summaryrefslogtreecommitdiffstats
path: root/drivers/scsi/scsi.c
diff options
context:
space:
mode:
authorJames Bottomley <James.Bottomley@steeleye.com>2005-08-05 21:45:40 -0500
committerJames Bottomley <jejb@mulgrave.(none)>2005-08-08 09:55:39 -0500
commitb21a41385118f9a6af3cd96ce71090c5ada52eb5 (patch)
tree4eb9124ae72e1a905094c259465718793698e603 /drivers/scsi/scsi.c
parentf03a567054fea4f9d43c50ec91338266c0bd588d (diff)
downloadop-kernel-dev-b21a41385118f9a6af3cd96ce71090c5ada52eb5.zip
op-kernel-dev-b21a41385118f9a6af3cd96ce71090c5ada52eb5.tar.gz
[SCSI] add global timeout to the scsi mid-layer
There are certain rogue devices (and the aic7xxx driver) that return BUSY or QUEUE_FULL forever. This code will apply a global timeout (of the total number of retries times the per command timer) to a given command. If it is exceeded, the command is completed regardless of its state. The patch also removes the unused field in the command: timeout and timeout_total. This solves the problem of detecting an endless loop in the mid-layer because of BUSY/QUEUE_FULL bouncing, but will not recover the device. In the aic7xxx case, the driver can be recovered by sending a bus reset, so possibly this should be tied into the error handler? Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Diffstat (limited to 'drivers/scsi/scsi.c')
-rw-r--r--drivers/scsi/scsi.c15
1 files changed, 15 insertions, 0 deletions
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index d1aa95d..4befbc2 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -268,6 +268,7 @@ struct scsi_cmnd *scsi_get_command(struct scsi_device *dev, int gfp_mask)
} else
put_device(&dev->sdev_gendev);
+ cmd->jiffies_at_alloc = jiffies;
return cmd;
}
EXPORT_SYMBOL(scsi_get_command);
@@ -798,9 +799,23 @@ static void scsi_softirq(struct softirq_action *h)
while (!list_empty(&local_q)) {
struct scsi_cmnd *cmd = list_entry(local_q.next,
struct scsi_cmnd, eh_entry);
+ /* The longest time any command should be outstanding is the
+ * per command timeout multiplied by the number of retries.
+ *
+ * For a typical command, this is 2.5 minutes */
+ unsigned long wait_for
+ = cmd->allowed * cmd->timeout_per_command;
list_del_init(&cmd->eh_entry);
disposition = scsi_decide_disposition(cmd);
+ if (disposition != SUCCESS &&
+ time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
+ dev_printk(KERN_ERR, &cmd->device->sdev_gendev,
+ "timing out command, waited %ds\n",
+ wait_for/HZ);
+ disposition = SUCCESS;
+ }
+
scsi_log_completion(cmd, disposition);
switch (disposition) {
case SUCCESS:
OpenPOWER on IntegriCloud