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, 175 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
new file mode 100644
index 000000000..564a8c675
--- /dev/null
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
+#define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
+
+#include <linux/bits.h>
+#include <asm/barrier.h>
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+/*
+ * Generic definitions for bit operations, should not be used in regular code
+ * directly.
+ */
+
+/**
+ * generic___set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+generic___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static __always_inline void
+generic___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * generic___change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+generic___change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * generic___test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * generic___test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __always_inline bool
+generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * generic_test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	/*
+	 * Unlike the bitops with the '__' prefix above, this one *is* atomic,
+	 * so `volatile` must always stay here with no cast-aways. See
+	 * `Documentation/atomic_bitops.txt` for the details.
+	 */
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/**
+ * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
+/*
+ * const_*() definitions provide good compile-time optimizations when
+ * the passed arguments can be resolved at compile time.
+ */
+#define const___set_bit			generic___set_bit
+#define const___clear_bit		generic___clear_bit
+#define const___change_bit		generic___change_bit
+#define const___test_and_set_bit	generic___test_and_set_bit
+#define const___test_and_clear_bit	generic___test_and_clear_bit
+#define const___test_and_change_bit	generic___test_and_change_bit
+#define const_test_bit_acquire		generic_test_bit_acquire
+
+/**
+ * const_test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ *
+ * A version of generic_test_bit() which discards the `volatile` qualifier to
+ * allow a compiler to optimize code harder. Non-atomic and to be called only
+ * for testing compile-time constants, e.g. by the corresponding macros, not
+ * directly from "regular" code.
+ */
+static __always_inline bool
+const_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr);
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long val = *p;
+
+	return !!(val & mask);
+}
+
+#endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */