[SCSI] libsas: suspend / resume support

libsas power management routines to suspend and recover the sas domain
based on a model where the lldd is allowed and expected to be
"forgetful".

sas_suspend_ha - disable event processing allowing the lldd to take down
                 links without concern for causing hotplug events.
                 Regardless of whether the lldd actually posts link down
                 messages libsas notifies the lldd that all
                 domain_devices are gone.

sas_prep_resume_ha - on the way back up before the lldd starts link
                     training clean out any spurious events that were
                     generated on the way down, and re-enable event
                     processing

sas_resume_ha - after the lldd has started and decided that all phys
		have posted link-up events this routine is called to let
		libsas start it's own timeout of any phys that did not
		resume.  After the timeout an lldd can cancel the
                phy teardown by posting a link-up event.

Storage for ex_change_count (u16) and phy_change_count (u8) are changed
to int so they can be set to -1 to indicate 'invalidated'.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jacek Danecki <jacek.danecki@intel.com>
Tested-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>

8 files changed, 310 insertions, 14 deletions

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index a59fcdc8fd6..905ae45133f 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -700,6 +700,92 @@ void sas_probe_sata(struct asd_sas_port *port)
                 if (ata_dev_disabled(sas_to_ata_dev(dev)))
                         sas_fail_probe(dev, __func__, -ENODEV);
         }
+
+}
+
+static bool sas_ata_flush_pm_eh(struct asd_sas_port *port, const char *func)
+{
+        struct domain_device *dev, *n;
+        bool retry = false;
+
+        list_for_each_entry_safe(dev, n, &port->dev_list, dev_list_node) {
+                int rc;
+
+                if (!dev_is_sata(dev))
+                        continue;
+
+                sas_ata_wait_eh(dev);
+                rc = dev->sata_dev.pm_result;
+                if (rc == -EAGAIN)
+                        retry = true;
+                else if (rc) {
+                        /* since we don't have a
+                         * ->port_{suspend|resume} routine in our
+                         *  ata_port ops, and no entanglements with
+                         *  acpi, suspend should just be mechanical trip
+                         *  through eh, catch cases where these
+                         *  assumptions are invalidated
+                         */
+                        WARN_ONCE(1, "failed %s %s error: %d\n", func,
+                                 dev_name(&dev->rphy->dev), rc);
+                }
+
+                /* if libata failed to power manage the device, tear it down */
+                if (ata_dev_disabled(sas_to_ata_dev(dev)))
+                        sas_fail_probe(dev, func, -ENODEV);
+        }
+
+        return retry;
+}
+
+void sas_suspend_sata(struct asd_sas_port *port)
+{
+        struct domain_device *dev;
+
+ retry:
+        mutex_lock(&port->ha->disco_mutex);
+        list_for_each_entry(dev, &port->dev_list, dev_list_node) {
+                struct sata_device *sata;
+
+                if (!dev_is_sata(dev))
+                        continue;
+
+                sata = &dev->sata_dev;
+                if (sata->ap->pm_mesg.event == PM_EVENT_SUSPEND)
+                        continue;
+
+                sata->pm_result = -EIO;
+                ata_sas_port_async_suspend(sata->ap, &sata->pm_result);
+        }
+        mutex_unlock(&port->ha->disco_mutex);
+
+        if (sas_ata_flush_pm_eh(port, __func__))
+                goto retry;
+}
+
+void sas_resume_sata(struct asd_sas_port *port)
+{
+        struct domain_device *dev;
+
+ retry:
+        mutex_lock(&port->ha->disco_mutex);
+        list_for_each_entry(dev, &port->dev_list, dev_list_node) {
+                struct sata_device *sata;
+
+                if (!dev_is_sata(dev))
+                        continue;
+
+                sata = &dev->sata_dev;
+                if (sata->ap->pm_mesg.event == PM_EVENT_ON)
+                        continue;
+
+                sata->pm_result = -EIO;
+                ata_sas_port_async_resume(sata->ap, &sata->pm_result);
+        }
+        mutex_unlock(&port->ha->disco_mutex);
+
+        if (sas_ata_flush_pm_eh(port, __func__))
+                goto retry;
 }
 
 /**
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 3e9dc1a8435..a0c3003e0c7 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -24,6 +24,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/async.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_eh.h>
 #include "sas_internal.h"
@@ -180,16 +181,18 @@ int sas_notify_lldd_dev_found(struct domain_device *dev)
         struct Scsi_Host *shost = sas_ha->core.shost;
         struct sas_internal *i = to_sas_internal(shost->transportt);
 
-        if (i->dft->lldd_dev_found) {
-                res = i->dft->lldd_dev_found(dev);
-                if (res) {
-                        printk("sas: driver on pcidev %s cannot handle "
-                               "device %llx, error:%d\n",
-                               dev_name(sas_ha->dev),
-                               SAS_ADDR(dev->sas_addr), res);
-                }
-                kref_get(&dev->kref);
+        if (!i->dft->lldd_dev_found)
+                return 0;
+
+        res = i->dft->lldd_dev_found(dev);
+        if (res) {
+                printk("sas: driver on pcidev %s cannot handle "
+                       "device %llx, error:%d\n",
+                       dev_name(sas_ha->dev),
+                       SAS_ADDR(dev->sas_addr), res);
         }
+        set_bit(SAS_DEV_FOUND, &dev->state);
+        kref_get(&dev->kref);
         return res;
 }
 
@@ -200,7 +203,10 @@ void sas_notify_lldd_dev_gone(struct domain_device *dev)
         struct Scsi_Host *shost = sas_ha->core.shost;
         struct sas_internal *i = to_sas_internal(shost->transportt);
 
-        if (i->dft->lldd_dev_gone) {
+        if (!i->dft->lldd_dev_gone)
+                return;
+
+        if (test_and_clear_bit(SAS_DEV_FOUND, &dev->state)) {
                 i->dft->lldd_dev_gone(dev);
                 sas_put_device(dev);
         }
@@ -234,6 +240,47 @@ static void sas_probe_devices(struct work_struct *work)
         }
 }
 
+static void sas_suspend_devices(struct work_struct *work)
+{
+        struct asd_sas_phy *phy;
+        struct domain_device *dev;
+        struct sas_discovery_event *ev = to_sas_discovery_event(work);
+        struct asd_sas_port *port = ev->port;
+        struct Scsi_Host *shost = port->ha->core.shost;
+        struct sas_internal *si = to_sas_internal(shost->transportt);
+
+        clear_bit(DISCE_SUSPEND, &port->disc.pending);
+
+        sas_suspend_sata(port);
+
+        /* lldd is free to forget the domain_device across the
+         * suspension, we force the issue here to keep the reference
+         * counts aligned
+         */
+        list_for_each_entry(dev, &port->dev_list, dev_list_node)
+                sas_notify_lldd_dev_gone(dev);
+
+        /* we are suspending, so we know events are disabled and
+         * phy_list is not being mutated
+         */
+        list_for_each_entry(phy, &port->phy_list, port_phy_el) {
+                if (si->dft->lldd_port_formed)
+                        si->dft->lldd_port_deformed(phy);
+                phy->suspended = 1;
+                port->suspended = 1;
+        }
+}
+
+static void sas_resume_devices(struct work_struct *work)
+{
+        struct sas_discovery_event *ev = to_sas_discovery_event(work);
+        struct asd_sas_port *port = ev->port;
+
+        clear_bit(DISCE_RESUME, &port->disc.pending);
+
+        sas_resume_sata(port);
+}
+
 /**
  * sas_discover_end_dev -- discover an end device (SSP, etc)
  * @end: pointer to domain device of interest
@@ -530,6 +577,8 @@ void sas_init_disc(struct sas_discovery *disc, struct asd_sas_port *port)
                 [DISCE_DISCOVER_DOMAIN] = sas_discover_domain,
                 [DISCE_REVALIDATE_DOMAIN] = sas_revalidate_domain,
                 [DISCE_PROBE] = sas_probe_devices,
+                [DISCE_SUSPEND] = sas_suspend_devices,
+                [DISCE_RESUME] = sas_resume_devices,
                 [DISCE_DESTRUCT] = sas_destruct_devices,
         };
 
diff --git a/drivers/scsi/libsas/sas_dump.c b/drivers/scsi/libsas/sas_dump.c
index fc460933575..cd6f99c1ae7 100644
--- a/drivers/scsi/libsas/sas_dump.c
+++ b/drivers/scsi/libsas/sas_dump.c
@@ -41,6 +41,7 @@ static const char *sas_phye_str[] = {
         [1] = "PHYE_OOB_DONE",
         [2] = "PHYE_OOB_ERROR",
         [3] = "PHYE_SPINUP_HOLD",
+        [4] = "PHYE_RESUME_TIMEOUT",
 };
 
 void sas_dprint_porte(int phyid, enum port_event pe)
diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c
index 789c4d8bb7a..aadbd5314c5 100644
--- a/drivers/scsi/libsas/sas_event.c
+++ b/drivers/scsi/libsas/sas_event.c
@@ -134,7 +134,7 @@ static void notify_port_event(struct asd_sas_phy *phy, enum port_event event)
                         &phy->port_events[event].work, ha);
 }
 
-static void notify_phy_event(struct asd_sas_phy *phy, enum phy_event event)
+void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event)
 {
         struct sas_ha_struct *ha = phy->ha;
 
@@ -159,7 +159,7 @@ int sas_init_events(struct sas_ha_struct *sas_ha)
 
         sas_ha->notify_ha_event = notify_ha_event;
         sas_ha->notify_port_event = notify_port_event;
-        sas_ha->notify_phy_event = notify_phy_event;
+        sas_ha->notify_phy_event = sas_notify_phy_event;
 
         return 0;
 }
diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c
index 014297c0588..dbc8a793fd8 100644
--- a/drivers/scsi/libsas/sas_init.c
+++ b/drivers/scsi/libsas/sas_init.c
@@ -178,7 +178,7 @@ Undo_phys:
         return error;
 }
 
-int sas_unregister_ha(struct sas_ha_struct *sas_ha)
+static void sas_disable_events(struct sas_ha_struct *sas_ha)
 {
         /* Set the state to unregistered to avoid further unchained
          * events to be queued, and flush any in-progress drainers
@@ -189,7 +189,11 @@ int sas_unregister_ha(struct sas_ha_struct *sas_ha)
         spin_unlock_irq(&sas_ha->lock);
         __sas_drain_work(sas_ha);
         mutex_unlock(&sas_ha->drain_mutex);
+}
 
+int sas_unregister_ha(struct sas_ha_struct *sas_ha)
+{
+        sas_disable_events(sas_ha);
         sas_unregister_ports(sas_ha);
 
         /* flush unregistration work */
@@ -381,6 +385,90 @@ int sas_set_phy_speed(struct sas_phy *phy,
         return ret;
 }
 
+void sas_prep_resume_ha(struct sas_ha_struct *ha)
+{
+        int i;
+
+        set_bit(SAS_HA_REGISTERED, &ha->state);
+
+        /* clear out any stale link events/data from the suspension path */
+        for (i = 0; i < ha->num_phys; i++) {
+                struct asd_sas_phy *phy = ha->sas_phy[i];
+
+                memset(phy->attached_sas_addr, 0, SAS_ADDR_SIZE);
+                phy->port_events_pending = 0;
+                phy->phy_events_pending = 0;
+                phy->frame_rcvd_size = 0;
+        }
+}
+EXPORT_SYMBOL(sas_prep_resume_ha);
+
+static int phys_suspended(struct sas_ha_struct *ha)
+{
+        int i, rc = 0;
+
+        for (i = 0; i < ha->num_phys; i++) {
+                struct asd_sas_phy *phy = ha->sas_phy[i];
+
+                if (phy->suspended)
+                        rc++;
+        }
+
+        return rc;
+}
+
+void sas_resume_ha(struct sas_ha_struct *ha)
+{
+        const unsigned long tmo = msecs_to_jiffies(25000);
+        int i;
+
+        /* deform ports on phys that did not resume
+         * at this point we may be racing the phy coming back (as posted
+         * by the lldd).  So we post the event and once we are in the
+         * libsas context check that the phy remains suspended before
+         * tearing it down.
+         */
+        i = phys_suspended(ha);
+        if (i)
+                dev_info(ha->dev, "waiting up to 25 seconds for %d phy%s to resume\n",
+                         i, i > 1 ? "s" : "");
+        wait_event_timeout(ha->eh_wait_q, phys_suspended(ha) == 0, tmo);
+        for (i = 0; i < ha->num_phys; i++) {
+                struct asd_sas_phy *phy = ha->sas_phy[i];
+
+                if (phy->suspended) {
+                        dev_warn(&phy->phy->dev, "resume timeout\n");
+                        sas_notify_phy_event(phy, PHYE_RESUME_TIMEOUT);
+                }
+        }
+
+        /* all phys are back up or timed out, turn on i/o so we can
+         * flush out disks that did not return
+         */
+        scsi_unblock_requests(ha->core.shost);
+        sas_drain_work(ha);
+}
+EXPORT_SYMBOL(sas_resume_ha);
+
+void sas_suspend_ha(struct sas_ha_struct *ha)
+{
+        int i;
+
+        sas_disable_events(ha);
+        scsi_block_requests(ha->core.shost);
+        for (i = 0; i < ha->num_phys; i++) {
+                struct asd_sas_port *port = ha->sas_port[i];
+
+                sas_discover_event(port, DISCE_SUSPEND);
+        }
+
+        /* flush suspend events while unregistered */
+        mutex_lock(&ha->drain_mutex);
+        __sas_drain_work(ha);
+        mutex_unlock(&ha->drain_mutex);
+}
+EXPORT_SYMBOL(sas_suspend_ha);
+
 static void sas_phy_release(struct sas_phy *phy)
 {
         kfree(phy->hostdata);
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 507e4cf12e5..1de67964e5a 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -89,6 +89,7 @@ int sas_smp_phy_control(struct domain_device *dev, int phy_id,
                         enum phy_func phy_func, struct sas_phy_linkrates *);
 int sas_smp_get_phy_events(struct sas_phy *phy);
 
+void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event);
 void sas_device_set_phy(struct domain_device *dev, struct sas_port *port);
 struct domain_device *sas_find_dev_by_rphy(struct sas_rphy *rphy);
 struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id);
diff --git a/drivers/scsi/libsas/sas_phy.c b/drivers/scsi/libsas/sas_phy.c
index 521422e857a..cdee446c29e 100644
--- a/drivers/scsi/libsas/sas_phy.c
+++ b/drivers/scsi/libsas/sas_phy.c
@@ -94,6 +94,25 @@ static void sas_phye_spinup_hold(struct work_struct *work)
         i->dft->lldd_control_phy(phy, PHY_FUNC_RELEASE_SPINUP_HOLD, NULL);
 }
 
+static void sas_phye_resume_timeout(struct work_struct *work)
+{
+        struct asd_sas_event *ev = to_asd_sas_event(work);
+        struct asd_sas_phy *phy = ev->phy;
+
+        clear_bit(PHYE_RESUME_TIMEOUT, &phy->phy_events_pending);
+
+        /* phew, lldd got the phy back in the nick of time */
+        if (!phy->suspended) {
+                dev_info(&phy->phy->dev, "resume timeout cancelled\n");
+                return;
+        }
+
+        phy->error = 0;
+        phy->suspended = 0;
+        sas_deform_port(phy, 1);
+}
+
+
 /* ---------- Phy class registration ---------- */
 
 int sas_register_phys(struct sas_ha_struct *sas_ha)
@@ -105,6 +124,8 @@ int sas_register_phys(struct sas_ha_struct *sas_ha)
                 [PHYE_OOB_DONE] = sas_phye_oob_done,
                 [PHYE_OOB_ERROR] = sas_phye_oob_error,
                 [PHYE_SPINUP_HOLD] = sas_phye_spinup_hold,
+                [PHYE_RESUME_TIMEOUT] = sas_phye_resume_timeout,
+
         };
 
         static const work_func_t sas_port_event_fns[PORT_NUM_EVENTS] = {
diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c
index e884a8c58a0..1398b714c01 100644
--- a/drivers/scsi/libsas/sas_port.c
+++ b/drivers/scsi/libsas/sas_port.c
@@ -39,6 +39,49 @@ static bool phy_is_wideport_member(struct asd_sas_port *port, struct asd_sas_phy
         return true;
 }
 
+static void sas_resume_port(struct asd_sas_phy *phy)
+{
+        struct domain_device *dev;
+        struct asd_sas_port *port = phy->port;
+        struct sas_ha_struct *sas_ha = phy->ha;
+        struct sas_internal *si = to_sas_internal(sas_ha->core.shost->transportt);
+
+        if (si->dft->lldd_port_formed)
+                si->dft->lldd_port_formed(phy);
+
+        if (port->suspended)
+                port->suspended = 0;
+        else {
+                /* we only need to handle "link returned" actions once */
+                return;
+        }
+
+        /* if the port came back:
+         * 1/ presume every device came back
+         * 2/ force the next revalidation to check all expander phys
+         */
+        list_for_each_entry(dev, &port->dev_list, dev_list_node) {
+                int i, rc;
+
+                rc = sas_notify_lldd_dev_found(dev);
+                if (rc) {
+                        sas_unregister_dev(port, dev);
+                        continue;
+                }
+
+                if (dev->dev_type == EDGE_DEV || dev->dev_type == FANOUT_DEV) {
+                        dev->ex_dev.ex_change_count = -1;
+                        for (i = 0; i < dev->ex_dev.num_phys; i++) {
+                                struct ex_phy *phy = &dev->ex_dev.ex_phy[i];
+
+                                phy->phy_change_count = -1;
+                        }
+                }
+        }
+
+        sas_discover_event(port, DISCE_RESUME);
+}
+
 /**
  * sas_form_port -- add this phy to a port
  * @phy: the phy of interest
@@ -58,7 +101,14 @@ static void sas_form_port(struct asd_sas_phy *phy)
         if (port) {
                 if (!phy_is_wideport_member(port, phy))
                         sas_deform_port(phy, 0);
-                else {
+                else if (phy->suspended) {
+                        phy->suspended = 0;
+                        sas_resume_port(phy);
+
+                        /* phy came back, try to cancel the timeout */
+                        wake_up(&sas_ha->eh_wait_q);
+                        return;
+                } else {
                         SAS_DPRINTK("%s: phy%d belongs to port%d already(%d)!\n",
                                     __func__, phy->id, phy->port->id,
                                     phy->port->num_phys);