scsi_error.c

来自「linux 内核源代码」· C语言 代码 · 共 1,918 行 · 第 1/4 页

/*
 *  scsi_error.c Copyright (C) 1997 Eric Youngdale
 *
 *  SCSI error/timeout handling
 *      Initial versions: Eric Youngdale.  Based upon conversations with
 *                        Leonard Zubkoff and David Miller at Linux Expo, 
 *                        ideas originating from all over the place.
 *
 *	Restructured scsi_unjam_host and associated functions.
 *	September 04, 2002 Mike Anderson ([e-mail])
 *
 *	Forward port of Russell King's ([e-mail]) changes and
 *	minor  cleanups.
 *	September 30, 2002 Mike Anderson ([e-mail])
 */

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/interrupt.h>
#include <linux/blkdev.h>
#include <linux/delay.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_transport.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h>

#include "scsi_priv.h"
#include "scsi_logging.h"
#include "scsi_transport_api.h"

#define SENSE_TIMEOUT		(10*HZ)

/*
 * These should *probably* be handled by the host itself.
 * Since it is allowed to sleep, it probably should.
 */
#define BUS_RESET_SETTLE_TIME   (10)
#define HOST_RESET_SETTLE_TIME  (10)

/* called with shost->host_lock held */
void scsi_eh_wakeup(struct Scsi_Host *shost)
{
	if (shost->host_busy == shost->host_failed) {
		wake_up_process(shost->ehandler);
		SCSI_LOG_ERROR_RECOVERY(5,
				printk("Waking error handler thread\n"));
	}
}

/**
 * scsi_schedule_eh - schedule EH for SCSI host
 * @shost:	SCSI host to invoke error handling on.
 *
 * Schedule SCSI EH without scmd.
 **/
void scsi_schedule_eh(struct Scsi_Host *shost)
{
	unsigned long flags;

	spin_lock_irqsave(shost->host_lock, flags);

	if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
	    scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
		shost->host_eh_scheduled++;
		scsi_eh_wakeup(shost);
	}

	spin_unlock_irqrestore(shost->host_lock, flags);
}
EXPORT_SYMBOL_GPL(scsi_schedule_eh);

/**
 * scsi_eh_scmd_add - add scsi cmd to error handling.
 * @scmd:	scmd to run eh on.
 * @eh_flag:	optional SCSI_EH flag.
 *
 * Return value:
 *	0 on failure.
 **/
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->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);
	shost->host_failed++;
	scsi_eh_wakeup(shost);
 out_unlock:
	spin_unlock_irqrestore(shost->host_lock, flags);
	return ret;
}

/**
 * scsi_add_timer - Start timeout timer for a single scsi command.
 * @scmd:	scsi command that is about to start running.
 * @timeout:	amount of time to allow this command to run.
 * @complete:	timeout function to call if timer isn't canceled.
 *
 * Notes:
 *    This should be turned into an inline function.  Each scsi command
 *    has its own timer, and as it is added to the queue, we set up the
 *    timer.  When the command completes, we cancel the timer.
 **/
void scsi_add_timer(struct scsi_cmnd *scmd, int timeout,
		    void (*complete)(struct scsi_cmnd *))
{

	/*
	 * If the clock was already running for this command, then
	 * first delete the timer.  The timer handling code gets rather
	 * confused if we don't do this.
	 */
	if (scmd->eh_timeout.function)
		del_timer(&scmd->eh_timeout);

	scmd->eh_timeout.data = (unsigned long)scmd;
	scmd->eh_timeout.expires = jiffies + timeout;
	scmd->eh_timeout.function = (void (*)(unsigned long)) complete;

	SCSI_LOG_ERROR_RECOVERY(5, printk("%s: scmd: %p, time:"
					  " %d, (%p)\n", __FUNCTION__,
					  scmd, timeout, complete));

	add_timer(&scmd->eh_timeout);
}

/**
 * scsi_delete_timer - Delete/cancel timer for a given function.
 * @scmd:	Cmd that we are canceling timer for
 *
 * Notes:
 *     This should be turned into an inline function.
 *
 * Return value:
 *     1 if we were able to detach the timer.  0 if we blew it, and the
 *     timer function has already started to run.
 **/
int scsi_delete_timer(struct scsi_cmnd *scmd)
{
	int rtn;

	rtn = del_timer(&scmd->eh_timeout);

	SCSI_LOG_ERROR_RECOVERY(5, printk("%s: scmd: %p,"
					 " rtn: %d\n", __FUNCTION__,
					 scmd, rtn));

	scmd->eh_timeout.data = (unsigned long)NULL;
	scmd->eh_timeout.function = NULL;

	return rtn;
}

/**
 * scsi_times_out - Timeout function for normal scsi commands.
 * @scmd:	Cmd that is timing out.
 *
 * Notes:
 *     We do not need to lock this.  There is the potential for a race
 *     only in that the normal completion handling might run, but if the
 *     normal completion function determines that the timer has already
 *     fired, then it mustn't do anything.
 **/
void scsi_times_out(struct scsi_cmnd *scmd)
{
	enum scsi_eh_timer_return (* eh_timed_out)(struct scsi_cmnd *);

	scsi_log_completion(scmd, TIMEOUT_ERROR);

	if (scmd->device->host->transportt->eh_timed_out)
		eh_timed_out = scmd->device->host->transportt->eh_timed_out;
	else if (scmd->device->host->hostt->eh_timed_out)
		eh_timed_out = scmd->device->host->hostt->eh_timed_out;
	else
		eh_timed_out = NULL;

	if (eh_timed_out)
		switch (eh_timed_out(scmd)) {
		case EH_HANDLED:
			__scsi_done(scmd);
			return;
		case EH_RESET_TIMER:
			scsi_add_timer(scmd, scmd->timeout_per_command,
				       scsi_times_out);
			return;
		case EH_NOT_HANDLED:
			break;
		}

	if (unlikely(!scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))) {
		scmd->result |= DID_TIME_OUT << 16;
		__scsi_done(scmd);
	}
}

/**
 * scsi_block_when_processing_errors - Prevent cmds from being queued.
 * @sdev:	Device on which we are performing recovery.
 *
 * Description:
 *     We block until the host is out of error recovery, and then check to
 *     see whether the host or the device is offline.
 *
 * Return value:
 *     0 when dev was taken offline by error recovery. 1 OK to proceed.
 **/
int scsi_block_when_processing_errors(struct scsi_device *sdev)
{
	int online;

	wait_event(sdev->host->host_wait, !scsi_host_in_recovery(sdev->host));

	online = scsi_device_online(sdev);

	SCSI_LOG_ERROR_RECOVERY(5, printk("%s: rtn: %d\n", __FUNCTION__,
					  online));

	return online;
}
EXPORT_SYMBOL(scsi_block_when_processing_errors);

#ifdef CONFIG_SCSI_LOGGING
/**
 * scsi_eh_prt_fail_stats - Log info on failures.
 * @shost:	scsi host being recovered.
 * @work_q:	Queue of scsi cmds to process.
 **/
static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost,
					  struct list_head *work_q)
{
	struct scsi_cmnd *scmd;
	struct scsi_device *sdev;
	int total_failures = 0;
	int cmd_failed = 0;
	int cmd_cancel = 0;
	int devices_failed = 0;

	shost_for_each_device(sdev, shost) {
		list_for_each_entry(scmd, work_q, eh_entry) {
			if (scmd->device == sdev) {
				++total_failures;
				if (scmd->eh_eflags & SCSI_EH_CANCEL_CMD)
					++cmd_cancel;
				else 
					++cmd_failed;
			}
		}

		if (cmd_cancel || cmd_failed) {
			SCSI_LOG_ERROR_RECOVERY(3,
				sdev_printk(KERN_INFO, sdev,
					    "%s: cmds failed: %d, cancel: %d\n",
					    __FUNCTION__, cmd_failed,
					    cmd_cancel));
			cmd_cancel = 0;
			cmd_failed = 0;
			++devices_failed;
		}
	}

	SCSI_LOG_ERROR_RECOVERY(2, printk("Total of %d commands on %d"
					  " devices require eh work\n",
				  total_failures, devices_failed));
}
#endif

/**
 * scsi_check_sense - Examine scsi cmd sense
 * @scmd:	Cmd to have sense checked.
 *
 * Return value:
 * 	SUCCESS or FAILED or NEEDS_RETRY
 *
 * Notes:
 *	When a deferred error is detected the current command has
 *	not been executed and needs retrying.
 **/
static int scsi_check_sense(struct scsi_cmnd *scmd)
{
	struct scsi_sense_hdr sshdr;

	if (! scsi_command_normalize_sense(scmd, &sshdr))
		return FAILED;	/* no valid sense data */

	if (scsi_sense_is_deferred(&sshdr))
		return NEEDS_RETRY;

	/*
	 * Previous logic looked for FILEMARK, EOM or ILI which are
	 * mainly associated with tapes and returned SUCCESS.
	 */
	if (sshdr.response_code == 0x70) {
		/* fixed format */
		if (scmd->sense_buffer[2] & 0xe0)
			return SUCCESS;
	} else {
		/*
		 * descriptor format: look for "stream commands sense data
		 * descriptor" (see SSC-3). Assume single sense data
		 * descriptor. Ignore ILI from SBC-2 READ LONG and WRITE LONG.
		 */
		if ((sshdr.additional_length > 3) &&
		    (scmd->sense_buffer[8] == 0x4) &&
		    (scmd->sense_buffer[11] & 0xe0))
			return SUCCESS;
	}

	switch (sshdr.sense_key) {
	case NO_SENSE:
		return SUCCESS;
	case RECOVERED_ERROR:
		return /* soft_error */ SUCCESS;

	case ABORTED_COMMAND:
		return NEEDS_RETRY;
	case NOT_READY:
	case UNIT_ATTENTION:
		/*
		 * if we are expecting a cc/ua because of a bus reset that we
		 * performed, treat this just as a retry.  otherwise this is
		 * information that we should pass up to the upper-level driver
		 * so that we can deal with it there.
		 */
		if (scmd->device->expecting_cc_ua) {
			scmd->device->expecting_cc_ua = 0;
			return NEEDS_RETRY;
		}
		/*
		 * if the device is in the process of becoming ready, we 
		 * should retry.
		 */
		if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01))
			return NEEDS_RETRY;
		/*
		 * if the device is not started, we need to wake
		 * the error handler to start the motor
		 */
		if (scmd->device->allow_restart &&
		    (sshdr.asc == 0x04) && (sshdr.ascq == 0x02))
			return FAILED;
		return SUCCESS;

		/* these three are not supported */
	case COPY_ABORTED:
	case VOLUME_OVERFLOW:
	case MISCOMPARE:
		return SUCCESS;

	case MEDIUM_ERROR:
		if (sshdr.asc == 0x11 || /* UNRECOVERED READ ERR */
		    sshdr.asc == 0x13 || /* AMNF DATA FIELD */
		    sshdr.asc == 0x14) { /* RECORD NOT FOUND */
			return SUCCESS;
		}
		return NEEDS_RETRY;

	case HARDWARE_ERROR:
		if (scmd->device->retry_hwerror)
			return NEEDS_RETRY;
		else
			return SUCCESS;

	case ILLEGAL_REQUEST:
	case BLANK_CHECK:
	case DATA_PROTECT:
	default:
		return SUCCESS;
	}
}

/**
 * scsi_eh_completed_normally - Disposition a eh cmd on return from LLD.
 * @scmd:	SCSI cmd to examine.
 *
 * Notes:
 *    This is *only* called when we are examining the status of commands
 *    queued during error recovery.  the main difference here is that we
 *    don't allow for the possibility of retries here, and we are a lot
 *    more restrictive about what we consider acceptable.
 **/
static int scsi_eh_completed_normally(struct scsi_cmnd *scmd)
{
	/*
	 * first check the host byte, to see if there is anything in there
	 * that would indicate what we need to do.
	 */
	if (host_byte(scmd->result) == DID_RESET) {
		/*
		 * rats.  we are already in the error handler, so we now
		 * get to try and figure out what to do next.  if the sense
		 * is valid, we have a pretty good idea of what to do.
		 * if not, we mark it as FAILED.
		 */
		return scsi_check_sense(scmd);
	}
	if (host_byte(scmd->result) != DID_OK)
		return FAILED;

	/*
	 * next, check the message byte.
	 */
	if (msg_byte(scmd->result) != COMMAND_COMPLETE)
		return FAILED;

	/*
	 * now, check the status byte to see if this indicates
	 * anything special.
	 */
	switch (status_byte(scmd->result)) {
	case GOOD:
	case COMMAND_TERMINATED:
		return SUCCESS;
	case CHECK_CONDITION:
		return scsi_check_sense(scmd);
	case CONDITION_GOOD:
	case INTERMEDIATE_GOOD:
	case INTERMEDIATE_C_GOOD:
		/*
		 * who knows?  FIXME(eric)
		 */
		return SUCCESS;
	case BUSY:
	case QUEUE_FULL:
	case RESERVATION_CONFLICT:
	default:
		return FAILED;
	}
	return FAILED;
}

/**
 * scsi_eh_done - Completion function for error handling.
 * @scmd:	Cmd that is done.
 **/
static void scsi_eh_done(struct scsi_cmnd *scmd)
{
	struct completion     *eh_action;

	SCSI_LOG_ERROR_RECOVERY(3,
		printk("%s scmd: %p result: %x\n",
			__FUNCTION__, scmd, scmd->result));

	eh_action = scmd->device->host->eh_action;
	if (eh_action)
		complete(eh_action);
}

/**
 * scsi_try_host_reset - ask host adapter to reset itself
 * @scmd:	SCSI cmd to send hsot reset.
 **/
static int scsi_try_host_reset(struct scsi_cmnd *scmd)
{
	unsigned long flags;
	int rtn;

	SCSI_LOG_ERROR_RECOVERY(3, printk("%s: Snd Host RST\n",
					  __FUNCTION__));