[SCSI] aacraid: Improved error handling

Received from Mark Salyzyn,

This set of fixes improve error handling stability of the driver. A popular
manifestation of the problems is an NULL pointer reference in the interrupt
handler when referencing portions of the scsi command context, or in the
scsi_done handling when an offlined device is referenced.

The aacraid driver currently does not get notification of orphaned command
completions due to devices going offline. The driver also fails to handle the
commands that are finished by the error handler, and thus can complete again
later at the hands of the adapter causing situations of completion of an
invalid scsi command context. Test Unit Ready calls abort assuming that the
abort was successful, but are not, and thus when the interrupt from the adapter
occurs, they reference invalid command contexts. We add in a TIMED_OUT flag to
inform the aacraid FIB context that the interrupt service should merely release
the driver resources and not complete the command up. We take advantage of this
with the abort handler as well for select abortable commands. And we detect and
react if a command that can not be aborted is currently still outstanding to
the controller when reissued by the retry mechanism.

Signed-off-by: Mark Haverkamp <markh@linux-foundation.org>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

1 files changed, 48 insertions, 3 deletions

diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 3d21d7dd2e5..0c4e27eb652 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -5,7 +5,7 @@
  * based on the old aacraid driver that is..
  * Adaptec aacraid device driver for Linux.
  *
- * Copyright (c) 2000 Adaptec, Inc. (aacraid@adaptec.com)
+ * Copyright (c) 2000-2007 Adaptec, Inc. (aacraid@adaptec.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -172,6 +172,30 @@ MODULE_PARM_DESC(acbsize, "Request a specific adapter control block (FIB) size.
 int expose_physicals = -1;
 module_param(expose_physicals, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(expose_physicals, "Expose physical components of the arrays. -1=protect 0=off, 1=on");
+
+
+static inline int aac_valid_context(struct scsi_cmnd *scsicmd,
+		struct fib *fibptr) {
+	struct scsi_device *device;
+
+	if (unlikely(!scsicmd || !scsicmd->scsi_done )) {
+		dprintk((KERN_WARNING "aac_valid_context: scsi command corrupt\n"))
+;
+                aac_fib_complete(fibptr);
+                aac_fib_free(fibptr);
+                return 0;
+        }
+	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
+	device = scsicmd->device;
+	if (unlikely(!device || !scsi_device_online(device))) {
+		dprintk((KERN_WARNING "aac_valid_context: scsi device corrupt\n"));
+		aac_fib_complete(fibptr);
+		aac_fib_free(fibptr);
+		return 0;
+	}
+	return 1;
+}
+
 /**
  *	aac_get_config_status	-	check the adapter configuration
  *	@common: adapter to query
@@ -342,6 +366,9 @@ static void get_container_name_callback(void *context, struct fib * fibptr)
 	scsicmd = (struct scsi_cmnd *) context;
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
 
+	if (!aac_valid_context(scsicmd, fibptr))
+		return;
+
 	dprintk((KERN_DEBUG "get_container_name_callback[cpu %d]: t = %ld.\n", smp_processor_id(), jiffies));
 	BUG_ON(fibptr == NULL);
 
@@ -431,9 +458,14 @@ static int aac_probe_container_callback2(struct scsi_cmnd * scsicmd)
 
 static int _aac_probe_container2(void * context, struct fib * fibptr)
 {
-	struct scsi_cmnd * scsicmd = (struct scsi_cmnd *)context;
-	struct fsa_dev_info *fsa_dev_ptr = ((struct aac_dev *)(scsicmd->device->host->hostdata))->fsa_dev;
+	struct fsa_dev_info *fsa_dev_ptr;
 	int (*callback)(struct scsi_cmnd *);
+	struct scsi_cmnd * scsicmd = (struct scsi_cmnd *)context;
+
+	if (!aac_valid_context(scsicmd, fibptr))
+		return 0;
+
+	fsa_dev_ptr = ((struct aac_dev *)(scsicmd->device->host->hostdata))->fsa_dev;
 
 	scsicmd->SCp.Status = 0;
 	if (fsa_dev_ptr) {
@@ -477,6 +509,9 @@ static int _aac_probe_container1(void * context, struct fib * fibptr)
 	scsicmd = (struct scsi_cmnd *) context;
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
 
+	if (!aac_valid_context(scsicmd, fibptr))
+		return 0;
+
 	aac_fib_init(fibptr);
 
 	dinfo = (struct aac_query_mount *)fib_data(fibptr);
@@ -1287,6 +1322,9 @@ static void io_callback(void *context, struct fib * fibptr)
 	scsicmd = (struct scsi_cmnd *) context;
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
 
+	if (!aac_valid_context(scsicmd, fibptr))
+		return;
+
 	dev = (struct aac_dev *)scsicmd->device->host->hostdata;
 	cid = scmd_id(scsicmd);
 
@@ -1534,6 +1572,9 @@ static void synchronize_callback(void *context, struct fib *fibptr)
 	cmd = context;
 	cmd->SCp.phase = AAC_OWNER_MIDLEVEL;
 
+	if (!aac_valid_context(cmd, fibptr))
+		return;
+
 	dprintk((KERN_DEBUG "synchronize_callback[cpu %d]: t = %ld.\n", 
 				smp_processor_id(), jiffies));
 	BUG_ON(fibptr == NULL);
@@ -2086,6 +2127,10 @@ static void aac_srb_callback(void *context, struct fib * fibptr)
 
 	scsicmd = (struct scsi_cmnd *) context;
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
+
+	if (!aac_valid_context(scsicmd, fibptr))
+		return;
+
 	dev = (struct aac_dev *)scsicmd->device->host->hostdata;
 
 	BUG_ON(fibptr == NULL);