Doug and list Hi, This patchset introduces Soft RoCE driver.
Some background on the driver: The original Soft-RoCE driver was implemented by Bob Pearson from SFW. Bob started the submission process [1], but his work was abandoned after v2. Mellanox decided to pick it up and continue the submission. As part of the process we detected some problems with the original implementation. Mainly, we wanted to RoCEv2, also, there are too many locks and context switches in the data path. Most of them are already removed. We've located the driver in the staging subtree. This follows a requirement to implement an IB transport library - Soft RoCE is in the same boat like the hfi1 driver. We need to define and implement a lib to prevent those code duplications. We did address the feedback provided on the original submission. Soft-RoCE is sitting on top of Matan's RoCEv2 series [2] which was taken to 4.5 and present Doug's k.o/for-4.5 branch. RXE user space (librxe) is located at github [4] with instructions how to use it [5] Some notes on the architecture and design: ib_rxe, implements the RDMA transport and registers with the RDMA core as a kernel verbs provider. It also implements the packet IO layer. ib_rxe attaches to the Linux netdev stack as a udp encapsulating protocol and can send and receive packets over any Ethernet device. It uses the RoCEv2 protocol to handle RDMA transport. The modules are configured by entries in /sys. There is a configuration script (rxe_cfg) that simplifies the use of this interface. rxe_cfg is part of the rxe user space code, librxe. The use of rxe verbs in user space requires the inclusion of librxe as a device specific plug-in to libibverbs. librxe is packaged separately [4]. Copies of the user space library and tools for 'upstream' and a clone of Doug's tree with these patches applied are available at github [3] under rxe_submission-v2 branch Architecture: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The driver components and a non asci chart of the module could be found at a pdf [6] presented by Bob before the original submission. The design is very similar, one thing that was changed, is the arbiter task that was removed. This reduced the number of context switches and locks during the data path. A TODO file is placed under the driver folder. Thanks, Kamal, Liran and Amir [1] - http://www.spinics.net/lists/linux-rdma/msg08936.html [2] - http://marc.info/?l=linux-rdma&m=145087562709661&w=2 [3] - https://github.com/SoftRoCE/rxe-dev [4] - https://github.com/SoftRoCE/librxe-dev [5] - https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home [6] - http://downloads.openfabrics.org/Media/Sonoma2010/Sonoma_2010_Wednesday_rxe.pdf Changes from V0: - Rebased to 4.3-rc1 - IPv4 based sessions work - Fixed the link speed and width we report to the query port verb - Update the TODO file with Sagi's request Changes from V1: - Rebased to 4.4.0-rc6 and to Doug's k.o/for-4.5 github branch - Move driver to be under "drivers/staging/rdma/" Amir Vadai (3): IB/core: Macro for RoCEv2 UDP port IB/rxe: Shared objects between user and kernel IB/rxe: TODO file while in staging Kamal Heib (29): IB/core: Add SEND_LAST_INV and SEND_ONLY_INV opcodes IB/rxe: IBA header types and methods IB/rxe: Bit mask and lengths declaration for different opcodes IB/rxe: Default rxe device and port parameters IB/rxe: External interface to lower level modules IB/rxe: Misc local interfaces between files in ib_rxe IB/rxe: Add maintainer for rxe driver IB/rxe: Work request's opcode information table IB/rxe: User/kernel shared queues infrastructure IB/rxe: Common user/kernel queue implementation IB/rxe: Interface to ib_core IB/rxe: Allocation pool for RDMA objects IB/rxe: RXE tasks handling IB/rxe: Address vector manipulation functions IB/rxe: Shared Receive Queue (SRQ) manipulation functions IB/rxe: Completion Queue (CQ) manipulation functions IB/rxe: Queue Pair (QP) handling IB/rxe: Memory Region (MR) handling IB/rxe: Multicast implementation IB/rxe: Received packets handling IB/rxe: Completion handling IB/rxe: QP request handling IB/rxe: QP response handling IB/rxe: Dummy