aboutsummaryrefslogtreecommitdiff
path: root/drivers/scsi/pm8001
diff options
context:
space:
mode:
authorDan Carpenter <error27@gmail.com>2010-04-23 14:01:04 +0200
committerJames Bottomley <James.Bottomley@suse.de>2010-05-02 11:04:23 -0400
commit2471b894068ec59ab3012e788401b345ef459e49 (patch)
tree09a540d9c6f5b0c7e2bd80ad12f3b6864e7d142d /drivers/scsi/pm8001
parentdaa142d1773dd3a986f02a8a4da929608d24daaa (diff)
[SCSI] pm8001: potential null dereference in pm8001_dev_gone_notify()
In the original code we dereferenced "pm8001_dev" before checking if it was null. This patch moves the dereference inside the condition. This was found by a static checker (smatch). I looked, but I couldn't tell if "pm8001_dev" dev was ever actually null. The approach in this patch seemed like the safest response. Signed-off-by: Dan Carpenter <error27@gmail.com> Acked-by: Jack Wang <jack_wang@usish.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Diffstat (limited to 'drivers/scsi/pm8001')
-rw-r--r--drivers/scsi/pm8001/pm8001_sas.c4
1 files changed, 3 insertions, 1 deletions
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index bff4f5139b9..cd02ceaf67f 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -885,11 +885,13 @@ static void pm8001_dev_gone_notify(struct domain_device *dev)
u32 tag;
struct pm8001_hba_info *pm8001_ha;
struct pm8001_device *pm8001_dev = dev->lldd_dev;
- u32 device_id = pm8001_dev->device_id;
+
pm8001_ha = pm8001_find_ha_by_dev(dev);
spin_lock_irqsave(&pm8001_ha->lock, flags);
pm8001_tag_alloc(pm8001_ha, &tag);
if (pm8001_dev) {
+ u32 device_id = pm8001_dev->device_id;
+
PM8001_DISC_DBG(pm8001_ha,
pm8001_printk("found dev[%d:%x] is gone.\n",
pm8001_dev->device_id, pm8001_dev->dev_type));