--- /dev/null
+From 53770f0ec5fd417429775ba006bc4abe14002335 Mon Sep 17 00:00:00 2001
+From: Mikulas Patocka <mpatocka@redhat.com>
+Date: Mon, 17 Feb 2020 07:43:03 -0500
+Subject: dm integrity: fix a deadlock due to offloading to an incorrect workqueue
+
+From: Mikulas Patocka <mpatocka@redhat.com>
+
+commit 53770f0ec5fd417429775ba006bc4abe14002335 upstream.
+
+If we need to perform synchronous I/O in dm_integrity_map_continue(),
+we must make sure that we are not in the map function - in order to
+avoid the deadlock due to bio queuing in generic_make_request. To
+avoid the deadlock, we offload the request to metadata_wq.
+
+However, metadata_wq also processes metadata updates for write requests.
+If there are too many requests that get offloaded to metadata_wq at the
+beginning of dm_integrity_map_continue, the workqueue metadata_wq
+becomes clogged and the system is incapable of processing any metadata
+updates.
+
+This causes a deadlock because all the requests that need to do metadata
+updates wait for metadata_wq to proceed and metadata_wq waits inside
+wait_and_add_new_range until some existing request releases its range
+lock (which doesn't happen because the range lock is released after
+metadata update).
+
+In order to fix the deadlock, we create a new workqueue offload_wq and
+offload requests to it - so that processing of offload_wq is independent
+from processing of metadata_wq.
+
+Fixes: 7eada909bfd7 ("dm: add integrity target")
+Cc: stable@vger.kernel.org # v4.12+
+Reported-by: Heinz Mauelshagen <heinzm@redhat.com>
+Tested-by: Heinz Mauelshagen <heinzm@redhat.com>
+Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
+Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
+Signed-off-by: Mike Snitzer <snitzer@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/md/dm-integrity.c | 15 +++++++++++++--
+ 1 file changed, 13 insertions(+), 2 deletions(-)
+
+--- a/drivers/md/dm-integrity.c
++++ b/drivers/md/dm-integrity.c
+@@ -198,6 +198,7 @@ struct dm_integrity_c {
+ struct list_head wait_list;
+ wait_queue_head_t endio_wait;
+ struct workqueue_struct *wait_wq;
++ struct workqueue_struct *offload_wq;
+
+ unsigned char commit_seq;
+ commit_id_t commit_ids[N_COMMIT_IDS];
+@@ -1237,7 +1238,7 @@ static void dec_in_flight(struct dm_inte
+ dio->range.logical_sector += dio->range.n_sectors;
+ bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
+ INIT_WORK(&dio->work, integrity_bio_wait);
+- queue_work(ic->wait_wq, &dio->work);
++ queue_work(ic->offload_wq, &dio->work);
+ return;
+ }
+ do_endio_flush(ic, dio);
+@@ -1657,7 +1658,7 @@ static void dm_integrity_map_continue(st
+
+ if (need_sync_io && from_map) {
+ INIT_WORK(&dio->work, integrity_bio_wait);
+- queue_work(ic->metadata_wq, &dio->work);
++ queue_work(ic->offload_wq, &dio->work);
+ return;
+ }
+
+@@ -3308,6 +3309,14 @@ static int dm_integrity_ctr(struct dm_ta
+ goto bad;
+ }
+
++ ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM,
++ METADATA_WORKQUEUE_MAX_ACTIVE);
++ if (!ic->offload_wq) {
++ ti->error = "Cannot allocate workqueue";
++ r = -ENOMEM;
++ goto bad;
++ }
++
+ ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1);
+ if (!ic->commit_wq) {
+ ti->error = "Cannot allocate workqueue";
+@@ -3544,6 +3553,8 @@ static void dm_integrity_dtr(struct dm_t
+ destroy_workqueue(ic->metadata_wq);
+ if (ic->wait_wq)
+ destroy_workqueue(ic->wait_wq);
++ if (ic->offload_wq)
++ destroy_workqueue(ic->offload_wq);
+ if (ic->commit_wq)
+ destroy_workqueue(ic->commit_wq);
+ if (ic->writer_wq)
--- /dev/null
+From 196ba6629cf95e51403337235d09742fcdc3febd Mon Sep 17 00:00:00 2001
+From: Deepak Ukey <deepak.ukey@microchip.com>
+Date: Tue, 9 Jul 2019 15:30:48 +0530
+Subject: scsi: pm80xx: Fixed kernel panic during error recovery for SATA drive
+
+From: Deepak Ukey <deepak.ukey@microchip.com>
+
+commit 196ba6629cf95e51403337235d09742fcdc3febd upstream.
+
+Disabling the SATA drive interface cause kernel panic. When the drive
+Interface is disabled, device should be deregistered after aborting all
+pending I/Os. Also changed the port recovery timeout to 10000 ms for
+PM8006 controller.
+
+Signed-off-by: Deepak Ukey <deepak.ukey@microchip.com>
+Signed-off-by: Viswas G <Viswas.G@microchip.com>
+Reviewed-by: Jack Wang <jinpu.wang@cloud.ionos.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/scsi/pm8001/pm8001_sas.c | 6 +++++-
+ drivers/scsi/pm8001/pm80xx_hwi.c | 2 +-
+ drivers/scsi/pm8001/pm80xx_hwi.h | 2 ++
+ 3 files changed, 8 insertions(+), 2 deletions(-)
+
+--- a/drivers/scsi/pm8001/pm8001_sas.c
++++ b/drivers/scsi/pm8001/pm8001_sas.c
+@@ -866,6 +866,8 @@ static void pm8001_dev_gone_notify(struc
+ spin_unlock_irqrestore(&pm8001_ha->lock, flags);
+ pm8001_exec_internal_task_abort(pm8001_ha, pm8001_dev ,
+ dev, 1, 0);
++ while (pm8001_dev->running_req)
++ msleep(20);
+ spin_lock_irqsave(&pm8001_ha->lock, flags);
+ }
+ PM8001_CHIP_DISP->dereg_dev_req(pm8001_ha, device_id);
+@@ -1238,8 +1240,10 @@ int pm8001_abort_task(struct sas_task *t
+ PM8001_MSG_DBG(pm8001_ha,
+ pm8001_printk("Waiting for Port reset\n"));
+ wait_for_completion(&completion_reset);
+- if (phy->port_reset_status)
++ if (phy->port_reset_status) {
++ pm8001_dev_gone_notify(dev);
+ goto out;
++ }
+
+ /*
+ * 4. SATA Abort ALL
+--- a/drivers/scsi/pm8001/pm80xx_hwi.c
++++ b/drivers/scsi/pm8001/pm80xx_hwi.c
+@@ -604,7 +604,7 @@ static void update_main_config_table(str
+ pm8001_ha->main_cfg_tbl.pm80xx_tbl.port_recovery_timer &=
+ 0x0000ffff;
+ pm8001_ha->main_cfg_tbl.pm80xx_tbl.port_recovery_timer |=
+- 0x140000;
++ CHIP_8006_PORT_RECOVERY_TIMEOUT;
+ }
+ pm8001_mw32(address, MAIN_PORT_RECOVERY_TIMER,
+ pm8001_ha->main_cfg_tbl.pm80xx_tbl.port_recovery_timer);
+--- a/drivers/scsi/pm8001/pm80xx_hwi.h
++++ b/drivers/scsi/pm8001/pm80xx_hwi.h
+@@ -228,6 +228,8 @@
+ #define SAS_MAX_AIP 0x200000
+ #define IT_NEXUS_TIMEOUT 0x7D0
+ #define PORT_RECOVERY_TIMEOUT ((IT_NEXUS_TIMEOUT/100) + 30)
++/* Port recovery timeout, 10000 ms for PM8006 controller */
++#define CHIP_8006_PORT_RECOVERY_TIMEOUT 0x640000
+
+ #ifdef __LITTLE_ENDIAN_BITFIELD
+ struct sas_identify_frame_local {
projects / thirdparty / kernel / stable-queue.git / commitdiff
