aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/staging/rdma/hfi1/verbs.h (follow)
AgeCommit message (Collapse)AuthorFilesLines
2016-04-28IB/hfi1: Use global defines for upper bits in opcodeMike Marciniszyn1-3/+0
The awkward coding for setting the allowed_ops field was tripping an smatch warning. This patch uses the more appropriate defines from include/rdma to avoid the issue. As part of the patch remove a mask that was duplicated in rdmavt include files and use that mask as appropriate. Fixes: 8bea6b1cfe6f ("IB/rdmavt: Add create queue pair functionality") Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-04-28IB/qib, IB/hfi1: Fix up UD loopback use of irq flagsMike Marciniszyn1-0/+1
The dual lock patch moved locking around and missed an issue with handling irq flags when processing UD loopback packets. This issue was revealed by smatch. Fix for both qib and hfi1 to pass the saved flags to the UD request builder and handle the changes correctly. Fixes: 46a80d62e6e0 ("IB/qib, staging/rdma/hfi1: add s_hlock for use in post send") Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-17IB/hfi1: Add adaptive cacheless verbs copyDean Luick1-0/+22
The kernel memcpy is faster than a cacheless copy. However, if too much of the L3 cache is overwritten by one-time copies then overall bandwidth suffers. Implement an adaptive scheme where full page copies are tracked and if the number of unique entries are larger than a threshold, verbs will use a cacheless copy. Tracked entries are gradually cleaned, allowing memcpy to resume once the larger copies have stopped. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Fix headerJubin John1-4/+1
Fix the header by moving the copyright notice out of the license text and to the top of the header. Also, update the copyright date. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove space after castJubin John1-2/+2
Remove the space after a cast to fix checkpatch check: CHECK: No space is necessary after a cast Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Add qp to send context mapping for PIOJubin John1-2/+0
PIO send context mapping is changed from per-VL to QPN based. qp to send context mapping is done using a mapping infrastructure similar to the current vl to sdma engine mapping. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Adaptive PIO for short messagesMike Marciniszyn1-0/+16
The change requires a new pio_busy field in the iowait structure to track the number of outstanding pios. The new counter together with the sdma counter serve as the basis for a packet by packet decision as to which egress mechanism to use. Since packets given to different egress mechanisms are not ordered, this scheme will preserve the order. The iowait drain/wait mechanisms are extended for a pio case. An additional qp wait flag is added for the PIO drain wait case. Currently the only pio wait is for buffers, so the no_bufs_available() routine name is changed to pio_wait() and a third argument is passed with one of the two pio wait flags to generalize the routine. A module parameter is added to hold a configurable threshold. For now, the module parameter is zero. A heuristic routine is added to return the func pointer of the proper egress routine to use. The heuristic is as follows: - SMI always uses pio - GSI,UD qps <= threshold use pio - UD qps > threadhold use sdma o No coordination with sdma is required because order is not required and this qp pio count is not maintained for UD - RC/UC ONLY packets <= threshold chose as follows: o If sdmas pending, use SDMA o Otherwise use pio and enable the pio tracking count at the time the pio buffer is allocated - RC/UC ONLY packets > threshold use SDMA o If pio's are pending the pio_wait with the new wait flag is called to delay for pios to drain The threshold is potentially reduced by the QP's mtu. The sc_buffer_alloc() has two additional args (a callback, a void *) which are exploited by the RC/UC cases to pass a new complete routine and a qp *. When the shadow ring completes the credit associated with a packet, the new complete routine is called. The verbs_pio_complete() will then decrement the busy count and trigger any drain waiters in qp destroy or reset. Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Add s_sendcontext priv fieldJubin John1-4/+5
s_sendcontext will be used to map the QPs to the send contexts for PIO. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove header memcpy from sdma send path.Dennis Dalessandro1-11/+7
Instead of writing the header into a buffer then copying it into another buffer to be sent, remove that memcpy and instead build the header directly into the tx request that will be sent. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Vennila Megavannan <vennila.megavannan@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10IB/qib, staging/rdma/hfi1: add s_hlock for use in post sendMike Marciniszyn1-1/+1
This patch adds an additional lock to reduce contention on the s_lock. This lock is used in post_send() so that the post_send is not serialized with the send engine and other send related processing. To do this the s_next_psn is now maintained on post_send() while post_send() related fields are moved to a new cache line. There is an s_avail maintained for the post_send() to mitigate trading cache lines with the send engine. The lock is released/acquired around releasing the just built packet to the egress mechanism. Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: actually use new RNR timer API in loopback pathMike Marciniszyn1-0/+1
