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, 82 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
new file mode 100644
index 000000000..ffb73b612
--- /dev/null
+++ b/include/asm-generic/bitops/lock.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
+#define _ASM_GENERIC_BITOPS_LOCK_H_
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics if
+ * the returned value is 0.
+ * It can be used to implement bit locks.
+ */
+static __always_inline int
+arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *addr)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	addr += BIT_WORD(nr);
+	if (READ_ONCE(*addr) & mask)
+		return 1;
+
+	old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)addr);
+	return !!(old & mask);
+}
+
+
+/**
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static __always_inline void
+arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	addr += BIT_WORD(nr);
+	raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)addr);
+}
+
+/**
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
+ * the bits in the word are protected by this lock some archs can use weaker
+ * ops to safely unlock.
+ *
+ * See for example x86's implementation.
+ */
+static inline void
+arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	unsigned long old;
+
+	addr += BIT_WORD(nr);
+	old = READ_ONCE(*addr);
+	old &= ~BIT_MASK(nr);
+	raw_atomic_long_set_release((atomic_long_t *)addr, old);
+}
+
+#ifndef arch_xor_unlock_is_negative_byte
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	long old;
+
+	old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#endif
+
+#include <asm-generic/bitops/instrumented-lock.h>
+
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */