aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/mlx5
AgeCommit message (Collapse)AuthorFilesLines
2019-01-15RDMA/mad: Reduce MAD scope to mlx5_ib onlyLeon Romanovsky4-7/+46
Management Datagram Interface (MAD) is applicable only when physical port is Infiniband. It makes MAD command logic to be completely unrelated to eth/core parts of mlx5. Signed-off-by: Leon Romanovsky <[email protected]> Acked-by: Jason Gunthorpe <[email protected]>
2019-01-14RDMA: Introduce and use rdma_device_to_ibdev()Parav Pandit1-5/+8
Introduce and use rdma_device_to_ibdev() API for those drivers which are registering one sysfs group and also use in ib_core. In subsequent patch, device->provider_ibdev one-to-one mapping is no longer holds true during accessing sysfs entries. Therefore, introduce an API rdma_device_to_ibdev() that provides such information. Signed-off-by: Parav Pandit <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-14RDMA: Rename port_callback to init_portParav Pandit1-1/+1
Most provider routines are callback routines which ib core invokes. _callback suffix doesn't convey information about when such callback is invoked. Therefore, rename port_callback to init_port. Additionally, store the init_port function pointer in ib_device_ops, so that it can be accessed in subsequent patches when binding rdma device to net namespace. Signed-off-by: Parav Pandit <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-10RDMA: Clear PD objects during their allocationLeon Romanovsky1-1/+1
As part of an audit process to update drivers to use rdma_restrack_add() ensure that PD objects is cleared before access. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-10IB/{core,hw}: Have ib_umem_get extract the ib_ucontext from ib_udataJason Gunthorpe8-49/+45
ib_umem_get() can only be called in a method callback, which always has a udata parameter. This allows ib_umem_get() to derive the ucontext pointer directly from the udata without requiring the drivers to find it in some way or another. Signed-off-by: Jason Gunthorpe <[email protected]> Signed-off-by: Shamir Rabinovitch <[email protected]>
2019-01-10IB/{core,uverbs}: Move ib_umem_xxx functions from ib_core to ib_uverbsShamir Rabinovitch1-1/+0
The next patch will add dependency from ib_umem_get in to ib_uverbs so move the required ib_umem_xxx functionality to it's correct module - ib_uverbs - and avoid circular dependecy from the form of ib_core -> ib_uverbs -> ib_core in depmod. Since this now requires all drivers to be build modular if uverbs is modular, hoist the test a couple drivers had into the main kconfig and apply it to all drivers uniformly. Signed-off-by: Shamir Rabinovitch <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-08RDMA/mlx5: Embed into the code flow the ODP config optionLeon Romanovsky3-41/+33
Convert various places to more readable code, which embeds CONFIG_INFINIBAND_ON_DEMAND_PAGING into the code flow. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-08RDMA/mlx5: Introduce and reuse helper to identify ODP MRLeon Romanovsky3-13/+16
Consolidate various checks if MR is ODP backed to one simple helper and update call sites to use it. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-08RDMA/core: Don't depend device ODP capabilities on kconfig optionLeon Romanovsky1-5/+5
Device capability bits are exposing what specific device supports from HW perspective. Those bits are not dependent on kernel configurations and RDMA/core should ensure that proper interfaces to users will be disabled if CONFIG_INFINIBAND_ON_DEMAND_PAGING is not set. Fixes: f4056bfd8ccf ("IB/core: Add on demand paging caps to ib_uverbs_ex_query_device") Fixes: 8cdd312cfed7 ("IB/mlx5: Implement the ODP capability query verb") Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-08RDMA: Clean structures from CONFIG_INFINIBAND_ON_DEMAND_PAGINGLeon Romanovsky1-2/+0
CONFIG_INFINIBAND_ON_DEMAND_PAGING is used in general structures to micro-optimize the memory footprint. Remove it, so it will allow us to simplify various ODP device flows. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-02Revert "IB/mlx5: Fix long EEH recover time with NVMe offloads"Leon Romanovsky1-16/+3
Longer term testing shows this patch didn't play well with MR cache and caused to call traces during remove_mkeys(). This reverts commit bb7e22a8ab00ff9ba911a45ba8784cef9e6d6f7a. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2019-01-02IB/mlx5: Allow XRC INI usage via verbs in DEVX contextYishai Hadas1-1/+2
