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, 127 insertions, 0 deletions

diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
new file mode 100644
index 000000000..7ee8a179d
--- /dev/null
+++ b/include/asm-generic/cacheflush.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_CACHEFLUSH_H
+#define _ASM_GENERIC_CACHEFLUSH_H
+
+#include <linux/instrumented.h>
+
+struct mm_struct;
+struct vm_area_struct;
+struct page;
+struct address_space;
+
+/*
+ * The cache doesn't need to be flushed when TLB entries change when
+ * the cache is mapped to physical memory, not virtual memory
+ */
+#ifndef flush_cache_all
+static inline void flush_cache_all(void)
+{
+}
+#endif
+
+#ifndef flush_cache_mm
+static inline void flush_cache_mm(struct mm_struct *mm)
+{
+}
+#endif
+
+#ifndef flush_cache_dup_mm
+static inline void flush_cache_dup_mm(struct mm_struct *mm)
+{
+}
+#endif
+
+#ifndef flush_cache_range
+static inline void flush_cache_range(struct vm_area_struct *vma,
+				     unsigned long start,
+				     unsigned long end)
+{
+}
+#endif
+
+#ifndef flush_cache_page
+static inline void flush_cache_page(struct vm_area_struct *vma,
+				    unsigned long vmaddr,
+				    unsigned long pfn)
+{
+}
+#endif
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+static inline void flush_dcache_page(struct page *page)
+{
+}
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#endif
+
+#ifndef flush_dcache_mmap_lock
+static inline void flush_dcache_mmap_lock(struct address_space *mapping)
+{
+}
+#endif
+
+#ifndef flush_dcache_mmap_unlock
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
+{
+}
+#endif
+
+#ifndef flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+#ifndef flush_icache_user_range
+#define flush_icache_user_range flush_icache_range
+#endif
+
+#ifndef flush_icache_user_page
+static inline void flush_icache_user_page(struct vm_area_struct *vma,
+					   struct page *page,
+					   unsigned long addr, int len)
+{
+}
+#endif
+
+#ifndef flush_cache_vmap
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+#ifndef flush_cache_vmap_early
+static inline void flush_cache_vmap_early(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+#ifndef flush_cache_vunmap
+static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+#ifndef copy_to_user_page
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
+	do { \
+		instrument_copy_to_user((void __user *)dst, src, len); \
+		memcpy(dst, src, len); \
+		flush_icache_user_page(vma, page, vaddr, len); \
+	} while (0)
+#endif
+
+
+#ifndef copy_from_user_page
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)		  \
+	do {								  \
+		instrument_copy_from_user_before(dst, (void __user *)src, \
+						 len);			  \
+		memcpy(dst, src, len);					  \
+		instrument_copy_from_user_after(dst, (void __user *)src, len, \
+						0);			  \
+	} while (0)
+#endif
+
+#endif /* _ASM_GENERIC_CACHEFLUSH_H */