2007-11-29 06:38:40 +08:00
|
|
|
/* -*- mode: c; c-basic-offset: 8; -*-
|
|
|
|
* vim: noexpandtab sw=8 ts=8 sts=0:
|
|
|
|
*
|
|
|
|
* stack_user.c
|
|
|
|
*
|
|
|
|
* Code which interfaces ocfs2 with fs/dlm and a userspace stack.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public
|
|
|
|
* License as published by the Free Software Foundation, version 2.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
2008-02-19 11:23:28 +08:00
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/miscdevice.h>
|
|
|
|
#include <linux/mutex.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2008-02-19 11:23:28 +08:00
|
|
|
#include <linux/reboot.h>
|
2014-01-22 07:48:32 +08:00
|
|
|
#include <linux/sched.h>
|
2008-02-19 11:40:12 +08:00
|
|
|
#include <asm/uaccess.h>
|
2007-11-29 06:38:40 +08:00
|
|
|
|
|
|
|
#include "stackglue.h"
|
|
|
|
|
2008-07-22 05:29:16 +08:00
|
|
|
#include <linux/dlm_plock.h>
|
2007-11-29 06:38:40 +08:00
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
/*
|
|
|
|
* 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
|
2008-02-19 09:07:09 +08:00
|
|
|
* client writes the version they would like to use, including the newline.
|
|
|
|
* Thus, the protocol tag is 'T01\n'. If the version tag written is
|
|
|
|
* unknown, -EINVAL is returned. Once the negotiation is complete, the
|
|
|
|
* client can start sending messages.
|
|
|
|
*
|
2008-02-21 07:39:44 +08:00
|
|
|
* The T01 protocol has three messages. First is the "SETN" message.
|
2008-02-21 06:44:34 +08:00
|
|
|
* It has the following syntax:
|
|
|
|
*
|
|
|
|
* SETN<space><8-char-hex-nodenum><newline>
|
|
|
|
*
|
|
|
|
* This is 14 characters.
|
|
|
|
*
|
|
|
|
* The "SETN" message must be the first message following the protocol.
|
|
|
|
* It tells ocfs2_control the local node number.
|
|
|
|
*
|
2008-02-21 07:39:44 +08:00
|
|
|
* 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
|
2010-01-30 08:06:29 +08:00
|
|
|
* ocfs2_user_plugin.sp_max_proto.pv_major, and the minor number
|
|
|
|
* must be less than or equal to ...sp_max_version.pv_minor.
|
2008-02-21 07:39:44 +08:00
|
|
|
*
|
|
|
|
* 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:
|
2008-02-19 09:07:09 +08:00
|
|
|
*
|
|
|
|
* DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline>
|
|
|
|
*
|
|
|
|
* eg:
|
|
|
|
*
|
|
|
|
* DOWN 632A924FDD844190BDA93C0DF6B94899 00000001\n
|
|
|
|
*
|
|
|
|
* This is 47 characters.
|
2008-02-19 11:23:28 +08:00
|
|
|
*/
|
|
|
|
|
2008-02-19 11:40:12 +08:00
|
|
|
/*
|
|
|
|
* Whether or not the client has done the handshake.
|
|
|
|
* For now, we have just one protocol version.
|
|
|
|
*/
|
|
|
|
#define OCFS2_CONTROL_PROTO "T01\n"
|
|
|
|
#define OCFS2_CONTROL_PROTO_LEN 4
|
2008-02-21 06:44:34 +08:00
|
|
|
|
|
|
|
/* Handshake states */
|
2008-02-19 11:40:12 +08:00
|
|
|
#define OCFS2_CONTROL_HANDSHAKE_INVALID (0)
|
|
|
|
#define OCFS2_CONTROL_HANDSHAKE_READ (1)
|
2008-02-21 06:44:34 +08:00
|
|
|
#define OCFS2_CONTROL_HANDSHAKE_PROTOCOL (2)
|
|
|
|
#define OCFS2_CONTROL_HANDSHAKE_VALID (3)
|
|
|
|
|
|
|
|
/* Messages */
|
|
|
|
#define OCFS2_CONTROL_MESSAGE_OP_LEN 4
|
|
|
|
#define OCFS2_CONTROL_MESSAGE_SETNODE_OP "SETN"
|
|
|
|
#define OCFS2_CONTROL_MESSAGE_SETNODE_TOTAL_LEN 14
|
2008-02-21 07:39:44 +08:00
|
|
|
#define OCFS2_CONTROL_MESSAGE_SETVERSION_OP "SETV"
|
|
|
|
#define OCFS2_CONTROL_MESSAGE_SETVERSION_TOTAL_LEN 11
|
2008-02-21 06:44:34 +08:00
|
|
|
#define OCFS2_CONTROL_MESSAGE_DOWN_OP "DOWN"
|
2008-02-19 09:07:09 +08:00
|
|
|
#define OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN 47
|
|
|
|
#define OCFS2_TEXT_UUID_LEN 32
|
2008-02-21 07:39:44 +08:00
|
|
|
#define OCFS2_CONTROL_MESSAGE_VERNUM_LEN 2
|
2008-02-19 09:07:09 +08:00
|
|
|
#define OCFS2_CONTROL_MESSAGE_NODENUM_LEN 8
|
2014-01-22 07:48:25 +08:00
|
|
|
#define VERSION_LOCK "version_lock"
|
2008-02-19 11:40:12 +08:00
|
|
|
|
2014-01-22 07:48:24 +08:00
|
|
|
enum ocfs2_connection_type {
|
|
|
|
WITH_CONTROLD,
|
|
|
|
NO_CONTROLD
|
|
|
|
};
|
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
2014-01-22 07:48:24 +08:00
|
|
|
enum ocfs2_connection_type oc_type;
|
2014-01-22 07:48:22 +08:00
|
|
|
atomic_t oc_this_node;
|
|
|
|
int oc_our_slot;
|
2014-01-22 07:48:25 +08:00
|
|
|
struct dlm_lksb oc_version_lksb;
|
|
|
|
char oc_lvb[DLM_LVB_LEN];
|
|
|
|
struct completion oc_sync_wait;
|
2014-01-22 07:48:32 +08:00
|
|
|
wait_queue_head_t oc_wait;
|
2008-02-19 11:23:28 +08:00
|
|
|
};
|
|
|
|
|
2008-02-19 11:40:12 +08:00
|
|
|
struct ocfs2_control_private {
|
|
|
|
struct list_head op_list;
|
|
|
|
int op_state;
|
2008-02-21 06:44:34 +08:00
|
|
|
int op_this_node;
|
2008-02-21 07:39:44 +08:00
|
|
|
struct ocfs2_protocol_version op_proto;
|
2008-02-21 06:44:34 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/* SETN<space><8-char-hex-nodenum><newline> */
|
|
|
|
struct ocfs2_control_message_setn {
|
|
|
|
char tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
|
|
|
|
char space;
|
|
|
|
char nodestr[OCFS2_CONTROL_MESSAGE_NODENUM_LEN];
|
|
|
|
char newline;
|
|
|
|
};
|
|
|
|
|
2008-02-21 07:39:44 +08:00
|
|
|
/* 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;
|
|
|
|
};
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
/* 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];
|
|
|
|
char space1;
|
|
|
|
char uuid[OCFS2_TEXT_UUID_LEN];
|
|
|
|
char space2;
|
|
|
|
char nodestr[OCFS2_CONTROL_MESSAGE_NODENUM_LEN];
|
|
|
|
char newline;
|
|
|
|
};
|
|
|
|
|
|
|
|
union ocfs2_control_message {
|
|
|
|
char tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
|
|
|
|
struct ocfs2_control_message_setn u_setn;
|
2008-02-21 07:39:44 +08:00
|
|
|
struct ocfs2_control_message_setv u_setv;
|
2008-02-21 06:44:34 +08:00
|
|
|
struct ocfs2_control_message_down u_down;
|
2008-02-19 11:40:12 +08:00
|
|
|
};
|
|
|
|
|
2008-05-10 09:49:29 +08:00
|
|
|
static struct ocfs2_stack_plugin ocfs2_user_plugin;
|
2008-02-21 06:29:27 +08:00
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
static atomic_t ocfs2_control_opened;
|
2008-02-21 06:44:34 +08:00
|
|
|
static int ocfs2_control_this_node = -1;
|
2008-02-21 07:39:44 +08:00
|
|
|
static struct ocfs2_protocol_version running_proto;
|
2008-02-19 11:23:28 +08:00
|
|
|
|
|
|
|
static LIST_HEAD(ocfs2_live_connection_list);
|
2008-02-19 11:40:12 +08:00
|
|
|
static LIST_HEAD(ocfs2_control_private_list);
|
2008-02-19 11:23:28 +08:00
|
|
|
static DEFINE_MUTEX(ocfs2_control_lock);
|
|
|
|
|
2008-02-19 11:40:12 +08:00
|
|
|
static inline void ocfs2_control_set_handshake_state(struct file *file,
|
|
|
|
int state)
|
|
|
|
{
|
|
|
|
struct ocfs2_control_private *p = file->private_data;
|
|
|
|
p->op_state = state;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ocfs2_control_get_handshake_state(struct file *file)
|
|
|
|
{
|
|
|
|
struct ocfs2_control_private *p = file->private_data;
|
|
|
|
return p->op_state;
|
|
|
|
}
|
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2010-11-19 06:03:09 +08:00
|
|
|
return NULL;
|
2008-02-19 11:23:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2014-01-22 07:48:23 +08:00
|
|
|
static int ocfs2_live_connection_attach(struct ocfs2_cluster_connection *conn,
|
|
|
|
struct ocfs2_live_connection *c)
|
2008-02-19 11:23:28 +08:00
|
|
|
{
|
|
|
|
int rc = 0;
|
|
|
|
|
|
|
|
mutex_lock(&ocfs2_control_lock);
|
|
|
|
c->oc_conn = conn;
|
|
|
|
|
2014-01-22 07:48:32 +08:00
|
|
|
if ((c->oc_type == NO_CONTROLD) || atomic_read(&ocfs2_control_opened))
|
2008-02-19 11:23:28 +08:00
|
|
|
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);
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
static int ocfs2_control_cfu(void *target, size_t target_len,
|
|
|
|
const char __user *buf, size_t count)
|
2008-02-19 11:40:12 +08:00
|
|
|
{
|
|
|
|
/* The T01 expects write(2) calls to have exactly one command */
|
2008-02-21 06:44:34 +08:00
|
|
|
if ((count != target_len) ||
|
|
|
|
(count > sizeof(union ocfs2_control_message)))
|
2008-02-19 11:40:12 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (copy_from_user(target, buf, target_len))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
return 0;
|
2008-02-19 11:40:12 +08:00
|
|
|
}
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
static ssize_t ocfs2_control_validate_protocol(struct file *file,
|
|
|
|
const char __user *buf,
|
|
|
|
size_t count)
|
2008-02-19 11:40:12 +08:00
|
|
|
{
|
|
|
|
ssize_t ret;
|
|
|
|
char kbuf[OCFS2_CONTROL_PROTO_LEN];
|
|
|
|
|
|
|
|
ret = ocfs2_control_cfu(kbuf, OCFS2_CONTROL_PROTO_LEN,
|
|
|
|
buf, count);
|
2008-02-21 06:44:34 +08:00
|
|
|
if (ret)
|
2008-02-19 11:40:12 +08:00
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (strncmp(kbuf, OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
ocfs2_control_set_handshake_state(file,
|
2008-02-21 06:44:34 +08:00
|
|
|
OCFS2_CONTROL_HANDSHAKE_PROTOCOL);
|
2008-02-19 11:40:12 +08:00
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2008-02-19 09:07:09 +08:00
|
|
|
static void ocfs2_control_send_down(const char *uuid,
|
|
|
|
int nodenum)
|
|
|
|
{
|
|
|
|
struct ocfs2_live_connection *c;
|
|
|
|
|
|
|
|
mutex_lock(&ocfs2_control_lock);
|
|
|
|
|
|
|
|
c = ocfs2_connection_find(uuid);
|
|
|
|
if (c) {
|
|
|
|
BUG_ON(c->oc_conn == NULL);
|
|
|
|
c->oc_conn->cc_recovery_handler(nodenum,
|
|
|
|
c->oc_conn->cc_recovery_data);
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&ocfs2_control_lock);
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
/*
|
|
|
|
* Called whenever configuration elements are sent to /dev/ocfs2_control.
