1 files changed, 49 insertions, 67 deletions

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 0fc8b48f052b..52b348c36d56 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -20,6 +20,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
@@ -49,7 +50,7 @@
 void scsi_eh_wakeup(struct Scsi_Host *shost)
 {
 	if (shost->host_busy == shost->host_failed) {
-		up(shost->eh_wait);
+		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5,
 				printk("Waking error handler thread\n"));
 	}
@@ -67,19 +68,24 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag)
 {
 	struct Scsi_Host *shost = scmd->device->host;
 	unsigned long flags;
+	int ret = 0;
 
-	if (shost->eh_wait == NULL)
+	if (!shost->ehandler)
 		return 0;
 
 	spin_lock_irqsave(shost->host_lock, flags);
+	if (scsi_host_set_state(shost, SHOST_RECOVERY))
+		if (scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY))
+			goto out_unlock;
 
+	ret = 1;
 	scmd->eh_eflags |= eh_flag;
 	list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q);
-	set_bit(SHOST_RECOVERY, &shost->shost_state);
 	shost->host_failed++;
 	scsi_eh_wakeup(shost);
+ out_unlock:
 	spin_unlock_irqrestore(shost->host_lock, flags);
-	return 1;
+	return ret;
 }
 
 /**
@@ -115,7 +121,6 @@ void scsi_add_timer(struct scsi_cmnd *scmd, int timeout,
 
 	add_timer(&scmd->eh_timeout);
 }
-EXPORT_SYMBOL(scsi_add_timer);
 
 /**
  * scsi_delete_timer - Delete/cancel timer for a given function.
@@ -143,7 +148,6 @@ int scsi_delete_timer(struct scsi_cmnd *scmd)
 
 	return rtn;
 }
-EXPORT_SYMBOL(scsi_delete_timer);
 
 /**
  * scsi_times_out - Timeout function for normal scsi commands.
@@ -177,8 +181,8 @@ void scsi_times_out(struct scsi_cmnd *scmd)
 		}
 
 	if (unlikely(!scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))) {
-		panic("Error handler thread not present at %p %p %s %d",
-		      scmd, scmd->device->host, __FILE__, __LINE__);
+		scmd->result |= DID_TIME_OUT << 16;
+		__scsi_done(scmd);
 	}
 }
 
@@ -197,7 +201,7 @@ int scsi_block_when_processing_errors(struct scsi_device *sdev)
 {
 	int online;
 
-	wait_event(sdev->host->host_wait, (!test_bit(SHOST_RECOVERY, &sdev->host->shost_state)));
+	wait_event(sdev->host->host_wait, !scsi_host_in_recovery(sdev->host));
 
 	online = scsi_device_online(sdev);
 
@@ -775,9 +779,11 @@ retry_tur:
 		__FUNCTION__, scmd, rtn));
 	if (rtn == SUCCESS)
 		return 0;
-	else if (rtn == NEEDS_RETRY)
+	else if (rtn == NEEDS_RETRY) {
 		if (retry_cnt--)
 			goto retry_tur;
+		return 0;
+	}
 	return 1;
 }
 
@@ -1439,6 +1445,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 static void scsi_restart_operations(struct Scsi_Host *shost)
 {
 	struct scsi_device *sdev;
+	unsigned long flags;
 
 	/*
 	 * If the door was locked, we need to insert a door lock request
@@ -1458,7 +1465,11 @@ static void scsi_restart_operations(struct Scsi_Host *shost)
 	SCSI_LOG_ERROR_RECOVERY(3, printk("%s: waking up host to restart\n",
 					  __FUNCTION__));
 
-	clear_bit(SHOST_RECOVERY, &shost->shost_state);
+	spin_lock_irqsave(shost->host_lock, flags);
+	if (scsi_host_set_state(shost, SHOST_RUNNING))
+		if (scsi_host_set_state(shost, SHOST_CANCEL))
+			BUG_ON(scsi_host_set_state(shost, SHOST_DEL));
+	spin_unlock_irqrestore(shost->host_lock, flags);
 
 	wake_up(&shost->host_wait);
 
