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, 46 insertions, 0 deletions

diff --git a/include/hyperv/hvgdk_ext.h b/include/hyperv/hvgdk_ext.h
new file mode 100644
index 000000000..641b591ee
--- /dev/null
+++ b/include/hyperv/hvgdk_ext.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the Microsoft Hypervisor.
+ */
+#ifndef _HV_HVGDK_EXT_H
+#define _HV_HVGDK_EXT_H
+
+#include "hvgdk_mini.h"
+
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001
+#define HV_EXT_CALL_MEMORY_HEAT_HINT		0x8003
+
+/* Extended hypercalls */
+enum {		/* HV_EXT_CALL */
+	HV_EXTCALL_QUERY_CAPABILITIES = 0x8001,
+	HV_EXTCALL_MEMORY_HEAT_HINT   = 0x8003,
+};
+
+/* HV_EXT_OUTPUT_QUERY_CAPABILITIES */
+#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8)
+
+enum {		/* HV_EXT_MEMORY_HEAT_HINT_TYPE */
+	HV_EXTMEM_HEAT_HINT_COLD = 0,
+	HV_EXTMEM_HEAT_HINT_HOT = 1,
+	HV_EXTMEM_HEAT_HINT_COLD_DISCARD = 2,
+	HV_EXTMEM_HEAT_HINT_MAX
+};
+
+/*
+ * The whole argument should fit in a page to be able to pass to the hypervisor
+ * in one hypercall.
+ */
+#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES  \
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \
+		sizeof(union hv_gpa_page_range))
+
+/* HvExtCallMemoryHeatHint hypercall */
+#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD	2
+struct hv_memory_hint {		/* HV_EXT_INPUT_MEMORY_HEAT_HINT */
+	u64 heat_type : 2;	/* HV_EXTMEM_HEAT_HINT_* */
+	u64 reserved : 62;
+	union hv_gpa_page_range ranges[];
+} __packed;
+
+#endif /* _HV_HVGDK_EXT_H */