IB/mthca: Recover from catastrophic errors

Trigger device remove and then add when a catastrophic error is
detected in hardware.  This, in turn, will cause a device reset, which
we hope will recover from the catastrophic condition.

Since this might interefere with debugging the root cause, add a
module option to suppress this behaviour.

Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index 33bd0b8bfd13..fe5cecf70fed 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -45,6 +45,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/timer.h>
 #include <linux/mutex.h>
+#include <linux/list.h>
 
 #include <asm/semaphore.h>
 
@@ -283,8 +284,11 @@ struct mthca_catas_err {
         unsigned long           stop;
         u32                     size;
         struct timer_list       timer;
+        struct list_head        list;
 };
 
+extern struct mutex mthca_device_mutex;
+
 struct mthca_dev {
         struct ib_device  ib_dev;
         struct pci_dev   *pdev;
@@ -450,6 +454,9 @@ void mthca_unregister_device(struct mthca_dev *dev);
 
 void mthca_start_catas_poll(struct mthca_dev *dev);
 void mthca_stop_catas_poll(struct mthca_dev *dev);
+int __mthca_restart_one(struct pci_dev *pdev);
+int mthca_catas_init(void);
+void mthca_catas_cleanup(void);
 
 int mthca_uar_alloc(struct mthca_dev *dev, struct mthca_uar *uar);
 void mthca_uar_free(struct mthca_dev *dev, struct mthca_uar *uar);