scsi: sd: Fix TCG OPAL unlock on system resume

Commit 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop
management") introduced the manage_system_start_stop scsi_device flag to
allow libata to indicate to the SCSI disk driver that nothing should be
done when resuming a disk on system resume. This change turned the
execution of sd_resume() into a no-op for ATA devices on system
resume. While this solved deadlock issues during device resume, this change
also wrongly removed the execution of opal_unlock_from_suspend().  As a
result, devices with TCG OPAL locking enabled remain locked and
inaccessible after a system resume from sleep.

To fix this issue, introduce the SCSI driver resume method and implement it
with the sd_resume() function calling opal_unlock_from_suspend(). The
former sd_resume() function is renamed to sd_resume_common() and modified
to call the new sd_resume() function. For non-ATA devices, this result in
no functional changes.

In order for libata to explicitly execute sd_resume() when a device is
resumed during system restart, the function scsi_resume_device() is
introduced. libata calls this function from the revalidation work executed
on devie resume, a state that is indicated with the new device flag
ATA_DFLAG_RESUMING. Doing so, locked TCG OPAL enabled devices are unlocked
on resume, allowing normal operation.

Fixes: 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop management")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218538
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240319071209.1179257-1-dlemoal@kernel.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

2 files changed, 53 insertions, 4 deletions

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 8d06475de17a..ffd7e7e72933 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1642,6 +1642,40 @@ int scsi_add_device(struct Scsi_Host *host, uint channel,
 }
 EXPORT_SYMBOL(scsi_add_device);
 
+int scsi_resume_device(struct scsi_device *sdev)
+{
+	struct device *dev = &sdev->sdev_gendev;
+	int ret = 0;
+
+	device_lock(dev);
+
+	/*
+	 * Bail out if the device or its queue are not running. Otherwise,
+	 * the rescan may block waiting for commands to be executed, with us
+	 * holding the device lock. This can result in a potential deadlock
+	 * in the power management core code when system resume is on-going.
+	 */
+	if (sdev->sdev_state != SDEV_RUNNING ||
+	    blk_queue_pm_only(sdev->request_queue)) {
+		ret = -EWOULDBLOCK;
+		goto unlock;
+	}
+
+	if (dev->driver && try_module_get(dev->driver->owner)) {
+		struct scsi_driver *drv = to_scsi_driver(dev->driver);
+
+		if (drv->resume)
+			ret = drv->resume(dev);
+		module_put(dev->driver->owner);
+	}
+
+unlock:
+	device_unlock(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(scsi_resume_device);
+
 int scsi_rescan_device(struct scsi_device *sdev)
 {
 	struct device *dev = &sdev->sdev_gendev;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ccff8f2e2e75..3cf898670290 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -4108,7 +4108,21 @@ static int sd_suspend_runtime(struct device *dev)
 	return sd_suspend_common(dev, true);
 }
 
-static int sd_resume(struct device *dev, bool runtime)
+static int sd_resume(struct device *dev)
+{
+	struct scsi_disk *sdkp = dev_get_drvdata(dev);
+
+	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
+
+	if (opal_unlock_from_suspend(sdkp->opal_dev)) {
+		sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int sd_resume_common(struct device *dev, bool runtime)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
 	int ret;
@@ -4124,7 +4138,7 @@ static int sd_resume(struct device *dev, bool runtime)
 	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
 	ret = sd_start_stop_device(sdkp, 1);
 	if (!ret) {
-		opal_unlock_from_suspend(sdkp->opal_dev);
+		sd_resume(dev);
 		sdkp->suspended = false;
 	}
 
@@ -4143,7 +4157,7 @@ static int sd_resume_system(struct device *dev)
 		return 0;
 	}
 
-	return sd_resume(dev, false);
+	return sd_resume_common(dev, false);
 }
 
 static int sd_resume_runtime(struct device *dev)
@@ -4170,7 +4184,7 @@ static int sd_resume_runtime(struct device *dev)
 				  "Failed to clear sense data\n");
 	}
 
-	return sd_resume(dev, true);
+	return sd_resume_common(dev, true);
 }
 
 static const struct dev_pm_ops sd_pm_ops = {
@@ -4193,6 +4207,7 @@ static struct scsi_driver sd_template = {
 		.pm		= &sd_pm_ops,
 	},
 	.rescan			= sd_rescan,
+	.resume			= sd_resume,
 	.init_command		= sd_init_command,
 	.uninit_command		= sd_uninit_command,
 	.done			= sd_done,