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/cachefiles/volume.c b/fs/cachefiles/volume.c
new file mode 100644
index 000000000..6c0da6136
--- /dev/null
+++ b/fs/cachefiles/volume.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Volume handling.
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include "internal.h"
+#include <trace/events/fscache.h>
+
+/*
+ * Allocate and set up a volume representation.  We make sure all the fanout
+ * directories are created and pinned.
+ */
+void cachefiles_acquire_volume(struct fscache_volume *vcookie)
+{
+	struct cachefiles_volume *volume;
+	struct cachefiles_cache *cache = vcookie->cache->cache_priv;
+	const struct cred *saved_cred;
+	struct dentry *vdentry, *fan;
+	size_t len;
+	char *name;
+	bool is_new = false;
+	int ret, n_accesses, i;
+
+	_enter("");
+
+	volume = kzalloc_obj(struct cachefiles_volume);
+	if (!volume)
+		return;
+	volume->vcookie = vcookie;
+	volume->cache = cache;
+	INIT_LIST_HEAD(&volume->cache_link);
+
+	cachefiles_begin_secure(cache, &saved_cred);
+
+	len = vcookie->key[0];
+	name = kmalloc(len + 3, GFP_NOFS);
+	if (!name)
+		goto error_vol;
+	name[0] = 'I';
+	memcpy(name + 1, vcookie->key + 1, len);
+	name[len + 1] = 0;
+
+retry:
+	vdentry = cachefiles_get_directory(cache, cache->store, name, &is_new);
+	if (IS_ERR(vdentry))
+		goto error_name;
+	volume->dentry = vdentry;
+
+	if (is_new) {
+		if (!cachefiles_set_volume_xattr(volume))
+			goto error_dir;
+	} else {
+		ret = cachefiles_check_volume_xattr(volume);
+		if (ret < 0) {
+			if (ret != -ESTALE)
+				goto error_dir;
+			vdentry = start_removing_dentry(cache->store, vdentry);
+			if (!IS_ERR(vdentry))
+				cachefiles_bury_object(cache, NULL, cache->store,
+						       vdentry,
+						       FSCACHE_VOLUME_IS_WEIRD);
+			cachefiles_put_directory(volume->dentry);
+			cond_resched();
+			goto retry;
+		}
+	}
+	
+	for (i = 0; i < 256; i++) {
+		sprintf(name, "@%02x", i);
+		fan = cachefiles_get_directory(cache, vdentry, name, NULL);
+		if (IS_ERR(fan))
+			goto error_fan;
+		volume->fanout[i] = fan;
+	}
+
+	cachefiles_end_secure(cache, saved_cred);
+
+	vcookie->cache_priv = volume;
+	n_accesses = atomic_inc_return(&vcookie->n_accesses); /* Stop wakeups on dec-to-0 */
+	trace_fscache_access_volume(vcookie->debug_id, 0,
+				    refcount_read(&vcookie->ref),
+				    n_accesses, fscache_access_cache_pin);
+
+	spin_lock(&cache->object_list_lock);
+	list_add(&volume->cache_link, &volume->cache->volumes);
+	spin_unlock(&cache->object_list_lock);
+
+	kfree(name);
+	return;
+
+error_fan:
+	for (i = 0; i < 256; i++)
+		cachefiles_put_directory(volume->fanout[i]);
+error_dir:
+	cachefiles_put_directory(volume->dentry);
+error_name:
+	kfree(name);
+error_vol:
+	kfree(volume);
+	cachefiles_end_secure(cache, saved_cred);
+}
+
+/*
+ * Release a volume representation.
+ */
+static void __cachefiles_free_volume(struct cachefiles_volume *volume)
+{
+	int i;
+
+	_enter("");
+
+	volume->vcookie->cache_priv = NULL;
+
+	for (i = 0; i < 256; i++)
+		cachefiles_put_directory(volume->fanout[i]);
+	cachefiles_put_directory(volume->dentry);
+	kfree(volume);
+}
+
+void cachefiles_free_volume(struct fscache_volume *vcookie)
+{
+	struct cachefiles_volume *volume = vcookie->cache_priv;
+
+	if (volume) {
+		spin_lock(&volume->cache->object_list_lock);
+		list_del_init(&volume->cache_link);
+		spin_unlock(&volume->cache->object_list_lock);
+		__cachefiles_free_volume(volume);
+	}
+}
+
+void cachefiles_withdraw_volume(struct cachefiles_volume *volume)
+{
+	cachefiles_set_volume_xattr(volume);
+	__cachefiles_free_volume(volume);
+}