From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Thu, 10 Feb 2022 15:28:09 +0530
Subject: scsi: mpi3mr: Fix deadlock while canceling the fw event
Git-commit: 580e6742205efe6b0bfa5a6a6079f509d99168e0
Patch-mainline: v5.18-rc1
References: jsc#PED-1446

During controller reset, the driver tries to flush all the pending firmware
event works from worker queue that are queued prior to the reset. However,
if any work is waiting for device addition/removal operation to be
completed at the SML, then a deadlock is observed. This is due to the
controller reset waiting for the device addition/removal to be completed
and the device/addition removal is waiting for the controller reset to be
completed.

To limit this deadlock, continue with the controller reset handling without
canceling the work which is waiting for device addition/removal operation
to complete at SML.

Link: https://lore.kernel.org/r/20220210095817.22828-2-sreekanth.reddy@broadcom.com
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Lee Duncan <lduncan@suse.com>
---
 drivers/scsi/mpi3mr/mpi3mr.h    |    4 +
 drivers/scsi/mpi3mr/mpi3mr_fw.c |    2 
 drivers/scsi/mpi3mr/mpi3mr_os.c |  106 ++++++++++++++++++++++++++++++++--------
 3 files changed, 91 insertions(+), 21 deletions(-)

--- a/drivers/scsi/mpi3mr/mpi3mr.h
+++ b/drivers/scsi/mpi3mr/mpi3mr.h
@@ -851,6 +851,8 @@ struct mpi3mr_ioc {
  * @send_ack: Event acknowledgment required or not
  * @process_evt: Bottomhalf processing required or not
  * @evt_ctx: Event context to send in Ack
+ * @pending_at_sml: waiting for device add/remove API to complete
+ * @discard: discard this event
  * @ref_count: kref count
  * @event_data: Actual MPI3 event data
  */
@@ -862,6 +864,8 @@ struct mpi3mr_fwevt {
 	bool send_ack;
 	bool process_evt;
 	u32 evt_ctx;
+	bool pending_at_sml;
+	bool discard;
 	struct kref ref_count;
 	char event_data[] __aligned(4);
 };
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -4235,8 +4235,8 @@ int mpi3mr_soft_reset_handler(struct mpi
 	memset(mrioc->devrem_bitmap, 0, mrioc->devrem_bitmap_sz);
 	memset(mrioc->removepend_bitmap, 0, mrioc->dev_handle_bitmap_sz);
 	memset(mrioc->evtack_cmds_bitmap, 0, mrioc->evtack_cmds_bitmap_sz);
-	mpi3mr_cleanup_fwevt_list(mrioc);
 	mpi3mr_flush_host_io(mrioc);
+	mpi3mr_cleanup_fwevt_list(mrioc);
 	mpi3mr_invalidate_devhandles(mrioc);
 	if (mrioc->prepare_for_reset) {
 		mrioc->prepare_for_reset = 0;
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -286,6 +286,35 @@ static struct mpi3mr_fwevt *mpi3mr_deque
 }
 
 /**
+ * mpi3mr_cancel_work - cancel firmware event
+ * @fwevt: fwevt object which needs to be canceled
+ *
+ * Return: Nothing.
+ */
+static void mpi3mr_cancel_work(struct mpi3mr_fwevt *fwevt)
+{
+	/*
+	 * Wait on the fwevt to complete. If this returns 1, then
+	 * the event was never executed.
+	 *
+	 * If it did execute, we wait for it to finish, and the put will
+	 * happen from mpi3mr_process_fwevt()
+	 */
+	if (cancel_work_sync(&fwevt->work)) {
+		/*
+		 * Put fwevt reference count after
+		 * dequeuing it from worker queue
+		 */
+		mpi3mr_fwevt_put(fwevt);
+		/*
+		 * Put fwevt reference count to neutralize
+		 * kref_init increment
+		 */
+		mpi3mr_fwevt_put(fwevt);
+	}
+}
+
+/**
  * mpi3mr_cleanup_fwevt_list - Cleanup firmware event list
  * @mrioc: Adapter instance reference
  *
@@ -302,28 +331,25 @@ void mpi3mr_cleanup_fwevt_list(struct mp
 	    !mrioc->fwevt_worker_thread)
 		return;
 
