aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/efa
AgeCommit message (Collapse)AuthorFilesLines
2024-08-23RDMA/efa: Add support for node guidYehuda Yitschak4-0/+6
Propagate the unique, per device, ID in the device attributes to the standard node_guid value in IB device. Link: https://patch.msgid.link/r/[email protected] Reviewed-by: Yonatan Nachum <[email protected]> Signed-off-by: Yehuda Yitschak <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2024-08-11RDMA: Pass uverbs_attr_bundle as part of '.reg_user_mr_dmabuf' APIYishai Hadas2-3/+3
Pass uverbs_attr_bundle as part of '.reg_user_mr_dmabuf' API instead of udata. This enables passing some new ioctl attributes to the drivers, as will be introduced in the next patches for mlx5 driver. Change the involved drivers accordingly. Signed-off-by: Yishai Hadas <[email protected]> Link: https://patch.msgid.link/9a25b2fc02443f7c36c2d93499ae25252b6afd40.1722512548.git.leon@kernel.org Signed-off-by: Leon Romanovsky <[email protected]>
2024-07-01RDMA/efa: Add EFA 0xefa3 PCI IDMichael Margolin1-0/+2
Add support for 0xefa3 devices. Reviewed-by: Yonatan Nachum <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2024-06-27RDMA: Pass entire uverbs attr bundle to create cq functionAkiva Goldberger2-2/+3
Changes the create_cq verb signature by sending the entire uverbs attr bundle as a parameter. This allows drivers to send driver specific attrs through ioctl for the create_cq verb and access them in their driver specific code. Also adds a new enum value for driver specific ioctl attributes for methods already supporting UHW. Link: https://lore.kernel.org/r/ed147343987c0d43fd391c1b2f85e2f425747387.1719512393.git.leon@kernel.org Signed-off-by: Akiva Goldberger <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2024-06-26RDMA/efa: Remove duplicate aenq enable macroYonatan Nachum1-4/+0
We have the same macro in main and verbs files and we don't use the macro in the verbs file, remove it. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2024-06-26RDMA/efa: Use offset_in_page() functionGal Pressman1-1/+1
Use offset_in_page() instead of open-coding it. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Yossi Leybovich <[email protected]> Reviewed-by: Firas Jahjah <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2024-05-30RDMA/efa: Properly handle unexpected AQ completionsMichael Margolin1-13/+17
Do not try to handle admin command completion if it has an unexpected command id and print a relevant error message. Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Yehuda Yitschak <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2024-05-30RDMA/efa: Fail probe on missing BARsMichael Margolin1-8/+22
In case any of PCI BARs is missing during device probe we would like to fail as early as possible. Fail if any of the required BARs isn't listed as a memory BAR. Reviewed-by: Daniel Kranzdorf <[email protected]> Reviewed-by: Firas Jahjah <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2024-05-08RDMA/efa: Support QP with unsolicited write w/ imm. receiveMichael Margolin4-3/+31
Add a new EFA flags attribute for QP creation, and support unsolicited write with immediate flag. QPs created with this flag set will not consume receive work requests for incoming RDMA write with immediate. Expose device capability bit for this feature support. Reviewed-by: Daniel Kranzdorf <[email protected]> Reviewed-by: Firas Jahjah <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2024-04-29RDMA/efa: Add shutdown notifierMichael Margolin1-0/+11
Add driver function to stop the device and release any active IRQs as preparation for shutdown. This should fix issues caused by unexpected AQ interrupts when booting kernel using kexec and possible data integrity issues when the system is being shutdown during traffic. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Yonatan Nachum <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2024-01-31RDMA/efa: Limit EQs to available MSI-X vectorsYonatan Nachum2-17/+16
When creating EQs we take into consideration the max number of EQs the device reported it can support and the number of available CPUs. There are situations where the number of EQs the device reported it can support and the PCI configuration of MSI-X is different, take it in account as well when creating EQs. Also request at least 1 MSI-X vector for the management queue and allow the kernel to return a number of vectors in a range between 1 and the max supported MSI-X vectors according to the PCI config. Reviewed-by: Michael Margolin <[email protected]> Reviewed-by: Yonatan Goldhirsh <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2024-01-07RDMA/efa: Add EFA query MR supportMichael Margolin6-6/+140
Add EFA driver uapi definitions and register a new query MR method that currently returns the physical interconnects the device is using to reach the MR. Update admin definitions and efa-abi accordingly. Reviewed-by: Anas Mousa <[email protected]> Reviewed-by: Firas Jahjah <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2023-08-22RDMA/efa: Fix wrong resources deallocation orderYonatan Nachum1-3/+3
When trying to destroy QP or CQ, we first decrease the refcount and potentially free memory regions allocated for the object and then request the device to destroy the object. If the device fails, the object isn't fully destroyed so the user/IB core can try to destroy the object again which will lead to underflow when trying to decrease an already zeroed refcount. Deallocate resources in reverse order of allocating them to safely free them. Fixes: ff6629f88c52 ("RDMA/efa: Do not delay freeing of DMA pages") Reviewed-by: Michael Margolin <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2023-07-12RDMA/efa: Add RDMA write HW statistics countersMichael Margolin4-2/+47
