:
> * VendorID is a new field that indicates that common subset of vendor
> option bits are supported as indicated by that VendorID.
> * AttributeModifier already exists, but overloaded to indicate which
> vendor options are supported by this VendorID.
>
> This is kernel part of such functionality which is responsible to get data
> from librdmacm and properly create and handle RDMA-CM messages.
>
> Thanks
>
> Leon Romanovsky (6):
> RDMA/cm: Add Enhanced Connection Establishment (ECE) bits
> RDMA/ucma: Extend ucma_connect to receive ECE parameters
> RDMA/ucma: Deliver ECE parameters through UCMA events
> RDMA/cm: Send and receive ECE parameter over the wire
> RDMA/cma: Connect ECE to rdma_accept
> RDMA/cma: Provide ECE reject reason
Applied to for-next, thanks
Jason
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2020-05-27 19:14 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2020-05-26 10:32 [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Leon Romanovsky
2020-05-26 10:33 ` [PATCH rdma-next v3 6/6] RDMA/cma: Provide ECE reject reason Leon Romanovsky
2020-05-26 11:36 ` Leon Romanovsky
2020-05-26 12:07 ` Leon Romanovsky
2020-05-27 19:14 ` [PATCH rdma-next v3 0/6] Add Enhanced Connection Established (ECE) Jason Gunthorpe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).