[SCSI] libsas: introduce sas_work to fix sas_drain_work vs sas_queue_work

When requeuing work to a draining workqueue the last work instance may
not be idle, so sas_queue_work() must not touch work->entry. Introduce
sas_work with a drain_node list_head to have a private list for
collecting work deferred due to drain collision.

Fixes reports like:
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff810410d4>] process_one_work+0x2e/0x338

Signed-off-by: Dan Williams <[e-mail]>
Signed-off-by: James Bottomley <[e-mail]>

drivers/scsi/libsas/sas_discover.c

···
 static void sas_probe_devices(struct work_struct *work)
 {
 	struct domain_device *dev, *n;
-	struct sas_discovery_event *ev =
-		container_of(work, struct sas_discovery_event, work);
+	struct sas_discovery_event *ev = to_sas_discovery_event(work);
 	struct asd_sas_port *port = ev->port;
 
 	clear_bit(DISCE_PROBE, &port->disc.pending);
···
 static void sas_destruct_devices(struct work_struct *work)
 {
 	struct domain_device *dev, *n;
-	struct sas_discovery_event *ev =
-		container_of(work, struct sas_discovery_event, work);
+	struct sas_discovery_event *ev = to_sas_discovery_event(work);
 	struct asd_sas_port *port = ev->port;
 
 	clear_bit(DISCE_DESTRUCT, &port->disc.pending);
···
 {
 	struct domain_device *dev;
 	int error = 0;
-	struct sas_discovery_event *ev =
-		container_of(work, struct sas_discovery_event, work);
+	struct sas_discovery_event *ev = to_sas_discovery_event(work);
 	struct asd_sas_port *port = ev->port;
 
 	clear_bit(DISCE_DISCOVER_DOMAIN, &port->disc.pending);
···
 static void sas_revalidate_domain(struct work_struct *work)
 {
 	int res = 0;
-	struct sas_discovery_event *ev =
-		container_of(work, struct sas_discovery_event, work);
+	struct sas_discovery_event *ev = to_sas_discovery_event(work);
 	struct asd_sas_port *port = ev->port;
 	struct sas_ha_struct *ha = port->ha;
 
···
 
 /* ---------- Events ---------- */
 
-static void sas_chain_work(struct sas_ha_struct *ha, struct work_struct *work)
+static void sas_chain_work(struct sas_ha_struct *ha, struct sas_work *sw)
 {
-	/* chained work is not subject to SA_HA_DRAINING or SAS_HA_REGISTERED */
-	scsi_queue_work(ha->core.shost, work);
+	/* chained work is not subject to SA_HA_DRAINING or
+	 * SAS_HA_REGISTERED, because it is either submitted in the
+	 * workqueue, or known to be submitted from a context that is
+	 * not racing against draining
+	 */
+	scsi_queue_work(ha->core.shost, &sw->work);
 }
 
 static void sas_chain_event(int event, unsigned long *pending,
-			    struct work_struct *work,
+			    struct sas_work *sw,
 			    struct sas_ha_struct *ha)
 {
 	if (!test_and_set_bit(event, pending)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&ha->state_lock, flags);
-		sas_chain_work(ha, work);
+		sas_chain_work(ha, sw);
 		spin_unlock_irqrestore(&ha->state_lock, flags);
 	}
 }
···
 
 	disc->pending = 0;
 	for (i = 0; i < DISC_NUM_EVENTS; i++) {
-		INIT_WORK(&disc->disc_work[i].work, sas_event_fns[i]);
+		INIT_SAS_WORK(&disc->disc_work[i].work, sas_event_fns[i]);
 		disc->disc_work[i].port = port;
 	}
 }

drivers/scsi/libsas/sas_event.c

···
 #include "sas_internal.h"
 #include "sas_dump.h"
 
-void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work)
+void sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw)
 {
 	if (!test_bit(SAS_HA_REGISTERED, &ha->state))
 		return;
 
