#include <sys/zfs_vfsops.h>
#include <sys/zfs_vnops.h>
#include <sys/zfs_znode.h>
+#include <sys/zfs_ctldir.h>
#include <sys/zpl.h>
}
/*
+ * 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)
+{
+ zfs_dirty_inode(ip, flags);
+}
+#else
+static void
+zpl_dirty_inode(struct inode *ip)
+{
+ zfs_dirty_inode(ip, 0);
+}
+#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
* 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. The ->evict_inode()
- * callback must minimally truncate the inode pages, and call
- * end_writeback() to complete all outstanding writeback for the
- * inode. After this is complete evict inode can cleanup any
+ * 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)
{
- truncate_inode_pages(&ip->i_data, 0);
- end_writeback(ip);
+ truncate_setsize(ip, 0);
+ clear_inode(ip);
zfs_inactive(ip);
}
static void
zpl_inode_delete(struct inode *ip)
{
- truncate_inode_pages(&ip->i_data, 0);
+ truncate_setsize(ip, 0);
clear_inode(ip);
}
}
static int
+zpl_sync_fs(struct super_block *sb, int wait)
+{
+ cred_t *cr = CRED();
+ int error;
+
+ crhold(cr);
+ error = -zfs_sync(sb, wait, cr);
+ crfree(cr);
+ ASSERT3S(error, <=, 0);
+
+ return (error);
+}
+
+static int
zpl_statfs(struct dentry *dentry, struct kstatfs *statp)
{
int error;
}
static int
-zpl_show_options(struct seq_file *seq, struct vfsmount *vfsp)
+zpl_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+ int error;
+ error = -zfs_remount(sb, flags, data);
+ ASSERT3S(error, <=, 0);
+
+ return (error);
+}
+
+static void
+zpl_umount_begin(struct super_block *sb)
{
- struct super_block *sb = vfsp->mnt_sb;
zfs_sb_t *zsb = sb->s_fs_info;
+ int count;
/*
- * The Linux VFS automatically handles the following flags:
- * MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, MNT_NOATIME, MNT_READONLY
+ * Best effort to unmount snapshots in .zfs/snapshot/. Normally this
+ * isn't required because snapshots have the MNT_SHRINKABLE flag set.
*/
+ if (zsb->z_ctldir)
+ (void) zfsctl_unmount_snapshots(zsb, MNT_FORCE, &count);
+}
+
+/*
+ * The Linux VFS automatically handles the following flags:
+ * MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, MNT_NOATIME, MNT_READONLY
+ */
+#ifdef HAVE_SHOW_OPTIONS_WITH_DENTRY
+static int
+zpl_show_options(struct seq_file *seq, struct dentry *root)
+{
+ zfs_sb_t *zsb = root->d_sb->s_fs_info;
+
+ seq_printf(seq, ",%s", zsb->z_flags & ZSB_XATTR ? "xattr" : "noxattr");
+
+ return (0);
+}
+#else
+static int
+zpl_show_options(struct seq_file *seq, struct vfsmount *vfsp)
+{
+ zfs_sb_t *zsb = vfsp->mnt_sb->s_fs_info;
- if (zsb->z_flags & ZSB_XATTR_USER)
- seq_printf(seq, ",%s", "xattr");
+ seq_printf(seq, ",%s", zsb->z_flags & ZSB_XATTR ? "xattr" : "noxattr");
return (0);
}
+#endif /* HAVE_SHOW_OPTIONS_WITH_DENTRY */
static int
zpl_fill_super(struct super_block *sb, void *data, int silent)
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, 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)
{
-#ifdef HAVE_SNAPSHOT
+ zfs_preumount(sb);
+ kill_anon_super(sb);
+}
+
+#ifdef HAVE_SHRINK
+/*
+ * Linux 3.1 - 3.x API
+ *
+ * The Linux 3.1 API introduced per-sb cache shrinkers to replace the
+ * global ones. This allows us a mechanism to cleanly target a specific
+ * zfs file system when the dnode and inode caches grow too large.
