summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw
AgeCommit message (Collapse)Author
2022-10-06Merge tag 'v6.0' into rdma.git for-nextJason Gunthorpe
Trvial merge conflicts against rdma.git for-rc resolved matching linux-next: drivers/infiniband/hw/hns/hns_roce_hw_v2.c drivers/infiniband/hw/hns/hns_roce_main.c https://lore.kernel.org/r/20220929124005.105149-1-broonie@kernel.org Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-29RDMA/usnic: fix set-but-not-unused variable 'flags' warningZeng Heng
Remove unused local variable 'flag' without any logic changes. Fixes: e3cf00d0a87f ("IB/usnic: Add Cisco VIC low-level hardware driver") Signed-off-by: Zeng Heng <zengheng4@huawei.com> Link: https://lore.kernel.org/r/20220929031200.4060891-1-zengheng4@huawei.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-28Merge branch 'mlx5-next' of ↵Jakub Kicinski
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux Saeed Mahameed says: ==================== updates from mlx5-next 2022-09-24 Updates form mlx5-next including[1]: 1) HW definitions and support for NPPS clock settings. 2) various cleanups 3) Enable hash mode by default for all NICs 4) page tracker and advanced virtualization HW definitions for vfio [1] https://lore.kernel.org/netdev/20220907233636.388475-1-saeed@kernel.org/ * 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux: net/mlx5: Remove from FPGA IFC file not-needed definitions net/mlx5: Remove unused structs net/mlx5: Remove unused functions net/mlx5: detect and enable bypass port select flow table net/mlx5: Lag, enable hash mode by default for all NICs net/mlx5: Lag, set active ports if support bypass port select flow table RDMA/mlx5: Don't set tx affinity when lag is in hash mode net/mlx5: add IFC bits for bypassing port select flow table net/mlx5: Add support for NPPS with real time mode net/mlx5: Expose NPPS related registers net/mlx5: Query ADV_VIRTUALIZATION capabilities net/mlx5: Introduce ifc bits for page tracker RDMA/mlx5: Move function mlx5_core_query_ib_ppcnt() to mlx5_ib ==================== Link: https://lore.kernel.org/all/20220927201906.234015-1-saeed@kernel.org/ Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-09-27RDMA/mlx5: Don't set tx affinity when lag is in hash modeLiu, Changcheng
In hash mode, without setting tx affinity explicitly, the port select flow table decides which port is used for the traffic. If port_select_flow_table_bypass capability is supported and tx affinity is set explicitly for QP/TIS, they will be added into the explicit affinity table in FW to check which port is used for the traffic. 1. The overloaded explicit affinity table may affect performance. To avoid this, do not set tx affinity explicitly by default. 2. The packets of the same flow need to be transmitted on the same port. Because the packets of the same flow use different QPs in slow & fast path, it shouldn't set tx affinity explicitly for these QPs. Signed-off-by: Liu, Changcheng <jerrliu@nvidia.com> Reviewed-by: Mark Bloch <mbloch@nvidia.com> Reviewed-by: Vlad Buslov <vladbu@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
2022-09-27IB/hfi1: Use skb_put_data() instead of skb_put/memcpy pairShang XiaoJing
Use skb_put_data() instead of skb_put() and memcpy(), which is shorter and clear. Drop the tmp variable that is not needed any more. Link: https://lore.kernel.org/r/20220927022919.16902-1-shangxiaojing@huawei.com Signed-off-by: Shang XiaoJing <shangxiaojing@huawei.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Unified Log Printing StyleGuofeng Yue
The first letter of the log information is changed to lowercase to keep the same style. Link: https://lore.kernel.org/r/20220922123315.3732205-13-xuhaoyue1@hisilicon.com Signed-off-by: Guofeng Yue <yueguofeng@hisilicon.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Replacing magic number with macros in apply_func_caps()Yixing Liu
Replacing magic number with macros in function apply_func_caps(). Link: https://lore.kernel.org/r/20220922123315.3732205-12-xuhaoyue1@hisilicon.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Repacing 'dseg_len' by macros in fill_ext_sge_inl_data()Luoyouming
The sge size is known to be constant, so it's unnecessary to use sizeof to calculate. Link: https://lore.kernel.org/r/20220922123315.3732205-11-xuhaoyue1@hisilicon.com Signed-off-by: Luoyouming <luoyouming@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'max_srq_desc_sz' in capsYangyang Li
The max_srq_desc_sz is defined in the code, but never used, so delete this redundant variable. Link: https://lore.kernel.org/r/20220922123315.3732205-10-xuhaoyue1@hisilicon.com Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'num_mtt_segs' and 'max_extend_sg'Yangyang Li
The num_mtt_segs and max_extend_sg used to be used for HIP06, remove them since the HIP06 code has been removed. Link: https://lore.kernel.org/r/20220922123315.3732205-9-xuhaoyue1@hisilicon.com Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'phy_addr' in hns_roce_hem_list_find_mtt()Chengchang Tang
This parameter has never been used. Remove it to simplify the function. Link: https://lore.kernel.org/r/20220922123315.3732205-8-xuhaoyue1@hisilicon.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'use_lowmem' argument from hns_roce_init_hem_table()Yunsheng Lin
As hns_roce_init_hem_table() is always called with use_lowmem being '1', and table->lowmem is set according to that argument, so remove table->lowmem too. Also, as the table->lowmem is used to indicate a dma buffer is allocated with GFP_HIGHUSER or GFP_KERNEL, and calling dma_alloc_coherent() with GFP_KERNEL seems like a common pattern. Link: https://lore.kernel.org/r/20220922123315.3732205-7-xuhaoyue1@hisilicon.com Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'bt_level' for hem_list_alloc_item()Yunsheng Lin
The 'bt_level' parameter is not used in hem_list_alloc_item(), so remove it. Link: https://lore.kernel.org/r/20220922123315.3732205-6-xuhaoyue1@hisilicon.com Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove redundant 'attr_mask' in modify_qp_init_to_init()Yixing Liu
The attr_mask variable is not used in the function, so remove it. Link: https://lore.kernel.org/r/20220922123315.3732205-5-xuhaoyue1@hisilicon.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove unnecessary brackets when getting pointGuofeng Yue
Delete () when using & to obtain an address. Link: https://lore.kernel.org/r/20220922123315.3732205-4-xuhaoyue1@hisilicon.com Signed-off-by: Guofeng Yue <yueguofeng@hisilicon.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Remove unnecessary braces for single statement blocksGuofeng Yue
Braces {} are not necessary for single statement blocks. Link: https://lore.kernel.org/r/20220922123315.3732205-3-xuhaoyue1@hisilicon.com Signed-off-by: Guofeng Yue <yueguofeng@hisilicon.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/hns: Cleanup for a spelling error of AsynchronousGuofeng Yue
Fixed a spelling error for Asynchronous. Link: https://lore.kernel.org/r/20220922123315.3732205-2-xuhaoyue1@hisilicon.com Signed-off-by: Guofeng Yue <yueguofeng@hisilicon.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/mlx5: Enable ATS support for MRs and umemsJason Gunthorpe
For mlx5 if ATS is enabled in the PCI config then the device will use ATS requests for only certain DMA operations. This has to be opted in by the SW side based on the mkey or umem settings. ATS slows down the PCI performance, so it should only be set in cases when it is needed. All of these cases revolve around optimizing PCI P2P transfers and avoiding bad cases where the bus just doesn't work. Link: https://lore.kernel.org/r/4-v1-bd147097458e+ede-umem_dmabuf_jgg@nvidia.com Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27RDMA/mlx5: Add support for dmabuf to devx umemJason Gunthorpe