Update device API and request RDMA write counters if RDMA write is supported by device. Expose newly added counters through ib core counters mechanism. Reviewed-by: Daniel Kranzdorf <[email protected]> Reviewed-by: Yonatan Nachum <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2023-05-16RDMA/efa: Fix unsupported page sizes in deviceYonatan Nachum1-1/+1
Device uses 4KB size blocks for user pages indirect list while the driver creates those blocks with the size of PAGE_SIZE of the kernel. On kernels with PAGE_SIZE different than 4KB (ARM RHEL), this leads to a failure on register MR with indirect list because of the miss communication between driver and device. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Michael Margolin <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2023-04-21RDMA/efa: Add rdma write capability to device capsYonatan Nachum3-17/+43
Add rdma write capability that is propagated from the device to rdma-core. Enable MR creation with remote write permissions according to this device capability. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Michael Margolin <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2023-03-22RDMA/efa: Add data polling capability feature bitYonatan Nachum2-3/+9
Add feature bit to existing device caps field. EFA supports data polling of 128 bytes blocks. The flag indicates that the NIC guarentees that a 128 byte aligned block is written in order, ie that observing the last 8 bits of the block mean the prior 127 bytes are also written. It is useful for "last data polling" acceleration techniques. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Yehuda Yitschak <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Yonatan Nachum <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Acked-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-10-24RDMA/efa: Add EFA 0xefa2 PCI IDMichael Margolin1-1/+3
Add support for 0xefa2 devices. Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-08-21RDMA/efa: Support CQ receive entries with source GIDMichael Margolin5-5/+309
Add a parameter for create CQ admin command to set source address on receive completion descriptors. Report capability for this feature through query device verb. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas Jahjah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Daniel Kranzdorf <[email protected]> Signed-off-by: Michael Margolin <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2021-10-28RDMA/efa: Add support for dmabuf memory regionsGal Pressman3-31/+101
Implement a dmabuf importer for the EFA driver. As ODP is not supported, the pinned dmabuf are used to prevent the move_notify callback from being called. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-10-12RDMA/counter: Add a descriptor in struct rdma_hw_statsAharon Landau1-9/+10
Add a counter statistic descriptor structure in rdma_hw_stats. In addition to the counter name, more meta-information will be added. This code extension is needed for optional-counter support in the following patches. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Aharon Landau <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Mark Zhang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-10-06RDMA/efa: CQ notificationsGal Pressman10-52/+610
This patch adds support for CQ notifications through the standard verbs api. In order to achieve that, a new event queue (EQ) object is introduced, which is in charge of reporting completion events to the driver. On driver load, EQs are allocated and their affinity is set to a single cpu. When a user app creates a CQ with a completion channel, the completion vector number is converted to a EQ number, which is in charge of reporting the CQ events. In addition, the CQ creation admin command now returns an offset for the CQ doorbell, which is mapped to the userspace provider and is used to arm the CQ when requested by the user. The EQs use a single doorbell (located on the registers BAR), which encodes the EQ number and arm as part of the doorbell value. The EQs are polled by the driver on each new EQE, and arm it when the poll is completed. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-09-02Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdmaLinus Torvalds3-85/+92
Pull rdma updates from Jason Gunthorpe: "This is quite a small cycle, no major series stands out. The HNS and rxe drivers saw the most activity this cycle, with rxe being broken for a good chunk of time. The significant deleted line count is due to a SPDX cleanup series. Summary: - Various cleanup and small features for rtrs - kmap_local_page() conversions - Driver updates and fixes for: efa, rxe, mlx5, hfi1, qed, hns - Cache the IB subnet prefix - Rework how CRC is calcuated in rxe - Clean reference counting in iwpm's netlink - Pull object allocation and lifecycle for user QPs to the uverbs core code - Several small hns features and continued general code cleanups - Fix the scatterlist confusion of orig_nents/nents introduced in an earlier patch creating the append operation" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (90 commits) RDMA/mlx5: Relax DCS QP creation checks RDMA/hns: Delete unnecessary blank lines. RDMA/hns: Encapsulate the qp db as a function RDMA/hns: Adjust the order in which irq are requested and enabled RDMA/hns: Remove RST2RST error prints for hw v1 RDMA/hns: Remove dqpn filling when modify qp from Init to Init RDMA/hns: Fix QP's resp incomplete assignment RDMA/hns: Fix query destination qpn RDMA/hfi1: Convert to SPDX identifier IB/rdmavt: Convert to SPDX identifier RDMA/hns: Bugfix for incorrect association between dip_idx and dgid RDMA/hns: Bugfix for the missing assignment for dip_idx RDMA/hns: Bugfix for data type of dip_idx RDMA/hns: Fix incorrect lsn field RDMA/irdma: Remove the repeated declaration RDMA/core/sa_query: Retry SA queries RDMA: Use the sg_table directly and remove the opencoded version from umem lib/scatterlist: Fix wrong update of orig_nents lib/scatterlist: Provide a dedicated function to support table append RDMA/hns: Delete unused hns bitmap interface ...
2021-08-22RDMA/efa: Rename vector field in efa_irq struct to irqnGal Pressman2-11/+9
The vector field naming is quite confusing, it is better referred to as irqn. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-08-22RDMA/efa: Remove unused cpu field from irq structGal Pressman2-3/+1
The cpu field in efa_irq struct is unused, remove it. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-08-20RDMA/efa: Free IRQ vectors on error flowGal Pressman1-0/+1
Make sure to free the IRQ vectors in case the allocation doesn't return the expected number of IRQs. Fixes: b7f5e880f377 ("RDMA/efa: Add the efa module") Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-08-03RDMA: Globally allocate and release QP memoryLeon Romanovsky3-22/+12
Convert QP object to follow IB/core general allocation scheme. That change allows us to make sure that restrack properly kref the memory. Link: https://lore.kernel.org/r/48e767124758aeecc433360ddd85eaa6325b34d9.1627040189.git.leonro@nvidia.com Reviewed-by: Gal Pressman <[email protected]> #efa Tested-by: Gal Pressman <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> #rdma and core Tested-by: Dennis Dalessandro <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Tested-by: Tatyana Nikolova <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-08-03RDMA/efa: Remove double QP type assignmentLeon Romanovsky1-1/+0
The QP type is set by the IB/core and shouldn't be set in the driver. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/838c40134c1590167b888ca06ad51071139ff2ae.1627040189.git.leonro@nvidia.com Acked-by: Gal Pressman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-07-15RDMA/efa: Split hardware stats to device and port statsGal Pressman1-48/+70
The hardware stats API distinguishes between device and port statistics, split the EFA stats accordingly instead of always dumping everything. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-06-16RDMA: Split the alloc_hw_stats() ops to port and device variantsJason Gunthorpe3-3/+14
This is being used to implement both the port and device global stats, which is causing some confusion in the drivers. For instance EFA and i40iw both seem to be misusing the device stats. Split it into two ops so drivers that don't support one or the other can leave the op NULL'd, making the calling code a little simpler to understand. Link: https://lore.kernel.org/r/1955c154197b2a159adc2dc97266ddc74afe420c.1623427137.git.leonro@nvidia.com Tested-by: Gal Pressman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-03-30RDMA/efa: Use strscpy instead of strlcpyGal Pressman1-5/+5
The strlcpy function doesn't limit the source length, use the preferred strscpy function instead. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-03-26RDMA: Support more than 255 rdma portsMark Bloch2-14/+14
Current code uses many different types when dealing with a port of a RDMA device: u8, unsigned int and u32. Switch to u32 to clean up the logic. This allows us to make (at least) the core view consistent and use the same type. Unfortunately not all places can be converted. Many uverbs functions expect port to be u8 so keep those places in order not to break UAPIs. HW/Spec defined values must also not be changed. With the switch to u32 we now can support devices with more than 255 ports. U32_MAX is reserved to make control logic a bit easier to deal with. As a device with U32_MAX ports probably isn't going to happen any time soon this seems like a non issue. When a device with more than 255 ports is created uverbs will report the RDMA device as having 255 ports as this is the max currently supported. The verbs interface is not changed yet because the IBTA spec limits the port size in too many places to be u8 and all applications that relies in verbs won't be able to cope with this change. At this stage, we are extending the interfaces that are using vendor channel solely Once the limitation is lifted mlx5 in switchdev mode will be able to have thousands of SFs created by the device. As the only instance of an RDMA device that reports more than 255 ports will be a representor device and it exposes itself as a RAW Ethernet only device CM/MAD/IPoIB and other ULPs aren't effected by this change and their sysfs/interfaces that are exposes to userspace can remain unchanged. While here cleanup some alignment issues and remove unneeded sanity checks (mainly in rdmavt), Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Mark Bloch <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-28RDMA/efa: Remove unused syndrome enum valuesGal Pressman1-6/+0
