IPoIB: Refresh paths instead of flushing them on SM change events

The patch tries to solve the problem of device going down and paths being
flushed on an SM change event. The method is to mark the paths as candidates for
refresh (by setting the new valid flag to 0), and wait for an ARP
probe a new path record query.

The solution requires a different and less intrusive handling of SM
change event. For that, the second argument of the flush function
changes its meaning from a boolean flag to a level.  In most cases, SM
failover doesn't cause LID change so traffic won't stop.  In the rare
cases of LID change, the remote host (the one that hadn't changed its
LID) will lose connectivity until paths are refreshed. This is no
worse than the current state.  In fact, preventing the device from
going down saves packets that otherwise would be lost.

Signed-off-by: Moni Levy <monil@voltaire.com>
Signed-off-by: Moni Shoua <monis@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 14 insertions, 3 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 2c522572e3c5..bb19587c5eaf 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -54,6 +54,12 @@
 
 /* constants */
 
+enum ipoib_flush_level {
+        IPOIB_FLUSH_LIGHT,
+        IPOIB_FLUSH_NORMAL,
+        IPOIB_FLUSH_HEAVY
+};
+
 enum {
         IPOIB_ENCAP_LEN           = 4,
 
@@ -284,10 +290,11 @@ struct ipoib_dev_priv {
 
         struct delayed_work pkey_poll_task;
         struct delayed_work mcast_task;
-        struct work_struct flush_task;
+        struct work_struct flush_light;
+        struct work_struct flush_normal;
+        struct work_struct flush_heavy;
         struct work_struct restart_task;
         struct delayed_work ah_reap_task;
-        struct work_struct pkey_event_task;
 
         struct ib_device *ca;
         u8                port;
@@ -369,6 +376,7 @@ struct ipoib_path {
 
         struct rb_node        rb_node;
         struct list_head      list;
+        int                   valid;
 };
 
 struct ipoib_neigh {
@@ -433,11 +441,14 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
                 struct ipoib_ah *address, u32 qpn);
 void ipoib_reap_ah(struct work_struct *work);
 
+void ipoib_mark_paths_invalid(struct net_device *dev);
 void ipoib_flush_paths(struct net_device *dev);
 struct ipoib_dev_priv *ipoib_intf_alloc(const char *format);
 
 int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
-void ipoib_ib_dev_flush(struct work_struct *work);
+void ipoib_ib_dev_flush_light(struct work_struct *work);
+void ipoib_ib_dev_flush_normal(struct work_struct *work);
+void ipoib_ib_dev_flush_heavy(struct work_struct *work);
 void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);