kernel.git/drivers/infiniband/core/cm.c, branch linux-6.8.y

RDMA/cm: Print the old state when cm_destroy_id gets timeout

2024-04-27T15:12:53Z

[ Upstream commit b68e1acb5834ed1a2ad42d9d002815a8bae7c0b6 ] The old state is helpful for debugging, as the current state is always IB_CM_IDLE when timeout happens. Fixes: 96d9cbe2f2ff ("RDMA/cm: add timeout to cm_destroy_id wait") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/20240322112049.2022994-1-markzhang@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin

RDMA/cm: add timeout to cm_destroy_id wait

2024-04-13T11:10:07Z

[ Upstream commit 96d9cbe2f2ff7abde021bac75eafaceabe9a51fa ] Add timeout to cm_destroy_id, so that userspace can trigger any data collection that would help in analyzing the cause of delay in destroying the cm_id. New noinline function helps dtrace/ebpf programs to hook on to it. Existing functionality isn't changed except triggering a probe-able new function at every timeout interval. We have seen cases where CM messages stuck with MAD layer (either due to software bug or faulty HCA), leading to cm_id getting stuck in the following call stack. This patch helps in resolving such issues faster. kernel: ... INFO: task XXXX:56778 blocked for more than 120 seconds. ... Call Trace: __schedule+0x2bc/0x895 schedule+0x36/0x7c schedule_timeout+0x1f6/0x31f ? __slab_free+0x19c/0x2ba wait_for_completion+0x12b/0x18a ? wake_up_q+0x80/0x73 cm_destroy_id+0x345/0x610 [ib_cm] ib_destroy_cm_id+0x10/0x20 [ib_cm] rdma_destroy_id+0xa8/0x300 [rdma_cm] ucma_destroy_id+0x13e/0x190 [rdma_ucm] ucma_write+0xe0/0x160 [rdma_ucm] __vfs_write+0x3a/0x16d vfs_write+0xb2/0x1a1 ? syscall_trace_enter+0x1ce/0x2b8 SyS_write+0x5c/0xd3 do_syscall_64+0x79/0x1b9 entry_SYSCALL_64_after_hwframe+0x16d/0x0 Signed-off-by: Manjunath Patil Link: https://lore.kernel.org/r/20240309063323.458102-1-manjunath.b.patil@oracle.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin

RDMA/cm: Trace icm_send_rej event before the cm state is reset

2023-04-09T09:52:57Z

Trace icm_send_rej event before the cm state is reset to idle, so that correct cm state will be logged. For example when an incoming request is rejected, the old trace log was: icm_send_rej: local_id=961102742 remote_id=3829151631 state=IDLE reason=REJ_CONSUMER_DEFINED With this patch: icm_send_rej: local_id=312971016 remote_id=3778819983 state=MRA_REQ_SENT reason=REJ_CONSUMER_DEFINED Fixes: 8dc105befe16 ("RDMA/cm: Add tracepoints to track MAD send operations") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/20230330072351.481200-1-markzhang@nvidia.com Signed-off-by: Leon Romanovsky

RDMA/cm: Make QP FLUSHABLE for supported device

2022-12-09T23:36:02Z

Similar to RDMA and Atomic qp attributes enabled by default in CM, enable FLUSH attribute for supported device. That makes applications that are built with rdma_create_ep, rdma_accept APIs have FLUSH qp attribute natively so that user is able to request FLUSH operation simpler. Note that, a FLUSH operation requires FLUSH are supported by both device(HCA) and memory region(MR) and QP at the same time, so it's safe to enable FLUSH qp attribute by default here. FLUSH attribute can be disable by modify_qp() interface. Link: https://lore.kernel.org/r/20221206130201.30986-10-lizhijian@fujitsu.com Signed-off-by: Li Zhijian Signed-off-by: Jason Gunthorpe

RDMA/cm: Use DLID from inbound/outbound PathRecords as the datapath DLID

2022-09-22T09:35:31Z

In inter-subnet cases, when inbound/outbound PRs are available, outbound_PR.dlid is used as the requestor's datapath DLID and inbound_PR.dlid is used as the responder's DLID. The inbound_PR.dlid is passed to responder side with the "ConnectReq.Primary_Local_Port_LID" field. With this solution the PERMISSIVE_LID is no longer used in Primary Local LID field. Signed-off-by: Mark Zhang Reviewed-by: Mark Bloch Link: https://lore.kernel.org/r/b3f6cac685bce9dde37c610be82e2c19d9e51d9e.1662631201.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky

RDMA/cm: Use SLID in the work completion as the DLID in responder side

2022-09-22T09:35:25Z

The responder should always use WC's SLID as the dlid, to follow the IB SPEC section "13.5.4.2 COMMON RESPONSE ACTIONS": A responder always takes the following actions in constructing a response packet: - The SLID of the received packet is used as the DLID in the response packet. Fixes: ac3a949fb2ff ("IB/CM: Set appropriate slid and dlid when handling CM request") Signed-off-by: Mark Zhang Reviewed-by: Mark Bloch Link: https://lore.kernel.org/r/cd17c240231e059d2fc07c17dfe555d548b917eb.1662631201.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky

IB/cm: Refactor cm_insert_listen() and cm_find_listen()

2022-08-30T09:14:23Z

Move the device and service_id match code at the top of cm_insert_listen() and cm_find_listen() into the final else branch. Link: https://lore.kernel.org/r/20220819090859.957943-4-markzhang@nvidia.com Signed-off-by: Mark Zhang Signed-off-by: Leon Romanovsky

IB/cm: remove cm_id_priv->id.service_mask and service_mask parameter of cm_init_listen()

2022-08-30T09:14:23Z

The service_mask is always ~cpu_to_be64(0), so the result is always a NOP when it is &'d with a service_id. Remove it for simplicity. Link: https://lore.kernel.org/r/20220819090859.957943-3-markzhang@nvidia.com Signed-off-by: Mark Zhang Signed-off-by: Leon Romanovsky

IB/cm: Remove the service_mask parameter from ib_cm_listen()

2022-08-30T09:14:23Z

Remove the service_mask parameter of ib_cm_listen(), as all callers use 0. Link: https://lore.kernel.org/r/20220819090859.957943-2-markzhang@nvidia.com Signed-off-by: Mark Zhang Signed-off-by: Leon Romanovsky

RDMA/cm: Fix memory leak in ib_cm_insert_listen

2022-06-24T19:41:03Z

cm_alloc_id_priv() allocates resource for the cm_id_priv. When cm_init_listen() fails it doesn't free it, leading to memory leak. Add the missing error unwind. Fixes: 98f67156a80f ("RDMA/cm: Simplify establishing a listen cm_id") Link: https://lore.kernel.org/r/20220621052546.4821-1-linmq006@gmail.com Signed-off-by: Miaoqian Lin Signed-off-by: Jason Gunthorpe