-	if (test_bit(SAS_HA_DRAINING, &ha->state))
-		list_add(&work->entry, &ha->defer_q);
-	else
-		scsi_queue_work(ha->core.shost, work);
+	if (test_bit(SAS_HA_DRAINING, &ha->state)) {
+		/* add it to the defer list, if not already pending */
+		if (list_empty(&sw->drain_node))
+			list_add(&sw->drain_node, &ha->defer_q);
+	} else
+		scsi_queue_work(ha->core.shost, &sw->work);
 }
 
 static void sas_queue_event(int event, unsigned long *pending,
-			    struct work_struct *work,
+			    struct sas_work *work,
 			    struct sas_ha_struct *ha)
 {
 	if (!test_and_set_bit(event, pending)) {
···
 void __sas_drain_work(struct sas_ha_struct *ha)
 {
 	struct workqueue_struct *wq = ha->core.shost->work_q;
-	struct work_struct *w, *_w;
+	struct sas_work *sw, *_sw;
 
 	set_bit(SAS_HA_DRAINING, &ha->state);
 	/* flush submitters */
···
 
 	spin_lock_irq(&ha->state_lock);
 	clear_bit(SAS_HA_DRAINING, &ha->state);
-	list_for_each_entry_safe(w, _w, &ha->defer_q, entry) {
-		list_del_init(&w->entry);
-		sas_queue_work(ha, w);
+	list_for_each_entry_safe(sw, _sw, &ha->defer_q, drain_node) {
+		list_del_init(&sw->drain_node);
+		sas_queue_work(ha, sw);
 	}
 	spin_unlock_irq(&ha->state_lock);
 }
···
 	int i;
 
 	for (i = 0; i < HA_NUM_EVENTS; i++) {
-		INIT_WORK(&sas_ha->ha_events[i].work, sas_ha_event_fns[i]);
+		INIT_SAS_WORK(&sas_ha->ha_events[i].work, sas_ha_event_fns[i]);
 		sas_ha->ha_events[i].ha = sas_ha;
 	}
 

drivers/scsi/libsas/sas_init.c

···
 
 void sas_hae_reset(struct work_struct *work)
 {
-	struct sas_ha_event *ev =
-		container_of(work, struct sas_ha_event, work);
+	struct sas_ha_event *ev = to_sas_ha_event(work);
 	struct sas_ha_struct *ha = ev->ha;
 
 	clear_bit(HAE_RESET, &ha->pending);
···
 
 static void phy_reset_work(struct work_struct *work)
 {
-	struct sas_phy_data *d = container_of(work, typeof(*d), reset_work);
+	struct sas_phy_data *d = container_of(work, typeof(*d), reset_work.work);
 
 	d->reset_result = transport_sas_phy_reset(d->phy, d->hard_reset);
 }
 
 static void phy_enable_work(struct work_struct *work)
 {
-	struct sas_phy_data *d = container_of(work, typeof(*d), enable_work);
+	struct sas_phy_data *d = container_of(work, typeof(*d), enable_work.work);
 
 	d->enable_result = sas_phy_enable(d->phy, d->enable);
 }
···
 		return -ENOMEM;
 
 	mutex_init(&d->event_lock);
-	INIT_WORK(&d->reset_work, phy_reset_work);
-	INIT_WORK(&d->enable_work, phy_enable_work);
+	INIT_SAS_WORK(&d->reset_work, phy_reset_work);
+	INIT_SAS_WORK(&d->enable_work, phy_enable_work);
 	d->phy = phy;
 	phy->hostdata = d;
 

drivers/scsi/libsas/sas_internal.h

···
 	struct mutex event_lock;
 	int hard_reset;
 	int reset_result;
-	struct work_struct reset_work;
+	struct sas_work reset_work;
 	int enable;
 	int enable_result;
-	struct work_struct enable_work;
+	struct sas_work enable_work;
 };
 
 void sas_scsi_recover_host(struct Scsi_Host *shost);
···
 void sas_porte_link_reset_err(struct work_struct *work);
 void sas_porte_timer_event(struct work_struct *work);
 void sas_porte_hard_reset(struct work_struct *work);
-void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work);
+void sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw);
 
 int sas_notify_lldd_dev_found(struct domain_device *);
 void sas_notify_lldd_dev_gone(struct domain_device *);

drivers/scsi/libsas/sas_phy.c

···
 
 static void sas_phye_loss_of_signal(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PHYE_LOSS_OF_SIGNAL, &phy->phy_events_pending);
···
 
 static void sas_phye_oob_done(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PHYE_OOB_DONE, &phy->phy_events_pending);
···
 
 static void sas_phye_oob_error(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 	struct sas_ha_struct *sas_ha = phy->ha;
 	struct asd_sas_port *port = phy->port;
···
 
 static void sas_phye_spinup_hold(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 	struct sas_ha_struct *sas_ha = phy->ha;
 	struct sas_internal *i =
···
 		phy->error = 0;
 		INIT_LIST_HEAD(&phy->port_phy_el);
 		for (k = 0; k < PORT_NUM_EVENTS; k++) {
-			INIT_WORK(&phy->port_events[k].work,
-				  sas_port_event_fns[k]);
+			INIT_SAS_WORK(&phy->port_events[k].work, sas_port_event_fns[k]);
 			phy->port_events[k].phy = phy;
 		}
 
 		for (k = 0; k < PHY_NUM_EVENTS; k++) {
-			INIT_WORK(&phy->phy_events[k].work,
-				  sas_phy_event_fns[k]);
+			INIT_SAS_WORK(&phy->phy_events[k].work, sas_phy_event_fns[k]);
 			phy->phy_events[k].phy = phy;
 		}
 
···
 		spin_lock_init(&phy->sas_prim_lock);
 		phy->frame_rcvd_size = 0;
 
-		phy->phy = sas_phy_alloc(&sas_ha->core.shost->shost_gendev,
-					 i);
+		phy->phy = sas_phy_alloc(&sas_ha->core.shost->shost_gendev, i);
 		if (!phy->phy)
 			return -ENOMEM;
 

drivers/scsi/libsas/sas_port.c

···
 
 void sas_porte_bytes_dmaed(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PORTE_BYTES_DMAED, &phy->port_events_pending);
···
 
 void sas_porte_broadcast_rcvd(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 	unsigned long flags;
 	u32 prim;
···
 
 void sas_porte_link_reset_err(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PORTE_LINK_RESET_ERR, &phy->port_events_pending);
···
 
 void sas_porte_timer_event(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PORTE_TIMER_EVENT, &phy->port_events_pending);
···
 
 void sas_porte_hard_reset(struct work_struct *work)
 {
-	struct asd_sas_event *ev =
-		container_of(work, struct asd_sas_event, work);
+	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
 	clear_bit(PORTE_HARD_RESET, &phy->port_events_pending);

include/scsi/libsas.h

···
 	struct kref kref;
 };
 
-struct sas_discovery_event {
+struct sas_work {
+	struct list_head drain_node;
 	struct work_struct work;
+};
+
+static inline void INIT_SAS_WORK(struct sas_work *sw, void (*fn)(struct work_struct *))
+{
+	INIT_WORK(&sw->work, fn);
+	INIT_LIST_HEAD(&sw->drain_node);
+}
+
+struct sas_discovery_event {
+	struct sas_work work;
 	struct asd_sas_port *port;
 };
+
+static inline struct sas_discovery_event *to_sas_discovery_event(struct work_struct *work)
+{
+	struct sas_discovery_event *ev = container_of(work, typeof(*ev), work.work);
+
+	return ev;
+}
 
 struct sas_discovery {
 	struct sas_discovery_event disc_work[DISC_NUM_EVENTS];
···
 	struct list_head destroy_list;
 	enum   sas_linkrate linkrate;
 
-	struct work_struct work;
+	struct sas_work work;
 
 /* public: */
 	int id;
···
 };
 
 struct asd_sas_event {
-	struct work_struct work;
+	struct sas_work work;
 	struct asd_sas_phy *phy;
 };
+
+static inline struct asd_sas_event *to_asd_sas_event(struct work_struct *work)
+{
+	struct asd_sas_event *ev = container_of(work, typeof(*ev), work.work);
+
+	return ev;
+}
 
 /* The phy pretty much is controlled by the LLDD.
  * The class only reads those fields.
···
 };
 
 struct sas_ha_event {
-	struct work_struct work;
+	struct sas_work work;
 	struct sas_ha_struct *ha;
 };
+
+static inline struct sas_ha_event *to_sas_ha_event(struct work_struct *work)
+{
+	struct sas_ha_event *ev = container_of(work, typeof(*ev), work.work);
+
+	return ev;
+}
 
 enum sas_ha_state {
 	SAS_HA_REGISTERED,