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, 221 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
new file mode 100644
index 000000000..2c07dd2af
--- /dev/null
+++ b/drivers/clocksource/timer-sprd.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Spreadtrum Communications Inc.
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+#include "timer-of.h"
+
+#define TIMER_NAME		"sprd_timer"
+
+#define TIMER_LOAD_LO		0x0
+#define TIMER_LOAD_HI		0x4
+#define TIMER_VALUE_LO		0x8
+#define TIMER_VALUE_HI		0xc
+
+#define TIMER_CTL		0x10
+#define TIMER_CTL_PERIOD_MODE	BIT(0)
+#define TIMER_CTL_ENABLE	BIT(1)
+#define TIMER_CTL_64BIT_WIDTH	BIT(16)
+
+#define TIMER_INT		0x14
+#define TIMER_INT_EN		BIT(0)
+#define TIMER_INT_RAW_STS	BIT(1)
+#define TIMER_INT_MASK_STS	BIT(2)
+#define TIMER_INT_CLR		BIT(3)
+
+#define TIMER_VALUE_SHDW_LO	0x18
+#define TIMER_VALUE_SHDW_HI	0x1c
+
+#define TIMER_VALUE_LO_MASK	GENMASK(31, 0)
+#define TIMER_VALUE_HI_MASK	GENMASK(31, 0)
+
+static void sprd_timer_enable(void __iomem *base, u32 flag)
+{
+	u32 val = readl_relaxed(base + TIMER_CTL);
+
+	val |= TIMER_CTL_ENABLE;
+	if (flag & TIMER_CTL_64BIT_WIDTH)
+		val |= TIMER_CTL_64BIT_WIDTH;
+	else
+		val &= ~TIMER_CTL_64BIT_WIDTH;
+
+	if (flag & TIMER_CTL_PERIOD_MODE)
+		val |= TIMER_CTL_PERIOD_MODE;
+	else
+		val &= ~TIMER_CTL_PERIOD_MODE;
+
+	writel_relaxed(val, base + TIMER_CTL);
+}
+
+static void sprd_timer_disable(void __iomem *base)
+{
+	u32 val = readl_relaxed(base + TIMER_CTL);
+
+	val &= ~TIMER_CTL_ENABLE;
+	writel_relaxed(val, base + TIMER_CTL);
+}
+
+static void sprd_timer_update_counter(void __iomem *base, unsigned long cycles)
+{
+	writel_relaxed(cycles & TIMER_VALUE_LO_MASK, base + TIMER_LOAD_LO);
+	writel_relaxed(0, base + TIMER_LOAD_HI);
+}
+
+static void sprd_timer_enable_interrupt(void __iomem *base)
+{
+	writel_relaxed(TIMER_INT_EN, base + TIMER_INT);
+}
+
+static void sprd_timer_clear_interrupt(void __iomem *base)
+{
+	u32 val = readl_relaxed(base + TIMER_INT);
+
+	val |= TIMER_INT_CLR;
+	writel_relaxed(val, base + TIMER_INT);
+}
+
+static int sprd_timer_set_next_event(unsigned long cycles,
+				     struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	sprd_timer_update_counter(timer_of_base(to), cycles);
+	sprd_timer_enable(timer_of_base(to), 0);
+
+	return 0;
+}
+
+static int sprd_timer_set_periodic(struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	sprd_timer_update_counter(timer_of_base(to), timer_of_period(to));
+	sprd_timer_enable(timer_of_base(to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static int sprd_timer_shutdown(struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	return 0;
+}
+
+static irqreturn_t sprd_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *ce = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_clear_interrupt(timer_of_base(to));
+
+	if (clockevent_state_oneshot(ce))
+		sprd_timer_disable(timer_of_base(to));
+
+	ce->event_handler(ce);
+	return IRQ_HANDLED;
+}
+
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = TIMER_NAME,
+		.rating = 300,
+		.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_PERIODIC |
+			CLOCK_EVT_FEAT_ONESHOT,
+		.set_state_shutdown = sprd_timer_shutdown,
+		.set_state_periodic = sprd_timer_set_periodic,
+		.set_next_event = sprd_timer_set_next_event,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.handler = sprd_timer_interrupt,
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static int __init sprd_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &to);
+	if (ret)
+		return ret;
+
+	sprd_timer_enable_interrupt(timer_of_base(&to));
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					1, UINT_MAX);
+
+	return 0;
+}
+
+static struct timer_of suspend_to = {
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+	u32 lo, hi;
+
+	do {
+		hi = readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_HI);
+		lo = readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_LO);
+	} while (hi != readl_relaxed(timer_of_base(&suspend_to) + TIMER_VALUE_SHDW_HI));
+
+	return ~(((u64)hi << 32) | lo);
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+	writel_relaxed(TIMER_VALUE_LO_MASK,
+		       timer_of_base(&suspend_to) + TIMER_LOAD_LO);
+	writel_relaxed(TIMER_VALUE_HI_MASK,
+		       timer_of_base(&suspend_to) + TIMER_LOAD_HI);
+	sprd_timer_enable(timer_of_base(&suspend_to),
+			  TIMER_CTL_PERIOD_MODE|TIMER_CTL_64BIT_WIDTH);
+
+	return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+	sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+	.name	= "sprd_suspend_timer",
+	.rating	= 200,
+	.read	= sprd_suspend_timer_read,
+	.enable = sprd_suspend_timer_enable,
+	.disable = sprd_suspend_timer_disable,
+	.mask	= CLOCKSOURCE_MASK(64),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &suspend_to);
+	if (ret)
+		return ret;
+
+	clocksource_register_hz(&suspend_clocksource,
+				timer_of_rate(&suspend_to));
+
+	return 0;
+}
+
+TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+		 sprd_suspend_timer_init);