diff options
Diffstat (limited to 'drivers/scsi/scsi_error.c')
| -rw-r--r-- | drivers/scsi/scsi_error.c | 1195 |
1 files changed, 926 insertions, 269 deletions
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 045a0868fc7..7e957918f33 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -3,19 +3,20 @@ * * SCSI error/timeout handling * Initial versions: Eric Youngdale. Based upon conversations with - * Leonard Zubkoff and David Miller at Linux Expo, + * 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 (andmike@us.ibm.com) * * Forward port of Russell King's (rmk@arm.linux.org.uk) changes and - * minor cleanups. + * minor cleanups. * September 30, 2002 Mike Anderson (andmike@us.ibm.com) */ #include <linux/module.h> #include <linux/sched.h> +#include <linux/gfp.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/kernel.h> @@ -24,11 +25,13 @@ #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> @@ -38,7 +41,9 @@ #include "scsi_logging.h" #include "scsi_transport_api.h" -#define SENSE_TIMEOUT (10*HZ) +#include <trace/events/scsi.h> + +static void scsi_eh_done(struct scsi_cmnd *scmd); /* * These should *probably* be handled by the host itself. @@ -47,10 +52,15 @@ #define BUS_RESET_SETTLE_TIME (10) #define HOST_RESET_SETTLE_TIME (10) +static int scsi_eh_try_stu(struct scsi_cmnd *scmd); +static int scsi_try_to_abort_cmd(struct scsi_host_template *, + struct scsi_cmnd *); + /* called with shost->host_lock held */ void scsi_eh_wakeup(struct Scsi_Host *shost) { if (shost->host_busy == shost->host_failed) { + trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, printk("Waking error handler thread\n")); @@ -79,6 +89,140 @@ void scsi_schedule_eh(struct Scsi_Host *shost) } EXPORT_SYMBOL_GPL(scsi_schedule_eh); +static int scsi_host_eh_past_deadline(struct Scsi_Host *shost) +{ + if (!shost->last_reset || shost->eh_deadline == -1) + return 0; + + /* + * 32bit accesses are guaranteed to be atomic + * (on all supported architectures), so instead + * of using a spinlock we can as well double check + * if eh_deadline has been set to 'off' during the + * time_before call. + */ + if (time_before(jiffies, shost->last_reset + shost->eh_deadline) && + shost->eh_deadline > -1) + return 0; + + return 1; +} + +/** + * scmd_eh_abort_handler - Handle command aborts + * @work: command to be aborted. + */ +void +scmd_eh_abort_handler(struct work_struct *work) +{ + struct scsi_cmnd *scmd = + container_of(work, struct scsi_cmnd, abort_work.work); + struct scsi_device *sdev = scmd->device; + int rtn; + + if (scsi_host_eh_past_deadline(sdev->host)) { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p eh timeout, not aborting\n", + scmd)); + } else { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "aborting command %p\n", scmd)); + rtn = scsi_try_to_abort_cmd(sdev->host->hostt, scmd); + if (rtn == SUCCESS) { + set_host_byte(scmd, DID_TIME_OUT); + if (scsi_host_eh_past_deadline(sdev->host)) { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p eh timeout, " + "not retrying aborted " + "command\n", scmd)); + } else if (!scsi_noretry_cmd(scmd) && + (++scmd->retries <= scmd->allowed)) { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_WARNING, scmd, + "scmd %p retry " + "aborted command\n", scmd)); + scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); + return; + } else { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_WARNING, scmd, + "scmd %p finish " + "aborted command\n", scmd)); + scsi_finish_command(scmd); + return; + } + } else { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p abort failed, rtn %d\n", + scmd, rtn)); + } + } + + if (!scsi_eh_scmd_add(scmd, 0)) { + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_WARNING, scmd, + "scmd %p terminate " + "aborted command\n", scmd)); + set_host_byte(scmd, DID_TIME_OUT); + scsi_finish_command(scmd); + } +} + +/** + * scsi_abort_command - schedule a command abort + * @scmd: scmd to abort. + * + * We only need to abort commands after a command timeout + */ +static int +scsi_abort_command(struct scsi_cmnd *scmd) +{ + struct scsi_device *sdev = scmd->device; + struct Scsi_Host *shost = sdev->host; + unsigned long flags; + + if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { + /* + * Retry after abort failed, escalate to next level. + */ + scmd->eh_eflags &= ~SCSI_EH_ABORT_SCHEDULED; + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p previous abort failed\n", scmd)); + cancel_delayed_work(&scmd->abort_work); + return FAILED; + } + + /* + * Do not try a command abort if + * SCSI EH has already started. + */ + spin_lock_irqsave(shost->host_lock, flags); + if (scsi_host_in_recovery(shost)) { + spin_unlock_irqrestore(shost->host_lock, flags); + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p not aborting, host in recovery\n", + scmd)); + return FAILED; + } + + if (shost->eh_deadline != -1 && !shost->last_reset) + shost->last_reset = jiffies; + spin_unlock_irqrestore(shost->host_lock, flags); + + scmd->eh_eflags |= SCSI_EH_ABORT_SCHEDULED; + SCSI_LOG_ERROR_RECOVERY(3, + scmd_printk(KERN_INFO, scmd, + "scmd %p abort scheduled\n", scmd)); + queue_delayed_work(shost->tmf_work_q, &scmd->abort_work, HZ / 100); + return SUCCESS; +} + /** * scsi_eh_scmd_add - add scsi cmd to error handling. * @scmd: scmd to run eh on. @@ -101,7 +245,12 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag) if (scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)) goto out_unlock; + if (shost->eh_deadline != -1 && !shost->last_reset) + shost->last_reset = jiffies; + ret = 1; + if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) + eh_flag &= ~SCSI_EH_CANCEL_CMD; scmd->eh_eflags |= eh_flag; list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q); shost->host_failed++; @@ -112,69 +261,8 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag) } /** - * 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. + * @req: request that is timing out. * * Notes: * We do not need to lock this. There is the potential for a race @@ -182,36 +270,34 @@ int scsi_delete_timer(struct scsi_cmnd *scmd) * 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 blk_eh_timer_return scsi_times_out(struct request *req) { - enum scsi_eh_timer_return (* eh_timed_out)(struct scsi_cmnd *); + struct scsi_cmnd *scmd = req->special; + enum blk_eh_timer_return rtn = BLK_EH_NOT_HANDLED; + struct Scsi_Host *host = scmd->device->host; + trace_scsi_dispatch_cmd_timeout(scmd); 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 (host->eh_deadline != -1 && !host->last_reset) + host->last_reset = jiffies; + + if (host->transportt->eh_timed_out) + rtn = host->transportt->eh_timed_out(scmd); + else if (host->hostt->eh_timed_out) + rtn = host->hostt->eh_timed_out(scmd); - if (unlikely(!scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))) { - scmd->result |= DID_TIME_OUT << 16; - __scsi_done(scmd); + if (rtn == BLK_EH_NOT_HANDLED) { + if (!host->hostt->no_async_abort && + scsi_abort_command(scmd) == SUCCESS) + return BLK_EH_NOT_HANDLED; + + set_host_byte(scmd, DID_TIME_OUT); + if (!scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD)) + rtn = BLK_EH_HANDLED; } + + return rtn; } /** @@ -233,7 +319,7 @@ int scsi_block_when_processing_errors(struct scsi_device *sdev) online = scsi_device_online(sdev); - SCSI_LOG_ERROR_RECOVERY(5, printk("%s: rtn: %d\n", __FUNCTION__, + SCSI_LOG_ERROR_RECOVERY(5, printk("%s: rtn: %d\n", __func__, online)); return online; @@ -262,7 +348,7 @@ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, ++total_failures; if (scmd->eh_eflags & SCSI_EH_CANCEL_CMD) ++cmd_cancel; - else + else ++cmd_failed; } } @@ -271,7 +357,7 @@ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: cmds failed: %d, cancel: %d\n", - __FUNCTION__, cmd_failed, + __func__, cmd_failed, cmd_cancel)); cmd_cancel = 0; cmd_failed = 0; @@ -281,16 +367,84 @@ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, SCSI_LOG_ERROR_RECOVERY(2, printk("Total of %d commands on %d" " devices require eh work\n", - total_failures, devices_failed)); + total_failures, devices_failed)); } #endif + /** + * scsi_report_lun_change - Set flag on all *other* devices on the same target + * to indicate that a UNIT ATTENTION is expected. + * @sdev: Device reporting the UNIT ATTENTION + */ +static void scsi_report_lun_change(struct scsi_device *sdev) +{ + sdev->sdev_target->expecting_lun_change = 1; +} + +/** + * scsi_report_sense - Examine scsi sense information and log messages for + * certain conditions, also issue uevents for some of them. + * @sdev: Device reporting the sense code + * @sshdr: sshdr to be examined + */ +static void scsi_report_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sshdr) +{ + enum scsi_device_event evt_type = SDEV_EVT_MAXBITS; /* i.e. none */ + + if (sshdr->sense_key == UNIT_ATTENTION) { + if (sshdr->asc == 0x3f && sshdr->ascq == 0x03) { + evt_type = SDEV_EVT_INQUIRY_CHANGE_REPORTED; + sdev_printk(KERN_WARNING, sdev, + "Inquiry data has changed"); + } else if (sshdr->asc == 0x3f && sshdr->ascq == 0x0e) { + evt_type = SDEV_EVT_LUN_CHANGE_REPORTED; + scsi_report_lun_change(sdev); + sdev_printk(KERN_WARNING, sdev, + "Warning! Received an indication that the " + "LUN assignments on this target have " + "changed. The Linux SCSI layer does not " + "automatically remap LUN assignments.\n"); + } else if (sshdr->asc == 0x3f) + sdev_printk(KERN_WARNING, sdev, + "Warning! Received an indication that the " + "operating parameters on this target have " + "changed. The Linux SCSI layer does not " + "automatically adjust these parameters.\n"); + + if (sshdr->asc == 0x38 && sshdr->ascq == 0x07) { + evt_type = SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED; + sdev_printk(KERN_WARNING, sdev, + "Warning! Received an indication that the " + "LUN reached a thin provisioning soft " + "threshold.\n"); + } + + if (sshdr->asc == 0x2a && sshdr->ascq == 0x01) { + evt_type = SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED; + sdev_printk(KERN_WARNING, sdev, + "Mode parameters changed"); + } else if (sshdr->asc == 0x2a && sshdr->ascq == 0x09) { + evt_type = SDEV_EVT_CAPACITY_CHANGE_REPORTED; + sdev_printk(KERN_WARNING, sdev, + "Capacity data has changed"); + } else if (sshdr->asc == 0x2a) + sdev_printk(KERN_WARNING, sdev, + "Parameters changed"); + } + + if (evt_type != SDEV_EVT_MAXBITS) { + set_bit(evt_type, sdev->pending_events); + schedule_work(&sdev->event_work); + } +} + /** * scsi_check_sense - Examine scsi cmd sense * @scmd: Cmd to have sense checked. * * Return value: - * SUCCESS or FAILED or NEEDS_RETRY + * SUCCESS or FAILED or NEEDS_RETRY or ADD_TO_MLQUEUE * * Notes: * When a deferred error is detected the current command has @@ -298,14 +452,35 @@ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, */ static int scsi_check_sense(struct scsi_cmnd *scmd) { + struct scsi_device *sdev = scmd->device; struct scsi_sense_hdr sshdr; 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; + + scsi_report_sense(sdev, &sshdr); + if (scsi_sense_is_deferred(&sshdr)) return NEEDS_RETRY; + if (sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh && + sdev->scsi_dh_data->scsi_dh->check_sense) { + int rc; + + rc = sdev->scsi_dh_data->scsi_dh->check_sense(sdev, &sshdr); + if (rc != SCSI_RETURN_NOT_HANDLED) + return rc; + /* handler does not care. Drop down to default handling */ + } + /* * Previous logic looked for FILEMARK, EOM or ILI which are * mainly associated with tapes and returned SUCCESS. @@ -333,6 +508,9 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) return /* soft_error */ SUCCESS; case ABORTED_COMMAND: + if (sshdr.asc == 0x10) /* DIF */ + return SUCCESS; + return NEEDS_RETRY; case NOT_READY: case UNIT_ATTENTION: @@ -343,11 +521,27 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) * 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 + * we might also expect a cc/ua if another LUN on the target + * reported a UA with an ASC/ASCQ of 3F 0E - + * REPORTED LUNS DATA HAS CHANGED. + */ + if (scmd->device->sdev_target->expecting_lun_change && + sshdr.asc == 0x3f && sshdr.ascq == 0x0e) + return NEEDS_RETRY; + /* + * if the device is in the process of becoming ready, we * should retry. */ if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01)) @@ -359,36 +553,113 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) if (scmd->device->allow_restart && (sshdr.asc == 0x04) && (sshdr.ascq == 0x02)) return FAILED; + /* + * Pass the UA upwards for a determination in the completion + * functions. + */ return SUCCESS; - /* these three are not supported */ + /* these are not supported */ + case DATA_PROTECT: + if (sshdr.asc == 0x27 && sshdr.ascq == 0x07) { + /* Thin provisioning hard threshold reached */ + set_host_byte(scmd, DID_ALLOC_FAILURE); + return SUCCESS; + } case COPY_ABORTED: case VOLUME_OVERFLOW: case MISCOMPARE: + case BLANK_CHECK: + set_host_byte(scmd, DID_TARGET_FAILURE); return SUCCESS; case MEDIUM_ERROR: if (sshdr.asc == 0x11 || /* UNRECOVERED READ ERR */ sshdr.asc == 0x13 || /* AMNF DATA FIELD */ sshdr.asc == 0x14) { /* RECORD NOT FOUND */ + set_host_byte(scmd, DID_MEDIUM_ERROR); return SUCCESS; } return NEEDS_RETRY; case HARDWARE_ERROR: if (scmd->device->retry_hwerror) - return NEEDS_RETRY; + return ADD_TO_MLQUEUE; else - return SUCCESS; + set_host_byte(scmd, DID_TARGET_FAILURE); case ILLEGAL_REQUEST: - case BLANK_CHECK: - case DATA_PROTECT: + 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 */ + set_host_byte(scmd, DID_TARGET_FAILURE); + } + return SUCCESS; + default: return SUCCESS; } } +static void scsi_handle_queue_ramp_up(struct scsi_device *sdev) +{ + struct scsi_host_template *sht = sdev->host->hostt; + struct scsi_device *tmp_sdev; + + if (!sht->change_queue_depth || + sdev->queue_depth >= sdev->max_queue_depth) + return; + + if (time_before(jiffies, + sdev->last_queue_ramp_up + sdev->queue_ramp_up_period)) + return; + + if (time_before(jiffies, + sdev->last_queue_full_time + sdev->queue_ramp_up_period)) + return; + + /* + * Walk all devices of a target and do + * ramp up on them. + */ + shost_for_each_device(tmp_sdev, sdev->host) { + if (tmp_sdev->channel != sdev->channel || + tmp_sdev->id != sdev->id || + tmp_sdev->queue_depth == sdev->max_queue_depth) + continue; + /* + * call back into LLD to increase queue_depth by one + * with ramp up reason code. + */ + sht->change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1, + SCSI_QDEPTH_RAMP_UP); + sdev->last_queue_ramp_up = jiffies; + } +} + +static void scsi_handle_queue_full(struct scsi_device *sdev) +{ + struct scsi_host_template *sht = sdev->host->hostt; + struct scsi_device *tmp_sdev; + + if (!sht->change_queue_depth) + return; + + shost_for_each_device(tmp_sdev, sdev->host) { + if (tmp_sdev->channel != sdev->channel || + tmp_sdev->id != sdev->id) + continue; + /* + * We do not know the number of commands that were at + * the device when we got the queue full so we start + * from the highest possible value and work our way down. + */ + sht->change_queue_depth(tmp_sdev, tmp_sdev->queue_depth - 1, + SCSI_QDEPTH_QFULL); + } +} + /** * scsi_eh_completed_normally - Disposition a eh cmd on return from LLD. * @scmd: SCSI cmd to examine. @@ -429,6 +700,7 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) */ switch (status_byte(scmd->result)) { case GOOD: + scsi_handle_queue_ramp_up(scmd->device); case COMMAND_TERMINATED: return SUCCESS; case CHECK_CONDITION: @@ -440,9 +712,18 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) * who knows? FIXME(eric) */ return SUCCESS; - case BUSY: - case QUEUE_FULL: case RESERVATION_CONFLICT: + if (scmd->cmnd[0] == TEST_UNIT_READY) + /* it is a success, we probed the device and + * found it */ + return SUCCESS; + /* otherwise, we failed to send the command */ + return FAILED; + case QUEUE_FULL: + scsi_handle_queue_full(scmd->device); + /* fall through */ + case BUSY: + return NEEDS_RETRY; default: return FAILED; } @@ -455,11 +736,11 @@ static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) */ static void scsi_eh_done(struct scsi_cmnd *scmd) { - struct completion *eh_action; + struct completion *eh_action; SCSI_LOG_ERROR_RECOVERY(3, printk("%s scmd: %p result: %x\n", - __FUNCTION__, scmd, scmd->result)); + __func__, scmd, scmd->result)); eh_action = scmd->device->host->eh_action; if (eh_action) @@ -468,28 +749,29 @@ static void scsi_eh_done(struct scsi_cmnd *scmd) /** * scsi_try_host_reset - ask host adapter to reset itself - * @scmd: SCSI cmd to send hsot reset. + * @scmd: SCSI cmd to send host reset. */ static int scsi_try_host_reset(struct scsi_cmnd *scmd) { unsigned long flags; int rtn; + struct Scsi_Host *host = scmd->device->host; + struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, printk("%s: Snd Host RST\n", - __FUNCTION__)); + __func__)); - if (!scmd->device->host->hostt->eh_host_reset_handler) + if (!hostt->eh_host_reset_handler) return FAILED; - rtn = scmd->device->host->hostt->eh_host_reset_handler(scmd); + rtn = hostt->eh_host_reset_handler(scmd); if (rtn == SUCCESS) { - if (!scmd->device->host->hostt->skip_settle_delay) + if (!hostt->skip_settle_delay) ssleep(HOST_RESET_SETTLE_TIME); - spin_lock_irqsave(scmd->device->host->host_lock, flags); - scsi_report_bus_reset(scmd->device->host, - scmd_channel(scmd)); - spin_unlock_irqrestore(scmd->device->host->host_lock, flags); + spin_lock_irqsave(host->host_lock, flags); + scsi_report_bus_reset(host, scmd_channel(scmd)); + spin_unlock_irqrestore(host->host_lock, flags); } return rtn; @@ -503,30 +785,37 @@ static int scsi_try_bus_reset(struct scsi_cmnd *scmd) { unsigned long flags; int rtn; + struct Scsi_Host *host = scmd->device->host; + struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, printk("%s: Snd Bus RST\n", - __FUNCTION__)); + __func__)); - if (!scmd->device->host->hostt->eh_bus_reset_handler) + if (!hostt->eh_bus_reset_handler) return FAILED; - rtn = scmd->device->host->hostt->eh_bus_reset_handler(scmd); + rtn = hostt->eh_bus_reset_handler(scmd); if (rtn == SUCCESS) { - if (!scmd->device->host->hostt->skip_settle_delay) + if (!hostt->skip_settle_delay) ssleep(BUS_RESET_SETTLE_TIME); - spin_lock_irqsave(scmd->device->host->host_lock, flags); - scsi_report_bus_reset(scmd->device->host, - scmd_channel(scmd)); - spin_unlock_irqrestore(scmd->device->host->host_lock, flags); + spin_lock_irqsave(host->host_lock, flags); + scsi_report_bus_reset(host, scmd_channel(scmd)); + spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } +static void __scsi_report_device_reset(struct scsi_device *sdev, void *data) +{ + sdev->was_reset = 1; + sdev->expecting_cc_ua = 1; +} + /** - * scsi_try_bus_device_reset - Ask host to perform a BDR on a dev - * @scmd: SCSI cmd used to send BDR + * scsi_try_target_reset - Ask host to perform a target reset + * @scmd: SCSI cmd used to send a target reset * * Notes: * There is no timeout for this operation. if this operation is @@ -534,66 +823,74 @@ static int scsi_try_bus_reset(struct scsi_cmnd *scmd) * timer on it, and set the host back to a consistent state prior to * returning. */ -static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd) +static int scsi_try_target_reset(struct scsi_cmnd *scmd) { + unsigned long flags; int rtn; + struct Scsi_Host *host = scmd->device->host; + struct scsi_host_template *hostt = host->hostt; - if (!scmd->device->host->hostt->eh_device_reset_handler) + if (!hostt->eh_target_reset_handler) return FAILED; - rtn = scmd->device->host->hostt->eh_device_reset_handler(scmd); + rtn = hostt->eh_target_reset_handler(scmd); if (rtn == SUCCESS) { - scmd->device->was_reset = 1; - scmd->device->expecting_cc_ua = 1; + spin_lock_irqsave(host->host_lock, flags); + __starget_for_each_device(scsi_target(scmd->device), NULL, + __scsi_report_device_reset); + spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } -static int __scsi_try_to_abort_cmd(struct scsi_cmnd *scmd) +/** + * scsi_try_bus_device_reset - Ask host to perform a BDR on a dev + * @scmd: SCSI cmd used to send BDR + * + * Notes: + * There is no timeout for this operation. if this operation is + * unreliable for a given host, then the host itself needs to put a + * timer on it, and set the host back to a consistent state prior to + * returning. + */ +static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd) { - if (!scmd->device->host->hostt->eh_abort_handler) + int rtn; + struct scsi_host_template *hostt = scmd->device->host->hostt; + + if (!hostt->eh_device_reset_handler) return FAILED; - return scmd->device->host->hostt->eh_abort_handler(scmd); + rtn = hostt->eh_device_reset_handler(scmd); + if (rtn == SUCCESS) + __scsi_report_device_reset(scmd->device, NULL); + return rtn; } -/** - * scsi_try_to_abort_cmd - Ask host to abort a running command. - * @scmd: SCSI cmd to abort from Lower Level. - * - * Notes: - * This function will not return until the user's completion function - * has been called. there is no timeout on this operation. if the - * author of the low-level driver wishes this operation to be timed, - * they can provide this facility themselves. helper functions in - * scsi_error.c can be supplied to make this easier to do. - */ -static int scsi_try_to_abort_cmd(struct scsi_cmnd *scmd) +static int scsi_try_to_abort_cmd(struct scsi_host_template *hostt, struct scsi_cmnd *scmd) { - /* - * scsi_done was called just after the command timed out and before - * we had a chance to process it. (db) - */ - if (scmd->serial_number == 0) - return SUCCESS; - return __scsi_try_to_abort_cmd(scmd); + if (!hostt->eh_abort_handler) + return FAILED; + + return hostt->eh_abort_handler(scmd); } static void scsi_abort_eh_cmnd(struct scsi_cmnd *scmd) { - if (__scsi_try_to_abort_cmd(scmd) != SUCCESS) + if (scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd) != SUCCESS) if (scsi_try_bus_device_reset(scmd) != SUCCESS) - if (scsi_try_bus_reset(scmd) != SUCCESS) - scsi_try_host_reset(scmd); + if (scsi_try_target_reset(scmd) != SUCCESS) + if (scsi_try_bus_reset(scmd) != SUCCESS) + scsi_try_host_reset(scmd); } /** - * 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 - * @cmnd_size: size in bytes of @cmnd + * @cmnd_size: size in bytes of @cmnd (must be <= BLK_MAX_CDB) * @sense_bytes: size of sense data to copy. or 0 (if != 0 @cmnd is ignored) * * This function is used to save a scsi command information before re-execution @@ -615,14 +912,21 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, * command. */ ses->cmd_len = scmd->cmd_len; - memcpy(ses->cmnd, scmd->cmnd, sizeof(scmd->cmnd)); + ses->cmnd = scmd->cmnd; ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->next_rq = scmd->request->next_rq; ses->result = scmd->result; + ses->underflow = scmd->underflow; + ses->prot_op = scmd->prot_op; + scmd->prot_op = SCSI_PROT_NORMAL; + scmd->eh_eflags = 0; + scmd->cmnd = ses->eh_cmnd; + memset(scmd->cmnd, 0, BLK_MAX_CDB); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->request->next_rq = NULL; + scmd->result = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, @@ -632,14 +936,13 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, scmd->sdb.table.sgl = &ses->sense_sgl; scmd->sc_data_direction = DMA_FROM_DEVICE; scmd->sdb.table.nents = 1; - memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); scmd->cmnd[0] = REQUEST_SENSE; scmd->cmnd[4] = scmd->sdb.length; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } else { scmd->sc_data_direction = DMA_NONE; if (cmnd) { - memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); + BUG_ON(cmnd_size > BLK_MAX_CDB); memcpy(scmd->cmnd, cmnd, cmnd_size); scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } @@ -660,11 +963,11 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, 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_prep_eh_cmnd + * @ses: saved information from a coresponding call to scsi_eh_prep_cmnd * - * Undo any damage done by above scsi_prep_eh_cmnd(). + * Undo any damage done by above scsi_eh_prep_cmnd(). */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { @@ -672,16 +975,18 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) * Restore original data */ scmd->cmd_len = ses->cmd_len; - memcpy(scmd->cmnd, ses->cmnd, sizeof(scmd->cmnd)); + scmd->cmnd = ses->cmnd; scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->request->next_rq = ses->next_rq; scmd->result = ses->result; + scmd->underflow = ses->underflow; + scmd->prot_op = ses->prot_op; } 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 @@ -700,56 +1005,75 @@ static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd, struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; DECLARE_COMPLETION_ONSTACK(done); - unsigned long timeleft; - unsigned long flags; + 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; - spin_lock_irqsave(shost->host_lock, flags); scsi_log_send(scmd); - shost->hostt->queuecommand(scmd, scsi_eh_done); - spin_unlock_irqrestore(shost->host_lock, flags); - - timeleft = wait_for_completion_timeout(&done, timeout); + scmd->scsi_done = scsi_eh_done; + 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); + rtn = SUCCESS; + } 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", - __FUNCTION__, scmd, timeleft)); + __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); SCSI_LOG_ERROR_RECOVERY(3, printk("%s: scsi_eh_completed_normally %x\n", - __FUNCTION__, rtn)); + __func__, rtn)); switch (rtn) { case SUCCESS: case NEEDS_RETRY: case FAILED: break; + case ADD_TO_MLQUEUE: + rtn = NEEDS_RETRY; + break; default: rtn = FAILED; break; } - } else { + } else if (!rtn) { scsi_abort_eh_cmnd(scmd); rtn = FAILED; } scsi_eh_restore_cmnd(scmd, &ses); + return rtn; } @@ -764,7 +1088,17 @@ static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd, */ static int scsi_request_sense(struct scsi_cmnd *scmd) { - return scsi_send_eh_cmnd(scmd, NULL, 0, SENSE_TIMEOUT, ~0); + return scsi_send_eh_cmnd(scmd, NULL, 0, scmd->device->eh_timeout, ~0); +} + +static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) +{ + 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, rtn); + } + return rtn; } /** @@ -794,7 +1128,7 @@ EXPORT_SYMBOL(scsi_eh_finish_cmd); * * Description: * See if we need to request sense information. if so, then get it - * now, so we have a better idea of what to do. + * now, so we have a better idea of what to do. * * Notes: * This has the unfortunate side effect that if a shost adapter does @@ -811,6 +1145,7 @@ int scsi_eh_get_sense(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; + struct Scsi_Host *shost; int rtn; list_for_each_entry_safe(scmd, next, work_q, eh_entry) { @@ -818,6 +1153,23 @@ int scsi_eh_get_sense(struct list_head *work_q, SCSI_SENSE_VALID(scmd)) continue; + shost = scmd->device->host; + if (scsi_host_eh_past_deadline(shost)) { + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + break; + } + if (status_byte(scmd->result) != CHECK_CONDITION) + /* + * don't request sense if there's no check condition + * status because the error we're processing isn't one + * that has a sense code (and some devices get + * confused by sense requests out of the blue) + */ + continue; + SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd, "%s: requesting sense\n", current->comm)); @@ -865,10 +1217,11 @@ static int scsi_eh_tur(struct scsi_cmnd *scmd) int retry_cnt = 1, rtn; retry_tur: - rtn = scsi_send_eh_cmnd(scmd, tur_command, 6, SENSE_TIMEOUT, 0); + rtn = scsi_send_eh_cmnd(scmd, tur_command, 6, + scmd->device->eh_timeout, 0); SCSI_LOG_ERROR_RECOVERY(3, printk("%s: scmd %p rtn %x\n", - __FUNCTION__, scmd, rtn)); + __func__, scmd, rtn)); switch (rtn) { case NEEDS_RETRY: @@ -883,6 +1236,62 @@ retry_tur: } /** + * scsi_eh_test_devices - check if devices are responding from error recovery. + * @cmd_list: scsi commands in error recovery. + * @work_q: queue for commands which still need more error recovery + * @done_q: queue for commands which are finished + * @try_stu: boolean on if a STU command should be tried in addition to TUR. + * + * Decription: + * Tests if devices are in a working state. Commands to devices now in + * a working state are sent to the done_q while commands to devices which + * are still failing to respond are returned to the work_q for more + * processing. + **/ +static int scsi_eh_test_devices(struct list_head *cmd_list, + struct list_head *work_q, + struct list_head *done_q, int try_stu) +{ + struct scsi_cmnd *scmd, *next; + struct scsi_device *sdev; + int finish_cmds; + + while (!list_empty(cmd_list)) { + scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry); + sdev = scmd->device; + + if (!try_stu) { + if (scsi_host_eh_past_deadline(sdev->host)) { + /* Push items back onto work_q */ + list_splice_init(cmd_list, work_q); + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, sdev->host, + "skip %s, past eh deadline", + __func__)); + break; + } + } + + finish_cmds = !scsi_device_online(scmd->device) || + (try_stu && !scsi_eh_try_stu(scmd) && + !scsi_eh_tur(scmd)) || + !scsi_eh_tur(scmd); + + list_for_each_entry_safe(scmd, next, cmd_list, eh_entry) + if (scmd->device == sdev) { + if (finish_cmds && + (try_stu || + scsi_eh_action(scmd, SUCCESS) == SUCCESS)) + scsi_eh_finish_cmd(scmd, done_q); + else + list_move_tail(&scmd->eh_entry, work_q); + } + } + return list_empty(work_q); +} + + +/** * scsi_eh_abort_cmds - abort pending commands. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. @@ -898,31 +1307,43 @@ static int scsi_eh_abort_cmds(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; + LIST_HEAD(check_list); int rtn; + struct Scsi_Host *shost; list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (!(scmd->eh_eflags & SCSI_EH_CANCEL_CMD)) continue; + shost = scmd->device->host; + if (scsi_host_eh_past_deadline(shost)) { + list_splice_init(&check_list, work_q); + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + return list_empty(work_q); + } SCSI_LOG_ERROR_RECOVERY(3, printk("%s: aborting cmd:" "0x%p\n", current->comm, scmd)); - rtn = scsi_try_to_abort_cmd(scmd); - if (rtn == SUCCESS) { - scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD; - if (!scsi_device_online(scmd->device) || - !scsi_eh_tur(scmd)) { - scsi_eh_finish_cmd(scmd, done_q); - } - - } else + rtn = scsi_try_to_abort_cmd(shost->hostt, scmd); + if (rtn == FAILED) { SCSI_LOG_ERROR_RECOVERY(3, printk("%s: aborting" " cmd failed:" "0x%p\n", current->comm, scmd)); + list_splice_init(&check_list, work_q); + return list_empty(work_q); + } + scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD; + if (rtn == FAST_IO_FAIL) + scsi_eh_finish_cmd(scmd, done_q); + else + list_move_tail(&scmd->eh_entry, &check_list); } - return list_empty(work_q); + return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** @@ -940,8 +1361,7 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd) int i, rtn = NEEDS_RETRY; for (i = 0; rtn == NEEDS_RETRY && i < 2; i++) - rtn = scsi_send_eh_cmnd(scmd, stu_command, 6, - scmd->device->timeout, 0); + rtn = scsi_send_eh_cmnd(scmd, stu_command, 6, scmd->device->request_queue->rq_timeout, 0); if (rtn == SUCCESS) return 0; @@ -958,7 +1378,7 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd) * * Notes: * If commands are failing due to not ready, initializing command required, - * try revalidating the device, which will end up sending a start unit. + * try revalidating the device, which will end up sending a start unit. */ static int scsi_eh_stu(struct Scsi_Host *shost, struct list_head *work_q, @@ -968,6 +1388,13 @@ static int scsi_eh_stu(struct Scsi_Host *shost, struct scsi_device *sdev; shost_for_each_device(sdev, shost) { + if (scsi_host_eh_past_deadline(shost)) { + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + break; + } stu_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev && SCSI_SENSE_VALID(scmd) && @@ -987,7 +1414,8 @@ static int scsi_eh_stu(struct Scsi_Host *shost, !scsi_eh_tur(stu_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { - if (scmd->device == sdev) + if (scmd->device == sdev && + scsi_eh_action(scmd, SUCCESS) == SUCCESS) scsi_eh_finish_cmd(scmd, done_q); } } @@ -1012,7 +1440,7 @@ static int scsi_eh_stu(struct Scsi_Host *shost, * Try a bus device reset. Still, look to see whether we have multiple * devices that are jammed or not - if we have multiple devices, it * makes no sense to try bus_device_reset - we really would need to try - * a bus_reset instead. + * a bus_reset instead. */ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, struct list_head *work_q, @@ -1023,6 +1451,13 @@ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, int rtn; shost_for_each_device(sdev, shost) { + if (scsi_host_eh_past_deadline(shost)) { + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + break; + } bdr_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev) { @@ -1037,12 +1472,14 @@ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, " 0x%p\n", current->comm, sdev)); rtn = scsi_try_bus_device_reset(bdr_scmd); - if (rtn == SUCCESS) { + if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { if (!scsi_device_online(sdev) || + rtn == FAST_IO_FAIL || !scsi_eh_tur(bdr_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { - if (scmd->device == sdev) + if (scmd->device == sdev && + scsi_eh_action(scmd, rtn) != FAILED) scsi_eh_finish_cmd(scmd, done_q); } @@ -1060,7 +1497,70 @@ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, } /** - * scsi_eh_bus_reset - send a bus reset + * scsi_eh_target_reset - send target reset if needed + * @shost: scsi host being recovered. + * @work_q: &list_head for pending commands. + * @done_q: &list_head for processed commands. + * + * Notes: + * Try a target reset. + */ +static int scsi_eh_target_reset(struct Scsi_Host *shost, + struct list_head *work_q, + struct list_head *done_q) +{ + LIST_HEAD(tmp_list); + LIST_HEAD(check_list); + + list_splice_init(work_q, &tmp_list); + + while (!list_empty(&tmp_list)) { + struct scsi_cmnd *next, *scmd; + int rtn; + unsigned int id; + + if (scsi_host_eh_past_deadline(shost)) { + /* push back on work queue for further processing */ + list_splice_init(&check_list, work_q); + list_splice_init(&tmp_list, work_q); + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + return list_empty(work_q); + } + + scmd = list_entry(tmp_list.next, struct scsi_cmnd, eh_entry); + id = scmd_id(scmd); + + SCSI_LOG_ERROR_RECOVERY(3, printk("%s: Sending target reset " + "to target %d\n", + current->comm, id)); + rtn = scsi_try_target_reset(scmd); + if (rtn != SUCCESS && rtn != FAST_IO_FAIL) + SCSI_LOG_ERROR_RECOVERY(3, printk("%s: Target reset" + " failed target: " + "%d\n", + current->comm, id)); + list_for_each_entry_safe(scmd, next, &tmp_list, eh_entry) { + if (scmd_id(scmd) != id) + continue; + + if (rtn == SUCCESS) + list_move_tail(&scmd->eh_entry, &check_list); + else if (rtn == FAST_IO_FAIL) + scsi_eh_finish_cmd(scmd, done_q); + else + /* push back on work queue for further processing */ + list_move(&scmd->eh_entry, work_q); + } + } + + return scsi_eh_test_devices(&check_list, work_q, done_q, 0); +} + +/** + * scsi_eh_bus_reset - send a bus reset * @shost: &scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. @@ -1070,6 +1570,7 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost, struct list_head *done_q) { struct scsi_cmnd *scmd, *chan_scmd, *next; + LIST_HEAD(check_list); unsigned int channel; int rtn; @@ -1077,10 +1578,19 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost, * we really want to loop over the various channels, and do this on * a channel by channel basis. we should also check to see if any * of the failed commands are on soft_reset devices, and if so, skip - * the reset. + * the reset. */ for (channel = 0; channel <= shost->max_channel; channel++) { + if (scsi_host_eh_past_deadline(shost)) { + list_splice_init(&check_list, work_q); + SCSI_LOG_ERROR_RECOVERY(3, + shost_printk(KERN_INFO, shost, + "skip %s, past eh deadline\n", + __func__)); + return list_empty(work_q); + } + chan_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) { if (channel == scmd_channel(scmd)) { @@ -1099,13 +1609,16 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost, " %d\n", current->comm, channel)); rtn = scsi_try_bus_reset(chan_scmd); - if (rtn == SUCCESS) { + if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { - if (channel == scmd_channel(scmd)) - if (!scsi_device_online(scmd->device) || - !scsi_eh_tur(scmd)) + if (channel == scmd_channel(scmd)) { + if (rtn == FAST_IO_FAIL) scsi_eh_finish_cmd(scmd, done_q); + else + list_move_tail(&scmd->eh_entry, + &check_list); + } } } else { SCSI_LOG_ERROR_RECOVERY(3, printk("%s: BRST" @@ -1114,11 +1627,11 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost, channel)); } } - return list_empty(work_q); + return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** - * scsi_eh_host_reset - send a host reset + * scsi_eh_host_reset - send a host reset * @work_q: list_head for processed commands. * @done_q: list_head for processed commands. */ @@ -1126,6 +1639,7 @@ static int scsi_eh_host_reset(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; + LIST_HEAD(check_list); int rtn; if (!list_empty(work_q)) { @@ -1137,10 +1651,9 @@ static int scsi_eh_host_reset(struct list_head *work_q, rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) { + list_splice_init(work_q, &check_list); + } else if (rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { - if (!scsi_device_online(scmd->device) || - (!scsi_eh_try_stu(scmd) && !scsi_eh_tur(scmd)) || - !scsi_eh_tur(scmd)) scsi_eh_finish_cmd(scmd, done_q); } } else { @@ -1149,7 +1662,7 @@ static int scsi_eh_host_reset(struct list_head *work_q, current->comm)); } } - return list_empty(work_q); + return scsi_eh_test_devices(&check_list, work_q, done_q, 1); } /** @@ -1177,6 +1690,45 @@ static void scsi_eh_offline_sdevs(struct list_head *work_q, } /** + * scsi_noretry_cmd - determine if command should be failed fast + * @scmd: SCSI cmd to examine. + */ +int scsi_noretry_cmd(struct scsi_cmnd *scmd) +{ + switch (host_byte(scmd->result)) { + case DID_OK: + break; + case DID_TIME_OUT: + goto check_type; + case DID_BUS_BUSY: + return (scmd->request->cmd_flags & REQ_FAILFAST_TRANSPORT); + case DID_PARITY: + return (scmd->request->cmd_flags & REQ_FAILFAST_DEV); + case DID_ERROR: + if (msg_byte(scmd->result) == COMMAND_COMPLETE && + status_byte(scmd->result) == RESERVATION_CONFLICT) + return 0; + /* fall through */ + case DID_SOFT_ERROR: + return (scmd->request->cmd_flags & REQ_FAILFAST_DRIVER); + } + + if (status_byte(scmd->result) != CHECK_CONDITION) + return 0; + +check_type: + /* + * assume caller has checked sense and determined + * the check condition was retryable. + */ + if (scmd->request->cmd_flags & REQ_FAILFAST_DEV || + scmd->request->cmd_type == REQ_TYPE_BLOCK_PC) + return 1; + else + return 0; +} + +/** * scsi_decide_disposition - Disposition a cmd on return from LLD. * @scmd: SCSI cmd to examine. * @@ -1201,7 +1753,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) if (!scsi_device_online(scmd->device)) { SCSI_LOG_ERROR_RECOVERY(5, printk("%s: device offline - report" " as SUCCESS\n", - __FUNCTION__)); + __func__)); return SUCCESS; } @@ -1223,9 +1775,13 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) * looks good. drop through, and check the next byte. */ break; + case DID_ABORT: + if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { + set_host_byte(scmd, DID_TIME_OUT); + return SUCCESS; + } case DID_NO_CONNECT: case DID_BAD_TARGET: - case DID_ABORT: /* * note - this means that we just report the status back * to the top level driver, not that we actually think @@ -1234,7 +1790,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) return SUCCESS; /* * when the low level driver returns did_soft_error, - * it is responsible for keeping an internal retry counter + * it is responsible for keeping an internal retry counter * in order to avoid endless loops (db) * * actually this is a bug in this function here. we should @@ -1248,7 +1804,21 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) case DID_REQUEUE: return ADD_TO_MLQUEUE; - + case DID_TRANSPORT_DISRUPTED: + /* + * LLD/transport was disrupted during processing of the IO. + * The transport class is now blocked/blocking, + * and the transport will decide what to do with the IO + * based on its timers and recovery capablilities if + * there are enough retries. + */ + goto maybe_retry; + case DID_TRANSPORT_FAILFAST: + /* + * The transport decided to failfast the IO (most likely + * the fast io fail tmo fired), so send IO directly upwards. + */ + return SUCCESS; case DID_ERROR: if (msg_byte(scmd->result) == COMMAND_COMPLETE && status_byte(scmd->result) == RESERVATION_CONFLICT) @@ -1258,7 +1828,6 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) */ break; /* fallthrough */ - case DID_BUS_BUSY: case DID_PARITY: goto maybe_retry; @@ -1291,6 +1860,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) */ switch (status_byte(scmd->result)) { case QUEUE_FULL: + scsi_handle_queue_full(scmd->device); /* * the case of trying to send too many commands to a * tagged queueing device. @@ -1304,9 +1874,13 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) */ return ADD_TO_MLQUEUE; case GOOD: + if (scmd->cmnd[0] == REPORT_LUNS) + scmd->device->sdev_target->expecting_lun_change = 0; + scsi_handle_queue_ramp_up(scmd->device); case COMMAND_TERMINATED: - case TASK_ABORTED: return SUCCESS; + case TASK_ABORTED: + goto maybe_retry; case CHECK_CONDITION: rtn = scsi_check_sense(scmd); if (rtn == NEEDS_RETRY) @@ -1328,6 +1902,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) case RESERVATION_CONFLICT: sdev_printk(KERN_INFO, scmd->device, "reservation conflict\n"); + set_host_byte(scmd, DID_NEXUS_FAILURE); return SUCCESS; /* causes immediate i/o error */ default: return FAILED; @@ -1341,7 +1916,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) * even if the request is marked fast fail, we still requeue * for queue congestion conditions (QUEUE_FULL or BUSY) */ if ((++scmd->retries) <= scmd->allowed - && !blk_noretry_request(scmd->request)) { + && !scsi_noretry_cmd(scmd)) { return NEEDS_RETRY; } else { /* @@ -1351,41 +1926,49 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) } } +static void eh_lock_door_done(struct request *req, int uptodate) +{ + __blk_put_request(req->q, req); +} + /** * scsi_eh_lock_door - Prevent medium removal for the specified device * @sdev: SCSI device to prevent medium removal * * Locking: - * We must be called from process context; scsi_allocate_request() - * may sleep. + * We must be called from process context. * * Notes: * We queue up an asynchronous "ALLOW MEDIUM REMOVAL" request on the * head of the devices request queue, and continue. - * - * Bugs: - * scsi_allocate_request() may sleep waiting for existing requests to - * be processed. However, since we haven't kicked off any request - * processing for this host, this may deadlock. - * - * If scsi_allocate_request() fails for what ever reason, we - * completely forget to lock the door. */ static void scsi_eh_lock_door(struct scsi_device *sdev) { - unsigned char cmnd[MAX_COMMAND_SIZE]; + struct request *req; - cmnd[0] = ALLOW_MEDIUM_REMOVAL; - cmnd[1] = 0; - cmnd[2] = 0; - cmnd[3] = 0; - cmnd[4] = SCSI_REMOVAL_PREVENT; - cmnd[5] = 0; + /* + * blk_get_request with GFP_KERNEL (__GFP_WAIT) sleeps until a + * request becomes available + */ + req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL); - scsi_execute_async(sdev, cmnd, 6, DMA_NONE, NULL, 0, 0, 10 * HZ, - 5, NULL, NULL, GFP_KERNEL); -} + blk_rq_set_block_pc(req); + req->cmd[0] = ALLOW_MEDIUM_REMOVAL; + req->cmd[1] = 0; + req->cmd[2] = 0; + req->cmd[3] = 0; + req->cmd[4] = SCSI_REMOVAL_PREVENT; + req->cmd[5] = 0; + + req->cmd_len = COMMAND_SIZE(req->cmd[0]); + + req->cmd_flags |= REQ_QUIET; + req->timeout = 10 * HZ; + req->retries = 5; + + blk_execute_rq_nowait(req->q, NULL, req, 1, eh_lock_door_done); +} /** * scsi_restart_operations - restart io operations to the specified host. @@ -1415,8 +1998,9 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * will be requests for character device operations, and also for * ioctls to queued block devices. */ - SCSI_LOG_ERROR_RECOVERY(3, printk("%s: waking up host to restart\n", - __FUNCTION__)); + SCSI_LOG_ERROR_RECOVERY(3, + printk("scsi_eh_%d waking up host to restart\n", + shost->host_no)); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RUNNING)) @@ -1433,6 +2017,20 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * 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); } /** @@ -1447,9 +2045,11 @@ void scsi_eh_ready_devs(struct Scsi_Host *shost, { if (!scsi_eh_stu(shost, work_q, done_q)) if (!scsi_eh_bus_device_reset(shost, work_q, done_q)) - if (!scsi_eh_bus_reset(shost, work_q, done_q)) - if (!scsi_eh_host_reset(work_q, done_q)) - scsi_eh_offline_sdevs(work_q, done_q); + if (!scsi_eh_target_reset(shost, work_q, done_q)) + if (!scsi_eh_bus_reset(shost, work_q, done_q)) + if (!scsi_eh_host_reset(work_q, done_q)) + scsi_eh_offline_sdevs(work_q, + done_q); } EXPORT_SYMBOL_GPL(scsi_eh_ready_devs); @@ -1464,7 +2064,7 @@ void scsi_eh_flush_done_q(struct list_head *done_q) list_for_each_entry_safe(scmd, next, done_q, eh_entry) { list_del_init(&scmd->eh_entry); if (scsi_device_online(scmd->device) && - !blk_noretry_request(scmd->request) && + !scsi_noretry_cmd(scmd) && (++scmd->retries <= scmd->allowed)) { SCSI_LOG_ERROR_RECOVERY(3, printk("%s: flush" " retry cmd: %p\n", @@ -1527,6 +2127,10 @@ static void scsi_unjam_host(struct Scsi_Host *shost) if (!scsi_eh_abort_cmds(&eh_work_q, &eh_done_q)) scsi_eh_ready_devs(shost, &eh_work_q, &eh_done_q); + spin_lock_irqsave(shost->host_lock, flags); + if (shost->eh_deadline != -1) + shost->last_reset = 0; + spin_unlock_irqrestore(shost->host_lock, flags); scsi_eh_flush_done_q(&eh_done_q); } @@ -1546,30 +2150,38 @@ int scsi_error_handler(void *data) * We use TASK_INTERRUPTIBLE so that the thread is not * counted against the load average as a running process. * We never actually get interrupted because kthread_run - * disables singal delivery for the created thread. + * 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", + printk("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)); + printk("scsi_eh_%d: waking up %d/%d/%d\n", + shost->host_no, shost->host_eh_scheduled, + shost->host_failed, shost->host_busy)); /* * We have a host that is failing for some reason. Figure out * 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 (!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", + shost->host_no)); + continue; + } + if (shost->transportt->eh_strategy_handler) shost->transportt->eh_strategy_handler(shost); else @@ -1583,7 +2195,8 @@ int scsi_error_handler(void *data) * which are still online. */ scsi_restart_operations(shost); - set_current_state(TASK_INTERRUPTIBLE); + if (!shost->eh_noresume) + scsi_autopm_put_host(shost); } __set_current_state(TASK_RUNNING); @@ -1619,10 +2232,8 @@ void scsi_report_bus_reset(struct Scsi_Host *shost, int channel) struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { - if (channel == sdev_channel(sdev)) { - sdev->was_reset = 1; - sdev->expecting_cc_ua = 1; - } + if (channel == sdev_channel(sdev)) + __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_bus_reset); @@ -1655,10 +2266,8 @@ void scsi_report_device_reset(struct Scsi_Host *shost, int channel, int target) __shost_for_each_device(sdev, shost) { if (channel == sdev_channel(sdev) && - target == sdev_id(sdev)) { - sdev->was_reset = 1; - sdev->expecting_cc_ua = 1; - } + target == sdev_id(sdev)) + __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_device_reset); @@ -1684,17 +2293,32 @@ scsi_reset_provider_done_command(struct scsi_cmnd *scmd) int scsi_reset_provider(struct scsi_device *dev, int flag) { - struct scsi_cmnd *scmd = scsi_get_command(dev, GFP_KERNEL); + struct scsi_cmnd *scmd; struct Scsi_Host *shost = dev->host; struct request req; unsigned long flags; int rtn; + if (scsi_autopm_get_host(shost) < 0) + return FAILED; + + if (!get_device(&dev->sdev_gendev)) { + rtn = FAILED; + goto out_put_autopm_host; + } + + scmd = scsi_get_command(dev, GFP_KERNEL); + if (!scmd) { + rtn = FAILED; + put_device(&dev->sdev_gendev); + goto out_put_autopm_host; + } + + blk_rq_init(NULL, &req); scmd->request = &req; - memset(&scmd->eh_timeout, 0, sizeof(scmd->eh_timeout)); - memset(&scmd->cmnd, '\0', sizeof(scmd->cmnd)); - + scmd->cmnd = req.cmd; + scmd->scsi_done = scsi_reset_provider_done_command; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); @@ -1702,8 +2326,6 @@ scsi_reset_provider(struct scsi_device *dev, int flag) scmd->sc_data_direction = DMA_BIDIRECTIONAL; - init_timer(&scmd->eh_timeout); - spin_lock_irqsave(shost->host_lock, flags); shost->tmf_in_progress = 1; spin_unlock_irqrestore(shost->host_lock, flags); @@ -1714,6 +2336,11 @@ scsi_reset_provider(struct scsi_device *dev, int flag) if (rtn == SUCCESS) break; /* FALLTHROUGH */ + case SCSI_TRY_RESET_TARGET: + rtn = scsi_try_target_reset(scmd); + if (rtn == SUCCESS) + break; + /* FALLTHROUGH */ case SCSI_TRY_RESET_BUS: rtn = scsi_try_bus_reset(scmd); if (rtn == SUCCESS) @@ -1736,13 +2363,15 @@ scsi_reset_provider(struct scsi_device *dev, int flag) */ SCSI_LOG_ERROR_RECOVERY(3, printk("%s: waking up host to restart after TMF\n", - __FUNCTION__)); + __func__)); wake_up(&shost->host_wait); scsi_run_host_queues(shost); scsi_next_command(scmd); +out_put_autopm_host: + scsi_autopm_put_host(shost); return rtn; } EXPORT_SYMBOL(scsi_reset_provider); @@ -1792,7 +2421,7 @@ int scsi_normalize_sense(const u8 *sense_buffer, int sb_len, if (sb_len > 7) sshdr->additional_length = sense_buffer[7]; } else { - /* + /* * fixed format */ if (sb_len > 2) @@ -1907,3 +2536,31 @@ int scsi_get_sense_info_fld(const u8 * sense_buffer, int sb_len, } } EXPORT_SYMBOL(scsi_get_sense_info_fld); + +/** + * scsi_build_sense_buffer - build sense data in a buffer + * @desc: Sense format (non zero == descriptor format, + * 0 == fixed format) + * @buf: Where to build sense data + * @key: Sense key + * @asc: Additional sense code + * @ascq: Additional sense code qualifier + * + **/ +void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq) +{ + if (desc) { + buf[0] = 0x72; /* descriptor, current */ + buf[1] = key; + buf[2] = asc; + buf[3] = ascq; + buf[7] = 0; + } else { + buf[0] = 0x70; /* fixed, current */ + buf[2] = key; + buf[7] = 0xa; + buf[12] = asc; + buf[13] = ascq; + } +} +EXPORT_SYMBOL(scsi_build_sense_buffer); |