virtio_blk: set the zone write granularitygrafted

virtblk_read_zoned_limits() reads the write granularity that the device
reports in virtio_blk_zoned_characteristics and assigns it to the
physical block size and to io_min, but never to the limit that is named
after it. queue_limits.zone_write_granularity is left at zero, so
blk_validate_zoned_limits() raises it to the logical block size:

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

A device that reports a granularity coarser than its logical block size,
which is what the field exists to express, therefore has it silently
reduced. A 512e host managed disk passed through to a guest reports a
logical block size of 512 and a write granularity of 4096, and the guest
ends up with a zone write granularity of 512.

bio_split_alignment() returns lim->zone_write_granularity if it is non-zero
and bio_split_io_at() may split a bio with as per bio_split_alignment().
This can real to the write getting rejected by the host drive, as the write
is not aligned to the physical block size.

zonefs also takes its block size from bdev_zone_write_granularity(), so it
would incorrectly use 512 on a disk that requires 4096.

sd_zbc_read_zones() sets the limit from the physical block size for the
same reason. NVMe ZNS and null_blk leave it unset, but the fallback
gives the right answer for them, as their write granularity is the
logical block size. virtio carries a separate value that may exceed it.

Set the zone write granularity from the value that the device reports.

Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 117 insertions, 0 deletions

diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
new file mode 100644
index 000000000..f138a4335
--- /dev/null
+++ b/drivers/acpi/container.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * container.c  - ACPI Generic Container Driver
+ *
+ * Copyright (C) 2004 Anil S Keshavamurthy (anil.s.keshavamurthy@intel.com)
+ * Copyright (C) 2004 Keiichiro Tokunaga (tokunaga.keiich@jp.fujitsu.com)
+ * Copyright (C) 2004 Motoyuki Ito (motoyuki@soft.fujitsu.com)
+ * Copyright (C) 2004 FUJITSU LIMITED
+ * Copyright (C) 2004, 2013 Intel Corp.
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+#include <linux/acpi.h>
+#include <linux/container.h>
+
+#include "internal.h"
+
+static const struct acpi_device_id container_device_ids[] = {
+	{"ACPI0004", 0},
+	{"PNP0A05", 0},
+	{"PNP0A06", 0},
+	{"", 0},
+};
+
+#ifdef CONFIG_ACPI_CONTAINER
+
+static int check_offline(struct acpi_device *adev, void *not_used)
+{
+	if (acpi_scan_is_offline(adev, false))
+		return 0;
+
+	return -EBUSY;
+}
+
+static int acpi_container_offline(struct container_dev *cdev)
+{
+	/* Check all of the dependent devices' physical companions. */
+	return acpi_dev_for_each_child(ACPI_COMPANION(&cdev->dev), check_offline, NULL);
+}
+
+static void acpi_container_release(struct device *dev)
+{
+	kfree(to_container_dev(dev));
+}
+
+static int container_device_attach(struct acpi_device *adev,
+				   const struct acpi_device_id *not_used)
+{
+	struct container_dev *cdev;
+	struct device *dev;
+	int ret;
+
+	if (adev->flags.is_dock_station)
+		return 0;
+
+	cdev = kzalloc_obj(*cdev);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->offline = acpi_container_offline;
+	dev = &cdev->dev;
+	dev->bus = &container_subsys;
+	dev_set_name(dev, "%s", dev_name(&adev->dev));
+	ACPI_COMPANION_SET(dev, adev);
+	dev->release = acpi_container_release;
+	ret = device_register(dev);
+	if (ret) {
+		put_device(dev);
+		return ret;
+	}
+	adev->driver_data = dev;
+	return 1;
+}
+
+static void container_device_detach(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	adev->driver_data = NULL;
+	if (dev)
+		device_unregister(dev);
+}
+
+static void container_device_online(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+static struct acpi_scan_handler container_handler = {
+	.ids = container_device_ids,
+	.attach = container_device_attach,
+	.detach = container_device_detach,
+	.hotplug = {
+		.enabled = true,
+		.demand_offline = true,
+		.notify_online = container_device_online,
+	},
+};
+
+void __init acpi_container_init(void)
+{
+	acpi_scan_add_handler(&container_handler);
+}
+
+#else
+
+static struct acpi_scan_handler container_handler = {
+	.ids = container_device_ids,
+};
+
+void __init acpi_container_init(void)
+{
+	acpi_scan_add_handler_with_hotplug(&container_handler, "container");
+}
+
+#endif /* CONFIG_ACPI_CONTAINER */