The patch series which added a new API for the RNR timer did not include an updated call in the loopback path. RC/UC RNR loopback would be broken without this. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: use new RNR timerMike Marciniszyn1-0/+2
Use the new RNR timer for hfi1. For qib, this timer doesn't exist, so exploit driver callbacks to use the new timer as appropriate. Reviewed-by: Jubin John <jubin.john@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: add unique rnr timerMike Marciniszyn1-0/+2
Add a new rnr timer to hfi1. This allows for future optimizations having the retry and rnr timers separate. Reviewed-by: Jubin John <jubin.john@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Removing unused struct hfi1_verbs_countersSebastian Sanchez1-16/+0
It removes the unused struct hfi1_verbs_counters from verbs.h Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove modify_port and port_immutable functionsHarish Chegondi1-1/+1
Delete code from query_port which has been moved into rvt_query_port Create a call back function to shut down a port which may be called from rvt_modify_port Signed-off-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Split last 8 bytes of copy to user bufferDean Luick1-1/+1
Copy the last 8 bytes of user mode RC WRITE_ONLY and WRITE_LAST opcodes separately from the rest of the data. It is a de-facto standard for some MPI implementations to use a poll on the last few bytes of a verbs message to indicate that the message has been received rather than follow the required function method. The driver uses the kernel memcpy routine, which becomes "rep movsb" on modern machines. This copy, while very fast, does not guarantee in-order copy completion and the result is an occasional perceived corrupted packet. Avoid the issue by splitting the last 8 bytes to copy from the verbs opcodes where it matters and performing an in-order byte copy. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Change send_schedule counter to a per cpu counterVennila Megavannan1-1/+0
A patch to fix fairness issues in QP scheduling requires n_send_schedule counter to be converted to a per cpu counter to reduce cache misses. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Vennila Megavannan <vennila.megavannan@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Fix SL->SC checksIra Weiny1-0/+2
SLs which are mapped to SC15 are invalid and should fail the operation. For RC/UC QP types, verify the AH information at modify_qp time and fail the modify_qp if the SL is invalid. For other QP types check the SL during post_send via the new rdmavt callback. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove srq functionalityJubin John1-17/+0
srq functionality is now in rdmavt. Remove it from the hfi1 driver. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove create and free mad agentsDennis Dalessandro1-4/+0
Get rid of create and free mad agent from the driver and use rdmavt version. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove modify queue pair from hfi1Dennis Dalessandro1-24/+7
In addition to removing the modify queue pair verb from hfi1 we also remove ancillary functions which existed only for modify queue pair and are also already present in hfi1. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove multicast verbs functionsDennis Dalessandro1-29/+0
Multicast is now supported by rdmavt. Remove the verbs multicast functions and use that. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Use rdmavt version of post_sendDennis Dalessandro1-31/+4
This patch removes the post_send and post_one_send from the hfi1 driver. The "posting" of sends will be done by rdmavt which will walk a WQE and queue work. This patch will still provide the capability to schedule that work as well as kick the progress. These are provided to the rdmavt layer. Reviewed-by: Jubin John <jubin.john@intel.com> Signed-off-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Edward Mascarenhas <edward.mascarenhas@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove CQ data structures and functions from hfi1Dennis Dalessandro1-64/+1
The completion queue is not a complex data structure and it can be removed at the same time as its functions. Unlike the more complicated queue pair which was done in multiple patches. This single patch removes all traces of hfi1 specific completeion queues from the hfi1 driver. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove qpdev and qpn table from hfi1Dennis Dalessandro1-3/+0
Another change on the way to removing queue pair functionality from hfi1. This patch removes the private queue pair structure and the table which holds the queue pair numbers in favor of using what is provided by rdmavt. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Use rdmavt send flags and recv flagsDennis Dalessandro1-81/+4
Use the definitions of the s_flags and r_flags which are now in rdmavt. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove mmap from hfi1Dennis Dalessandro1-17/+0
