linux-dev/drivers/infiniband/sw/rxe, branch master

RDMA/rxe: Fix mr leak in RESPST_ERR_RNR

2022-10-25T05:59:29Z

rxe_recheck_mr() will increase mr's ref_cnt, so we should call rxe_put(mr) to drop mr's ref_cnt in RESPST_ERR_RNR to avoid below warning: WARNING: CPU: 0 PID: 4156 at drivers/infiniband/sw/rxe/rxe_pool.c:259 __rxe_cleanup+0x1df/0x240 [rdma_rxe] ... Call Trace: rxe_dereg_mr+0x4c/0x60 [rdma_rxe] ib_dereg_mr_user+0xa8/0x200 [ib_core] ib_mr_pool_destroy+0x77/0xb0 [ib_core] nvme_rdma_destroy_queue_ib+0x89/0x240 [nvme_rdma] nvme_rdma_free_queue+0x40/0x50 [nvme_rdma] nvme_rdma_teardown_io_queues.part.0+0xc3/0x120 [nvme_rdma] nvme_rdma_error_recovery_work+0x4d/0xf0 [nvme_rdma] process_one_work+0x582/0xa40 ? pwq_dec_nr_in_flight+0x100/0x100 ? rwlock_bug.part.0+0x60/0x60 worker_thread+0x2a9/0x700 ? process_one_work+0xa40/0xa40 kthread+0x168/0x1a0 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Link: https://lore.kernel.org/r/20221024052049.20577-1-lizhijian@fujitsu.com Fixes: 8a1a0be894da ("RDMA/rxe: Replace mr by rkey in responder resources") Signed-off-by: Li Zhijian Signed-off-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky

RDMA/rxe: Remove error/warning messages from packet receiver path

2022-09-29T09:57:56Z

Incoming packets to rxe are passed from UDP layer using an encapsulation socket. If there are any clients reachable to a node, they can invoke the encapsulation handler arbitrarily by sending malicious or irrelevant packets. This can potentially cause a message overflow and a subsequent slowdown on the node. Signed-off-by: Daisuke Matsuda Link: https://lore.kernel.org/r/20220929080023.304242-1-matsuda-daisuke@fujitsu.com Signed-off-by: Leon Romanovsky

RDMA/rxe: Remove redundant num_sge fields

2022-09-27T13:15:24Z

In include/uapi/rdma/rdma_user_rxe.h there are redundant copies of num_sge in the rxe_send_wr, rxe_recv_wqe, and rxe_dma_info. Only the ones in rxe_dma_info are actually used by the rxe kernel driver. The userspace would set these values, but the kernel never read them. This change has no affect on the current ABI and new or old versions of rdma-core operate correctly with new or old versions of the kernel rxe driver. Link: https://lore.kernel.org/r/20220913222716.18335-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe

RDMA/rxe: Fix resize_finish() in rxe_queue.c

2022-09-27T13:15:24Z

Currently in resize_finish() in rxe_queue.c there is a loop which copies the entries in the original queue into a newly allocated queue. The termination logic for this loop is incorrect. The call to queue_next_index() updates cons but has no effect on whether the queue is empty. So if the queue starts out empty nothing is copied but if it is not then the loop will run forever. This patch changes the loop to compare the value of cons to the original producer index. Fixes: ae6e843fe08d0 ("RDMA/rxe: Add memory barriers to kernel queues") Link: https://lore.kernel.org/r/20220825221446.6512-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Reviewed-by: Li Zhijian Signed-off-by: Jason Gunthorpe

RDMA/rxe: Set pd early in mr alloc routines

2022-09-27T13:15:24Z

Move setting of pd in mr objects ahead of any possible errors so that it will always be set in rxe_mr_cleanup() to avoid seg faults when rxe_put(mr_pd(mr)) is called. Fixes: cf40367961d8 ("RDMA/rxe: Move mr cleanup code to rxe_mr_cleanup()") Link: https://lore.kernel.org/r/20220805183153.32007-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Reviewed-by: Li Zhijian Signed-off-by: Jason Gunthorpe

RDMA/rxe: Add send_common_ack() helper

2022-09-26T17:14:25Z

Most code in send_ack() and send_atomic_ack() are duplicate, move them to a new helper send_common_ack(). In newer IBA spec, some opcodes require acknowledge with a zero-length read response, with this new helper, we can easily implement it later. Link: https://lore.kernel.org/r/1659335010-2-1-git-send-email-lizhijian@fujitsu.com Signed-off-by: Li Zhijian Signed-off-by: Jason Gunthorpe

RDMA/rxe: Use members of generic struct in rxe_mr

2022-09-22T09:46:39Z

rxe_mr and ib_mr have interchangeable members. Remove device specific members and use ones in the generic struct. Both 'iova' and 'length' are filled in ib_uverbs or ib_core layer after MR registration. Signed-off-by: Daisuke Matsuda Link: https://lore.kernel.org/r/20220921080844.1616883-2-matsuda-daisuke@fujitsu.com Signed-off-by: Leon Romanovsky

RDMA/rxe: convert pr_warn to pr_debug

2022-09-08T08:03:15Z

They could be triggered by user APIs with invalid parameters. Signed-off-by: Li Zhijian Link: https://lore.kernel.org/r/1662518901-2-2-git-send-email-lizhijian@fujitsu.com Signed-off-by: Leon Romanovsky

RDMA/rxe: use %u to print u32 variables

2022-09-08T08:03:15Z

struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; ... To avoid getting a negative value from dmesg: [410580.579965] rdma_rxe: invalid send sge = 65535 > 32 [410580.583818] rdma_rxe: invalid send wr = -1 > 1048576 [410582.771323] rdma_rxe: invalid recv sge = 65535 > 32 [410582.775310] rdma_rxe: invalid recv wr = -1 > 1048576 Signed-off-by: Li Zhijian Link: https://lore.kernel.org/r/1662518901-2-1-git-send-email-lizhijian@fujitsu.com Signed-off-by: Leon Romanovsky

RDMA/rxe: Delete error messages triggered by incoming Read requests

2022-08-31T06:57:09Z

An incoming Read request causes multiple Read responses. If a user MR to copy data from is unavailable or responder cannot send a reply, then the error messages can be printed for each response attempt, resulting in message overflow. Link: https://lore.kernel.org/r/20220829071218.1639065-1-matsuda-daisuke@fujitsu.com Signed-off-by: Daisuke Matsuda Signed-off-by: Leon Romanovsky