From: James Smart <jsmart2021@gmail.com>
To: linux-scsi@vger.kernel.org
Cc: James Smart <jsmart2021@gmail.com>,
Dick Kennedy <dick.kennedy@broadcom.com>
Subject: [PATCH 22/42] lpfc: Fix deadlock on host_lock during cable pulls
Date: Wed, 14 Aug 2019 16:56:52 -0700 [thread overview]
Message-ID: <20190814235712.4487-23-jsmart2021@gmail.com> (raw)
In-Reply-To: <20190814235712.4487-1-jsmart2021@gmail.com>
During cable pull testing a deadlock was seen between
lpfc_nlp_counters() vs lpfc_mbox_process_link_up() vs
lpfc_work_list_done(). They are all waiting on the
shost->host_lock.
Issue is all of these cases raise irq when taking out
the lock but use spin_unlock_irq() when unlocking. The
unlock path is will unconditionally re-enable interrupts
in cases where irq state should be preserved. The re-enablement
allowed the other paths to execute which then causes the
deadlock.
Fix by converting the lock/unlock to irqsave/irqrestore.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
---
drivers/scsi/lpfc/lpfc_hbadisc.c | 47 ++++++++++++++++++++++------------------
1 file changed, 26 insertions(+), 21 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index a47db99784ab..44e779e4c885 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -118,6 +118,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
struct lpfc_work_evt *evtp;
int put_node;
int put_rport;
+ unsigned long iflags;
rdata = rport->dd_data;
ndlp = rdata->pnode;
@@ -170,22 +171,22 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
}
shost = lpfc_shost_from_vport(vport);
- spin_lock_irq(shost->host_lock);
+ spin_lock_irqsave(shost->host_lock, iflags);
ndlp->nlp_flag |= NLP_IN_DEV_LOSS;
- spin_unlock_irq(shost->host_lock);
+ spin_unlock_irqrestore(shost->host_lock, iflags);
/* We need to hold the node by incrementing the reference
* count until this queued work is done
*/
evtp->evt_arg1 = lpfc_nlp_get(ndlp);
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irqsave(&phba->hbalock, iflags);
if (evtp->evt_arg1) {
evtp->evt = LPFC_EVT_DEV_LOSS;
list_add_tail(&evtp->evt_listp, &phba->work_list);
lpfc_worker_wake_up(phba);
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
return;
}
@@ -212,14 +213,15 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
int put_node;
int warn_on = 0;
int fcf_inuse = 0;
+ unsigned long iflags;
rport = ndlp->rport;
vport = ndlp->vport;
shost = lpfc_shost_from_vport(vport);
- spin_lock_irq(shost->host_lock);
+ spin_lock_irqsave(shost->host_lock, iflags);
ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
- spin_unlock_irq(shost->host_lock);
+ spin_unlock_irqrestore(shost->host_lock, iflags);
if (!rport)
return fcf_inuse;
@@ -3115,8 +3117,9 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
int rc;
struct fcf_record *fcf_record;
uint32_t fc_flags = 0;
+ unsigned long iflags;
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irqsave(&phba->hbalock, iflags);
phba->fc_linkspeed = bf_get(lpfc_mbx_read_top_link_spd, la);
if (!(phba->hba_flag & HBA_FCOE_MODE)) {
@@ -3213,12 +3216,12 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
vport->fc_myDID = phba->fc_pref_DID;
fc_flags |= FC_LBIT;
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
if (fc_flags) {
- spin_lock_irq(shost->host_lock);
+ spin_lock_irqsave(shost->host_lock, iflags);
vport->fc_flag |= fc_flags;
- spin_unlock_irq(shost->host_lock);
+ spin_unlock_irqrestore(shost->host_lock, iflags);
}
lpfc_linkup(phba);
@@ -3292,22 +3295,22 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
* The driver is expected to do FIP/FCF. Call the port
* and get the FCF Table.
*/
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irqsave(&phba->hbalock, iflags);
if (phba->hba_flag & FCF_TS_INPROG) {
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
return;
}
/* This is the initial FCF discovery scan */
phba->fcf.fcf_flag |= FCF_INIT_DISC;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
lpfc_printf_log(phba, KERN_INFO, LOG_FIP | LOG_DISCOVERY,
"2778 Start FCF table scan at linkup\n");
rc = lpfc_sli4_fcf_scan_read_fcf_rec(phba,
LPFC_FCOE_FCF_GET_FIRST);
if (rc) {
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irqsave(&phba->hbalock, iflags);
phba->fcf.fcf_flag &= ~FCF_INIT_DISC;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
goto out;
}
/* Reset FCF roundrobin bmask for new discovery */
@@ -3366,6 +3369,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
MAILBOX_t *mb = &pmb->u.mb;
struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)(pmb->ctx_buf);
uint8_t attn_type;
+ unsigned long iflags;
/* Unblock ELS traffic */
pring = lpfc_phba_elsring(phba);
@@ -3387,12 +3391,12 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
memcpy(&phba->alpa_map[0], mp->virt, 128);
- spin_lock_irq(shost->host_lock);
+ spin_lock_irqsave(shost->host_lock, iflags);
if (bf_get(lpfc_mbx_read_top_pb, la))
vport->fc_flag |= FC_BYPASSED_MODE;
else
vport->fc_flag &= ~FC_BYPASSED_MODE;
- spin_unlock_irq(shost->host_lock);
+ spin_unlock_irqrestore(shost->host_lock, iflags);
if (phba->fc_eventTag <= la->eventTag) {
phba->fc_stat.LinkMultiEvent++;
@@ -3403,12 +3407,12 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
phba->fc_eventTag = la->eventTag;
if (phba->sli_rev < LPFC_SLI_REV4) {
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irqsave(&phba->hbalock, iflags);
if (bf_get(lpfc_mbx_read_top_mm, la))
phba->sli.sli_flag |= LPFC_MENLO_MAINT;
else
phba->sli.sli_flag &= ~LPFC_MENLO_MAINT;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
}
phba->link_events++;
@@ -4196,8 +4200,9 @@ static void
lpfc_nlp_counters(struct lpfc_vport *vport, int state, int count)
{
struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+ unsigned long iflags;
- spin_lock_irq(shost->host_lock);
+ spin_lock_irqsave(shost->host_lock, iflags);
switch (state) {
case NLP_STE_UNUSED_NODE:
vport->fc_unused_cnt += count;
@@ -4227,7 +4232,7 @@ lpfc_nlp_counters(struct lpfc_vport *vport, int state, int count)
vport->fc_npr_cnt += count;
break;
}
- spin_unlock_irq(shost->host_lock);
+ spin_unlock_irqrestore(shost->host_lock, iflags);
}
static void
--
2.13.7
next prev parent reply other threads:[~2019-08-14 23:57 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-14 23:56 [PATCH 00/42] lpfc: Update lpfc to revision 12.4.0.0 James Smart
2019-08-14 23:56 ` [PATCH 01/42] lpfc: Limit xri count for kdump environment James Smart
2019-08-14 23:56 ` [PATCH 02/42] lpfc: Fix PLOGI failure with high remoteport count James Smart
2019-08-14 23:56 ` [PATCH 03/42] lpfc: Fix ELS field alignments James Smart
2019-08-14 23:56 ` [PATCH 04/42] lpfc: Fix crash on driver unload in wq free James Smart
2019-08-14 23:56 ` [PATCH 05/42] lpfc: Fix failure to clear non-zero eq_delay after io rate reduction James Smart
2019-08-14 23:56 ` [PATCH 06/42] lpfc: Fix leak of ELS completions on adapter reset James Smart
2019-08-14 23:56 ` [PATCH 07/42] lpfc: Fix port relogin failure due to GID_FT interaction James Smart
2019-08-14 23:56 ` [PATCH 08/42] lpfc: Fix discovery when target has no GID_FT information James Smart
2019-08-14 23:56 ` [PATCH 09/42] lpfc: Fix ADISC reception terminating login state if a NVME target James Smart
