netfs: zero the tail of a short DIO/unbuffered readgrafted

The buffered read collector zero-fills the tail of a short read that
stops below the inode's i_size (netfs_clear_unread()), so a read that
races an extending write still returns the expected number of bytes.
The non-buffered collector path does no such thing: it just records
how much was transferred.

Add the same zero-fill for the non-buffered case, gated on
NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short
result from it is known to be safe to treat as a hole, as opposed to
NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of
the file and should be reported short as-is. Only CLEAR_TAIL should
zero-fill here; a real EOF must stay a real short read.

No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest,
so this is inert on its own -- a following change teaches cifs to set
it in the one case that needs it.

Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Bharath SM <bharathsm@microsoft.com>
Cc: stable@vger.kernel.org

1 files changed, 168 insertions, 0 deletions

diff --git a/drivers/of/kobj.c b/drivers/of/kobj.c
new file mode 100644
index 000000000..9f17305f1
--- /dev/null
+++ b/drivers/of/kobj.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include <kunit/visibility.h>
+
+#include "of_private.h"
+
+/* true when node is initialized */
+static int of_node_is_initialized(const struct device_node *node)
+{
+	return node && node->kobj.state_initialized;
+}
+
+/* true when node is attached (i.e. present on sysfs) */
+int of_node_is_attached(const struct device_node *node)
+{
+	return node && node->kobj.state_in_sysfs;
+}
+
+
+#ifndef CONFIG_OF_DYNAMIC
+static void of_node_release(struct kobject *kobj)
+{
+	/* Without CONFIG_OF_DYNAMIC, no nodes gets freed */
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
+const struct kobj_type of_node_ktype = {
+	.release = of_node_release,
+};
+EXPORT_SYMBOL_IF_KUNIT(of_node_ktype);
+
+static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
+				const struct bin_attribute *bin_attr, char *buf,
+				loff_t offset, size_t count)
+{
+	struct property *pp = container_of(bin_attr, struct property, attr);
+	return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
+}
+
+/* always return newly allocated name, caller must free after use */
+static const char *safe_name(const struct kobject *kobj, const char *orig_name)
+{
+	const char *name = orig_name;
+	struct kernfs_node *kn;
+	int i = 0;
+
+	/* don't be a hero. After 16 tries give up */
+	while (i < 16 && (kn = sysfs_get_dirent(kobj->sd, name))) {
+		sysfs_put(kn);
+		if (name != orig_name)
+			kfree(name);
+		name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
+	}
+
+	if (name == orig_name) {
+		name = kstrdup(orig_name, GFP_KERNEL);
+	} else {
+		pr_warn("Duplicate name in %s, renamed to \"%s\"\n",
+			kobject_name(kobj), name);
+	}
+	return name;
+}
+
+int __of_add_property_sysfs(struct device_node *np, struct property *pp)
+{
+	int rc;
+
+	/* Important: Don't leak passwords */
+	bool secure = strncmp(pp->name, "security-", 9) == 0;
+
+	if (!IS_ENABLED(CONFIG_SYSFS))
+		return 0;
+
+	if (!of_kset || !of_node_is_attached(np))
+		return 0;
+
+	sysfs_bin_attr_init(&pp->attr);
+	pp->attr.attr.name = safe_name(&np->kobj, pp->name);
+	pp->attr.attr.mode = secure ? 0400 : 0444;
+	pp->attr.size = secure ? 0 : pp->length;
+	pp->attr.read = of_node_property_read;
+
+	rc = sysfs_create_bin_file(&np->kobj, &pp->attr);
+	WARN(rc, "error adding attribute %s to node %pOF\n", pp->name, np);
+	return rc;
+}
+
+void __of_sysfs_remove_bin_file(struct device_node *np, const struct property *prop)
+{
+	if (!IS_ENABLED(CONFIG_SYSFS))
+		return;
+
+	sysfs_remove_bin_file(&np->kobj, &prop->attr);
+	kfree(prop->attr.attr.name);
+}
+
+void __of_remove_property_sysfs(struct device_node *np, const struct property *prop)
+{
+	/* at early boot, bail here and defer setup to of_init() */
+	if (of_kset && of_node_is_attached(np))
+		__of_sysfs_remove_bin_file(np, prop);
+}
+
+void __of_update_property_sysfs(struct device_node *np, struct property *newprop,
+		const struct property *oldprop)
+{
+	/* At early boot, bail out and defer setup to of_init() */
+	if (!of_kset)
+		return;
+
+	if (oldprop)
+		__of_sysfs_remove_bin_file(np, oldprop);
+	__of_add_property_sysfs(np, newprop);
+}
+
+int __of_attach_node_sysfs(struct device_node *np)
+{
+	const char *name;
+	struct kobject *parent;
+	struct property *pp;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_SYSFS) || !of_kset)
+		return 0;
+
+	np->kobj.kset = of_kset;
+	if (!np->parent) {
+		/* Nodes without parents are new top level trees */
+		name = safe_name(&of_kset->kobj, "base");
+		parent = NULL;
+	} else {
+		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
+		parent = &np->parent->kobj;
+	}
+	if (!name)
+		return -ENOMEM;
+
+	rc = kobject_add(&np->kobj, parent, "%s", name);
+	kfree(name);
+	if (rc)
+		return rc;
+
+	for_each_property_of_node(np, pp)
+		__of_add_property_sysfs(np, pp);
+
+	of_node_get(np);
+	return 0;
+}
+
+void __of_detach_node_sysfs(struct device_node *np)
+{
+	struct property *pp;
+
+	BUG_ON(!of_node_is_initialized(np));
+	if (!of_kset)
+		return;
+
+	/* only remove properties if on sysfs */
+	if (of_node_is_attached(np)) {
+		for_each_property_of_node(np, pp)
+			__of_sysfs_remove_bin_file(np, pp);
+		kobject_del(&np->kobj);
+	}
+
+	of_node_put(np);
+}