@@ -1580,50 +1591,31 @@ int scsi_error_handler(void *data)
 {
 	struct Scsi_Host *shost = (struct Scsi_Host *) data;
 	int rtn;
-	DECLARE_MUTEX_LOCKED(sem);
-
-	/*
-	 *    Flush resources
-	 */
-
-	daemonize("scsi_eh_%d", shost->host_no);
 
 	current->flags |= PF_NOFREEZE;
 
-	shost->eh_wait = &sem;
-	shost->ehandler = current;
-
+	
 	/*
-	 * Wake up the thread that created us.
+	 * Note - we always use TASK_INTERRUPTIBLE even if the module
+	 * was loaded as part of the kernel.  The reason is that
+	 * UNINTERRUPTIBLE would cause this thread to be counted in
+	 * the load average as a running process, and an interruptible
+	 * wait doesn't.
 	 */
-	SCSI_LOG_ERROR_RECOVERY(3, printk("Wake up parent of"
-					  " scsi_eh_%d\n",shost->host_no));
-
-	complete(shost->eh_notify);
-
-	while (1) {
-		/*
-		 * If we get a signal, it means we are supposed to go
-		 * away and die.  This typically happens if the user is
-		 * trying to unload a module.
-		 */
-		SCSI_LOG_ERROR_RECOVERY(1, printk("Error handler"
-						  " scsi_eh_%d"
-						  " sleeping\n",shost->host_no));
-
-		/*
-		 * Note - we always use down_interruptible with the semaphore
-		 * even if the module was loaded as part of the kernel.  The
-		 * reason is that down() will cause this thread to be counted
-		 * in the load average as a running process, and down
-		 * interruptible doesn't.  Given that we need to allow this
-		 * thread to die if the driver was loaded as a module, using
-		 * semaphores isn't unreasonable.
-		 */
-		down_interruptible(&sem);
-		if (shost->eh_kill)
-			break;
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		if (shost->host_failed == 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;
+		}
 
+		__set_current_state(TASK_RUNNING);
 		SCSI_LOG_ERROR_RECOVERY(1, printk("Error handler"
 						  " scsi_eh_%d waking"
 						  " up\n",shost->host_no));
@@ -1650,32 +1642,18 @@ int scsi_error_handler(void *data)
 		 * which are still online.
 		 */
 		scsi_restart_operations(shost);
-
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
 
+	__set_current_state(TASK_RUNNING);
+
 	SCSI_LOG_ERROR_RECOVERY(1, printk("Error handler scsi_eh_%d"
 					  " exiting\n",shost->host_no));
 
 	/*
 	 * Make sure that nobody tries to wake us up again.
 	 */
-	shost->eh_wait = NULL;
-
-	/*
-	 * Knock this down too.  From this point on, the host is flying
-	 * without a pilot.  If this is because the module is being unloaded,
-	 * that's fine.  If the user sent a signal to this thing, we are
-	 * potentially in real danger.
-	 */
-	shost->eh_active = 0;
 	shost->ehandler = NULL;
-
-	/*
-	 * If anyone is waiting for us to exit (i.e. someone trying to unload
-	 * a driver), then wake up that process to let them know we are on
-	 * the way out the door.
-	 */
-	complete_and_exit(shost->eh_notify, 0);
 	return 0;
 }
 
@@ -1846,12 +1824,16 @@ EXPORT_SYMBOL(scsi_reset_provider);
 int scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
                          struct scsi_sense_hdr *sshdr)
 {
-	if (!sense_buffer || !sb_len || (sense_buffer[0] & 0x70) != 0x70)
+	if (!sense_buffer || !sb_len)
 		return 0;
 
 	memset(sshdr, 0, sizeof(struct scsi_sense_hdr));
 
 	sshdr->response_code = (sense_buffer[0] & 0x7f);
+
+	if (!scsi_sense_valid(sshdr))
+		return 0;
+
 	if (sshdr->response_code >= 0x72) {
 		/*
 		 * descriptor format