The ocfs2_control misc device is how a userspace control daemon (controld)
talks to the filesystem. Introduce the bare-bones filesystem ops.
Signed-off-by: Joel Becker <joel.becker@xxxxxxxxxx>
---
fs/ocfs2/stack_user.c | 184 ++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 183 insertions(+), 1 deletions(-)
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 920eb11..fdca5d3 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -18,17 +18,199 @@
*/
#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/reboot.h>
#include "stackglue.h"
-static int __init user_stack_init(void)
+/*
+ * The control protocol starts with a handshake. Until the handshake
+ * is complete, the control device will fail all write(2)s.
+ *
+ * The handshake is simple. First, the client reads until EOF. Each line
+ * of output is a supported protocol tag. All protocol tags are a single
+ * character followed by a two hex digit version number. Currently the
+ * only things supported is T01, for "Text-base version 0x01". Next, the
+ * client writes the version they would like to use. If the version tag
+ * written is unknown, -EINVAL is returned. Once the negotiation is
+ * complete, the client can start sending messages.
+ */
+
+/*
+ * ocfs2_live_connection is refcounted because the filesystem and
+ * miscdevice sides can detach in different order. Let's just be safe.
+ */
+struct ocfs2_live_connection {
+ struct list_head oc_list;
+ struct ocfs2_cluster_connection *oc_conn;
+};
+
+static atomic_t ocfs2_control_opened;
+
+static LIST_HEAD(ocfs2_live_connection_list);
+static DEFINE_MUTEX(ocfs2_control_lock);
+
+static struct ocfs2_live_connection *ocfs2_connection_find(const char *name)
+{
+ size_t len = strlen(name);
+ struct ocfs2_live_connection *c;
+
+ BUG_ON(!mutex_is_locked(&ocfs2_control_lock));
+
+ list_for_each_entry(c, &ocfs2_live_connection_list, oc_list) {
+ if ((c->oc_conn->cc_namelen == len) &&
+ !strncmp(c->oc_conn->cc_name, name, len))
+ return c;
+ }
+
+ return c;
+}
+
+/*
+ * ocfs2_live_connection structures are created underneath the ocfs2
+ * mount path. Since the VFS prevents multiple calls to
+ * fill_super(), we can't get dupes here.
+ */
+static int ocfs2_live_connection_new(struct ocfs2_cluster_connection *conn,
+ struct ocfs2_live_connection **c_ret)
+{
+ int rc = 0;
+ struct ocfs2_live_connection *c;
+
+ c = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL);
+ if (!c)
+ return -ENOMEM;
+
+ mutex_lock(&ocfs2_control_lock);
+ c->oc_conn = conn;
+
+ if (atomic_read(&ocfs2_control_opened))
+ list_add(&c->oc_list, &ocfs2_live_connection_list);
+ else {
+ printk(KERN_ERR
+ "ocfs2: Userspace control daemon is not present\n");
+ rc = -ESRCH;
+ }
+
+ mutex_unlock(&ocfs2_control_lock);
+
+ if (!rc)
+ *c_ret = c;
+ else
+ kfree(c);
+
+ return rc;
+}
+
+/*
+ * This function disconnects the cluster connection from ocfs2_control.
+ * Afterwards, userspace can't affect the cluster connection.
+ */
+static void ocfs2_live_connection_drop(struct ocfs2_live_connection *c)
+{
+ mutex_lock(&ocfs2_control_lock);
+ list_del_init(&c->oc_list);
+ c->oc_conn = NULL;
+ mutex_unlock(&ocfs2_control_lock);
+
+ kfree(c);
+}
+
+
+static ssize_t ocfs2_control_write(struct file *file,
+ const char __user *buf,
+ size_t count,
+ loff_t *ppos)
{
return 0;
}
+static ssize_t ocfs2_control_read(struct file *file,
+ char __user *buf,
+ size_t count,
+ loff_t *ppos)
+{
+ return 0;
+}
+
+static int ocfs2_control_release(struct inode *inode, struct file *file)
+{
+ if (atomic_dec_and_test(&ocfs2_control_opened)) {
+ mutex_lock(&ocfs2_control_lock);
+ if (!list_empty(&ocfs2_live_connection_list)) {
+ /* XXX: Do bad things! */
+ printk(KERN_ERR
+ "ocfs2: Unexpected release of ocfs2_control!\n"
+ " Loss of cluster connection requires "
+ "an emergency restart!\n");
+ emergency_restart();
+ }
+ mutex_unlock(&ocfs2_control_lock);
+ }
+
+ return 0;
+}
+
+static int ocfs2_control_open(struct inode *inode, struct file *file)
+{
+ atomic_inc(&ocfs2_control_opened);
+
+ return 0;
+}
+
+static const struct file_operations ocfs2_control_fops = {
+ .open = ocfs2_control_open,
+ .release = ocfs2_control_release,
+ .read = ocfs2_control_read,
+ .write = ocfs2_control_write,
+ .owner = THIS_MODULE,
+};
+
+struct miscdevice ocfs2_control_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "ocfs2_control",
+ .fops = &ocfs2_control_fops,
+};
+
+static int ocfs2_control_init(void)
+{
+ int rc;
+
+ atomic_set(&ocfs2_control_opened, 0);
+
+ rc = misc_register(&ocfs2_control_device);
+ if (rc)
+ printk(KERN_ERR
+ "ocfs2: Unable to register ocfs2_control device "
+ "(errno %d)\n",
+ -rc);
+
+ return rc;
+}
+
+static void ocfs2_control_exit(void)
+{
+ int rc;
+
+ rc = misc_deregister(&ocfs2_control_device);
+ if (rc)
+ printk(KERN_ERR
+ "ocfs2: Unable to deregister ocfs2_control device "
+ "(errno %d)\n",
+ -rc);
+}
+
+static int __init user_stack_init(void)
+{
+ return ocfs2_control_init();
+}
+
static void __exit user_stack_exit(void)
{
+ ocfs2_control_exit();
}
MODULE_AUTHOR("Oracle");
--
1.5.3.8
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
