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, 73 insertions, 0 deletions

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
new file mode 100644
index 000000000..3a9001a04
--- /dev/null
+++ b/include/net/dst_ops.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_DST_OPS_H
+#define _NET_DST_OPS_H
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/cache.h>
+
+struct dst_entry;
+struct kmem_cachep;
+struct net_device;
+struct sk_buff;
+struct sock;
+struct net;
+
+struct dst_ops {
+	unsigned short		family;
+	unsigned int		gc_thresh;
+
+	void			(*gc)(struct dst_ops *ops);
+	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
+	unsigned int		(*default_advmss)(const struct dst_entry *);
+	unsigned int		(*mtu)(const struct dst_entry *);
+	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
+	void			(*destroy)(struct dst_entry *);
+	void			(*ifdown)(struct dst_entry *,
+					  struct net_device *dev);
+	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
+	void			(*link_failure)(struct sk_buff *);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
+	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
+						struct sk_buff *skb,
+						const void *daddr);
+	void			(*confirm_neigh)(const struct dst_entry *dst,
+						 const void *daddr);
+
+	struct kmem_cache	*kmem_cachep;
+
+	struct percpu_counter	pcpuc_entries ____cacheline_aligned_in_smp;
+};
+
+static inline int dst_entries_get_fast(struct dst_ops *dst)
+{
+	return percpu_counter_read_positive(&dst->pcpuc_entries);
+}
+
+static inline int dst_entries_get_slow(struct dst_ops *dst)
+{
+	return percpu_counter_sum_positive(&dst->pcpuc_entries);
+}
+
+#define DST_PERCPU_COUNTER_BATCH 32
+static inline void dst_entries_add(struct dst_ops *dst, int val)
+{
+	percpu_counter_add_batch(&dst->pcpuc_entries, val,
+				 DST_PERCPU_COUNTER_BATCH);
+}
+
+static inline int dst_entries_init(struct dst_ops *dst)
+{
+	return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
+}
+
+static inline void dst_entries_destroy(struct dst_ops *dst)
+{
+	percpu_counter_destroy(&dst->pcpuc_entries);
+}
+
+#endif