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>

2 files changed, 78 insertions, 0 deletions

diff --git a/include/uapi/misc/uacce/hisi_qm.h b/include/uapi/misc/uacce/hisi_qm.h
new file mode 100644
index 000000000..10504b48e
--- /dev/null
+++ b/include/uapi/misc/uacce/hisi_qm.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_HISI_QM_H
+#define _UAPI_HISI_QM_H
+
+#include <linux/types.h>
+
+/**
+ * struct hisi_qp_ctx - User data for hisi qp.
+ * @id: qp_index return to user space
+ * @qc_type: Accelerator algorithm type
+ */
+struct hisi_qp_ctx {
+	__u16 id;
+	__u16 qc_type;
+};
+
+/**
+ * struct hisi_qp_info - User data for hisi qp.
+ * @sqe_size: Submission queue element size
+ * @sq_depth: The number of sqe
+ * @cq_depth: The number of cqe
+ * @reserved: Reserved data
+ */
+struct hisi_qp_info {
+	__u32 sqe_size;
+	__u16 sq_depth;
+	__u16 cq_depth;
+	__u64 reserved;
+};
+
+#define HISI_QM_API_VER_BASE "hisi_qm_v1"
+#define HISI_QM_API_VER2_BASE "hisi_qm_v2"
+#define HISI_QM_API_VER3_BASE "hisi_qm_v3"
+#define HISI_QM_API_VER5_BASE "hisi_qm_v5"
+
+/* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */
+#define UACCE_CMD_QM_SET_QP_CTX	_IOWR('H', 10, struct hisi_qp_ctx)
+/* UACCE_CMD_QM_SET_QP_INFO: Set qp depth and BD size */
+#define UACCE_CMD_QM_SET_QP_INFO _IOWR('H', 11, struct hisi_qp_info)
+#endif
diff --git a/include/uapi/misc/uacce/uacce.h b/include/uapi/misc/uacce/uacce.h
new file mode 100644
index 000000000..cc7185678
--- /dev/null
+++ b/include/uapi/misc/uacce/uacce.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPIUUACCE_H
+#define _UAPIUUACCE_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * UACCE_CMD_START_Q: Start queue
+ */
+#define UACCE_CMD_START_Q	_IO('W', 0)
+
+/*
+ * UACCE_CMD_PUT_Q:
+ * User actively stop queue and free queue resource immediately
+ * Optimization method since close fd may delay
+ */
+#define UACCE_CMD_PUT_Q		_IO('W', 1)
+
+/*
+ * UACCE Device flags:
+ * UACCE_DEV_SVA: Shared Virtual Addresses
+ *		  Support PASID
+ *		  Support device page faults (PCI PRI or SMMU Stall)
+ */
+#define UACCE_DEV_SVA		BIT(0)
+
+/**
+ * enum uacce_qfrt: queue file region type
+ * @UACCE_QFRT_MMIO: device mmio region
+ * @UACCE_QFRT_DUS: device user share region
+ */
+enum uacce_qfrt {
+	UACCE_QFRT_MMIO = 0,
+	UACCE_QFRT_DUS = 1,
+};
+
+#endif