From device point of view both XRC target and initiator are XRC transport type. Fix to use the expected UID as was handled for the XRC target case to allow its usage via verbs in DEVX context. Fixes: 5aa3771ded54 ("IB/mlx5: Allow XRC usage via verbs in DEVX context") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Artemy Kovalyov <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-28Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdmaLinus Torvalds13-573/+928
Pull rdma updates from Jason Gunthorpe: "This has been a fairly typical cycle, with the usual sorts of driver updates. Several series continue to come through which improve and modernize various parts of the core code, and we finally are starting to get the uAPI command interface cleaned up. - Various driver fixes for bnxt_re, cxgb3/4, hfi1, hns, i40iw, mlx4, mlx5, qib, rxe, usnic - Rework the entire syscall flow for uverbs to be able to run over ioctl(). Finally getting past the historic bad choice to use write() for command execution - More functional coverage with the mlx5 'devx' user API - Start of the HFI1 series for 'TID RDMA' - SRQ support in the hns driver - Support for new IBTA defined 2x lane widths - A big series to consolidate all the driver function pointers into a big struct and have drivers provide a 'static const' version of the struct instead of open coding initialization - New 'advise_mr' uAPI to control device caching/loading of page tables - Support for inline data in SRPT - Modernize how umad uses the driver core and creates cdev's and sysfs files - First steps toward removing 'uobject' from the view of the drivers" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (193 commits) RDMA/srpt: Use kmem_cache_free() instead of kfree() RDMA/mlx5: Signedness bug in UVERBS_HANDLER() IB/uverbs: Signedness bug in UVERBS_HANDLER() IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported IB/umad: Start using dev_groups of class IB/umad: Use class_groups and let core create class file IB/umad: Refactor code to use cdev_device_add() IB/umad: Avoid destroying device while it is accessed IB/umad: Simplify and avoid dynamic allocation of class IB/mlx5: Fix wrong error unwind IB/mlx4: Remove set but not used variable 'pd' RDMA/iwcm: Don't copy past the end of dev_name() string IB/mlx5: Fix long EEH recover time with NVMe offloads IB/mlx5: Simplify netdev unbinding IB/core: Move query port to ioctl RDMA/nldev: Expose port_cap_flags2 IB/core: uverbs copy to struct or zero helper IB/rxe: Reuse code which sets port state IB/rxe: Make counters thread safe IB/mlx5: Use the correct commands for UMEM and UCTX allocation ...
2018-12-22RDMA/mlx5: Signedness bug in UVERBS_HANDLER()Dan Carpenter1-1/+1
The "num_actions" variable needs to be signed for the error handling to work. The maximum number of actions is less than 256 so int type is large enough for that. Fixes: cbfdd442c43e ("IB/uverbs: Add helper to get array size from ptr attribute") Signed-off-by: Dan Carpenter <[email protected]> Acked-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-21IB/mlx5: Allocate the per-port Q counter shared when DEVX is supportedYishai Hadas3-2/+26
The per-port Q counter is some kernel resource and as such may be used by few UID(s) upon DEVX usage. To enable using it for QP/RQ when DEVX context is used need to allocate it with a sharing mode indication to let firmware allows its usage. The UID = 0xffff was chosen to mark it. Signed-off-by: Yishai Hadas <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20IB/mlx5: Fix wrong error unwindJason Gunthorpe1-3/+5
The destroy_workqueue on error unwind is missing, and the code jumps to the wrong exit label. Fixes: 813e90b1aeaa ("IB/mlx5: Add advise_mr() support") Acked-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20IB/mlx5: Fix long EEH recover time with NVMe offloadsHuy Nguyen1-3/+16
On NVMe offloads connection with many IO queues, EEH takes long time to recover. The culprit is the synchronize_srcu in the destroy_mkey. The solution is to use synchronize_srcu only for ODP mkey. Fixes: b4cfe447d47b ("IB/mlx5: Implement on demand paging by adding support for MMU notifiers") Signed-off-by: Huy Nguyen <[email protected]> Reviewed-by: Daniel Jurgens <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20IB/mlx5: Simplify netdev unbindingOr Gerlitz1-5/+9
When dealing with netdev unregister events, we just need to know that this is our currently bounded netdev. There's no need to do any further checks/queries. This patch doesn't change any functionality. Signed-off-by: Or Gerlitz <[email protected]> Reviewed-by: Mark Bloch <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20IB/mlx5: Use the correct commands for UMEM and UCTX allocationYishai Hadas1-19/+15
