#include <scsi/scsi_eh.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
#include "../scsi/scsi_transport_api.h"
#include <linux/libata.h>
ATA_EH_FASTDRAIN_INTERVAL = 3000,
ATA_EH_UA_TRIES = 5,
+
+ /* probe speed down parameters, see ata_eh_schedule_probe() */
+ ATA_EH_PROBE_TRIAL_INTERVAL = 60000, /* 1 min */
+ ATA_EH_PROBE_TRIALS = 2,
};
/* The following table determines how we sequence resets. Each entry
ULONG_MAX,
};
+static const unsigned long ata_eh_flush_timeouts[] = {
+ 15000, /* be generous with flush */
+ 15000, /* ditto */
+ 30000, /* and even more generous */
+ ULONG_MAX,
+};
+
static const unsigned long ata_eh_other_timeouts[] = {
5000, /* same rationale as identify timeout */
10000, /* ditto */
.timeouts = ata_eh_other_timeouts, },
{ .commands = CMDS(ATA_CMD_INIT_DEV_PARAMS),
.timeouts = ata_eh_other_timeouts, },
+ { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT),
+ .timeouts = ata_eh_flush_timeouts },
};
#undef CMDS
/* For new EH, all qcs are finished in one of three ways -
* normal completion, error completion, and SCSI timeout.
- * Both cmpletions can race against SCSI timeout. When normal
+ * Both completions can race against SCSI timeout. When normal
* completion wins, the qc never reaches EH. When error
* completion wins, the qc has ATA_QCFLAG_FAILED set.
*
int nr_timedout = 0;
spin_lock_irqsave(ap->lock, flags);
-
+
+ /* This must occur under the ap->lock as we don't want
+ a polled recovery to race the real interrupt handler
+
+ The lost_interrupt handler checks for any completed but
+ non-notified command and completes much like an IRQ handler.
+
+ We then fall into the error recovery code which will treat
+ this as if normal completion won the race */
+
+ if (ap->ops->lost_interrupt)
+ ap->ops->lost_interrupt(ap);
+
list_for_each_entry_safe(scmd, tmp, &host->eh_cmd_q, eh_entry) {
struct ata_queued_cmd *qc;
ap->eh_tries = ATA_EH_MAX_TRIES;
} else
spin_unlock_wait(ap->lock);
+
+ /* If we timed raced normal completion and there is nothing to
+ recover nr_timedout == 0 why exactly are we doing error recovery ? */
repeat:
/* invoke error handler */
void ata_qc_schedule_eh(struct ata_queued_cmd *qc)
{
struct ata_port *ap = qc->ap;
+ struct request_queue *q = qc->scsicmd->device->request_queue;
+ unsigned long flags;
WARN_ON(!ap->ops->error_handler);
* Note that ATA_QCFLAG_FAILED is unconditionally set after
* this function completes.
*/
+ spin_lock_irqsave(q->queue_lock, flags);
blk_abort_request(qc->scsicmd->request);
+ spin_unlock_irqrestore(q->queue_lock, flags);
}
/**
* ata_port_freeze - abort & freeze port
* @ap: ATA port to freeze
*
- * Abort and freeze @ap.
+ * Abort and freeze @ap. The freeze operation must be called
+ * first, because some hardware requires special operations
+ * before the taskfile registers are accessible.
*
* LOCKING:
* spin_lock_irqsave(host lock)
WARN_ON(!ap->ops->error_handler);
- nr_aborted = ata_port_abort(ap);
__ata_port_freeze(ap);
+ nr_aborted = ata_port_abort(ap);
return nr_aborted;
}
ata_acpi_on_disable(dev);
ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 | ATA_DNXFER_QUIET);
dev->class++;
+
+ /* From now till the next successful probe, ering is used to
+ * track probe failures. Clear accumulated device error info.
+ */
+ ata_ering_clear(&dev->ering);
}
/**
}
/* okay, this error is ours */
+ memset(&tf, 0, sizeof(tf));
rc = ata_eh_read_log_10h(dev, &tag, &tf);
if (rc) {
ata_link_printk(link, KERN_ERR, "failed to read log page 10h "
/* speed down? */
if (verdict & ATA_EH_SPDN_SPEED_DOWN) {
/* speed down SATA link speed if possible */
- if (sata_down_spd_limit(link) == 0) {
+ if (sata_down_spd_limit(link, 0) == 0) {
action |= ATA_EH_RESET;
goto done;
}
qc->err_mask &= ~(AC_ERR_DEV | AC_ERR_OTHER);
/* determine whether the command is worth retrying */
- if (!(qc->err_mask & AC_ERR_INVALID) &&
- ((qc->flags & ATA_QCFLAG_IO) || qc->err_mask != AC_ERR_DEV))
+ if (qc->flags & ATA_QCFLAG_IO ||
+ (!(qc->err_mask & AC_ERR_INVALID) &&
+ qc->err_mask != AC_ERR_DEV))
qc->flags |= ATA_QCFLAG_RETRY;
/* accumulate error info */
}
/**
+ * ata_get_cmd_descript - get description for ATA command
+ * @command: ATA command code to get description for
+ *
+ * Return a textual description of the given command, or NULL if the
+ * command is not known.
+ *
+ * LOCKING:
+ * None
+ */
+const char *ata_get_cmd_descript(u8 command)
+{
+#ifdef CONFIG_ATA_VERBOSE_ERROR
+ static const struct
+ {
+ u8 command;
+ const char *text;
+ } cmd_descr[] = {
+ { ATA_CMD_DEV_RESET, "DEVICE RESET" },
+ { ATA_CMD_CHK_POWER, "CHECK POWER MODE" },
+ { ATA_CMD_STANDBY, "STANDBY" },
+ { ATA_CMD_IDLE, "IDLE" },
+ { ATA_CMD_EDD, "EXECUTE DEVICE DIAGNOSTIC" },
+ { ATA_CMD_DOWNLOAD_MICRO, "DOWNLOAD MICROCODE" },
+ { ATA_CMD_NOP, "NOP" },
+ { ATA_CMD_FLUSH, "FLUSH CACHE" },
+ { ATA_CMD_FLUSH_EXT, "FLUSH CACHE EXT" },
+ { ATA_CMD_ID_ATA, "IDENTIFY DEVICE" },
+ { ATA_CMD_ID_ATAPI, "IDENTIFY PACKET DEVICE" },
+ { ATA_CMD_SERVICE, "SERVICE" },
+ { ATA_CMD_READ, "READ DMA" },
+ { ATA_CMD_READ_EXT, "READ DMA EXT" },
+ { ATA_CMD_READ_QUEUED, "READ DMA QUEUED" },
+ { ATA_CMD_READ_STREAM_EXT, "READ STREAM EXT" },
+ { ATA_CMD_READ_STREAM_DMA_EXT, "READ STREAM DMA EXT" },
+ { ATA_CMD_WRITE, "WRITE DMA" },
+ { ATA_CMD_WRITE_EXT, "WRITE DMA EXT" },
+ { ATA_CMD_WRITE_QUEUED, "WRITE DMA QUEUED EXT" },
+ { ATA_CMD_WRITE_STREAM_EXT, "WRITE STREAM EXT" },
+ { ATA_CMD_WRITE_STREAM_DMA_EXT, "WRITE STREAM DMA EXT" },
+ { ATA_CMD_WRITE_FUA_EXT, "WRITE DMA FUA EXT" },
+ { 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_PIO_READ, "READ SECTOR(S)" },
+ { ATA_CMD_PIO_READ_EXT, "READ SECTOR(S) EXT" },
+ { ATA_CMD_PIO_WRITE, "WRITE SECTOR(S)" },
+ { ATA_CMD_PIO_WRITE_EXT, "WRITE SECTOR(S) EXT" },
+ { ATA_CMD_READ_MULTI, "READ MULTIPLE" },
+ { ATA_CMD_READ_MULTI_EXT, "READ MULTIPLE EXT" },
+ { ATA_CMD_WRITE_MULTI, "WRITE MULTIPLE" },
+ { ATA_CMD_WRITE_MULTI_EXT, "WRITE MULTIPLE EXT" },
+ { ATA_CMD_WRITE_MULTI_FUA_EXT, "WRITE MULTIPLE FUA EXT" },
+ { ATA_CMD_SET_FEATURES, "SET FEATURES" },
+ { ATA_CMD_SET_MULTI, "SET MULTIPLE MODE" },
+ { ATA_CMD_VERIFY, "READ VERIFY SECTOR(S)" },
+ { ATA_CMD_VERIFY_EXT, "READ VERIFY SECTOR(S) EXT" },
+ { ATA_CMD_WRITE_UNCORR_EXT, "WRITE UNCORRECTABLE EXT" },
+ { ATA_CMD_STANDBYNOW1, "STANDBY IMMEDIATE" },
+ { ATA_CMD_IDLEIMMEDIATE, "IDLE IMMEDIATE" },
+ { ATA_CMD_SLEEP, "SLEEP" },
+ { ATA_CMD_INIT_DEV_PARAMS, "INITIALIZE DEVICE PARAMETERS" },
+ { ATA_CMD_READ_NATIVE_MAX, "READ NATIVE MAX ADDRESS" },
+ { ATA_CMD_READ_NATIVE_MAX_EXT, "READ NATIVE MAX ADDRESS EXT" },
+ { ATA_CMD_SET_MAX, "SET MAX ADDRESS" },
+ { ATA_CMD_SET_MAX_EXT, "SET MAX ADDRESS EXT" },
+ { ATA_CMD_READ_LOG_EXT, "READ LOG EXT" },
+ { 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_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_WRITE, "WRITE BUFFER" },
+ { ATA_CMD_CONF_OVERLAY, "DEVICE CONFIGURATION OVERLAY" },
+ { ATA_CMD_SEC_SET_PASS, "SECURITY SET PASSWORD" },
+ { ATA_CMD_SEC_UNLOCK, "SECURITY UNLOCK" },
+ { ATA_CMD_SEC_ERASE_PREP, "SECURITY ERASE PREPARE" },
+ { ATA_CMD_SEC_ERASE_UNIT, "SECURITY ERASE UNIT" },
+ { ATA_CMD_SEC_FREEZE_LOCK, "SECURITY FREEZE LOCK" },
+ { ATA_CMD_SEC_DISABLE_PASS, "SECURITY DISABLE PASSWORD" },
+ { ATA_CMD_CONFIG_STREAM, "CONFIGURE STREAM" },
+ { ATA_CMD_SMART, "SMART" },
+ { ATA_CMD_MEDIA_LOCK, "DOOR LOCK" },
+ { ATA_CMD_MEDIA_UNLOCK, "DOOR UNLOCK" },
+ { ATA_CMD_CHK_MED_CRD_TYP, "CHECK MEDIA CARD TYPE" },
+ { ATA_CMD_CFA_REQ_EXT_ERR, "CFA REQUEST EXTENDED ERROR" },
+ { ATA_CMD_CFA_WRITE_NE, "CFA WRITE SECTORS WITHOUT ERASE" },
+ { 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_READ_LONG, "READ LONG (with retries)" },
+ { ATA_CMD_READ_LONG_ONCE, "READ LONG (without retries)" },
+ { ATA_CMD_WRITE_LONG, "WRITE LONG (with retries)" },
+ { ATA_CMD_WRITE_LONG_ONCE, "WRITE LONG (without retries)" },
+ { ATA_CMD_RESTORE, "RECALIBRATE" },
+ { 0, NULL } /* terminate list */
+ };
+
+ unsigned int i;
+ for (i = 0; cmd_descr[i].text; i++)
+ if (cmd_descr[i].command == command)
+ return cmd_descr[i].text;
+#endif
+
+ return NULL;
+}
+
+/**
* ata_eh_link_report - report error handling to user
* @link: ATA link EH is going on
*
ata_link_printk(link, KERN_ERR, "%s\n", desc);
}
+#ifdef CONFIG_ATA_VERBOSE_ERROR
if (ehc->i.serror)
ata_link_printk(link, KERN_ERR,
"SError: { %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s}\n",
ehc->i.serror & SERR_TRANS_ST_ERROR ? "TrStaTrns " : "",
ehc->i.serror & SERR_UNRECOG_FIS ? "UnrecFIS " : "",
ehc->i.serror & SERR_DEV_XCHG ? "DevExch " : "");
+#endif
for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
dma_str[qc->dma_dir]);
}
- if (ata_is_atapi(qc->tf.protocol))
- snprintf(cdb_buf, sizeof(cdb_buf),
+ if (ata_is_atapi(qc->tf.protocol)) {
+ if (qc->scsicmd)
+ scsi_print_command(qc->scsicmd);
