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>

1 files changed, 32 insertions, 1 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 ---------- */