During testing the command format was changed to close a security hole. Revise the driver to use the command format that will actually be supported in GA firmware. Both the UMEM and UCTX are intended only for use by the kernel and cannot be executed using a general command. Since the UMEM and CTX are not part of the general object the caps bits were moved to be some log_xxx location in the general HCA caps. The firmware code was adapted as well to match the above. Fixes: a8b92ca1b0e5 ("IB/mlx5: Introduce DEVX") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Achiad Shochat <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20IB/mlx5: Use uid as part of alloc/dealloc transport domainYishai Hadas1-0/+2
Use uid as part of alloc/dealloc transport domain to let firmware manages the resources correctly. Fixes: d2d19121ae2f ("IB/mlx5: Set uid as part of TD commands") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Artemy Kovalyov <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-20Merge branch 'mlx5-next' into rdma.gitJason Gunthorpe4-28/+25
From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux mlx5 updates taken for dependencies on following patches. * branche 'mlx5-next': (23 commits) IB/mlx5: Introduce uid as part of alloc/dealloc transport domain net/mlx5: Add shared Q counter bits net/mlx5: Continue driver initialization despite debugfs failure net/mlx5: Fold the modify lag code into function net/mlx5: Add lag affinity info to log net/mlx5: Split the activate lag function into two routines net/mlx5: E-Switch, Introduce flow counter affinity IB/mlx5: Unify e-switch representors load approach between uplink and VFs net/mlx5: Use lowercase 'X' for hex values net/mlx5: Remove duplicated include from eswitch.c net/mlx5: Remove the get protocol device interface entry net/mlx5: Support extended destination format in flow steering command net/mlx5: E-Switch, Change vhca id valid bool field to bit flag net/mlx5: Introduce extended destination fields net/mlx5: Revise gre and nvgre key formats net/mlx5: Add monitor commands layout and event data net/mlx5: Add support for plugged-disabled cable status in PME net/mlx5: Add support for PCIe power slot exceeded error in PME net/mlx5: Rework handling of port module events net/mlx5: Move flow counters data structures from flow steering header ...
2018-12-20Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2-6/+7
Lots of conflicts, by happily all cases of overlapping changes, parallel adds, things of that nature. Thanks to Stephen Rothwell, Saeed Mahameed, and others for their guidance in these resolutions. Signed-off-by: David S. Miller <[email protected]>
2018-12-19RDMA: Mark if destroy address handle is in a sleepable contextGal Pressman2-2/+2
Introduce a 'flags' field to destroy address handle callback and add a flag that marks whether the callback is executed in an atomic context or not. This will allow drivers to wait for completion instead of polling for it when it is allowed. Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-19RDMA: Mark if create address handle is in a sleepable contextGal Pressman2-2/+2
Introduce a 'flags' field to create address handle callback and add a flag that marks whether the callback is executed in an atomic context or not. This will allow drivers to wait for completion instead of polling for it when it is allowed. Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-19IB/mlx5: Fix compile issue when ODP disabledDoug Ledford1-4/+4
When CONFIG_INFINIBAND_ON_DEMAND_PAGING is not enabled, we were getting build failures for defined but not used code. Fix that. Fixes: 813e90b1aeaa ("IB/mlx5: Add advise_mr() support") Signed-off-by: Jason Gunthorpe <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2018-12-18RDMA: Cleanup undesired pd->uobject usageShamir Rabinovitch2-9/+9
Drivers should be using udata to determine if a method is invoked from user space or kernel space. A pd does not necessarily say a different objects is kernel or user. Transforming the tests to use udata eliminates a large number of uobject references from the drivers. Signed-off-by: Shamir Rabinovitch <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-18IB/mlx5: Add advise_mr() supportMoni Shoua4-9/+157
The verb advise_mr() is used to give advice to the kernel about an address range that belongs to a MR. Implement the verb and register it on the device. The current implementation supports the only known advice to date, prefetch. Signed-off-by: Moni Shoua <[email protected]> Reviewed-by: Guy Levi <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-18IB/uverbs: Add helper to get array size from ptr attributeMoni Shoua1-7/+5
