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, 63 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-sp.h b/drivers/clocksource/timer-sp.h
new file mode 100644
index 000000000..811f840be
--- /dev/null
+++ b/drivers/clocksource/timer-sp.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM timer implementation, found in Integrator, Versatile and Realview
+ * platforms.  Not all platforms support all registers and bits in these
+ * registers, so we mark them with A for Integrator AP, C for Integrator
+ * CP, V for Versatile and R for Realview.
+ *
+ * Integrator AP has 16-bit timers, Integrator CP, Versatile and Realview
+ * can have 16-bit or 32-bit selectable via a bit in the control register.
+ *
+ * Every SP804 contains two identical timers.
+ */
+#define NR_TIMERS	2
+#define TIMER_1_BASE	0x00
+#define TIMER_2_BASE	0x20
+
+#define TIMER_LOAD	0x00			/* ACVR rw */
+#define TIMER_VALUE	0x04			/* ACVR ro */
+#define TIMER_CTRL	0x08			/* ACVR rw */
+#define TIMER_CTRL_ONESHOT	(1 << 0)	/*  CVR */
+#define TIMER_CTRL_32BIT	(1 << 1)	/*  CVR */
+#define TIMER_CTRL_DIV1		(0 << 2)	/* ACVR */
+#define TIMER_CTRL_DIV16	(1 << 2)	/* ACVR */
+#define TIMER_CTRL_DIV256	(2 << 2)	/* ACVR */
+#define TIMER_CTRL_IE		(1 << 5)	/*   VR */
+#define TIMER_CTRL_PERIODIC	(1 << 6)	/* ACVR */
+#define TIMER_CTRL_ENABLE	(1 << 7)	/* ACVR */
+
+#define TIMER_INTCLR	0x0c			/* ACVR wo */
+#define TIMER_RIS	0x10			/*  CVR ro */
+#define TIMER_MIS	0x14			/*  CVR ro */
+#define TIMER_BGLOAD	0x18			/*  CVR rw */
+
+struct sp804_timer {
+	int load;
+	int load_h;
+	int value;
+	int value_h;
+	int ctrl;
+	int intclr;
+	int ris;
+	int mis;
+	int bgload;
+	int bgload_h;
+	int timer_base[NR_TIMERS];
+	int width;
+};
+
+struct sp804_clkevt {
+	void __iomem *base;
+	void __iomem *load;
+	void __iomem *load_h;
+	void __iomem *value;
+	void __iomem *value_h;
+	void __iomem *ctrl;
+	void __iomem *intclr;
+	void __iomem *ris;
+	void __iomem *mis;
+	void __iomem *bgload;
+	void __iomem *bgload_h;
+	unsigned long reload;
+	int width;
+};