+ else
+ snprintf(cdb_buf, sizeof(cdb_buf),
"cdb %02x %02x %02x %02x %02x %02x %02x %02x "
"%02x %02x %02x %02x %02x %02x %02x %02x\n ",
cdb[0], cdb[1], cdb[2], cdb[3],
cdb[4], cdb[5], cdb[6], cdb[7],
cdb[8], cdb[9], cdb[10], cdb[11],
cdb[12], cdb[13], cdb[14], cdb[15]);
+ } else {
+ const char *descr = ata_get_cmd_descript(cmd->command);
+ if (descr)
+ ata_dev_printk(qc->dev, KERN_ERR,
+ "failed command: %s\n", descr);
+ }
ata_dev_printk(qc->dev, KERN_ERR,
"cmd %02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x "
res->device, qc->err_mask, ata_err_string(qc->err_mask),
qc->err_mask & AC_ERR_NCQ ? " <F>" : "");
+#ifdef CONFIG_ATA_VERBOSE_ERROR
if (res->command & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ |
ATA_ERR)) {
if (res->command & ATA_BUSY)
res->feature & ATA_UNC ? "UNC " : "",
res->feature & ATA_IDNF ? "IDNF " : "",
res->feature & ATA_ABORTED ? "ABRT " : "");
+#endif
}
}
struct ata_port *ap = link->ap;
struct ata_link *slave = ap->slave_link;
struct ata_eh_context *ehc = &link->eh_context;
- struct ata_eh_context *sehc = &slave->eh_context;
+ struct ata_eh_context *sehc = slave ? &slave->eh_context : NULL;
unsigned int *classes = ehc->classes;
unsigned int lflags = link->flags;
int verbose = !(ehc->i.flags & ATA_EHI_QUIET);
}
/* prereset() might have cleared ATA_EH_RESET. If so,
- * bang classes and return.
+ * bang classes, thaw and return.
*/
if (reset && !(ehc->i.action & ATA_EH_RESET)) {
ata_for_each_dev(dev, link, ALL)
classes[dev->devno] = ATA_DEV_NONE;
+ if ((ap->pflags & ATA_PFLAG_FROZEN) &&
+ ata_is_host_link(link))
+ ata_eh_thaw_port(ap);
rc = 0;
goto out;
}
ata_eh_about_to_do(link, NULL, ATA_EH_RESET);
rc = ata_do_reset(link, reset, classes, deadline, true);
+ if (rc) {
+ failed_link = link;
+ goto fail;
+ }
}
} else {
if (verbose)
dev->pio_mode = XFER_PIO_0;
dev->flags &= ~ATA_DFLAG_SLEEPING;
- if (!ata_phys_link_offline(ata_dev_phys_link(dev))) {
- /* apply class override */
- if (lflags & ATA_LFLAG_ASSUME_ATA)
- classes[dev->devno] = ATA_DEV_ATA;
- else if (lflags & ATA_LFLAG_ASSUME_SEMB)
- classes[dev->devno] = ATA_DEV_SEMB_UNSUP;
- } else
- classes[dev->devno] = ATA_DEV_NONE;
+ if (ata_phys_link_offline(ata_dev_phys_link(dev)))
+ continue;
+
+ /* apply class override */
+ if (lflags & ATA_LFLAG_ASSUME_ATA)
+ classes[dev->devno] = ATA_DEV_ATA;
+ else if (lflags & ATA_LFLAG_ASSUME_SEMB)
+ classes[dev->devno] = ATA_DEV_SEMB_UNSUP;
}
/* record current link speed */
postreset(slave, classes);
}
- /* clear cached SError */
+ /*
+ * Some controllers can't be frozen very well and may set
+ * spuruious error conditions during reset. Clear accumulated
+ * error information. As reset is the final recovery action,
+ * nothing is lost by doing this.
