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, 141 insertions, 0 deletions

diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
new file mode 100644
index 000000000..a676084be
--- /dev/null
+++ b/fs/squashfs/decompressor.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * decompressor.c
+ */
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+#include "page_actor.h"
+
+/*
+ * This file (and decompressor.h) implements a decompressor framework for
+ * Squashfs, allowing multiple decompressors to be easily supported
+ */
+
+static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
+	NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
+};
+
+#ifndef CONFIG_SQUASHFS_LZ4
+static const struct squashfs_decompressor squashfs_lz4_comp_ops = {
+	NULL, NULL, NULL, NULL, LZ4_COMPRESSION, "lz4", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_LZO
+static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
+	NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_XZ
+static const struct squashfs_decompressor squashfs_xz_comp_ops = {
+	NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_ZLIB
+static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
+	NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_ZSTD
+static const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0
+};
+#endif
+
+static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
+	NULL, NULL, NULL, NULL, 0, "unknown", 0
+};
+
+static const struct squashfs_decompressor *decompressor[] = {
+	&squashfs_zlib_comp_ops,
+	&squashfs_lz4_comp_ops,
+	&squashfs_lzo_comp_ops,
+	&squashfs_xz_comp_ops,
+	&squashfs_lzma_unsupported_comp_ops,
+	&squashfs_zstd_comp_ops,
+	&squashfs_unknown_comp_ops
+};
+
+
+const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
+{
+	int i;
+
+	for (i = 0; decompressor[i]->id; i++)
+		if (id == decompressor[i]->id)
+			break;
+
+	return decompressor[i];
+}
+
+
+static void *get_comp_opts(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *buffer = NULL, *comp_opts;
+	struct squashfs_page_actor *actor = NULL;
+	int length = 0;
+
+	/*
+	 * Read decompressor specific options from file system if present
+	 */
+	if (SQUASHFS_COMP_OPTS(flags)) {
+		buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (buffer == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		actor = squashfs_page_actor_init(&buffer, 1, 0);
+		if (actor == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		length = squashfs_read_data(sb,
+			sizeof(struct squashfs_super_block), 0, NULL, actor);
+
+		if (length < 0) {
+			comp_opts = ERR_PTR(length);
+			goto out;
+		}
+	}
+
+	comp_opts = squashfs_comp_opts(msblk, buffer, length);
+
+out:
+	kfree(actor);
+	kfree(buffer);
+	return comp_opts;
+}
+
+
+void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *stream, *comp_opts = get_comp_opts(sb, flags);
+
+	if (IS_ERR(comp_opts))
+		return comp_opts;
+
+	stream = msblk->thread_ops->create(msblk, comp_opts);
+	if (IS_ERR(stream))
+		kfree(comp_opts);
+
+	return stream;
+}