#include <linux/interrupt.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
+#include <linux/jiffies.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
+#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_transport.h>
#include <scsi/scsi_host.h>
#include <trace/events/scsi.h>
+static void scsi_eh_done(struct scsi_cmnd *scmd);
+
#define SENSE_TIMEOUT (10*HZ)
/*
else if (host->hostt->eh_timed_out)
rtn = host->hostt->eh_timed_out(scmd);
+ scmd->result |= DID_TIME_OUT << 16;
+
if (unlikely(rtn == BLK_EH_NOT_HANDLED &&
- !scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))) {
- scmd->result |= DID_TIME_OUT << 16;
+ !scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD)))
rtn = BLK_EH_HANDLED;
- }
return rtn;
}
if (! scsi_command_normalize_sense(scmd, &sshdr))
return FAILED; /* no valid sense data */
+ if (scmd->cmnd[0] == TEST_UNIT_READY && scmd->scsi_done != scsi_eh_done)
+ /*
+ * nasty: for mid-layer issued TURs, we need to return the
+ * actual sense data without any recovery attempt. For eh
+ * issued ones, we need to try to recover and interpret
+ */
+ return SUCCESS;
+
if (scsi_sense_is_deferred(&sshdr))
return NEEDS_RETRY;
* so that we can deal with it there.
*/
if (scmd->device->expecting_cc_ua) {
- scmd->device->expecting_cc_ua = 0;
- return NEEDS_RETRY;
+ /*
+ * Because some device does not queue unit
+ * attentions correctly, we carefully check
+ * additional sense code and qualifier so as
+ * not to squash media change unit attention.
+ */
+ if (sshdr.asc != 0x28 || sshdr.ascq != 0x00) {
+ scmd->device->expecting_cc_ua = 0;
+ return NEEDS_RETRY;
+ }
}
/*
* if the device is in the process of becoming ready, we
return TARGET_ERROR;
case ILLEGAL_REQUEST:
+ if (sshdr.asc == 0x20 || /* Invalid command operation code */
+ sshdr.asc == 0x21 || /* Logical block address out of range */
+ sshdr.asc == 0x24 || /* Invalid field in cdb */
+ sshdr.asc == 0x26) { /* Parameter value invalid */
+ return TARGET_ERROR;
+ }
+ return SUCCESS;
+
default:
return SUCCESS;
}
}
/**
- * scsi_eh_prep_cmnd - Save a scsi command info as part of error recory
+ * scsi_eh_prep_cmnd - Save a scsi command info as part of error recovery
* @scmd: SCSI command structure to hijack
* @ses: structure to save restore information
* @cmnd: CDB to send. Can be NULL if no new cmnd is needed
EXPORT_SYMBOL(scsi_eh_prep_cmnd);
/**
- * scsi_eh_restore_cmnd - Restore a scsi command info as part of error recory
+ * scsi_eh_restore_cmnd - Restore a scsi command info as part of error recovery
* @scmd: SCSI command structure to restore
* @ses: saved information from a coresponding call to scsi_eh_prep_cmnd
*
EXPORT_SYMBOL(scsi_eh_restore_cmnd);
/**
- * scsi_send_eh_cmnd - submit a scsi command as part of error recory
+ * scsi_send_eh_cmnd - submit a scsi command as part of error recovery
* @scmd: SCSI command structure to hijack
* @cmnd: CDB to send
* @cmnd_size: size in bytes of @cmnd
struct scsi_device *sdev = scmd->device;
struct Scsi_Host *shost = sdev->host;
DECLARE_COMPLETION_ONSTACK(done);
- unsigned long timeleft;
+ unsigned long timeleft = timeout;
struct scsi_eh_save ses;
+ const unsigned long stall_for = msecs_to_jiffies(100);
int rtn;
+retry:
scsi_eh_prep_cmnd(scmd, &ses, cmnd, cmnd_size, sense_bytes);
shost->eh_action = &done;
scsi_log_send(scmd);
scmd->scsi_done = scsi_eh_done;
- shost->hostt->queuecommand(shost, scmd);
-
- timeleft = wait_for_completion_timeout(&done, timeout);
+ rtn = shost->hostt->queuecommand(shost, scmd);
+ if (rtn) {
+ if (timeleft > stall_for) {
+ scsi_eh_restore_cmnd(scmd, &ses);
+ timeleft -= stall_for;
+ msleep(jiffies_to_msecs(stall_for));
+ goto retry;
+ }
+ /* signal not to enter either branch of the if () below */
+ timeleft = 0;
+ rtn = NEEDS_RETRY;
+ } else {
+ timeleft = wait_for_completion_timeout(&done, timeout);
+ }
shost->eh_action = NULL;
- scsi_log_completion(scmd, SUCCESS);
+ scsi_log_completion(scmd, rtn);
SCSI_LOG_ERROR_RECOVERY(3,
printk("%s: scmd: %p, timeleft: %ld\n",
__func__, scmd, timeleft));
/*
- * If there is time left scsi_eh_done got called, and we will
- * examine the actual status codes to see whether the command
- * actually did complete normally, else tell the host to forget
- * about this command.
+ * If there is time left scsi_eh_done got called, and we will examine
+ * the actual status codes to see whether the command actually did
+ * complete normally, else if we have a zero return and no time left,
+ * the command must still be pending, so abort it and return FAILED.
+ * If we never actually managed to issue the command, because
+ * ->queuecommand() kept returning non zero, use the rtn = FAILED
+ * value above (so don't execute either branch of the if)
*/
if (timeleft) {
rtn = scsi_eh_completed_normally(scmd);
rtn = FAILED;
break;
}
- } else {
+ } else if (!rtn) {
scsi_abort_eh_cmnd(scmd);
rtn = FAILED;
}
scsi_eh_restore_cmnd(scmd, &ses);
+
+ if (scmd->request->cmd_type != REQ_TYPE_BLOCK_PC) {
+ struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
+ if (sdrv->eh_action)
+ rtn = sdrv->eh_action(scmd, cmnd, cmnd_size, rtn);
+ }
+
return rtn;
}
* Need to modify host byte to signal a
* permanent target failure
*/
- scmd->result |= (DID_TARGET_FAILURE << 16);
+ set_host_byte(scmd, DID_TARGET_FAILURE);
rtn = SUCCESS;
}
/* if rtn == FAILED, we have no sense information;
case RESERVATION_CONFLICT:
sdev_printk(KERN_INFO, scmd->device,
"reservation conflict\n");
- scmd->result |= (DID_NEXUS_FAILURE << 16);
+ set_host_byte(scmd, DID_NEXUS_FAILURE);
return SUCCESS; /* causes immediate i/o error */
default:
return FAILED;
* requests are started.
*/
scsi_run_host_queues(shost);
+
+ /*
+ * if eh is active and host_eh_scheduled is pending we need to re-run
+ * recovery. we do this check after scsi_run_host_queues() to allow
+ * everything pent up since the last eh run a chance to make forward
+ * progress before we sync again. Either we'll immediately re-run
+ * recovery or scsi_device_unbusy() will wake us again when these
+ * pending commands complete.
+ */
+ spin_lock_irqsave(shost->host_lock, flags);
+ if (shost->host_eh_scheduled)
+ if (scsi_host_set_state(shost, SHOST_RECOVERY))
+ WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY));
+ spin_unlock_irqrestore(shost->host_lock, flags);
}
/**
* We never actually get interrupted because kthread_run
* disables signal delivery for the created thread.
*/
- set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
shost->host_failed != shost->host_busy) {
SCSI_LOG_ERROR_RECOVERY(1,
printk("Error handler scsi_eh_%d sleeping\n",
shost->host_no));
schedule();
- set_current_state(TASK_INTERRUPTIBLE);
continue;
}
* what we need to do to get it up and online again (if we can).
* If we fail, we end up taking the thing offline.
*/
- if (scsi_autopm_get_host(shost) != 0) {
+ if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) {
SCSI_LOG_ERROR_RECOVERY(1,
printk(KERN_ERR "Error handler scsi_eh_%d "
"unable to autoresume\n",
* which are still online.
*/
scsi_restart_operations(shost);
- scsi_autopm_put_host(shost);
- set_current_state(TASK_INTERRUPTIBLE);
+ if (!shost->eh_noresume)
+ scsi_autopm_put_host(shost);
}
__set_current_state(TASK_RUNNING);
projects / firefly-linux-kernel-4.4.55.git / blobdiff