[PATCH 4.14 108/193] scsi: lpfc: Fix crash receiving ELS while detaching driver

[Greg Kroah-Hartman]

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>

commit 1234a6d54fed8a00091968c4eb2fb52e1cbb8e2e upstream.

The driver crashes when attempting to use a freed ndpl pointer.

The pci_remove_one handler runs on a separate kernel thread. The order
of the removal is starting by freeing all of the ndlps and then
disabling interrupts. In between these two events the driver can still
receive an ELS and process it. When it tries to use the ndlp pointer
will be NULL

Change the order of the pci_remove_one vs disable interrupts so that
interrupts are disabled before the ndlp's are freed.

Signed-off-by: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>
Signed-off-by: James Smart <james.smart@xxxxxxxxxxxx>
Reviewed-by: Johannes Thumshirn <jthumshirn@xxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/scsi/lpfc/lpfc_attr.c      |    6 ++++--
 drivers/scsi/lpfc/lpfc_bsg.c       |    4 +++-
 drivers/scsi/lpfc/lpfc_els.c       |    7 ++++++-
 drivers/scsi/lpfc/lpfc_hbadisc.c   |    5 ++++-
 drivers/scsi/lpfc/lpfc_init.c      |   14 +++++++-------
 drivers/scsi/lpfc/lpfc_nportdisc.c |    2 +-
 drivers/scsi/lpfc/lpfc_sli.c       |   12 ++++++++++++
 7 files changed, 37 insertions(+), 13 deletions(-)

--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -3134,7 +3134,8 @@ lpfc_txq_hw_show(struct device *dev, str
 	struct lpfc_hba   *phba = ((struct lpfc_vport *) shost->hostdata)->phba;
 	struct lpfc_sli_ring *pring = lpfc_phba_elsring(phba);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", pring->txq_max);
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			pring ? pring->txq_max : 0);
 }
 
 static DEVICE_ATTR(txq_hw, S_IRUGO,
@@ -3147,7 +3148,8 @@ lpfc_txcmplq_hw_show(struct device *dev,
 	struct lpfc_hba   *phba = ((struct lpfc_vport *) shost->hostdata)->phba;
 	struct lpfc_sli_ring *pring = lpfc_phba_elsring(phba);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", pring->txcmplq_max);
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			pring ? pring->txcmplq_max : 0);
 }
 
 static DEVICE_ATTR(txcmplq_hw, S_IRUGO,
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2911,7 +2911,7 @@ static int lpfcdiag_loop_post_rxbufs(str
 		}
 	}
 
-	if (!cmdiocbq || !rxbmp || !rxbpl || !rxbuffer) {
+	if (!cmdiocbq || !rxbmp || !rxbpl || !rxbuffer || !pring) {
 		ret_val = -ENOMEM;
 		goto err_post_rxbufs_exit;
 	}
@@ -5421,6 +5421,8 @@ lpfc_bsg_timeout(struct bsg_job *job)
 	struct lpfc_iocbq *check_iocb, *next_iocb;
 
 	pring = lpfc_phba_elsring(phba);
+	if (unlikely(!pring))
+		return -EIO;
 
 	/* if job's driver data is NULL, the command completed or is in the
 	 * the process of completing.  In this case, return status to request
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -7430,6 +7430,8 @@ lpfc_els_timeout_handler(struct lpfc_vpo
 	timeout = (uint32_t)(phba->fc_ratov << 1);
 
 	pring = lpfc_phba_elsring(phba);
+	if (unlikely(!pring))
+		return;
 
 	if ((phba->pport->load_flag & FC_UNLOADING))
 		return;
@@ -9310,6 +9312,9 @@ void lpfc_fabric_abort_nport(struct lpfc
 
 	pring = lpfc_phba_elsring(phba);
 
+	if (unlikely(!pring))
+		return;
+
 	spin_lock_irq(&phba->hbalock);
 	list_for_each_entry_safe(piocb, tmp_iocb, &phba->fabric_iocb_list,
 				 list) {
@@ -9416,7 +9421,7 @@ lpfc_sli4_els_xri_aborted(struct lpfc_hb
 				rxid, 1);
 
