kernel/linux.git/drivers/infiniband/ulp, branch v6.19.11

RDMA/rtrs-clt: For conn rejection use actual err number

2026-03-04T12:20:34+00:00

[ Upstream commit fc290630702b530c2969061e7ef0d869a5b6dc4f ] When the connection establishment request is rejected from the server side, then the actual error number sent back should be used. Signed-off-by: Md Haris Iqbal Link: https://patch.msgid.link/20260107161517.56357-10-haris.iqbal@ionos.com Reviewed-by: Grzegorz Prajsner Reviewed-by: Jack Wang Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin

RDMA/rtrs-srv: fix SG mapping

2026-02-26T23:01:15+00:00

[ Upstream commit 83835f7c07b523c7ca2a5ad0a511670b5810539e ] This fixes the following error on the server side: RTRS server session allocation failed: -EINVAL caused by the caller of the `ib_dma_map_sg()`, which does not expect less mapped entries, than requested, which is in the order of things and can be easily reproduced on the machine with enabled IOMMU. The fix is to treat any positive number of mapped sg entries as a successful mapping and cache DMA addresses by traversing modified SG table. Fixes: 9cb837480424 ("RDMA/rtrs: server: main functionality") Signed-off-by: Roman Penyaev Signed-off-by: Jack Wang Signed-off-by: Grzegorz Prajsner Link: https://patch.msgid.link/20260107161517.56357-2-haris.iqbal@ionos.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin

RDMA/rtrs: server: remove dead code

2026-02-26T23:01:14+00:00

[ Upstream commit a3572bdc3a028ca47f77d7166ac95b719cf77d50 ] As rkey had been initialized to zero, the WARN_ON_ONCE should never been triggered. Remove it. Fixes: 9cb837480424 ("RDMA/rtrs: server: main functionality") Signed-off-by: Honggang LI Link: https://patch.msgid.link/20251224023819.138846-1-honggangli@163.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin

RDMA/rtrs: Fix clt_path::max_pages_per_mr calculation

2025-12-30T10:47:32+00:00

If device max_mr_size bits in the range [mr_page_shift+31:mr_page_shift] are zero, the `min3` function will set clt_path::max_pages_per_mr to zero. `alloc_path_reqs` will pass zero, which is invalid, as the third parameter to `ib_alloc_mr`. Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality") Signed-off-by: Honggang LI Link: https://patch.msgid.link/20251229025617.13241-1-honggangli@163.com Signed-off-by: Leon Romanovsky

RTRS/rtrs: clean up rtrs headers kernel-doc

2025-12-17T17:47:07+00:00

Fix all (30+) kernel-doc warnings in rtrs.h and rtrs-pri.h. The changes are: - add ending ':' to enum member names - change enum description separators from '-' to ':' - add "struct" keyword to kernel-doc for structs where missing - fix enum names in enum rtrs_clt_con_type - add a '-' separator and drop the "()" in enum rtrs_clt_con_type - convert struct rtrs_addr to kernel-doc format - add missing struct member descriptions for struct rtrs_attrs Link: https://patch.msgid.link/r/20251129022146.1498273-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Acked-by: Jack Wang Signed-off-by: Jason Gunthorpe

