Patch "scsi: qedf: Wait for stag work during unload" has been added to the 6.1-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    scsi: qedf: Wait for stag work during unload

to the 6.1-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     scsi-qedf-wait-for-stag-work-during-unload.patch
and it can be found in the queue-6.1 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 2a35c25cdd2fa7429b6cbe7a0ec962f4c7baad55
Author: Saurav Kashyap <skashyap@xxxxxxxxxxx>
Date:   Wed May 15 14:41:00 2024 +0530

    scsi: qedf: Wait for stag work during unload
    
    [ Upstream commit 78e88472b60936025b83eba57cffa59d3501dc07 ]
    
    If stag work is already scheduled and unload is called, it can lead to
    issues as unload cleans up the work element. Wait for stag work to get
    completed before cleanup during unload.
    
    Signed-off-by: Saurav Kashyap <skashyap@xxxxxxxxxxx>
    Signed-off-by: Nilesh Javali <njavali@xxxxxxxxxxx>
    Link: https://lore.kernel.org/r/20240515091101.18754-3-skashyap@xxxxxxxxxxx
    Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index c5c0bbdafc4ea..81b84757faae0 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -362,6 +362,7 @@ struct qedf_ctx {
 #define QEDF_IN_RECOVERY		5
 #define QEDF_DBG_STOP_IO		6
 #define QEDF_PROBING			8
+#define QEDF_STAG_IN_PROGRESS		9
 	unsigned long flags; /* Miscellaneous state flags */
 	int fipvlan_retries;
 	u8 num_queues;
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 27f4028bff3bf..524807f9f4eb1 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -318,11 +318,18 @@ static struct fc_seq *qedf_elsct_send(struct fc_lport *lport, u32 did,
 	 */
 	if (resp == fc_lport_flogi_resp) {
 		qedf->flogi_cnt++;
+		qedf->flogi_pending++;
+
+		if (test_bit(QEDF_UNLOADING, &qedf->flags)) {
+			QEDF_ERR(&qedf->dbg_ctx, "Driver unloading\n");
+			qedf->flogi_pending = 0;
+		}
+
 		if (qedf->flogi_pending >= QEDF_FLOGI_RETRY_CNT) {
 			schedule_delayed_work(&qedf->stag_work, 2);
 			return NULL;
 		}
-		qedf->flogi_pending++;
+
 		return fc_elsct_send(lport, did, fp, op, qedf_flogi_resp,
 		    arg, timeout);
 	}
@@ -911,13 +918,14 @@ void qedf_ctx_soft_reset(struct fc_lport *lport)
 	struct qedf_ctx *qedf;
 	struct qed_link_output if_link;
 
+	qedf = lport_priv(lport);
+
 	if (lport->vport) {
+		clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags);
 		printk_ratelimited("Cannot issue host reset on NPIV port.\n");
 		return;
 	}
 
-	qedf = lport_priv(lport);
-
 	qedf->flogi_pending = 0;
 	/* For host reset, essentially do a soft link up/down */
 	atomic_set(&qedf->link_state, QEDF_LINK_DOWN);
@@ -937,6 +945,7 @@ void qedf_ctx_soft_reset(struct fc_lport *lport)
 	if (!if_link.link_up) {
 		QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC,
 			  "Physical link is not up.\n");
+		clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags);
 		return;
 	}
 	/* Flush and wait to make sure link down is processed */
@@ -949,6 +958,7 @@ void qedf_ctx_soft_reset(struct fc_lport *lport)
 		  "Queue link up work.\n");
 	queue_delayed_work(qedf->link_update_wq, &qedf->link_update,
 	    0);
+	clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags);
 }
 
 /* Reset the host by gracefully logging out and then logging back in */
@@ -3725,6 +3735,7 @@ static void __qedf_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedf_ctx *qedf;
 	int rc;
+	int cnt = 0;
 
 	if (!pdev) {
 		QEDF_ERR(NULL, "pdev is NULL.\n");
@@ -3742,6 +3753,17 @@ static void __qedf_remove(struct pci_dev *pdev, int mode)
 		return;
 	}
 
+stag_in_prog:
+	if (test_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags)) {
+		QEDF_ERR(&qedf->dbg_ctx, "Stag in progress, cnt=%d.\n", cnt);
+		cnt++;
+
+		if (cnt < 5) {
+			msleep(500);
+			goto stag_in_prog;
+		}
+	}
+
 	if (mode != QEDF_MODE_RECOVERY)
 		set_bit(QEDF_UNLOADING, &qedf->flags);
 
@@ -4017,6 +4039,8 @@ void qedf_stag_change_work(struct work_struct *work)
 		return;
 	}
 
+	set_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags);
+
 	printk_ratelimited("[%s]:[%s:%d]:%d: Performing software context reset.",
 			dev_name(&qedf->pdev->dev), __func__, __LINE__,
 			qedf->dbg_ctx.host_no);