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, 64 insertions, 0 deletions

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
new file mode 100644
index 000000000..bb1b3dee0
--- /dev/null
+++ b/include/net/af_unix.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_NET_AFUNIX_H
+#define __LINUX_NET_AFUNIX_H
+
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/net.h>
+#include <linux/path.h>
+#include <linux/refcount.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <net/sock.h>
+#include <uapi/linux/un.h>
+
+#if IS_ENABLED(CONFIG_UNIX)
+struct unix_sock *unix_get_socket(struct file *filp);
+#else
+static inline struct unix_sock *unix_get_socket(struct file *filp)
+{
+	return NULL;
+}
+#endif
+
+struct unix_address {
+	refcount_t	refcnt;
+	int		len;
+	struct sockaddr_un name[];
+};
+
+struct scm_stat {
+	atomic_t nr_fds;
+	unsigned long nr_unix_fds;
+};
+
+/* The AF_UNIX socket */
+struct unix_sock {
+	/* WARNING: sk has to be the first member */
+	struct sock		sk;
+	struct unix_address	*addr;
+	struct path		path;
+	struct mutex		iolock, bindlock;
+	struct sock		*peer;
+	struct sock		*listener;
+	struct unix_vertex	*vertex;
+	spinlock_t		lock;
+	struct socket_wq	peer_wq;
+#define peer_wait		peer_wq.wait
+	wait_queue_entry_t	peer_wake;
+	struct scm_stat		scm_stat;
+	int			inq_len;
+	bool			recvmsg_inq;
+	bool			scm_rights_notrunc;
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	struct sk_buff		*oob_skb;
+#endif
+};
+
+#define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
+
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+
+#endif