path: root/fs/xfs/libxfs/xfs_defer.c

// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2016 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
#include "xfs_refcount.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
#include "xfs_buf.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"

static struct kmem_cache	*xfs_defer_pending_cache;

/*
 * Deferred Operations in XFS
 *
 * Due to the way locking rules work in XFS, certain transactions (block
 * mapping and unmapping, typically) have permanent reservations so that
 * we can roll the transaction to adhere to AG locking order rules and
 * to unlock buffers between metadata updates.  Prior to rmap/reflink,
 * the mapping code had a mechanism to perform these deferrals for
 * extents that were going to be freed; this code makes that facility
 * more generic.
 *
 * When adding the reverse mapping and reflink features, it became
 * necessary to perform complex remapping multi-transactions to comply
 * with AG locking order rules, and to be able to spread a single
 * refcount update operation (an operation on an n-block extent can
 * update as many as n records!) among multiple transactions.  XFS can
 * roll a transaction to facilitate this, but using this facility
 * requires us to log "intent" items in case log recovery needs to
 * redo the operation, and to log "done" items to indicate that redo
 * is not necessary.
 *
 * Deferred work is tracked in xfs_defer_pending items.  Each pending
 * item tracks one type of deferred work.  Incoming work items (which
 * have not yet had an intent logged) are attached to a pending item
 * on the dop_intake list, where they wait for the caller to finish
 * the deferred operations.
 *
 * Finishing a set of deferred operations is an involved process.  To
 * start, we define "rolling a deferred-op transaction" as follows:
 *
 * > For each xfs_defer_pending item on the dop_intake list,
 *   - Sort the work items in AG order.  XFS locking
 *     order rules require us to lock buffers in AG order.
 *   - Create a log intent item for that type.
 *   - Attach it to the pending item.
 *   - Move the pending item from the dop_intake list to the
 *     dop_pending list.
 * > Roll the transaction.
 *
 * NOTE: To avoid exceeding the transaction reservation, we limit the
 * number of items that we attach to a given xfs_defer_pending.
 *
 * The actual finishing process looks like this:
 *
 * > For each xfs_defer_pending in the dop_pending list,
 *   - Roll the deferred-op transaction as above.
 *   - Create a log done item for that type, and attach it to the
 *     log intent item.
 *   - For each work item attached to the log intent item,
 *     * Perform the described action.
 *     * Attach the work item to the log done item.
 *     * If the result of doing the work was -EAGAIN, ->finish work
 *       wants a new transaction.  See the "Requesting a Fresh
 *       Transaction while Finishing Deferred Work" section below for
 *       details.
 *
 * The key here is that we must log an intent item for all pending
 * work items every time we roll the transaction, and that we must log
 * a done item as soon as the work is completed.  With this mechanism
 * we can perform complex remapping operations, chaining intent items
 * as needed.
 *
 * Requesting a Fresh Transaction while Finishing Deferred Work
 *
 * If ->finish_item decides that it needs a fresh transaction to
 * finish the work, it must ask its caller (xfs_defer_finish) for a
 * continuation.  The most likely cause of this circumstance are the
 * refcount adjust functions deciding that they've logged enough items
 * to be at risk of exceeding the transaction reservation.
 *
 * To get a fresh transaction, we want to log the existing log done
 * item to prevent the log intent item from replaying, immediately log
 * a new log intent item with the unfinished work items, roll the
 * transaction, and re-call ->finish_item wherever it left off.  The
 * log done item and the new log intent item must be in the same
 * transaction or atomicity cannot be guaranteed; defer_finish ensures
 * that this happens.
 *
 * This requires some coordination between ->finish_item and
 * defer_finish.  Upon deciding to request a new transaction,
 * ->finish_item should update the current work item to reflect the
 * unfinished work.  Next, it should reset the log done item's list
 * count to the number of items finished, and return -EAGAIN.
 * defer_finish sees the -EAGAIN, logs the new log intent item
 * with the remaining work items, and leaves the xfs_defer_pending
 * item at the head of the dop_work queue.  Then it rolls the
 * transaction and picks up processing where it left off.  It is
 * required that ->finish_item must be careful to leave enough
 * transaction reservation to fit the new log intent item.
 *
 * This is an example of remapping the extent (E, E+B) into file X at
 * offset A and dealing with the extent (C, C+B) already being mapped
 * there:
 * +-------------------------------------------------+
 * | Unmap file X startblock C offset A length B     | t0
 * | Intent to reduce refcount for extent (C, B)     |
 * | Intent to remove rmap (X, C, A, B)              |
 * | Intent to free extent (D, 1) (bmbt block)       |
 * | Intent to map (X, A, B) at startblock E         |
 * +-------------------------------------------------+
 * | Map file X startblock E offset A length B       | t1
 * | Done mapping (X, E, A, B)                       |
 * | Intent to increase refcount for extent (E, B)   |
 * | Intent to add rmap (X, E, A, B)                 |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C, B)               | t2
 * | Done reducing refcount for extent (C, 9)        |
 * | Intent to reduce refcount for extent (C+9, B-9) |
 * | (ran out of space after 9 refcount updates)     |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C+9, B+9)           | t3
 * | Done reducing refcount for extent (C+9, B-9)    |
 * | Increase refcount for extent (E, B)             |
 * | Done increasing refcount for extent (E, B)      |
 * | Intent to free extent (C, B)                    |
 * | Intent to free extent (F, 1) (refcountbt block) |
 * | Intent to remove rmap (F, 1, REFC)              |
 * +-------------------------------------------------+
 * | Remove rmap (X, C, A, B)                        | t4
 * | Done removing rmap (X, C, A, B)                 |
 * | Add rmap (X, E, A, B)                           |
 * | Done adding rmap (X, E, A, B)                   |
 * | Remove rmap (F, 1, REFC)                        |
 * | Done removing rmap (F, 1, REFC)                 |
 * +-------------------------------------------------+
 * | Free extent (C, B)                              | t5
 * | Done freeing extent (C, B)                      |
 * | Free extent (D, 1)                              |
 * | Done freeing extent (D, 1)                      |
 * | Free extent (F, 1)                              |
 * | Done freeing extent (F, 1)                      |
 * +-------------------------------------------------+
 *
 * If we should crash before t2 commits, log recovery replays
 * the following intent items:
 *
 * - Intent to reduce refcount for extent (C, B)
 * - Intent to remove rmap (X, C, A, B)
 * - Intent to free extent (D, 1) (bmbt block)
 * - Intent to increase refcount for extent (E, B)
 * - Intent to add rmap (X, E, A, B)
 *
 * In the process of recovering, it should also generate and take care
 * of these intent items:
 *
 * - Intent to free extent (C, B)
 * - Intent to free extent (F, 1) (refcountbt block)
 * - Intent to remove rmap (F, 1, REFC)
 *
 * Note that the continuation requested between t2 and t3 is likely to
 * reoccur.
 */

