scsi: libsas: shut down the PHY if events reached the threshold

If the PHY burst too many events, we will alloc a lot of events for the
worker. This may leads to memory exhaustion.

Dan Williams suggested to shut down the PHY if the events reached the
threshold, because in this case the PHY may have gone into some
erroneous state. Users can re-enable the PHY by sysfs if they want.

We cannot use the fixed memory pool because if we run out of events, the
shut down event and loss of signal event will lost too. The events still
need to be allocated and processed in this case.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
CC: John Garry <john.garry@huawei.com>
CC: Johannes Thumshirn <jthumshirn@suse.de>
CC: Ewan Milne <emilne@redhat.com>
CC: Christoph Hellwig <hch@lst.de>
CC: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 64 insertions, 2 deletions

diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c
index e04f6d6f5aff..22bfc025ae81 100644
--- a/drivers/scsi/libsas/sas_init.c
+++ b/drivers/scsi/libsas/sas_init.c
@@ -123,6 +123,8 @@ int sas_register_ha(struct sas_ha_struct *sas_ha)
 	INIT_LIST_HEAD(&sas_ha->defer_q);
 	INIT_LIST_HEAD(&sas_ha->eh_dev_q);
 
+	sas_ha->event_thres = SAS_PHY_SHUTDOWN_THRES;
+
 	error = sas_register_phys(sas_ha);
 	if (error) {
 		printk(KERN_NOTICE "couldn't register sas phys:%d\n", error);
@@ -557,14 +559,43 @@ EXPORT_SYMBOL_GPL(sas_domain_attach_transport);
 
 struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy)
 {
+	struct asd_sas_event *event;
 	gfp_t flags = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL;
+	struct sas_ha_struct *sas_ha = phy->ha;
+	struct sas_internal *i =
+		to_sas_internal(sas_ha->core.shost->transportt);
+
+	event = kmem_cache_zalloc(sas_event_cache, flags);
+	if (!event)
+		return NULL;
 
-	return kmem_cache_zalloc(sas_event_cache, flags);
+	atomic_inc(&phy->event_nr);
+
+	if (atomic_read(&phy->event_nr) > phy->ha->event_thres) {
+		if (i->dft->lldd_control_phy) {
+			if (cmpxchg(&phy->in_shutdown, 0, 1) == 0) {
+				sas_printk("The phy%02d bursting events, shut it down.\n",
+					phy->id);
+				sas_notify_phy_event(phy, PHYE_SHUTDOWN);
+			}
+		} else {
+			/* Do not support PHY control, stop allocating events */
+			WARN_ONCE(1, "PHY control not supported.\n");
+			kmem_cache_free(sas_event_cache, event);
+			atomic_dec(&phy->event_nr);
+			event = NULL;
+		}
+	}
+
+	return event;
 }
 
 void sas_free_event(struct asd_sas_event *event)
 {
+	struct asd_sas_phy *phy = event->phy;
+
 	kmem_cache_free(sas_event_cache, event);
+	atomic_dec(&phy->event_nr);
 }
 
 /* ---------- SAS Class register/unregister ---------- */
diff --git a/drivers/scsi/libsas/sas_phy.c b/drivers/scsi/libsas/sas_phy.c
index 59f82929b0a3..bf3e1b979ca6 100644
--- a/drivers/scsi/libsas/sas_phy.c
+++ b/drivers/scsi/libsas/sas_phy.c
@@ -35,6 +35,7 @@ static void sas_phye_loss_of_signal(struct work_struct *work)
 	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
+	phy->in_shutdown = 0;
 	phy->error = 0;
 	sas_deform_port(phy, 1);
 }
@@ -44,6 +45,7 @@ static void sas_phye_oob_done(struct work_struct *work)
 	struct asd_sas_event *ev = to_asd_sas_event(work);
 	struct asd_sas_phy *phy = ev->phy;
 
+	phy->in_shutdown = 0;
 	phy->error = 0;
 }
 
@@ -105,6 +107,28 @@ static void sas_phye_resume_timeout(struct work_struct *work)
 }
 
 
+static void sas_phye_shutdown(struct work_struct *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 =
+		to_sas_internal(sas_ha->core.shost->transportt);
+
+	if (phy->enabled) {
+		int ret;
+
+		phy->error = 0;
+		phy->enabled = 0;
+		ret = i->dft->lldd_control_phy(phy, PHY_FUNC_DISABLE, NULL);
+		if (ret)
+			sas_printk("lldd disable phy%02d returned %d\n",
+				phy->id, ret);
+	} else
+		sas_printk("phy%02d is not enabled, cannot shutdown\n",
+			phy->id);
+}
+
 /* ---------- Phy class registration ---------- */
 
 int sas_register_phys(struct sas_ha_struct *sas_ha)
@@ -116,6 +140,7 @@ int sas_register_phys(struct sas_ha_struct *sas_ha)
 		struct asd_sas_phy *phy = sas_ha->sas_phy[i];
 
 		phy->error = 0;
+		atomic_set(&phy->event_nr, 0);
 		INIT_LIST_HEAD(&phy->port_phy_el);
 
 		phy->port = NULL;
@@ -151,5 +176,5 @@ const work_func_t sas_phy_event_fns[PHY_NUM_EVENTS] = {
 	[PHYE_OOB_ERROR] = sas_phye_oob_error,
 	[PHYE_SPINUP_HOLD] = sas_phye_spinup_hold,
 	[PHYE_RESUME_TIMEOUT] = sas_phye_resume_timeout,
-
+	[PHYE_SHUTDOWN] = sas_phye_shutdown,
 };
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index ee1b25299dd6..de8f043475c2 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -75,6 +75,7 @@ enum phy_event {
 	PHYE_OOB_ERROR,
 	PHYE_SPINUP_HOLD,             /* hot plug SATA, no COMWAKE sent */
 	PHYE_RESUME_TIMEOUT,
+	PHYE_SHUTDOWN,
 	PHY_NUM_EVENTS,
 };
 
@@ -311,12 +312,15 @@ static inline void INIT_SAS_EVENT(struct asd_sas_event *ev,
 	ev->event = event;
 }
 
+#define SAS_PHY_SHUTDOWN_THRES   1024
 
 /* The phy pretty much is controlled by the LLDD.
  * The class only reads those fields.
  */
 struct asd_sas_phy {
 /* private: */
+	atomic_t event_nr;
+	int in_shutdown;
 	int error;
 	int suspended;
 
@@ -404,6 +408,8 @@ struct sas_ha_struct {
 
 	struct list_head eh_done_q;  /* complete via scsi_eh_flush_done_q */
 	struct list_head eh_ata_q; /* scmds to promote from sas to ata eh */
+
+	int event_thres;
 };
 
 #define SHOST_TO_SAS_HA(_shost) (*(struct sas_ha_struct **)(_shost)->hostdata)