The notification syndrome enum values are unused, remove them. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-28RDMA/efa: Remove unused 'select' field from get/set feature command descriptorGal Pressman1-9/+2
The 'select' field in the get/set feature admin command is unimplemented, unused and misleading, remove it. The command always refers to the current values. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-28RDMA/efa: Remove unnecessary indentation in defs commentsGal Pressman2-6/+6
The indentation in the subsequent comment lines is unnecessary, remove it. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-28RDMA/efa: Remove duplication of upper/lower_32_bitsGal Pressman1-9/+6
The EFA_DMA_ADDR_TO_UINT32_HIGH/LOW macros are the same as the kernel's upper/lower_32_bits, remove them and use kernel macros instead. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-28RDMA/efa: Remove redundant NULL pointer check of CQEGal Pressman1-10/+6
A pointer to store the command completion must be provided as it is always used in efa_com_put_comp_ctx() to return the completion context back to the pool. Remove the NULL pointer check and the redundant 'status' field stored on the context as it could be retrieved from the completion itself. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2021-01-22RDMA/hw/efa/efa_com: Stop using param description notation for non-paramsLee Jones1-1/+1
Fixes the following W=1 kernel build warning(s): drivers/infiniband/hw/efa/efa_com.c:801: warning: Excess function parameter 'note' description in 'efa_com_admin_q_comp_intr_handler' Link: https://lore.kernel.org/r/[email protected] Cc: Gal Pressman <[email protected]> Cc: Yossi Leybovich <[email protected]> Cc: Doug Ledford <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: [email protected] Signed-off-by: Lee Jones <[email protected]> Acked-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-12-16Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdmaLinus Torvalds2-31/+9
Pull rdma updates from Jason Gunthorpe: "A smaller set of patches, nothing stands out as being particularly major this cycle. The biggest item would be the new HIP09 HW support from HNS, otherwise it was pretty quiet for new work here: - Driver bug fixes and updates: bnxt_re, cxgb4, rxe, hns, i40iw, cxgb4, mlx4 and mlx5 - Bug fixes and polishing for the new rts ULP - Cleanup of uverbs checking for allowed driver operations - Use sysfs_emit all over the place - Lots of bug fixes and clarity improvements for hns - hip09 support for hns - NDR and 50/100Gb signaling rates - Remove dma_virt_ops and go back to using the IB DMA wrappers - mlx5 optimizations for contiguous DMA regions" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (147 commits) RDMA/cma: Don't overwrite sgid_attr after device is released RDMA/mlx5: Fix MR cache memory leak RDMA/rxe: Use acquire/release for memory ordering RDMA/hns: Simplify AEQE process for different types of queue RDMA/hns: Fix inaccurate prints RDMA/hns: Fix incorrect symbol types RDMA/hns: Clear redundant variable initialization RDMA/hns: Fix coding style issues RDMA/hns: Remove unnecessary access right set during INIT2INIT RDMA/hns: WARN_ON if get a reserved sl from users RDMA/hns: Avoid filling sl in high 3 bits of vlan_id RDMA/hns: Do shift on traffic class when using RoCEv2 RDMA/hns: Normalization the judgment of some features RDMA/hns: Limit the length of data copied between kernel and userspace RDMA/mlx4: Remove bogus dev_base_lock usage RDMA/uverbs: Fix incorrect variable type RDMA/core: Do not indicate device ready when device enablement fails RDMA/core: Clean up cq pool mechanism RDMA/core: Update kernel documentation for ib_create_named_qp() MAINTAINERS: SOFT-ROCE: Change Zhu Yanjun's email address ...
