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, 83 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
new file mode 100644
index 000000000..30e88fc1d
--- /dev/null
+++ b/include/asm-generic/pgtable_uffd.h
@@ -0,0 +1,83 @@
+#ifndef _ASM_GENERIC_PGTABLE_UFFD_H
+#define _ASM_GENERIC_PGTABLE_UFFD_H
+
+/*
+ * Some platforms can customize the uffd PTE bit, making it unavailable
+ * even if the architecture provides the resource.
+ * Adding this API allows architectures to add their own checks for the
+ * devices on which the kernel is running.
+ * Note: When overriding it, please make sure the
+ * CONFIG_HAVE_ARCH_USERFAULTFD_WP is part of this macro.
+ */
+#ifndef pgtable_supports_uffd
+#define pgtable_supports_uffd()	IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP)
+#endif
+
+static inline bool uffd_supports_wp_marker(void)
+{
+	return pgtable_supports_uffd() && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP);
+}
+
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static __always_inline int pte_uffd(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline int pmd_uffd(pmd_t pmd)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_mkuffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_mkuffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_clear_uffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_clear_uffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_swp_mkuffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline int pte_swp_uffd(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_swp_clear_uffd(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_swp_mkuffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline int pmd_swp_uffd(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pmd_t pmd_swp_clear_uffd(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
+#endif /* _ASM_GENERIC_PGTABLE_UFFD_H */