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, 159 insertions, 0 deletions

diff --git a/include/net/net_debug.h b/include/net/net_debug.h
new file mode 100644
index 000000000..47f7a4a87
--- /dev/null
+++ b/include/net/net_debug.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NET_DEBUG_H
+#define _LINUX_NET_DEBUG_H
+
+#include <linux/bug.h>
+#include <linux/kern_levels.h>
+
+struct net_device;
+
+__printf(3, 4) __cold
+void netdev_printk(const char *level, const struct net_device *dev,
+		   const char *format, ...);
+__printf(2, 3) __cold
+void netdev_emerg(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_alert(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_crit(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_err(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_warn(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_notice(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_info(const struct net_device *dev, const char *format, ...);
+
+#define netdev_level_once(level, dev, fmt, ...)			\
+do {								\
+	static bool __section(".data..once") __print_once;	\
+								\
+	if (!__print_once) {					\
+		__print_once = true;				\
+		netdev_printk(level, dev, fmt, ##__VA_ARGS__);	\
+	}							\
+} while (0)
+
+#define netdev_emerg_once(dev, fmt, ...) \
+	netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
+#define netdev_alert_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
+#define netdev_crit_once(dev, fmt, ...) \
+	netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
+#define netdev_err_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
+#define netdev_warn_once(dev, fmt, ...) \
+	netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
+#define netdev_notice_once(dev, fmt, ...) \
+	netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
+#define netdev_info_once(dev, fmt, ...) \
+	netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netdev_dbg(__dev, format, args...)			\
+do {								\
+	dynamic_netdev_dbg(__dev, format, ##args);		\
+} while (0)
+#elif defined(DEBUG)
+#define netdev_dbg(__dev, format, args...)			\
+	netdev_printk(KERN_DEBUG, __dev, format, ##args)
+#else
+#define netdev_dbg(__dev, format, args...)			\
+({								\
+	if (0)							\
+		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
+})
+#endif
+
+#if defined(VERBOSE_DEBUG)
+#define netdev_vdbg	netdev_dbg
+#else
+
+#define netdev_vdbg(dev, format, args...)			\
+({								\
+	if (0)							\
+		netdev_printk(KERN_DEBUG, dev, format, ##args);	\
+	0;							\
+})
+#endif
+
+/* netif printk helpers, similar to netdev_printk */
+
+#define netif_printk(priv, type, level, dev, fmt, args...)	\
+do {					  			\
+	if (netif_msg_##type(priv))				\
+		netdev_printk(level, (dev), fmt, ##args);	\
+} while (0)
+
+#define netif_level(level, priv, type, dev, fmt, args...)	\
+do {								\
+	if (netif_msg_##type(priv))				\
+		netdev_##level(dev, fmt, ##args);		\
+} while (0)
+
+#define netif_emerg(priv, type, dev, fmt, args...)		\
+	netif_level(emerg, priv, type, dev, fmt, ##args)
+#define netif_alert(priv, type, dev, fmt, args...)		\
+	netif_level(alert, priv, type, dev, fmt, ##args)
+#define netif_crit(priv, type, dev, fmt, args...)		\
+	netif_level(crit, priv, type, dev, fmt, ##args)
+#define netif_err(priv, type, dev, fmt, args...)		\
+	netif_level(err, priv, type, dev, fmt, ##args)
+#define netif_warn(priv, type, dev, fmt, args...)		\
+	netif_level(warn, priv, type, dev, fmt, ##args)
+#define netif_notice(priv, type, dev, fmt, args...)		\
+	netif_level(notice, priv, type, dev, fmt, ##args)
+#define netif_info(priv, type, dev, fmt, args...)		\
+	netif_level(info, priv, type, dev, fmt, ##args)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netif_dbg(priv, type, netdev, format, args...)		\
+do {								\
+	if (netif_msg_##type(priv))				\
+		dynamic_netdev_dbg(netdev, format, ##args);	\
+} while (0)
+#elif defined(DEBUG)
+#define netif_dbg(priv, type, dev, format, args...)		\
+	netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
+#else
+#define netif_dbg(priv, type, dev, format, args...)			\
+({									\
+	if (0)								\
+		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+	0;								\
+})
+#endif
+
+/* if @cond then downgrade to debug, else print at @level */
+#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...)     \
+	do {                                                              \
+		if (cond)                                                 \
+			netif_dbg(priv, type, netdev, fmt, ##args);       \
+		else                                                      \
+			netif_ ## level(priv, type, netdev, fmt, ##args); \
+	} while (0)
+
+#if defined(VERBOSE_DEBUG)
+#define netif_vdbg	netif_dbg
+#else
+#define netif_vdbg(priv, type, dev, format, args...)		\
+({								\
+	if (0)							\
+		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+	0;							\
+})
+#endif
+
+
+#if defined(CONFIG_DEBUG_NET)
+#define DEBUG_NET_WARN_ON_ONCE(cond) ((void)WARN_ON_ONCE(cond))
+#define DEBUG_NET_WARN_ONCE(cond, format...) ((void)WARN_ONCE(cond, format))
+#else
+#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define DEBUG_NET_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
+#endif
+
+#endif	/* _LINUX_NET_DEBUG_H */