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, 230 insertions, 0 deletions

diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
new file mode 100644
index 000000000..79e067b51
--- /dev/null
+++ b/lib/generic-radix-tree.c
@@ -0,0 +1,230 @@
+
+#include <linux/atomic.h>
+#include <linux/export.h>
+#include <linux/generic-radix-tree.h>
+#include <linux/gfp.h>
+#include <linux/kmemleak.h>
+
+/*
+ * Returns pointer to the specified byte @offset within @radix, or NULL if not
+ * allocated
+ */
+void *__genradix_ptr(struct __genradix *radix, size_t offset)
+{
+	return __genradix_ptr_inlined(radix, offset);
+}
+EXPORT_SYMBOL(__genradix_ptr);
+
+/*
+ * Returns pointer to the specified byte @offset within @radix, allocating it if
+ * necessary - newly allocated slots are always zeroed out:
+ */
+void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
+			   struct genradix_node **preallocated,
+			   gfp_t gfp_mask)
+{
+	struct genradix_root *v = READ_ONCE(radix->root);
+	struct genradix_node *n, *new_node = NULL;
+	unsigned level;
+
+	if (preallocated)
+		swap(new_node, *preallocated);
+
+	/* Increase tree depth if necessary: */
+	while (1) {
+		struct genradix_root *r = v, *new_root;
+
+		n	= genradix_root_to_node(r);
+		level	= genradix_root_to_depth(r);
+
+		if (n && ilog2(offset) < genradix_depth_shift(level))
+			break;
+
+		if (!new_node) {
+			new_node = genradix_alloc_node(gfp_mask);
+			if (!new_node)
+				return NULL;
+		}
+
+		new_node->children[0] = n;
+		new_root = ((struct genradix_root *)
+			    ((unsigned long) new_node | (n ? level + 1 : 0)));
+
+		if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) {
+			v = new_root;
+			new_node = NULL;
+		} else {
+			new_node->children[0] = NULL;
+		}
+	}
+
+	while (level--) {
+		struct genradix_node **p =
+			&n->children[offset >> genradix_depth_shift(level)];
+		offset &= genradix_depth_size(level) - 1;
+
+		n = READ_ONCE(*p);
+		if (!n) {
+			if (!new_node) {
+				new_node = genradix_alloc_node(gfp_mask);
+				if (!new_node)
+					return NULL;
+			}
+
+			if (!(n = cmpxchg_release(p, NULL, new_node)))
+				swap(n, new_node);
+		}
+	}
+
+	if (new_node)
+		genradix_free_node(new_node);
+
+	return &n->data[offset];
+}
+EXPORT_SYMBOL(__genradix_ptr_alloc);
+
+void *__genradix_iter_peek(struct genradix_iter *iter,
+			   struct __genradix *radix,
+			   size_t objs_per_page)
+{
+	struct genradix_root *r;
+	struct genradix_node *n;
+	unsigned level, i;
+
+	if (iter->offset == SIZE_MAX)
+		return NULL;
+
+restart:
+	r = READ_ONCE(radix->root);
+	if (!r)
+		return NULL;
+
+	n	= genradix_root_to_node(r);
+	level	= genradix_root_to_depth(r);
+
+	if (ilog2(iter->offset) >= genradix_depth_shift(level))
+		return NULL;
+
+	while (level) {
+		level--;
+
+		i = (iter->offset >> genradix_depth_shift(level)) &
+			(GENRADIX_ARY - 1);
+
+		while (!n->children[i]) {
+			size_t objs_per_ptr = genradix_depth_size(level);
+
+			if (iter->offset + objs_per_ptr < iter->offset) {
+				iter->offset	= SIZE_MAX;
+				iter->pos	= SIZE_MAX;
+				return NULL;
+			}
+
+			i++;
+			iter->offset = round_down(iter->offset + objs_per_ptr,
+						  objs_per_ptr);
+			iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) *
+				objs_per_page;
+			if (i == GENRADIX_ARY)
+				goto restart;
+		}
+
+		n = n->children[i];
+	}
+
+	return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)];
+}
+EXPORT_SYMBOL(__genradix_iter_peek);
+
+void *__genradix_iter_peek_prev(struct genradix_iter *iter,
+				struct __genradix *radix,
+				size_t objs_per_page,
+				size_t obj_size_plus_page_remainder)
+{
+	struct genradix_root *r;
+	struct genradix_node *n;
+	unsigned level, i;
+
+	if (iter->offset == SIZE_MAX)
+		return NULL;
+
+restart:
+	r = READ_ONCE(radix->root);
+	if (!r)
+		return NULL;
+
+	n	= genradix_root_to_node(r);
+	level	= genradix_root_to_depth(r);
+
+	if (ilog2(iter->offset) >= genradix_depth_shift(level)) {
+		iter->offset = genradix_depth_size(level);
+		iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page;
+
+		iter->offset -= obj_size_plus_page_remainder;
+		iter->pos--;
+	}
+
+	while (level) {
+		level--;
+
+		i = (iter->offset >> genradix_depth_shift(level)) &
+			(GENRADIX_ARY - 1);
+
+		while (!n->children[i]) {
+			size_t objs_per_ptr = genradix_depth_size(level);
+
+			iter->offset = round_down(iter->offset, objs_per_ptr);
+			iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page;
+
+			if (!iter->offset)
+				return NULL;
+
+			iter->offset -= obj_size_plus_page_remainder;
+			iter->pos--;
+
+			if (!i)
+				goto restart;
+			--i;
+		}
+
+		n = n->children[i];
+	}
+
+	return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)];
+}
+EXPORT_SYMBOL(__genradix_iter_peek_prev);
+
+static void genradix_free_recurse(struct genradix_node *n, unsigned level)
+{
+	if (level) {
+		unsigned i;
+
+		for (i = 0; i < GENRADIX_ARY; i++)
+			if (n->children[i])
+				genradix_free_recurse(n->children[i], level - 1);
+	}
+
+	genradix_free_node(n);
+}
+
+int __genradix_prealloc(struct __genradix *radix, size_t size,
+			gfp_t gfp_mask)
+{
+	size_t offset;
+
+	for (offset = 0; offset < size; offset += GENRADIX_NODE_SIZE)
+		if (!__genradix_ptr_alloc(radix, offset, NULL, gfp_mask))
+			return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(__genradix_prealloc);
+
+void __genradix_free(struct __genradix *radix)
+{
+	struct genradix_root *r = xchg(&radix->root, NULL);
+
+	genradix_free_recurse(genradix_root_to_node(r),
+			      genradix_root_to_depth(r));
+}
+EXPORT_SYMBOL(__genradix_free);