[PATCH v9 0/3] libsas error handling + discovery v9

[PATCH v9 0/3] libsas error handling + discovery v9

[Dan Williams]

Changes since v8: http://marc.info/?l=linux-scsi&m=132886259501191&w=2

Noticed that the rebased version of "libsas: close scsi_remove_target()
vs libata-eh race" mistakenly dropped a necessary call to
sas_put_device().

...reflowed the other two patches as a result, and added Jeff Garzik's
acked-by:

[PATCH 1/3] libsas: close scsi_remove_target() vs libata-eh race
[PATCH 2/3] libsas: improve debug statements
[PATCH 3/3] libsas: async ata scanning

Incremental diff from v8:

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 1b1d4b7..bc0cecc 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -715,6 +715,7 @@ static void async_sas_ata_eh(void *data, async_cookie_t cookie)
 	kref_get(&dev->kref);
 	sas_ata_printk(KERN_DEBUG, dev, "dev error handler\n");
 	ata_scsi_port_error_handler(ha->core.shost, ap);
+	sas_put_device(dev);
 }
 
 static bool sas_ata_dev_eh_valid(struct domain_device *dev)

[PATCH v9 1/3] libsas: close scsi_remove_target() vs libata-eh race

[Dan Williams]

ata_port lifetime in libata follows the host.  In libsas it follows the
scsi_target.  Once scsi_remove_device() has caused all commands to be
completed it allows scsi_remove_target() to immediately proceed to
freeing the ata_port causing bug reports like:

[  848.393333] BUG: spinlock bad magic on CPU#4, kworker/u:2/5107
[  848.400262] general protection fault: 0000 [#1] SMP
[  848.406244] CPU 4
[  848.408310] Modules linked in: nls_utf8 ipv6 uinput i2c_i801 i2c_core iTCO_wdt iTCO_vendor_support ioatdma dca sg sd_mod sr_mod cdrom ahci libahci isci libsas libata scsi_transport_sas [last unloaded: scsi_wait_scan]
[  848.432060]
[  848.434137] Pid: 5107, comm: kworker/u:2 Not tainted 3.2.0-isci+ #8 Intel Corporation S2600CP/S2600CP
[  848.445310] RIP: 0010:[<ffffffff8126a68c>]  [<ffffffff8126a68c>] spin_dump+0x5e/0x8c
[  848.454787] RSP: 0018:ffff8807f868dca0  EFLAGS: 00010002
[  848.461137] RAX: 0000000000000048 RBX: ffff8807fe86a630 RCX: ffffffff817d0be0
[  848.469520] RDX: 0000000000000000 RSI: ffffffff814af1cf RDI: 0000000000000002
[  848.477959] RBP: ffff8807f868dcb0 R08: 00000000ffffffff R09: 000000006b6b6b6b
[  848.486327] R10: 000000000003fb8c R11: ffffffff81a19448 R12: 6b6b6b6b6b6b6b6b
[  848.494699] R13: ffff8808027dc520 R14: 0000000000000000 R15: 000000000000001e
[  848.503067] FS:  0000000000000000(0000) GS:ffff88083fd00000(0000) knlGS:0000000000000000
[  848.512899] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[  848.519710] CR2: 00007ff77d001000 CR3: 00000007f7a5d000 CR4: 00000000000406e0
[  848.528072] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  848.536446] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[  848.544831] Process kworker/u:2 (pid: 5107, threadinfo ffff8807f868c000, task ffff8807ff348000)
[  848.555327] Stack:
[  848.557959]  ffff8807fe86a630 ffff8807fe86a630 ffff8807f868dcd0 ffffffff8126a6e0
[  848.567072]  ffffffff817c142f ffff8807fe86a630 ffff8807f868dcf0 ffffffff8126a703
[  848.576190]  ffff8808027dc520 0000000000000286 ffff8807f868dd10 ffffffff814af1bb
[  848.585281] Call Trace:
[  848.588409]  [<ffffffff8126a6e0>] spin_bug+0x26/0x28
[  848.594357]  [<ffffffff8126a703>] do_raw_spin_unlock+0x21/0x88
[  848.601283]  [<ffffffff814af1bb>] _raw_spin_unlock_irqrestore+0x2c/0x65
[  848.609089]  [<ffffffffa001c103>] ata_scsi_port_error_handler+0x548/0x557 [libata]
[  848.618331]  [<ffffffff81061813>] ? async_schedule+0x17/0x17
[  848.625060]  [<ffffffffa004f30f>] async_sas_ata_eh+0x45/0x69 [libsas]
[  848.632655]  [<ffffffff810618aa>] async_run_entry_fn+0x97/0x125
[  848.639670]  [<ffffffff81057439>] process_one_work+0x207/0x38d
[  848.646577]  [<ffffffff8105738c>] ? process_one_work+0x15a/0x38d
[  848.653681]  [<ffffffff810576f7>] worker_thread+0x138/0x21c
[  848.660305]  [<ffffffff810575bf>] ? process_one_work+0x38d/0x38d
[  848.667493]  [<ffffffff8105b098>] kthread+0x9d/0xa5
[  848.673382]  [<ffffffff8106e1bd>] ? trace_hardirqs_on_caller+0x12f/0x166
[  848.681304]  [<ffffffff814b7704>] kernel_thread_helper+0x4/0x10
[  848.688324]  [<ffffffff814af534>] ? retint_restore_args+0x13/0x13
[  848.695530]  [<ffffffff8105affb>] ? __init_kthread_worker+0x5b/0x5b
[  848.702929]  [<ffffffff814b7700>] ? gs_change+0x13/0x13
[  848.709155] Code: 00 00 48 8d 88 38 04 00 00 44 8b 80 84 02 00 00 31 c0 e8 cf 1b 24 00 41 83 c8 ff 44 8b 4b 08 48 c7 c1 e0 0b 7d 81 4d 85 e4 74 10 <45> 8b 84 24 84 02 00 00 49 8d 8c 24 38 04 00 00 8b 53 04 48 89
[  848.732467] RIP  [<ffffffff8126a68c>] spin_dump+0x5e/0x8c
[  848.738905]  RSP <ffff8807f868dca0>
[  848.743743] ---[ end trace 143161646eee8caa ]---

...so arrange for the ata_port to have the same end of life as the domain
device.

Reported-by: Marcin Tomczak <marcin.tomczak@intel.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/scsi/libsas/sas_ata.c       |    5 +++++
 drivers/scsi/libsas/sas_discover.c  |    5 +++++
 drivers/scsi/libsas/sas_scsi_host.c |    3 ---
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 37a9e73..26a943e 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -661,8 +661,13 @@ static void async_sas_ata_eh(void *data, async_cookie_t cookie)
 	struct ata_port *ap = dev->sata_dev.ap;
 	struct sas_ha_struct *ha = dev->port->ha;
 
+	/* hold a reference over eh since we may be racing with final
+	 * remove once all commands are completed
+	 */
+	kref_get(&dev->kref);
 	ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata port error handler");
 	ata_scsi_port_error_handler(ha->core.shost, ap);
+	sas_put_device(dev);
 }
 
 void sas_ata_strategy_handler(struct Scsi_Host *shost)
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 3ef7741..9367101 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -242,6 +242,11 @@ void sas_free_device(struct kref *kref)
 	if (dev->dev_type == EDGE_DEV || dev->dev_type == FANOUT_DEV)
 		kfree(dev->ex_dev.ex_phy);
 
+	if (dev_is_sata(dev) && dev->sata_dev.ap) {
+		ata_sas_port_destroy(dev->sata_dev.ap);
+		dev->sata_dev.ap = NULL;
+	}
+
 	kfree(dev);
 }
 
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 731c892..b563ff2 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -1028,9 +1028,6 @@ void sas_target_destroy(struct scsi_target *starget)
 	if (!found_dev)
 		return;
 
-	if (dev_is_sata(found_dev))
-		ata_sas_port_destroy(found_dev->sata_dev.ap);
-
 	starget->hostdata = NULL;
 	sas_put_device(found_dev);
 }

[PATCH v9 2/3] libsas: improve debug statements

[Dan Williams]

It's difficult to determine which domain_device is triggering error recovery,
so convert messages like:

  sas: ex 5001b4da000e703f phy08:T attached: 5001b4da000e7028
  sas: ex 5001b4da000e703f phy09:T attached: 5001b4da000e7029
  ...
  ata7: sas eh calling libata port error handler
  ata8: sas eh calling libata port error handler

