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, 310 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-lpc32xx.c b/drivers/clocksource/timer-lpc32xx.c
new file mode 100644
index 000000000..68eae6378
--- /dev/null
+++ b/drivers/clocksource/timer-lpc32xx.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clocksource driver for NXP LPC32xx/18xx/43xx timer
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on:
+ * time-efm32 Copyright (C) 2013 Pengutronix
+ * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+#define LPC32XX_TIMER_IR		0x000
+#define  LPC32XX_TIMER_IR_MR0INT	BIT(0)
+#define LPC32XX_TIMER_TCR		0x004
+#define  LPC32XX_TIMER_TCR_CEN		BIT(0)
+#define  LPC32XX_TIMER_TCR_CRST		BIT(1)
+#define LPC32XX_TIMER_TC		0x008
+#define LPC32XX_TIMER_PR		0x00c
+#define LPC32XX_TIMER_MCR		0x014
+#define  LPC32XX_TIMER_MCR_MR0I		BIT(0)
+#define  LPC32XX_TIMER_MCR_MR0R		BIT(1)
+#define  LPC32XX_TIMER_MCR_MR0S		BIT(2)
+#define LPC32XX_TIMER_MR0		0x018
+#define LPC32XX_TIMER_CTCR		0x070
+
+struct lpc32xx_clock_event_ddata {
+	struct clock_event_device evtdev;
+	void __iomem *base;
+	u32 ticks_per_jiffy;
+};
+
+/* Needed for the sched clock */
+static void __iomem *clocksource_timer_counter;
+
+static u64 notrace lpc32xx_read_sched_clock(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static unsigned long lpc32xx_delay_timer_read(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static struct delay_timer lpc32xx_delay_timer = {
+	.read_current_timer = lpc32xx_delay_timer_read,
+};
+
+static int lpc32xx_clkevt_next_event(unsigned long delta,
+				     struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/*
+	 * Place timer in reset and program the delta in the match
+	 * channel 0 (MR0). When the timer counter matches the value
+	 * in MR0 register the match will trigger an interrupt.
+	 * After setup the timer is released from reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Disable the timer */
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/*
+	 * When using oneshot, we must also disable the timer
+	 * to wait for the first call to set_next_event().
+	 */
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	/* Enable interrupt, reset on match and stop on match (MCR). */
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+		       LPC32XX_TIMER_MCR_MR0S, ddata->base + LPC32XX_TIMER_MCR);
+	return 0;
+}
+
+static int lpc32xx_clkevt_periodic(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Enable interrupt and reset on match. */
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R,
+		       ddata->base + LPC32XX_TIMER_MCR);
+
+	/*
+	 * Place timer in reset and program the delta in the match
+	 * channel 0 (MR0).
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(ddata->ticks_per_jiffy, ddata->base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
+{
+	struct lpc32xx_clock_event_ddata *ddata = dev_id;
+
+	/* Clear match on channel 0 */
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, ddata->base + LPC32XX_TIMER_IR);
+
+	ddata->evtdev.event_handler(&ddata->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
+	.evtdev = {
+		.name			= "lpc3220 clockevent",
+		.features		= CLOCK_EVT_FEAT_ONESHOT |
+					  CLOCK_EVT_FEAT_PERIODIC,
+		.rating			= 300,
+		.set_next_event		= lpc32xx_clkevt_next_event,
+		.set_state_shutdown	= lpc32xx_clkevt_shutdown,
+		.set_state_oneshot	= lpc32xx_clkevt_oneshot,
+		.set_state_periodic	= lpc32xx_clkevt_periodic,
+	},
+};
+
+static int __init lpc32xx_clocksource_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%ld)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	/*
+	 * Disable and reset timer then set it to free running timer
+	 * mode (CTCR) with no prescaler (PR) or match operations (MCR).
+	 * After setup the timer is released from reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
+	writel_relaxed(0, base + LPC32XX_TIMER_MCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, base + LPC32XX_TIMER_TCR);
+
+	rate = clk_get_rate(clk);
+	ret = clocksource_mmio_init(base + LPC32XX_TIMER_TC, "lpc3220 timer",
+				    rate, 300, 32, clocksource_mmio_readl_up);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		goto err_clocksource_init;
+	}
+
+	clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+	lpc32xx_delay_timer.freq = rate;
+	register_current_timer_delay(&lpc32xx_delay_timer);
+	sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
+
+	return 0;
+
+err_clocksource_init:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+static int __init lpc32xx_clockevent_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret, irq;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%ld)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("get irq failed\n");
+		ret = -ENOENT;
+		goto err_irq;
+	}
+
+	/*
+	 * Disable timer and clear any pending interrupt (IR) on match
+	 * channel 0 (MR0). Clear the prescaler as it's not used.
+	 */
+	writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
+
+	rate = clk_get_rate(clk);
+	lpc32xx_clk_event_ddata.base = base;
+	lpc32xx_clk_event_ddata.ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ);
+	clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
+					rate, 1, -1);
+
+	ret = request_irq(irq, lpc32xx_clock_event_handler,
+			  IRQF_TIMER | IRQF_IRQPOLL, "lpc3220 clockevent",
+			  &lpc32xx_clk_event_ddata);
+	if (ret) {
+		pr_err("request irq failed\n");
+		goto err_irq;
+	}
+
+	return 0;
+
+err_irq:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+/*
+ * This function asserts that we have exactly one clocksource and one
+ * clock_event_device in the end.
+ */
+static int __init lpc32xx_timer_init(struct device_node *np)
+{
+	static int has_clocksource, has_clockevent;
+	int ret = 0;
+
+	if (!has_clocksource) {
+		ret = lpc32xx_clocksource_init(np);
+		if (!ret) {
+			has_clocksource = 1;
+			return 0;
+		}
+	}
+
+	if (!has_clockevent) {
+		ret = lpc32xx_clockevent_init(np);
+		if (!ret) {
+			has_clockevent = 1;
+			return 0;
+		}
+	}
+
+	return ret;
+}
+TIMER_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init);