-	while ((fwevt = mpi3mr_dequeue_fwevt(mrioc)) ||
-	    (fwevt = mrioc->current_event)) {
+	while ((fwevt = mpi3mr_dequeue_fwevt(mrioc)))
+		mpi3mr_cancel_work(fwevt);
+
+	if (mrioc->current_event) {
+		fwevt = mrioc->current_event;
 		/*
-		 * Wait on the fwevt to complete. If this returns 1, then
-		 * the event was never executed, and we need a put for the
-		 * reference the work had on the fwevt.
-		 *
-		 * If it did execute, we wait for it to finish, and the put will
-		 * happen from mpi3mr_process_fwevt()
+		 * Don't call cancel_work_sync() API for the
+		 * fwevt work if the controller reset is
+		 * get called as part of processing the
+		 * same fwevt work (or) when worker thread is
+		 * waiting for device add/remove APIs to complete.
+		 * Otherwise we will see deadlock.
 		 */
-		if (cancel_work_sync(&fwevt->work)) {
-			/*
-			 * Put fwevt reference count after
-			 * dequeuing it from worker queue
-			 */
-			mpi3mr_fwevt_put(fwevt);
-			/*
-			 * Put fwevt reference count to neutralize
-			 * kref_init increment
-			 */
-			mpi3mr_fwevt_put(fwevt);
+		if (current_work() == &fwevt->work || fwevt->pending_at_sml) {
+			fwevt->discard = 1;
+			return;
 		}
+
+		mpi3mr_cancel_work(fwevt);
 	}
 }
 
@@ -691,6 +717,24 @@ static struct mpi3mr_tgt_dev  *__mpi3mr_
 }
 
 /**
+ * mpi3mr_print_device_event_notice - print notice related to post processing of
+ *					device event after controller reset.
+ *
+ * @mrioc: Adapter instance reference
+ * @device_add: true for device add event and false for device removal event
+ *
+ * Return: None.
+ */
+static void mpi3mr_print_device_event_notice(struct mpi3mr_ioc *mrioc,
+	bool device_add)
+{
+	ioc_notice(mrioc, "Device %s was in progress before the reset and\n",
+	    (device_add ? "addition" : "removal"));
+	ioc_notice(mrioc, "completed after reset, verify whether the exposed devices\n");
+	ioc_notice(mrioc, "are matched with attached devices for correctness\n");
+}
+
+/**
  * mpi3mr_remove_tgtdev_from_host - Remove dev from upper layers
  * @mrioc: Adapter instance reference
  * @tgtdev: Target device structure
@@ -714,8 +758,17 @@ static void mpi3mr_remove_tgtdev_from_ho
 	}
 
 	if (tgtdev->starget) {
+		if (mrioc->current_event)
+			mrioc->current_event->pending_at_sml = 1;
 		scsi_remove_target(&tgtdev->starget->dev);
 		tgtdev->host_exposed = 0;
+		if (mrioc->current_event) {
+			mrioc->current_event->pending_at_sml = 0;
+			if (mrioc->current_event->discard) {
+				mpi3mr_print_device_event_notice(mrioc, false);
+				return;
+			}
+		}
 	}
 	ioc_info(mrioc, "%s :Removed handle(0x%04x), wwid(0x%016llx)\n",
 	    __func__, tgtdev->dev_handle, (unsigned long long)tgtdev->wwid);
@@ -749,11 +802,20 @@ static int mpi3mr_report_tgtdev_to_host(
 	}
 	if (!tgtdev->host_exposed && !mrioc->reset_in_progress) {
 		tgtdev->host_exposed = 1;
+		if (mrioc->current_event)
+			mrioc->current_event->pending_at_sml = 1;
 		scsi_scan_target(&mrioc->shost->shost_gendev, 0,
 		    tgtdev->perst_id,
 		    SCAN_WILD_CARD, SCSI_SCAN_INITIAL);
 		if (!tgtdev->starget)
 			tgtdev->host_exposed = 0;
+		if (mrioc->current_event) {
+			mrioc->current_event->pending_at_sml = 0;
+			if (mrioc->current_event->discard) {
+				mpi3mr_print_device_event_notice(mrioc, true);
+				goto out;
+			}
+		}
 	}
 out:
 	if (tgtdev)
@@ -1193,6 +1255,8 @@ static void mpi3mr_sastopochg_evt_bh(str
 	mpi3mr_sastopochg_evt_debug(mrioc, event_data);
 
 	for (i = 0; i < event_data->num_entries; i++) {
+		if (fwevt->discard)
+			return;
 		handle = le16_to_cpu(event_data->phy_entry[i].attached_dev_handle);
 		if (!handle)
 			continue;
@@ -1324,6 +1388,8 @@ static void mpi3mr_pcietopochg_evt_bh(st
 	mpi3mr_pcietopochg_evt_debug(mrioc, event_data);
 
 	for (i = 0; i < event_data->num_entries; i++) {
+		if (fwevt->discard)
+			return;
 		handle =
 		    le16_to_cpu(event_data->port_entry[i].attached_dev_handle);
 		if (!handle)
@@ -1362,8 +1428,8 @@ static void mpi3mr_pcietopochg_evt_bh(st
 static void mpi3mr_fwevt_bh(struct mpi3mr_ioc *mrioc,
 	struct mpi3mr_fwevt *fwevt)
 {
-	mrioc->current_event = fwevt;
 	mpi3mr_fwevt_del_from_list(mrioc, fwevt);
+	mrioc->current_event = fwevt;
 
 	if (mrioc->stop_drv_processing)
 		goto out;