scsi: core: Ensure that the SCSI error handler gets woken up

If scsi_eh_scmd_add() is called concurrently with
scsi_host_queue_ready() while shost->host_blocked > 0 then it can
happen that neither function wakes up the SCSI error handler. Fix
this by making every function that decreases the host_busy counter
wake up the error handler if necessary and by protecting the
host_failed checks with the SCSI host lock.

Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
References: https://marc.info/?l=linux-kernel&m=150461610630736
Fixes: commit 7466501608 ("scsi: convert host_busy to atomic_t")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Tested-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Cc: Konstantin Khorenko <khorenko@virtuozzo.com>
Cc: Stuart Hayes <stuart.w.hayes@gmail.com>
Cc: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This commit is contained in:
Bart Van Assche 2017-12-04 10:06:23 -08:00 committed by Martin K. Petersen
parent 156baec397
commit 3bd6f43f5c
4 changed files with 52 additions and 13 deletions

View File

@ -318,6 +318,9 @@ static void scsi_host_dev_release(struct device *dev)
scsi_proc_hostdir_rm(shost->hostt);
/* Wait for functions invoked through call_rcu(&shost->rcu, ...) */
rcu_barrier();
if (shost->tmf_work_q)
destroy_workqueue(shost->tmf_work_q);
if (shost->ehandler)
@ -325,6 +328,8 @@ static void scsi_host_dev_release(struct device *dev)
if (shost->work_q)
destroy_workqueue(shost->work_q);
destroy_rcu_head(&shost->rcu);
if (shost->shost_state == SHOST_CREATED) {
/*
* Free the shost_dev device name here if scsi_host_alloc()
@ -399,6 +404,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
INIT_LIST_HEAD(&shost->starved_list);
init_waitqueue_head(&shost->host_wait);
mutex_init(&shost->scan_mutex);
init_rcu_head(&shost->rcu);
index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL);
if (index < 0)

View File

@ -220,6 +220,17 @@ static void scsi_eh_reset(struct scsi_cmnd *scmd)
}
}
static void scsi_eh_inc_host_failed(struct rcu_head *head)
{
struct Scsi_Host *shost = container_of(head, typeof(*shost), rcu);
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
shost->host_failed++;
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
}
/**
* scsi_eh_scmd_add - add scsi cmd to error handling.
* @scmd: scmd to run eh on.
@ -242,9 +253,12 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
scsi_eh_reset(scmd);
list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q);
shost->host_failed++;
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
/*
* Ensure that all tasks observe the host state change before the
* host_failed change.
*/
call_rcu(&shost->rcu, scsi_eh_inc_host_failed);
}
/**

View File

@ -318,23 +318,40 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
cmd->cmd_len = scsi_command_size(cmd->cmnd);
}
/*
* Decrement the host_busy counter and wake up the error handler if necessary.
* Avoid as follows that the error handler is not woken up if shost->host_busy
* == shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination
* with an RCU read lock in this function to ensure that this function in its
* entirety either finishes before scsi_eh_scmd_add() increases the
* host_failed counter or that it notices the shost state change made by
* scsi_eh_scmd_add().
*/
static void scsi_dec_host_busy(struct Scsi_Host *shost)
{
unsigned long flags;
rcu_read_lock();
atomic_dec(&shost->host_busy);
if (unlikely(scsi_host_in_recovery(shost))) {
spin_lock_irqsave(shost->host_lock, flags);
if (shost->host_failed || shost->host_eh_scheduled)
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
}
rcu_read_unlock();
}
void scsi_device_unbusy(struct scsi_device *sdev)
{
struct Scsi_Host *shost = sdev->host;
struct scsi_target *starget = scsi_target(sdev);
unsigned long flags;
atomic_dec(&shost->host_busy);
scsi_dec_host_busy(shost);
if (starget->can_queue > 0)
atomic_dec(&starget->target_busy);
if (unlikely(scsi_host_in_recovery(shost) &&
(shost->host_failed || shost->host_eh_scheduled))) {
spin_lock_irqsave(shost->host_lock, flags);
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
}
atomic_dec(&sdev->device_busy);
}
@ -1532,7 +1549,7 @@ starved:
list_add_tail(&sdev->starved_entry, &shost->starved_list);
spin_unlock_irq(shost->host_lock);
out_dec:
atomic_dec(&shost->host_busy);
scsi_dec_host_busy(shost);
return 0;
}
@ -2018,7 +2035,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_STS_OK;
out_dec_host_busy:
atomic_dec(&shost->host_busy);
scsi_dec_host_busy(shost);
out_dec_target_busy:
if (scsi_target(sdev)->can_queue > 0)
atomic_dec(&scsi_target(sdev)->target_busy);

View File

@ -571,6 +571,8 @@ struct Scsi_Host {
struct blk_mq_tag_set tag_set;
};
struct rcu_head rcu;
atomic_t host_busy; /* commands actually active on low-level */
atomic_t host_blocked;