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, 49 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/msgbuf.h b/include/uapi/asm-generic/msgbuf.h
new file mode 100644
index 000000000..6504d7b74
--- /dev/null
+++ b/include/uapi/asm-generic/msgbuf.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MSGBUF_H
+#define __ASM_GENERIC_MSGBUF_H
+
+#include <asm/bitsperlong.h>
+#include <asm/ipcbuf.h>
+
+/*
+ * generic msqid64_ds structure.
+ *
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * msqid64_ds was originally meant to be architecture specific, but
+ * everyone just ended up making identical copies without specific
+ * optimizations, so we may just as well all use the same one.
+ *
+ * 64 bit architectures use a 64-bit long time field here, while
+ * 32 bit architectures have a pair of unsigned long values.
+ * On big-endian systems, the lower half is in the wrong place.
+ *
+ * Pad space is left for:
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+#if __BITS_PER_LONG == 64
+	long		 msg_stime;	/* last msgsnd time */
+	long		 msg_rtime;	/* last msgrcv time */
+	long		 msg_ctime;	/* last change time */
+#else
+	unsigned long	msg_stime;	/* last msgsnd time */
+	unsigned long	msg_stime_high;
+	unsigned long	msg_rtime;	/* last msgrcv time */
+	unsigned long	msg_rtime_high;
+	unsigned long	msg_ctime;	/* last change time */
+	unsigned long	msg_ctime_high;
+#endif
+	unsigned long	msg_cbytes;	/* current number of bytes on queue */
+	unsigned long	msg_qnum;	/* number of messages in queue */
+	unsigned long	 msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	unsigned long	 __unused4;
+	unsigned long	 __unused5;
+};
+
+#endif /* __ASM_GENERIC_MSGBUF_H */