...into:

  sas: ex 5001517e85cfefff phy05:T:9 attached: 5001517e85cfefe5 (stp)
  sas: ex 5001517e3b0af0bf phy11:T:8 attached: 5001517e3b0af0ab (stp)
  ...
  sas: ata7: end_device-21:1: dev error handler
  sas: ata8: end_device-20:0:5: dev error handler

which shows attached link rate, device type, and associates a
domain_device with its ata_port id to correlate messages emitted from
libata-eh.

As Doug notes, we can also take the opportunity to clarify expander phy
routing capabilities.

Cc: Douglas Gilbert <dgilbert@interlog.com>
[dgilbert@interlog.com: clarify table2table with 'U']
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/scsi/libsas/sas_ata.c      |   43 ++++++++++++++++-----
 drivers/scsi/libsas/sas_expander.c |   74 +++++++++++++++++++++++++-----------
 2 files changed, 85 insertions(+), 32 deletions(-)

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 40edf52..ba1ebfe 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -317,6 +317,28 @@ static int local_ata_check_ready(struct ata_link *link)
 	}
 }
 
+static int sas_ata_printk(const char *level, const struct domain_device *ddev,
+			  const char *fmt, ...)
+{
+	struct ata_port *ap = ddev->sata_dev.ap;
+	struct device *dev = &ddev->rphy->dev;
+	struct va_format vaf;
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	r = printk("%ssas: ata%u: %s: %pV",
+		   level, ap->print_id, dev_name(dev), &vaf);
+
+	va_end(args);
+
+	return r;
+}
+
 static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
 			      unsigned long deadline)
 {
@@ -333,7 +355,7 @@ static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
 	res = i->dft->lldd_I_T_nexus_reset(dev);
 
 	if (res != TMF_RESP_FUNC_COMPLETE)
-		SAS_DPRINTK("%s: Unable to reset ata device?\n", __func__);
+		sas_ata_printk(KERN_DEBUG, dev, "Unable to reset ata device?\n");
 
 	phy = sas_get_local_phy(dev);
 	if (scsi_is_sas_phy_local(phy))
@@ -344,7 +366,7 @@ static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
 
 	ret = ata_wait_after_reset(link, deadline, check_ready);
 	if (ret && ret != -EAGAIN)
-		ata_link_err(link, "COMRESET failed (errno=%d)\n", ret);
+		sas_ata_printk(KERN_ERR, dev, "reset failed (errno=%d)\n", ret);
 
 	/* XXX: if the class changes during the reset the upper layer
 	 * should be informed, if the device has gone away we assume
@@ -665,7 +687,7 @@ static void async_sas_ata_eh(void *data, async_cookie_t cookie)
 	 * remove once all commands are completed
 	 */
 	kref_get(&dev->kref);
-	ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata port error handler");
+	sas_ata_printk(KERN_DEBUG, dev, "dev error handler\n");
 	ata_scsi_port_error_handler(ha->core.shost, ap);
 	sas_put_device(dev);
 }
@@ -703,26 +725,27 @@ void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
 		struct list_head *done_q)
 {
 	struct scsi_cmnd *cmd, *n;
-	struct ata_port *ap;
+	struct domain_device *eh_dev;
 
 	do {
 		LIST_HEAD(sata_q);
-
-		ap = NULL;
+		eh_dev = NULL;
 
 		list_for_each_entry_safe(cmd, n, work_q, eh_entry) {
 			struct domain_device *ddev = cmd_to_domain_dev(cmd);
 
 			if (!dev_is_sata(ddev) || TO_SAS_TASK(cmd))
 				continue;
-			if (ap && ap != ddev->sata_dev.ap)
+			if (eh_dev && eh_dev != ddev)
 				continue;
-			ap = ddev->sata_dev.ap;
+			eh_dev = ddev;
 			list_move(&cmd->eh_entry, &sata_q);
 		}
 
 		if (!list_empty(&sata_q)) {
-			ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata cmd error handler\n");
+			struct ata_port *ap = eh_dev->sata_dev.ap;
+
+			sas_ata_printk(KERN_DEBUG, eh_dev, "cmd error handler\n");
 			ata_scsi_cmd_error_handler(shost, ap, &sata_q);
 			/*
 			 * ata's error handler may leave the cmd on the list
@@ -738,7 +761,7 @@ void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
 			while (!list_empty(&sata_q))
 				list_del_init(sata_q.next);
 		}
-	} while (ap);
+	} while (eh_dev);
 }
 
 void sas_ata_schedule_reset(struct domain_device *dev)
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 68a80a0..4b2ecd3 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -166,7 +166,22 @@ static inline void *alloc_smp_resp(int size)
 	return kzalloc(size, GFP_KERNEL);
 }
 
-/* ---------- Expander configuration ---------- */
+static char sas_route_char(struct domain_device *dev, struct ex_phy *phy)
+{
+	switch (phy->routing_attr) {
+	case TABLE_ROUTING:
+		if (dev->ex_dev.t2t_supp)
+			return 'U';
+		else
+			return 'T';
+	case DIRECT_ROUTING:
+		return 'D';
+	case SUBTRACTIVE_ROUTING:
+		return 'S';
+	default:
+		return '?';
+	}
+}
 
 static void sas_set_ex_phy(struct domain_device *dev, int phy_id,
 			   void *disc_resp)
@@ -176,9 +191,10 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id,
 	struct smp_resp *resp = disc_resp;
 	struct discover_resp *dr = &resp->disc;
 	struct sas_rphy *rphy = dev->rphy;
-	int rediscover = (phy->phy != NULL);
+	bool new_phy = !phy->phy;
+	char *type;
 
-	if (!rediscover) {
+	if (new_phy) {
 		phy->phy = sas_phy_alloc(&rphy->dev, phy_id);
 
 		/* FIXME: error_handling */
@@ -223,20 +239,41 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id,
 	phy->phy->maximum_linkrate = dr->pmax_linkrate;
 	phy->phy->negotiated_linkrate = phy->linkrate;
 
-	if (!rediscover)
+	if (new_phy)
 		if (sas_phy_add(phy->phy)) {
 			sas_phy_free(phy->phy);
 			return;
 		}
 
-	SAS_DPRINTK("ex %016llx phy%02d:%c attached: %016llx\n",
-		    SAS_ADDR(dev->sas_addr), phy->phy_id,
-		    phy->routing_attr == TABLE_ROUTING ? 'T' :
-		    phy->routing_attr == DIRECT_ROUTING ? 'D' :
-		    phy->routing_attr == SUBTRACTIVE_ROUTING ? 'S' : '?',
-		    SAS_ADDR(phy->attached_sas_addr));
+	switch (phy->attached_dev_type) {
+	case NO_DEVICE:
+		type = "no device";
+		break;
+	case SAS_END_DEV:
+		if (phy->attached_iproto) {
+			if (phy->attached_tproto)
+				type = "host+target";
+			else
+				type = "host";
+		} else {
+			if (dr->attached_sata_dev)
+				type = "stp";
+			else
+				type = "ssp";
+		}
+		break;
+	case EDGE_DEV:
+	case FANOUT_DEV:
+		type = "smp";
+		break;
+	default:
+		type = "unknown";
+	}
 
-	return;
+	SAS_DPRINTK("ex %016llx phy%02d:%c:%X attached: %016llx (%s)\n",
+		    SAS_ADDR(dev->sas_addr), phy->phy_id,
+		    sas_route_char(dev, phy), phy->linkrate,
+		    SAS_ADDR(phy->attached_sas_addr), type);
 }
 
 /* check if we have an existing attached ata device on this expander phy */
@@ -1176,32 +1213,25 @@ static void sas_print_parent_topology_bug(struct domain_device *child,
 						 struct ex_phy *parent_phy,
 						 struct ex_phy *child_phy)
 {
-	static const char ra_char[] = {
-		[DIRECT_ROUTING] = 'D',
-		[SUBTRACTIVE_ROUTING] = 'S',
-		[TABLE_ROUTING] = 'T',
-	};
 	static const char *ex_type[] = {
 		[EDGE_DEV] = "edge",
 		[FANOUT_DEV] = "fanout",
 	};
 	struct domain_device *parent = child->parent;
 
