[PATCH] ipmi: kcs error0 delay

BMCs can get into ERROR0 state while flashing new firmware, particularly while
the BMC is erasing the next flash block, which may take a just under 2 seconds
on a Dell PowerEdge 2800 (1.75 seconds typical), during which time the
single-threaded firmware may not be able to process new commands.  In
particular, clearing OBF may not take effect immediately.

We want it to delay in ERROR0 after clearing OBF a bit waiting for OBF to
actually be clear before proceeding.

This introduces a new return value from the LLDD's event loop,
SI_SM_CALL_WITH_TICK_DELAY.  This means the calling thread/timer should
schedule_timeout() at least 1 tick, rather than busy-wait.  This is a longer
delay than SI_SM_CALL_WITH_DELAY, which is typically a 250us busy-wait.

Signed-off-by: Matt Domsch <Matt_Domsch@dell.com>
Signed-off-by: Corey Minyard <minyard@acm.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 8 insertions, 0 deletions

diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c
index dc83365ede4a..da1554194d3d 100644
--- a/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -41,6 +41,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/string.h>
+#include <linux/jiffies.h>
 #include <linux/ipmi_msgdefs.h>         /* for completion codes */
 #include "ipmi_si_sm.h"
 
@@ -99,6 +100,7 @@ enum kcs_states {
 #define IBF_RETRY_TIMEOUT 1000000
 #define OBF_RETRY_TIMEOUT 1000000
 #define MAX_ERROR_RETRIES 10
+#define ERROR0_OBF_WAIT_JIFFIES (2*HZ)
 
 struct si_sm_data
 {
@@ -115,6 +117,7 @@ struct si_sm_data
         unsigned int  error_retries;
         long          ibf_timeout;
         long          obf_timeout;
+        unsigned long  error0_timeout;
 };
 
 static unsigned int init_kcs_data(struct si_sm_data *kcs,
@@ -187,6 +190,7 @@ static inline void start_error_recovery(struct si_sm_data *kcs, char *reason)
                         printk(KERN_DEBUG "ipmi_kcs_sm: kcs hosed: %s\n", reason);
                 kcs->state = KCS_HOSED;
         } else {
+                kcs->error0_timeout = jiffies + ERROR0_OBF_WAIT_JIFFIES;
                 kcs->state = KCS_ERROR0;
         }
 }
@@ -423,6 +427,10 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 
         case KCS_ERROR0:
                 clear_obf(kcs, status);
+                status = read_status(kcs);
+                if  (GET_STATUS_OBF(status)) /* controller isn't responding */
+                        if (time_before(jiffies, kcs->error0_timeout))
+                                return SI_SM_CALL_WITH_TICK_DELAY;
                 write_cmd(kcs, KCS_GET_STATUS_ABORT);
                 kcs->state = KCS_ERROR1;
                 break;