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, 65 insertions, 0 deletions

diff --git a/fs/pnode.h b/fs/pnode.h
new file mode 100644
index 000000000..b029db225
--- /dev/null
+++ b/fs/pnode.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/fs/pnode.h
+ *
+ * (C) Copyright IBM Corporation 2005.
+ */
+#ifndef _LINUX_PNODE_H
+#define _LINUX_PNODE_H
+
+#include <linux/list.h>
+#include "mount.h"
+
+#define IS_MNT_SHARED(m) ((m)->mnt_t_flags & T_SHARED)
+#define IS_MNT_SLAVE(m) ((m)->mnt_master)
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
+#define CLEAR_MNT_SHARED(m) ((m)->mnt_t_flags &= ~T_SHARED)
+#define IS_MNT_UNBINDABLE(m) ((m)->mnt_t_flags & T_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt_t_flags & T_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt_t_flags |= T_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt_t_flags &= ~T_MARKED)
+#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
+
+#define CL_EXPIRE    		0x01
+#define CL_SLAVE     		0x02
+#define CL_COPY_UNBINDABLE	0x04
+#define CL_MAKE_SHARED 		0x08
+#define CL_PRIVATE 		0x10
+#define CL_COPY_MNT_NS_FILE	0x40
+
+/*
+ * EXCL[namespace_sem]
+ */
+static inline void set_mnt_shared(struct mount *mnt)
+{
+	mnt->mnt_t_flags &= ~T_SHARED_MASK;
+	mnt->mnt_t_flags |= T_SHARED;
+}
+
+static inline bool peers(const struct mount *m1, const struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
+void change_mnt_propagation(struct mount *, int);
+void bulk_make_private(struct list_head *);
+int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
+		struct hlist_head *);
+void propagate_umount(struct list_head *);
+int propagate_mount_busy(struct mount *, int);
+void propagate_mount_unlock(struct mount *);
+void mnt_release_group_id(struct mount *);
+int get_dominating_id(struct mount *mnt, const struct path *root);
+int mnt_get_count(struct mount *mnt);
+void mnt_set_mountpoint(struct mount *, struct mountpoint *,
+			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
+struct mount *copy_tree(struct mount *, struct dentry *, int);
+bool is_path_reachable(struct mount *, struct dentry *,
+			 const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
+bool propagation_would_overmount(const struct mount *from,
+				 const struct mount *to,
+				 const struct mountpoint *mp);
+#endif /* _LINUX_PNODE_H */