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, 154 insertions, 0 deletions

diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
new file mode 100644
index 000000000..487fbc51d
--- /dev/null
+++ b/fs/squashfs/zstd_wrapper.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * zstd_wrapper.c
+ */
+
+#include <linux/mutex.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+#include <linux/zstd.h>
+#include <linux/vmalloc.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs.h"
+#include "decompressor.h"
+#include "page_actor.h"
+
+struct workspace {
+	void *mem;
+	size_t mem_size;
+	size_t window_size;
+};
+
+static void *zstd_init(struct squashfs_sb_info *msblk, void *buff)
+{
+	struct workspace *wksp = kmalloc_obj(*wksp);
+
+	if (wksp == NULL)
+		goto failed;
+	wksp->window_size = max_t(size_t,
+			msblk->block_size, SQUASHFS_METADATA_SIZE);
+	wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size);
+	wksp->mem = vmalloc(wksp->mem_size);
+	if (wksp->mem == NULL)
+		goto failed;
+
+	return wksp;
+
+failed:
+	ERROR("Failed to allocate zstd workspace\n");
+	kfree(wksp);
+	return ERR_PTR(-ENOMEM);
+}
+
+
+static void zstd_free(void *strm)
+{
+	struct workspace *wksp = strm;
+
+	if (wksp)
+		vfree(wksp->mem);
+	kfree(wksp);
+}
+
+
+static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct bio *bio, int offset, int length,
+	struct squashfs_page_actor *output)
+{
+	struct workspace *wksp = strm;
+	zstd_dstream *stream;
+	size_t total_out = 0;
+	int error = 0;
+	zstd_in_buffer in_buf = { NULL, 0, 0 };
+	zstd_out_buffer out_buf = { NULL, 0, 0 };
+	struct bvec_iter_all iter_all = {};
+	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+
+	stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size);
+
+	if (!stream) {
+		ERROR("Failed to initialize zstd decompressor\n");
+		return -EIO;
+	}
+
+	out_buf.size = PAGE_SIZE;
+	out_buf.dst = squashfs_first_page(output);
+	if (IS_ERR(out_buf.dst)) {
+		error = PTR_ERR(out_buf.dst);
+		goto finish;
+	}
+
+	for (;;) {
+		size_t zstd_err;
+
+		if (in_buf.pos == in_buf.size) {
+			const void *data;
+			int avail;
+
+			if (!bio_next_segment(bio, &iter_all)) {
+				error = -EIO;
+				break;
+			}
+
+			avail = min(length, ((int)bvec->bv_len) - offset);
+			data = bvec_virt(bvec);
+			length -= avail;
+			in_buf.src = data + offset;
+			in_buf.size = avail;
+			in_buf.pos = 0;
+			offset = 0;
+		}
+
+		if (out_buf.pos == out_buf.size) {
+			out_buf.dst = squashfs_next_page(output);
+			if (IS_ERR(out_buf.dst)) {
+				error = PTR_ERR(out_buf.dst);
+				break;
+			} else if (out_buf.dst == NULL) {
+				/* Shouldn't run out of pages
+				 * before stream is done.
+				 */
+				error = -EIO;
+				break;
+			}
+			out_buf.pos = 0;
+			out_buf.size = PAGE_SIZE;
+		}
+
+		total_out -= out_buf.pos;
+		zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf);
+		total_out += out_buf.pos; /* add the additional data produced */
+		if (zstd_err == 0)
+			break;
+
+		if (zstd_is_error(zstd_err)) {
+			ERROR("zstd decompression error: %d\n",
+					(int)zstd_get_error_code(zstd_err));
+			error = -EIO;
+			break;
+		}
+	}
+
+finish:
+
+	squashfs_finish_page(output);
+
+	return error ? error : total_out;
+}
+
+const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	.init = zstd_init,
+	.free = zstd_free,
+	.decompress = zstd_uncompress,
+	.id = ZSTD_COMPRESSION,
+	.name = "zstd",
+	.alloc_buffer = 1,
+	.supported = 1
+};