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, 150 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-vt8500.c b/drivers/clocksource/timer-vt8500.c
new file mode 100644
index 000000000..a469b1b5f
--- /dev/null
+++ b/drivers/clocksource/timer-vt8500.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  arch/arm/mach-vt8500/timer.c
+ *
+ *  Copyright (C) 2012 Tony Prisk <linux@prisktech.co.nz>
+ *  Copyright (C) 2010 Alexey Charkov <alchark@gmail.com>
+ */
+
+/*
+ * This file is copied and modified from the original timer.c provided by
+ * Alexey Charkov. Minor changes have been made for Device Tree Support.
+ */
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define VT8500_TIMER_OFFSET	0x0100
+#define VT8500_TIMER_HZ		3000000
+#define TIMER_MATCH_VAL		0x0000
+#define TIMER_COUNT_VAL		0x0010
+#define TIMER_STATUS_VAL	0x0014
+#define TIMER_IER_VAL		0x001c		/* interrupt enable */
+#define TIMER_CTRL_VAL		0x0020
+#define TIMER_AS_VAL		0x0024		/* access status */
+#define TIMER_COUNT_R_ACTIVE	(1 << 5)	/* not ready for read */
+#define TIMER_COUNT_W_ACTIVE	(1 << 4)	/* not ready for write */
+#define TIMER_MATCH_W_ACTIVE	(1 << 0)	/* not ready for write */
+
+#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
+
+#define MIN_OSCR_DELTA		16
+
+static void __iomem *regbase;
+
+static u64 vt8500_timer_read(struct clocksource *cs)
+{
+	int loops = msecs_to_loops(10);
+	writel(3, regbase + TIMER_CTRL_VAL);
+	while ((readl((regbase + TIMER_AS_VAL)) & TIMER_COUNT_R_ACTIVE)
+						&& --loops)
+		cpu_relax();
+	return readl(regbase + TIMER_COUNT_VAL);
+}
+
+static struct clocksource clocksource = {
+	.name           = "vt8500_timer",
+	.rating         = 200,
+	.read           = vt8500_timer_read,
+	.mask           = CLOCKSOURCE_MASK(32),
+	.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int vt8500_timer_set_next_event(unsigned long cycles,
+				    struct clock_event_device *evt)
+{
+	int loops = msecs_to_loops(10);
+	u64 alarm = clocksource.read(&clocksource) + cycles;
+	while ((readl(regbase + TIMER_AS_VAL) & TIMER_MATCH_W_ACTIVE)
+						&& --loops)
+		cpu_relax();
+	writel((unsigned long)alarm, regbase + TIMER_MATCH_VAL);
+
+	if ((signed)(alarm - clocksource.read(&clocksource)) <= MIN_OSCR_DELTA)
+		return -ETIME;
+
+	writel(1, regbase + TIMER_IER_VAL);
+
+	return 0;
+}
+
+static int vt8500_shutdown(struct clock_event_device *evt)
+{
+	writel(readl(regbase + TIMER_CTRL_VAL) | 1, regbase + TIMER_CTRL_VAL);
+	writel(0, regbase + TIMER_IER_VAL);
+	return 0;
+}
+
+static struct clock_event_device clockevent = {
+	.name			= "vt8500_timer",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= vt8500_timer_set_next_event,
+	.set_state_shutdown	= vt8500_shutdown,
+	.set_state_oneshot	= vt8500_shutdown,
+};
+
+static irqreturn_t vt8500_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+	writel(0xf, regbase + TIMER_STATUS_VAL);
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static int __init vt8500_timer_init(struct device_node *np)
+{
+	int timer_irq, ret;
+
+	regbase = of_iomap(np, 0);
+	if (!regbase) {
+		pr_err("%s: Missing iobase description in Device Tree\n",
+								__func__);
+		return -ENXIO;
+	}
+
+	timer_irq = irq_of_parse_and_map(np, 0);
+	if (!timer_irq) {
+		pr_err("%s: Missing irq description in Device Tree\n",
+								__func__);
+		return -EINVAL;
+	}
+
+	writel(1, regbase + TIMER_CTRL_VAL);
+	writel(0xf, regbase + TIMER_STATUS_VAL);
+	writel(~0, regbase + TIMER_MATCH_VAL);
+
+	ret = clocksource_register_hz(&clocksource, VT8500_TIMER_HZ);
+	if (ret) {
+		pr_err("%s: clocksource_register failed for %s\n",
+		       __func__, clocksource.name);
+		return ret;
+	}
+
+	clockevent.cpumask = cpumask_of(0);
+
+	ret = request_irq(timer_irq, vt8500_timer_interrupt,
+			  IRQF_TIMER | IRQF_IRQPOLL, "vt8500_timer",
+			  &clockevent);
+	if (ret) {
+		pr_err("%s: setup_irq failed for %s\n", __func__,
+							clockevent.name);
+		return ret;
+	}
+
+	clockevents_config_and_register(&clockevent, VT8500_TIMER_HZ,
+					MIN_OSCR_DELTA * 2, 0xf0000000);
+
+	return 0;
+}
+
+TIMER_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init);