Mmap data structure has already been moved to rdmavt and hfi1 supports it. Now that the mmap functionality has also been moved to rdmavt its time for hfi1 to use that as well. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove ibport and use rdmavt versionDennis Dalessandro1-48/+3
Remove most of the ibport members from hfi1 and use the rdmavt version. Also register the port with rdmavt. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove srq from hfi1Dennis Dalessandro1-13/+0
SRQ data structure has been moved to rdmavt. Make use of it. Reviewed-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove hfi1 MR and hfi1 specific qp typeDennis Dalessandro1-320/+46
This patch does the actual removal of the queue pair from the hfi1 driver along with a number of dependent data structures. These were moved to rvt. It also removes the MR functions to use those in rdmavt. These two pieces can not reasonably be split apart becuase they depend on each other. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Use address handle in rdmavt and remove from hfi1Dennis Dalessandro1-18/+2
Original patch from Kamal Heib <kamalh@mellanox.com>, split apart from original and modified to accomodate recent changes in rdmavt. Remove AH from hfi1 and use rdmavt version. Signed-off-by: Kamal Heib <kamalh@mellanox.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove driver specific members from hfi1 qp typeDennis Dalessandro1-7/+23
In preparation for moving the queue pair data structure to rdmavt the members of the driver specific queue pairs which are not common need to be pushed off to a private driver structure. This structure will be available in the queue pair once moved to rdmavt as a void pointer. This patch while not adding a lot of value in and of itself is a prerequisite to move the queue pair out of the drivers and into rdmavt. The driver specific, private queue pair data structure should condense as more of the send side code moves to rdmavt. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Remove MR data structures from hfi1Dennis Dalessandro1-53/+10
Remove MR data structures from hfi1 and use the version in rdmavt Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Use rdmavt protection domainDennis Dalessandro1-14/+1
Remove protection domain from hfi1 and use rdmavt's version. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Consolidate dma ops for hfi1Ira Weiny1-2/+0
Remove the dma.c file from hfi1 in favor of using that which is present in rdmavt. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10staging/rdma/hfi1: Begin to use rdmavt for verbsDennis Dalessandro1-2/+6
This patch begins to make use of rdmavt by registering with it and providing access to the header files. This is just the beginning of rdmavt support in hfi1. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01staging/hfi1: Move s_sde to read mostly section of hfi1_qpHarish Chegondi1-1/+1
This would reduce L2 cache misses on s_sde in the _hfi1_schedule_send function when invoked from post_send thereby improving performance of post_send. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-23Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdmaLinus Torvalds1-4/+0
Pull rdma updates from Doug Ledford: "Initial roundup of 4.5 merge window patches - Remove usage of ib_query_device and instead store attributes in ib_device struct - Move iopoll out of block and into lib, rename to irqpoll, and use in several places in the rdma stack as our new completion queue polling library mechanism. Update the other block drivers that already used iopoll to use the new mechanism too. - Replace the per-entry GID table locks with a single GID table lock - IPoIB multicast cleanup - Cleanups to the IB MR facility - Add support for 64bit extended IB counters - Fix for netlink oops while parsing RDMA nl messages - RoCEv2 support for the core IB code - mlx4 RoCEv2 support - mlx5 RoCEv2 support - Cross Channel support for mlx5 - Timestamp support for mlx5 - Atomic support for mlx5 - Raw QP support for mlx5 - MAINTAINERS update for mlx4/mlx5 - Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates - Add support for remote invalidate to the iSER driver (pushed through the RDMA tree due to dependencies, acknowledged by nab) - Update to NFSoRDMA (pushed through the RDMA tree due to dependencies, acknowledged by Bruce)" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits) IB/mlx5: Unify CQ create flags check IB/mlx5: Expose Raw Packet QP to user space consumers {IB, net}/mlx5: Move the modify QP operation table to mlx5_ib IB/mlx5: Support setting Ethernet priority for Raw Packet QPs IB/mlx5: Add Raw Packet QP query functionality IB/mlx5: Add create and destroy functionality for Raw Packet QP IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types IB/mlx5: Allocate a Transport Domain for each ucontext net/mlx5_core: Warn on unsupported events of QP/RQ/SQ net/mlx5_core: Add RQ and SQ event handling net/mlx5_core: Export transport objects IB/mlx5: Expose CQE version to user-space IB/mlx5: Add CQE version 1 support to user QPs and SRQs IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext IB/sa: Fix netlink local service GFP crash IB/srpt: Remove redundant wc array IB/qib: Improve ipoib UD performance IB/mlx4: Advertise RoCE v2 support IB/mlx4: Create and use another QP1 for RoCEv2 IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers ...
