6.17-stable review patch. If anyone has any objections, please let me know.
------------------
From: Justin Tee justin.tee@broadcom.com
[ Upstream commit 2bf81856a403c92a4ce375288f33fba82ca2ccc6 ]
There is a timing race condition when a PRLI may be sent on the wire before PLOGI_ACC in Point to Point topology. Fix by deferring REG_RPI mbox completion handling to after PLOGI_ACC's CQE completion. Because the discovery state machine only sends PRLI after REG_RPI mbox completion, PRLI is now guaranteed to be sent after PLOGI_ACC.
Signed-off-by: Justin Tee justin.tee@broadcom.com Message-ID: 20250915180811.137530-8-justintee8345@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/lpfc/lpfc_els.c | 10 +++++++--- drivers/scsi/lpfc/lpfc_nportdisc.c | 23 ++++++++++++++++++----- 2 files changed, 25 insertions(+), 8 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 3f703932b2f07..8762fb84f14f1 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -5339,12 +5339,12 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, ulp_status, ulp_word4, did); /* ELS response tag <ulpIoTag> completes */ lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, - "0110 ELS response tag x%x completes " + "0110 ELS response tag x%x completes fc_flag x%lx" "Data: x%x x%x x%x x%x x%lx x%x x%x x%x %p %p\n", - iotag, ulp_status, ulp_word4, tmo, + iotag, vport->fc_flag, ulp_status, ulp_word4, tmo, ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state, ndlp->nlp_rpi, kref_read(&ndlp->kref), mbox, ndlp); - if (mbox) { + if (mbox && !test_bit(FC_PT2PT, &vport->fc_flag)) { if (ulp_status == 0 && test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) { if (!lpfc_unreg_rpi(vport, ndlp) && @@ -5403,6 +5403,10 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } out_free_mbox: lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED); + } else if (mbox && test_bit(FC_PT2PT, &vport->fc_flag) && + test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) { + lpfc_mbx_cmpl_reg_login(phba, mbox); + clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag); } out: if (ndlp && shost) { diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index a596b80d03d4d..3799bdf2f1b88 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -326,8 +326,14 @@ lpfc_defer_plogi_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *login_mbox) /* Now that REG_RPI completed successfully, * we can now proceed with sending the PLOGI ACC. */ - rc = lpfc_els_rsp_acc(login_mbox->vport, ELS_CMD_PLOGI, - save_iocb, ndlp, NULL); + if (test_bit(FC_PT2PT, &ndlp->vport->fc_flag)) { + rc = lpfc_els_rsp_acc(login_mbox->vport, ELS_CMD_PLOGI, + save_iocb, ndlp, login_mbox); + } else { + rc = lpfc_els_rsp_acc(login_mbox->vport, ELS_CMD_PLOGI, + save_iocb, ndlp, NULL); + } + if (rc) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "4576 PLOGI ACC fails pt2pt discovery: " @@ -335,9 +341,16 @@ lpfc_defer_plogi_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *login_mbox) } }
- /* Now process the REG_RPI cmpl */ - lpfc_mbx_cmpl_reg_login(phba, login_mbox); - clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag); + /* If this is a fabric topology, complete the reg_rpi and prli now. + * For Pt2Pt, the reg_rpi and PRLI are deferred until after the LS_ACC + * completes. This ensures, in Pt2Pt, that the PLOGI LS_ACC is sent + * before the PRLI. + */ + if (!test_bit(FC_PT2PT, &ndlp->vport->fc_flag)) { + /* Now process the REG_RPI cmpl */ + lpfc_mbx_cmpl_reg_login(phba, login_mbox); + clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag); + } kfree(save_iocb); }