From: Justin Tee justin.tee@broadcom.com
[ Upstream commit 2be1d4f11944cd6283cb97268b3e17c4424945ca ]
When the HBA is undergoing a reset or is handling an errata event, NULL ptr dereference crashes may occur in routines such as lpfc_sli_flush_io_rings(), lpfc_dev_loss_tmo_callbk(), or lpfc_abort_handler().
Add NULL ptr checks before dereferencing hdwq pointers that may have been freed due to operations colliding with a reset or errata event handler.
Signed-off-by: Justin Tee justin.tee@broadcom.com Link: https://lore.kernel.org/r/20240726231512.92867-4-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_hbadisc.c | 3 ++- drivers/scsi/lpfc/lpfc_scsi.c | 13 +++++++++++-- drivers/scsi/lpfc/lpfc_sli.c | 11 +++++++++++ 3 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 6943f6c6395c4..f21c5993e8d72 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -175,7 +175,8 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->nlp_state, ndlp->fc4_xpt_flags);
/* Don't schedule a worker thread event if the vport is going down. */ - if (test_bit(FC_UNLOADING, &vport->load_flag)) { + if (test_bit(FC_UNLOADING, &vport->load_flag) || + !test_bit(HBA_SETUP, &phba->hba_flag)) { spin_lock_irqsave(&ndlp->lock, iflags); ndlp->rport = NULL;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 98ce9d97a2257..60cd60ebff38e 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5555,11 +5555,20 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
iocb = &lpfc_cmd->cur_iocbq; if (phba->sli_rev == LPFC_SLI_REV4) { - pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring; - if (!pring_s4) { + /* if the io_wq & pring are gone, the port was reset. */ + if (!phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq || + !phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring) { + lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP, + "2877 SCSI Layer I/O Abort Request " + "IO CMPL Status x%x ID %d LUN %llu " + "HBA_SETUP %d\n", FAILED, + cmnd->device->id, + (u64)cmnd->device->lun, + test_bit(HBA_SETUP, &phba->hba_flag)); ret = FAILED; goto out_unlock_hba; } + pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring; spin_lock(&pring_s4->ring_lock); } /* the command is in process of being cancelled */ diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 88debef2fb6db..7dc34c71eb78c 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -4687,6 +4687,17 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) /* Look on all the FCP Rings for the iotag */ if (phba->sli_rev >= LPFC_SLI_REV4) { for (i = 0; i < phba->cfg_hdw_queue; i++) { + if (!phba->sli4_hba.hdwq || + !phba->sli4_hba.hdwq[i].io_wq) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, + "7777 hdwq's deleted %lx " + "%lx %x %x\n", + phba->pport->load_flag, + phba->hba_flag, + phba->link_state, + phba->sli.sli_flag); + return; + } pring = phba->sli4_hba.hdwq[i].io_wq->pring;
spin_lock_irq(&pring->ring_lock);