[SCSI] aacraid: fix File System going into read-only mode

These particular problems were reported by Cisco and SAP and customers
as well. Cisco reported on RHEL4 U6 and SAP reported on SLES9 SP4 and
SLES10 SP2. We added these fixes on RHEL4 U6 and gave a private build
to IBM and Cisco. Cisco and IBM tested it for more than 15 days and
they reported that they did not see the issue so far. Before the fix,
Cisco used to see the issue within 5 days. We generated a patch for
SLES9 SP4 and SLES10 SP2 and submitted to Novell. Novell applied the
patch and gave a test build to SAP. SAP tested and reported that the
build is working properly.

We also tested in our lab using the tools "dishogsync", which is IO
stress tool and the tool was provided by Cisco.

Issue1:  File System going into read-only mode

Root cause: The driver tends to not free the memory (FIB) when the
management request exits prematurely. The accumulation of such
un-freed memory causes the driver to fail to allocate anymore memory
(FIB) and hence return 0x70000 value to the upper layer, which puts
the file system into read only mode.

Fix details: The fix makes sure to free the memory (FIB) even if the
request exits prematurely hence ensuring the driver wouldn't run out
of memory (FIBs).


Issue2: False Raid Alert occurs

When the Physical Drives and Logical drives are reported as deleted or
added, even though there is no change done on the system

Root cause: Driver IOCTLs is signaled with EINTR while waiting on
response from the lower layers. Returning "EINTR" will never initiate
internal retry.

Fix details: The issue was fixed by replacing "EINTR" with
"ERESTARTSYS" for mid-layer retries.

Signed-off-by: Penchala Narasimha Reddy <ServeRAIDDriver@hcl.in>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

1 files changed, 61 insertions, 11 deletions

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 956261f25181..94d2954d79ae 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -189,7 +189,14 @@ struct fib *aac_fib_alloc(struct aac_dev *dev)
 
 void aac_fib_free(struct fib *fibptr)
 {
-        unsigned long flags;
+        unsigned long flags, flagsv;
+
+        spin_lock_irqsave(&fibptr->event_lock, flagsv);
+        if (fibptr->done == 2) {
+                spin_unlock_irqrestore(&fibptr->event_lock, flagsv);
+                return;
+        }
+        spin_unlock_irqrestore(&fibptr->event_lock, flagsv);
 
         spin_lock_irqsave(&fibptr->dev->fib_lock, flags);
         if (unlikely(fibptr->flags & FIB_CONTEXT_FLAG_TIMED_OUT))
@@ -390,6 +397,8 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
         struct hw_fib * hw_fib = fibptr->hw_fib_va;
         unsigned long flags = 0;
         unsigned long qflags;
+        unsigned long mflags = 0;
+
 
         if (!(hw_fib->header.XferState & cpu_to_le32(HostOwned)))
                 return -EBUSY;
@@ -471,9 +480,31 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
         if (!dev->queues)
                 return -EBUSY;
 
-        if(wait)
+        if (wait) {
+
+                spin_lock_irqsave(&dev->manage_lock, mflags);
+                if (dev->management_fib_count >= AAC_NUM_MGT_FIB) {
+                        printk(KERN_INFO "No management Fibs Available:%d\n",
+                                                dev->management_fib_count);
+                        spin_unlock_irqrestore(&dev->manage_lock, mflags);
+                        return -EBUSY;
+                }
+                dev->management_fib_count++;
+                spin_unlock_irqrestore(&dev->manage_lock, mflags);
                 spin_lock_irqsave(&fibptr->event_lock, flags);
-        aac_adapter_deliver(fibptr);
+        }
+
+        if (aac_adapter_deliver(fibptr) != 0) {
+                printk(KERN_ERR "aac_fib_send: returned -EBUSY\n");
+                if (wait) {
+                        spin_unlock_irqrestore(&fibptr->event_lock, flags);
+                        spin_lock_irqsave(&dev->manage_lock, mflags);
+                        dev->management_fib_count--;
+                        spin_unlock_irqrestore(&dev->manage_lock, mflags);
+                }
+                return -EBUSY;
+        }
+
 
         /*
          *      If the caller wanted us to wait for response wait now.
@@ -516,14 +547,15 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
                                 udelay(5);
                         }
                 } else if (down_interruptible(&fibptr->event_wait)) {
-                        fibptr->done = 2;
-                        up(&fibptr->event_wait);
+                        /* Do nothing ... satisfy
+                         * down_interruptible must_check */
                 }
+
                 spin_lock_irqsave(&fibptr->event_lock, flags);
-                if ((fibptr->done == 0) || (fibptr->done == 2)) {
+                if (fibptr->done == 0) {
                         fibptr->done = 2; /* Tell interrupt we aborted */
                         spin_unlock_irqrestore(&fibptr->event_lock, flags);
-                        return -EINTR;
+                        return -ERESTARTSYS;
                 }
                 spin_unlock_irqrestore(&fibptr->event_lock, flags);
                 BUG_ON(fibptr->done == 0);
@@ -689,6 +721,7 @@ int aac_fib_adapter_complete(struct fib *fibptr, unsigned short size)
 
 int aac_fib_complete(struct fib *fibptr)
 {
+        unsigned long flags;
         struct hw_fib * hw_fib = fibptr->hw_fib_va;
 
         /*
@@ -709,6 +742,13 @@ int aac_fib_complete(struct fib *fibptr)
          *      command is complete that we had sent to the adapter and this
          *      cdb could be reused.
          */
+        spin_lock_irqsave(&fibptr->event_lock, flags);
+        if (fibptr->done == 2) {
+                spin_unlock_irqrestore(&fibptr->event_lock, flags);
+                return 0;
+        }
+        spin_unlock_irqrestore(&fibptr->event_lock, flags);
+
         if((hw_fib->header.XferState & cpu_to_le32(SentFromHost)) &&
                 (hw_fib->header.XferState & cpu_to_le32(AdapterProcessed)))
         {
@@ -1355,7 +1395,10 @@ int aac_reset_adapter(struct aac_dev * aac, int forced)
 
                         if (status >= 0)
                                 aac_fib_complete(fibctx);
-                        aac_fib_free(fibctx);
+                        /* FIB should be freed only after getting
+                         * the response from the F/W */
+                        if (status != -ERESTARTSYS)
+                                aac_fib_free(fibctx);
                 }
         }
 
@@ -1759,6 +1802,7 @@ int aac_command_thread(void *data)
                                 struct fib *fibptr;
 
                                 if ((fibptr = aac_fib_alloc(dev))) {
+                                        int status;
                                         __le32 *info;
 
                                         aac_fib_init(fibptr);
@@ -1769,15 +1813,21 @@ int aac_command_thread(void *data)
 
                                         *info = cpu_to_le32(now.tv_sec);
 
-                                        (void)aac_fib_send(SendHostTime,
+                                        status = aac_fib_send(SendHostTime,
                                                 fibptr,
                                                 sizeof(*info),
                                                 FsaNormal,
                                                 1, 1,
                                                 NULL,
                                                 NULL);
-                                        aac_fib_complete(fibptr);
-                                        aac_fib_free(fibptr);
+                                        /* Do not set XferState to zero unless
+                                         * receives a response from F/W */
+                                        if (status >= 0)
+                                                aac_fib_complete(fibptr);
+                                        /* FIB should be freed only after
+                                         * getting the response from the F/W */
+                                        if (status != -ERESTARTSYS)
+                                                aac_fib_free(fibptr);
                                 }
                                 difference = (long)(unsigned)update_interval*HZ;
                         } else {