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, 87 insertions, 0 deletions

diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h
new file mode 100644
index 000000000..03b0ec7af
--- /dev/null
+++ b/include/asm-generic/delay.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_DELAY_H
+#define __ASM_GENERIC_DELAY_H
+
+#include <linux/math.h>
+#include <vdso/time64.h>
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/*
+ * The microseconds/nanosecond delay multiplicators are used to convert a
+ * constant microseconds/nanoseconds value to a value which can be used by the
+ * architectures specific implementation to transform it into loops.
+ */
+#define UDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, USEC_PER_SEC))
+#define NDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, NSEC_PER_SEC))
+
+/*
+ * The maximum constant udelay/ndelay value picked out of thin air to prevent
+ * too long constant udelays/ndelays.
+ */
+#define DELAY_CONST_MAX   20000
+
+/**
+ * udelay - Inserting a delay based on microseconds with busy waiting
+ * @usec:	requested delay in microseconds
+ *
+ * When delaying in an atomic context ndelay(), udelay() and mdelay() are the
+ * only valid variants of delaying/sleeping to go with.
+ *
+ * When inserting delays in non atomic context which are shorter than the time
+ * which is required to queue e.g. an hrtimer and to enter then the scheduler,
+ * it is also valuable to use udelay(). But it is not simple to specify a
+ * generic threshold for this which will fit for all systems. An approximation
+ * is a threshold for all delays up to 10 microseconds.
+ *
+ * When having a delay which is larger than the architecture specific
+ * %MAX_UDELAY_MS value, please make sure mdelay() is used. Otherwise a overflow
+ * risk is given.
+ *
+ * Please note that ndelay(), udelay() and mdelay() may return early for several
+ * reasons (https://lists.openwall.net/linux-kernel/2011/01/09/56):
+ *
+ * #. computed loops_per_jiffy too low (due to the time taken to execute the
+ *    timer interrupt.)
+ * #. cache behaviour affecting the time it takes to execute the loop function.
+ * #. CPU clock rate changes.
+ */
+static __always_inline void udelay(unsigned long usec)
+{
+	if (__builtin_constant_p(usec)) {
+		if (usec >= DELAY_CONST_MAX)
+			__bad_udelay();
+		else
+			__const_udelay(usec * UDELAY_CONST_MULT);
+	} else {
+		__udelay(usec);
+	}
+}
+
+/**
+ * ndelay - Inserting a delay based on nanoseconds with busy waiting
+ * @nsec:	requested delay in nanoseconds
+ *
+ * See udelay() for basic information about ndelay() and it's variants.
+ */
+static __always_inline void ndelay(unsigned long nsec)
+{
+	if (__builtin_constant_p(nsec)) {
+		if (nsec >= DELAY_CONST_MAX)
+			__bad_ndelay();
+		else
+			__const_udelay(nsec * NDELAY_CONST_MULT);
+	} else {
+		__ndelay(nsec);
+	}
+}
+#define ndelay(x) ndelay(x)
+
+#endif /* __ASM_GENERIC_DELAY_H */