From b15ebe0b5d0b95aeb1d84cae3649df1e0e065e9b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 17 Nov 2011 17:59:49 -0800 Subject: [SCSI] libsas: replace event locks with atomic bitops The locks only served to make sure the pending event bitmask was updated consistently. Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- drivers/scsi/libsas/sas_event.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'drivers/scsi/libsas/sas_event.c') diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 9db30fb5caf..9c084bc09bb 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -30,7 +30,7 @@ static void notify_ha_event(struct sas_ha_struct *sas_ha, enum ha_event event) { BUG_ON(event >= HA_NUM_EVENTS); - sas_queue_event(event, &sas_ha->event_lock, &sas_ha->pending, + sas_queue_event(event, &sas_ha->pending, &sas_ha->ha_events[event].work, sas_ha); } @@ -40,7 +40,7 @@ static void notify_port_event(struct asd_sas_phy *phy, enum port_event event) BUG_ON(event >= PORT_NUM_EVENTS); - sas_queue_event(event, &ha->event_lock, &phy->port_events_pending, + sas_queue_event(event, &phy->port_events_pending, &phy->port_events[event].work, ha); } @@ -50,7 +50,7 @@ static void notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) BUG_ON(event >= PHY_NUM_EVENTS); - sas_queue_event(event, &ha->event_lock, &phy->phy_events_pending, + sas_queue_event(event, &phy->phy_events_pending, &phy->phy_events[event].work, ha); } @@ -62,8 +62,6 @@ int sas_init_events(struct sas_ha_struct *sas_ha) int i; - spin_lock_init(&sas_ha->event_lock); - for (i = 0; i < HA_NUM_EVENTS; i++) { INIT_WORK(&sas_ha->ha_events[i].work, sas_ha_event_fns[i]); sas_ha->ha_events[i].ha = sas_ha; -- cgit v1.2.3-70-g09d2 From b1124cd3ec97406c767b90bf7e93ecd2d2915592 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 19 Dec 2011 16:42:34 -0800 Subject: [SCSI] libsas: introduce sas_drain_work() When an lldd invokes ->notify_port_event() it can trigger a chain of libsas events to: 1/ form the port and find the direct attached device 2/ if the attached device is an expander perform domain discovery A call to flush_workqueue() will only flush the initial port formation work. Currently libsas users need to call scsi_flush_work() up to the max depth of chain (which will grow from 2 to 3 when ata discovery is moved to its own discovery event). Instead of open coding multiple calls switch to use drain_workqueue() to flush sas work. drain_workqueue() does not handle new work submitted during the drain so libsas needs a bit of infrastructure to hold off unchained work submissions while a drain is in flight. A lldd ->notify() event is considered 'unchained' while a sas_discover_event() is 'chained'. As Tejun notes: "For now, I think it would be best to add private wrapper in libsas to support deferring unchained work items while draining." Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- drivers/scsi/aic94xx/aic94xx_init.c | 2 +- drivers/scsi/isci/host.c | 8 ++---- drivers/scsi/libsas/sas_discover.c | 21 +++++++++++++- drivers/scsi/libsas/sas_event.c | 55 +++++++++++++++++++++++++++++++++++++ drivers/scsi/libsas/sas_init.c | 9 ++++-- drivers/scsi/libsas/sas_internal.h | 14 ---------- drivers/scsi/mvsas/mv_sas.c | 2 +- drivers/scsi/pm8001/pm8001_sas.c | 4 ++- include/scsi/libsas.h | 4 +++ 9 files changed, 93 insertions(+), 26 deletions(-) (limited to 'drivers/scsi/libsas/sas_event.c') diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index 8db4e727628..2b3717f6d22 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -971,7 +971,7 @@ static int asd_scan_finished(struct Scsi_Host *shost, unsigned long time) if (time < HZ) return 0; /* Wait for discovery to finish */ - scsi_flush_work(shost); + sas_drain_work(SHOST_TO_SAS_HA(shost)); return 1; } diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index 508aa8ce25b..e3cf3832c5b 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -650,15 +650,13 @@ static void isci_host_start_complete(struct isci_host *ihost, enum sci_status co int isci_host_scan_finished(struct Scsi_Host *shost, unsigned long time) { - struct isci_host *ihost = SHOST_TO_SAS_HA(shost)->lldd_ha; + struct sas_ha_struct *ha = SHOST_TO_SAS_HA(shost); + struct isci_host *ihost = ha->lldd_ha; if (test_bit(IHOST_START_PENDING, &ihost->flags)) return 0; - /* todo: use sas_flush_discovery once it is upstream */ - scsi_flush_work(shost); - - scsi_flush_work(shost); + sas_drain_work(ha); dev_dbg(&ihost->pdev->dev, "%s: ihost->status = %d, time = %ld\n", diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index ed041189e76..32e01176604 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -367,6 +367,25 @@ static void sas_revalidate_domain(struct work_struct *work) /* ---------- Events ---------- */ +static void sas_chain_work(struct sas_ha_struct *ha, struct work_struct *work) +{ + /* chained work is not subject to SA_HA_DRAINING or SAS_HA_REGISTERED */ + scsi_queue_work(ha->core.shost, work); +} + +static void sas_chain_event(int event, unsigned long *pending, + struct work_struct *work, + struct sas_ha_struct *ha) +{ + if (!test_and_set_bit(event, pending)) { + unsigned long flags; + + spin_lock_irqsave(&ha->state_lock, flags); + sas_chain_work(ha, work); + spin_unlock_irqrestore(&ha->state_lock, flags); + } +} + int sas_discover_event(struct asd_sas_port *port, enum discover_event ev) { struct sas_discovery *disc; @@ -377,7 +396,7 @@ int sas_discover_event(struct asd_sas_port *port, enum discover_event ev) BUG_ON(ev >= DISC_NUM_EVENTS); - sas_queue_event(ev, &disc->pending, &disc->disc_work[ev].work, port->ha); + sas_chain_event(ev, &disc->pending, &disc->disc_work[ev].work, port->ha); return 0; } diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 9c084bc09bb..e5035aa4c2a 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -22,10 +22,65 @@ * */ +#include #include #include "sas_internal.h" #include "sas_dump.h" +static void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work) +{ + if (!test_bit(SAS_HA_REGISTERED, &ha->state)) + return; + + if (test_bit(SAS_HA_DRAINING, &ha->state)) + list_add(&work->entry, &ha->defer_q); + else + scsi_queue_work(ha->core.shost, work); +} + +static void sas_queue_event(int event, unsigned long *pending, + struct work_struct *work, + struct sas_ha_struct *ha) +{ + if (!test_and_set_bit(event, pending)) { + unsigned long flags; + + spin_lock_irqsave(&ha->state_lock, flags); + sas_queue_work(ha, work); + spin_unlock_irqrestore(&ha->state_lock, flags); + } +} + +int sas_drain_work(struct sas_ha_struct *ha) +{ + struct workqueue_struct *wq = ha->core.shost->work_q; + struct work_struct *w, *_w; + int err; + + err = mutex_lock_interruptible(&ha->drain_mutex); + if (err) + return err; + + set_bit(SAS_HA_DRAINING, &ha->state); + /* flush submitters */ + spin_lock_irq(&ha->state_lock); + spin_unlock_irq(&ha->state_lock); + + drain_workqueue(wq); + + spin_lock_irq(&ha->state_lock); + clear_bit(SAS_HA_DRAINING, &ha->state); + list_for_each_entry_safe(w, _w, &ha->defer_q, entry) { + list_del_init(&w->entry); + sas_queue_work(ha, w); + } + spin_unlock_irq(&ha->state_lock); + mutex_unlock(&ha->drain_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(sas_drain_work); + static void notify_ha_event(struct sas_ha_struct *sas_ha, enum ha_event event) { BUG_ON(event >= HA_NUM_EVENTS); diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index da244e68fe6..572b943d760 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -114,6 +114,8 @@ int sas_register_ha(struct sas_ha_struct *sas_ha) set_bit(SAS_HA_REGISTERED, &sas_ha->state); spin_lock_init(&sas_ha->state_lock); + mutex_init(&sas_ha->drain_mutex); + INIT_LIST_HEAD(&sas_ha->defer_q); error = sas_register_phys(sas_ha); if (error) { @@ -157,12 +159,13 @@ int sas_unregister_ha(struct sas_ha_struct *sas_ha) { unsigned long flags; - /* Set the state to unregistered to avoid further - * events to be queued */ + /* Set the state to unregistered to avoid further unchained + * events to be queued + */ spin_lock_irqsave(&sas_ha->state_lock, flags); clear_bit(SAS_HA_REGISTERED, &sas_ha->state); spin_unlock_irqrestore(&sas_ha->state_lock, flags); - scsi_flush_work(sas_ha->core.shost); + sas_drain_work(sas_ha); sas_unregister_ports(sas_ha); diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 1fd84b3f091..948ea64cc2e 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -92,20 +92,6 @@ static inline int sas_smp_host_handler(struct Scsi_Host *shost, } #endif -static inline void sas_queue_event(int event, unsigned long *pending, - struct work_struct *work, - struct sas_ha_struct *sas_ha) -{ - if (!test_and_set_bit(event, pending)) { - unsigned long flags; - - spin_lock_irqsave(&sas_ha->state_lock, flags); - if (test_bit(SAS_HA_REGISTERED, &sas_ha->state)) - scsi_queue_work(sas_ha->core.shost, work); - spin_unlock_irqrestore(&sas_ha->state_lock, flags); - } -} - static inline void sas_fill_in_rphy(struct domain_device *dev, struct sas_rphy *rphy) { diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index a4884a57cf7..b118e632bc7 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -308,7 +308,7 @@ int mvs_scan_finished(struct Scsi_Host *shost, unsigned long time) if (mvs_prv->scan_finished == 0) return 0; - scsi_flush_work(shost); + sas_drain_work(sha); return 1; } diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 9589fc941a8..50837933a1e 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -256,12 +256,14 @@ void pm8001_scan_start(struct Scsi_Host *shost) int pm8001_scan_finished(struct Scsi_Host *shost, unsigned long time) { + struct sas_ha_struct *ha = SHOST_TO_SAS_HA(shost); + /* give the phy enabling interrupt event time to come in (1s * is empirically about all it takes) */ if (time < HZ) return 0; /* Wait for discovery to finish */ - scsi_flush_work(shost); + sas_drain_work(ha); return 1; } diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 8e402d5a064..42900fa95a0 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -330,6 +330,7 @@ struct sas_ha_event { enum sas_ha_state { SAS_HA_REGISTERED, + SAS_HA_DRAINING, }; struct sas_ha_struct { @@ -337,6 +338,8 @@ struct sas_ha_struct { struct sas_ha_event ha_events[HA_NUM_EVENTS]; unsigned long pending; + struct list_head defer_q; /* work queued while draining */ + struct mutex drain_mutex; unsigned long state; spinlock_t state_lock; @@ -657,6 +660,7 @@ int sas_eh_bus_reset_handler(struct scsi_cmnd *cmd); extern void sas_target_destroy(struct scsi_target *); extern int sas_slave_alloc(struct scsi_device *); extern int sas_ioctl(struct scsi_device *sdev, int cmd, void __user *arg); +extern int sas_drain_work(struct sas_ha_struct *ha); extern int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, struct request *req); -- cgit v1.2.3-70-g09d2 From 87c8331fcf72e501c3a3c0cdc5c9391ec72f7cf2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 17 Nov 2011 17:59:51 -0800 Subject: [SCSI] libsas: prevent domain rediscovery competing with ata error handling libata error handling provides for a timeout for link recovery. libsas must not rescan for previously known devices in this interval otherwise it may remove a device that is simply waiting for its link to recover. Let libata-eh make the determination of when the link is stable and prevent libsas (host workqueue) from taking action while this determination is pending. Using a mutex (ha->disco_mutex) to flush and disable revalidation while eh is running requires any discovery action that may block on eh be moved to its own context outside the lock. Probing ATA devices explicitly waits on ata-eh and the cache-flush-io issued during device removal may also pend awaiting eh completion. Essentially any rphy add/remove activity needs to run outside the lock. This adds two new cleanup states for sas_unregister_domain_devices() 'allocated-but-not-probed', and 'flagged-for-destruction'. In the 'allocated-but-not-probed' state dev->rphy points to a rphy that is known to have not been through a sas_rphy_add() event. At domain teardown check if this device is still pending probe and cleanup accordingly. Similarly if a device has already been queued for removal then sas_unregister_domain_devices has nothing to do. Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- drivers/scsi/libsas/sas_ata.c | 55 ++++++++++++++++++++++++++++++--- drivers/scsi/libsas/sas_discover.c | 63 ++++++++++++++++++++++++++++++++++---- drivers/scsi/libsas/sas_event.c | 26 ++++++++++++++++ drivers/scsi/libsas/sas_expander.c | 5 ++- drivers/scsi/libsas/sas_init.c | 2 ++ drivers/scsi/libsas/sas_internal.h | 3 ++ drivers/scsi/libsas/sas_port.c | 2 ++ drivers/scsi/scsi_transport_sas.c | 18 +++++++++-- include/scsi/libsas.h | 12 ++++++-- include/scsi/sas_ata.h | 5 +++ include/scsi/scsi_transport_sas.h | 1 + 11 files changed, 174 insertions(+), 18 deletions(-) (limited to 'drivers/scsi/libsas/sas_event.c') diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 2fc5a3961ca..4b6365c6410 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -758,6 +758,35 @@ static int sas_discover_sata_pm(struct domain_device *dev) return -ENODEV; } +void sas_probe_sata(struct work_struct *work) +{ + struct domain_device *dev, *n; + struct sas_discovery_event *ev = + container_of(work, struct sas_discovery_event, work); + struct asd_sas_port *port = ev->port; + + clear_bit(DISCE_PROBE, &port->disc.pending); + + list_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) { + int err; + + spin_lock_irq(&port->dev_list_lock); + list_add_tail(&dev->dev_list_node, &port->dev_list); + spin_unlock_irq(&port->dev_list_lock); + + err = sas_rphy_add(dev->rphy); + + if (err) { + SAS_DPRINTK("%s: for %s device %16llx returned %d\n", + __func__, dev->parent ? "exp-attached" : + "direct-attached", + SAS_ADDR(dev->sas_addr), err); + sas_unregister_dev(port, dev); + } else + list_del_init(&dev->disco_list_node); + } +} + /** * sas_discover_sata -- discover an STP/SATA domain device * @dev: pointer to struct domain_device of interest @@ -794,10 +823,15 @@ int sas_discover_sata(struct domain_device *dev) break; } sas_notify_lldd_dev_gone(dev); - if (!res) { - sas_notify_lldd_dev_found(dev); - res = sas_rphy_add(dev->rphy); - } + + if (res) + return res; + + res = sas_notify_lldd_dev_found(dev); + if (res) + return res; + + sas_discover_event(dev->port, DISCE_PROBE); return res; } @@ -805,6 +839,17 @@ int sas_discover_sata(struct domain_device *dev) void sas_ata_strategy_handler(struct Scsi_Host *shost) { struct scsi_device *sdev; + struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(shost); + + /* it's ok to defer revalidation events during ata eh, these + * disks are in one of three states: + * 1/ present for initial domain discovery, and these + * resets will cause bcn flutters + * 2/ hot removed, we'll discover that after eh fails + * 3/ hot added after initial discovery, lost the race, and need + * to catch the next train. + */ + sas_disable_revalidation(sas_ha); shost_for_each_device(sdev, shost) { struct domain_device *ddev = sdev_to_domain_dev(sdev); @@ -816,6 +861,8 @@ void sas_ata_strategy_handler(struct Scsi_Host *shost) ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata port error handler"); ata_scsi_port_error_handler(shost, ap); } + + sas_enable_revalidation(sas_ha); } int sas_ata_timed_out(struct scsi_cmnd *cmd, struct sas_task *task, diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 32e01176604..7e8fdcb202b 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -148,9 +148,14 @@ static int sas_get_port_device(struct asd_sas_port *port) port->disc.max_level = 0; dev->rphy = rphy; - spin_lock_irq(&port->dev_list_lock); - list_add_tail(&dev->dev_list_node, &port->dev_list); - spin_unlock_irq(&port->dev_list_lock); + + if (dev_is_sata(dev)) + list_add_tail(&dev->disco_list_node, &port->disco_list); + else { + spin_lock_irq(&port->dev_list_lock); + list_add_tail(&dev->dev_list_node, &port->dev_list); + spin_unlock_irq(&port->dev_list_lock); + } return 0; } @@ -255,14 +260,43 @@ static void sas_unregister_common_dev(struct asd_sas_port *port, struct domain_d sas_put_device(dev); } -void sas_unregister_dev(struct asd_sas_port *port, struct domain_device *dev) +static void sas_destruct_devices(struct work_struct *work) { - if (dev->rphy) { + struct domain_device *dev, *n; + struct sas_discovery_event *ev = + container_of(work, struct sas_discovery_event, work); + struct asd_sas_port *port = ev->port; + + clear_bit(DISCE_DESTRUCT, &port->disc.pending); + + list_for_each_entry_safe(dev, n, &port->destroy_list, disco_list_node) { + list_del_init(&dev->disco_list_node); + sas_remove_children(&dev->rphy->dev); sas_rphy_delete(dev->rphy); dev->rphy = NULL; + sas_unregister_common_dev(port, dev); + + sas_put_device(dev); + } +} + +void sas_unregister_dev(struct asd_sas_port *port, struct domain_device *dev) +{ + if (!test_bit(SAS_DEV_DESTROY, &dev->state) && + !list_empty(&dev->disco_list_node)) { + /* this rphy never saw sas_rphy_add */ + list_del_init(&dev->disco_list_node); + sas_rphy_free(dev->rphy); + dev->rphy = NULL; + sas_unregister_common_dev(port, dev); + } + + if (dev->rphy && !test_and_set_bit(SAS_DEV_DESTROY, &dev->state)) { + sas_rphy_unlink(dev->rphy); + list_move_tail(&dev->disco_list_node, &port->destroy_list); + sas_discover_event(dev->port, DISCE_DESTRUCT); } - sas_unregister_common_dev(port, dev); } void sas_unregister_domain_devices(struct asd_sas_port *port) @@ -271,6 +305,8 @@ void sas_unregister_domain_devices(struct asd_sas_port *port) list_for_each_entry_safe_reverse(dev, n, &port->dev_list, dev_list_node) sas_unregister_dev(port, dev); + list_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) + sas_unregister_dev(port, dev); port->port->rphy = NULL; @@ -335,6 +371,7 @@ static void sas_discover_domain(struct work_struct *work) sas_rphy_free(dev->rphy); dev->rphy = NULL; + list_del_init(&dev->disco_list_node); spin_lock_irq(&port->dev_list_lock); list_del_init(&dev->dev_list_node); spin_unlock_irq(&port->dev_list_lock); @@ -353,16 +390,28 @@ static void sas_revalidate_domain(struct work_struct *work) struct sas_discovery_event *ev = container_of(work, struct sas_discovery_event, work); struct asd_sas_port *port = ev->port; + struct sas_ha_struct *ha = port->ha; + + /* prevent revalidation from finding sata links in recovery */ + mutex_lock(&ha->disco_mutex); + if (test_bit(SAS_HA_ATA_EH_ACTIVE, &ha->state)) { + SAS_DPRINTK("REVALIDATION DEFERRED on port %d, pid:%d\n", + port->id, task_pid_nr(current)); + goto out; + } clear_bit(DISCE_REVALIDATE_DOMAIN, &port->disc.pending); SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id, task_pid_nr(current)); + if (port->port_dev) res = sas_ex_revalidate_domain(port->port_dev); SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n", port->id, task_pid_nr(current), res); + out: + mutex_unlock(&ha->disco_mutex); } /* ---------- Events ---------- */ @@ -414,6 +463,8 @@ void sas_init_disc(struct sas_discovery *disc, struct asd_sas_port *port) static const work_func_t sas_event_fns[DISC_NUM_EVENTS] = { [DISCE_DISCOVER_DOMAIN] = sas_discover_domain, [DISCE_REVALIDATE_DOMAIN] = sas_revalidate_domain, + [DISCE_PROBE] = sas_probe_sata, + [DISCE_DESTRUCT] = sas_destruct_devices, }; disc->pending = 0; diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index e5035aa4c2a..933d757499b 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -81,6 +81,32 @@ int sas_drain_work(struct sas_ha_struct *ha) } EXPORT_SYMBOL_GPL(sas_drain_work); +void sas_disable_revalidation(struct sas_ha_struct *ha) +{ + mutex_lock(&ha->disco_mutex); + set_bit(SAS_HA_ATA_EH_ACTIVE, &ha->state); + mutex_unlock(&ha->disco_mutex); +} + +void sas_enable_revalidation(struct sas_ha_struct *ha) +{ + int i; + + mutex_lock(&ha->disco_mutex); + clear_bit(SAS_HA_ATA_EH_ACTIVE, &ha->state); + for (i = 0; i < ha->num_phys; i++) { + struct asd_sas_port *port = ha->sas_port[i]; + const int ev = DISCE_REVALIDATE_DOMAIN; + struct sas_discovery *d = &port->disc; + + if (!test_and_clear_bit(ev, &d->pending)) + continue; + + sas_queue_event(ev, &d->pending, &d->disc_work[ev].work, ha); + } + mutex_unlock(&ha->disco_mutex); +} + static void notify_ha_event(struct sas_ha_struct *sas_ha, enum ha_event event) { BUG_ON(event >= HA_NUM_EVENTS); diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index f33d0c9911c..e45b259dac4 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -704,9 +704,7 @@ static struct domain_device *sas_ex_discover_end_dev( child->rphy = rphy; - spin_lock_irq(&parent->port->dev_list_lock); - list_add_tail(&child->dev_list_node, &parent->port->dev_list); - spin_unlock_irq(&parent->port->dev_list_lock); + list_add_tail(&child->disco_list_node, &parent->port->disco_list); res = sas_discover_sata(child); if (res) { @@ -756,6 +754,7 @@ static struct domain_device *sas_ex_discover_end_dev( sas_rphy_free(child->rphy); child->rphy = NULL; + list_del(&child->disco_list_node); spin_lock_irq(&parent->port->dev_list_lock); list_del(&child->dev_list_node); spin_unlock_irq(&parent->port->dev_list_lock); diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 572b943d760..52cd11d7666 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -104,6 +104,7 @@ int sas_register_ha(struct sas_ha_struct *sas_ha) { int error = 0; + mutex_init(&sas_ha->disco_mutex); spin_lock_init(&sas_ha->phy_port_lock); sas_hash_addr(sas_ha->hashed_sas_addr, sas_ha->sas_addr); @@ -168,6 +169,7 @@ int sas_unregister_ha(struct sas_ha_struct *sas_ha) sas_drain_work(sas_ha); sas_unregister_ports(sas_ha); + sas_drain_work(sas_ha); if (sas_ha->lldd_max_execute_num > 1) { sas_shutdown_queue(sas_ha); diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 948ea64cc2e..ebe9b81ddef 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -56,6 +56,8 @@ enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *); int sas_init_queue(struct sas_ha_struct *sas_ha); int sas_init_events(struct sas_ha_struct *sas_ha); void sas_shutdown_queue(struct sas_ha_struct *sas_ha); +void sas_disable_revalidation(struct sas_ha_struct *ha); +void sas_enable_revalidation(struct sas_ha_struct *ha); void sas_deform_port(struct asd_sas_phy *phy, int gone); @@ -138,6 +140,7 @@ static inline struct domain_device *sas_alloc_device(void) if (dev) { INIT_LIST_HEAD(&dev->siblings); INIT_LIST_HEAD(&dev->dev_list_node); + INIT_LIST_HEAD(&dev->disco_list_node); kref_init(&dev->kref); } return dev; diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c index d88e55f9732..2980bde4e34 100644 --- a/drivers/scsi/libsas/sas_port.c +++ b/drivers/scsi/libsas/sas_port.c @@ -277,6 +277,8 @@ static void sas_init_port(struct asd_sas_port *port, memset(port, 0, sizeof(*port)); port->id = i; INIT_LIST_HEAD(&port->dev_list); + INIT_LIST_HEAD(&port->disco_list); + INIT_LIST_HEAD(&port->destroy_list); spin_lock_init(&port->phy_list_lock); INIT_LIST_HEAD(&port->phy_list); port->ha = sas_ha; diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 9d9330ae421..9421bae8af1 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -1602,6 +1602,20 @@ sas_rphy_delete(struct sas_rphy *rphy) } EXPORT_SYMBOL(sas_rphy_delete); +/** + * sas_rphy_unlink - unlink SAS remote PHY + * @rphy: SAS remote phy to unlink from its parent port + * + * Removes port reference to an rphy + */ +void sas_rphy_unlink(struct sas_rphy *rphy) +{ + struct sas_port *parent = dev_to_sas_port(rphy->dev.parent); + + parent->rphy = NULL; +} +EXPORT_SYMBOL(sas_rphy_unlink); + /** * sas_rphy_remove - remove SAS remote PHY * @rphy: SAS remote phy to remove @@ -1612,7 +1626,6 @@ void sas_rphy_remove(struct sas_rphy *rphy) { struct device *dev = &rphy->dev; - struct sas_port *parent = dev_to_sas_port(dev->parent); switch (rphy->identify.device_type) { case SAS_END_DEVICE: @@ -1626,10 +1639,9 @@ sas_rphy_remove(struct sas_rphy *rphy) break; } + sas_rphy_unlink(rphy); transport_remove_device(dev); device_del(dev); - - parent->rphy = NULL; } EXPORT_SYMBOL(sas_rphy_remove); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index d792b13cfcf..bd6e89ece2a 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -86,7 +86,9 @@ enum discover_event { DISCE_DISCOVER_DOMAIN = 0U, DISCE_REVALIDATE_DOMAIN = 1, DISCE_PORT_GONE = 2, - DISC_NUM_EVENTS = 3, + DISCE_PROBE = 3, + DISCE_DESTRUCT = 4, + DISC_NUM_EVENTS = 5, }; /* ---------- Expander Devices ---------- */ @@ -175,6 +177,7 @@ struct sata_device { enum { SAS_DEV_GONE, + SAS_DEV_DESTROY, }; struct domain_device { @@ -191,6 +194,7 @@ struct domain_device { struct asd_sas_port *port; /* shortcut to root of the tree */ struct list_head dev_list_node; + struct list_head disco_list_node; /* awaiting probe or destruct */ enum sas_protocol iproto; enum sas_protocol tproto; @@ -226,7 +230,6 @@ struct sas_discovery { int max_level; }; - /* The port struct is Class:RW, driver:RO */ struct asd_sas_port { /* private: */ @@ -236,6 +239,8 @@ struct asd_sas_port { struct domain_device *port_dev; spinlock_t dev_list_lock; struct list_head dev_list; + struct list_head disco_list; + struct list_head destroy_list; enum sas_linkrate linkrate; struct sas_phy *phy; @@ -334,6 +339,7 @@ struct sas_ha_event { enum sas_ha_state { SAS_HA_REGISTERED, SAS_HA_DRAINING, + SAS_HA_ATA_EH_ACTIVE, }; struct sas_ha_struct { @@ -346,6 +352,8 @@ struct sas_ha_struct { unsigned long state; spinlock_t state_lock; + struct mutex disco_mutex; + struct scsi_core core; /* public: */ diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 7d5013f8653..557fc9a8559 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -45,6 +45,7 @@ int sas_ata_timed_out(struct scsi_cmnd *cmd, struct sas_task *task, enum blk_eh_timer_return *rtn); int sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q); +void sas_probe_sata(struct work_struct *work); #else @@ -78,6 +79,10 @@ static inline int sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q, return 0; } +static inline void sas_probe_sata(struct work_struct *work) +{ +} + #endif #endif /* _SAS_ATA_H_ */ diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index ffeebc34a4f..6d14daac758 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -194,6 +194,7 @@ void sas_rphy_free(struct sas_rphy *); extern int sas_rphy_add(struct sas_rphy *); extern void sas_rphy_remove(struct sas_rphy *); extern void sas_rphy_delete(struct sas_rphy *); +extern void sas_rphy_unlink(struct sas_rphy *); extern int scsi_is_sas_rphy(const struct device *); struct sas_port *sas_port_alloc(struct device *, int); -- cgit v1.2.3-70-g09d2 From 0b3e09da1350397f3f8b6fd839ab455b0b587451 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 20 Dec 2011 01:03:48 -0800 Subject: [SCSI] libsas: perform sas-transport resets in shost->workq context Extend the sas transport class to allow transport users to attach extra data to a sas_phy (->hostdata). Use this area in libsas to move resets to workq context in preparation for scheduling ata device resets through libata-eh. Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- drivers/scsi/libsas/sas_event.c | 2 +- drivers/scsi/libsas/sas_init.c | 59 +++++++++++++++++++++++++++++++++++++- drivers/scsi/libsas/sas_internal.h | 10 +++++++ drivers/scsi/scsi_transport_sas.c | 18 +++++++++++- include/scsi/scsi_transport_sas.h | 5 +++- 5 files changed, 90 insertions(+), 4 deletions(-) (limited to 'drivers/scsi/libsas/sas_event.c') diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 933d757499b..dbfaceeea0f 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -27,7 +27,7 @@ #include "sas_internal.h" #include "sas_dump.h" -static void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work) +void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work) { if (!test_bit(SAS_HA_REGISTERED, &ha->state)) return; diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index e17fe35af30..cb65adf4ab1 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -290,9 +290,66 @@ int sas_set_phy_speed(struct sas_phy *phy, return ret; } +static void sas_phy_release(struct sas_phy *phy) +{ + kfree(phy->hostdata); + phy->hostdata = NULL; +} + +static void phy_reset_work(struct work_struct *work) +{ + struct sas_phy_data *d = container_of(work, typeof(*d), reset_work); + + d->reset_result = sas_phy_reset(d->phy, d->hard_reset); +} + +static int sas_phy_setup(struct sas_phy *phy) +{ + struct sas_phy_data *d = kzalloc(sizeof(*d), GFP_KERNEL); + + if (!d) + return -ENOMEM; + + mutex_init(&d->event_lock); + INIT_WORK(&d->reset_work, phy_reset_work); + d->phy = phy; + phy->hostdata = d; + + return 0; +} + +static int queue_phy_reset(struct sas_phy *phy, int hard_reset) +{ + struct Scsi_Host *shost = dev_to_shost(phy->dev.parent); + struct sas_ha_struct *ha = SHOST_TO_SAS_HA(shost); + struct sas_phy_data *d = phy->hostdata; + int rc; + + if (!d) + return -ENOMEM; + + /* libsas workqueue coordinates ata-eh reset with discovery */ + mutex_lock(&d->event_lock); + d->reset_result = 0; + d->hard_reset = hard_reset; + + spin_lock_irq(&ha->state_lock); + sas_queue_work(ha, &d->reset_work); + spin_unlock_irq(&ha->state_lock); + + rc = sas_drain_work(ha); + if (rc == 0) + rc = d->reset_result; + mutex_unlock(&d->event_lock); + + return rc; +} + static struct sas_function_template sft = { .phy_enable = sas_phy_enable, - .phy_reset = sas_phy_reset, + .phy_reset = queue_phy_reset, + .phy_setup = sas_phy_setup, + .phy_release = sas_phy_release, .set_phy_speed = sas_set_phy_speed, .get_linkerrors = sas_get_linkerrors, .smp_handler = sas_smp_handler, diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 662ffcba99d..9ba65e0c6f9 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -38,6 +38,15 @@ #define TO_SAS_TASK(_scsi_cmd) ((void *)(_scsi_cmd)->host_scribble) #define ASSIGN_SAS_TASK(_sc, _t) do { (_sc)->host_scribble = (void *) _t; } while (0) +struct sas_phy_data { + /* let reset be performed in sas_queue_work() context */ + struct sas_phy *phy; + struct mutex event_lock; + int hard_reset; + int reset_result; + struct work_struct reset_work; +}; + void sas_scsi_recover_host(struct Scsi_Host *shost); int sas_show_class(enum sas_class class, char *buf); @@ -66,6 +75,7 @@ void sas_porte_broadcast_rcvd(struct work_struct *work); void sas_porte_link_reset_err(struct work_struct *work); void sas_porte_timer_event(struct work_struct *work); void sas_porte_hard_reset(struct work_struct *work); +void sas_queue_work(struct sas_ha_struct *ha, struct work_struct *work); int sas_notify_lldd_dev_found(struct domain_device *); void sas_notify_lldd_dev_gone(struct domain_device *); diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 9421bae8af1..ab3bd0b5ffd 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -652,9 +652,21 @@ sas_phy_linkerror_attr(running_disparity_error_count); sas_phy_linkerror_attr(loss_of_dword_sync_count); sas_phy_linkerror_attr(phy_reset_problem_count); +static int sas_phy_setup(struct transport_container *tc, struct device *dev, + struct device *cdev) +{ + struct sas_phy *phy = dev_to_phy(dev); + struct Scsi_Host *shost = dev_to_shost(phy->dev.parent); + struct sas_internal *i = to_sas_internal(shost->transportt); + + if (i->f->phy_setup) + i->f->phy_setup(phy); + + return 0; +} static DECLARE_TRANSPORT_CLASS(sas_phy_class, - "sas_phy", NULL, NULL, NULL); + "sas_phy", sas_phy_setup, NULL, NULL); static int sas_phy_match(struct attribute_container *cont, struct device *dev) { @@ -678,7 +690,11 @@ static int sas_phy_match(struct attribute_container *cont, struct device *dev) static void sas_phy_release(struct device *dev) { struct sas_phy *phy = dev_to_phy(dev); + struct Scsi_Host *shost = dev_to_shost(phy->dev.parent); + struct sas_internal *i = to_sas_internal(shost->transportt); + if (i->f->phy_release) + i->f->phy_release(phy); put_device(dev->parent); kfree(phy); } diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 6d14daac758..42817facaed 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -75,7 +75,8 @@ struct sas_phy { /* for the list of phys belonging to a port */ struct list_head port_siblings; - struct work_struct reset_work; + /* available to the lldd */ + void *hostdata; }; #define dev_to_phy(d) \ @@ -169,6 +170,8 @@ struct sas_function_template { int (*get_bay_identifier)(struct sas_rphy *); int (*phy_reset)(struct sas_phy *, int); int (*phy_enable)(struct