From 10a214dc996236e6547b84fb5ca007316b30c2e6 Mon Sep 17 00:00:00 2001 From: Devesh Sharma Date: Thu, 24 Dec 2015 13:14:07 -0500 Subject: RDMA/ocrdma: Depend on async link events from CNA Recently Dough Ledford reported a deadlock happening between ocrdma-load sequence and NetworkManager service issuing "open" on be2net interface. The deadlock happens when any be2net hook (e.g. open/close) is called in parallel to insmod ocrdma.ko. A. be2net is sending administrative open/close event to ocrdma holding device_list_mutex. It does this from ndo_open/ndo_stop hooks of be2net. So sequence of locks is rtnl_lock---> device_list lock B. When new ocrdma roce device gets registered, infiniband stack now takes rtnl_lock in ib_register_device() in GID initialization routines. So sequence of locks in this path is device_list lock ---> rtnl_lock. This improper locking sequence causes deadlock. With this patch we stop using administrative open and close events injected by be2net driver. These events were used to dispatch PORT_ACTIVE and PORT_ERROR events to the IB-stack. This patch implements a logic to receive async-link-events generated from CNA whenever link-state-change is detected. Now on, these async-events will be used to dispatch PORT_ACTIVE and PORT_ERROR events to IB-stack. Depending on async-events from CNA removes the need to hold device-list-mutex and thus breaks the busy-wait scenario. Reported-by: Doug Ledford CC: Sathya Perla Signed-off-by: Padmanabh Ratnakar Signed-off-by: Selvin Xavier Signed-off-by: Devesh Sharma Signed-off-by: Doug Ledford --- drivers/infiniband/hw/ocrdma/ocrdma_sli.h | 49 ++++++++++++++++++++++++++++--- 1 file changed, 45 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband/hw/ocrdma/ocrdma_sli.h') diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 6a38268bbe9f..99dd6fdf06d7 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -465,8 +465,11 @@ struct ocrdma_ae_qp_mcqe { u32 valid_ae_event; }; -#define OCRDMA_ASYNC_RDMA_EVE_CODE 0x14 -#define OCRDMA_ASYNC_GRP5_EVE_CODE 0x5 +enum ocrdma_async_event_code { + OCRDMA_ASYNC_LINK_EVE_CODE = 0x01, + OCRDMA_ASYNC_GRP5_EVE_CODE = 0x05, + OCRDMA_ASYNC_RDMA_EVE_CODE = 0x14 +}; enum ocrdma_async_grp5_events { OCRDMA_ASYNC_EVENT_QOS_VALUE = 0x01, @@ -489,6 +492,44 @@ enum OCRDMA_ASYNC_EVENT_TYPE { OCRDMA_MAX_ASYNC_ERRORS }; +struct ocrdma_ae_lnkst_mcqe { + u32 speed_state_ptn; + u32 qos_reason_falut; + u32 evt_tag; + u32 valid_ae_event; +}; + +enum { + OCRDMA_AE_LSC_PORT_NUM_MASK = 0x3F, + OCRDMA_AE_LSC_PT_SHIFT = 0x06, + OCRDMA_AE_LSC_PT_MASK = (0x03 << + OCRDMA_AE_LSC_PT_SHIFT), + OCRDMA_AE_LSC_LS_SHIFT = 0x08, + OCRDMA_AE_LSC_LS_MASK = (0xFF << + OCRDMA_AE_LSC_LS_SHIFT), + OCRDMA_AE_LSC_LD_SHIFT = 0x10, + OCRDMA_AE_LSC_LD_MASK = (0xFF << + OCRDMA_AE_LSC_LD_SHIFT), + OCRDMA_AE_LSC_PPS_SHIFT = 0x18, + OCRDMA_AE_LSC_PPS_MASK = (0xFF << + OCRDMA_AE_LSC_PPS_SHIFT), + OCRDMA_AE_LSC_PPF_MASK = 0xFF, + OCRDMA_AE_LSC_ER_SHIFT = 0x08, + OCRDMA_AE_LSC_ER_MASK = (0xFF << + OCRDMA_AE_LSC_ER_SHIFT), + OCRDMA_AE_LSC_QOS_SHIFT = 0x10, + OCRDMA_AE_LSC_QOS_MASK = (0xFFFF << + OCRDMA_AE_LSC_QOS_SHIFT) +}; + +enum { + OCRDMA_AE_LSC_PLINK_DOWN = 0x00, + OCRDMA_AE_LSC_PLINK_UP = 0x01, + OCRDMA_AE_LSC_LLINK_DOWN = 0x02, + OCRDMA_AE_LSC_LLINK_MASK = 0x02, + OCRDMA_AE_LSC_LLINK_UP = 0x03 +}; + /* mailbox command request and responses */ enum { OCRDMA_MBX_QUERY_CFG_CQ_OVERFLOW_SHIFT = 2, @@ -676,7 +717,7 @@ enum { OCRDMA_PHY_PFLT_SHIFT = 0x18, OCRDMA_QOS_LNKSP_MASK = 0xFFFF0000, OCRDMA_QOS_LNKSP_SHIFT = 0x10, - OCRDMA_LLST_MASK = 0xFF, + OCRDMA_LINK_ST_MASK = 0x01, OCRDMA_PLFC_MASK = 0x00000400, OCRDMA_PLFC_SHIFT = 0x8, OCRDMA_PLRFC_MASK = 0x00000200, @@ -691,7 +732,7 @@ struct ocrdma_get_link_speed_rsp { u32 pflt_pps_ld_pnum; u32 qos_lsp; - u32 res_lls; + u32 res_lnk_st; }; enum { -- cgit v1.2.3