On Wed, 2019-05-01 at 13:48 +0300, Gal Pressman wrote: > Hello all, > The following v6 patchset introduces the Amazon Elastic Fabric Adapter (EFA) > driver. > > EFA is a networking adapter designed to support user space network > communication, initially offered in the Amazon EC2 environment. First release > of EFA supports datagram send/receive operations and does not support > connection-oriented or read/write operations. > > EFA supports Unreliable Datagrams (UD) as well as a new unordered, Scalable > Reliable Datagram protocol (SRD). SRD provides support for reliable datagrams > and more complete error handling than typical RD, but, unlike RD, it does not > support ordering nor segmentation. > > EFA reliable datagram transport provides reliable out-of-order delivery, > transparently utilizing multiple network paths to reduce network tail > latency. Its interface is similar to UD, in particular it supports > message size up to MTU, with error handling extended to support reliable > communication. More information regarding SRD can be found at [1]. > > Kernel verbs and in-kernel services are initially not supported but are planned > for future releases. > > EFA enabled EC2 instances have two different devices allocated, one for ENA > (netdev) and one for EFA, the two are separate pci devices with no in-kernel > communication between them. > > This patchset also introduces RDMA subsystem ibdev_* print helpers which should > be used by the other new drivers that are currently under review (irdma, siw) > and over time by all drivers in the subsystem. > The print format is similar to the netdev_* helpers. > > PR for rdma-core provider was sent: > https://github.com/linux-rdma/rdma-core/pull/475 > > Thanks to everyone who took the time to review our last submissions (Jason, Doug, > Sean, Dennis, Leon, Christoph, Parav, Sagi, Steve, Shiraz), it is very > appreciated. This looks to me like all of the requirements we discussed at the OFA workshop for inclusion (must have UD in addition to SRD, must have a pull request for the user space portion, must have processed prior review comments) have been met. I did a cursory review of this patchset and have no specific objections that I'm willing to hold things up for. I'll give this a few days for other people to comment, but I'm basically ready to take it. I will, however, take patch 1/12 sooner and feed it to for-next so other drivers can start modifying their prints to use the new helper. -- Doug Ledford <dledford@xxxxxxxxxx> GPG KeyID: B826A3330E572FDD Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDD
Attachment:
signature.asc
Description: This is a digitally signed message part
