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, 304 insertions, 0 deletions

diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
new file mode 100644
index 000000000..1501c7db9
--- /dev/null
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
+
+#define pr_fmt(fmt) "mips-gic-timer: " fmt
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/sched_clock.h>
+#include <linux/smp.h>
+#include <linux/time.h>
+#include <asm/mips-cps.h>
+
+static DEFINE_PER_CPU(struct clock_event_device, gic_clockevent_device);
+static int gic_timer_irq;
+static unsigned int gic_frequency;
+static unsigned int gic_count_width;
+static bool __read_mostly gic_clock_unstable;
+
+static void gic_clocksource_unstable(char *reason);
+
+static u64 notrace gic_read_count_2x32(void)
+{
+	unsigned int hi, hi2, lo;
+
+	do {
+		hi = read_gic_counter_32h();
+		lo = read_gic_counter_32l();
+		hi2 = read_gic_counter_32h();
+	} while (hi2 != hi);
+
+	return (((u64) hi) << 32) + lo;
+}
+
+static u64 notrace gic_read_count_64(void)
+{
+	return read_gic_counter();
+}
+
+static u64 notrace gic_read_count(void)
+{
+	if (mips_cm_is64)
+		return gic_read_count_64();
+
+	return gic_read_count_2x32();
+}
+
+static int gic_next_event(unsigned long delta, struct clock_event_device *evt)
+{
+	int cpu = cpumask_first(evt->cpumask);
+	u64 cnt;
+	int res;
+
+	cnt = gic_read_count();
+	cnt += (u64)delta;
+	if (cpu == raw_smp_processor_id()) {
+		write_gic_vl_compare(cnt);
+	} else {
+		write_gic_vl_other(mips_cm_vp_id(cpu));
+		write_gic_vo_compare(cnt);
+	}
+	res = ((int)(gic_read_count() - cnt) >= 0) ? -ETIME : 0;
+	return res;
+}
+
+static irqreturn_t gic_compare_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *cd = dev_id;
+
+	write_gic_vl_compare(read_gic_vl_compare());
+	cd->event_handler(cd);
+	return IRQ_HANDLED;
+}
+
+static void gic_clockevent_cpu_init(unsigned int cpu,
+				    struct clock_event_device *cd)
+{
+	cd->name		= "MIPS GIC";
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_C3STOP;
+
+	cd->rating		= 350;
+	cd->irq			= gic_timer_irq;
+	cd->cpumask		= cpumask_of(cpu);
+	cd->set_next_event	= gic_next_event;
+
+	clockevents_config_and_register(cd, gic_frequency, 0x300, 0x7fffffff);
+
+	enable_percpu_irq(gic_timer_irq, IRQ_TYPE_NONE);
+}
+
+static void gic_clockevent_cpu_exit(struct clock_event_device *cd)
+{
+	disable_percpu_irq(gic_timer_irq);
+}
+
+static void gic_update_frequency(void *data)
+{
+	unsigned long rate = (unsigned long)data;
+
+	clockevents_update_freq(this_cpu_ptr(&gic_clockevent_device), rate);
+}
+
+static int gic_starting_cpu(unsigned int cpu)
+{
+	/* Ensure the GIC counter is running */
+	clear_gic_config(GIC_CONFIG_COUNTSTOP);
+
+	gic_clockevent_cpu_init(cpu, this_cpu_ptr(&gic_clockevent_device));
+	return 0;
+}
+
+static int gic_clk_notifier(struct notifier_block *nb, unsigned long action,
+			    void *data)
+{
+	struct clk_notifier_data *cnd = data;
+
+	if (action == POST_RATE_CHANGE) {
+		gic_clocksource_unstable("ref clock rate change");
+		on_each_cpu(gic_update_frequency, (void *)cnd->new_rate, 1);
+	}
+
+	return NOTIFY_OK;
+}
+
+static int gic_dying_cpu(unsigned int cpu)
+{
+	gic_clockevent_cpu_exit(this_cpu_ptr(&gic_clockevent_device));
+	return 0;
+}
+
+static struct notifier_block gic_clk_nb = {
+	.notifier_call = gic_clk_notifier,
+};
+
+static int gic_clockevent_init(void)
+{
+	int ret;
+
+	if (!gic_frequency)
+		return -ENXIO;
+
+	ret = request_percpu_irq(gic_timer_irq, gic_compare_interrupt,
+				 "timer", &gic_clockevent_device);
+	if (ret < 0) {
+		pr_err("IRQ %d setup failed (%d)\n", gic_timer_irq, ret);
+		return ret;
+	}
+
+	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
+	return 0;
+}
+
+static u64 gic_hpt_read(struct clocksource *cs)
+{
+	return gic_read_count();
+}
+
+static u64 gic_hpt_read_multicluster(struct clocksource *cs)
+{
+	unsigned int hi, hi2, lo;
+	u64 count;
+
+	mips_cm_lock_other(0, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+
+	if (mips_cm_is64) {
+		count = read_gic_redir_counter();
+		goto out;
+	}
+
+	hi = read_gic_redir_counter_32h();
+	while (true) {
+		lo = read_gic_redir_counter_32l();
+
+		/* If hi didn't change then lo didn't wrap & we're done */
+		hi2 = read_gic_redir_counter_32h();
+		if (hi2 == hi)
+			break;
+
+		/* Otherwise, repeat with the latest hi value */
+		hi = hi2;
+	}
+
+	count = (((u64)hi) << 32) + lo;
+out:
+	mips_cm_unlock_other();
+	return count;
+}
+
+static struct clocksource gic_clocksource = {
+	.name			= "GIC",
+	.read			= gic_hpt_read,
+	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
+	.vdso_clock_mode	= VDSO_CLOCKMODE_GIC,
+};
+
+static void gic_clocksource_unstable(char *reason)
+{
+	if (gic_clock_unstable)
+		return;
+
+	gic_clock_unstable = true;
+
+	pr_info("GIC timer is unstable due to %s\n", reason);
+
+	clocksource_mark_unstable(&gic_clocksource);
+}
+
+static int __init __gic_clocksource_init(void)
+{
+	int ret;
+
+	/* Set clocksource mask. */
+	gic_count_width = read_gic_config() & GIC_CONFIG_COUNTBITS;
+	gic_count_width >>= __ffs(GIC_CONFIG_COUNTBITS);
+	gic_count_width *= 4;
+	gic_count_width += 32;
+	gic_clocksource.mask = CLOCKSOURCE_MASK(gic_count_width);
+
+	/* Calculate a somewhat reasonable rating value. */
+	if (mips_cm_revision() >= CM_REV_CM3 || !IS_ENABLED(CONFIG_CPU_FREQ))
+		gic_clocksource.rating = 300; /* Good when frequecy is stable */
+	else
+		gic_clocksource.rating = 200;
+	gic_clocksource.rating += clamp(gic_frequency / 10000000, 0, 99);
+
+	if (mips_cps_multicluster_cpus()) {
+		gic_clocksource.read = &gic_hpt_read_multicluster;
+		gic_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+	}
+
+	ret = clocksource_register_hz(&gic_clocksource, gic_frequency);
+	if (ret < 0)
+		pr_warn("Unable to register clocksource\n");
+
+	return ret;
+}
+
+static int __init gic_clocksource_of_init(struct device_node *node)
+{
+	struct clk *clk;
+	int ret;
+
+	if (!mips_gic_present() || !node->parent ||
+	    !of_device_is_compatible(node->parent, "mti,gic")) {
+		pr_warn("No DT definition\n");
+		return -ENXIO;
+	}
+
+	clk = of_clk_get(node, 0);
+	if (!IS_ERR(clk)) {
+		ret = clk_prepare_enable(clk);
+		if (ret < 0) {
+			pr_err("Failed to enable clock\n");
+			clk_put(clk);
+			return ret;
+		}
+
+		gic_frequency = clk_get_rate(clk);
+	} else if (of_property_read_u32(node, "clock-frequency",
+					&gic_frequency)) {
+		pr_err("Frequency not specified\n");
+		return -EINVAL;
+	}
+	gic_timer_irq = irq_of_parse_and_map(node, 0);
+	if (!gic_timer_irq) {
+		pr_err("IRQ not specified\n");
+		return -EINVAL;
+	}
+
+	ret = __gic_clocksource_init();
+	if (ret)
+		return ret;
+
+	ret = gic_clockevent_init();
+	if (!ret && !IS_ERR(clk)) {
+		if (clk_notifier_register(clk, &gic_clk_nb) < 0)
+			pr_warn("Unable to register clock notifier\n");
+	}
+
+	/*
+	 * It's safe to use the MIPS GIC timer as a sched clock source only if
+	 * its ticks are stable, which is true on either the platforms with
+	 * stable CPU frequency or on the platforms with CM3 and CPU frequency
+	 * change performed by the CPC core clocks divider.
+	 */
+	if ((mips_cm_revision() >= CM_REV_CM3 || !IS_ENABLED(CONFIG_CPU_FREQ)) &&
+	     !mips_cps_multicluster_cpus()) {
+		sched_clock_register(mips_cm_is64 ?
+				     gic_read_count_64 : gic_read_count_2x32,
+				     gic_count_width, gic_frequency);
+	}
+
+	return 0;
+}
+TIMER_OF_DECLARE(mips_gic_timer, "mti,gic-timer",
+		       gic_clocksource_of_init);