2015-12-23IB: remove support for phys MRsChristoph Hellwig1-4/+0
We have stopped using phys MRs in the kernel a while ago, so let's remove all the cruft used to implement them. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> [core] Reviewed-By: Devesh Sharma<devesh.sharma@avagotech.com> [ocrdma] Reviewed-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2015-12-21staging/rdma/hfi1: HFI now sends OPA Traps instead of IBTAErik E. Kahn1-1/+1
send_trap() was still using old ib_smp instead of opa_smp for formatting and sending traps. Reviewed-by: Arthur Kepner <arthur.kepner@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Erik E. Kahn <erik.kahn@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: Reduce number of parameters passed to send handlersDennis Dalessandro1-8/+15
The current send function handlers are passed a bunch of parameters that are already part of the data structure that is passed in first (qp). This patch removes all of this and just passes the QP. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: add ACK coalescing logicMike Marciniszyn1-3/+4
Implement ACK coalesing logic using a 8 bit counter. The algorithm is send pio ack when: - fecn present - this is the first packet in an interrupt session - counter is >= HFI1_PSN_CREDIT Otherwise the ack is defered. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: add common routine for queuing acksMike Marciniszyn1-5/+7
This patch is a prelimary patch required to coalesce acks. The routine to "schedule" a QP for sending a NAK is now centralized in rc_defer_ack(). The flag is changed for clarity since the all acks will potentially use the deferral mechanism. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: pre-compute sc and sde for RC/UC QPsMike Marciniszyn1-1/+2
Now that we have a multi-threaded work queue we precomputed and store the SC and SDE on RC and UC QPs for faster access. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: Use parallel workqueue for SDMA enginesMike Marciniszyn1-1/+0
The workqueue is currently single threaded per port which for a small number of SDMA engines is ok. For hfi1, the there are up to 16 SDMA engines that can be fed descriptors in parallel. Use alloc_workqueue with a workqueue limit of the number of sdma engines and with WQ_CPU_INTENSIVE and WQ_HIGHPRI specified. Then change send to use the new scheduler which no longer needs to get the s_lock Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-19staging/rdma/hfi1: move hfi1_migrate_qpMike Marciniszyn1-2/+0
Move hfi1_migrate_qp from ruc.c to qp.[hc] in prep for modifying the QP workqueue. Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-11-07Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdmaLinus Torvalds1-8/+6
Pull rdma updates from Doug Ledford: "This is my initial round of 4.4 merge window patches. There are a few other things I wish to get in for 4.4 that aren't in this pull, as this represents what has gone through merge/build/run testing and not what is the last few items for which testing is not yet complete. - "Checksum offload support in user space" enablement - Misc cxgb4 fixes, add T6 support - Misc usnic fixes - 32 bit build warning fixes - Misc ocrdma fixes - Multicast loopback prevention extension - Extend the GID cache to store and return attributes of GIDs - Misc iSER updates - iSER clustering update - Network NameSpace support for rdma CM - Work Request cleanup series - New Memory Registration API" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (76 commits) IB/core, cma: Make __attribute_const__ declarations sparse-friendly IB/core: Remove old fast registration API IB/ipath: Remove fast registration from the code IB/hfi1: Remove fast registration from the code RDMA/nes: Remove old FRWR API IB/qib: Remove old FRWR API iw_cxgb4: Remove old FRWR API RDMA/cxgb3: Remove old FRWR API RDMA/ocrdma: Remove old FRWR API IB/mlx4: Remove old FRWR API support IB/mlx5: Remove old FRWR API support IB/srp: Dont allocate a page vector when using fast_reg IB/srp: Remove srp_finish_mapping IB/srp: Convert to new registration API IB/srp: Split srp_map_sg RDS/IW: Convert to new memory registration API svcrdma: Port to new memory registration API xprtrdma: Port to new memory registration API iser-target: Port to new memory registration API IB/iser: Port to new fast registration API ...
2015-10-29IB/hfi1: Remove fast registration from the codeSagi Grimberg1-8/+0
The driver does not support it anyway, and the support should be added to a generic layer shared by both hfi1, qib and softroce drivers. Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2015-10-27staging/rdma/hfi1: Add a schedule in send threadDean Luick1-0/+1
When under heavy load, the send handler can run too long without allowing other tasks to run. Add a conditional resched to break this up. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-10-27staging/rdma/hfi1: Fix regression in send performanceMike Marciniszyn1-2/+0
The clear_ahg call is new in hfi1 vs qib. For small messages the progress routine always builds one and clears out the ahg state when the queue has gone to empty which is the predominant case for small messages. Inline the routine and avoid the call to sdma_ahg_free to mitigate the performance impact. Finally, move the routine to qp.h for scope reasons. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.