+ */
spin_lock_irqsave(link->ap->lock, flags);
- link->eh_info.serror = 0;
+ memset(&link->eh_info, 0, sizeof(link->eh_info));
if (slave)
- slave->eh_info.serror = 0;
+ memset(&slave->eh_info, 0, sizeof(link->eh_info));
+ ap->pflags &= ~ATA_PFLAG_EH_PENDING;
spin_unlock_irqrestore(link->ap->lock, flags);
- /* Make sure onlineness and classification result correspond.
+ /*
+ * Make sure onlineness and classification result correspond.
* Hotplug could have happened during reset and some
* controllers fail to wait while a drive is spinning up after
* being hotplugged causing misdetection. By cross checking
- * link onlineness and classification result, those conditions
- * can be reliably detected and retried.
+ * link on/offlineness and classification result, those
+ * conditions can be reliably detected and retried.
*/
nr_unknown = 0;
ata_for_each_dev(dev, link, ALL) {
- /* convert all ATA_DEV_UNKNOWN to ATA_DEV_NONE */
- if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
- classes[dev->devno] = ATA_DEV_NONE;
- if (ata_phys_link_online(ata_dev_phys_link(dev)))
+ if (ata_phys_link_online(ata_dev_phys_link(dev))) {
+ if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
+ ata_dev_printk(dev, KERN_DEBUG, "link online "
+ "but device misclassifed\n");
+ classes[dev->devno] = ATA_DEV_NONE;
nr_unknown++;
+ }
+ } else if (ata_phys_link_offline(ata_dev_phys_link(dev))) {
+ if (ata_class_enabled(classes[dev->devno]))
+ ata_dev_printk(dev, KERN_DEBUG, "link offline, "
+ "clearing class %d to NONE\n",
+ classes[dev->devno]);
+ classes[dev->devno] = ATA_DEV_NONE;
+ } else if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
+ ata_dev_printk(dev, KERN_DEBUG, "link status unknown, "
+ "clearing UNKNOWN to NONE\n");
+ classes[dev->devno] = ATA_DEV_NONE;
}
}
if (classify && nr_unknown) {
if (try < max_tries) {
ata_link_printk(link, KERN_WARNING, "link online but "
- "device misclassified, retrying\n");
+ "%d devices misclassified, retrying\n",
+ nr_unknown);
failed_link = link;
rc = -EAGAIN;
goto fail;
}
ata_link_printk(link, KERN_WARNING,
- "link online but device misclassified, "
- "device detection might fail\n");
+ "link online but %d devices misclassified, "
+ "device detection might fail\n", nr_unknown);
}
/* reset successful, schedule revalidation */
}
if (try == max_tries - 1) {
- sata_down_spd_limit(link);
+ sata_down_spd_limit(link, 0);
if (slave)
- sata_down_spd_limit(slave);
+ sata_down_spd_limit(slave, 0);
} else if (rc == -EPIPE)
- sata_down_spd_limit(failed_link);
+ sata_down_spd_limit(failed_link, 0);
if (hardreset)
reset = hardreset;
} else if (dev->class == ATA_DEV_UNKNOWN &&
ehc->tries[dev->devno] &&
ata_class_enabled(ehc->classes[dev->devno])) {
+ /* Temporarily set dev->class, it will be
+ * permanently set once all configurations are
+ * complete. This is necessary because new
+ * device configuration is done in two
+ * separate loops.
+ */
dev->class = ehc->classes[dev->devno];
if (dev->class == ATA_DEV_PMP)
else
rc = ata_dev_read_id(dev, &dev->class,
readid_flags, dev->id);
+
+ /* read_id might have changed class, store and reset */
+ ehc->classes[dev->devno] = dev->class;
+ dev->class = ATA_DEV_UNKNOWN;
+
switch (rc) {
case 0:
+ /* clear error info accumulated during probe */
+ ata_ering_clear(&dev->ering);
new_mask |= 1 << dev->devno;
break;
case -ENOENT:
/* IDENTIFY was issued to non-existent
* device. No need to reset. Just
- * thaw and kill the device.
+ * thaw and ignore the device.
*/
ata_eh_thaw_port(ap);
- dev->class = ATA_DEV_UNKNOWN;
break;
default:
- dev->class = ATA_DEV_UNKNOWN;
goto err;
}
}
* device detection messages backwards.
*/
ata_for_each_dev(dev, link, ALL) {
- if (!(new_mask & (1 << dev->devno)) ||
- dev->class == ATA_DEV_PMP)
+ if (!(new_mask & (1 << dev->devno)))
+ continue;
+
+ dev->class = ehc->classes[dev->devno];
+
+ if (dev->class == ATA_DEV_PMP)
continue;
ehc->i.flags |= ATA_EHI_PRINTINFO;
rc = ata_dev_configure(dev);
ehc->i.flags &= ~ATA_EHI_PRINTINFO;
- if (rc)
+ if (rc) {
+ dev->class = ATA_DEV_UNKNOWN;
goto err;
+ }
spin_lock_irqsave(ap->lock, flags);
ap->pflags |= ATA_PFLAG_SCSI_HOTPLUG;
/**
* ata_set_mode - Program timings and issue SET FEATURES - XFER
* @link: link on which timings will be programmed
- * @r_failed_dev: out paramter for failed device
+ * @r_failed_dev: out parameter for failed device
*
* Set ATA device disk transfer mode (PIO3, UDMA6, etc.). If
* ata_set_mode() fails, pointer to the failing device is
int i;
for (i = 0; i < ATA_EH_UA_TRIES; i++) {
- u8 sense_buffer[SCSI_SENSE_BUFFERSIZE];
+ u8 *sense_buffer = dev->link->ap->sector_buf;
u8 sense_key = 0;
unsigned int err_mask;
return 0;
}
+/**
+ * ata_eh_maybe_retry_flush - Retry FLUSH if necessary
+ * @dev: ATA device which may need FLUSH retry
+ *
+ * If @dev failed FLUSH, it needs to be reported upper layer
+ * immediately as it means that @dev failed to remap and already
+ * lost at least a sector and further FLUSH retrials won't make
+ * any difference to the lost sector. However, if FLUSH failed
+ * for other reasons, for example transmission error, FLUSH needs
+ * to be retried.
+ *
+ * This function determines whether FLUSH failure retry is
+ * necessary and performs it if so.
+ *
+ * RETURNS:
+ * 0 if EH can continue, -errno if EH needs to be repeated.
+ */
+static int ata_eh_maybe_retry_flush(struct ata_device *dev)
+{
+ struct ata_link *link = dev->link;
+ struct ata_port *ap = link->ap;
+ struct ata_queued_cmd *qc;
+ struct ata_taskfile tf;
+ unsigned int err_mask;
+ int rc = 0;
+
+ /* did flush fail for this device? */
+ if (!ata_tag_valid(link->active_tag))
+ return 0;
+
+ qc = __ata_qc_from_tag(ap, link->active_tag);
+ if (qc->dev != dev || (qc->tf.command != ATA_CMD_FLUSH_EXT &&
+ qc->tf.command != ATA_CMD_FLUSH))
+ return 0;
+
+ /* if the device failed it, it should be reported to upper layers */
+ if (qc->err_mask & AC_ERR_DEV)
+ return 0;
+
+ /* flush failed for some other reason, give it another shot */
+ ata_tf_init(dev, &tf);
+
+ tf.command = qc->tf.command;
+ tf.flags |= ATA_TFLAG_DEVICE;
+ tf.protocol = ATA_PROT_NODATA;
+
+ ata_dev_printk(dev, KERN_WARNING, "retrying FLUSH 0x%x Emask 0x%x\n",
+ tf.command, qc->err_mask);
+
+ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+ if (!err_mask) {
+ /*
+ * FLUSH is complete but there's no way to
+ * successfully complete a failed command from EH.
+ * Making sure retry is allowed at least once and
+ * retrying it should do the trick - whatever was in
+ * the cache is already on the platter and this won't
+ * cause infinite loop.
+ */
+ qc->scsicmd->allowed = max(qc->scsicmd->allowed, 1);
+ } else {
+ ata_dev_printk(dev, KERN_WARNING, "FLUSH failed Emask 0x%x\n",
+ err_mask);
+ rc = -EIO;
+
+ /* if device failed it, report it to upper layers */
+ if (err_mask & AC_ERR_DEV) {
+ qc->err_mask |= AC_ERR_DEV;
+ qc->result_tf = tf;
+ if (!(ap->pflags & ATA_PFLAG_FROZEN))
+ rc = 0;
+ }
+ }
+ return rc;
+}
+
static int ata_link_nr_enabled(struct ata_link *link)
{
struct ata_device *dev;
return 1;
}
+static int ata_count_probe_trials_cb(struct ata_ering_entry *ent, void *void_arg)
+{
+ u64 interval = msecs_to_jiffies(ATA_EH_PROBE_TRIAL_INTERVAL);
+ u64 now = get_jiffies_64();
+ int *trials = void_arg;
+
+ if (ent->timestamp < now - min(now, interval))
+ return -1;
+
+ (*trials)++;
+ return 0;
+}
+
static int ata_eh_schedule_probe(struct ata_device *dev)
{
struct ata_eh_context *ehc = &dev->link->eh_context;
+ struct ata_link *link = ata_dev_phys_link(dev);
+ int trials = 0;
if (!(ehc->i.probe_mask & (1 << dev->devno)) ||
(ehc->did_probe_mask & (1 << dev->devno)))
ehc->saved_xfer_mode[dev->devno] = 0;
ehc->saved_ncq_enabled &= ~(1 << dev->devno);
+ /* Record and count probe trials on the ering. The specific
+ * error mask used is irrelevant. Because a successful device
+ * detection clears the ering, this count accumulates only if
+ * there are consecutive failed probes.
+ *
+ * If the count is equal to or higher than ATA_EH_PROBE_TRIALS
+ * in the last ATA_EH_PROBE_TRIAL_INTERVAL, link speed is
+ * forced to 1.5Gbps.
+ *
+ * This is to work around cases where failed link speed
+ * negotiation results in device misdetection leading to
+ * infinite DEVXCHG or PHRDY CHG events.
+ */
+ ata_ering_record(&dev->ering, 0, AC_ERR_OTHER);
+ ata_ering_map(&dev->ering, ata_count_probe_trials_cb, &trials);
+
+ if (trials > ATA_EH_PROBE_TRIALS)
+ sata_down_spd_limit(link, 1);
+
return 1;
}
{
struct ata_eh_context *ehc = &dev->link->eh_context;
- ehc->tries[dev->devno]--;
+ /* -EAGAIN from EH routine indicates retry without prejudice.
+ * The requester is responsible for ensuring forward progress.
+ */
+ if (err != -EAGAIN)
+ ehc->tries[dev->devno]--;
switch (err) {
case -ENODEV:
/* This is the last chance, better to slow
* down than lose it.
*/
- sata_down_spd_limit(ata_dev_phys_link(dev));
+ sata_down_spd_limit(ata_dev_phys_link(dev), 0);
if (dev->pio_mode > XFER_PIO_0)
ata_down_xfermask_limit(dev, ATA_DNXFER_PIO);
}
}
}
+ /* retry flush if necessary */
+ ata_for_each_dev(dev, link, ALL) {
+ if (dev->class != ATA_DEV_ATA)
+ continue;
+ rc = ata_eh_maybe_retry_flush(dev);
+ if (rc)
+ goto dev_fail;
+ }
+
/* configure link power saving */
if (ehc->i.action & ATA_EH_LPM)
ata_for_each_dev(dev, link, ALL)
*/
static void ata_eh_handle_port_resume(struct ata_port *ap)
{
+ struct ata_link *link;
+ struct ata_device *dev;
unsigned long flags;
int rc = 0;
WARN_ON(!(ap->pflags & ATA_PFLAG_SUSPENDED));
+ /*
+ * Error timestamps are in jiffies which doesn't run while
+ * suspended and PHY events during resume isn't too uncommon.
+ * When the two are combined, it can lead to unnecessary speed
+ * downs if the machine is suspended and resumed repeatedly.
+ * Clear error history.
+ */
+ ata_for_each_link(link, ap, HOST_FIRST)
+ ata_for_each_dev(dev, link, ALL)
+ ata_ering_clear(&dev->ering);
+
ata_acpi_set_state(ap, PMSG_ON);
if (ap->ops->port_resume)