When the parser of an ioctl command has the knowledge that a ptr attribute in a bundle represents an array of structures, it is useful for it to know the number of elements in the array. This is done by dividing the attribute length with the element size. Signed-off-by: Moni Shoua <[email protected]> Reviewed-by: Guy Levi <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-18RDMA/mlx5: Fix function name typo 'fileds' -> 'fields'Gal Pressman1-4/+4
Fix typo in 'set_mr_fileds' -> 'set_mr_fields'. Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-18RDMA/mlx5: Delete unreachable handle_atomic code by simplifying SW completionLeon Romanovsky3-100/+5
Handle atomic was left as unimplemented from 2013, remove the code till this part will be developed. Remove the dead code by simplifying SW completion logic which is supposed to be the same for send and receive paths. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Reported-by: Stephen Rothwell <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Tested-by: Stephen Rothwell <[email protected]> # compile tested Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-14net/mlx5: Make RoCE and SR-IOV LAG modes explicitAviv Heller3-6/+10
With the introduction of SR-IOV LAG, checking whether LAG is active is no longer good enough, since RoCE and SR-IOV LAG each entails different behavior by both the core and infiniband drivers. This patch introduces facilities to discern LAG type, in addition to mlx5_lag_is_active(). These are implemented in such a way as to allow more complex mode combinations in the future. Signed-off-by: Aviv Heller <[email protected]> Reviewed-by: Roi Dayan <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
2018-12-14Merge branch 'mlx5-next' of ↵Saeed Mahameed3-22/+19
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux mlx5-next shared branch with rdma subtree to avoid mlx5 rdma v.s. netdev conflicts. Highlights: 1) Lag refactroing and flow counter affinity bits. 2) mlx5 core cleanups By Roi Dayan (2) and others * 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: net/mlx5: Fold the modify lag code into function net/mlx5: Add lag affinity info to log net/mlx5: Split the activate lag function into two routines net/mlx5: E-Switch, Introduce flow counter affinity IB/mlx5: Unify e-switch representors load approach between uplink and VFs net/mlx5: Use lowercase 'X' for hex values net/mlx5: Remove duplicated include from eswitch.c Signed-off-by: Saeed Mahameed <[email protected]>
2018-12-14IB/mlx5: Unify e-switch representors load approach between uplink and VFsMark Bloch3-22/+19
When in switchdev mode and the add function is called by the core level driver, make sure we only register the callbacks, but don't create the mlx5 IB device or initialize anything. With this change all the IB devices in switchdev mode are created only once the load callback is invoked by the e-switch core sub-module. This follows the design paradigm under which the all the Eth representors must be loaded before any of IB reprs is loaded. Signed-off-by: Mark Bloch <[email protected]> Acked-by: Or Gerlitz <[email protected]> Reviewed-by: Leon Romanovsky <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
2018-12-12RDMA: Start use ib_device_opsKamal Heib1-1/+1
Make all the required change to start use the ib_device_ops structure. Signed-off-by: Kamal Heib <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-12RDMA/mlx5: Initialize ib_device_ops structKamal Heib1-96/+131
Initialize ib_device_ops with the supported operations using ib_set_device_ops(). Signed-off-by: Kamal Heib <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11IB/{mlx5,ocrdma,qedr,rxe}: Omit port validation from IB verbsYuval Shaia1-5/+0
RDMA core layer already make sure port is valid, no need to check it here again. For the pkey validation this depends on commit b3ac5742fead ("RDMA/core: Validate port number in query_pkey verb") Signed-off-by: Yuval Shaia <[email protected]> Acked-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11RDMA/mlx5: Fail early if user tries to create flows on IB representorsLeon Romanovsky1-4/+12
IB representors don't support creation of RAW ethernet QP flows. Disable them by reusing existing RDMA/core support macros. We do it for both creation and matcher because latter is not usable if no flow creation is available. Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11IB/mlx5: Remove duplicated include from mlx5_ib.hYueHaibing1-1/+0
Remove duplicated include. Signed-off-by: YueHaibing <[email protected]> Acked-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11IB/mlx5: Add 2X width support to query_portMichael Guralnik2-1/+7
Report to the user 2x width over MAD interface. Signed-off-by: Michael Guralnik <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11Merge tag 'v4.20-rc6' into rdma.git for-nextJason Gunthorpe3-29/+32
For dependencies in following patches.
