1 files changed, 295 insertions, 54 deletions

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index e48302eae55f..7f099d6e4e0b 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -57,6 +57,7 @@ enum {
         /* error flags */
         ATA_EFLAG_IS_IO                 = (1 << 0),
         ATA_EFLAG_DUBIOUS_XFER          = (1 << 1),
+        ATA_EFLAG_OLD_ER                = (1 << 31),
 
         /* error categories */
         ATA_ECAT_NONE                   = 0,
@@ -396,14 +397,9 @@ static struct ata_ering_entry *ata_ering_top(struct ata_ering *ering)
         return NULL;
 }
 
-static void ata_ering_clear(struct ata_ering *ering)
-{
-        memset(ering, 0, sizeof(*ering));
-}
-
-static int ata_ering_map(struct ata_ering *ering,
-                         int (*map_fn)(struct ata_ering_entry *, void *),
-                         void *arg)
+int ata_ering_map(struct ata_ering *ering,
+                  int (*map_fn)(struct ata_ering_entry *, void *),
+                  void *arg)
 {
         int idx, rc = 0;
         struct ata_ering_entry *ent;
@@ -422,6 +418,17 @@ static int ata_ering_map(struct ata_ering *ering,
         return rc;
 }
 
+int ata_ering_clear_cb(struct ata_ering_entry *ent, void *void_arg)
+{
+        ent->eflags |= ATA_EFLAG_OLD_ER;
+        return 0;
+}
+
+static void ata_ering_clear(struct ata_ering *ering)
+{
+        ata_ering_map(ering, ata_ering_clear_cb, NULL);
+}
+
 static unsigned int ata_eh_dev_action(struct ata_device *dev)
 {
         struct ata_eh_context *ehc = &dev->link->eh_context;
@@ -456,6 +463,41 @@ static void ata_eh_clear_action(struct ata_link *link, struct ata_device *dev,
 }
 
 /**
+ *      ata_eh_acquire - acquire EH ownership
+ *      @ap: ATA port to acquire EH ownership for
+ *
+ *      Acquire EH ownership for @ap.  This is the basic exclusion
+ *      mechanism for ports sharing a host.  Only one port hanging off
+ *      the same host can claim the ownership of EH.
+ *
+ *      LOCKING:
+ *      EH context.
+ */
+void ata_eh_acquire(struct ata_port *ap)
+{
+        mutex_lock(&ap->host->eh_mutex);
+        WARN_ON_ONCE(ap->host->eh_owner);
+        ap->host->eh_owner = current;
+}
+
+/**
+ *      ata_eh_release - release EH ownership
+ *      @ap: ATA port to release EH ownership for
+ *
+ *      Release EH ownership for @ap if the caller.  The caller must
+ *      have acquired EH ownership using ata_eh_acquire() previously.
+ *
+ *      LOCKING:
+ *      EH context.
+ */
+void ata_eh_release(struct ata_port *ap)
+{
+        WARN_ON_ONCE(ap->host->eh_owner != current);
+        ap->host->eh_owner = NULL;
+        mutex_unlock(&ap->host->eh_mutex);
+}
+
+/**
  *      ata_scsi_timed_out - SCSI layer time out callback
  *      @cmd: timed out SCSI command
  *
@@ -545,11 +587,43 @@ static void ata_eh_unload(struct ata_port *ap)
 void ata_scsi_error(struct Scsi_Host *host)
 {
         struct ata_port *ap = ata_shost_to_port(host);
-        int i;
         unsigned long flags;
+        LIST_HEAD(eh_work_q);
 
         DPRINTK("ENTER\n");
 
+        spin_lock_irqsave(host->host_lock, flags);
+        list_splice_init(&host->eh_cmd_q, &eh_work_q);
+        spin_unlock_irqrestore(host->host_lock, flags);
+
+        ata_scsi_cmd_error_handler(host, ap, &eh_work_q);
+
+        /* If we timed raced normal completion and there is nothing to
+           recover nr_timedout == 0 why exactly are we doing error recovery ? */
+        ata_scsi_port_error_handler(host, ap);
+
+        /* finish or retry handled scmd's and clean up */
+        WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+
+        DPRINTK("EXIT\n");
+}
+
+/**
+ * ata_scsi_cmd_error_handler - error callback for a list of commands
+ * @host:       scsi host containing the port
+ * @ap:         ATA port within the host
+ * @eh_work_q:  list of commands to process
+ *
+ * process the given list of commands and return those finished to the
+ * ap->eh_done_q.  This function is the first part of the libata error
+ * handler which processes a given list of failed commands.
+ */
+void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
+                                struct list_head *eh_work_q)
+{
+        int i;
+        unsigned long flags;
+
         /* make sure sff pio task is not running */
         ata_sff_flush_pio_task(ap);
 