|
|
|
|
* If all configuration elements are present, try to set the global
|
2008-02-21 07:39:44 +08:00
|
|
|
* 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.
|
2008-02-21 06:44:34 +08:00
|
|
|
*/
|
|
|
|
static int ocfs2_control_install_private(struct file *file)
|
|
|
|
{
|
|
|
|
int rc = 0;
|
|
|
|
int set_p = 1;
|
|
|
|
struct ocfs2_control_private *p = file->private_data;
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
BUG_ON(p->op_state != OCFS2_CONTROL_HANDSHAKE_PROTOCOL);
|
|
|
|
|
2008-02-21 07:39:44 +08:00
|
|
|
mutex_lock(&ocfs2_control_lock);
|
|
|
|
|
|
|
|
if (p->op_this_node < 0) {
|
2008-02-21 06:44:34 +08:00
|
|
|
set_p = 0;
|
2008-02-21 07:39:44 +08:00
|
|
|
} else if ((ocfs2_control_this_node >= 0) &&
|
|
|
|
(ocfs2_control_this_node != p->op_this_node)) {
|
|
|
|
rc = -EINVAL;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
2008-02-21 06:44:34 +08:00
|
|
|
|
2008-02-21 07:39:44 +08:00
|
|
|
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))) {
|
2008-02-21 06:44:34 +08:00
|
|
|
rc = -EINVAL;
|
2008-02-21 07:39:44 +08:00
|
|
|
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:
|
2008-02-21 06:44:34 +08:00
|
|
|
mutex_unlock(&ocfs2_control_lock);
|
|
|
|
|
|
|
|
if (!rc && set_p) {
|
|
|
|
/* We set the global values successfully */
|
|
|
|
atomic_inc(&ocfs2_control_opened);
|
|
|
|
ocfs2_control_set_handshake_state(file,
|
|
|
|
OCFS2_CONTROL_HANDSHAKE_VALID);
|
|
|
|
}
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
static int ocfs2_control_do_setnode_msg(struct file *file,
|
|
|
|
struct ocfs2_control_message_setn *msg)
|
2008-02-19 09:07:09 +08:00
|
|
|
{
|
|
|
|
long nodenum;
|
2008-02-21 06:44:34 +08:00
|
|
|
char *ptr = NULL;
|
|
|
|
struct ocfs2_control_private *p = file->private_data;
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
if (ocfs2_control_get_handshake_state(file) !=
|
|
|
|
OCFS2_CONTROL_HANDSHAKE_PROTOCOL)
|
|
|
|
return -EINVAL;
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_SETNODE_OP,
|
|
|
|
OCFS2_CONTROL_MESSAGE_OP_LEN))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((msg->space != ' ') || (msg->newline != '\n'))
|
|
|
|
return -EINVAL;
|
|
|
|
msg->space = msg->newline = '\0';
|
|
|
|
|
|
|
|
nodenum = simple_strtol(msg->nodestr, &ptr, 16);
|
|
|
|
if (!ptr || *ptr)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((nodenum == LONG_MIN) || (nodenum == LONG_MAX) ||
|
|
|
|
(nodenum > INT_MAX) || (nodenum < 0))
|
|
|
|
return -ERANGE;
|
|
|
|
p->op_this_node = nodenum;
|
|
|
|
|
|
|
|
return ocfs2_control_install_private(file);
|
|
|
|
}
|
|
|
|
|
2008-02-21 07:39:44 +08:00
|
|
|
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 =
|
2010-01-30 08:06:29 +08:00
|
|
|
&ocfs2_user_plugin.sp_max_proto;
|
2008-02-21 07:39:44 +08:00
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
static int ocfs2_control_do_down_msg(struct file *file,
|
|
|
|
struct ocfs2_control_message_down *msg)
|
|
|
|
{
|
|
|
|
long nodenum;
|
|
|
|
char *p = NULL;
|
|
|
|
|
|
|
|
if (ocfs2_control_get_handshake_state(file) !=
|
|
|
|
OCFS2_CONTROL_HANDSHAKE_VALID)
|
|
|
|
return -EINVAL;
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_DOWN_OP,
|
|
|
|
OCFS2_CONTROL_MESSAGE_OP_LEN))
|
2008-02-19 09:07:09 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
if ((msg->space1 != ' ') || (msg->space2 != ' ') ||
|
|
|
|
(msg->newline != '\n'))
|
2008-02-19 09:07:09 +08:00
|
|
|
return -EINVAL;
|
2008-02-21 06:44:34 +08:00
|
|
|
msg->space1 = msg->space2 = msg->newline = '\0';
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
nodenum = simple_strtol(msg->nodestr, &p, 16);
|
2008-02-19 09:07:09 +08:00
|
|
|
if (!p || *p)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((nodenum == LONG_MIN) || (nodenum == LONG_MAX) ||
|
|
|
|
(nodenum > INT_MAX) || (nodenum < 0))
|
|
|
|
return -ERANGE;
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
ocfs2_control_send_down(msg->uuid, nodenum);
|
2008-02-19 09:07:09 +08:00
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t ocfs2_control_message(struct file *file,
|
|
|
|
const char __user *buf,
|
|
|
|
size_t count)
|
|
|
|
{
|
|
|
|
ssize_t ret;
|
|
|
|
union ocfs2_control_message msg;
|
|
|
|
|
|
|
|
/* Try to catch padding issues */
|
|
|
|
WARN_ON(offsetof(struct ocfs2_control_message_down, uuid) !=
|
|
|
|
(sizeof(msg.u_down.tag) + sizeof(msg.u_down.space1)));
|
|
|
|
|
|
|
|
memset(&msg, 0, sizeof(union ocfs2_control_message));
|
|
|
|
ret = ocfs2_control_cfu(&msg, count, buf, count);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if ((count == OCFS2_CONTROL_MESSAGE_SETNODE_TOTAL_LEN) &&
|
|
|
|
!strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_SETNODE_OP,
|
|
|
|
OCFS2_CONTROL_MESSAGE_OP_LEN))
|
|
|
|
ret = ocfs2_control_do_setnode_msg(file, &msg.u_setn);
|
2008-02-21 07:39:44 +08:00
|
|
|
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);
|
2008-02-21 06:44:34 +08:00
|
|
|
else if ((count == OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN) &&
|
|
|
|
!strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_DOWN_OP,
|
|
|
|
OCFS2_CONTROL_MESSAGE_OP_LEN))
|
|
|
|
ret = ocfs2_control_do_down_msg(file, &msg.u_down);
|
|
|
|
else
|
|
|
|
ret = -EINVAL;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret ? ret : count;
|
2008-02-19 09:07:09 +08:00
|
|
|
}
|
2008-02-19 11:23:28 +08:00
|
|
|
|
|
|
|
static ssize_t ocfs2_control_write(struct file *file,
|
|
|
|
const char __user *buf,
|
|
|
|
size_t count,
|
|
|
|
loff_t *ppos)
|
2007-11-29 06:38:40 +08:00
|
|
|
{
|
2008-02-19 11:40:12 +08:00
|
|
|
ssize_t ret;
|
|
|
|
|
|
|
|
switch (ocfs2_control_get_handshake_state(file)) {
|
|
|
|
case OCFS2_CONTROL_HANDSHAKE_INVALID:
|
|
|
|
ret = -EINVAL;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case OCFS2_CONTROL_HANDSHAKE_READ:
|
2008-02-21 06:44:34 +08:00
|
|
|
ret = ocfs2_control_validate_protocol(file, buf,
|
|
|
|
count);
|
2008-02-19 11:40:12 +08:00
|
|
|
break;
|
|
|
|
|
2008-02-21 06:44:34 +08:00
|
|
|
case OCFS2_CONTROL_HANDSHAKE_PROTOCOL:
|
2008-02-19 11:40:12 +08:00
|
|
|
case OCFS2_CONTROL_HANDSHAKE_VALID:
|
2008-02-19 09:07:09 +08:00
|
|
|
ret = ocfs2_control_message(file, buf, count);
|
2008-02-19 11:40:12 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
ret = -EIO;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
2007-11-29 06:38:40 +08:00
|
|
|
}
|
|
|
|
|
2008-02-19 11:40:12 +08:00
|
|
|
/*
|
|
|
|
* This is a naive version. If we ever have a new protocol, we'll expand
|
|
|
|
* it. Probably using seq_file.
|
|
|
|
*/
|
2008-02-19 11:23:28 +08:00
|
|
|
static ssize_t ocfs2_control_read(struct file *file,
|
|
|
|
char __user *buf,
|
|
|
|
size_t count,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
2008-06-10 07:34:23 +08:00
|
|
|
ssize_t ret;
|
2008-02-19 11:40:12 +08:00
|
|
|
|
2008-06-10 07:34:23 +08:00
|
|
|
ret = simple_read_from_buffer(buf, count, ppos,
|
|
|
|
OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN);
|
2008-02-19 11:40:12 +08:00
|
|
|
|
|
|
|
/* Have we read the whole protocol list? */
|
2008-06-10 07:34:23 +08:00
|
|
|
if (ret > 0 && *ppos >= OCFS2_CONTROL_PROTO_LEN)
|
2008-02-19 11:40:12 +08:00
|
|
|
ocfs2_control_set_handshake_state(file,
|
|
|
|
OCFS2_CONTROL_HANDSHAKE_READ);
|
|
|
|
|
2008-06-10 07:34:23 +08:00
|
|
|
return ret;
|
2008-02-19 11:23:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int ocfs2_control_release(struct inode *inode, struct file *file)
|
|
|
|
{
|
2008-02-19 11:40:12 +08:00
|
|
|
struct ocfs2_control_private *p = file->private_data;
|
|
|
|
|
|
|
|
mutex_lock(&ocfs2_control_lock);
|
|
|
|
|
|
|
|
if (ocfs2_control_get_handshake_state(file) !=
|
|
|
|
OCFS2_CONTROL_HANDSHAKE_VALID)
|
|
|
|
goto out;
|
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
if (atomic_dec_and_test(&ocfs2_control_opened)) {
|
|
|
|
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();
|
|
|
|
}
|
2008-02-21 07:39:44 +08:00
|
|
|
/*
|
|
|
|
* Last valid close clears the node number and resets
|
|
|
|
* the locking protocol version
|
|
|
|
*/
|
2008-02-21 06:44:34 +08:00
|
|
|
ocfs2_control_this_node = -1;
|
2008-02-21 07:39:44 +08:00
|
|
|
running_proto.pv_major = 0;
|
2014-10-10 06:24:52 +08:00
|
|
|
running_proto.pv_minor = 0;
|
2008-02-19 11:23:28 +08:00
|
|
|
}
|
|
|
|
|
2008-02-19 11:40:12 +08:00
|
|
|
out:
|
|
|
|
list_del_init(&p->op_list);
|
|
|
|
file->private_data = NULL;
|
|
|
|
|
|
|
|
mutex_unlock(&ocfs2_control_lock);
|
|
|
|
|
|
|
|
kfree(p);
|
|
|
|
|
2008-02-19 11:23:28 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ocfs2_control_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
2008-02-19 11:40:12 +08:00
|
|
|
struct ocfs2_control_private *p;
|
|
|
|
|
|
|
|
p = kzalloc(sizeof(struct ocfs2_control_private), GFP_KERNEL);
|
|
|
|
if (!p)
|
|
|
|
return -ENOMEM;
|
2008-02-21 06:44:34 +08:00
|
|
|
p->op_this_node = -1;
|
2008-02-19 11:40:12 +08:00
|
|
|
|
|
|
|
mutex_lock(&ocfs2_control_lock);
|
|
|
|
file->private_data = p;
|
|
|
|
list_add(&p->op_list, &ocfs2_control_private_list);
|
|
|
|
mutex_unlock(&ocfs2_control_lock);
|
2008-02-19 11:23:28 +08:00
|
|
|
|
|
|
|
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,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
|
|
|
.llseek = default_llseek,
|
2008-02-19 11:23:28 +08:00
|
|
|
};
|
|
|
|
|
2008-04-21 16:49:26 +08:00
|
|
|
static struct miscdevice ocfs2_control_device = {
|
2008-02-19 11:23:28 +08:00
|
|
|
.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);
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
static void fsdlm_lock_ast_wrapper(void *astarg)
|
|
|
|
{
|
2010-01-30 06:46:44 +08:00
|
|
|
struct ocfs2_dlm_lksb *lksb = astarg;
|
2010-01-29 11:22:39 +08:00
|
|
|
int status = lksb->lksb_fsdlm.sb_status;
|
2008-02-21 06:29:27 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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)
|
2010-01-30 07:46:23 +08:00
|
|
|
lksb->lksb_conn->cc_proto->lp_unlock_ast(lksb, 0);
|
2008-02-21 06:29:27 +08:00
|
|
|
else
|
2010-01-30 07:46:23 +08:00
|
|
|
lksb->lksb_conn->cc_proto->lp_lock_ast(lksb);
|
2008-02-21 06:29:27 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void fsdlm_blocking_ast_wrapper(void *astarg, int level)
|
|
|
|
{
|
2010-01-30 06:46:44 +08:00
|
|
|
struct ocfs2_dlm_lksb *lksb = astarg;
|
2010-01-29 11:22:39 +08:00
|
|
|
|
2010-01-30 07:46:23 +08:00
|
|
|
lksb->lksb_conn->cc_proto->lp_blocking_ast(lksb, level);
|
2008-02-21 06:29:27 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int user_dlm_lock(struct ocfs2_cluster_connection *conn,
|
|
|
|
int mode,
|
2010-01-30 06:46:44 +08:00
|
|
|
struct ocfs2_dlm_lksb *lksb,
|
2008-02-21 06:29:27 +08:00
|
|
|
u32 flags,
|
|
|
|
void *name,
|
2010-01-29 11:22:39 +08:00
|
|
|
unsigned int namelen)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
|
|
|
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,
|
2010-01-29 11:22:39 +08:00
|
|
|
fsdlm_lock_ast_wrapper, lksb,
|
2008-02-21 06:29:27 +08:00
|
|
|
fsdlm_blocking_ast_wrapper);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int user_dlm_unlock(struct ocfs2_cluster_connection *conn,
|
2010-01-30 06:46:44 +08:00
|
|
|
struct ocfs2_dlm_lksb *lksb,
|
2010-01-29 11:22:39 +08:00
|
|
|
u32 flags)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = dlm_unlock(conn->cc_lockspace, lksb->lksb_fsdlm.sb_lkid,
|
2010-01-29 11:22:39 +08:00
|
|
|
flags, &lksb->lksb_fsdlm, lksb);
|
2008-02-21 06:29:27 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-01-30 06:46:44 +08:00
|
|
|
static int user_dlm_lock_status(struct ocfs2_dlm_lksb *lksb)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
|
|
|
return lksb->lksb_fsdlm.sb_status;
|
|
|
|
}
|
|
|
|
|
2010-01-30 06:46:44 +08:00
|
|
|
static int user_dlm_lvb_valid(struct ocfs2_dlm_lksb *lksb)
|
2009-06-20 06:14:13 +08:00
|
|
|
{
|
|
|
|
int invalid = lksb->lksb_fsdlm.sb_flags & DLM_SBF_VALNOTVALID;
|
|
|
|
|
|
|
|
return !invalid;
|
|
|
|
}
|
|
|
|
|
2010-01-30 06:46:44 +08:00
|
|
|
static void *user_dlm_lvb(struct ocfs2_dlm_lksb *lksb)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
2008-11-11 06:24:57 +08:00
|
|
|
if (!lksb->lksb_fsdlm.sb_lvbptr)
|
|
|
|
lksb->lksb_fsdlm.sb_lvbptr = (char *)lksb +
|
|
|
|
sizeof(struct dlm_lksb);
|
2008-02-21 06:29:27 +08:00
|
|
|
return (void *)(lksb->lksb_fsdlm.sb_lvbptr);
|
|
|
|
}
|
|
|
|
|
2010-01-30 06:46:44 +08:00
|
|
|
static void user_dlm_dump_lksb(struct ocfs2_dlm_lksb *lksb)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2008-07-22 05:29:16 +08:00
|
|
|
static int user_plock(struct ocfs2_cluster_connection *conn,
|
|
|
|
u64 ino,
|
|
|
|
struct file *file,
|
|
|
|
int cmd,
|
|
|
|
struct file_lock *fl)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* This more or less just demuxes the plock request into any
|
|
|
|
* one of three dlm calls.
|
|
|
|
*
|
|
|
|
* Internally, fs/dlm will pass these to a misc device, which
|
|
|
|
* a userspace daemon will read and write to.
|
|
|
|
*
|
|
|
|
* For now, cancel requests (which happen internally only),
|
|
|
|
* are turned into unlocks. Most of this function taken from
|
|
|
|
* gfs2_lock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (cmd == F_CANCELLK) {
|
|
|
|
cmd = F_SETLK;
|
|
|
|
fl->fl_type = F_UNLCK;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (IS_GETLK(cmd))
|
|
|
|
return dlm_posix_get(conn->cc_lockspace, ino, file, fl);
|
|
|
|
else if (fl->fl_type == F_UNLCK)
|
|
|
|
return dlm_posix_unlock(conn->cc_lockspace, ino, file, fl);
|
|
|
|
else
|
|
|
|
return dlm_posix_lock(conn->cc_lockspace, ino, file, cmd, fl);
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2014-01-22 07:48:25 +08:00
|
|
|
static void lvb_to_version(char *lvb, struct ocfs2_protocol_version *ver)
|
|
|
|
{
|
|
|
|
struct ocfs2_protocol_version *pv =
|
|
|
|
(struct ocfs2_protocol_version *)lvb;
|
|
|
|
/*
|
|
|
|
* ocfs2_protocol_version has two u8 variables, so we don't
|
|
|
|
* need any endian conversion.
|
|
|
|
*/
|
|
|
|
ver->pv_major = pv->pv_major;
|
|
|
|
ver->pv_minor = pv->pv_minor;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void version_to_lvb(struct ocfs2_protocol_version *ver, char *lvb)
|
|
|
|
{
|
|
|
|
struct ocfs2_protocol_version *pv =
|
|
|
|
(struct ocfs2_protocol_version *)lvb;
|
|
|
|
/*
|
|
|
|
* ocfs2_protocol_version has two u8 variables, so we don't
|
|
|
|
* need any endian conversion.
|
|
|
|
*/
|
|
|
|
pv->pv_major = ver->pv_major;
|
|
|
|
pv->pv_minor = ver->pv_minor;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void sync_wait_cb(void *arg)
|
|
|
|
{
|
|
|
|
struct ocfs2_cluster_connection *conn = arg;
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
complete(&lc->oc_sync_wait);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int sync_unlock(struct ocfs2_cluster_connection *conn,
|
|
|
|
struct dlm_lksb *lksb, char *name)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
|
|
|
|
error = dlm_unlock(conn->cc_lockspace, lksb->sb_lkid, 0, lksb, conn);
|
|
|
|
if (error) {
|
|
|
|
printk(KERN_ERR "%s lkid %x error %d\n",
|
|
|
|
name, lksb->sb_lkid, error);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
wait_for_completion(&lc->oc_sync_wait);
|
|
|
|
|
|
|
|
if (lksb->sb_status != -DLM_EUNLOCK) {
|
|
|
|
printk(KERN_ERR "%s lkid %x status %d\n",
|
|
|
|
name, lksb->sb_lkid, lksb->sb_status);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int sync_lock(struct ocfs2_cluster_connection *conn,
|
|
|
|
int mode, uint32_t flags,
|
|
|
|
struct dlm_lksb *lksb, char *name)
|
|
|
|
{
|
|
|
|
int error, status;
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
|
|
|
|
error = dlm_lock(conn->cc_lockspace, mode, lksb, flags,
|
|
|
|
name, strlen(name),
|
|
|
|
0, sync_wait_cb, conn, NULL);
|
|
|
|
if (error) {
|
|
|
|
printk(KERN_ERR "%s lkid %x flags %x mode %d error %d\n",
|
|
|
|
name, lksb->sb_lkid, flags, mode, error);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
wait_for_completion(&lc->oc_sync_wait);
|
|
|
|
|
|
|
|
status = lksb->sb_status;
|
|
|
|
|
|
|
|
if (status && status != -EAGAIN) {
|
|
|
|
printk(KERN_ERR "%s lkid %x flags %x mode %d status %d\n",
|
|
|
|
name, lksb->sb_lkid, flags, mode, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
return status;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int version_lock(struct ocfs2_cluster_connection *conn, int mode,
|
|
|
|
int flags)
|
|
|
|
{
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
return sync_lock(conn, mode, flags,
|
|
|
|
&lc->oc_version_lksb, VERSION_LOCK);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int version_unlock(struct ocfs2_cluster_connection *conn)
|
|
|
|
{
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
return sync_unlock(conn, &lc->oc_version_lksb, VERSION_LOCK);
|
|
|
|
}
|
|
|
|
|
2014-01-22 07:48:32 +08:00
|
|
|
/* get_protocol_version()
|
|
|
|
*
|
|
|
|
* To exchange ocfs2 versioning, we use the LVB of the version dlm lock.
|
|
|
|
* The algorithm is:
|
|
|
|
* 1. Attempt to take the lock in EX mode (non-blocking).
|
|
|
|
* 2. If successful (which means it is the first mount), write the
|
|
|
|
* version number and downconvert to PR lock.
|
|
|
|
* 3. If unsuccessful (returns -EAGAIN), read the version from the LVB after
|
|
|
|
* taking the PR lock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int get_protocol_version(struct ocfs2_cluster_connection *conn)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
struct ocfs2_protocol_version pv;
|
|
|
|
|
|
|
|
running_proto.pv_major =
|
|
|
|
ocfs2_user_plugin.sp_max_proto.pv_major;
|
|
|
|
running_proto.pv_minor =
|
|
|
|
ocfs2_user_plugin.sp_max_proto.pv_minor;
|
|
|
|
|
|
|
|
lc->oc_version_lksb.sb_lvbptr = lc->oc_lvb;
|
|
|
|
ret = version_lock(conn, DLM_LOCK_EX,
|
|
|
|
DLM_LKF_VALBLK|DLM_LKF_NOQUEUE);
|
|
|
|
if (!ret) {
|
|
|
|
conn->cc_version.pv_major = running_proto.pv_major;
|
|
|
|
conn->cc_version.pv_minor = running_proto.pv_minor;
|
|
|
|
version_to_lvb(&running_proto, lc->oc_lvb);
|
|
|
|
version_lock(conn, DLM_LOCK_PR, DLM_LKF_CONVERT|DLM_LKF_VALBLK);
|
|
|
|
} else if (ret == -EAGAIN) {
|
|
|
|
ret = version_lock(conn, DLM_LOCK_PR, DLM_LKF_VALBLK);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
lvb_to_version(lc->oc_lvb, &pv);
|
|
|
|
|
|
|
|
if ((pv.pv_major != running_proto.pv_major) ||
|
|
|
|
(pv.pv_minor > running_proto.pv_minor)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
conn->cc_version.pv_major = pv.pv_major;
|
|
|
|
conn->cc_version.pv_minor = pv.pv_minor;
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2014-01-22 07:48:22 +08:00
|
|
|
static void user_recover_prep(void *arg)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void user_recover_slot(void *arg, struct dlm_slot *slot)
|
|
|
|
{
|
|
|
|
struct ocfs2_cluster_connection *conn = arg;
|
|
|
|
printk(KERN_INFO "ocfs2: Node %d/%d down. Initiating recovery.\n",
|
|
|
|
slot->nodeid, slot->slot);
|
|
|
|
conn->cc_recovery_handler(slot->nodeid, conn->cc_recovery_data);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
static void user_recover_done(void *arg, struct dlm_slot *slots,
|
|
|
|
int num_slots, int our_slot,
|
|
|
|
uint32_t generation)
|
|
|
|
{
|
|
|
|
struct ocfs2_cluster_connection *conn = arg;
|
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < num_slots; i++)
|
|
|
|
if (slots[i].slot == our_slot) {
|
|
|
|
atomic_set(&lc->oc_this_node, slots[i].nodeid);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
lc->oc_our_slot = our_slot;
|
2014-01-22 07:48:32 +08:00
|
|
|
wake_up(&lc->oc_wait);
|
2014-01-22 07:48:22 +08:00
|
|
|
}
|
|
|
|
|
2014-01-22 07:48:37 +08:00
|
|
|
static const struct dlm_lockspace_ops ocfs2_ls_ops = {
|
2014-01-22 07:48:22 +08:00
|
|
|
.recover_prep = user_recover_prep,
|
|
|
|
.recover_slot = user_recover_slot,
|
|
|
|
.recover_done = user_recover_done,
|
|
|
|
};
|
|
|
|
|
2014-01-22 07:48:32 +08:00
|
|
|
static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn)
|
|
|
|
{
|
|
|
|
version_unlock(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;
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
|
|
|
|
{
|
|
|
|
dlm_lockspace_t *fsdlm;
|
2014-01-22 07:48:23 +08:00
|
|
|
struct ocfs2_live_connection *lc;
|
2014-01-22 07:48:32 +08:00
|
|
|
int rc, ops_rv;
|
2008-02-21 06:29:27 +08:00
|
|
|
|
|
|
|
BUG_ON(conn == NULL);
|
|
|
|
|
2014-01-22 07:48:23 +08:00
|
|
|
lc = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL);
|
2015-04-15 06:42:59 +08:00
|
|
|
if (!lc)
|
|
|
|
return -ENOMEM;
|
2014-01-22 07:48:23 +08:00
|
|
|
|
2014-01-22 07:48:32 +08:00
|
|
|
init_waitqueue_head(&lc->oc_wait);
|
|
|
|
init_completion(&lc->oc_sync_wait);
|
|
|
|
atomic_set(&lc->oc_this_node, 0);
|
|
|
|
conn->cc_private = lc;
|
|
|
|
lc->oc_type = NO_CONTROLD;
|
|
|
|
|
|
|
|
rc = dlm_new_lockspace(conn->cc_name, conn->cc_cluster_name,
|
|
|
|
DLM_LSFL_FS, DLM_LVB_LEN,
|
|
|
|
&ocfs2_ls_ops, conn, &ops_rv, &fsdlm);
|
|
|
|
if (rc)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (ops_rv == -EOPNOTSUPP) {
|
|
|
|
lc->oc_type = WITH_CONTROLD;
|
|
|
|
printk(KERN_NOTICE "ocfs2: You seem to be using an older "
|
|
|
|
"version of dlm_controld and/or ocfs2-tools."
|
|
|
|
" Please consider upgrading.\n");
|
|
|
|
} else if (ops_rv) {
|
|
|
|
rc = ops_rv;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
conn->cc_lockspace = fsdlm;
|
|
|
|
|
2014-01-22 07:48:23 +08:00
|
|
|
rc = ocfs2_live_connection_attach(conn, lc);
|
2008-02-21 06:29:27 +08:00
|
|
|
if (rc)
|
|
|
|
goto out;
|
|
|
|
|
2014-01-22 07:48:32 +08:00
|
|
|
if (lc->oc_type == NO_CONTROLD) {
|
|
|
|
rc = get_protocol_version(conn);
|
|
|
|
if (rc) {
|
|
|
|
printk(KERN_ERR "ocfs2: Could not determine"
|
|
|
|
" locking version\n");
|
|
|
|
user_cluster_disconnect(conn);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
wait_event(lc->oc_wait, (atomic_read(&lc->oc_this_node) > 0));
|
|
|
|
}
|
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
/*
|
|
|
|
* 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 "
|
2014-01-22 07:48:32 +08:00
|
|
|
"%u.%u because negotiated protocol is %u.%u\n",
|
2008-02-21 06:29:27 +08:00
|
|
|
conn->cc_version.pv_major, conn->cc_version.pv_minor,
|
|
|
|
running_proto.pv_major, running_proto.pv_minor);
|
|
|
|
rc = -EPROTO;
|
2014-01-22 07:48:23 +08:00
|
|
|
ocfs2_live_connection_drop(lc);
|
|
|
|
lc = NULL;
|
2008-02-21 06:29:27 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2015-04-15 06:42:42 +08:00
|
|
|
if (rc)
|
2014-01-22 07:48:23 +08:00
|
|
|
kfree(lc);
|
2008-02-21 06:29:27 +08:00
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2014-01-22 07:48:24 +08:00
|
|
|
static int user_cluster_this_node(struct ocfs2_cluster_connection *conn,
|
|
|
|
unsigned int *this_node)
|
2008-02-21 06:29:27 +08:00
|
|
|
{
|
|
|
|
int rc;
|
2014-01-22 07:48:24 +08:00
|
|
|
struct ocfs2_live_connection *lc = conn->cc_private;
|
2008-02-21 06:29:27 +08:00
|
|
|
|
2014-01-22 07:48:24 +08:00
|
|
|
if (lc->oc_type == WITH_CONTROLD)
|
|
|
|
rc = ocfs2_control_get_this_node();
|
2014-01-22 07:48:32 +08:00
|
|
|
else if (lc->oc_type == NO_CONTROLD)
|
|
|
|
rc = atomic_read(&lc->oc_this_node);
|
2014-01-22 07:48:24 +08:00
|
|
|
else
|
|
|
|
rc = -EINVAL;
|
2014-01-22 07:48:32 +08:00
|
|
|
|
2008-02-21 06:29:27 +08:00
|
|
|
if (rc < 0)
|
|
|
|
return rc;
|
|
|
|
|
|
|
|
*this_node = rc;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-05-10 09:49:29 +08:00
|
|
|
static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
|
2008-02-21 06:29:27 +08:00
|
|
|
.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,
|
2009-06-20 06:14:13 +08:00
|
|
|
.lvb_valid = user_dlm_lvb_valid,
|
2008-02-21 06:29:27 +08:00
|
|
|
.lock_lvb = user_dlm_lvb,
|
2008-07-22 05:29:16 +08:00
|
|
|
.plock = user_plock,
|
2008-02-21 06:29:27 +08:00
|
|
|
.dump_lksb = user_dlm_dump_lksb,
|
|
|
|
};
|
|
|
|
|
2008-05-10 09:49:29 +08:00
|
|
|
static struct ocfs2_stack_plugin ocfs2_user_plugin = {
|
2008-02-21 06:29:27 +08:00
|
|
|
.sp_name = "user",
|
2008-05-10 09:49:29 +08:00
|
|
|
.sp_ops = &ocfs2_user_plugin_ops,
|
2008-02-21 06:29:27 +08:00
|
|
|
.sp_owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2008-05-10 09:49:29 +08:00
|
|
|
static int __init ocfs2_user_plugin_init(void)
|
2008-02-19 11:23:28 +08:00
|
|
|
{
|
2008-02-21 06:29:27 +08:00
|
|
|
int rc;
|
|
|
|
|
|
|
|
rc = ocfs2_control_init();
|
|
|
|
if (!rc) {
|
2008-05-10 09:49:29 +08:00
|
|
|
rc = ocfs2_stack_glue_register(&ocfs2_user_plugin);
|
2008-02-21 06:29:27 +08:00
|
|
|
if (rc)
|
|
|
|
ocfs2_control_exit();
|
|
|
|
}
|
|
|
|
|
|
|
|
return rc;
|
2008-02-19 11:23:28 +08:00
|
|
|
}
|
|
|
|
|
2008-05-10 09:49:29 +08:00
|
|
|
static void __exit ocfs2_user_plugin_exit(void)
|
2007-11-29 06:38:40 +08:00
|
|
|
{
|
2008-05-10 09:49:29 +08:00
|
|
|
ocfs2_stack_glue_unregister(&ocfs2_user_plugin);
|
2008-02-19 11:23:28 +08:00
|
|
|
ocfs2_control_exit();
|
2007-11-29 06:38:40 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
MODULE_AUTHOR("Oracle");
|
|
|
|
MODULE_DESCRIPTION("ocfs2 driver for userspace cluster stacks");
|
|
|
|
MODULE_LICENSE("GPL");
|
2008-05-10 09:49:29 +08:00
|
|
|
module_init(ocfs2_user_plugin_init);
|
|
|
|
module_exit(ocfs2_user_plugin_exit);
|