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, 154 insertions, 0 deletions

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
new file mode 100644
index 000000000..414e9adf4
--- /dev/null
+++ b/include/net/inetpeer.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *		INETPEER - A storage for permanent information about peers
+ *
+ *  Authors:	Andrey V. Savochkin <saw@msu.ru>
+ */
+
+#ifndef _NET_INETPEER_H
+#define _NET_INETPEER_H
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/spinlock.h>
+#include <linux/rtnetlink.h>
+#include <net/ipv6.h>
+#include <linux/atomic.h>
+
+/* IPv4 address key for cache lookups */
+struct ipv4_addr_key {
+	__be32	addr;
+	int	vif;
+};
+
+#define INETPEER_MAXKEYSZ   (sizeof(struct in6_addr) / sizeof(u32))
+
+struct inetpeer_addr {
+	union {
+		struct ipv4_addr_key	a4;
+		struct in6_addr		a6;
+		u32			key[INETPEER_MAXKEYSZ];
+	};
+	__u16				family;
+};
+
+struct inet_peer {
+	struct rb_node		rb_node;
+	u64			hash;
+	struct inetpeer_addr	daddr;
+
+	u32			metrics[RTAX_MAX];
+	u32			rate_tokens;	/* rate limiting for ICMP */
+	u32			n_redirects;
+	unsigned long		rate_last;
+	/*
+	 * Once inet_peer is queued for deletion (refcnt == 0), following field
+	 * is not available: rid
+	 * We can share memory with rcu_head to help keep inet_peer small.
+	 */
+	union {
+		struct {
+			atomic_t			rid;		/* Frag reception counter */
+		};
+		struct rcu_head         rcu;
+	};
+
+	/* following fields might be frequently dirtied */
+	__u32			dtime;	/* the time of last use of not referenced entries */
+	refcount_t		refcnt;
+};
+
+struct inet_peer_base {
+	struct rb_root		rb_root;
+	seqlock_t		lock;
+	int			total;
+};
+
+void inet_peer_base_init(struct inet_peer_base *);
+
+void inet_initpeers(void) __init;
+
+#define INETPEER_METRICS_NEW	(~(u32) 0)
+
+static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
+{
+	iaddr->a4.addr = ip;
+	iaddr->a4.vif = 0;
+	iaddr->family = AF_INET;
+}
+
+static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
+{
+	return iaddr->a4.addr;
+}
+
+static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
+					struct in6_addr *in6)
+{
+	iaddr->a6 = *in6;
+	iaddr->family = AF_INET6;
+}
+
+static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
+{
+	return &iaddr->a6;
+}
+
+/* can be called with or without local BH being disabled */
+struct inet_peer *inet_getpeer(struct inet_peer_base *base,
+			       const struct inetpeer_addr *daddr);
+
+static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
+						__be32 v4daddr,
+						int vif)
+{
+	struct inetpeer_addr daddr;
+
+	daddr.a4.addr = v4daddr;
+	daddr.a4.vif = vif;
+	daddr.family = AF_INET;
+	return inet_getpeer(base, &daddr);
+}
+
+static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
+						const struct in6_addr *v6daddr)
+{
+	struct inetpeer_addr daddr;
+
+	daddr.a6 = *v6daddr;
+	daddr.family = AF_INET6;
+	return inet_getpeer(base, &daddr);
+}
+
+static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
+				    const struct inetpeer_addr *b)
+{
+	int i, n;
+
+	if (a->family != b->family)
+		return a->family < b->family ? -1 : 1;
+
+	if (a->family == AF_INET)
+		n = sizeof(a->a4) / sizeof(u32);
+	else
+		n = sizeof(a->a6) / sizeof(u32);
+
+	for (i = 0; i < n; i++) {
+		if (a->key[i] == b->key[i])
+			continue;
+		if (a->key[i] < b->key[i])
+			return -1;
+		return 1;
+	}
+
+	return 0;
+}
+
+/* can be called from BH context or outside */
+void inet_putpeer(struct inet_peer *p);
+bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
+
+void inetpeer_invalidate_tree(struct inet_peer_base *);
+
+#endif /* _NET_INETPEER_H */