 			/* Check if TXQ queue needs to be serviced */
-			if (!(list_empty(&pring->txq)))
+			if (pring && !list_empty(&pring->txq))
 				lpfc_worker_wake_up(phba);
 			return;
 		}
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -3324,7 +3324,8 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_
 
 	/* Unblock ELS traffic */
 	pring = lpfc_phba_elsring(phba);
-	pring->flag &= ~LPFC_STOP_IOCB_EVENT;
+	if (pring)
+		pring->flag &= ~LPFC_STOP_IOCB_EVENT;
 
 	/* Check for error */
 	if (mb->mbxStatus) {
@@ -5430,6 +5431,8 @@ lpfc_free_tx(struct lpfc_hba *phba, stru
 
 	psli = &phba->sli;
 	pring = lpfc_phba_elsring(phba);
+	if (unlikely(!pring))
+		return;
 
 	/* Error matching iocb on txq or txcmplq
 	 * First check the txq.
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -11404,6 +11404,13 @@ lpfc_pci_remove_one_s4(struct pci_dev *p
 	/* Remove FC host and then SCSI host with the physical port */
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
+	/*
+	 * Bring down the SLI Layer. This step disables all interrupts,
+	 * clears the rings, discards all mailbox commands, and resets
+	 * the HBA FCoE function.
+	 */
+	lpfc_debugfs_terminate(vport);
+	lpfc_sli4_hba_unset(phba);
 
 	/* Perform ndlp cleanup on the physical port.  The nvme and nvmet
 	 * localports are destroyed after to cleanup all transport memory.
@@ -11412,13 +11419,6 @@ lpfc_pci_remove_one_s4(struct pci_dev *p
 	lpfc_nvmet_destroy_targetport(phba);
 	lpfc_nvme_destroy_localport(vport);
 
-	/*
-	 * Bring down the SLI Layer. This step disables all interrupts,
-	 * clears the rings, discards all mailbox commands, and resets
-	 * the HBA FCoE function.
-	 */
-	lpfc_debugfs_terminate(vport);
-	lpfc_sli4_hba_unset(phba);
 
 	lpfc_stop_hba_timers(phba);
 	spin_lock_irq(&phba->hbalock);
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -216,7 +216,7 @@ lpfc_els_abort(struct lpfc_hba *phba, st
 	pring = lpfc_phba_elsring(phba);
 
 	/* In case of error recovery path, we might have a NULL pring here */
-	if (!pring)
+	if (unlikely(!pring))
 		return;
 
 	/* Abort outstanding I/O on NPort <nlp_DID> */
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -10632,6 +10632,14 @@ lpfc_sli_issue_abort_iotag(struct lpfc_h
 	    (cmdiocb->iocb_flag & LPFC_DRIVER_ABORTED) != 0)
 		return 0;
 
+	if (!pring) {
+		if (cmdiocb->iocb_flag & LPFC_IO_FABRIC)
+			cmdiocb->fabric_iocb_cmpl = lpfc_ignore_els_cmpl;
+		else
+			cmdiocb->iocb_cmpl = lpfc_ignore_els_cmpl;
+		goto abort_iotag_exit;
+	}
+
 	/*
 	 * If we're unloading, don't abort iocb on the ELS ring, but change
 	 * the callback so that nothing happens when it finishes.
@@ -12500,6 +12508,8 @@ lpfc_sli4_els_wcqe_to_rspiocbq(struct lp
 	unsigned long iflags;
 
 	pring = lpfc_phba_elsring(phba);
+	if (unlikely(!pring))
+		return NULL;
 
 	wcqe = &irspiocbq->cq_event.cqe.wcqe_cmpl;
 	spin_lock_irqsave(&pring->ring_lock, iflags);
@@ -18694,6 +18704,8 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 	uint32_t txq_cnt = 0;
 
 	pring = lpfc_phba_elsring(phba);
+	if (unlikely(!pring))
+		return 0;
 
 	spin_lock_irqsave(&pring->ring_lock, iflags);
 	list_for_each_entry(piocbq, &pring->txq, list) {