@@ -572,20 +646,20 @@ void ata_scsi_error(struct Scsi_Host *host)
                 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) {
+
+                list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
                         struct ata_queued_cmd *qc;
 
                         for (i = 0; i < ATA_MAX_QUEUE; i++) {
@@ -628,15 +702,29 @@ void ata_scsi_error(struct Scsi_Host *host)
                 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:
+}
+EXPORT_SYMBOL(ata_scsi_cmd_error_handler);
+
+/**
+ * ata_scsi_port_error_handler - recover the port after the commands
+ * @host:       SCSI host containing the port
+ * @ap:         the ATA port
+ *
+ * Handle the recovery of the port @ap after all the commands
+ * have been recovered.
+ */
+void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
+{
+        unsigned long flags;
+
         /* invoke error handler */
         if (ap->ops->error_handler) {
                 struct ata_link *link;
 
+                /* acquire EH ownership */
+                ata_eh_acquire(ap);
+ repeat:
                 /* kill fast drain timer */
                 del_timer_sync(&ap->fastdrain_timer);
 
@@ -683,7 +771,7 @@ void ata_scsi_error(struct Scsi_Host *host)
                 /* process port suspend request */
                 ata_eh_handle_port_suspend(ap);
 
-                /* Exception might have happend after ->error_handler
+                /* Exception might have happened after ->error_handler
                  * recovered the port but before this point.  Repeat
                  * EH in such case.
                  */
@@ -711,14 +799,12 @@ void ata_scsi_error(struct Scsi_Host *host)
                 host->host_eh_scheduled = 0;
 
                 spin_unlock_irqrestore(ap->lock, flags);
+                ata_eh_release(ap);
         } else {
                 WARN_ON(ata_qc_from_tag(ap, ap->link.active_tag) == NULL);
                 ap->ops->eng_timeout(ap);
         }
 
-        /* finish or retry handled scmd's and clean up */
-        WARN_ON(host->host_failed || !list_empty(&host->eh_cmd_q));
-
         scsi_eh_flush_done_q(&ap->eh_done_q);
 
         /* clean up */
@@ -739,9 +825,8 @@ void ata_scsi_error(struct Scsi_Host *host)
         wake_up_all(&ap->eh_wait_q);
 
         spin_unlock_irqrestore(ap->lock, flags);
-
-        DPRINTK("EXIT\n");
 }
+EXPORT_SYMBOL_GPL(ata_scsi_port_error_handler);
 
 /**
  *      ata_port_wait_eh - Wait for the currently pending EH to complete
@@ -772,7 +857,7 @@ void ata_port_wait_eh(struct ata_port *ap)
 
         /* make sure SCSI EH is complete */
         if (scsi_host_in_recovery(ap->scsi_host)) {
-                msleep(10);
+                ata_msleep(ap, 10);
                 goto retry;
         }
 }
@@ -1573,9 +1658,9 @@ static void ata_eh_analyze_serror(struct ata_link *link)
          * host links.  For disabled PMP links, only N bit is
          * considered as X bit is left at 1 for link plugging.
          */
-        hotplug_mask = 0;
-
-        if (!(link->flags & ATA_LFLAG_DISABLED) || ata_is_host_link(link))
+        if (link->lpm_policy > ATA_LPM_MAX_POWER)
+                hotplug_mask = 0;       /* hotplug doesn't work w/ LPM */
+        else if (!(link->flags & ATA_LFLAG_DISABLED) || ata_is_host_link(link))
                 hotplug_mask = SERR_PHYRDY_CHG | SERR_DEV_XCHG;
         else
                 hotplug_mask = SERR_PHYRDY_CHG;
@@ -1657,7 +1742,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
  *
  *      Analyze taskfile of @qc and further determine cause of
  *      failure.  This function also requests ATAPI sense data if
- *      avaliable.
+ *      available.
  *
  *      LOCKING:
  *      Kernel thread context (may sleep).
@@ -1755,7 +1840,7 @@ static int speed_down_verdict_cb(struct ata_ering_entry *ent, void *void_arg)
         struct speed_down_verdict_arg *arg = void_arg;
         int cat;
 
