ata: libata-scsi: Disable scsi device manage_system_start_stop

The introduction of a device link to create a consumer/supplier
relationship between the scsi device of an ATA device and the ATA port
of that ATA device fixes the ordering of system suspend and resume
operations. For suspend, the scsi device is suspended first and the ata
port after it. This is fine as this allows the synchronize cache and
START STOP UNIT commands issued by the scsi disk driver to be executed
before the ata port is disabled.

For resume operations, the ata port is resumed first, followed
by the scsi device. This allows having the request queue of the scsi
device to be unfrozen after the ata port resume is scheduled in EH,
thus avoiding to see new requests prematurely issued to the ATA device.
Since libata sets manage_system_start_stop to 1, the scsi disk resume
operation also results in issuing a START STOP UNIT command to the
device being resumed so that the device exits standby power mode.

However, restoring the ATA device to the active power mode must be
synchronized with libata EH processing of the port resume operation to
avoid either 1) seeing the start stop unit command being received too
early when the port is not yet resumed and ready to accept commands, or
after the port resume process issues commands such as IDENTIFY to
revalidate the device. In this last case, the risk is that the device
revalidation fails with timeout errors as the drive is still spun down.

Commit 0a8589055936 ("ata,scsi: do not issue START STOP UNIT on resume")
disabled issuing the START STOP UNIT command to avoid issues with it.
But this is incorrect as transitioning a device to the active power
mode from the standby power mode set on suspend requires a media access
command. The IDENTIFY, READ LOG and SET FEATURES commands executed in
libata EH context triggered by the ata port resume operation may thus
fail.

Fix these synchronization issues is by handling a device power mode
transitions for system suspend and resume directly in libata EH context,
without relying on the scsi disk driver management triggered with the
manage_system_start_stop flag.

To do this, the following libata helper functions are introduced:

1) ata_dev_power_set_standby():

This function issues a STANDBY IMMEDIATE command to transitiom a device
to the standby power mode. For HDDs, this spins down the disks. This
function applies only to ATA and ZAC devices and does nothing otherwise.
This function also does nothing for devices that have the
ATA_FLAG_NO_POWEROFF_SPINDOWN or ATA_FLAG_NO_HIBERNATE_SPINDOWN flag
set.

For suspend, call ata_dev_power_set_standby() in
ata_eh_handle_port_suspend() before the port is disabled and frozen.
ata_eh_unload() is also modified to transition all enabled devices to
the standby power mode when the system is shutdown or devices removed.

2) ata_dev_power_set_active() and

This function applies to ATA or ZAC devices and issues a VERIFY command
for 1 sector at LBA 0 to transition the device to the active power mode.
For HDDs, since this function will complete only once the disk spin up.
Its execution uses the same timeouts as for reset, to give the drive
enough time to complete spinup without triggering a command timeout.

For resume, call ata_dev_power_set_active() in
ata_eh_revalidate_and_attach() after the port has been enabled and
before any other command is issued to the device.

With these changes, the manage_system_start_stop and no_start_on_resume
scsi device flags do not need to be set in ata_scsi_dev_config(). The
flag manage_runtime_start_stop is still set to allow the sd driver to
spinup/spindown a disk through the sd runtime operations.

Fixes: 0a8589055936 ("ata,scsi: do not issue START STOP UNIT on resume")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 45 insertions, 1 deletions

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 4cf4f57e57b8..b1b2c276371e 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -147,6 +147,8 @@ 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_VERIFY),
+	  .timeouts = ata_eh_reset_timeouts },
 };
 #undef CMDS
 
@@ -498,7 +500,19 @@ static void ata_eh_unload(struct ata_port *ap)
 	struct ata_device *dev;
 	unsigned long flags;
 
-	/* Restore SControl IPM and SPD for the next driver and
+	/*
+	 * Unless we are restarting, transition all enabled devices to
+	 * standby power mode.
+	 */
+	if (system_state != SYSTEM_RESTART) {
+		ata_for_each_link(link, ap, PMP_FIRST) {
+			ata_for_each_dev(dev, link, ENABLED)
+				ata_dev_power_set_standby(dev);
+		}
+	}
+
+	/*
+	 * Restore SControl IPM and SPD for the next driver and
 	 * disable attached devices.
 	 */
 	ata_for_each_link(link, ap, PMP_FIRST) {
@@ -684,6 +698,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
 			ehc->saved_xfer_mode[devno] = dev->xfer_mode;
 			if (ata_ncq_enabled(dev))
 				ehc->saved_ncq_enabled |= 1 << devno;
+
+			/* If we are resuming, wake up the device */
+			if (ap->pflags & ATA_PFLAG_RESUMING)
+				ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE;
 		}
 	}
 
@@ -743,6 +761,8 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
 	/* clean up */
 	spin_lock_irqsave(ap->lock, flags);
 
+	ap->pflags &= ~ATA_PFLAG_RESUMING;
+
 	if (ap->pflags & ATA_PFLAG_LOADING)
 		ap->pflags &= ~ATA_PFLAG_LOADING;
 	else if ((ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) &&
@@ -1218,6 +1238,13 @@ void ata_eh_detach_dev(struct ata_device *dev)
 	struct ata_eh_context *ehc = &link->eh_context;
 	unsigned long flags;
 
+	/*
+	 * If the device is still enabled, transition it to standby power mode
+	 * (i.e. spin down HDDs).
+	 */
+	if (ata_dev_enabled(dev))
+		ata_dev_power_set_standby(dev);
+
 	ata_dev_disable(dev);
 
 	spin_lock_irqsave(ap->lock, flags);
@@ -3016,6 +3043,15 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
 		if (ehc->i.flags & ATA_EHI_DID_RESET)
 			readid_flags |= ATA_READID_POSTRESET;
 
+		/*
+		 * When resuming, before executing any command, make sure to
+		 * transition the device to the active power mode.
+		 */
+		if ((action & ATA_EH_SET_ACTIVE) && ata_dev_enabled(dev)) {
+			ata_dev_power_set_active(dev);
+			ata_eh_done(link, dev, ATA_EH_SET_ACTIVE);
+		}
+
 		if ((action & ATA_EH_REVALIDATE) && ata_dev_enabled(dev)) {
 			WARN_ON(dev->class == ATA_DEV_PMP);
 
@@ -3989,6 +4025,7 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap)
 	unsigned long flags;
 	int rc = 0;
 	struct ata_device *dev;
+	struct ata_link *link;
 
 	/* are we suspending? */
 	spin_lock_irqsave(ap->lock, flags);
@@ -4001,6 +4038,12 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap)
 
 	WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED);
 
+	/* Set all devices attached to the port in standby mode */
+	ata_for_each_link(link, ap, HOST_FIRST) {
+		ata_for_each_dev(dev, link, ENABLED)
+			ata_dev_power_set_standby(dev);
+	}
+
 	/*
 	 * If we have a ZPODD attached, check its zero
 	 * power ready status before the port is frozen.
@@ -4083,6 +4126,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap)
 	/* update the flags */
 	spin_lock_irqsave(ap->lock, flags);
 	ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED);
+	ap->pflags |= ATA_PFLAG_RESUMING;
 	spin_unlock_irqrestore(ap->lock, flags);
 }
 #endif /* CONFIG_PM */