mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 18:11:00 +03:00
278bee9319
Re-factor the .zfs/snapshot auto-mouting code to take in to account changes made to the upstream kernels. And to lay the groundwork for enabling access to .zfs snapshots via NFS clients. This patch makes the following core improvements. * All actively auto-mounted snapshots are now tracked in two global trees which are indexed by snapshot name and objset id respectively. This allows for fast lookups of any auto-mounted snapshot regardless without needing access to the parent dataset. * Snapshot entries are added to the tree in zfsctl_snapshot_mount(). However, they are now removed from the tree in the context of the unmount process. This eliminates the need complicated error logic in zfsctl_snapshot_unmount() to handle unmount failures. * References are now taken on the snapshot entries in the tree to ensure they always remain valid while a task is outstanding. * The MNT_SHRINKABLE flag is set on the snapshot vfsmount_t right after the auto-mount succeeds. This allows to kernel to unmount idle auto-mounted snapshots if needed removing the need for the zfsctl_unmount_snapshots() function. * Snapshots in active use will not be automatically unmounted. As long as at least one dentry is revalidated every zfs_expire_snapshot/2 seconds the auto-unmount expiration timer will be extended. * Commit torvalds/linux@bafc9b7 caused snapshots auto-mounted by ZFS to be immediately unmounted when the dentry was revalidated. This was a consequence of ZFS invaliding all snapdir dentries to ensure that negative dentries didn't mask new snapshots. This patch modifies the behavior such that only negative dentries are invalidated. This solves the issue and may result in a performance improvement. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3589 Closes #3344 Closes #3295 Closes #3257 Closes #3243 Closes #3030 Closes #2841
368 lines
8.7 KiB
C
368 lines
8.7 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright (c) 2011, Lawrence Livermore National Security, LLC.
|
|
*/
|
|
|
|
|
|
#include <sys/zfs_vfsops.h>
|
|
#include <sys/zfs_vnops.h>
|
|
#include <sys/zfs_znode.h>
|
|
#include <sys/zfs_ctldir.h>
|
|
#include <sys/zpl.h>
|
|
|
|
|
|
static struct inode *
|
|
zpl_inode_alloc(struct super_block *sb)
|
|
{
|
|
struct inode *ip;
|
|
|
|
VERIFY3S(zfs_inode_alloc(sb, &ip), ==, 0);
|
|
ip->i_version = 1;
|
|
|
|
return (ip);
|
|
}
|
|
|
|
static void
|
|
zpl_inode_destroy(struct inode *ip)
|
|
{
|
|
ASSERT(atomic_read(&ip->i_count) == 0);
|
|
zfs_inode_destroy(ip);
|
|
}
|
|
|
|
/*
|
|
* Called from __mark_inode_dirty() to reflect that something in the
|
|
* inode has changed. We use it to ensure the znode system attributes
|
|
* are always strictly update to date with respect to the inode.
|
|
*/
|
|
#ifdef HAVE_DIRTY_INODE_WITH_FLAGS
|
|
static void
|
|
zpl_dirty_inode(struct inode *ip, int flags)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
zfs_dirty_inode(ip, flags);
|
|
spl_fstrans_unmark(cookie);
|
|
}
|
|
#else
|
|
static void
|
|
zpl_dirty_inode(struct inode *ip)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
zfs_dirty_inode(ip, 0);
|
|
spl_fstrans_unmark(cookie);
|
|
}
|
|
#endif /* HAVE_DIRTY_INODE_WITH_FLAGS */
|
|
|
|
/*
|
|
* When ->drop_inode() is called its return value indicates if the
|
|
* inode should be evicted from the inode cache. If the inode is
|
|
* unhashed and has no links the default policy is to evict it
|
|
* immediately.
|
|
*
|
|
* Prior to 2.6.36 this eviction was accomplished by the vfs calling
|
|
* ->delete_inode(). It was ->delete_inode()'s responsibility to
|
|
* truncate the inode pages and call clear_inode(). The call to
|
|
* clear_inode() synchronously invalidates all the buffers and
|
|
* calls ->clear_inode(). It was ->clear_inode()'s responsibility
|
|
* to cleanup and filesystem specific data before freeing the inode.
|
|
*
|
|
* This elaborate mechanism was replaced by ->evict_inode() which
|
|
* does the job of both ->delete_inode() and ->clear_inode(). It
|
|
* will be called exactly once, and when it returns the inode must
|
|
* be in a state where it can simply be freed.i
|
|
*
|
|
* The ->evict_inode() callback must minimally truncate the inode pages,
|
|
* and call clear_inode(). For 2.6.35 and later kernels this will
|
|
* simply update the inode state, with the sync occurring before the
|
|
* truncate in evict(). For earlier kernels clear_inode() maps to
|
|
* end_writeback() which is responsible for completing all outstanding
|
|
* write back. In either case, once this is done it is safe to cleanup
|
|
* any remaining inode specific data via zfs_inactive().
|
|
* remaining filesystem specific data.
|
|
*/
|
|
#ifdef HAVE_EVICT_INODE
|
|
static void
|
|
zpl_evict_inode(struct inode *ip)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
truncate_setsize(ip, 0);
|
|
clear_inode(ip);
|
|
zfs_inactive(ip);
|
|
spl_fstrans_unmark(cookie);
|
|
}
|
|
|
|
#else
|
|
|
|
static void
|
|
zpl_drop_inode(struct inode *ip)
|
|
{
|
|
generic_delete_inode(ip);
|
|
}
|
|
|
|
static void
|
|
zpl_clear_inode(struct inode *ip)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
zfs_inactive(ip);
|
|
spl_fstrans_unmark(cookie);
|
|
}
|
|
|
|
static void
|
|
zpl_inode_delete(struct inode *ip)
|
|
{
|
|
truncate_setsize(ip, 0);
|
|
clear_inode(ip);
|
|
}
|
|
#endif /* HAVE_EVICT_INODE */
|
|
|
|
static void
|
|
zpl_put_super(struct super_block *sb)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
int error;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
error = -zfs_umount(sb);
|
|
spl_fstrans_unmark(cookie);
|
|
ASSERT3S(error, <=, 0);
|
|
}
|
|
|
|
static int
|
|
zpl_sync_fs(struct super_block *sb, int wait)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
cred_t *cr = CRED();
|
|
int error;
|
|
|
|
crhold(cr);
|
|
cookie = spl_fstrans_mark();
|
|
error = -zfs_sync(sb, wait, cr);
|
|
spl_fstrans_unmark(cookie);
|
|
crfree(cr);
|
|
ASSERT3S(error, <=, 0);
|
|
|
|
return (error);
|
|
}
|
|
|
|
static int
|
|
zpl_statfs(struct dentry *dentry, struct kstatfs *statp)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
int error;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
error = -zfs_statvfs(dentry, statp);
|
|
spl_fstrans_unmark(cookie);
|
|
ASSERT3S(error, <=, 0);
|
|
|
|
return (error);
|
|
}
|
|
|
|
static int
|
|
zpl_remount_fs(struct super_block *sb, int *flags, char *data)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
int error;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
error = -zfs_remount(sb, flags, data);
|
|
spl_fstrans_unmark(cookie);
|
|
ASSERT3S(error, <=, 0);
|
|
|
|
return (error);
|
|
}
|
|
|
|
/*
|
|
* ZFS specific features must be explicitly handled here, the VFS will
|
|
* automatically handled the following generic functionality.
|
|
*
|
|
* MNT_NOSUID,
|
|
* MNT_NODEV,
|
|
* MNT_NOEXEC,
|
|
* MNT_NOATIME,
|
|
* MNT_NODIRATIME,
|
|
* MNT_READONLY,
|
|
* MNT_STRICTATIME,
|
|
* MS_SYNCHRONOUS,
|
|
* MS_DIRSYNC,
|
|
* MS_MANDLOCK.
|
|
*/
|
|
static int
|
|
__zpl_show_options(struct seq_file *seq, zfs_sb_t *zsb)
|
|
{
|
|
seq_printf(seq, ",%s", zsb->z_flags & ZSB_XATTR ? "xattr" : "noxattr");
|
|
|
|
#ifdef CONFIG_FS_POSIX_ACL
|
|
switch (zsb->z_acl_type) {
|
|
case ZFS_ACLTYPE_POSIXACL:
|
|
seq_puts(seq, ",posixacl");
|
|
break;
|
|
default:
|
|
seq_puts(seq, ",noacl");
|
|
break;
|
|
}
|
|
#endif /* CONFIG_FS_POSIX_ACL */
|
|
|
|
return (0);
|
|
}
|
|
|
|
#ifdef HAVE_SHOW_OPTIONS_WITH_DENTRY
|
|
static int
|
|
zpl_show_options(struct seq_file *seq, struct dentry *root)
|
|
{
|
|
return (__zpl_show_options(seq, root->d_sb->s_fs_info));
|
|
}
|
|
#else
|
|
static int
|
|
zpl_show_options(struct seq_file *seq, struct vfsmount *vfsp)
|
|
{
|
|
return (__zpl_show_options(seq, vfsp->mnt_sb->s_fs_info));
|
|
}
|
|
#endif /* HAVE_SHOW_OPTIONS_WITH_DENTRY */
|
|
|
|
static int
|
|
zpl_fill_super(struct super_block *sb, void *data, int silent)
|
|
{
|
|
fstrans_cookie_t cookie;
|
|
int error;
|
|
|
|
cookie = spl_fstrans_mark();
|
|
error = -zfs_domount(sb, data, silent);
|
|
spl_fstrans_unmark(cookie);
|
|
ASSERT3S(error, <=, 0);
|
|
|
|
return (error);
|
|
}
|
|
|
|
#ifdef HAVE_MOUNT_NODEV
|
|
static struct dentry *
|
|
zpl_mount(struct file_system_type *fs_type, int flags,
|
|
const char *osname, void *data)
|
|
{
|
|
zpl_mount_data_t zmd = { osname, data };
|
|
|
|
return (mount_nodev(fs_type, flags, &zmd, zpl_fill_super));
|
|
}
|
|
#else
|
|
static int
|
|
zpl_get_sb(struct file_system_type *fs_type, int flags,
|
|
const char *osname, void *data, struct vfsmount *mnt)
|
|
{
|
|
zpl_mount_data_t zmd = { osname, data };
|
|
|
|
return (get_sb_nodev(fs_type, flags, &zmd, zpl_fill_super, mnt));
|
|
}
|
|
#endif /* HAVE_MOUNT_NODEV */
|
|
|
|
static void
|
|
zpl_kill_sb(struct super_block *sb)
|
|
{
|
|
zfs_preumount(sb);
|
|
kill_anon_super(sb);
|
|
|
|
#ifdef HAVE_S_INSTANCES_LIST_HEAD
|
|
sb->s_instances.next = &(zpl_fs_type.fs_supers);
|
|
#endif /* HAVE_S_INSTANCES_LIST_HEAD */
|
|
}
|
|
|
|
void
|
|
zpl_prune_sb(int64_t nr_to_scan, void *arg)
|
|
{
|
|
struct super_block *sb = (struct super_block *)arg;
|
|
int objects = 0;
|
|
|
|
(void) -zfs_sb_prune(sb, nr_to_scan, &objects);
|
|
}
|
|
|
|
#ifdef HAVE_NR_CACHED_OBJECTS
|
|
static int
|
|
zpl_nr_cached_objects(struct super_block *sb)
|
|
{
|
|
zfs_sb_t *zsb = sb->s_fs_info;
|
|
int nr;
|
|
|
|
mutex_enter(&zsb->z_znodes_lock);
|
|
nr = zsb->z_nr_znodes;
|
|
mutex_exit(&zsb->z_znodes_lock);
|
|
|
|
return (nr);
|
|
}
|
|
#endif /* HAVE_NR_CACHED_OBJECTS */
|
|
|
|
#ifdef HAVE_FREE_CACHED_OBJECTS
|
|
/*
|
|
* Attempt to evict some meta data from the cache. The ARC operates in
|
|
* terms of bytes while the Linux VFS uses objects. Now because this is
|
|
* just a best effort eviction and the exact values aren't critical so we
|
|
* extrapolate from an object count to a byte size using the znode_t size.
|
|
*/
|
|
static void
|
|
zpl_free_cached_objects(struct super_block *sb, int nr_to_scan)
|
|
{
|
|
/* noop */
|
|
}
|
|
#endif /* HAVE_FREE_CACHED_OBJECTS */
|
|
|
|
const struct super_operations zpl_super_operations = {
|
|
.alloc_inode = zpl_inode_alloc,
|
|
.destroy_inode = zpl_inode_destroy,
|
|
.dirty_inode = zpl_dirty_inode,
|
|
.write_inode = NULL,
|
|
#ifdef HAVE_EVICT_INODE
|
|
.evict_inode = zpl_evict_inode,
|
|
#else
|
|
.drop_inode = zpl_drop_inode,
|
|
.clear_inode = zpl_clear_inode,
|
|
.delete_inode = zpl_inode_delete,
|
|
#endif /* HAVE_EVICT_INODE */
|
|
.put_super = zpl_put_super,
|
|
.sync_fs = zpl_sync_fs,
|
|
.statfs = zpl_statfs,
|
|
.remount_fs = zpl_remount_fs,
|
|
.show_options = zpl_show_options,
|
|
.show_stats = NULL,
|
|
#ifdef HAVE_NR_CACHED_OBJECTS
|
|
.nr_cached_objects = zpl_nr_cached_objects,
|
|
#endif /* HAVE_NR_CACHED_OBJECTS */
|
|
#ifdef HAVE_FREE_CACHED_OBJECTS
|
|
.free_cached_objects = zpl_free_cached_objects,
|
|
#endif /* HAVE_FREE_CACHED_OBJECTS */
|
|
};
|
|
|
|
struct file_system_type zpl_fs_type = {
|
|
.owner = THIS_MODULE,
|
|
.name = ZFS_DRIVER,
|
|
#ifdef HAVE_MOUNT_NODEV
|
|
.mount = zpl_mount,
|
|
#else
|
|
.get_sb = zpl_get_sb,
|
|
#endif /* HAVE_MOUNT_NODEV */
|
|
.kill_sb = zpl_kill_sb,
|
|
};
|