2020-12-01RDMA/efa: Use dma_set_mask_and_coherent() to simplify codeGal Pressman1-9/+2
Use dma_set_mask_and_coherent() instead of pci_set_dma_mask() followed by a pci_set_consistent_dma_mask(). Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-12-01RDMA/efa: Use the correct current and new states in modify QPGal Pressman1-2/+2
The local variables cur_state and new_state hold the state that should be used for the modify QP operation instead of the ones in the ib_qp_attr struct. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Firas JahJah <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-11-16RDMA/efa: Remove .create_ah callback assignmentGal Pressman1-1/+0
Drivers now expose two callbacks for address handle creation, one for uverbs and one for kverbs. EFA only supports uverbs so the .create_ah assignment can be removed. Fix the core code caller to check the proper function pointer. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Gal Pressman <[email protected]> Acked-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-26RDMA: Remove AH from uverbs_cmd_maskJason Gunthorpe1-4/+1
Drivers that need a uverbs AH should instead set the create_user_ah() op similar to reg_user_mr(). MODIFY_AH and QUERY_AH cmds were never implemented so are just deleted. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-26RDMA: Check flags during create_cqJason Gunthorpe1-0/+3
Each driver should check that the CQ attrs is supported. Unfortuantely when flags was added to the CQ attrs the drivers were not updated, uverbs_ex_cmd_mask was used to block it. This was missed when create CQ was converted to ioctl, so non-zero flags could have been passed into drivers. Check that flags is zero in all drivers that don't use it, remove IB_USER_VERBS_EX_CMD_CREATE_CQ from uverbs_ex_cmd_mask. Fixes: 41b2a71fc848 ("IB/uverbs: Move ioctl path of create_cq and destroy_cq to a new file") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-26RDMA: Check attr_mask during modify_qpJason Gunthorpe1-0/+3
Each driver should check that it can support the provided attr_mask during modify_qp. IB_USER_VERBS_EX_CMD_MODIFY_QP was being used to block modify_qp_ex because the driver didn't check RATE_LIMIT. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-26RDMA: Remove elements in uverbs_cmd_mask that all drivers setJason Gunthorpe1-15/+1
This is a step toward eliminating uverbs_cmd_mask. Preset this list in the core code. Only the op reg_user_mr wasn't already being required from the drivers. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-26RDMA: Remove uverbs_ex_cmd_mask values that are linked to functionsJason Gunthorpe1-3/+0
Since a while now the uverbs layer checks if the driver implements a function before allowing the ucmd to proceed. This largely obsoletes the cmd_mask stuff, but there is some tricky bits in drivers preventing it from being removed. Remove the easy elements of uverbs_ex_cmd_mask by pre-setting them in the core code. These are triggered soley based on the related ops function pointer. query_device_ex is not triggered based on an op, but all drivers already implement something compatible with the extension, so enable it globally too. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jason Gunthorpe <[email protected]>
2020-10-16RDMA: Explicitly pass in the dma_device to ib_register_deviceJason Gunthorpe1-2/+2
The code in setup_dma_device has become rather convoluted, move all of this to the drivers. Drives now pass in a DMA capable struct device which will be used to setup DMA, or drivers must fully configure the ibdev for DMA and pass in NULL. Other than setting the masks in rvt all drivers were doing this already anyhow. mthca, mlx4 and mlx5 were already setting up maximum DMA segment size for DMA based on their hardweare limits in: __mthca_init_one() dma_set_max_seg_size (1G) __mlx4_init_one() dma_set_max_seg_size (1G) mlx5_pci_init() set_dma_caps() dma_set_max_seg_size (2G) Other non software drivers (except usnic) were extended to UINT_MAX [1, 2] instead of 2G as was before. [1] https://lore.kernel.org/linux-rdma/[email protected]/ [2] https://lore.kernel.org/linux-rdma/[email protected]/ Link: https://lore.kernel.org/r/[email protected] Link: https://lore.kernel.org/r/6b2ed339933d066622d5715903870676d8cc523a.1602590106.git.mchehab+huawei@kernel.org Suggested-by: Christoph Hellwig <[email protected]> Signed-off-by: Parav Pandit <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Reviewed-by: Christoph Hellwig <[email protected]> Signed-off-by: Mauro Carvalho Chehab <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-22RDMA/efa: Drop double zeroing for sg_init_table()Julia Lawall1-1/+1
sg_init_table() zeroes its first argument, so the allocation of that argument doesn't have to. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ expression x,n,flags; @@ x = - kcalloc + kmalloc_array (n,sizeof(*x),flags) ... sg_init_table(x,n) // </smpl> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Julia Lawall <[email protected]> Acked-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-22RDMA/efa: Add messages and RDMA read work requests HW statsDaniel Kranzdorf4-7/+99
Add separate stats types for send messages and RDMA read work requests. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Kranzdorf <[email protected]> Reviewed-by: Yossi Leybovich <[email protected]> Signed-off-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.