cciss: Ignore stale commands after reboot

When doing an unexpected shutdown like kexec the cciss
firmware might still have some commands in flight, which
it is trying to complete.
The driver is doing it's best on resetting the HBA,
but sadly there's a firmware issue causing the firmware
_not_ to abort or drop old commands.
So the firmware will send us commands which we haven't
accounted for, causing the driver to panic.

With this patch we're just ignoring these commands as
there is nothing we could be doing with them anyway.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Mike Miller <mike.miller@hp.com>
Signed-off-by: Jens Axboe <axboe@carl.(none)>

diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index c7a527c..65a0655 100644 (file)
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -226,8 +226,18 @@ static inline void addQ(struct hlist_head *list, CommandList_struct *c)
 
 static inline void removeQ(CommandList_struct *c)
 {
-       if (WARN_ON(hlist_unhashed(&c->list)))
+       /*
+        * After kexec/dump some commands might still
+        * be in flight, which the firmware will try
+        * to complete. Resetting the firmware doesn't work
+        * with old fw revisions, so we have to mark
+        * them off as 'stale' to prevent the driver from
+        * falling over.
+        */
+       if (WARN_ON(hlist_unhashed(&c->list))) {
+               c->cmd_type = CMD_MSG_STALE;
                return;
+       }
 
        hlist_del_init(&c->list);
 }
@@ -4246,7 +4256,8 @@ static void fail_all_cmds(unsigned long ctlr)
        while (!hlist_empty(&h->cmpQ)) {
                c = hlist_entry(h->cmpQ.first, CommandList_struct, list);
                removeQ(c);
-               c->err_info->CommandStatus = CMD_HARDWARE_ERR;
+               if (c->cmd_type != CMD_MSG_STALE)
+                       c->err_info->CommandStatus = CMD_HARDWARE_ERR;
                if (c->cmd_type == CMD_RWREQ) {
                        complete_command(h, c, 0);
                } else if (c->cmd_type == CMD_IOCTL_PEND)

diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h
index cd665b0..dbaed1e 100644 (file)
--- a/drivers/block/cciss_cmd.h
+++ b/drivers/block/cciss_cmd.h
@@ -274,6 +274,7 @@ typedef struct _ErrorInfo_struct {
 #define CMD_SCSI       0x03
 #define CMD_MSG_DONE   0x04
 #define CMD_MSG_TIMEOUT 0x05
+#define CMD_MSG_STALE  0xff
 
 /* This structure needs to be divisible by 8 for new
  * indexing method.