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, 292 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c
new file mode 100644
index 000000000..3d804128c
--- /dev/null
+++ b/drivers/clocksource/timer-stm32-lp.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) STMicroelectronics 2019 - All Rights Reserved
+ * Authors: Benjamin Gaignard <benjamin.gaignard@st.com> for STMicroelectronics.
+ *	    Pascal Paillet <p.paillet@st.com> for STMicroelectronics.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/stm32-lptimer.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/pm_wakeirq.h>
+
+#define CFGR_PSC_OFFSET		9
+#define STM32_LP_RATING		1000
+#define STM32_TARGET_CLKRATE	(32000 * HZ)
+#define STM32_LP_MAX_PSC	7
+
+struct stm32_lp_private {
+	struct regmap *reg;
+	struct clock_event_device clkevt;
+	unsigned long period;
+	u32 psc;
+	struct device *dev;
+	struct clk *clk;
+	u32 version;
+};
+
+static struct stm32_lp_private*
+to_priv(struct clock_event_device *clkevt)
+{
+	return container_of(clkevt, struct stm32_lp_private, clkevt);
+}
+
+static int stm32_clkevent_lp_shutdown(struct clock_event_device *clkevt)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	regmap_write(priv->reg, STM32_LPTIM_CR, 0);
+	regmap_write(priv->reg, STM32_LPTIM_IER, 0);
+	/* clear pending flags */
+	regmap_write(priv->reg, STM32_LPTIM_ICR, STM32_LPTIM_ARRMCF);
+
+	return 0;
+}
+
+static int stm32mp25_clkevent_lp_set_evt(struct stm32_lp_private *priv, unsigned long evt)
+{
+	int ret;
+	u32 val;
+
+	regmap_read(priv->reg, STM32_LPTIM_CR, &val);
+	if (!FIELD_GET(STM32_LPTIM_ENABLE, val)) {
+		/* Enable LPTIMER to be able to write into IER and ARR registers */
+		regmap_write(priv->reg, STM32_LPTIM_CR, STM32_LPTIM_ENABLE);
+		/*
+		 * After setting the ENABLE bit, a delay of two counter clock cycles is needed
+		 * before the LPTIM is actually enabled. For 32KHz rate, this makes approximately
+		 * 62.5 micro-seconds, round it up.
+		 */
+		udelay(63);
+	}
+	/* set next event counter */
+	regmap_write(priv->reg, STM32_LPTIM_ARR, evt);
+	/* enable ARR interrupt */
+	regmap_write(priv->reg, STM32_LPTIM_IER, STM32_LPTIM_ARRMIE);
+
+	/* Poll DIEROK and ARROK to ensure register access has completed */
+	ret = regmap_read_poll_timeout_atomic(priv->reg, STM32_LPTIM_ISR, val,
+					      (val & STM32_LPTIM_DIEROK_ARROK) ==
+					      STM32_LPTIM_DIEROK_ARROK,
+					      10, 500);
+	if (ret) {
+		dev_err(priv->dev, "access to LPTIM timed out\n");
+		/* Disable LPTIMER */
+		regmap_write(priv->reg, STM32_LPTIM_CR, 0);
+		return ret;
+	}
+	/* Clear DIEROK and ARROK flags */
+	regmap_write(priv->reg, STM32_LPTIM_ICR, STM32_LPTIM_DIEROKCF_ARROKCF);
+
+	return 0;
+}
+
+static void stm32_clkevent_lp_set_evt(struct stm32_lp_private *priv, unsigned long evt)
+{
+	/* disable LPTIMER to be able to write into IER register*/
+	regmap_write(priv->reg, STM32_LPTIM_CR, 0);
+	/* enable ARR interrupt */
+	regmap_write(priv->reg, STM32_LPTIM_IER, STM32_LPTIM_ARRMIE);
+	/* enable LPTIMER to be able to write into ARR register */
+	regmap_write(priv->reg, STM32_LPTIM_CR, STM32_LPTIM_ENABLE);
+	/* set next event counter */
+	regmap_write(priv->reg, STM32_LPTIM_ARR, evt);
+}
+
+static int stm32_clkevent_lp_set_timer(unsigned long evt,
+				       struct clock_event_device *clkevt,
+				       int is_periodic)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+	int ret;
+
+	if (priv->version == STM32_LPTIM_VERR_23) {
+		ret = stm32mp25_clkevent_lp_set_evt(priv, evt);
+		if (ret)
+			return ret;
+	} else {
+		stm32_clkevent_lp_set_evt(priv, evt);
+	}
+
+	/* start counter */
+	if (is_periodic)
+		regmap_write(priv->reg, STM32_LPTIM_CR,
+			     STM32_LPTIM_CNTSTRT | STM32_LPTIM_ENABLE);
+	else
+		regmap_write(priv->reg, STM32_LPTIM_CR,
+			     STM32_LPTIM_SNGSTRT | STM32_LPTIM_ENABLE);
+
+	return 0;
+}
+
+static int stm32_clkevent_lp_set_next_event(unsigned long evt,
+					    struct clock_event_device *clkevt)
+{
+	return stm32_clkevent_lp_set_timer(evt, clkevt,
+					   clockevent_state_periodic(clkevt));
+}
+
+static int stm32_clkevent_lp_set_periodic(struct clock_event_device *clkevt)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	return stm32_clkevent_lp_set_timer(priv->period, clkevt, true);
+}
+
+static int stm32_clkevent_lp_set_oneshot(struct clock_event_device *clkevt)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	return stm32_clkevent_lp_set_timer(priv->period, clkevt, false);
+}
+
+static irqreturn_t stm32_clkevent_lp_irq_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	regmap_write(priv->reg, STM32_LPTIM_ICR, STM32_LPTIM_ARRMCF);
+
+	if (clkevt->event_handler)
+		clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void stm32_clkevent_lp_set_prescaler(struct stm32_lp_private *priv,
+					    unsigned long *rate)
+{
+	int i;
+
+	for (i = 0; i <= STM32_LP_MAX_PSC; i++) {
+		if (DIV_ROUND_CLOSEST(*rate, 1 << i) < STM32_TARGET_CLKRATE)
+			break;
+	}
+
+	regmap_write(priv->reg, STM32_LPTIM_CFGR, i << CFGR_PSC_OFFSET);
+
+	/* Adjust rate and period given the prescaler value */
+	*rate = DIV_ROUND_CLOSEST(*rate, (1 << i));
+	priv->period = DIV_ROUND_UP(*rate, HZ);
+	priv->psc = i;
+}
+
+static void stm32_clkevent_lp_suspend(struct clock_event_device *clkevt)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	stm32_clkevent_lp_shutdown(clkevt);
+
+	/* balance clk_prepare_enable() from the probe */
+	clk_disable_unprepare(priv->clk);
+}
+
+static void stm32_clkevent_lp_resume(struct clock_event_device *clkevt)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+
+	clk_prepare_enable(priv->clk);
+
+	/* restore prescaler */
+	regmap_write(priv->reg, STM32_LPTIM_CFGR, priv->psc << CFGR_PSC_OFFSET);
+}
+
+static void stm32_clkevent_lp_init(struct stm32_lp_private *priv,
+				  struct device_node *np, unsigned long rate)
+{
+	priv->clkevt.name = np->full_name;
+	priv->clkevt.cpumask = cpu_possible_mask;
+	priv->clkevt.features = CLOCK_EVT_FEAT_PERIODIC |
+				CLOCK_EVT_FEAT_ONESHOT;
+	priv->clkevt.set_state_shutdown = stm32_clkevent_lp_shutdown;
+	priv->clkevt.set_state_periodic = stm32_clkevent_lp_set_periodic;
+	priv->clkevt.set_state_oneshot = stm32_clkevent_lp_set_oneshot;
+	priv->clkevt.set_next_event = stm32_clkevent_lp_set_next_event;
+	priv->clkevt.rating = STM32_LP_RATING;
+	priv->clkevt.suspend = stm32_clkevent_lp_suspend;
+	priv->clkevt.resume = stm32_clkevent_lp_resume;
+	priv->clkevt.owner = THIS_MODULE;
+
+	clockevents_config_and_register(&priv->clkevt, rate, 0x1,
+					STM32_LPTIM_MAX_ARR);
+}
+
+static int stm32_clkevent_lp_probe(struct platform_device *pdev)
+{
+	struct stm32_lptimer *ddata = dev_get_drvdata(pdev->dev.parent);
+	struct stm32_lp_private *priv;
+	unsigned long rate;
+	int ret, irq;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reg = ddata->regmap;
+	priv->version = ddata->version;
+	priv->clk = ddata->clk;
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return -EINVAL;
+
+	rate = clk_get_rate(priv->clk);
+	if (!rate) {
+		ret = -EINVAL;
+		goto out_clk_disable;
+	}
+
+	irq = platform_get_irq(to_platform_device(pdev->dev.parent), 0);
+	if (irq <= 0) {
+		ret = irq;
+		goto out_clk_disable;
+	}
+
+	if (of_property_read_bool(pdev->dev.parent->of_node, "wakeup-source")) {
+		device_set_wakeup_capable(&pdev->dev, true);
+
+		ret = dev_pm_set_wake_irq(&pdev->dev, irq);
+		if (ret)
+			goto out_clk_disable;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, stm32_clkevent_lp_irq_handler,
+			       IRQF_TIMER, pdev->name, &priv->clkevt);
+	if (ret)
+		goto out_clk_disable;
+
+	stm32_clkevent_lp_set_prescaler(priv, &rate);
+
+	stm32_clkevent_lp_init(priv, pdev->dev.parent->of_node, rate);
+
+	priv->dev = &pdev->dev;
+
+	return 0;
+
+out_clk_disable:
+	clk_disable_unprepare(priv->clk);
+	return ret;
+}
+
+static const struct of_device_id stm32_clkevent_lp_of_match[] = {
+	{ .compatible = "st,stm32-lptimer-timer", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm32_clkevent_lp_of_match);
+
+static struct platform_driver stm32_clkevent_lp_driver = {
+	.probe  = stm32_clkevent_lp_probe,
+	.driver	= {
+		.name = "stm32-lptimer-timer",
+		.of_match_table = stm32_clkevent_lp_of_match,
+		.suppress_bind_attrs = true,
+	},
+};
+module_platform_driver(stm32_clkevent_lp_driver);
+
+MODULE_DESCRIPTION("STMicroelectronics STM32 clockevent low power driver");