-        if (ent->timestamp < arg->since)
+        if ((ent->eflags & ATA_EFLAG_OLD_ER) || (ent->timestamp < arg->since))
                 return -1;
 
         cat = ata_eh_categorize_error(ent->eflags, ent->err_mask,
@@ -1808,7 +1893,7 @@ static int speed_down_verdict_cb(struct ata_ering_entry *ent, void *void_arg)
  *         occurred during last 5 mins, NCQ_OFF.
  *
  *      3. If more than 8 ATA_BUS, TOUT_HSM or UNK_DEV errors
- *         ocurred during last 5 mins, FALLBACK_TO_PIO
+ *         occurred during last 5 mins, FALLBACK_TO_PIO
  *
  *      4. If more than 3 TOUT_HSM or UNK_DEV errors occurred
  *         during last 10 mins, NCQ_OFF.
@@ -2492,7 +2577,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
         if (link->flags & ATA_LFLAG_NO_SRST)
                 softreset = NULL;
 
-        /* make sure each reset attemp is at least COOL_DOWN apart */
+        /* make sure each reset attempt is at least COOL_DOWN apart */
         if (ehc->i.flags & ATA_EHI_DID_RESET) {
                 now = jiffies;
                 WARN_ON(time_after(ehc->last_reset, now));
@@ -2651,7 +2736,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
                         if (!reset) {
                                 ata_link_printk(link, KERN_ERR,
                                                 "follow-up softreset required "
-                                                "but no softreset avaliable\n");
+                                                "but no softreset available\n");
                                 failed_link = link;
                                 rc = -EINVAL;
                                 goto fail;
@@ -2717,10 +2802,11 @@ int ata_eh_reset(struct ata_link *link, int classify,
         }
 
         /*
-         * 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.
+         * Some controllers can't be frozen very well and may set spurious
+         * error conditions during reset.  Clear accumulated error
+         * information and re-thaw the port if frozen.  As reset is the
+         * final recovery action and we cross check link onlineness against
+         * device classification later, no hotplug event is lost by this.
          */
         spin_lock_irqsave(link->ap->lock, flags);
         memset(&link->eh_info, 0, sizeof(link->eh_info));
@@ -2729,6 +2815,9 @@ int ata_eh_reset(struct ata_link *link, int classify,
         ap->pflags &= ~ATA_PFLAG_EH_PENDING;
         spin_unlock_irqrestore(link->ap->lock, flags);
 
+        if (ap->pflags & ATA_PFLAG_FROZEN)
+                ata_eh_thaw_port(ap);
+
         /*
          * Make sure onlineness and classification result correspond.
          * Hotplug could have happened during reset and some
@@ -2777,8 +2866,9 @@ int ata_eh_reset(struct ata_link *link, int classify,
         ata_eh_done(link, NULL, ATA_EH_RESET);
         if (slave)
                 ata_eh_done(slave, NULL, ATA_EH_RESET);
-        ehc->last_reset = jiffies;      /* update to completion time */
+        ehc->last_reset = jiffies;              /* update to completion time */
         ehc->i.action |= ATA_EH_REVALIDATE;
+        link->lpm_policy = ATA_LPM_UNKNOWN;     /* reset LPM state */
 
         rc = 0;
  out:
@@ -2810,8 +2900,10 @@ int ata_eh_reset(struct ata_link *link, int classify,
                         "reset failed (errno=%d), retrying in %u secs\n",
                         rc, DIV_ROUND_UP(jiffies_to_msecs(delta), 1000));
 
+                ata_eh_release(ap);
                 while (delta)
                         delta = schedule_timeout_uninterruptible(delta);
+                ata_eh_acquire(ap);
         }
 
         if (try == max_tries - 1) {
@@ -3204,7 +3296,138 @@ static int ata_eh_maybe_retry_flush(struct ata_device *dev)
         return rc;
 }
 
-static int ata_link_nr_enabled(struct ata_link *link)
+/**
+ *      ata_eh_set_lpm - configure SATA interface power management
+ *      @link: link to configure power management
+ *      @policy: the link power management policy
+ *      @r_failed_dev: out parameter for failed device
+ *
+ *      Enable SATA Interface power management.  This will enable
+ *      Device Interface Power Management (DIPM) for min_power
+ *      policy, and then call driver specific callbacks for
+ *      enabling Host Initiated Power management.
+ *
+ *      LOCKING:
+ *      EH context.
+ *
+ *      RETURNS:
+ *      0 on success, -errno on failure.
+ */
+static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+                          struct ata_device **r_failed_dev)
+{
+        struct ata_port *ap = ata_is_host_link(link) ? link->ap : NULL;
+        struct ata_eh_context *ehc = &link->eh_context;
+        struct ata_device *dev, *link_dev = NULL, *lpm_dev = NULL;
+        enum ata_lpm_policy old_policy = link->lpm_policy;
+        bool no_dipm = link->ap->flags & ATA_FLAG_NO_DIPM;
+        unsigned int hints = ATA_LPM_EMPTY | ATA_LPM_HIPM;
+        unsigned int err_mask;
+        int rc;
+
+        /* if the link or host doesn't do LPM, noop */
+        if ((link->flags & ATA_LFLAG_NO_LPM) || (ap && !ap->ops->set_lpm))
+                return 0;
+
+        /*
+         * DIPM is enabled only for MIN_POWER as some devices
+         * misbehave when the host NACKs transition to SLUMBER.  Order
+         * device and link configurations such that the host always
+         * allows DIPM requests.
+         */
+        ata_for_each_dev(dev, link, ENABLED) {
+                bool hipm = ata_id_has_hipm(dev->id);
+                bool dipm = ata_id_has_dipm(dev->id) && !no_dipm;
+
+                /* find the first enabled and LPM enabled devices */
+                if (!link_dev)
+                        link_dev = dev;
+
+                if (!lpm_dev && (hipm || dipm))
+                        lpm_dev = dev;
+
+                hints &= ~ATA_LPM_EMPTY;
+                if (!hipm)
+                        hints &= ~ATA_LPM_HIPM;
+
+                /* disable DIPM before changing link config */
+                if (policy != ATA_LPM_MIN_POWER && dipm) {
+                        err_mask = ata_dev_set_feature(dev,
+                                        SETFEATURES_SATA_DISABLE, SATA_DIPM);
+                        if (err_mask && err_mask != AC_ERR_DEV) {
+                                ata_dev_printk(dev, KERN_WARNING,
+                                        "failed to disable DIPM, Emask 0x%x\n",
+                                        err_mask);
+                                rc = -EIO;
+                                goto fail;
+                        }
+                }
+        }
+
+        if (ap) {
+                rc = ap->ops->set_lpm(link, policy, hints);
+                if (!rc && ap->slave_link)
+                        rc = ap->ops->set_lpm(ap->slave_link, policy, hints);
+        } else
+                rc = sata_pmp_set_lpm(link, policy, hints);
+
+        /*
+         * Attribute link config failure to the first (LPM) enabled
+         * device on the link.
+         */
+        if (rc) {
+                if (rc == -EOPNOTSUPP) {
+                        link->flags |= ATA_LFLAG_NO_LPM;
+                        return 0;
+                }
+                dev = lpm_dev ? lpm_dev : link_dev;
+                goto fail;
+        }
+
+        /*
+         * Low level driver acked the transition.  Issue DIPM command
+         * with the new policy set.
+         */
+        link->lpm_policy = policy;
+        if (ap && ap->slave_link)
+                ap->slave_link->lpm_policy = policy;
+
+        /* host config updated, enable DIPM if transitioning to MIN_POWER */
+        ata_for_each_dev(dev, link, ENABLED) {
+                if (policy == ATA_LPM_MIN_POWER && !no_dipm &&
+                    ata_id_has_dipm(dev->id)) {
+                        err_mask = ata_dev_set_feature(dev,
+                                        SETFEATURES_SATA_ENABLE, SATA_DIPM);
+                        if (err_mask && err_mask != AC_ERR_DEV) {
+                                ata_dev_printk(dev, KERN_WARNING,
+                                        "failed to enable DIPM, Emask 0x%x\n",
+                                        err_mask);
+                                rc = -EIO;
+                                goto fail;
+                        }
+                }
+        }
+
+        return 0;
+
+fail:
+        /* restore the old policy */
+        link->lpm_policy = old_policy;
+        if (ap && ap->slave_link)
+                ap->slave_link->lpm_policy = old_policy;
+
+        /* if no device or only one more chance is left, disable LPM */
+        if (!dev || ehc->tries[dev->devno] <= 2) {
+                ata_link_printk(link, KERN_WARNING,
+                                "disabling LPM on the link\n");
+                link->flags |= ATA_LFLAG_NO_LPM;
+        }
+        if (r_failed_dev)
+                *r_failed_dev = dev;
+        return rc;
+}
+
+int ata_link_nr_enabled(struct ata_link *link)
 {
         struct ata_device *dev;
         int cnt = 0;
@@ -3288,6 +3511,16 @@ static int ata_eh_schedule_probe(struct ata_device *dev)
         ehc->saved_xfer_mode[dev->devno] = 0;
         ehc->saved_ncq_enabled &= ~(1 << dev->devno);
 
