scsi: core: Avoid that ATA error handling can trigger a kernel hang or oops

Avoid that the recently introduced call_rcu() call in the SCSI core
triggers a double call_rcu() call.
Reported-by: Natanael Copa <ncopa@alpinelinux.org>
Reported-by: Damien Le Moal <damien.lemoal@wdc.com>
References: https://bugzilla.kernel.org/show_bug.cgi?id=198861
Fixes: 3bd6f43f ("scsi: core: Ensure that the SCSI error handler gets woken up")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Natanael Copa <ncopa@alpinelinux.org>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Alexandre Oliva <oliva@gnu.org>
Cc: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
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>

drivers/scsi/hosts.c

@@ -328,8 +328,6 @@ 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()
@@ -404,7 +402,6 @@ 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)

drivers/scsi/scsi_error.c

@@ -223,7 +223,8 @@ 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);
+	struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
+	struct Scsi_Host *shost = scmd->device->host;
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
@@ -259,7 +260,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
 	 * Ensure that all tasks observe the host state change before the
 	 * host_failed change.
 	 */
-	call_rcu(&shost->rcu, scsi_eh_inc_host_failed);
+	call_rcu(&scmd->rcu, scsi_eh_inc_host_failed);
 }
 
 /**

drivers/scsi/scsi_lib.c

@@ -670,6 +670,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
 	if (!blk_rq_is_scsi(req)) {
 		WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
 		cmd->flags &= ~SCMD_INITIALIZED;
+		destroy_rcu_head(&cmd->rcu);
 	}
 
 	if (req->mq_ctx) {
@@ -1150,6 +1151,7 @@ static void scsi_initialize_rq(struct request *rq)
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
 	scsi_req_init(&cmd->req);
+	init_rcu_head(&cmd->rcu);
 	cmd->jiffies_at_alloc = jiffies;
 	cmd->retries = 0;
 }

include/scsi/scsi_cmnd.h

@@ -69,6 +69,9 @@ struct scsi_cmnd {
 	struct list_head list;  /* scsi_cmnd participates in queue lists */
 	struct list_head eh_entry; /* entry for the host eh_cmd_q */
 	struct delayed_work abort_work;
+
+	struct rcu_head rcu;
+
 	int eh_eflags;		/* Used by error handlr */
 
 	/*

include/scsi/scsi_host.h

@@ -571,8 +571,6 @@ 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;