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, 196 insertions, 0 deletions

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
new file mode 100644
index 000000000..ea6ec61a0
--- /dev/null
+++ b/fs/proc/namespaces.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *const ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+	&pidns_for_children_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
+#endif
+	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
+#ifdef CONFIG_TIME_NS
+	&timens_operations,
+	&timens_for_children_operations,
+#endif
+};
+
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
+{
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	struct path ns_path;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	task = get_proc_task(inode);
+	if (!task)
+		return ERR_PTR(-EACCES);
+
+	error = down_read_killable(&task->signal->exec_update_lock);
+	if (error)
+		goto out_put_task;
+
+	error = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto out;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (error)
+		goto out;
+
+	error = nd_jump_link(&ns_path);
+out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return ERR_PTR(error);
+}
+
+static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	char name[50];
+	int res = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return res;
+
+	res = down_read_killable(&task->signal->exec_update_lock);
+	if (res)
+		goto out_put_task;
+
+	res = -EACCES;
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name, strlen(name));
+	}
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return res;
+}
+
+static const struct inode_operations proc_ns_link_inode_operations = {
+	.readlink	= proc_ns_readlink,
+	.get_link	= proc_ns_get_link,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	inode->i_op = &proc_ns_link_inode_operations;
+	ei->ns_ops = ns_ops;
+	pid_update_inode(task, inode);
+
+	return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
+}
+
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct proc_ns_operations *const *entry, *const *last;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_ns_dir_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations *const *entry, *const *last;
+	unsigned int len = dentry->d_name.len;
+	struct dentry *res = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	if (entry == last)
+		goto out;
+
+	res = proc_ns_instantiate(dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return res;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_nochmod_setattr,
+};