2018-12-11IB/mlx5: Add HDR speed support to query portMichael Guralnik1-0/+5
Report HDR speed when HDR is supported in CapabilityMask2 and the actual speed is HDR. Signed-off-by: Michael Guralnik <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11IB/mlx5: Report CapabilityMask2 in ib_query_portMichael Guralnik2-0/+7
CapabilityMask2 exists when IB_PORT_CAP_MASK2_SUP is set in the original capability mask. In such cases, query its value and report it in query port. Signed-off-by: Michael Guralnik <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-11IB/core: Add new IB ratesMichael Guralnik1-1/+1
Add the new rates that were added to Infiniband spec as part of HDR and 2x support. Signed-off-by: Michael Guralnik <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-10Merge branch 'mlx5-next' of ↵Saeed Mahameed9-141/+1309
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux mlx5-next shared branch with rdma subtree to avoid mlx5 rdma v.s. netdev conflicts. Highlights: 1) RDMA ODP (On Demand Paging) improvements and moving ODP logic to mlx5 RDMA driver 2) Improved mlx5 core driver and device events handling and provided API for upper layers to subscribe to device events. 3) RDMA only code cleanup from mlx5 core 4) Add helper to get CQE opcode 5) Rework handling of port module events 6) shared mlx5_ifc.h updates to avoid conflicts Signed-off-by: Saeed Mahameed <[email protected]>
2018-12-10net/mlx5: Revise gre and nvgre key formatsOz Shlomo1-2/+2
GRE RFC defines a 32 bit key field. NVGRE RFC splits the 32 bit key field to 24 bit VSID (gre_key_h) and 8 bit flow entropy (gre_key_l). Define the two key parsing alternatives in a union, thus enabling both access methods. Signed-off-by: Oz Shlomo <[email protected]> Reviewed-by: Eli Britstein <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
2018-12-09IB/mlx5: Use helper to get CQE opcodeTariq Toukan1-4/+4
Use the new helper that extracts the opcode from a CQE (completion queue entry) structure. Signed-off-by: Tariq Toukan <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]> Acked-by: Leon Romanovsky <[email protected]>
2018-12-07Merge branch 'mlx5-packet-credit-fc' into rdma.gitJason Gunthorpe3-2/+17
Danit Goldberg says: Packet based credit mode Packet based credit mode is an alternative end-to-end credit mode for QPs set during their creation. Credits are transported from the responder to the requester to optimize the use of its receive resources. In packet-based credit mode, credits are issued on a per packet basis. The advantage of this feature comes while sending large RDMA messages through switches that are short in memory. The first commit exposes QP creation flag and the HCA capability. The second commit adds support for a new DV QP creation flag. The last commit report packet based credit mode capability via the MLX5DV device capabilities. * branch 'mlx5-packet-credit-fc': IB/mlx5: Report packet based credit mode device capability IB/mlx5: Add packet based credit mode support net/mlx5: Expose packet based credit mode Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-07IB/mlx5: Report packet based credit mode device capabilityDanit Goldberg1-0/+3
Report packet based credit mode capability via the mlx5 DV interface. Signed-off-by: Danit Goldberg <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-07IB/mlx5: Add packet based credit mode supportDanit Goldberg2-2/+14
The device can support two credit modes, message based (default) and packet based. In order to enable packet based mode, the QP should be created with special flag that indicates this. This patch adds support for the new DV QP creation flag that can be used for RC QPs in order to change the credit mode. Signed-off-by: Danit Goldberg <[email protected]> Reviewed-by: Majd Dibbiny <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2018-12-06IB/mlx5: Enable TX on a DEVX flow tableAlex Vesker1-4/+4
Flow table can be passed as a DEVX object which is a valid destination in an EGRESS flow. Fix the original code to allow that. Fixes: a7ee18bdee83 ("RDMA/mlx5: Allow creating a matcher for a NIC TX flow table") Signed-off-by: Alex Vesker <[email protected]> Reviewed-by: Yishai Hadas <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.