sas_phy *, int); + int (*phy_setup)(struct sas_phy *); + void (*phy_release)(struct sas_phy *); int (*set_phy_speed)(struct sas_phy *, struct sas_phy_linkrates *); int (*smp_handler)(struct Scsi_Host *, struct sas_rphy *, struct request *); }; -- cgit v1.2.3-70-g09d2 From 5d7f6d1071eadd020edb2cf366d358e0f6d0a0f9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 12 Jan 2012 11:47:24 -0800 Subject: [SCSI] libsas: fix sas_unregister_ports vs sas_drain_work We need to hold drain_mutex across the unregistration as port down events queue device removal as chained events, so we need to make sure no other drainers are active. [ 1118.673968] WARNING: at kernel/workqueue.c:996 __queue_work+0x11a/0x326() [ 1118.681982] Hardware name: S2600CP [ 1118.686193] Modules linked in: isci(-) libsas scsi_transport_sas nls_utf8 ipv6 uinput sg iTCO_wdt iTCO_vendor_support i2c_i801 i2c_core ioatdma dca sd_mod sr_mod cdrom ahci libahci libata [last unloaded: scsi_transport_sas] [ 1118.709893] Pid: 6831, comm: rmmod Not tainted 3.2.0-isci+ #1 [ 1118.716727] Call Trace: [ 1118.719867] [] warn_slowpath_common+0x85/0x9d [ 1118.727000] [] warn_slowpath_null+0x1a/0x1c [ 1118.733942] [] __queue_work+0x11a/0x326 [ 1118.740481] [] queue_work_on+0x1b/0x22 [ 1118.746925] [] queue_work+0x37/0x3e [ 1118.753105] [] ? sas_discover_event+0x55/0x82 [libsas] [ 1118.761094] [] scsi_queue_work+0x42/0x44 [ 1118.767717] [] sas_discover_event+0x69/0x82 [libsas] [ 1118.775509] [] sas_unregister_dev+0xc3/0xcc [libsas] [ 1118.783319] [] sas_unregister_domain_devices+0x4a/0xc8 [libsas] [ 1118.792731] [] sas_deform_port+0x60/0x1a6 [libsas] [ 1118.800339] [] sas_unregister_ports+0x33/0x44 [libsas] [ 1118.808342] [] sas_unregister_ha+0x41/0x6b [libsas] [ 1118.816055] [] isci_unregister+0x22/0x4d [isci] [ 1118.823384] [] isci_pci_remove+0x2e/0x60 [isci] Reported-by: Jacek Danecki Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- drivers/scsi/libsas/sas_event.c | 19 +++++++++++++------ drivers/scsi/libsas/sas_init.c | 18 +++++++++++------- drivers/scsi/libsas/sas_internal.h | 1 + 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'drivers/scsi/libsas/sas_event.c') diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index dbfaceeea0f..16639bbae62 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -51,15 +51,11 @@ static void sas_queue_event(int event, unsigned long *pending, } } -int sas_drain_work(struct sas_ha_struct *ha) + +void __sas_drain_work(struct sas_ha_struct *ha) { struct workqueue_struct *wq = ha->core.shost->work_q; struct work_struct *w, *_w; - int err; - - err = mutex_lock_interruptible(&ha->drain_mutex); - if (err) - return err; set_bit(SAS_HA_DRAINING, &ha->state); /* flush submitters */ @@ -75,6 +71,17 @@ int sas_drain_work(struct sas_ha_struct *ha) sas_queue_work(ha, w); } spin_unlock_irq(&ha->state_lock); +} + +int sas_drain_work(struct sas_ha_struct *ha) +{ + int err; + + err = mutex_lock_interruptible(&ha->drain_mutex); + if (err) + return err; + if (test_bit(SAS_HA_REGISTERED, &ha->state)) + __sas_drain_work(ha); mutex_unlock(&ha->drain_mutex); return 0; diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index dc93e118146..09c14ca3fbd 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -160,18 +160,22 @@ Undo_phys: int sas_unregister_ha(struct sas_ha_struct *sas_ha) { - unsigned long flags; - /* Set the state to unregistered to avoid further unchained - * events to be queued + * events to be queued, and flush any in-progress drainers */ - spin_lock_irqsave(&sas_ha->state_lock, flags); + mutex_lock(&sas_ha->drain_mutex); + spin_lock_irq(&sas_ha->state_lock); clear_bit(SAS_HA_REGISTERED, &sas_ha->state); - spin_unlock_irqrestore(&sas_ha->state_lock, flags); - sas_drain_work(sas_ha); + spin_unlock_irq(&sas_ha->state_lock); + __sas_drain_work(sas_ha); + mutex_unlock(&sas_ha->drain_mutex); sas_unregister_ports(sas_ha); - sas_drain_work(sas_ha); + + /* flush unregistration work */ + mutex_lock(&sas_ha->drain_mutex); + __sas_drain_work(sas_ha); + mutex_unlock(&sas_ha->drain_mutex); if (sas_ha->lldd_max_execute_num > 1) { sas_shutdown_queue(sas_ha); diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 4157f6e1eda..7818c4673c3 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -70,6 +70,7 @@ int sas_init_events(struct sas_ha_struct *sas_ha); void sas_shutdown_queue(struct sas_ha_struct *sas_ha); void sas_disable_revalidation(struct sas_ha_struct *ha); void sas_enable_revalidation(struct sas_ha_struct *ha); +void __sas_drain_work(struct sas_ha_struct *ha); void sas_deform_port(struct asd_sas_phy *phy, int gone); -- cgit v1.2.3-70-g09d2