kernfs: sysfs: support custom llseek method for sysfs entries

As of now, seeking in sysfs files is handled by generic_file_llseek().
There are situations where one may want to customize seeking logic:

- Many sysfs entries are fixed files while generic_file_llseek() accepts
  past-the-end positions. Not only being useless by itself, this
  also means a bug in userspace code will trigger not at lseek(), but at
  some later point making debugging harder.
- generic_file_llseek() relies on f_mapping->host to get the file size
  which might not be correct for all sysfs entries.
  See commit 636b21b ("PCI: Revoke mappings like devmem") as an example.

Implement llseek method to override this behavior at sysfs attribute
level. The method is optional, and if it is absent,
generic_file_llseek() is called to preserve backwards compatibility.

Signed-off-by: Valentine Sinitsyn <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Valentine Sinitsyn

fs/kernfs/file.c

@@ -903,6 +903,33 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return ret;
 }
 
+static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	loff_t ret;
+
+	/*
+	 * @of->mutex nests outside active ref and is primarily to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		return -ENODEV;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->llseek)
+		ret = ops->llseek(of, offset, whence);
+	else
+		ret = generic_file_llseek(file, offset, whence);
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+	return ret;
+}
+
 static void kernfs_notify_workfn(struct work_struct *work)
 {
 	struct kernfs_node *kn;
@@ -1005,7 +1032,7 @@ EXPORT_SYMBOL_GPL(kernfs_notify);
 const struct file_operations kernfs_file_fops = {
 	.read_iter	= kernfs_fop_read_iter,
 	.write_iter	= kernfs_fop_write_iter,
-	.llseek		= generic_file_llseek,
+	.llseek		= kernfs_fop_llseek,
 	.mmap		= kernfs_fop_mmap,
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,

fs/sysfs/file.c

@@ -167,6 +167,18 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
 	return battr->mmap(of->file, kobj, battr, vma);
 }
 
+static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset,
+				  int whence)
+{
+	struct bin_attribute *battr = of->kn->priv;
+	struct kobject *kobj = of->kn->parent->priv;
+
+	if (battr->llseek)
+		return battr->llseek(of->file, kobj, battr, offset, whence);
+	else
+		return generic_file_llseek(of->file, offset, whence);
+}
+
 static int sysfs_kf_bin_open(struct kernfs_open_file *of)
 {
 	struct bin_attribute *battr = of->kn->priv;
@@ -249,6 +261,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
 	.write		= sysfs_kf_bin_write,
 	.mmap		= sysfs_kf_bin_mmap,
 	.open		= sysfs_kf_bin_open,
+	.llseek		= sysfs_kf_bin_llseek,
 };
 
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,

include/linux/kernfs.h

@@ -316,6 +316,7 @@ struct kernfs_ops {
 			 struct poll_table_struct *pt);
 
 	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
+	loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence);
 };
 
 /*

include/linux/sysfs.h

@@ -181,6 +181,8 @@ struct bin_attribute {
 			char *, loff_t, size_t);
 	ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *,
 			 char *, loff_t, size_t);
+	loff_t (*llseek)(struct file *, struct kobject *, struct bin_attribute *,
+			 loff_t, int);
 	int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr,
 		    struct vm_area_struct *vma);
 };