scsi: lpfc: Fix NPIV port deletion crash

The driver is calling schedule_timeout after the DA_ID nameserver request
and LOGO commands are issued to the fabric by the initiator virtual
endport.  These fixed delay functions are causing long delays in the
driver's worker thread when processing discovery I/Os in a serialized
fashion, which is then triggering mailbox timeout errors artificially.

To fix this, don't wait on the DA_ID request to complete and call
wait_event_timeout to allow the vport delete thread to make progress on an
event driven basis rather than fixing the wait time.

Link: https://lore.kernel.org/r/20211204002644.116455-5-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This commit is contained in:
James Smart 2021-12-03 16:26:39 -08:00 committed by Martin K. Petersen
parent 7576d48c64
commit 8ed190a919
4 changed files with 73 additions and 25 deletions

View file

@ -669,8 +669,6 @@ struct lpfc_vport {
struct timer_list els_tmofunc;
struct timer_list delayed_disc_tmo;
int unreg_vpi_cmpl;
uint8_t load_flag;
#define FC_LOADING 0x1 /* HBA in process of loading drvr */
#define FC_UNLOADING 0x2 /* HBA in process of unloading drvr */

View file

@ -10978,10 +10978,19 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
lpfc_can_disctmo(vport);
}
if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) {
/* Wake up lpfc_vport_delete if waiting...*/
if (ndlp->logo_waitq)
wake_up(ndlp->logo_waitq);
spin_lock_irq(&ndlp->lock);
ndlp->nlp_flag &= ~(NLP_ISSUE_LOGO | NLP_LOGO_SND);
ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
spin_unlock_irq(&ndlp->lock);
}
/* Safe to release resources now. */
lpfc_els_free_iocb(phba, cmdiocb);
lpfc_nlp_put(ndlp);
vport->unreg_vpi_cmpl = VPORT_ERROR;
}
/**

View file

@ -3928,7 +3928,6 @@ lpfc_mbx_cmpl_unreg_vpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
vport->vpi_state &= ~LPFC_VPI_REGISTERED;
vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
spin_unlock_irq(shost->host_lock);
vport->unreg_vpi_cmpl = VPORT_OK;
mempool_free(pmb, phba->mbox_mem_pool);
lpfc_cleanup_vports_rrqs(vport, NULL);
/*
@ -3958,7 +3957,6 @@ lpfc_mbx_unreg_vpi(struct lpfc_vport *vport)
lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
"1800 Could not issue unreg_vpi\n");
mempool_free(mbox, phba->mbox_mem_pool);
vport->unreg_vpi_cmpl = VPORT_ERROR;
return rc;
}
return 0;

View file

@ -485,23 +485,68 @@ lpfc_vport_create(struct fc_vport *fc_vport, bool disable)
return rc;
}
static int
lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
{
int rc;
struct lpfc_hba *phba = vport->phba;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
spin_lock_irq(&ndlp->lock);
if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO) &&
!ndlp->logo_waitq) {
ndlp->logo_waitq = &waitq;
ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
ndlp->nlp_flag |= NLP_ISSUE_LOGO;
ndlp->save_flags |= NLP_WAIT_FOR_LOGO;
}
spin_unlock_irq(&ndlp->lock);
rc = lpfc_issue_els_npiv_logo(vport, ndlp);
if (!rc) {
wait_event_timeout(waitq,
(!(ndlp->save_flags & NLP_WAIT_FOR_LOGO)),
msecs_to_jiffies(phba->fc_ratov * 2000));
if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO))
goto logo_cmpl;
/* LOGO wait failed. Correct status. */
rc = -EINTR;
} else {
rc = -EIO;
}
/* Error - clean up node flags. */
spin_lock_irq(&ndlp->lock);
ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
spin_unlock_irq(&ndlp->lock);
logo_cmpl:
lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT,
"1824 Issue LOGO completes with status %d\n",
rc);
spin_lock_irq(&ndlp->lock);
ndlp->logo_waitq = NULL;
spin_unlock_irq(&ndlp->lock);
return rc;
}
static int
disable_vport(struct fc_vport *fc_vport)
{
struct lpfc_vport *vport = *(struct lpfc_vport **)fc_vport->dd_data;
struct lpfc_hba *phba = vport->phba;
struct lpfc_nodelist *ndlp = NULL, *next_ndlp = NULL;
long timeout;
struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
/* Can't disable during an outstanding delete. */
if (vport->load_flag & FC_UNLOADING)
return 0;
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (ndlp && phba->link_state >= LPFC_LINK_UP) {
vport->unreg_vpi_cmpl = VPORT_INVAL;
timeout = msecs_to_jiffies(phba->fc_ratov * 2000);
if (!lpfc_issue_els_npiv_logo(vport, ndlp))
while (vport->unreg_vpi_cmpl == VPORT_INVAL && timeout)
timeout = schedule_timeout(timeout);
}
if (ndlp && phba->link_state >= LPFC_LINK_UP)
(void)lpfc_send_npiv_logo(vport, ndlp);
lpfc_sli_host_down(vport);
@ -600,7 +645,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
struct lpfc_vport *vport = *(struct lpfc_vport **)fc_vport->dd_data;
struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
struct lpfc_hba *phba = vport->phba;
long timeout;
int rc;
if (vport->port_type == LPFC_PHYSICAL_PORT) {
lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
@ -665,15 +710,14 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
phba->fc_topology != LPFC_TOPOLOGY_LOOP) {
if (vport->cfg_enable_da_id) {
/* Send DA_ID and wait for a completion. */
timeout = msecs_to_jiffies(phba->fc_ratov * 2000);
if (!lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0))
while (vport->ct_flags && timeout)
timeout = schedule_timeout(timeout);
else
rc = lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0);
if (rc) {
lpfc_printf_log(vport->phba, KERN_WARNING,
LOG_VPORT,
"1829 CT command failed to "
"delete objects on fabric\n");
"delete objects on fabric, "
"rc %d\n", rc);
}
}
/*
@ -688,11 +732,10 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp)
goto skip_logo;
vport->unreg_vpi_cmpl = VPORT_INVAL;
timeout = msecs_to_jiffies(phba->fc_ratov * 2000);
if (!lpfc_issue_els_npiv_logo(vport, ndlp))
while (vport->unreg_vpi_cmpl == VPORT_INVAL && timeout)
timeout = schedule_timeout(timeout);
rc = lpfc_send_npiv_logo(vport, ndlp);
if (rc)
goto skip_logo;
}
if (!(phba->pport->load_flag & FC_UNLOADING))