This is modeled after the similar EFA enablement in commit 66f4817b5712 ("RDMA/efa: Add support for dmabuf memory regions"). Like EFA there is no support for revocation so we simply call the ib_umem_dmabuf_get_pinned() to obtain a umem instead of the normal ib_umem_get(). Everything else stays the same. Link: https://lore.kernel.org/r/3-v1-bd147097458e+ede-umem_dmabuf_jgg@nvidia.com Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-09-27Merge branch 'mlx5-vfio' into mlx5-nextLeon Romanovsky
Merge net/mlx5 dependencies for device DMA logging. Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
2022-09-22IB: Set IOVA/LENGTH on IB_MR in core/uverbs layersDaisuke Matsuda
Set 'iova' and 'length' on ib_mr in ib_uverbs and ib_core layers to let all drivers have the members filled. Also, this commit removes redundancy in the respective drivers. Previously, commit 04c0a5fcfcf65 ("IB/uverbs: Set IOVA on IB MR in uverbs layer") changed to set 'iova', but seems to have missed 'length' and the ib_core layer at that time. Fixes: 04c0a5fcfcf65 ("IB/uverbs: Set IOVA on IB MR in uverbs layer") Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com> Link: https://lore.kernel.org/r/20220921080844.1616883-1-matsuda-daisuke@fujitsu.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-21RDMA/erdma: Support dynamic mtuCheng Xu
Hardware now support jumbo frame for RDMA. So we introduce a new CMDQ message to support mtu change notification. Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com> Link: https://lore.kernel.org/r/20220909093822.33868-5-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20IB/hfi1: remove rc_only_opcode and uc_only_opcode declarationsGaosheng Cui
rc_only_opcode and uc_only_opcode have been removed since commit b374e060cc2a ("IB/hfi1: Consolidate pio control masks into single definition"), so remove them. Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com> Link: https://lore.kernel.org/r/20220911092325.3216513-1-cuigaosheng1@huawei.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/erdma: Make hardware internal opcodes invisible to driverCheng Xu
Some opcodes are used in hardware internally, and driver does not care about them. So, we change them to reserved opcodes in driver. Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com> Link: https://lore.kernel.org/r/20220909093822.33868-4-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/erdma: Remove redundant includesCheng Xu
Many of erdma's includes are redundant, because they are already included indirectly by kernel headers or custom headers. So we remove all the unnecessary direct-includes. Besides, add linux/pci.h to erdma.h because it's also used in the file. Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com> Link: https://lore.kernel.org/r/20220909093822.33868-3-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/erdma: Eliminate unnecessary casting for erdma_post_cmd_waitCheng Xu
erdma_post_cmd_wait does not use the 'u64 *req' input parameter directly. So it is better to define it to 'void *req', and by this we can eliminate the casting when calling erdma_post_cmd_wait. Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com> Link: https://lore.kernel.org/r/20220909093822.33868-2-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/qib: fix repeated words in commentswangjianli
Delete the redundant word 'to'. Signed-off-by: wangjianli <wangjianli@cdjrlc.com> Link: https://lore.kernel.org/r/20220908132036.42355-1-wangjianli@cdjrlc.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/hfi1: fix repeated words in commentswangjianli
Delete the redundant word 'to'. Signed-off-by: wangjianli <wangjianli@cdjrlc.com> Link: https://lore.kernel.org/r/20220908131824.41106-1-wangjianli@cdjrlc.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/irdma: Validate udata inlen and outlenShiraz Saleem