DMA callbacks for RXE device IB/rxe: ICRC calculations IB/rxe: Module init hooks IB/rxe: Interface to netdev stack IB/rxe: sysfs interface to RXE IB/rxe: Add Soft-RoCE to kbuild and makefiles MAINTAINERS | 9 + drivers/staging/rdma/Kconfig | 2 + drivers/staging/rdma/Makefile | 1 + drivers/staging/rdma/rxe/Kconfig | 23 + drivers/staging/rdma/rxe/Makefile | 24 + drivers/staging/rdma/rxe/TODO | 18 + drivers/staging/rdma/rxe/rxe.c | 436 ++++++++++ drivers/staging/rdma/rxe/rxe.h | 72 ++ drivers/staging/rdma/rxe/rxe_av.c | 87 ++ drivers/staging/rdma/rxe/rxe_comp.c | 728 +++++++++++++++++ drivers/staging/rdma/rxe/rxe_cq.c | 165 ++++ drivers/staging/rdma/rxe/rxe_dma.c | 166 ++++ drivers/staging/rdma/rxe/rxe_hdr.h | 950 ++++++++++++++++++++++ drivers/staging/rdma/rxe/rxe_icrc.c | 96 +++ drivers/staging/rdma/rxe/rxe_loc.h | 291 +++++++ drivers/staging/rdma/rxe/rxe_mcast.c | 190 +++++ drivers/staging/rdma/rxe/rxe_mmap.c | 173 ++++ drivers/staging/rdma/rxe/rxe_mr.c | 764 ++++++++++++++++++ drivers/staging/rdma/rxe/rxe_net.c | 729 +++++++++++++++++ drivers/staging/rdma/rxe/rxe_net.h | 78 ++ drivers/staging/rdma/rxe/rxe_opcode.c | 961 ++++++++++++++++++++++ drivers/staging/rdma/rxe/rxe_opcode.h | 128 +++ drivers/staging/rdma/rxe/rxe_param.h | 177 ++++ drivers/staging/rdma/rxe/rxe_pool.c | 511 ++++++++++++ drivers/staging/rdma/rxe/rxe_pool.h | 161 ++++ drivers/staging/rdma/rxe/rxe_qp.c | 835 +++++++++++++++++++ drivers/staging/rdma/rxe/rxe_queue.c | 217 +++++ drivers/staging/rdma/rxe/rxe_queue.h | 178 +++++ drivers/staging/rdma/rxe/rxe_recv.c | 371 +++++++++ drivers/staging/rdma/rxe/rxe_req.c | 679 ++++++++++++++++ drivers/staging/rdma/rxe/rxe_resp.c | 1368 +++++++++++++++++++++++++++++++ drivers/staging/rdma/rxe/rxe_srq.c | 195 +++++ drivers/staging/rdma/rxe/rxe_sysfs.c | 168 ++++ drivers/staging/rdma/rxe/rxe_task.c | 154 ++++ drivers/staging/rdma/rxe/rxe_task.h | 95 +++ drivers/staging/rdma/rxe/rxe_verbs.c | 1423 +++++++++++++++++++++++++++++++++ drivers/staging/rdma/rxe/rxe_verbs.h | 486 +++++++++++ include/rdma/ib_pack.h | 4 + include/rdma/ib_verbs.h | 2 + include/uapi/rdma/Kbuild | 1 + include/uapi/rdma/ib_rxe.h | 139 ++++ 41 files changed, 13255 insertions(+) create mode 100644 drivers/staging/rdma/rxe/Kconfig create mode 100644 drivers/staging/rdma/rxe/Makefile create mode 100644 drivers/staging/rdma/rxe/TODO create mode 100644 drivers/staging/rdma/rxe/rxe.c create mode 100644 drivers/staging/rdma/rxe/rxe.h create mode 100644 drivers/staging/rdma/rxe/rxe_av.c create mode 100644 drivers/staging/rdma/rxe/rxe_comp.c create mode 100644 drivers/staging/rdma/rxe/rxe_cq.c create mode 100644 drivers/staging/rdma/rxe/rxe_dma.c create mode 100644 drivers/staging/rdma/rxe/rxe_hdr.h create mode 100644 drivers/staging/rdma/rxe/rxe_icrc.c create mode 100644 drivers/staging/rdma/rxe/rxe_loc.h create mode 100644 drivers/staging/rdma/rxe/rxe_mcast.c create mode 100644 drivers/staging/rdma/rxe/rxe_mmap.c create mode 100644 drivers/staging/rdma/rxe/rxe_mr.c create mode 100644 drivers/staging/rdma/rxe/rxe_net.c create mode 100644 drivers/staging/rdma/rxe/rxe_net.h create mode 100644 drivers/staging/rdma/rxe/rxe_opcode.c create mode 100644 drivers/staging/rdma/rxe/rxe_opcode.h create mode 100644 drivers/staging/rdma/rxe/rxe_param.h create mode 100644 drivers/staging/rdma/rxe/rxe_pool.c create mode 100644 drivers/staging/rdma/rxe/rxe_pool.h create mode 100644 drivers/staging/rdma/rxe/rxe_qp.c create mode 100644 drivers/staging/rdma/rxe/rxe_queue.c create mode 100644 drivers/staging/rdma/rxe/rxe_queue.h create mode 100644 drivers/staging/rdma/rxe/rxe_recv.c create mode 100644 drivers/staging/rdma/rxe/rxe_req.c create mode 100644 drivers/staging/rdma/rxe/rxe_resp.c create mode 100644 drivers/staging/rdma/rxe/rxe_srq.c create mode 100644 drivers/staging/rdma/rxe/rxe_sysfs.c create mode 100644 drivers/staging/rdma/rxe/rxe_task.c create mode 100644 drivers/staging/rdma/rxe/rxe_task.h create mode 100644 drivers/staging/rdma/rxe/rxe_verbs.c create mode 100644 drivers/staging/rdma/rxe/rxe_verbs.h create mode 100644 include/uapi/rdma/ib_rxe.h -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html