[PATCH AUTOSEL 4.18 42/58] scsi: ipr: System hung while dlpar adding primary ipr adapter back

From: Sasha Levin
Date: Mon Oct 08 2018 - 11:35:16 EST


From: Wen Xiong <wenxiong@xxxxxxxxxxxxxxxxxx>

[ Upstream commit 318ddb34b2052f838aa243d07173e2badf3e630e ]

While dlpar adding primary ipr adapter back, driver goes through adapter
initialization then schedule ipr_worker_thread to start te disk scan by
dropping the host lock, calling scsi_add_device. Then get the adapter reset
request again, so driver does scsi_block_requests, this will cause the
scsi_add_device get hung until we unblock. But we can't run ipr_worker_thread
to do the unblock because its stuck in scsi_add_device.

This patch fixes the issue.

[mkp: typo and whitespace fixes]

Signed-off-by: Wen Xiong <wenxiong@xxxxxxxxxxxxxxxxxx>
Acked-by: Brian King <brking@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
---
drivers/scsi/ipr.c | 106 ++++++++++++++++++++++++++-------------------
drivers/scsi/ipr.h | 1 +
2 files changed, 62 insertions(+), 45 deletions(-)

diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 02d65dce74e5..2e8a91341254 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -3310,6 +3310,65 @@ static void ipr_release_dump(struct kref *kref)
LEAVE;
}

+static void ipr_add_remove_thread(struct work_struct *work)
+{
+ unsigned long lock_flags;
+ struct ipr_resource_entry *res;
+ struct scsi_device *sdev;
+ struct ipr_ioa_cfg *ioa_cfg =
+ container_of(work, struct ipr_ioa_cfg, scsi_add_work_q);
+ u8 bus, target, lun;
+ int did_work;
+
+ ENTER;
+ spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+
+restart:
+ do {
+ did_work = 0;
+ if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) {
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+ return;
+ }
+
+ list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
+ if (res->del_from_ml && res->sdev) {
+ did_work = 1;
+ sdev = res->sdev;
+ if (!scsi_device_get(sdev)) {
+ if (!res->add_to_ml)
+ list_move_tail(&res->queue, &ioa_cfg->free_res_q);
+ else
+ res->del_from_ml = 0;
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+ scsi_remove_device(sdev);
+ scsi_device_put(sdev);
+ spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+ }
+ break;
+ }
+ }
+ } while (did_work);
+
+ list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
+ if (res->add_to_ml) {
+ bus = res->bus;
+ target = res->target;
+ lun = res->lun;
+ res->add_to_ml = 0;
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+ scsi_add_device(ioa_cfg->host, bus, target, lun);
+ spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+ goto restart;
+ }
+ }
+
+ ioa_cfg->scan_done = 1;
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+ kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE);
+ LEAVE;
+}
+
/**
* ipr_worker_thread - Worker thread
* @work: ioa config struct
@@ -3324,13 +3383,9 @@ static void ipr_release_dump(struct kref *kref)
static void ipr_worker_thread(struct work_struct *work)
{
unsigned long lock_flags;
- struct ipr_resource_entry *res;
- struct scsi_device *sdev;
struct ipr_dump *dump;
struct ipr_ioa_cfg *ioa_cfg =
container_of(work, struct ipr_ioa_cfg, work_q);
- u8 bus, target, lun;
- int did_work;

ENTER;
spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
@@ -3368,49 +3423,9 @@ static void ipr_worker_thread(struct work_struct *work)
return;
}

-restart:
- do {
- did_work = 0;
- if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) {
- spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
- return;
- }
+ schedule_work(&ioa_cfg->scsi_add_work_q);

- list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
- if (res->del_from_ml && res->sdev) {
- did_work = 1;
- sdev = res->sdev;
- if (!scsi_device_get(sdev)) {
- if (!res->add_to_ml)
- list_move_tail(&res->queue, &ioa_cfg->free_res_q);
- else
- res->del_from_ml = 0;
- spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
- scsi_remove_device(sdev);
- scsi_device_put(sdev);
- spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
- }
- break;
- }
- }
- } while (did_work);
-
- list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
- if (res->add_to_ml) {
- bus = res->bus;
- target = res->target;
- lun = res->lun;
- res->add_to_ml = 0;
- spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
- scsi_add_device(ioa_cfg->host, bus, target, lun);
- spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
- goto restart;
- }
- }
-
- ioa_cfg->scan_done = 1;
spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
- kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE);
LEAVE;
}

@@ -9908,6 +9923,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
INIT_LIST_HEAD(&ioa_cfg->free_res_q);
INIT_LIST_HEAD(&ioa_cfg->used_res_q);
INIT_WORK(&ioa_cfg->work_q, ipr_worker_thread);
+ INIT_WORK(&ioa_cfg->scsi_add_work_q, ipr_add_remove_thread);
init_waitqueue_head(&ioa_cfg->reset_wait_q);
init_waitqueue_head(&ioa_cfg->msi_wait_q);
init_waitqueue_head(&ioa_cfg->eeh_wait_q);
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 93570734cbfb..a98cfd24035a 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1568,6 +1568,7 @@ struct ipr_ioa_cfg {
u8 saved_mode_page_len;

struct work_struct work_q;
+ struct work_struct scsi_add_work_q;
struct workqueue_struct *reset_work_q;

wait_queue_head_t reset_wait_q;
--
2.17.1