Currently ib_copy_from_udata and ib_copy_to_udata could underfill the request and response buffer if the user-space passes an undersized value for udata->inlen or udata->outlen respectively [1] This could lead to undesirable behavior. Zero initing the buffer only goes as far as preventing using the buffer uninitialized. Validate udata->inlen and udata->outlen passed from user-space to ensure they are at least the required minimum size. [1] https://lore.kernel.org/linux-rdma/MWHPR11MB0029F37D40D9D4A993F8F549E9D79@MWHPR11MB0029.namprd11.prod.outlook.com/ Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220907191324.1173-3-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-20RDMA/irdma: Align AE id codes to correct flush code and eventSindhu-Devale
A number of asynchronous event (AE) ids were not aligned to the correct flush_code and event_type. Fix these up so that the correct IBV error and event codes are returned to application. Also, add handling for new AE ids like IRDMA_AE_INVALID_REQUEST to return the correct WC error code. Fixes: 44d9e52977a1 ("RDMA/irdma: Implement device initialization definitions") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220907191324.1173-2-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-08RDMA/mlx5: Remove duplicate assignment in umr_rereg_pas()Daisuke Matsuda
The same value is assigned to 'mr->ibmr.length'. Remove redundant one. Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com> Link: https://lore.kernel.org/r/20220908083058.3993700-1-matsuda-daisuke@fujitsu.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-07RDMA/irdma: Report RNR NAK generation in device capsSindhu-Devale
Report RNR NAK generation when device capabilities are queried Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220906223244.1119-6-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-07RDMA/irdma: Use s/g array in post send only when its validSindhu-Devale
Send with invalidate verb call can pass in an uninitialized s/g array with 0 sge's which is filled into irdma WQE and causes a HW asynchronous event. Fix this by using the s/g array in irdma post send only when its valid. Fixes: 551c46e ("RDMA/irdma: Add user/kernel shared libraries") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220906223244.1119-5-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-07RDMA/irdma: Return correct WC error for bind operation failureSindhu-Devale
When a QP and a MR on a local host are in different PDs, the HW generates an asynchronous event (AE). The same AE is generated when a QP and a MW are in different PDs during a bind operation. Return the more appropriate IBV_WC_MW_BIND_ERR for the latter case by checking the OP type from the CQE in error. Fixes: 551c46edc769 ("RDMA/irdma: Add user/kernel shared libraries") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220906223244.1119-4-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-07RDMA/irdma: Return error on MR deregister CQP failureSindhu-Devale
The MR deregister CQP can fail if an MW is bound to it. Return an appropriate error for this case. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220906223244.1119-3-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-07RDMA/irdma: Report the correct max cqes from query deviceSindhu-Devale
Report the correct max cqes available to an application taking into account a reserved entry to detect overflow. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale <sindhu.devale@intel.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Link: https://lore.kernel.org/r/20220906223244.1119-2-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05RDMA/hfi1: Remove the unneeded result variableye xingchen
Return the value set_link_state() directly instead of storing it in another redundant variable. Reported-by: Zeal Robot <zealci@zte.com.cn> Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn> Link: https://lore.kernel.org/r/20220901074209.313004-1-ye.xingchen@zte.com.cn Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05Merge branch 'mlx5-next' into wip/leon-for-nextLeon Romanovsky
Perform merge of Mellanox shared branch. * mlx5-next: RDMA/mlx5: Move function mlx5_core_query_ib_ppcnt() to mlx5_ib
2022-09-05RDMA/mlx5: Move function mlx5_core_query_ib_ppcnt() to mlx5_ibChris Mi
