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, 110 insertions, 0 deletions

diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c
new file mode 100644
index 000000000..63ae3a691
--- /dev/null
+++ b/drivers/clocksource/clps711x-timer.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Cirrus Logic CLPS711X clocksource driver
+ *
+ *  Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru>
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+enum {
+	CLPS711X_CLKSRC_CLOCKSOURCE,
+	CLPS711X_CLKSRC_CLOCKEVENT,
+};
+
+static void __iomem *tcd;
+
+static u64 notrace clps711x_sched_clock_read(void)
+{
+	return ~readw(tcd);
+}
+
+static void __init clps711x_clksrc_init(struct clk *clock, void __iomem *base)
+{
+	unsigned long rate = clk_get_rate(clock);
+
+	tcd = base;
+
+	clocksource_mmio_init(tcd, "clps711x-clocksource", rate, 300, 16,
+			      clocksource_mmio_readw_down);
+
+	sched_clock_register(clps711x_sched_clock_read, 16, rate);
+}
+
+static irqreturn_t clps711x_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base,
+					unsigned int irq)
+{
+	struct clock_event_device *clkevt;
+	unsigned long rate;
+
+	clkevt = kzalloc_obj(*clkevt);
+	if (!clkevt)
+		return -ENOMEM;
+
+	rate = clk_get_rate(clock);
+
+	/* Set Timer prescaler */
+	writew(DIV_ROUND_CLOSEST(rate, HZ), base);
+
+	clkevt->name = "clps711x-clockevent";
+	clkevt->rating = 300;
+	clkevt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_C3STOP;
+	clkevt->cpumask = cpumask_of(0);
+	clockevents_config_and_register(clkevt, HZ, 0, 0);
+
+	return request_irq(irq, clps711x_timer_interrupt, IRQF_TIMER,
+			   "clps711x-timer", clkevt);
+}
+
+static int __init clps711x_timer_init(struct device_node *np)
+{
+	unsigned int irq = irq_of_parse_and_map(np, 0);
+	struct clk *clock = of_clk_get(np, 0);
+	void __iomem *base = of_iomap(np, 0);
+	int ret = 0;
+
+	if (!base)
+		return -ENOMEM;
+	if (!irq) {
+		ret = -EINVAL;
+		goto unmap_io;
+	}
+	if (IS_ERR(clock)) {
+		ret = PTR_ERR(clock);
+		goto unmap_io;
+	}
+
+	switch (of_alias_get_id(np, "timer")) {
+	case CLPS711X_CLKSRC_CLOCKSOURCE:
+		clps711x_clksrc_init(clock, base);
+		return 0;
+	case CLPS711X_CLKSRC_CLOCKEVENT:
+		ret =  _clps711x_clkevt_init(clock, base, irq);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+unmap_io:
+	iounmap(base);
+	return ret;
+}
+TIMER_OF_DECLARE(clps711x, "cirrus,ep7209-timer", clps711x_timer_init);