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/net/inet_common.h b/include/net/inet_common.h
new file mode 100644
index 000000000..3d747896b
--- /dev/null
+++ b/include/net/inet_common.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _INET_COMMON_H
+#define _INET_COMMON_H
+
+#include <linux/indirect_call_wrapper.h>
+#include <linux/net.h>
+#include <linux/netdev_features.h>
+#include <linux/types.h>
+#include <net/sock.h>
+
+extern const struct proto_ops inet_stream_ops;
+extern const struct proto_ops inet_dgram_ops;
+
+/*
+ *	INET4 prototypes used by INET6
+ */
+
+struct msghdr;
+struct net;
+struct page;
+struct sock;
+struct socket;
+
+int inet_release(struct socket *sock);
+int inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+			int addr_len, int flags);
+int __inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+			  int addr_len, int flags, int is_sendmsg);
+int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+		       int addr_len, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock,
+		struct proto_accept_arg *arg);
+void __inet_accept(struct socket *sock, struct socket *newsock,
+		   struct sock *newsk);
+int inet_send_prepare(struct sock *sk);
+int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
+void inet_splice_eof(struct socket *sock);
+int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags);
+int inet_shutdown(struct socket *sock, int how);
+int inet_listen(struct socket *sock, int backlog);
+int __inet_listen_sk(struct sock *sk, int backlog);
+void inet_sock_destruct(struct sock *sk);
+int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len);
+int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+/* Don't allocate port at this moment, defer to connect. */
+#define BIND_FORCE_ADDRESS_NO_PORT	(1 << 0)
+/* Grab and release socket lock. */
+#define BIND_WITH_LOCK			(1 << 1)
+/* Called from BPF program. */
+#define BIND_FROM_BPF			(1 << 2)
+/* Skip CAP_NET_BIND_SERVICE check. */
+#define BIND_NO_CAP_NET_BIND_SERVICE	(1 << 3)
+int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len,
+		u32 flags);
+int inet_getname(struct socket *sock, struct sockaddr *uaddr,
+		 int peer);
+int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+int inet_ctl_sock_create(struct sock **sk, unsigned short family,
+			 unsigned short type, unsigned char protocol,
+			 struct net *net);
+int inet_recv_error(struct sock *sk, struct msghdr *msg, int len);
+
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb);
+int inet_gro_complete(struct sk_buff *skb, int nhoff);
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features);
+
+static inline void inet_ctl_sock_destroy(struct sock *sk)
+{
+	if (sk)
+		sock_release(sk->sk_socket);
+}
+
+#define indirect_call_gro_receive(f2, f1, cb, head, skb)	\
+({								\
+	unlikely(gro_recursion_inc_test(skb)) ?			\
+		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
+		INDIRECT_CALL_2(cb, f2, f1, head, skb);		\
+})
+
+#endif