[libsas PATCH v10 4/9] libsas: enforce eh strategy handlers only in eh context

[Dan Williams <dan.j.williams@intel.com>]

The strategy handlers may be called in places that are problematic for
libsas (i.e. sata resets outside of domain revalidation filtering /
libata link recovery), or problematic for userspace (non-blocking ioctl
to sleeping reset functions).  However, these routines are also called
for eh escalations and recovery of scsi_eh_prep_cmnd(), so permit them
as long as we are running in the host's error handler, otherwise arrange
for them to be triggered in eh_context.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/scsi/libsas/sas_discover.c  |   11 +++
 drivers/scsi/libsas/sas_init.c      |    2 +
 drivers/scsi/libsas/sas_scsi_host.c |  121 ++++++++++++++++++++++++++++++++++-
 include/scsi/libsas.h               |   10 +++
 4 files changed, 140 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index a730ac9..3c8527d 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -39,6 +39,7 @@ void sas_init_dev(struct domain_device *dev)
 {
         switch (dev->dev_type) {
         case SAS_END_DEV:
+		INIT_LIST_HEAD(&dev->ssp_dev.eh_list_node);
                 break;
         case EDGE_DEV:
         case FANOUT_DEV:
@@ -274,6 +275,8 @@ void sas_free_device(struct kref *kref)
 
 static void sas_unregister_common_dev(struct asd_sas_port *port, struct domain_device *dev)
 {
+	struct sas_ha_struct *ha = port->ha;
+
 	sas_notify_lldd_dev_gone(dev);
 	if (!dev->parent)
 		dev->port->port_dev = NULL;
@@ -286,6 +289,14 @@ static void sas_unregister_common_dev(struct asd_sas_port *port, struct domain_d
 		sas_ata_end_eh(dev->sata_dev.ap);
 	spin_unlock_irq(&port->dev_list_lock);
 
+	spin_lock_irq(&ha->lock);
+	if (dev->dev_type == SAS_END_DEV &&
+	    !list_empty(&dev->ssp_dev.eh_list_node)) {
+		list_del_init(&dev->ssp_dev.eh_list_node);
+		ha->eh_active--;
+	}
+	spin_unlock_irq(&ha->lock);
+
 	sas_put_device(dev);
 }
 
diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c
index 6909fef..1bbab3d 100644
--- a/drivers/scsi/libsas/sas_init.c
+++ b/drivers/scsi/libsas/sas_init.c
@@ -116,7 +116,9 @@ int sas_register_ha(struct sas_ha_struct *sas_ha)
 	set_bit(SAS_HA_REGISTERED, &sas_ha->state);
 	spin_lock_init(&sas_ha->lock);
 	mutex_init(&sas_ha->drain_mutex);
+	init_waitqueue_head(&sas_ha->eh_wait_q);
 	INIT_LIST_HEAD(&sas_ha->defer_q);
+	INIT_LIST_HEAD(&sas_ha->eh_dev_q);
 
 	error = sas_register_phys(sas_ha);
 	if (error) {
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index cd63d80..50a18a6 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -460,14 +460,88 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev)
 }
 EXPORT_SYMBOL_GPL(sas_get_local_phy);
 
+static void sas_wait_eh(struct domain_device *dev)
+{
+	struct sas_ha_struct *ha = dev->port->ha;
+	DEFINE_WAIT(wait);
+
+	if (dev_is_sata(dev)) {
+		ata_port_wait_eh(dev->sata_dev.ap);
+		return;
+	}
+ retry:
+	spin_lock_irq(&ha->lock);
+
+	while (test_bit(SAS_DEV_EH_PENDING, &dev->state)) {
+		prepare_to_wait(&ha->eh_wait_q, &wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock_irq(&ha->lock);
+		schedule();
+		spin_lock_irq(&ha->lock);
+	}
+	finish_wait(&ha->eh_wait_q, &wait);
+
+	spin_unlock_irq(&ha->lock);
+
+	/* make sure SCSI EH is complete */
+	if (scsi_host_in_recovery(ha->core.shost)) {
+		msleep(10);
+		goto retry;
+	}
+}
+EXPORT_SYMBOL(sas_wait_eh);
+
+static int sas_queue_reset(struct domain_device *dev, int reset_type, int lun, int wait)
+{
+	struct sas_ha_struct *ha = dev->port->ha;
+	int scheduled = 0, tries = 100;
+
+	/* ata: promote lun reset to bus reset */
+	if (dev_is_sata(dev)) {
+		sas_ata_schedule_reset(dev);
+		if (wait)
+			sas_ata_wait_eh(dev);
+		return SUCCESS;
+	}
+
+	while (!scheduled && tries--) {
+		spin_lock_irq(&ha->lock);
+		if (!test_bit(SAS_DEV_EH_PENDING, &dev->state) &&
+		    !test_bit(reset_type, &dev->state)) {
+			scheduled = 1;
+			ha->eh_active++;
+			list_add_tail(&dev->ssp_dev.eh_list_node, &ha->eh_dev_q);
+			set_bit(SAS_DEV_EH_PENDING, &dev->state);
+			set_bit(reset_type, &dev->state);
+			int_to_scsilun(lun, &dev->ssp_dev.reset_lun);
+			scsi_schedule_eh(ha->core.shost);
+		}
+		spin_unlock_irq(&ha->lock);
+
+		if (wait)
+			sas_wait_eh(dev);
+
+		if (scheduled)
+			return SUCCESS;
+	}
+
+	SAS_DPRINTK("%s reset of %s failed\n",
+		    reset_type == SAS_DEV_LU_RESET ? "LUN" : "Bus",
+		    dev_name(&dev->rphy->dev));
+
+	return FAILED;
+}
+
 /* Attempt to send a LUN reset message to a device */
 int sas_eh_device_reset_handler(struct scsi_cmnd *cmd)
 {
-	struct domain_device *dev = cmd_to_domain_dev(cmd);
-	struct sas_internal *i =
-		to_sas_internal(dev->port->ha->core.shost->transportt);
-	struct scsi_lun lun;
 	int res;
+	struct scsi_lun lun;
+	struct Scsi_Host *host = cmd->device->host;
+	struct domain_device *dev = cmd_to_domain_dev(cmd);
+	struct sas_internal *i = to_sas_internal(host->transportt);
+
+	if (current != host->ehandler)
+		return sas_queue_reset(dev, SAS_DEV_LU_RESET, cmd->device->lun, 0);
 
 	int_to_scsilun(cmd->device->lun, &lun);
 
@@ -486,8 +560,12 @@ int sas_eh_bus_reset_handler(struct scsi_cmnd *cmd)
 {
 	struct domain_device *dev = cmd_to_domain_dev(cmd);
 	struct sas_phy *phy = sas_get_local_phy(dev);
+	struct Scsi_Host *host = cmd->device->host;
 	int res;
 
+	if (current != host->ehandler)
+		return sas_queue_reset(dev, SAS_DEV_RESET, 0, 0);
+
 	res = sas_phy_reset(phy, 1);
 	if (res)
 		SAS_DPRINTK("Bus reset of %s failed 0x%x\n",
@@ -667,6 +745,39 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 	goto out;
 }
 
+static void sas_eh_handle_resets(struct Scsi_Host *shost)
+{
+	struct sas_ha_struct *ha = SHOST_TO_SAS_HA(shost);
+	struct sas_internal *i = to_sas_internal(shost->transportt);
+
+	/* handle directed resets to sas devices */
+	spin_lock_irq(&ha->lock);
+	while (!list_empty(&ha->eh_dev_q)) {
+		struct domain_device *dev;
+		struct ssp_device *ssp;
+
+		ssp = list_entry(ha->eh_dev_q.next, typeof(*ssp), eh_list_node);
+		list_del_init(&ssp->eh_list_node);
+		dev = container_of(ssp, typeof(*dev), ssp_dev);
+		kref_get(&dev->kref);
+		WARN_ONCE(dev_is_sata(dev), "ssp reset to ata device?\n");
+
+		spin_unlock_irq(&ha->lock);
+
+		if (test_and_clear_bit(SAS_DEV_LU_RESET, &dev->state))
+			i->dft->lldd_lu_reset(dev, ssp->reset_lun.scsi_lun);
+
+		if (test_and_clear_bit(SAS_DEV_RESET, &dev->state))
+			i->dft->lldd_I_T_nexus_reset(dev);
+
+		sas_put_device(dev);
+		spin_lock_irq(&ha->lock);
+		clear_bit(SAS_DEV_EH_PENDING, &dev->state);
+		ha->eh_active--;
+	}
+	spin_unlock_irq(&ha->lock);
+}
+
 
 void sas_scsi_recover_host(struct Scsi_Host *shost)
 {
@@ -709,6 +820,8 @@ out:
 	if (ha->lldd_max_execute_num > 1)
 		wake_up_process(ha->core.queue_thread);
 
+	sas_eh_handle_resets(shost);
+
 	/* now link into libata eh --- if we have any ata devices */
 	sas_ata_strategy_handler(shost);
 
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index c0c94b3..1b14d80 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -174,10 +174,17 @@ struct sata_device {
 	struct ata_taskfile tf;
 };
 
+struct ssp_device {
+	struct list_head eh_list_node; /* pending a user requested eh action */
+	struct scsi_lun reset_lun;
+};
+
 enum {
 	SAS_DEV_GONE,
 	SAS_DEV_DESTROY,
 	SAS_DEV_EH_PENDING,
+	SAS_DEV_LU_RESET,
+	SAS_DEV_RESET,
 };
 
 struct domain_device {
@@ -211,6 +218,7 @@ struct domain_device {
         union {
                 struct expander_device ex_dev;
                 struct sata_device     sata_dev; /* STP & directly attached */
+		struct ssp_device      ssp_dev;
         };
 
         void *lldd_dev;
@@ -387,6 +395,8 @@ struct sas_ha_struct {
 	unsigned long	  state;
 	spinlock_t 	  lock;
 	int		  eh_active;
+	wait_queue_head_t eh_wait_q;
+	struct list_head  eh_dev_q;
 
 	struct mutex disco_mutex;