-	sas_printk("%s ex %016llx (T2T supp:%d) phy 0x%x <--> %s ex %016llx "
-		   "(T2T supp:%d) phy 0x%x has %c:%c routing link!\n",
+	sas_printk("%s ex %016llx phy 0x%x <--> %s ex %016llx "
+		   "phy 0x%x has %c:%c routing link!\n",
 
 		   ex_type[parent->dev_type],
 		   SAS_ADDR(parent->sas_addr),
-		   parent->ex_dev.t2t_supp,
 		   parent_phy->phy_id,
 
 		   ex_type[child->dev_type],
 		   SAS_ADDR(child->sas_addr),
-		   child->ex_dev.t2t_supp,
 		   child_phy->phy_id,
 
-		   ra_char[parent_phy->routing_attr],
-		   ra_char[child_phy->routing_attr]);
+		   sas_route_char(parent, parent_phy),
+		   sas_route_char(child, child_phy));
 }
 
 static int sas_check_eeds(struct domain_device *child,

[PATCH v9 3/3] libsas: async ata scanning

[Dan Williams]

libsas ata error handling is already async but this does not help the
scan case.  Move initial link recovery out from under host->scan_mutex,
and delay synchronization with eh until after all port probe/recovery
work has been queued.

Device ordering is maintained with scan order by still calling
sas_rphy_add() in order of domain discovery.

Since we now scan the domain list when invoking libata-eh we need to be
careful to check for fully initialized ata ports.

Cc: Xiangliang Yu <yuxiangl@marvell.com>
Cc: Luben Tuikov <ltuikov@yahoo.com>
Acked-by: Jack Wang <jack_wang@usish.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/ata/libata-core.c           |   34 +++++++++-------
 drivers/ata/libata-scsi.c           |   13 ++++++
 drivers/ata/libata.h                |    1 
 drivers/scsi/aic94xx/aic94xx_init.c |    1 
 drivers/scsi/isci/init.c            |    1 
 drivers/scsi/libsas/sas_ata.c       |   74 ++++++++++++++++++++++++++++++-----
 drivers/scsi/libsas/sas_discover.c  |   22 +++++-----
 drivers/scsi/libsas/sas_internal.h  |    9 ++++
 drivers/scsi/libsas/sas_scsi_host.c |   18 ---------
 drivers/scsi/mvsas/mv_init.c        |    1 
 drivers/scsi/pm8001/pm8001_init.c   |    1 
 include/linux/libata.h              |    1 
 include/scsi/libsas.h               |    1 
 include/scsi/sas_ata.h              |   12 +++---
 14 files changed, 123 insertions(+), 66 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c04ad68..1654c94 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5874,29 +5874,31 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 	host->ops = ops;
 }
 
-int ata_port_probe(struct ata_port *ap)
+void __ata_port_probe(struct ata_port *ap)
 {
-	int rc = 0;
+	struct ata_eh_info *ehi = &ap->link.eh_info;
+	unsigned long flags;
 
-	/* probe */
-	if (ap->ops->error_handler) {
-		struct ata_eh_info *ehi = &ap->link.eh_info;
-		unsigned long flags;
+	/* kick EH for boot probing */
+	spin_lock_irqsave(ap->lock, flags);
 
-		/* kick EH for boot probing */
-		spin_lock_irqsave(ap->lock, flags);
+	ehi->probe_mask |= ATA_ALL_DEVICES;
+	ehi->action |= ATA_EH_RESET;
+	ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET;
 
-		ehi->probe_mask |= ATA_ALL_DEVICES;
-		ehi->action |= ATA_EH_RESET;
-		ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET;
+	ap->pflags &= ~ATA_PFLAG_INITIALIZING;
+	ap->pflags |= ATA_PFLAG_LOADING;
+	ata_port_schedule_eh(ap);
 
-		ap->pflags &= ~ATA_PFLAG_INITIALIZING;
-		ap->pflags |= ATA_PFLAG_LOADING;
-		ata_port_schedule_eh(ap);
+	spin_unlock_irqrestore(ap->lock, flags);
+}
 
-		spin_unlock_irqrestore(ap->lock, flags);
+int ata_port_probe(struct ata_port *ap)
+{
+	int rc = 0;
 
-		/* wait for EH to finish */
+	if (ap->ops->error_handler) {
+		__ata_port_probe(ap);
 		ata_port_wait_eh(ap);
 	} else {
 		DPRINTK("ata%u: bus probe begin\n", ap->print_id);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2a5412e..faf8730 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3837,6 +3837,19 @@ void ata_sas_port_stop(struct ata_port *ap)
 }
 EXPORT_SYMBOL_GPL(ata_sas_port_stop);
 
+int ata_sas_async_port_init(struct ata_port *ap)
+{
+	int rc = ap->ops->port_start(ap);
+
+	if (!rc) {
+		ap->print_id = ata_print_id++;
+		__ata_port_probe(ap);
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ata_sas_async_port_init);
+
 /**
  *	ata_sas_port_init - Initialize a SATA device
  *	@ap: SATA port to initialize
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 78c356d..2a2aa51 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -104,6 +104,7 @@ extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern struct ata_port *ata_port_alloc(struct ata_host *host);
 extern const char *sata_spd_string(unsigned int spd);
 extern int ata_port_probe(struct ata_port *ap);
+extern void __ata_port_probe(struct ata_port *ap);
 
 /* libata-acpi.c */
 #ifdef CONFIG_ATA_ACPI
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index eea988a..ff80552 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -81,7 +81,6 @@ static struct scsi_host_template aic94xx_sht = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.eh_device_reset_handler	= sas_eh_device_reset_handler,
 	.eh_bus_reset_handler	= sas_eh_bus_reset_handler,
-	.slave_alloc		= sas_slave_alloc,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 };
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 437f76b..9a28270 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -157,7 +157,6 @@ static struct scsi_host_template isci_sht = {
 	.sg_tablesize			= SG_ALL,
 	.max_sectors			= SCSI_DEFAULT_MAX_SECTORS,
 	.use_clustering			= ENABLE_CLUSTERING,
-	.slave_alloc			= sas_slave_alloc,
 	.target_destroy			= sas_target_destroy,
 	.ioctl				= sas_ioctl,
 	.shost_attrs			= isci_host_attrs,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index a9ec164..eb8b77c 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -585,11 +585,10 @@ static struct ata_port_info sata_port_info = {
 	.port_ops = &sas_sata_ops
 };
 
-int sas_ata_init_host_and_port(struct domain_device *found_dev,
-			       struct scsi_target *starget)
+int sas_ata_init_host_and_port(struct domain_device *found_dev)
 {
-	struct Scsi_Host *shost = dev_to_shost(&starget->dev);
-	struct sas_ha_struct *ha = SHOST_TO_SAS_HA(shost);
+	struct sas_ha_struct *ha = found_dev->port->ha;
+	struct Scsi_Host *shost = ha->core.shost;
 	struct ata_port *ap;
 
 	ata_host_init(&found_dev->sata_dev.ata_host,
@@ -607,6 +606,8 @@ int sas_ata_init_host_and_port(struct domain_device *found_dev,
 	ap->private_data = found_dev;
 	ap->cbl = ATA_CBL_SATA;
 	ap->scsi_host = shost;
+	/* publish initialized ata port */
+	smp_wmb();
 	found_dev->sata_dev.ap = ap;
 
 	return 0;
@@ -683,6 +684,38 @@ static void sas_get_ata_command_set(struct domain_device *dev)
 		dev->sata_dev.command_set = ATAPI_COMMAND_SET;
 }
 
+void sas_probe_sata(struct asd_sas_port *port)
+{
+	struct domain_device *dev, *n;
+	int err;
+
+	mutex_lock(&port->ha->disco_mutex);
+	list_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) {
+		if (!dev_is_sata(dev))
+			continue;
+
+		err = sas_ata_init_host_and_port(dev);
+		if (err)
+			sas_fail_probe(dev, __func__, err);
+		else
+			ata_sas_async_port_init(dev->sata_dev.ap);
+	}
+	mutex_unlock(&port->ha->disco_mutex);
+
+	list_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) {
+		if (!dev_is_sata(dev))
+			continue;
+
+		sas_ata_wait_eh(dev);
+
+		/* if libata could not bring the link up, don't surface
+		 * the device
+		 */
+		if (ata_dev_disabled(sas_to_ata_dev(dev)))
+			sas_fail_probe(dev, __func__, -ENODEV);
+	}
+}
+
 /**
  * sas_discover_sata -- discover an STP/SATA domain device
  * @dev: pointer to struct domain_device of interest
@@ -724,11 +757,23 @@ static void async_sas_ata_eh(void *data, async_cookie_t cookie)
 	sas_put_device(dev);
 }
 
+static bool sas_ata_dev_eh_valid(struct domain_device *dev)
+{
+	struct ata_port *ap;
+
+	if (!dev_is_sata(dev))
+		return false;
+	ap = dev->sata_dev.ap;
+	/* consume fully initialized ata ports */
+	smp_rmb();
+	return !!ap;
+}
+
 void sas_ata_strategy_handler(struct Scsi_Host *shost)
 {
-	struct scsi_device *sdev;
 	struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(shost);
 	LIST_HEAD(async);
+	int i;
 
 	/* it's ok to defer revalidation events during ata eh, these
 	 * disks are in one of three states:
@@ -740,14 +785,21 @@ void sas_ata_strategy_handler(struct Scsi_Host *shost)
 	 */
 	sas_disable_revalidation(sas_ha);
 
-	shost_for_each_device(sdev, shost) {
-		struct domain_device *ddev = sdev_to_domain_dev(sdev);
-
-		if (!dev_is_sata(ddev))
-			continue;
+	spin_lock_irq(&sas_ha->phy_port_lock);
+	for (i = 0; i < sas_ha->num_phys; i++) {
+		struct asd_sas_port *port = sas_ha->sas_port[i];
+		struct domain_device *dev;
 
-		async_schedule_domain(async_sas_ata_eh, ddev, &async);
+		spin_lock(&port->dev_list_lock);
+		list_for_each_entry(dev, &port->dev_list, dev_list_node) {
+			if (!sas_ata_dev_eh_valid(dev))
+				continue;
+			async_schedule_domain(async_sas_ata_eh, dev, &async);
+		}
+		spin_unlock(&port->dev_list_lock);
 	}
+	spin_unlock_irq(&sas_ha->phy_port_lock);
+
 	async_synchronize_full_domain(&async);
 
 	sas_enable_revalidation(sas_ha);
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index f60b602..ed3f8c0 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -207,22 +207,22 @@ static void sas_probe_devices(struct work_struct *work)
 
 	clear_bit(DISCE_PROBE, &port->disc.pending);
 
-	list_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) {
-		int err;
-
+	/* devices must be domain members before link recovery and probe */
+	list_for_each_entry(dev, &port->disco_list, disco_list_node) {
 		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);
+	sas_probe_sata(port);
 
-		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_for_each_entry_safe(dev, n, &port->disco_list, disco_list_node) {
+		int err;
+
+		err = sas_rphy_add(dev->rphy);
+		if (err)
+			sas_fail_probe(dev, __func__, err);
+		else
 			list_del_init(&dev->disco_list_node);
 	}
 }
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index e028d7a..d0d9bf1 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -113,6 +113,15 @@ static inline int sas_smp_host_handler(struct Scsi_Host *shost,
 }
 #endif
 
+static inline void sas_fail_probe(struct domain_device *dev, const char *func, int 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(dev->port, dev);
+}
+
 static inline void sas_fill_in_rphy(struct domain_device *dev,
 				    struct sas_rphy *rphy)
 {
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index e58ca50..3701ff7 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -762,17 +762,10 @@ int sas_target_alloc(struct scsi_target *starget)
 {
 	struct sas_rphy *rphy = dev_to_rphy(starget->dev.parent);
 	struct domain_device *found_dev = sas_find_dev_by_rphy(rphy);
-	int res;
 
 	if (!found_dev)
 		return -ENODEV;
 
-	if (dev_is_sata(found_dev)) {
-		res = sas_ata_init_host_and_port(found_dev, starget);
-		if (res)
-			return res;
-	}
-
 	kref_get(&found_dev->kref);
 	starget->hostdata = found_dev;
 	return 0;
@@ -1012,16 +1005,6 @@ void sas_task_abort(struct sas_task *task)
 	}
 }
 
-int sas_slave_alloc(struct scsi_device *scsi_dev)
-{
-	struct domain_device *dev = sdev_to_domain_dev(scsi_dev);
-
-	if (dev_is_sata(dev))
-		return ata_sas_port_init(dev->sata_dev.ap);
-
-	return 0;
-}
-
 void sas_target_destroy(struct scsi_target *starget)
 {
 	struct domain_device *found_dev = starget->hostdata;
@@ -1082,6 +1065,5 @@ EXPORT_SYMBOL_GPL(sas_task_abort);
 EXPORT_SYMBOL_GPL(sas_phy_reset);
 EXPORT_SYMBOL_GPL(sas_eh_device_reset_handler);
 EXPORT_SYMBOL_GPL(sas_eh_bus_reset_handler);
-EXPORT_SYMBOL_GPL(sas_slave_alloc);
 EXPORT_SYMBOL_GPL(sas_target_destroy);
 EXPORT_SYMBOL_GPL(sas_ioctl);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index d45878b..cc59dff 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -73,7 +73,6 @@ static struct scsi_host_template mvs_sht = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.eh_device_reset_handler = sas_eh_device_reset_handler,
 	.eh_bus_reset_handler	= sas_eh_bus_reset_handler,
-	.slave_alloc		= sas_slave_alloc,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= mvst_host_attrs,
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index bd165ea..36efaa7 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -75,7 +75,6 @@ static struct scsi_host_template pm8001_sht = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.eh_device_reset_handler = sas_eh_device_reset_handler,
 	.eh_bus_reset_handler	= sas_eh_bus_reset_handler,
-	.slave_alloc		= sas_slave_alloc,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= pm8001_host_attrs,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index aa42704..42378d6 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -996,6 +996,7 @@ extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
 extern void ata_sas_port_destroy(struct ata_port *);
 extern struct ata_port *ata_sas_port_alloc(struct ata_host *,
 					   struct ata_port_info *, struct Scsi_Host *);
+extern int ata_sas_async_port_init(struct ata_port *);
 extern int ata_sas_port_init(struct ata_port *);
 extern int ata_sas_port_start(struct ata_port *ap);
 extern void ata_sas_port_stop(struct ata_port *ap);
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 4a42be3..20153d5 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -646,7 +646,6 @@ int sas_phy_reset(struct sas_phy *phy, int hard_reset);
 int sas_queue_up(struct sas_task *task);
 extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
-extern int sas_slave_alloc(struct scsi_device *);
 extern int sas_slave_configure(struct scsi_device *);
 extern int sas_change_queue_depth(struct scsi_device *, int new_depth,
 				  int reason);
diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h
index 1556eff..cdccd2e 100644
--- a/include/scsi/sas_ata.h
+++ b/include/scsi/sas_ata.h
@@ -37,15 +37,14 @@ static inline int dev_is_sata(struct domain_device *dev)
 }
 
 int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy);
-int sas_ata_init_host_and_port(struct domain_device *found_dev,
-			       struct scsi_target *starget);
-
+int sas_ata_init_host_and_port(struct domain_device *found_dev);
 void sas_ata_task_abort(struct sas_task *task);
 void sas_ata_strategy_handler(struct Scsi_Host *shost);
 void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
 		struct list_head *done_q);
 void sas_ata_schedule_reset(struct domain_device *dev);
 void sas_ata_wait_eh(struct domain_device *dev);
+void sas_probe_sata(struct asd_sas_port *port);
 #else
 
 
@@ -53,8 +52,7 @@ static inline int dev_is_sata(struct domain_device *dev)
 {
 	return 0;
 }
-static inline int sas_ata_init_host_and_port(struct domain_device *found_dev,
-			       struct scsi_target *starget)
+static inline int sas_ata_init_host_and_port(struct domain_device *found_dev)
 {
 	return 0;
 }
@@ -79,6 +77,10 @@ static inline void sas_ata_wait_eh(struct domain_device *dev)
 {
 }
 
+static inline void sas_probe_sata(struct asd_sas_port *port)
+{
+}
+
 static inline int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy)
 {
 	return 0;