+        /* the link maybe in a deep sleep, wake it up */
+        if (link->lpm_policy > ATA_LPM_MAX_POWER) {
+                if (ata_is_host_link(link))
+                        link->ap->ops->set_lpm(link, ATA_LPM_MAX_POWER,
+                                               ATA_LPM_EMPTY);
+                else
+                        sata_pmp_set_lpm(link, ATA_LPM_MAX_POWER,
+                                         ATA_LPM_EMPTY);
+        }
+
         /* 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
@@ -3389,8 +3622,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 {
         struct ata_link *link;
         struct ata_device *dev;
-        int nr_failed_devs;
-        int rc;
+        int rc, nr_fails;
         unsigned long flags, deadline;
 
         DPRINTK("ENTER\n");
@@ -3431,7 +3663,6 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 
  retry:
         rc = 0;
-        nr_failed_devs = 0;
 
         /* if UNLOADING, finish immediately */
         if (ap->pflags & ATA_PFLAG_UNLOADING)
@@ -3501,8 +3732,10 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
                 if (time_before_eq(deadline, now))
                         break;
 
+                ata_eh_release(ap);
                 deadline = wait_for_completion_timeout(&ap->park_req_pending,
                                                        deadline - now);
+                ata_eh_acquire(ap);
         } while (deadline);
         ata_for_each_link(link, ap, EDGE) {
                 ata_for_each_dev(dev, link, ALL) {
@@ -3516,13 +3749,17 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
         }
 
         /* the rest */
-        ata_for_each_link(link, ap, EDGE) {
+        nr_fails = 0;
+        ata_for_each_link(link, ap, PMP_FIRST) {
                 struct ata_eh_context *ehc = &link->eh_context;
 
+                if (sata_pmp_attached(ap) && ata_is_host_link(link))
+                        goto config_lpm;
+
                 /* revalidate existing devices and attach new ones */
                 rc = ata_eh_revalidate_and_attach(link, &dev);
                 if (rc)
-                        goto dev_fail;
+                        goto rest_fail;
 
                 /* if PMP got attached, return, pmp EH will take care of it */
                 if (link->device->class == ATA_DEV_PMP) {
@@ -3534,7 +3771,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
                 if (ehc->i.flags & ATA_EHI_SETMODE) {
                         rc = ata_set_mode(link, &dev);
                         if (rc)
-                                goto dev_fail;
+                                goto rest_fail;
                         ehc->i.flags &= ~ATA_EHI_SETMODE;
                 }
 
@@ -3547,7 +3784,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
                                         continue;
                                 rc = atapi_eh_clear_ua(dev);
                                 if (rc)
-                                        goto dev_fail;
+                                        goto rest_fail;
                         }
                 }
 
@@ -3557,21 +3794,25 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
                                 continue;
                         rc = ata_eh_maybe_retry_flush(dev);
                         if (rc)
-                                goto dev_fail;
+                                goto rest_fail;
                 }
 
+        config_lpm:
                 /* configure link power saving */
-                if (ehc->i.action & ATA_EH_LPM)
-                        ata_for_each_dev(dev, link, ALL)
-                                ata_dev_enable_pm(dev, ap->pm_policy);
+                if (link->lpm_policy != ap->target_lpm_policy) {
+                        rc = ata_eh_set_lpm(link, ap->target_lpm_policy, &dev);
+                        if (rc)
+                                goto rest_fail;
+                }
 
                 /* this link is okay now */
                 ehc->i.flags = 0;
                 continue;
 
-dev_fail:
-                nr_failed_devs++;
-                ata_eh_handle_dev_fail(dev, rc);
+        rest_fail:
+                nr_fails++;
+                if (dev)
+                        ata_eh_handle_dev_fail(dev, rc);
 
                 if (ap->pflags & ATA_PFLAG_FROZEN) {
                         /* PMP reset requires working host port.
@@ -3583,7 +3824,7 @@ dev_fail:
                 }
         }
 
-        if (nr_failed_devs)
+        if (nr_fails)
                 goto retry;
 
  out: