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, 72 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h
new file mode 100644
index 000000000..74a632b85
--- /dev/null
+++ b/drivers/clocksource/timer-of.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TIMER_OF_H__
+#define __TIMER_OF_H__
+
+#include <linux/clockchips.h>
+
+#define TIMER_OF_BASE	0x1
+#define TIMER_OF_CLOCK	0x2
+#define TIMER_OF_IRQ	0x4
+
+struct of_timer_irq {
+	int irq;
+	int index;
+	const char *name;
+	unsigned long flags;
+	irq_handler_t handler;
+};
+
+struct of_timer_base {
+	void __iomem *base;
+	const char *name;
+	int index;
+};
+
+struct of_timer_clk {
+	struct clk *clk;
+	const char *name;
+	int index;
+	unsigned long rate;
+	unsigned long period;
+};
+
+struct timer_of {
+	unsigned int flags;
+	struct device_node *np;
+	struct clock_event_device clkevt;
+	struct of_timer_base of_base;
+	struct of_timer_irq  of_irq;
+	struct of_timer_clk  of_clk;
+	void *private_data;
+};
+
+static inline struct timer_of *to_timer_of(struct clock_event_device *clkevt)
+{
+	return container_of(clkevt, struct timer_of, clkevt);
+}
+
+static inline void __iomem *timer_of_base(struct timer_of *to)
+{
+	return to->of_base.base;
+}
+
+static inline int timer_of_irq(struct timer_of *to)
+{
+	return to->of_irq.irq;
+}
+
+static inline unsigned long timer_of_rate(struct timer_of *to)
+{
+	return to->of_clk.rate;
+}
+
+static inline unsigned long timer_of_period(struct timer_of *to)
+{
+	return to->of_clk.period;
+}
+
+int timer_of_init(struct device_node *np, struct timer_of *to);
+
+void timer_of_cleanup(struct timer_of *to);
+
+#endif