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, 157 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-ralink.c b/drivers/clocksource/timer-ralink.c
new file mode 100644
index 000000000..68434d9ed
--- /dev/null
+++ b/drivers/clocksource/timer-ralink.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ralink System Tick Counter driver present on RT3352 and MT7620 SoCs.
+ *
+ * Copyright (C) 2013 by John Crispin <john@phrozen.org>
+ */
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/reset.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#define SYSTICK_FREQ		(50 * 1000)
+
+#define SYSTICK_CONFIG		0x00
+#define SYSTICK_COMPARE		0x04
+#define SYSTICK_COUNT		0x08
+
+/* route systick irq to mips irq 7 instead of the r4k-timer */
+#define CFG_EXT_STK_EN		0x2
+/* enable the counter */
+#define CFG_CNT_EN		0x1
+
+struct systick_device {
+	void __iomem *membase;
+	struct clock_event_device dev;
+	int irq_requested;
+	int freq_scale;
+};
+
+static int systick_set_oneshot(struct clock_event_device *evt);
+static int systick_shutdown(struct clock_event_device *evt);
+
+static int systick_next_event(unsigned long delta,
+			      struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+	u32 count;
+
+	sdev = container_of(evt, struct systick_device, dev);
+	count = ioread32(sdev->membase + SYSTICK_COUNT);
+	count = (count + delta) % SYSTICK_FREQ;
+	iowrite32(count, sdev->membase + SYSTICK_COMPARE);
+
+	return 0;
+}
+
+static void systick_event_handler(struct clock_event_device *dev)
+{
+	/* noting to do here */
+}
+
+static irqreturn_t systick_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *dev = (struct clock_event_device *)dev_id;
+
+	dev->event_handler(dev);
+
+	return IRQ_HANDLED;
+}
+
+static struct systick_device systick = {
+	.dev = {
+		/*
+		 * cevt-r4k uses 300, make sure systick
+		 * gets used if available
+		 */
+		.rating			= 310,
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event		= systick_next_event,
+		.set_state_shutdown	= systick_shutdown,
+		.set_state_oneshot	= systick_set_oneshot,
+		.event_handler		= systick_event_handler,
+	},
+};
+
+static int systick_shutdown(struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	if (sdev->irq_requested)
+		free_irq(systick.dev.irq, &systick.dev);
+	sdev->irq_requested = 0;
+	iowrite32(0, systick.membase + SYSTICK_CONFIG);
+
+	return 0;
+}
+
+static int systick_set_oneshot(struct clock_event_device *evt)
+{
+	const char *name = systick.dev.name;
+	struct systick_device *sdev;
+	int irq = systick.dev.irq;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	if (!sdev->irq_requested) {
+		if (request_irq(irq, systick_interrupt,
+				IRQF_PERCPU | IRQF_TIMER, name, &systick.dev))
+			pr_err("Failed to request irq %d (%s)\n", irq, name);
+	}
+	sdev->irq_requested = 1;
+	iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
+		  systick.membase + SYSTICK_CONFIG);
+
+	return 0;
+}
+
+static int __init ralink_systick_init(struct device_node *np)
+{
+	int ret;
+
+	systick.membase = of_iomap(np, 0);
+	if (!systick.membase)
+		return -ENXIO;
+
+	systick.dev.name = np->name;
+	clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
+	systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+	systick.dev.max_delta_ticks = 0x7fff;
+	systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+	systick.dev.min_delta_ticks = 0x3;
+	systick.dev.irq = irq_of_parse_and_map(np, 0);
+	if (!systick.dev.irq) {
+		pr_err("%pOFn: request_irq failed", np);
+		ret = -EINVAL;
+		goto err_iounmap;
+	}
+
+	ret = clocksource_mmio_init(systick.membase + SYSTICK_COUNT, np->name,
+				    SYSTICK_FREQ, 301, 16,
+				    clocksource_mmio_readl_up);
+	if (ret)
+		goto err_free_irq;
+
+	clockevents_register_device(&systick.dev);
+
+	pr_info("%pOFn: running - mult: %d, shift: %d\n",
+			np, systick.dev.mult, systick.dev.shift);
+
+	return 0;
+
+err_free_irq:
+	irq_dispose_mapping(systick.dev.irq);
+err_iounmap:
+	iounmap(systick.membase);
+	return ret;
+}
+
+TIMER_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init);