path: root/fs/ceph/snap.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>

#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/decode.h>

/* unused map expires after 5 minutes */
#define CEPH_SNAPID_MAP_TIMEOUT	(5 * 60 * HZ)

/*
 * Snapshots in ceph are driven in large part by cooperation from the
 * client.  In contrast to local file systems or file servers that
 * implement snapshots at a single point in the system, ceph's
 * distributed access to storage requires clients to help decide
 * whether a write logically occurs before or after a recently created
 * snapshot.
 *
 * This provides a perfect instantanous client-wide snapshot.  Between
 * clients, however, snapshots may appear to be applied at slightly
 * different points in time, depending on delays in delivering the
 * snapshot notification.
 *
 * Snapshots are _not_ file system-wide.  Instead, each snapshot
 * applies to the subdirectory nested beneath some directory.  This
 * effectively divides the hierarchy into multiple "realms," where all
 * of the files contained by each realm share the same set of
 * snapshots.  An individual realm's snap set contains snapshots
 * explicitly created on that realm, as well as any snaps in its
 * parent's snap set _after_ the point at which the parent became it's
 * parent (due to, say, a rename).  Similarly, snaps from prior parents
 * during the time intervals during which they were the parent are included.
 *
 * The client is spared most of this detail, fortunately... it must only
 * maintains a hierarchy of realms reflecting the current parent/child
 * realm relationship, and for each realm has an explicit list of snaps
 * inherited from prior parents.
 *
 * A snap_realm struct is maintained for realms containing every inode
 * with an open cap in the system.  (The needed snap realm information is
 * provided by the MDS whenever a cap is issued, i.e., on open.)  A 'seq'
 * version number is used to ensure that as realm parameters change (new
 * snapshot, new parent, etc.) the client's realm hierarchy is updated.
 *
 * The realm hierarchy drives the generation of a 'snap context' for each
 * realm, which simply lists the resulting set of snaps for the realm.  This
 * is attached to any writes sent to OSDs.
 */
/*
 * Unfortunately error handling is a bit mixed here.  If we get a snap
 * update, but don't have enough memory to update our realm hierarchy,
 * it's not clear what we can do about it (besides complaining to the
 * console).
 */


/*
 * increase ref count for the realm
 *
 * caller must hold snap_rwsem.
 */
void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
			 struct ceph_snap_realm *realm)
{
	lockdep_assert_held(&mdsc->snap_rwsem);

	/*
	 * The 0->1 and 1->0 transitions must take the snap_empty_lock
	 * atomically with the refcount change. Go ahead and bump the
	 * nref here, unless it's 0, in which case we take the spinlock
	 * and then do the increment and remove it from the list.
	 */
	if (atomic_inc_not_zero(&realm->nref))
		return;

	spin_lock(&mdsc->snap_empty_lock);
	if (atomic_inc_return(&realm->nref) == 1)
		list_del_init(&realm->empty_item);
	spin_unlock(&mdsc->snap_empty_lock);
}

static void __insert_snap_realm(struct rb_root *root,
				struct ceph_snap_realm *new)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_snap_realm *r = NULL;

	while (*p) {
		parent = *p;
		r = rb_entry(parent, struct ceph_snap_realm, node);
		if (new->ino < r->ino)
			p = &(*p)->rb_left;
		else if (new->ino > r->ino)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
}

/*
 * create and get the realm rooted at @ino and bump its ref count.
 *
 * caller must hold snap_rwsem for write.
 */
static struct ceph_snap_realm *ceph_create_snap_realm(
	struct ceph_mds_client *mdsc,
	u64 ino)
{
	struct ceph_snap_realm *realm;

	lockdep_assert_held_write(&mdsc->snap_rwsem);

	realm = kzalloc(sizeof(*realm), GFP_NOFS);
	if (!realm)
		return ERR_PTR(-ENOMEM);

	atomic_set(&realm->nref, 1);    /* for caller */
	realm->ino = ino;
	INIT_LIST_HEAD(&realm->children);
	INIT_LIST_HEAD(&realm->child_item);
	INIT_LIST_HEAD(&realm->empty_item);
	INIT_LIST_HEAD(&realm->dirty_item);
	INIT_LIST_HEAD(&realm->inodes_with_caps);
	spin_lock_init(&realm->inodes_with_caps_lock);
	__insert_snap_realm(&mdsc->snap_realms, realm);
	mdsc->num_snap_realms++;

	dout("create_snap_realm %llx %p\n", realm->ino, realm);
	return realm;
}

/*
 * lookup the realm rooted at @ino.
 *
 * caller must hold snap_rwsem.
 */
static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
						   u64 ino)
{
	struct rb_node *n = mdsc->snap_realms.rb_node;
	struct ceph_snap_realm *r;

	lockdep_assert_held(&mdsc->snap_rwsem);

	while (n) {
		r = rb_entry(n, struct ceph_snap_realm, node);
		if (ino < r->ino)
			n = n->rb_left;
		else if (ino > r->ino)
			n =</