Hi Linus, This seems unusually big for the second pull request from RDMA. irdma is the usual new driver fixes, but the rest seems to just be people testing into obscure corners. The out-of-subsystem change to fork.c is to export mmput_async() as we can't do the synchronous put due to held locks and interaction with mmu notifiers. Thanks, Jason The following changes since commit b16de8b9e7d1aae169d059c3a0dd9a881a3c0d1d: RDMA: Handle the return code from dma_resv_wait_timeout() properly (2022-08-16 17:13:23 +0300) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus for you to fetch changes up to a261786fdc0a5bed2e5f994dcc0ffeeeb0d662c7: RDMA/irdma: Report RNR NAK generation in device caps (2022-09-07 11:22:18 +0300) ---------------------------------------------------------------- v6.0 second rc pull request Many bug fixes in several drivers: - Fix misuse of the DMA API in rtrs - Several irdma issues: hung task due to SQ flushing, incorrect capability reporting to userspace, improper error handling for MW corners, touching an uninitialized SGL for during invalidation. - hns was using the wrong page size limits for the HW, an incorrect calculation of wqe_shift causing WQE corruption, and mis computed a timer id. - Fix a crash in SRP triggered by blktests - Fix compiler errors by calling virt_to_page() with the proper type in siw - Userspace triggerable deadlock in ODP - mlx5 could use the wrong profile due to some driver loading races, counters were not working in some device configurations, and a crash on error unwind. ---------------------------------------------------------------- Chengchang Tang (1): RDMA/hns: Fix supported page size Chris Mi (1): RDMA/mlx5: Set local port to one when accessing counters Jack Wang (2): RDMA/rtrs-clt: Use the right sg_cnt after ib_dma_map_sg RDMA/rtrs-srv: Pass the correct number of entries for dma mapped SGL Linus Walleij (1): RDMA/siw: Pass a pointer to virt_to_page() Maher Sanalla (1): RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting profile Maor Gottlieb (1): RDMA/mlx5: Fix UMR cleanup on error flow of driver init Michael Guralnik (1): RDMA/cma: Fix arguments order in net device validation Shiraz Saleem (1): RDMA/irdma: Fix drain SQ hang with no completion Sindhu-Devale (5): RDMA/irdma: Report the correct max cqes from query device RDMA/irdma: Return error on MR deregister CQP failure RDMA/irdma: Return correct WC error for bind operation failure RDMA/irdma: Use s/g array in post send only when its valid RDMA/irdma: Report RNR NAK generation in device caps Wenpeng Liang (2): RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shift MAINTAINERS: Update maintainers of HiSilicon RoCE Yishai Hadas (1): IB/core: Fix a nested dead lock as part of ODP flow Yixing Liu (1): RDMA/hns: Remove the num_qpc_timer variable yangx.jy@fujitsu.com (1): RDMA/srp: Set scmnd->result only when scmnd is not NULL MAINTAINERS | 2 +- drivers/infiniband/core/cma.c | 4 ++-- drivers/infiniband/core/umem_odp.c | 2 +- drivers/infiniband/hw/hns/hns_roce_device.h | 1 - drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +-- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 4 ++-- drivers/infiniband/hw/hns/hns_roce_main.c | 2 +- drivers/infiniband/hw/hns/hns_roce_qp.c | 7 ++----- drivers/infiniband/hw/irdma/uk.c | 7 +++++-- drivers/infiniband/hw/irdma/utils.c | 15 +++++++++------ drivers/infiniband/hw/irdma/verbs.c | 13 ++++++++++--- drivers/infiniband/hw/mlx5/mad.c | 6 ++++++ drivers/infiniband/hw/mlx5/main.c | 2 +- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + drivers/infiniband/hw/mlx5/umr.c | 3 +++ drivers/infiniband/sw/siw/siw_qp_tx.c | 18 ++++++++++++++---- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 9 +++++---- drivers/infiniband/ulp/rtrs/rtrs-srv.c | 14 +++++++------- drivers/infiniband/ulp/srp/ib_srp.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 23 +++++++++++++++++++++-- include/linux/mlx5/driver.h | 19 ++++++++++--------- kernel/fork.c | 1 + 22 files changed, 105 insertions(+), 54 deletions(-)