This patch doesn't change any functionality, but move one function to mlx5_ib because it is not used by mlx5_core. The actual fix is in the next patch. Reviewed-by: Roi Dayan <roid@nvidia.com> Signed-off-by: Chris Mi <cmi@nvidia.com> Link: https://lore.kernel.org/r/fd47b9138412bd94ed30f838026cbb4cf3878150.1661763871.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05IB/mlx5: Support querying eswitch functions from DEVXBodong Wang
Query eswitch functions returns information of the external host PF(if it exists). It can be used to check if DEVX is running on ECPF. Reviewed-by: Erez Shitrit <erezsh@nvidia.com> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Bodong Wang <bodong@mellanox.com> Link: https://lore.kernel.org/r/4265925178ab3224dc1d3e3784bb312d808edca5.1661763785.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05RDMA/mlx5: Fix UMR cleanup on error flow of driver initMaor Gottlieb
The cited commit removed from the cleanup flow of umr the checks if the resources were created. This could lead to null-ptr-deref in case that we had failure in mlx5_ib_stage_ib_reg_init stage. Fix it by adding new state to the umr that can say if the resources were created or not and check it in the umr cleanup flow before destroying the resources. Fixes: 04876c12c19e ("RDMA/mlx5: Move init and cleanup of UMR to umr.c") Reviewed-by: Michael Guralnik <michaelgur@nvidia.com> Signed-off-by: Maor Gottlieb <maorg@nvidia.com> Link: https://lore.kernel.org/r/4cfa61386cf202e9ce330e8d228ce3b25a36326e.1661763459.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05RDMA/mlx5: Set local port to one when accessing countersChris Mi
When accessing Ports Performance Counters Register (PPCNT), local port must be one if it is Function-Per-Port HCA that HCA_CAP.num_ports is 1. The offending patch can change the local port to other values when accessing PPCNT after enabling switchdev mode. The following syndrome will be printed: # cat /sys/class/infiniband/rdmap4s0f0/ports/2/counters/* # dmesg mlx5_core 0000:04:00.0: mlx5_cmd_check:756:(pid 12450): ACCESS_REG(0x805) op_mod(0x1) failed, status bad parameter(0x3), syndrome (0x1e5585) Fix it by setting local port to one for Function-Per-Port HCA. Fixes: 210b1f78076f ("IB/mlx5: When not in dual port RoCE mode, use provided port as native") Reviewed-by: Mark Bloch <mbloch@nvidia.com> Signed-off-by: Chris Mi <cmi@nvidia.com> Link: https://lore.kernel.org/r/6c5086c295c76211169e58dbd610fb0402360bab.1661763459.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-09-05RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting profileMaher Sanalla
When the RDMA auxiliary driver probes, it sets its profile based on devlink driverinit value. The latter might not be in sync with FW yet (In case devlink reload is not performed), thus causing a mismatch between RDMA driver and FW. This results in the following FW syndrome when the RDMA driver tries to adjust RoCE state, which fails the probe: "0xC1F678 | modify_nic_vport_context: roce_en set on a vport that doesn't support roce" To prevent this, select the PF profile based on FW RoCE capability instead of relying on devlink driverinit value. To provide backward compatibility of the RoCE disable feature, on older FW's where roce_rw is not set (FW RoCE capability is read-only), keep the current behavior e.g., rely on devlink driverinit value. Fixes: fbfa97b4d79f ("net/mlx5: Disable roce at HCA level") Reviewed-by: Shay Drory <shayd@nvidia.com> Reviewed-by: Michael Guralnik <michaelgur@nvidia.com> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Maher Sanalla <msanalla@nvidia.com> Link: https://lore.kernel.org/r/cb34ce9a1df4a24c135cb804db87f7d2418bd6cc.1661763459.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-30RDMA/hns: Remove redundant member doorbell_qpn of struct hns_roce_qpWenpeng Liang
The value of doorbell_qpn is always equal to qpn on current hardware versions. So remove it. Link: https://lore.kernel.org/r/20220829105021.1427804-5-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-30RDMA/hns: Remove the num_qpc_timer variableYixing Liu
