diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 830429483319..2fd4ca96b308 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -282,11 +282,20 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; - unsigned int busy = scsi_host_busy(shost); + unsigned int busy; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; + spin_unlock_irqrestore(shost->host_lock, flags); + /* + * The counting of busy requests needs to occur after adding to + * host_failed or after the lock acquire for adding to host_failed + * to prevent a race with host unbusy and missing an eh wakeup. + */ + busy = scsi_host_busy(shost); + + spin_lock_irqsave(shost->host_lock, flags); scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index d7e42293b864..7ddb73cd6d9f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -376,6 +376,14 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + /* + * Ensure the clear of SCMD_STATE_INFLIGHT is visible to + * other CPUs before counting busy requests. Otherwise, + * reordering can cause CPUs to race and miss an eh wakeup + * when no CPU sees all busy requests as done or timed out. + */ + smp_mb(); + unsigned int busy = scsi_host_busy(shost); spin_lock_irqsave(shost->host_lock, flags);