Merge tag 'ata-7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/libata/linux

Pull ata fixes from Damien Le Moal:

 - Fix PCI resource initialization in the sata_mv driver to keep legacy
   Marvell boards functional (Rosen)

 - Fix ahci_ceva driver initialization error path (Radhey)

 - Fix libata header file to remove a kernel doc compilation warning
   (Randy)

 - Increase the timeout for the STANDBY IMMEDIATE command to avoid
   suspend failures with drives that are slow to respond to this command
   (Matt)

 - Fixes for the handling of timed out commands in the presence of
   deferred non-NCQ commands, to avoid excessive delays in executing the
   error handler (me)

 - Disable link power management for a couple of WD drives that have
   been identified as not functioning properly when power management is
   used (Niklas)

 - Fix the device iteration loop when checking for link power management
   support to correctly handle port multiplier setups (Niklas)

* tag 'ata-7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/libata/linux:
  ata: libata-sata: fix ata_scsi_lpm_supported() iteration
  ata: libata-core: Disable LPM on WD Green 2.5 480GB
  ata: libata-core: Disable LPM on some WD drives
  scsi: libsas: terminate deferred commands on time out
  ata: libata-scsi: schedule deferred atapi command
  ata: libata-scsi: terminate deferred commands on time out
  ata: libata-eh: Increase STANDBY IMMEDIATE timeout
  ata: libata: avoid kernel-doc warnings
  ata: ahci_ceva: fix error paths in ceva_ahci_platform_enable_resources()
  ata: sata_mv: accept 1 or 2 resources in platform probe

11 files changed, 173 insertions, 46 deletions

diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index 2d6a08c23d6a..2961e53288f4 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -211,7 +211,7 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 
 		rc = phy_init(hpriv->phys[i]);
 		if (rc)
-			goto disable_rsts;
+			goto exit_phys;
 	}
 
 	/* De-assert the controller reset */
@@ -230,14 +230,24 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 
 	return 0;
 
-disable_rsts:
-	ahci_platform_deassert_rsts(hpriv);
-
 disable_phys:
 	while (--i >= 0) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		phy_power_off(hpriv->phys[i]);
 		phy_exit(hpriv->phys[i]);
 	}
+	ahci_platform_assert_rsts(hpriv);
+	goto disable_clks;
+
+exit_phys:
+	while (--i >= 0) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
+		phy_exit(hpriv->phys[i]);
+	}
 
 disable_clks:
 	ahci_platform_disable_clks(hpriv);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c43bd28b20b1..961d03fbc4d9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4414,6 +4414,15 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	{ "WDC WD3200JD-*",		NULL,	ATA_QUIRK_WD_BROKEN_LPM },
 
 	/*
+	 * WD drives with LPM issues (irrespective of supported SATA speeds).
+	 * (Unlike ATA_QUIRK_WD_BROKEN_LPM, which is only applied if the drive
+	 * exposes SATA Gen1 speed support, and SATA Gen1 speed support only.)
+	 */
+	{ "WDC WD100EFGX-68CPLN0",	NULL,	ATA_QUIRK_NOLPM },
+	{ "WDC WD102KFBX-68M95N0",	NULL,	ATA_QUIRK_NOLPM },
+	{ "WD Green 2.5 480GB",		NULL,	ATA_QUIRK_NOLPM },
+
+	/*
 	 * This sata dom device goes on a walkabout when the ATA_LOG_DIRECTORY
 	 * log page is accessed. Ensure we never ask for this log page with
 	 * these devices.
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 05df7ea6954a..c154103d892c 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -106,6 +106,12 @@ static const unsigned int ata_eh_flush_timeouts[] = {
 	UINT_MAX,
 };
 
+static const unsigned int ata_eh_standby_timeouts[] = {
+	15000,	/* Some drives may be slow to standby */
+	/* but don't hold up a suspend too long waiting for them */
+	UINT_MAX,
+};
+
 static const unsigned int ata_eh_other_timeouts[] = {
 	 5000,	/* same rationale as identify timeout */
 	10000,	/* ditto */
@@ -147,6 +153,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = {
 	  .timeouts = ata_eh_other_timeouts, },
 	{ .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT),
 	  .timeouts = ata_eh_flush_timeouts },
+	{ .commands = CMDS(ATA_CMD_STANDBYNOW1),
+	  .timeouts = ata_eh_standby_timeouts },
 	{ .commands = CMDS(ATA_CMD_VERIFY),
 	  .timeouts = ata_eh_reset_timeouts },
 };
@@ -650,29 +658,12 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		set_host_byte(scmd, DID_OK);
 
 		ata_qc_for_each_raw(ap, qc, i) {
-			if (qc->scsicmd != scmd)
-				continue;
-			if ((qc->flags & ATA_QCFLAG_ACTIVE) ||
-			    qc == qc->dev->link->deferred_qc)
+			if (qc->scsicmd == scmd &&
+			    qc->flags & ATA_QCFLAG_ACTIVE)
 				break;
 		}
 
-		if (i < ATA_MAX_QUEUE && qc == qc->dev->link->deferred_qc) {
-			/*
-			 * This is a deferred command that timed out while
-			 * waiting for the command queue to drain. Since the qc
-			 * is not active yet (deferred_qc is still set, so the
-			 * deferred qc work has not issued the command yet),
-			 * simply signal the timeout by finishing the SCSI
-			 * command and clear the deferred qc to prevent the
-			 * deferred qc work from issuing this qc.
-			 */
-			WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE);
-			qc->dev->link->deferred_qc = NULL;
-			cancel_work(&qc->dev->link->deferred_qc_work);
-			set_host_byte(scmd, DID_TIME_OUT);
-			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
-		} else if (i < ATA_MAX_QUEUE) {
+		if (i < ATA_MAX_QUEUE) {
 			/* the scmd has an associated qc */
 			if (!(qc->flags & ATA_QCFLAG_EH)) {
 				/* which hasn't failed yet, timeout */
@@ -948,10 +939,10 @@ static void ata_eh_set_pending(struct ata_port *ap, bool fastdrain)
 	ap->pflags |= ATA_PFLAG_EH_PENDING;
 
 	/*
-	 * If we have a deferred qc, requeue it so that it is retried once EH
-	 * completes.
+	 * If we have deferred QCs, requeue them so that the SCSI EH task can
+	 * run.
 	 */
-	ata_scsi_requeue_deferred_qc(ap);
+	ata_scsi_requeue_deferred_qc(ap, NULL);
 
 	if (!fastdrain)
 		return;
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index b0706c30da05..ad40f516c6d4 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -913,7 +913,7 @@ static bool ata_scsi_lpm_supported(struct ata_port *ap)
 		return false;
 
 	ata_for_each_link(link, ap, EDGE) {
-		ata_for_each_dev(dev, &ap->link, ENABLED) {
+		ata_for_each_dev(dev, link, ENABLED) {
 			if (dev->quirks & ATA_QUIRK_NOLPM)
 				return false;
 		}
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 5868526301a2..d2160ee7ca7d 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1685,26 +1685,80 @@ void ata_scsi_deferred_qc_work(struct work_struct *work)
 	spin_unlock_irqrestore(ap->lock, flags);
 }
 
-void ata_scsi_requeue_deferred_qc(struct ata_port *ap)
+enum scsi_timeout_action ata_scsi_requeue_deferred_qc(struct ata_port *ap,
+					struct scsi_cmnd *timedout_scmd)
 {
+	enum scsi_timeout_action action = SCSI_EH_NOT_HANDLED;
+	struct ata_queued_cmd *qc;
 	struct ata_link *link;
+	u32 host_byte;
 
 	lockdep_assert_held(ap->lock);
 
 	/*
-	 * If we have a deferred qc when a reset occurs or NCQ commands fail,
-	 * do not try to be smart about what to do with this deferred command
-	 * and simply requeue it by completing it with DID_REQUEUE.
+	 * If we have deferred QCs when a reset, a timeout or an NCQ command
+	 * fails, do not try to be smart about what to do with the deferred
+	 * commands and simply terminate them and let the SCSI layer decide
+	 * what to do.
 	 */
 	ata_for_each_link(link, ap, PMP_FIRST) {
-		struct ata_queued_cmd *qc = link->deferred_qc;
+		qc = link->deferred_qc;
+		if (!qc)
+			continue;
 
-		if (qc) {
-			link->deferred_qc = NULL;
-			cancel_work(&link->deferred_qc_work);
-			ata_scsi_qc_done(qc, true, DID_REQUEUE << 16);
+		/*
+		 * Clear the deferred QC so that the deferred work does not try
+		 * to issue it.
+		 */
+		link->deferred_qc = NULL;
+		cancel_work(&link->deferred_qc_work);
+
+		/*
+		 * We are going to complete some scsi command, either with
+		 * DID_TIME_OUT if the command timed out while waiting for being
+		 * issued, or with DID_REQUEUE if another command timed out or
+		 * we had a failed command. However, the block layer may re-issue
+		 * these commands immediately, keeping the scsi host busy and
+		 * thus preventing the SCSI EH task from running.
+		 * So schedule EH on the port to prevent accepting new commands
+		 * until everything is sorted out with the error or timeout that
+		 * got us here in the first place. Note that we set EH pending
+		 * on the port before calling ata_port_schedule_eh() so that we
+		 * do not reenter this function from ata_eh_set_pending() with
+		 * timedout_scmd being NULL and erroneously retry deferred QCs
+		 * that have timed out on other links.
+		 */
+		if (!ata_port_eh_scheduled(ap)) {
+			ap->pflags |= ATA_PFLAG_EH_PENDING;
+			ata_port_schedule_eh(ap);
 		}
+
+		/*
+		 * If we are being called from scsi_timeout(), then we have a
+		 * non-NULL timedout_scmd. If the timed out command is for a
+		 * deferred QC, terminate that deferred QC with DID_TIME_OUT and
+		 * requeue all other deferred QCs. In this case we need to
+		 * return SCSI_EH_DONE, because the timed out command was
+		 * handled.
+		 * If the timed out command is not for a deferred QC, we need to
+		 * requeue all deferred QCs, and return SCSI_EH_NOT_HANDLED so
+		 * that the timed out command gets added to the EH work queue
+		 * with scsi_eh_scmd_add(), for later handling with libata EH
+		 * ata_scsi_cmd_error_handler().
+		 * If timedout_scmd is NULL, we simply need to requeue all
+		 * deferred QCs and the return value does not matter as we were
+		 * not called from scsi_timeout().
+		 */
+		if (timedout_scmd && qc->scsicmd == timedout_scmd) {
+			host_byte = DID_TIME_OUT;
+			action = SCSI_EH_DONE;
+		} else {
+			host_byte = DID_REQUEUE;
+		}
+		ata_scsi_qc_done(qc, true, host_byte << 16);
 	}
+
+	return action;
 }
 
 static void ata_scsi_schedule_deferred_qc(struct ata_link *link)
@@ -1723,13 +1777,42 @@ static void ata_scsi_schedule_deferred_qc(struct ata_link *link)
 		return;
 
 	if (ata_port_eh_scheduled(ap)) {
-		ata_scsi_requeue_deferred_qc(ap);
+		ata_scsi_requeue_deferred_qc(ap, NULL);
 		return;
 	}
 	if (!ap->ops->qc_defer(qc))
 		queue_work(system_highpri_wq, &link->deferred_qc_work);
 }
 
+enum scsi_timeout_action ata_scsi_retry_deferred_qc(struct ata_port *ap,
+						    struct scsi_cmnd *scmd)
+{
+	enum scsi_timeout_action action;
+	unsigned long flags;
+
+	spin_lock_irqsave(ap->lock, flags);
+	action = ata_scsi_requeue_deferred_qc(ap, scmd);
+	spin_unlock_irqrestore(ap->lock, flags);
+
+	return action;
+}
+EXPORT_SYMBOL_GPL(ata_scsi_retry_deferred_qc);
+
+enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *scmd)
+{
+	struct ata_port *ap = ata_shost_to_port(scmd->device->host);
+
+	/*
+	 * ata_scsi_cmd_error_handler() takes care of commands that timed out
+	 * while executing. However, if we have deferred QCs while a timeout
+	 * triggers, we must requeue these commands for retry so that we do not
+	 * unnecessarily delay starting the SCSI EH task until these deferred
+	 * commands also time out.
+	 */
+	return ata_scsi_retry_deferred_qc(ap, scmd);
+}
+EXPORT_SYMBOL_GPL(ata_scsi_eh_timed_out);
+
 static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
 {
 	struct ata_link *link = qc->dev->link;
@@ -2911,6 +2994,7 @@ static void atapi_fixup_inquiry(struct scsi_cmnd *cmd)
 
 static void atapi_qc_complete(struct ata_queued_cmd *qc)
 {
+	struct ata_link *link = qc->dev->link;
 	struct scsi_cmnd *cmd = qc->scsicmd;
 	unsigned int err_mask = qc->err_mask;
 
@@ -2936,8 +3020,16 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
 		if (qc->cdb[0] == ALLOW_MEDIUM_REMOVAL && qc->dev->sdev)
 			qc->dev->sdev->locked = 0;
 
-		ata_scsi_qc_done(qc, true, SAM_STAT_CHECK_CONDITION);
-		return;
+		if (cmd->result)
+			ata_scsi_qc_done(qc, false, 0);
+		else
+			ata_scsi_qc_done(qc, true, SAM_STAT_CHECK_CONDITION);
+		goto schedule_deferred;
+	}
+
+	if (cmd->result) {
+		ata_scsi_qc_done(qc, false, 0);
+		goto schedule_deferred;
 	}
 
 	/* successful completion path */
@@ -2945,6 +3037,9 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
 		atapi_fixup_inquiry(cmd);
 
 	ata_scsi_qc_done(qc, true, SAM_STAT_GOOD);
+
+schedule_deferred:
+	ata_scsi_schedule_deferred_qc(link);
 }
 /**
  *	atapi_xlat - Initialize PACKET taskfile
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 700627596ce1..8dacc1daabf0 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -180,7 +180,8 @@ enum scsi_qc_status __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
 					struct ata_port *ap)
 	__must_hold(ap->lock);
 void ata_scsi_deferred_qc_work(struct work_struct *work);
-void ata_scsi_requeue_deferred_qc(struct ata_port *ap);
+enum scsi_timeout_action ata_scsi_requeue_deferred_qc(struct ata_port *ap,
+						      struct scsi_cmnd *scmd);
 
 /* libata-eh.c */
 extern unsigned int ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 41647a56a9f4..365454390d7e 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4027,7 +4027,7 @@ static int mv_platform_probe(struct platform_device *pdev)
 	/*
 	 * Simple resource validation ..
 	 */
-	if (unlikely(pdev->num_resources != 1)) {
+	if (unlikely(pdev->num_resources != 1 && pdev->num_resources != 2)) {
 		dev_err(&pdev->dev, "invalid number of resources\n");
 		return -EINVAL;
 	}
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index c83282733ec4..97ac3db5dccb 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -502,6 +502,21 @@ int sas_eh_target_reset_handler(struct scsi_cmnd *cmd)
 }
 EXPORT_SYMBOL_GPL(sas_eh_target_reset_handler);
 
+/*
+ * Handle deferred QCs in case of a command timeout.
+ * See ata_scsi_eh_timed_out() for details.
+ */
+enum scsi_timeout_action sas_eh_timed_out(struct scsi_cmnd *cmd)
+{
+	struct domain_device *dev = cmd_to_domain_dev(cmd);
+
+	if (dev_is_sata(dev))
+		return ata_scsi_retry_deferred_qc(dev->sata_dev.ap, cmd);
+
+	return SCSI_EH_NOT_HANDLED;
+}
+EXPORT_SYMBOL_GPL(sas_eh_timed_out);
+
 /* Try to reset a device */
 static int try_to_reset_cmd_device(struct scsi_cmnd *cmd)
 {
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 8fd48bcb2a46..7daad4cad985 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -762,8 +762,7 @@ static inline bool ata_id_sense_reporting_enabled(const u16 *id)
 	return id[ATA_ID_COMMAND_SET_4] & BIT(6);
 }
 
-/**
- *
+/*
  * Word: 206 - SCT Command Transport
  *    15:12 - Vendor Specific
  *     11:6 - Reserved
@@ -810,8 +809,9 @@ static inline bool ata_id_sct_supported(const u16 *id)
  *
  *	The practical impact of this is that ata_id_major_version cannot
  *	reliably report on drives below ATA3.
+ *
+ *	Returns: major version of ATA drive level or %0 if unknown
  */
-
 static inline unsigned int ata_id_major_version(const u16 *id)
 {
 	unsigned int mver;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 96e626d6a7ca..1827502b9cf2 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -425,7 +425,7 @@ enum {
 	/* This should match the actual table size of
 	 * ata_eh_cmd_timeout_table in libata-eh.c.
 	 */
-	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8,
+	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 9,
 
 	/* User visible DMA mask for DMA control. DO NOT renumber. */
 	ATA_DMA_MASK_ATA	= (1 << 0),	/* DMA on ATA Disk */
@@ -1153,6 +1153,9 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 #endif
 extern enum scsi_qc_status ata_scsi_queuecmd(struct Scsi_Host *h,
 					     struct scsi_cmnd *cmd);
+enum scsi_timeout_action ata_scsi_retry_deferred_qc(struct ata_port *ap,
+						    struct scsi_cmnd *scmd);
+enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *cmd);
 #if IS_REACHABLE(CONFIG_ATA)
 bool ata_scsi_dma_need_drain(struct request *rq);
 #else
@@ -1464,6 +1467,7 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	.ioctl			= ata_scsi_ioctl,		\
 	ATA_SCSI_COMPAT_IOCTL					\
 	.queuecommand		= ata_scsi_queuecmd,		\
+	.eh_timed_out		= ata_scsi_eh_timed_out,	\
 	.dma_need_drain		= ata_scsi_dma_need_drain,	\
 	.this_id		= ATA_SHT_THIS_ID,		\
 	.emulated		= ATA_SHT_EMULATED,		\
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 163f23c92b41..c7017ae76c61 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -705,6 +705,7 @@ void sas_task_abort(struct sas_task *);
 int sas_eh_abort_handler(struct scsi_cmnd *cmd);
 int sas_eh_device_reset_handler(struct scsi_cmnd *cmd);
 int sas_eh_target_reset_handler(struct scsi_cmnd *cmd);
+enum scsi_timeout_action sas_eh_timed_out(struct scsi_cmnd *cmd);
 
 extern void sas_target_destroy(struct scsi_target *);
 extern int sas_sdev_init(struct scsi_device *);
@@ -743,6 +744,7 @@ void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event,
 	.this_id			= -1,				\
 	.eh_device_reset_handler	= sas_eh_device_reset_handler,	\
 	.eh_target_reset_handler	= sas_eh_target_reset_handler,	\
+	.eh_timed_out			= sas_eh_timed_out,		\
 	.target_destroy			= sas_target_destroy,		\
 	.ioctl				= sas_ioctl,			\