The bt number of qpc_timer of HIP09 increases compared with that of HIP08. Therefore, qpc_timer_bt_num and num_qpc_timer do not match. As a result, the driver may fail to allocate qpc_timer. So the driver needs to uniquely uses qpc_timer_bt_num to represent the bt number of qpc_timer. Fixes: 0e40dc2f70cd ("RDMA/hns: Add timer allocation support for hip08") Link: https://lore.kernel.org/r/20220829105021.1427804-4-liangwenpeng@huawei.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-30RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shiftWenpeng Liang
The value of qp->rq.wqe_shift of HIP08 is always determined by the number of sge. So delete the wrong branch. Fixes: cfc85f3e4b7f ("RDMA/hns: Add profile support for hip08 driver") Fixes: 926a01dc000d ("RDMA/hns: Add QP operations support for hip08 SoC") Link: https://lore.kernel.org/r/20220829105021.1427804-3-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-30RDMA/hns: Fix supported page sizeChengchang Tang
The supported page size for hns is (4K, 128M), not (4K, 2G). Fixes: cfc85f3e4b7f ("RDMA/hns: Add profile support for hip08 driver") Link: https://lore.kernel.org/r/20220829105021.1427804-2-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-28RDMA/irdma: Fix drain SQ hang with no completionShiraz Saleem
SW generated completions for outstanding WRs posted on SQ after QP is in error target the wrong CQ. This causes the ib_drain_sq to hang with no completion. Fix this to generate completions on the right CQ. [ 863.969340] INFO: task kworker/u52:2:671 blocked for more than 122 seconds. [ 863.979224] Not tainted 5.14.0-130.el9.x86_64 #1 [ 863.986588] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 863.996997] task:kworker/u52:2 state:D stack: 0 pid: 671 ppid: 2 flags:0x00004000 [ 864.007272] Workqueue: xprtiod xprt_autoclose [sunrpc] [ 864.014056] Call Trace: [ 864.017575] __schedule+0x206/0x580 [ 864.022296] schedule+0x43/0xa0 [ 864.026736] schedule_timeout+0x115/0x150 [ 864.032185] __wait_for_common+0x93/0x1d0 [ 864.037717] ? usleep_range_state+0x90/0x90 [ 864.043368] __ib_drain_sq+0xf6/0x170 [ib_core] [ 864.049371] ? __rdma_block_iter_next+0x80/0x80 [ib_core] [ 864.056240] ib_drain_sq+0x66/0x70 [ib_core] [ 864.062003] rpcrdma_xprt_disconnect+0x82/0x3b0 [rpcrdma] [ 864.069365] ? xprt_prepare_transmit+0x5d/0xc0 [sunrpc] [ 864.076386] xprt_rdma_close+0xe/0x30 [rpcrdma] [ 864.082593] xprt_autoclose+0x52/0x100 [sunrpc] [ 864.088718] process_one_work+0x1e8/0x3c0 [ 864.094170] worker_thread+0x50/0x3b0 [ 864.099109] ? rescuer_thread+0x370/0x370 [ 864.104473] kthread+0x149/0x170 [ 864.109022] ? set_kthread_struct+0x40/0x40 [ 864.114713] ret_from_fork+0x22/0x30 Fixes: 81091d7696ae ("RDMA/irdma: Add SW mechanism to generate completions on error") Link: https://lore.kernel.org/r/20220824154358.117-1-shiraz.saleem@intel.com Reported-by: Kamal Heib <kamalheib1@gmail.com> Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-24RDMA/hns: Support MR's restrack raw ops for hns driverWenpeng Liang
The MR raw restrack attributes come from the queue context maintained by the ROCEE. For example: $ rdma res show mr dev hns_0 mrn 6 -dd -jp -r [ { "ifindex": 4, "ifname": "hns_0", "data": [ 1,0,0,0,2,0,0,0,0,3,0,0,0,0,2,0,0,0,0,0,32,0,0,0,2,0,0,0, 2,0,0,0,0,0,0,0 ] } ] Link: https://lore.kernel.org/r/20220822104455.2311053-8-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
2022-08-23RDMA/hns: Support MR's restrack ops for hns driverWenpeng Liang
The MR restrack attributes come from the queue information maintained by the driver. For example: $ rdma res show mr dev hns_0 mrn 6 -dd -jp [ { "ifindex": 4, "ifname": "hns_0", "mrn": 6, "rkey": "300", "lkey": "300", "mrlen": 131072, "pdn": 8, "pid": 1524, "comm": "ib_send_bw" }, "drv_pbl_hop_num": 2, "drv_ba_pg_shift": 14, "drv_buf_pg_shift": 12 } Link: https://lore.kernel.org/r/20220822104455.2311053-7-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Leon Romanovsky <leon@kernel.org>
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-04 10:51:04 +0000