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, 85 insertions, 0 deletions

diff --git a/include/net/ping.h b/include/net/ping.h
new file mode 100644
index 000000000..bcbdb5a13
--- /dev/null
+++ b/include/net/ping.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions for the "ping" module.
+ */
+#ifndef _PING_H
+#define _PING_H
+
+#include <net/icmp.h>
+#include <net/netns/hash.h>
+
+/* PING_HTABLE_SIZE must be power of 2 */
+#define PING_HTABLE_SIZE 	64
+#define PING_HTABLE_MASK 	(PING_HTABLE_SIZE-1)
+
+#define GID_T_MAX (((gid_t)~0U) - 1)
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	void (*ip6_datagram_recv_common_ctl)(struct sock *sk,
+					     struct msghdr *msg,
+					     struct sk_buff *skb);
+	void (*ip6_datagram_recv_specific_ctl)(struct sock *sk,
+					       struct msghdr *msg,
+					       struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     const struct net_device *dev, int strict);
+};
+
+struct ping_iter_state {
+	struct seq_net_private  p;
+	int			bucket;
+	sa_family_t		family;
+};
+
+extern struct proto ping_prot;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct msghdr *msg;
+	sa_family_t family;
+	__wsum wcheck;
+};
+
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		  int flags);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void ping_seq_stop(struct seq_file *seq, void *v);
+
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
+#endif
+
+void __init ping_init(void);
+int  __init pingv6_init(void);
+void pingv6_exit(void);
+
+#endif /* _PING_H */