#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
+#include <linux/smp_lock.h>
#include <linux/reboot.h>
#include <asm/uaccess.h>
+#include "ocfs2.h" /* For struct ocfs2_lock_res */
#include "stackglue.h"
* unknown, -EINVAL is returned. Once the negotiation is complete, the
* client can start sending messages.
*
- * The T01 protocol only has two messages. First is the "SETN" message.
+ * The T01 protocol has three messages. First is the "SETN" message.
* It has the following syntax:
*
* SETN<space><8-char-hex-nodenum><newline>
* The "SETN" message must be the first message following the protocol.
* It tells ocfs2_control the local node number.
*
- * Once the local node number has been set, the "DOWN" message can be
- * sent for node down notification. It has the following syntax:
+ * Next comes the "SETV" message. It has the following syntax:
+ *
+ * SETV<space><2-char-hex-major><space><2-char-hex-minor><newline>
+ *
+ * This is 11 characters.
+ *
+ * The "SETV" message sets the filesystem locking protocol version as
+ * negotiated by the client. The client negotiates based on the maximum
+ * version advertised in /sys/fs/ocfs2/max_locking_protocol. The major
+ * number from the "SETV" message must match
+ * ocfs2_user_plugin.sp_proto->lp_max_version.pv_major, and the minor number
+ * must be less than or equal to ...->lp_max_version.pv_minor.
+ *
+ * Once this information has been set, mounts will be allowed. From this
+ * point on, the "DOWN" message can be sent for node down notification.
+ * It has the following syntax:
*
* DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline>
*
#define OCFS2_CONTROL_MESSAGE_OP_LEN 4
#define OCFS2_CONTROL_MESSAGE_SETNODE_OP "SETN"
#define OCFS2_CONTROL_MESSAGE_SETNODE_TOTAL_LEN 14
+#define OCFS2_CONTROL_MESSAGE_SETVERSION_OP "SETV"
+#define OCFS2_CONTROL_MESSAGE_SETVERSION_TOTAL_LEN 11
#define OCFS2_CONTROL_MESSAGE_DOWN_OP "DOWN"
#define OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN 47
#define OCFS2_TEXT_UUID_LEN 32
+#define OCFS2_CONTROL_MESSAGE_VERNUM_LEN 2
#define OCFS2_CONTROL_MESSAGE_NODENUM_LEN 8
/*
struct list_head op_list;
int op_state;
int op_this_node;
+ struct ocfs2_protocol_version op_proto;
};
/* SETN<space><8-char-hex-nodenum><newline> */
char newline;
};
+/* SETV<space><2-char-hex-major><space><2-char-hex-minor><newline> */
+struct ocfs2_control_message_setv {
+ char tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
+ char space1;
+ char major[OCFS2_CONTROL_MESSAGE_VERNUM_LEN];
+ char space2;
+ char minor[OCFS2_CONTROL_MESSAGE_VERNUM_LEN];
+ char newline;
+};
+
/* DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline> */
struct ocfs2_control_message_down {
char tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
union ocfs2_control_message {
char tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
struct ocfs2_control_message_setn u_setn;
+ struct ocfs2_control_message_setv u_setv;
struct ocfs2_control_message_down u_down;
};
+static struct ocfs2_stack_plugin ocfs2_user_plugin;
+
static atomic_t ocfs2_control_opened;
static int ocfs2_control_this_node = -1;
+static struct ocfs2_protocol_version running_proto;
static LIST_HEAD(ocfs2_live_connection_list);
static LIST_HEAD(ocfs2_control_private_list);
/*
* Called whenever configuration elements are sent to /dev/ocfs2_control.
* If all configuration elements are present, try to set the global
- * values. If not, return -EAGAIN. If there is a problem, return a
- * different error.
+ * values. If there is a problem, return an error. Skip any missing
+ * elements, and only bump ocfs2_control_opened when we have all elements
+ * and are successful.
*/
static int ocfs2_control_install_private(struct file *file)
{
BUG_ON(p->op_state != OCFS2_CONTROL_HANDSHAKE_PROTOCOL);
- if (p->op_this_node < 0)
+ mutex_lock(&ocfs2_control_lock);
+
+ if (p->op_this_node < 0) {
set_p = 0;
+ } else if ((ocfs2_control_this_node >= 0) &&
+ (ocfs2_control_this_node != p->op_this_node)) {
+ rc = -EINVAL;
+ goto out_unlock;
+ }
- mutex_lock(&ocfs2_control_lock);
- if (ocfs2_control_this_node < 0) {
- if (set_p)
- ocfs2_control_this_node = p->op_this_node;
- } else if (ocfs2_control_this_node != p->op_this_node)
+ if (!p->op_proto.pv_major) {
+ set_p = 0;
+ } else if (!list_empty(&ocfs2_live_connection_list) &&
+ ((running_proto.pv_major != p->op_proto.pv_major) ||
+ (running_proto.pv_minor != p->op_proto.pv_minor))) {
rc = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (set_p) {
+ ocfs2_control_this_node = p->op_this_node;
+ running_proto.pv_major = p->op_proto.pv_major;
+ running_proto.pv_minor = p->op_proto.pv_minor;
+ }
+
+out_unlock:
mutex_unlock(&ocfs2_control_lock);
if (!rc && set_p) {
return rc;
}
+static int ocfs2_control_get_this_node(void)
+{
+ int rc;
+
+ mutex_lock(&ocfs2_control_lock);
+ if (ocfs2_control_this_node < 0)
+ rc = -EINVAL;
+ else
+ rc = ocfs2_control_this_node;
+ mutex_unlock(&ocfs2_control_lock);
+
+ return rc;
+}
+
static int ocfs2_control_do_setnode_msg(struct file *file,
struct ocfs2_control_message_setn *msg)
{
return ocfs2_control_install_private(file);
}
+static int ocfs2_control_do_setversion_msg(struct file *file,
+ struct ocfs2_control_message_setv *msg)
+ {
+ long major, minor;
+ char *ptr = NULL;
+ struct ocfs2_control_private *p = file->private_data;
+ struct ocfs2_protocol_version *max =
+ &ocfs2_user_plugin.sp_proto->lp_max_version;
+
+ if (ocfs2_control_get_handshake_state(file) !=
+ OCFS2_CONTROL_HANDSHAKE_PROTOCOL)
+ return -EINVAL;
+
+ if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_SETVERSION_OP,
+ OCFS2_CONTROL_MESSAGE_OP_LEN))
+ return -EINVAL;
+
+ if ((msg->space1 != ' ') || (msg->space2 != ' ') ||
+ (msg->newline != '\n'))
+ return -EINVAL;
+ msg->space1 = msg->space2 = msg->newline = '\0';
+
+ major = simple_strtol(msg->major, &ptr, 16);
+ if (!ptr || *ptr)
+ return -EINVAL;
+ minor = simple_strtol(msg->minor, &ptr, 16);
+ if (!ptr || *ptr)
+ return -EINVAL;
+
+ /*
+ * The major must be between 1 and 255, inclusive. The minor
+ * must be between 0 and 255, inclusive. The version passed in
+ * must be within the maximum version supported by the filesystem.
+ */
+ if ((major == LONG_MIN) || (major == LONG_MAX) ||
+ (major > (u8)-1) || (major < 1))
+ return -ERANGE;
+ if ((minor == LONG_MIN) || (minor == LONG_MAX) ||
+ (minor > (u8)-1) || (minor < 0))
+ return -ERANGE;
+ if ((major != max->pv_major) ||
+ (minor > max->pv_minor))
+ return -EINVAL;
+
+ p->op_proto.pv_major = major;
+ p->op_proto.pv_minor = minor;
+
+ return ocfs2_control_install_private(file);
+}
+
static int ocfs2_control_do_down_msg(struct file *file,
struct ocfs2_control_message_down *msg)
{
!strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_SETNODE_OP,
OCFS2_CONTROL_MESSAGE_OP_LEN))
ret = ocfs2_control_do_setnode_msg(file, &msg.u_setn);
+ else if ((count == OCFS2_CONTROL_MESSAGE_SETVERSION_TOTAL_LEN) &&
+ !strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_SETVERSION_OP,
+ OCFS2_CONTROL_MESSAGE_OP_LEN))
+ ret = ocfs2_control_do_setversion_msg(file, &msg.u_setv);
else if ((count == OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN) &&
!strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_DOWN_OP,
OCFS2_CONTROL_MESSAGE_OP_LEN))
"an emergency restart!\n");
emergency_restart();
}
- /* Last valid close clears the node number */
+ /*
+ * Last valid close clears the node number and resets
+ * the locking protocol version
+ */
ocfs2_control_this_node = -1;
+ running_proto.pv_major = 0;
+ running_proto.pv_major = 0;
}
out:
return -ENOMEM;
p->op_this_node = -1;
+ lock_kernel();
mutex_lock(&ocfs2_control_lock);
file->private_data = p;
list_add(&p->op_list, &ocfs2_control_private_list);
mutex_unlock(&ocfs2_control_lock);
+ unlock_kernel();
return 0;
}
.owner = THIS_MODULE,
};
-struct miscdevice ocfs2_control_device = {
+static struct miscdevice ocfs2_control_device = {
.minor = MISC_DYNAMIC_MINOR,
.name = "ocfs2_control",
.fops = &ocfs2_control_fops,
-rc);
}
-static int __init user_stack_init(void)
+static struct dlm_lksb *fsdlm_astarg_to_lksb(void *astarg)
+{
+ struct ocfs2_lock_res *res = astarg;
+ return &res->l_lksb.lksb_fsdlm;
+}
+
+static void fsdlm_lock_ast_wrapper(void *astarg)
+{
+ struct dlm_lksb *lksb = fsdlm_astarg_to_lksb(astarg);
+ int status = lksb->sb_status;
+
+ BUG_ON(ocfs2_user_plugin.sp_proto == NULL);
+
+ /*
+ * For now we're punting on the issue of other non-standard errors
+ * where we can't tell if the unlock_ast or lock_ast should be called.
+ * The main "other error" that's possible is EINVAL which means the
+ * function was called with invalid args, which shouldn't be possible
+ * since the caller here is under our control. Other non-standard
+ * errors probably fall into the same category, or otherwise are fatal
+ * which means we can't carry on anyway.
+ */
+
+ if (status == -DLM_EUNLOCK || status == -DLM_ECANCEL)
+ ocfs2_user_plugin.sp_proto->lp_unlock_ast(astarg, 0);
+ else
+ ocfs2_user_plugin.sp_proto->lp_lock_ast(astarg);
+}
+
+static void fsdlm_blocking_ast_wrapper(void *astarg, int level)
+{
+ BUG_ON(ocfs2_user_plugin.sp_proto == NULL);
+
+ ocfs2_user_plugin.sp_proto->lp_blocking_ast(astarg, level);
+}
+
+static int user_dlm_lock(struct ocfs2_cluster_connection *conn,
+ int mode,
+ union ocfs2_dlm_lksb *lksb,
+ u32 flags,
+ void *name,
+ unsigned int namelen,
+ void *astarg)
+{
+ int ret;
+
+ if (!lksb->lksb_fsdlm.sb_lvbptr)
+ lksb->lksb_fsdlm.sb_lvbptr = (char *)lksb +
+ sizeof(struct dlm_lksb);
+
+ ret = dlm_lock(conn->cc_lockspace, mode, &lksb->lksb_fsdlm,
+ flags|DLM_LKF_NODLCKWT, name, namelen, 0,
+ fsdlm_lock_ast_wrapper, astarg,
+ fsdlm_blocking_ast_wrapper);
+ return ret;
+}
+
+static int user_dlm_unlock(struct ocfs2_cluster_connection *conn,
+ union ocfs2_dlm_lksb *lksb,
+ u32 flags,
+ void *astarg)
+{
+ int ret;
+
+ ret = dlm_unlock(conn->cc_lockspace, lksb->lksb_fsdlm.sb_lkid,
+ flags, &lksb->lksb_fsdlm, astarg);
+ return ret;
+}
+
+static int user_dlm_lock_status(union ocfs2_dlm_lksb *lksb)
+{
+ return lksb->lksb_fsdlm.sb_status;
+}
+
+static void *user_dlm_lvb(union ocfs2_dlm_lksb *lksb)
+{
+ return (void *)(lksb->lksb_fsdlm.sb_lvbptr);
+}
+
+static void user_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb)
+{
+}
+
+/*
+ * Compare a requested locking protocol version against the current one.
+ *
+ * If the major numbers are different, they are incompatible.
+ * If the current minor is greater than the request, they are incompatible.
+ * If the current minor is less than or equal to the request, they are
+ * compatible, and the requester should run at the current minor version.
+ */
+static int fs_protocol_compare(struct ocfs2_protocol_version *existing,
+ struct ocfs2_protocol_version *request)
+{
+ if (existing->pv_major != request->pv_major)
+ return 1;
+
+ if (existing->pv_minor > request->pv_minor)
+ return 1;
+
+ if (existing->pv_minor < request->pv_minor)
+ request->pv_minor = existing->pv_minor;
+
+ return 0;
+}
+
+static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
{
- return ocfs2_control_init();
+ dlm_lockspace_t *fsdlm;
+ struct ocfs2_live_connection *control;
+ int rc = 0;
+
+ BUG_ON(conn == NULL);
+
+ rc = ocfs2_live_connection_new(conn, &control);
+ if (rc)
+ goto out;
+
+ /*
+ * running_proto must have been set before we allowed any mounts
+ * to proceed.
+ */
+ if (fs_protocol_compare(&running_proto, &conn->cc_version)) {
+ printk(KERN_ERR
+ "Unable to mount with fs locking protocol version "
+ "%u.%u because the userspace control daemon has "
+ "negotiated %u.%u\n",
+ conn->cc_version.pv_major, conn->cc_version.pv_minor,
+ running_proto.pv_major, running_proto.pv_minor);
+ rc = -EPROTO;
+ ocfs2_live_connection_drop(control);
+ goto out;
+ }
+
+ rc = dlm_new_lockspace(conn->cc_name, strlen(conn->cc_name),
+ &fsdlm, DLM_LSFL_FS, DLM_LVB_LEN);
+ if (rc) {
+ ocfs2_live_connection_drop(control);
+ goto out;
+ }
+
+ conn->cc_private = control;
+ conn->cc_lockspace = fsdlm;
+out:
+ return rc;
+}
+
+static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn)
+{
+ dlm_release_lockspace(conn->cc_lockspace, 2);
+ conn->cc_lockspace = NULL;
+ ocfs2_live_connection_drop(conn->cc_private);
+ conn->cc_private = NULL;
+ return 0;
+}
+
+static int user_cluster_this_node(unsigned int *this_node)
+{
+ int rc;
+
+ rc = ocfs2_control_get_this_node();
+ if (rc < 0)
+ return rc;
+
+ *this_node = rc;
+ return 0;
+}
+
+static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
+ .connect = user_cluster_connect,
+ .disconnect = user_cluster_disconnect,
+ .this_node = user_cluster_this_node,
+ .dlm_lock = user_dlm_lock,
+ .dlm_unlock = user_dlm_unlock,
+ .lock_status = user_dlm_lock_status,
+ .lock_lvb = user_dlm_lvb,
+ .dump_lksb = user_dlm_dump_lksb,
+};
+
+static struct ocfs2_stack_plugin ocfs2_user_plugin = {
+ .sp_name = "user",
+ .sp_ops = &ocfs2_user_plugin_ops,
+ .sp_owner = THIS_MODULE,
+};
+
+
+static int __init ocfs2_user_plugin_init(void)
+{
+ int rc;
+
+ rc = ocfs2_control_init();
+ if (!rc) {
+ rc = ocfs2_stack_glue_register(&ocfs2_user_plugin);
+ if (rc)
+ ocfs2_control_exit();
+ }
+
+ return rc;
}
-static void __exit user_stack_exit(void)
+static void __exit ocfs2_user_plugin_exit(void)
{
+ ocfs2_stack_glue_unregister(&ocfs2_user_plugin);
ocfs2_control_exit();
}
MODULE_AUTHOR("Oracle");
MODULE_DESCRIPTION("ocfs2 driver for userspace cluster stacks");
MODULE_LICENSE("GPL");
-module_init(user_stack_init);
-module_exit(user_stack_exit);
+module_init(ocfs2_user_plugin_init);
+module_exit(ocfs2_user_plugin_exit);
projects / cascardo / linux.git / blobdiff