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

2025-12-05T02:54:37+00:00

Pull rdma updates from Jason Gunthorpe: "This has another new RDMA driver 'bng_en' for latest generation Broadcom NICs. There might be one more new driver still to come. Otherwise it is a fairly quite cycle. Summary: - Minor driver bug fixes and updates to cxgb4, rxe, rdmavt, bnxt_re, mlx5 - Many bug fix patches for irdma - WQ_PERCPU annotations and system_dfl_wq changes - Improved mlx5 support for "other eswitches" and multiple PFs - 1600Gbps link speed reporting support. Four Digits Now! - New driver bng_en for latest generation Broadcom NICs - Bonding support for hns - Adjust mlx5's hmm based ODP to work with the very large address space created by the new 5 level paging default on x86 - Lockdep fixups in rxe and siw" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (65 commits) RDMA/rxe: reclassify sockets in order to avoid false positives from lockdep RDMA/siw: reclassify sockets in order to avoid false positives from lockdep RDMA/bng_re: Remove prefetch instruction RDMA/core: Reduce cond_resched() frequency in __ib_umem_release RDMA/irdma: Fix SRQ shadow area address initialization RDMA/irdma: Remove doorbell elision logic RDMA/irdma: Do not set IBK_LOCAL_DMA_LKEY for GEN3+ RDMA/irdma: Do not directly rely on IB_PD_UNSAFE_GLOBAL_RKEY RDMA/irdma: Add missing mutex destroy RDMA/irdma: Fix SIGBUS in AEQ destroy RDMA/irdma: Add a missing kfree of struct irdma_pci_f for GEN2 RDMA/irdma: Fix data race in irdma_free_pble RDMA/irdma: Fix data race in irdma_sc_ccq_arm RDMA/mlx5: Add support for 1600_8x lane speed RDMA/core: Add new IB rate for XDR (8x) support IB/mlx5: Reduce IMR KSM size when 5-level paging is enabled RDMA/bnxt_re: Pass correct flag for dma mr creation RDMA/bnxt_re: Fix the inline size for GenP7 devices RDMA/hns: Support reset recovery for bond RDMA/hns: Support link state reporting for bond ...

RDMA/rtrs: server: Fix error handling in get_or_create_srv

2025-11-10T08:09:41+00:00

After device_initialize() is called, use put_device() to release the device according to kernel device management rules. While direct kfree() work in this case, using put_device() is more correct. Found by code review. Fixes: 9cb837480424 ("RDMA/rtrs: server: main functionality") Signed-off-by: Ma Ke Link: https://patch.msgid.link/20251110005158.13394-1-make24@iscas.ac.cn Acked-by: Jack Wang Signed-off-by: Leon Romanovsky

IB/isert: add WQ_PERCPU to alloc_workqueue users

2025-11-09T11:30:58+00:00

Currently if a user enqueues a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistency cannot be addressed without refactoring the API. alloc_workqueue() treats all queues as per-CPU by default, while unbound workqueues must opt-in via WQ_UNBOUND. This default is suboptimal: most workloads benefit from unbound queues, allowing the scheduler to place worker threads where they’re needed and reducing noise when CPUs are isolated. This continues the effort to refactor workqueue APIs, which began with the introduction of new workqueues and a new alloc_workqueue flag in: commit 128ea9f6ccfb ("workqueue: Add system_percpu_wq and system_dfl_wq") commit 930c2ea566af ("workqueue: Add new WQ_PERCPU flag") This change adds a new WQ_PERCPU flag to explicitly request alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified. With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND), any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND must now use WQ_PERCPU. Once migration is complete, WQ_UNBOUND can be removed and unbound will become the implicit default. Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Link: https://patch.msgid.link/20251107133626.190952-1-marco.crivellari@suse.com Signed-off-by: Leon Romanovsky

IB/iser: add WQ_PERCPU to alloc_workqueue users

2025-11-09T11:30:48+00:00

Currently if a user enqueues a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistency cannot be addressed without refactoring the API. alloc_workqueue() treats all queues as per-CPU by default, while unbound workqueues must opt-in via WQ_UNBOUND. This default is suboptimal: most workloads benefit from unbound queues, allowing the scheduler to place worker threads where they’re needed and reducing noise when CPUs are isolated. This continues the effort to refactor workqueue APIs, which began with the introduction of new workqueues and a new alloc_workqueue flag in: commit 128ea9f6ccfb ("workqueue: Add system_percpu_wq and system_dfl_wq") commit 930c2ea566af ("workqueue: Add new WQ_PERCPU flag") This change adds a new WQ_PERCPU flag to explicitly request alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified. With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND), any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND must now use WQ_PERCPU. Once migration is complete, WQ_UNBOUND can be removed and unbound will become the implicit default. Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Link: https://patch.msgid.link/20251107133306.187939-1-marco.crivellari@suse.com Signed-off-by: Leon Romanovsky

IB/IPoIB: Add support for hwtstamp get/set ndos

2025-10-31T23:36:43+00:00

Add support for the ndo_hwtstamp_get and ndo_hwtstamp_set operations in IPoIB. This allows lower devices to handle hardware timestamp configuration through the new ndos instead of the legacy ioctls. Signed-off-by: Carolina Jubran Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/1761819910-1011051-6-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski