diff options
Diffstat (limited to 'drivers/ata/libata-eh.c')
| -rw-r--r-- | drivers/ata/libata-eh.c | 181 |
1 files changed, 128 insertions, 53 deletions
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index a9b28203800..dad83df555c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1,7 +1,7 @@ /* * libata-eh.c - libata error handling * - * Maintained by: Jeff Garzik <jgarzik@pobox.com> + * Maintained by: Tejun Heo <tj@kernel.org> * Please ALWAYS copy linux-ide@vger.kernel.org * on emails. * @@ -95,12 +95,13 @@ enum { * represents timeout for that try. The first try can be soft or * hardreset. All others are hardreset if available. In most cases * the first reset w/ 10sec timeout should succeed. Following entries - * are mostly for error handling, hotplug and retarded devices. + * are mostly for error handling, hotplug and those outlier devices that + * take an exceptionally long time to recover from reset. */ static const unsigned long ata_eh_reset_timeouts[] = { 10000, /* most drives spin up by 10sec */ 10000, /* > 99% working drives spin up before 20sec */ - 35000, /* give > 30 secs of idleness for retarded devices */ + 35000, /* give > 30 secs of idleness for outlier devices */ 5000, /* and sweet one last chance */ ULONG_MAX, /* > 1 min has elapsed, give up */ }; @@ -419,7 +420,7 @@ int ata_ering_map(struct ata_ering *ering, return rc; } -int ata_ering_clear_cb(struct ata_ering_entry *ent, void *void_arg) +static int ata_ering_clear_cb(struct ata_ering_entry *ent, void *void_arg) { ent->eflags |= ATA_EFLAG_OLD_ER; return 0; @@ -793,12 +794,12 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ata_for_each_link(link, ap, HOST_FIRST) memset(&link->eh_info, 0, sizeof(link->eh_info)); - /* Clear host_eh_scheduled while holding ap->lock such - * that if exception occurs after this point but - * before EH completion, SCSI midlayer will + /* end eh (clear host_eh_scheduled) while holding + * ap->lock such that if exception occurs after this + * point but before EH completion, SCSI midlayer will * re-initiate EH. */ - host->host_eh_scheduled = 0; + ap->ops->end_eh(ap); spin_unlock_irqrestore(ap->lock, flags); ata_eh_release(ap); @@ -863,6 +864,7 @@ void ata_port_wait_eh(struct ata_port *ap) goto retry; } } +EXPORT_SYMBOL_GPL(ata_port_wait_eh); static int ata_eh_nr_in_flight(struct ata_port *ap) { @@ -985,16 +987,13 @@ void ata_qc_schedule_eh(struct ata_queued_cmd *qc) } /** - * ata_port_schedule_eh - schedule error handling without a qc - * @ap: ATA port to schedule EH for - * - * Schedule error handling for @ap. EH will kick in as soon as - * all commands are drained. + * ata_std_sched_eh - non-libsas ata_ports issue eh with this common routine + * @ap: ATA port to schedule EH for * - * LOCKING: + * LOCKING: inherited from ata_port_schedule_eh * spin_lock_irqsave(host lock) */ -void ata_port_schedule_eh(struct ata_port *ap) +void ata_std_sched_eh(struct ata_port *ap) { WARN_ON(!ap->ops->error_handler); @@ -1006,6 +1005,44 @@ void ata_port_schedule_eh(struct ata_port *ap) DPRINTK("port EH scheduled\n"); } +EXPORT_SYMBOL_GPL(ata_std_sched_eh); + +/** + * ata_std_end_eh - non-libsas ata_ports complete eh with this common routine + * @ap: ATA port to end EH for + * + * In the libata object model there is a 1:1 mapping of ata_port to + * shost, so host fields can be directly manipulated under ap->lock, in + * the libsas case we need to hold a lock at the ha->level to coordinate + * these events. + * + * LOCKING: + * spin_lock_irqsave(host lock) + */ +void ata_std_end_eh(struct ata_port *ap) +{ + struct Scsi_Host *host = ap->scsi_host; + + host->host_eh_scheduled = 0; +} +EXPORT_SYMBOL(ata_std_end_eh); + + +/** + * ata_port_schedule_eh - schedule error handling without a qc + * @ap: ATA port to schedule EH for + * + * Schedule error handling for @ap. EH will kick in as soon as + * all commands are drained. + * + * LOCKING: + * spin_lock_irqsave(host lock) + */ +void ata_port_schedule_eh(struct ata_port *ap) +{ + /* see: ata_std_sched_eh, unless you know better */ + ap->ops->sched_eh(ap); +} static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link) { @@ -1286,14 +1323,14 @@ void ata_eh_qc_complete(struct ata_queued_cmd *qc) * should be retried. To be used from EH. * * SCSI midlayer limits the number of retries to scmd->allowed. - * scmd->retries is decremented for commands which get retried + * scmd->allowed is incremented for commands which get retried * due to unrelated failures (qc->err_mask is zero). */ void ata_eh_qc_retry(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; - if (!qc->err_mask && scmd->retries) - scmd->retries--; + if (!qc->err_mask) + scmd->allowed++; __ata_eh_qc_complete(qc); } @@ -1451,6 +1488,7 @@ static const char *ata_err_string(unsigned int err_mask) /** * ata_read_log_page - read a specific log page * @dev: target device + * @log: log to read * @page: page to read * @buf: buffer to store read page * @sectors: number of sectors to read @@ -1463,17 +1501,18 @@ static const char *ata_err_string(unsigned int err_mask) * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ -static unsigned int ata_read_log_page(struct ata_device *dev, - u8 page, void *buf, unsigned int sectors) +unsigned int ata_read_log_page(struct ata_device *dev, u8 log, + u8 page, void *buf, unsigned int sectors) { struct ata_taskfile tf; unsigned int err_mask; - DPRINTK("read log page - page %d\n", page); + DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); ata_tf_init(dev, &tf); tf.command = ATA_CMD_READ_LOG_EXT; - tf.lbal = page; + tf.lbal = log; + tf.lbam = page; tf.nsect = sectors; tf.hob_nsect = sectors >> 8; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_LBA48 | ATA_TFLAG_DEVICE; @@ -1509,7 +1548,7 @@ static int ata_eh_read_log_10h(struct ata_device *dev, u8 csum; int i; - err_mask = ata_read_log_page(dev, ATA_LOG_SATA_NCQ, buf, 1); + err_mask = ata_read_log_page(dev, ATA_LOG_SATA_NCQ, 0, buf, 1); if (err_mask) return -EIO; @@ -1553,7 +1592,7 @@ static int ata_eh_read_log_10h(struct ata_device *dev, * RETURNS: * 0 on success, AC_ERR_* mask on failure. */ -static unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key) +unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key) { u8 cdb[ATAPI_CDB_LEN] = { TEST_UNIT_READY, 0, 0, 0, 0, 0 }; struct ata_taskfile tf; @@ -1586,7 +1625,7 @@ static unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key) * RETURNS: * 0 on success, AC_ERR_* mask on failure */ -static unsigned int atapi_eh_request_sense(struct ata_device *dev, +unsigned int atapi_eh_request_sense(struct ata_device *dev, u8 *sense_buf, u8 dfl_sense_key) { u8 cdb[ATAPI_CDB_LEN] = @@ -1772,7 +1811,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, case ATA_DEV_ATA: if (err & ATA_ICRC) qc->err_mask |= AC_ERR_ATA_BUS; - if (err & ATA_UNC) + if (err & (ATA_UNC | ATA_AMNF)) qc->err_mask |= AC_ERR_MEDIA; if (err & ATA_IDNF) qc->err_mask |= AC_ERR_INVALID; @@ -2046,6 +2085,26 @@ static unsigned int ata_eh_speed_down(struct ata_device *dev, } /** + * ata_eh_worth_retry - analyze error and decide whether to retry + * @qc: qc to possibly retry + * + * Look at the cause of the error and decide if a retry + * might be useful or not. We don't want to retry media errors + * because the drive itself has probably already taken 10-30 seconds + * doing its own internal retries before reporting the failure. + */ +static inline int ata_eh_worth_retry(struct ata_queued_cmd *qc) +{ + if (qc->err_mask & AC_ERR_MEDIA) + return 0; /* don't retry media errors */ + if (qc->flags & ATA_QCFLAG_IO) + return 1; /* otherwise retry anything from fs stack */ + if (qc->err_mask & AC_ERR_INVALID) + return 0; /* don't retry these */ + return qc->err_mask != AC_ERR_DEV; /* retry if not dev error */ +} + +/** * ata_eh_link_autopsy - analyze error and determine recovery action * @link: host link to perform autopsy on * @@ -2119,9 +2178,7 @@ static void ata_eh_link_autopsy(struct ata_link *link) qc->err_mask &= ~(AC_ERR_DEV | AC_ERR_OTHER); /* determine whether the command is worth retrying */ - if (qc->flags & ATA_QCFLAG_IO || - (!(qc->err_mask & AC_ERR_INVALID) && - qc->err_mask != AC_ERR_DEV)) + if (ata_eh_worth_retry(qc)) qc->flags |= ATA_QCFLAG_RETRY; /* accumulate error info */ @@ -2237,6 +2294,7 @@ const char *ata_get_cmd_descript(u8 command) { ATA_CMD_IDLE, "IDLE" }, { ATA_CMD_EDD, "EXECUTE DEVICE DIAGNOSTIC" }, { ATA_CMD_DOWNLOAD_MICRO, "DOWNLOAD MICROCODE" }, + { ATA_CMD_DOWNLOAD_MICRO_DMA, "DOWNLOAD MICROCODE DMA" }, { ATA_CMD_NOP, "NOP" }, { ATA_CMD_FLUSH, "FLUSH CACHE" }, { ATA_CMD_FLUSH_EXT, "FLUSH CACHE EXT" }, @@ -2257,6 +2315,8 @@ const char *ata_get_cmd_descript(u8 command) { ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" }, { ATA_CMD_FPDMA_READ, "READ FPDMA QUEUED" }, { ATA_CMD_FPDMA_WRITE, "WRITE FPDMA QUEUED" }, + { ATA_CMD_FPDMA_SEND, "SEND FPDMA QUEUED" }, + { ATA_CMD_FPDMA_RECV, "RECEIVE FPDMA QUEUED" }, { ATA_CMD_PIO_READ, "READ SECTOR(S)" }, { ATA_CMD_PIO_READ_EXT, "READ SECTOR(S) EXT" }, { ATA_CMD_PIO_WRITE, "WRITE SECTOR(S)" }, @@ -2283,12 +2343,15 @@ const char *ata_get_cmd_descript(u8 command) { ATA_CMD_WRITE_LOG_EXT, "WRITE LOG EXT" }, { ATA_CMD_READ_LOG_DMA_EXT, "READ LOG DMA EXT" }, { ATA_CMD_WRITE_LOG_DMA_EXT, "WRITE LOG DMA EXT" }, + { ATA_CMD_TRUSTED_NONDATA, "TRUSTED NON-DATA" }, { ATA_CMD_TRUSTED_RCV, "TRUSTED RECEIVE" }, { ATA_CMD_TRUSTED_RCV_DMA, "TRUSTED RECEIVE DMA" }, { ATA_CMD_TRUSTED_SND, "TRUSTED SEND" }, { ATA_CMD_TRUSTED_SND_DMA, "TRUSTED SEND DMA" }, { ATA_CMD_PMP_READ, "READ BUFFER" }, + { ATA_CMD_PMP_READ_DMA, "READ BUFFER DMA" }, { ATA_CMD_PMP_WRITE, "WRITE BUFFER" }, + { ATA_CMD_PMP_WRITE_DMA, "WRITE BUFFER DMA" }, { ATA_CMD_CONF_OVERLAY, "DEVICE CONFIGURATION OVERLAY" }, { ATA_CMD_SEC_SET_PASS, "SECURITY SET PASSWORD" }, { ATA_CMD_SEC_UNLOCK, "SECURITY UNLOCK" }, @@ -2307,6 +2370,8 @@ const char *ata_get_cmd_descript(u8 command) { ATA_CMD_CFA_TRANS_SECT, "CFA TRANSLATE SECTOR" }, { ATA_CMD_CFA_ERASE, "CFA ERASE SECTORS" }, { ATA_CMD_CFA_WRITE_MULT_NE, "CFA WRITE MULTIPLE WITHOUT ERASE" }, + { ATA_CMD_REQ_SENSE_DATA, "REQUEST SENSE DATA EXT" }, + { ATA_CMD_SANITIZE_DEVICE, "SANITIZE DEVICE" }, { ATA_CMD_READ_LONG, "READ LONG (with retries)" }, { ATA_CMD_READ_LONG_ONCE, "READ LONG (without retries)" }, { ATA_CMD_WRITE_LONG, "WRITE LONG (with retries)" }, @@ -2338,7 +2403,7 @@ static void ata_eh_link_report(struct ata_link *link) struct ata_port *ap = link->ap; struct ata_eh_context *ehc = &link->eh_context; const char *frozen, *desc; - char tries_buf[6]; + char tries_buf[6] = ""; int tag, nr_failed = 0; if (ehc->i.flags & ATA_EHI_QUIET) @@ -2369,9 +2434,8 @@ static void ata_eh_link_report(struct ata_link *link) if (ap->pflags & ATA_PFLAG_FROZEN) frozen = " frozen"; - memset(tries_buf, 0, sizeof(tries_buf)); if (ap->eh_tries < ATA_EH_MAX_TRIES) - snprintf(tries_buf, sizeof(tries_buf) - 1, " t%d", + snprintf(tries_buf, sizeof(tries_buf), " t%d", ap->eh_tries); if (ehc->i.dev) { @@ -2492,11 +2556,12 @@ static void ata_eh_link_report(struct ata_link *link) } if (cmd->command != ATA_CMD_PACKET && - (res->feature & (ATA_ICRC | ATA_UNC | ATA_IDNF | - ATA_ABORTED))) - ata_dev_err(qc->dev, "error: { %s%s%s%s}\n", + (res->feature & (ATA_ICRC | ATA_UNC | ATA_AMNF | + ATA_IDNF | ATA_ABORTED))) + ata_dev_err(qc->dev, "error: { %s%s%s%s%s}\n", res->feature & ATA_ICRC ? "ICRC " : "", res->feature & ATA_UNC ? "UNC " : "", + res->feature & ATA_AMNF ? "AMNF " : "", res->feature & ATA_IDNF ? "IDNF " : "", res->feature & ATA_ABORTED ? "ABRT " : ""); #endif @@ -2569,6 +2634,8 @@ int ata_eh_reset(struct ata_link *link, int classify, */ while (ata_eh_reset_timeouts[max_tries] != ULONG_MAX) max_tries++; + if (link->flags & ATA_LFLAG_RST_ONCE) + max_tries = 1; if (link->flags & ATA_LFLAG_NO_HRST) hardreset = NULL; if (link->flags & ATA_LFLAG_NO_SRST) @@ -2599,6 +2666,7 @@ int ata_eh_reset(struct ata_link *link, int classify, * bus as we may be talking too fast. */ dev->pio_mode = XFER_PIO_0; + dev->dma_mode = 0xff; /* If the controller has a pio mode setup function * then use it to set the chipset to rights. Don't @@ -2950,7 +3018,7 @@ static inline void ata_eh_pull_park_action(struct ata_port *ap) * ourselves at the beginning of each pass over the loop. * * Additionally, all write accesses to &ap->park_req_pending - * through INIT_COMPLETION() (see below) or complete_all() + * through reinit_completion() (see below) or complete_all() * (see ata_scsi_park_store()) are protected by the host lock. * As a result we have that park_req_pending.done is zero on * exit from this function, i.e. when ATA_EH_PARK actions for @@ -2964,7 +3032,7 @@ static inline void ata_eh_pull_park_action(struct ata_port *ap) */ spin_lock_irqsave(ap->lock, flags); - INIT_COMPLETION(ap->park_req_pending); + reinit_completion(&ap->park_req_pending); ata_for_each_link(link, ap, EDGE) { ata_for_each_dev(dev, link, ALL) { struct ata_eh_info *ehi = &link->eh_info; @@ -3500,7 +3568,8 @@ static int ata_count_probe_trials_cb(struct ata_ering_entry *ent, void *void_arg u64 now = get_jiffies_64(); int *trials = void_arg; - if (ent->timestamp < now - min(now, interval)) + if ((ent->eflags & ATA_EFLAG_OLD_ER) || + (ent->timestamp < now - min(now, interval))) return -1; (*trials)++; @@ -3797,6 +3866,8 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset, rc = atapi_eh_clear_ua(dev); if (rc) goto rest_fail; + if (zpodd_dev_enabled(dev)) + zpodd_post_poweron(dev); } } @@ -3962,11 +4033,12 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) { unsigned long flags; int rc = 0; + struct ata_device *dev; /* are we suspending? */ spin_lock_irqsave(ap->lock, flags); if (!(ap->pflags & ATA_PFLAG_PM_PENDING) || - ap->pm_mesg.event == PM_EVENT_ON) { + ap->pm_mesg.event & PM_EVENT_RESUME) { spin_unlock_irqrestore(ap->lock, flags); return; } @@ -3974,6 +4046,18 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED); + /* + * If we have a ZPODD attached, check its zero + * power ready status before the port is frozen. + * Only needed for runtime suspend. + */ + if (PMSG_IS_AUTO(ap->pm_mesg)) { + ata_for_each_dev(dev, &ap->link, ENABLED) { + if (zpodd_dev_enabled(dev)) + zpodd_on_suspend(dev); + } + } + /* tell ACPI we're suspending */ rc = ata_acpi_on_suspend(ap); if (rc) @@ -3985,9 +4069,9 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) if (ap->ops->port_suspend) rc = ap->ops->port_suspend(ap, ap->pm_mesg); - ata_acpi_set_state(ap, PMSG_SUSPEND); + ata_acpi_set_state(ap, ap->pm_mesg); out: - /* report result */ + /* update the flags */ spin_lock_irqsave(ap->lock, flags); ap->pflags &= ~ATA_PFLAG_PM_PENDING; @@ -3996,11 +4080,6 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) else if (ap->pflags & ATA_PFLAG_FROZEN) ata_port_schedule_eh(ap); - if (ap->pm_result) { - *ap->pm_result = rc; - ap->pm_result = NULL; - } - spin_unlock_irqrestore(ap->lock, flags); return; @@ -4025,7 +4104,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) /* are we resuming? */ spin_lock_irqsave(ap->lock, flags); if (!(ap->pflags & ATA_PFLAG_PM_PENDING) || - ap->pm_mesg.event != PM_EVENT_ON) { + !(ap->pm_mesg.event & PM_EVENT_RESUME)) { spin_unlock_irqrestore(ap->lock, flags); return; } @@ -4044,7 +4123,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) ata_for_each_dev(dev, link, ALL) ata_ering_clear(&dev->ering); - ata_acpi_set_state(ap, PMSG_ON); + ata_acpi_set_state(ap, ap->pm_mesg); if (ap->ops->port_resume) rc = ap->ops->port_resume(ap); @@ -4052,13 +4131,9 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) /* tell ACPI that we're resuming */ ata_acpi_on_resume(ap); - /* report result */ + /* update the flags */ spin_lock_irqsave(ap->lock, flags); ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED); - if (ap->pm_result) { - *ap->pm_result = rc; - ap->pm_result = NULL; - } spin_unlock_irqrestore(ap->lock, flags); } #endif /* CONFIG_PM */ |