+ *
+ * In addition, the 3.0 kernel added the iterate_supers_type() helper
+ * function which is used to safely walk all of the zfs file systems.
+ */
+static void
+zpl_prune_sb(struct super_block *sb, void *arg)
+{
+ int objects = 0;
+ int error;
+
+ error = -zfs_sb_prune(sb, *(unsigned long *)arg, &objects);
+ ASSERT3S(error, <=, 0);
+
+ return;
+}
+
+void
+zpl_prune_sbs(int64_t bytes_to_scan, void *private)
+{
+ unsigned long nr_to_scan = (bytes_to_scan / sizeof(znode_t));
+
+ iterate_supers_type(&zpl_fs_type, zpl_prune_sb, &nr_to_scan);
+ kmem_reap();
+}
+#else
+/*
+ * Linux 2.6.x - 3.0 API
+ *
+ * These are best effort interfaces are provided by the SPL to induce
+ * the Linux VM subsystem to reclaim a fraction of the both dnode and
+ * inode caches. Ideally, we want to just target the zfs file systems
+ * however our only option is to reclaim from them all.
+ */
+void
+zpl_prune_sbs(int64_t bytes_to_scan, void *private)
+{
+ unsigned long nr_to_scan = (bytes_to_scan / sizeof(znode_t));
+
+ shrink_dcache_memory(nr_to_scan, GFP_KERNEL);
+ shrink_icache_memory(nr_to_scan, GFP_KERNEL);
+ kmem_reap();
+}
+#endif /* HAVE_SHRINK */
+
+#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;
- if (zsb && dmu_objset_is_snapshot(zsb->z_os))
- zfs_snap_destroy(zsb);
-#endif /* HAVE_SNAPSHOT */
+ mutex_enter(&zsb->z_znodes_lock);
+ nr = zsb->z_nr_znodes;
+ mutex_exit(&zsb->z_znodes_lock);
- kill_anon_super(sb);
+ 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)
+{
+ arc_adjust_meta(nr_to_scan * sizeof(znode_t), B_FALSE);
}
+#endif /* HAVE_FREE_CACHED_OBJECTS */
const struct super_operations zpl_super_operations = {
- .alloc_inode = zpl_inode_alloc,
- .destroy_inode = zpl_inode_destroy,
- .dirty_inode = NULL,
- .write_inode = NULL,
- .drop_inode = NULL,
+ .alloc_inode = zpl_inode_alloc,
+ .destroy_inode = zpl_inode_destroy,
+ .dirty_inode = zpl_dirty_inode,
+ .write_inode = NULL,
+ .drop_inode = NULL,
#ifdef HAVE_EVICT_INODE
- .evict_inode = zpl_evict_inode,
+ .evict_inode = zpl_evict_inode,
#else
- .clear_inode = zpl_clear_inode,
- .delete_inode = zpl_inode_delete,
+ .clear_inode = zpl_clear_inode,
+ .delete_inode = zpl_inode_delete,
#endif /* HAVE_EVICT_INODE */
- .put_super = zpl_put_super,
- .write_super = NULL,
- .sync_fs = NULL,
- .freeze_fs = NULL,
- .unfreeze_fs = NULL,
- .statfs = zpl_statfs,
- .remount_fs = NULL,
- .show_options = zpl_show_options,
- .show_stats = NULL,
+ .put_super = zpl_put_super,
+ .sync_fs = zpl_sync_fs,
+ .statfs = zpl_statfs,
+ .remount_fs = zpl_remount_fs,
+ .umount_begin = zpl_umount_begin,
+ .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 */
};
-#if 0
-const struct export_operations zpl_export_operations = {
- .fh_to_dentry = NULL,
- .fh_to_parent = NULL,
- .get_parent = NULL,
-};
-#endif
-
struct file_system_type zpl_fs_type = {
- .owner = THIS_MODULE,
- .name = ZFS_DRIVER,
- .get_sb = zpl_get_sb,
- .kill_sb = zpl_kill_sb,
+ .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,
};