2019-08-14 23:56 ` [PATCH 10/42] lpfc: Fix issuing init_vpi mbox on SLI-3 card James Smart
2019-08-14 23:56 ` [PATCH 11/42] lpfc: Fix Oops in nvme_register with target logout/login James Smart
2019-08-14 23:56 ` [PATCH 12/42] lpfc: Fix irq raising in lpfc_sli_hba_down James Smart
2019-08-14 23:56 ` [PATCH 13/42] lpfc: Fix oops when fewer hdwqs than cpus James Smart
2019-08-14 23:56 ` [PATCH 14/42] lpfc: Fix FLOGI handling across multiple link up/down conditions James Smart
2019-08-14 23:56 ` [PATCH 15/42] lpfc: Fix null ptr oops updating lpfc_devloss_tmo via sysfs attribute James Smart
2019-08-14 23:56 ` [PATCH 16/42] lpfc: Fix devices that don't return after devloss followed by rediscovery James Smart
2019-08-14 23:56 ` [PATCH 17/42] lpfc: Fix loss of remote port after devloss due to lack of RPIs James Smart
2019-08-14 23:56 ` [PATCH 18/42] lpfc: Fix propagation of devloss_tmo setting to nvme transport James Smart
2019-08-14 23:56 ` [PATCH 19/42] lpfc: Fix sg_seg_cnt for HBAs that don't support NVME James Smart
2019-08-14 23:56 ` [PATCH 20/42] lpfc: Fix driver nvme rescan logging James Smart
2019-08-14 23:56 ` [PATCH 21/42] lpfc: Fix error in remote port address change James Smart
2019-08-14 23:56 ` James Smart [this message]
2019-08-14 23:56 ` [PATCH 23/42] lpfc: Fix crash due to port reset racing vs adapter error handling James Smart
2019-08-14 23:56 ` [PATCH 24/42] lpfc: Fix too many sg segments spamming in kernel log James Smart
2019-08-14 23:56 ` [PATCH 25/42] lpfc: Fix hang when downloading fw on port enabled for nvme James Smart
2019-08-14 23:56 ` [PATCH 26/42] lpfc: Fix nvme target mode ABTSing a received ABTS James Smart
2019-08-14 23:56 ` [PATCH 27/42] lpfc: Fix nvme sg_seg_cnt display if HBA does not support NVME James Smart
2019-08-14 23:56 ` [PATCH 28/42] lpfc: Fix sli4 adapter initialization with MSI James Smart
2019-08-14 23:56 ` [PATCH 29/42] lpfc: Fix upcall to bsg done in non-success cases James Smart
2019-08-14 23:57 ` [PATCH 30/42] lpfc: Fix Max Frame Size value shown in fdmishow output James Smart
2019-08-14 23:57 ` [PATCH 31/42] lpfc: Fix reported physical link speed on a disabled trunked link James Smart
2019-08-14 23:57 ` [PATCH 32/42] lpfc: Fix BlockGuard enablement on FCoE adapters James Smart
2019-08-14 23:57 ` [PATCH 33/42] lpfc: Fix nvme first burst module parameter description James Smart
2019-08-14 23:57 ` [PATCH 34/42] lpfc: Fix coverity warnings James Smart
2019-08-14 23:57 ` [PATCH 35/42] lpfc: Add simple unlikely optimizations to reduce NVME latency James Smart
2019-08-14 23:57 ` [PATCH 36/42] lpfc: Migrate to %px and %pf in kernel print calls James Smart
2019-08-14 23:57 ` [PATCH 37/42] lpfc: Add first and second level hardware revisions to sysfs reporting James Smart
2019-08-14 23:57 ` [PATCH 38/42] lpfc: Add MDS driver loopback diagnostics support James Smart
2019-08-14 23:57 ` [PATCH 39/42] lpfc: Support dynamic unbounded SGL lists on G7 hardware James Smart
2019-08-14 23:57 ` [PATCH 40/42] lpfc: Add NVMe sequence level error recovery support James Smart
2019-08-14 23:57 ` [PATCH 41/42] lpfc: Merge per-protocol WQ/CQ pairs into single per-cpu pair James Smart
2019-08-14 23:57 ` [PATCH 42/42] lpfc: Update lpfc version to 12.4.0.0 James Smart
2019-08-20 3:06 ` [PATCH 00/42] lpfc: Update lpfc to revision 12.4.0.0 Martin K. Petersen
2019-08-27 13:31 ` Hannes Reinecke
2019-08-28 0:10 ` James Smart
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190814235712.4487-23-jsmart2021@gmail.com \
--to=jsmart2021@gmail.com \
--cc=dick.kennedy@broadcom.com \
--cc=linux-scsi@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).