b77b4a4815
So far, at mount time, gfs2 would take the freeze glock in shared mode and then immediately drop it again, turning it into a cached glock that can be reclaimed at any time. To freeze the filesystem cluster-wide, the node initiating the freeze would take the freeze glock in exclusive mode, which would cause the freeze glock's freeze_go_sync() callback to run on each node. There, gfs2 would freeze the filesystem and schedule gfs2_freeze_func() to run. gfs2_freeze_func() would re-acquire the freeze glock in shared mode, thaw the filesystem, and drop the freeze glock again. The initiating node would keep the freeze glock held in exclusive mode. To thaw the filesystem, the initiating node would drop the freeze glock again, which would allow gfs2_freeze_func() to resume on all nodes, leaving the filesystem in the thawed state. It turns out that in freeze_go_sync(), we cannot reliably and safely freeze the filesystem. This is primarily because the final unmount of a filesystem takes a write lock on the s_umount rw semaphore before calling into gfs2_put_super(), and freeze_go_sync() needs to call freeze_super() which also takes a write lock on the same semaphore, causing a deadlock. We could work around this by trying to take an active reference on the super block first, which would prevent unmount from running at the same time. But that can fail, and freeze_go_sync() isn't actually allowed to fail. To get around this, this patch changes the freeze glock locking scheme as follows: At mount time, each node takes the freeze glock in shared mode. To freeze a filesystem, the initiating node first freezes the filesystem locally and then drops and re-acquires the freeze glock in exclusive mode. All other nodes notice that there is contention on the freeze glock in their go_callback callbacks, and they schedule gfs2_freeze_func() to run. There, they freeze the filesystem locally and drop and re-acquire the freeze glock before re-thawing the filesystem. This is happening outside of the glock state engine, so there, we are allowed to fail. From a cluster point of view, taking and immediately dropping a glock is indistinguishable from taking the glock and only dropping it upon contention, so this new scheme is compatible with the old one. Thanks to Li Dong <lidong@vivo.com> for reporting a locking bug in gfs2_freeze_func() in a previous version of this commit. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
67 lines
2.3 KiB
C
67 lines
2.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
|
*/
|
|
|
|
#ifndef __SUPER_DOT_H__
|
|
#define __SUPER_DOT_H__
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/dcache.h>
|
|
#include "incore.h"
|
|
|
|
/* Supported fs format version range */
|
|
#define GFS2_FS_FORMAT_MIN (1801)
|
|
#define GFS2_FS_FORMAT_MAX (1802)
|
|
|
|
extern void gfs2_lm_unmount(struct gfs2_sbd *sdp);
|
|
|
|
static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
|
|
{
|
|
unsigned int x;
|
|
spin_lock(&sdp->sd_jindex_spin);
|
|
x = sdp->sd_journals;
|
|
spin_unlock(&sdp->sd_jindex_spin);
|
|
return x;
|
|
}
|
|
|
|
extern void gfs2_jindex_free(struct gfs2_sbd *sdp);
|
|
|
|
extern struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid);
|
|
extern int gfs2_jdesc_check(struct gfs2_jdesc *jd);
|
|
extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
|
|
struct gfs2_inode **ipp);
|
|
|
|
extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
|
|
extern void gfs2_make_fs_ro(struct gfs2_sbd *sdp);
|
|
extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
|
|
extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
|
|
extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
|
|
s64 dinodes);
|
|
extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc,
|
|
const void *buf);
|
|
extern void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc,
|
|
void *buf);
|
|
extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh);
|
|
extern int gfs2_statfs_sync(struct super_block *sb, int type);
|
|
extern void gfs2_freeze_func(struct work_struct *work);
|
|
extern void gfs2_thaw_freeze_initiator(struct super_block *sb);
|
|
|
|
extern void free_local_statfs_inodes(struct gfs2_sbd *sdp);
|
|
extern struct inode *find_local_statfs_inode(struct gfs2_sbd *sdp,
|
|
unsigned int index);
|
|
extern void free_sbd(struct gfs2_sbd *sdp);
|
|
|
|
extern struct file_system_type gfs2_fs_type;
|
|
extern struct file_system_type gfs2meta_fs_type;
|
|
extern const struct export_operations gfs2_export_ops;
|
|
extern const struct super_operations gfs2_super_ops;
|
|
extern const struct dentry_operations gfs2_dops;
|
|
|
|
extern const struct xattr_handler *gfs2_xattr_handlers_max[];
|
|
extern const struct xattr_handler **gfs2_xattr_handlers_min;
|
|
|
|
#endif /* __SUPER_DOT_H__ */
|
|
|