static const struct xfs_defer_op_type *defer_op_types[] = {
	[XFS_DEFER_OPS_TYPE_BMAP]	= &xfs_bmap_update_defer_type,
	[XFS_DEFER_OPS_TYPE_REFCOUNT]	= &xfs_refcount_update_defer_type,
	[XFS_DEFER_OPS_TYPE_RMAP]	= &xfs_rmap_update_defer_type,
	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
};

/*
 * Ensure there's a log intent item associated with this deferred work item if
 * the operation must be restarted on crash.  Returns 1 if there's a log item;
 * 0 if there isn't; or a negative errno.
 */
static int
xfs_defer_create_intent(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp,
	bool				sort)
{
	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
	struct xfs_log_item		*lip;

	if (dfp->dfp_intent)
		return 1;

	lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
	if (!lip)
		return 0;
	if (IS_ERR(lip))
		return PTR_ERR(lip);

	dfp->dfp_intent = lip;
	return 1;
}

/*
 * For each pending item in the intake list, log its intent item and the
 * associated extents, then add the entire intake list to the end of
 * the pending list.
 *
 * Returns 1 if at least one log item was associated with the deferred work;
 * 0 if there are no log items; or a negative errno.
 */
static int
xfs_defer_create_intents(
	struct xfs_trans		*tp)
{
	struct xfs_defer_pending	*dfp;
	int				ret = 0;

	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
		int			ret2;

		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
		ret2 = xfs_defer_create_intent(tp, dfp, true);
		if (ret2 < 0)
			return ret2;
		ret |= ret2;
	}
	return ret;
}

/* Abort all the intents that were committed. */
STATIC void
xfs_defer_trans_abort(
	struct xfs_trans		*tp,
	struct list_head		*dop_pending)
{
	struct xfs_defer_pending	*dfp;
	const struct xfs_defer_op_type	*ops;

	trace_xfs_defer_trans_abort(tp, _RET_IP_);

	/* Abort intent items that don't have a done item. */
	list_for_each_entry(dfp, dop_pending, dfp_list) {
		ops = defer_op_types[dfp->dfp_type];
		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
		if (dfp->dfp_intent && !dfp->dfp_done) {
			ops->abort_intent(dfp->dfp_intent);
			dfp->dfp_intent = NULL;
		}
	}
}

/*
 * Capture resources that the caller said not to release ("held") when the
 * transaction commits.  Caller is responsible for zero-initializing @dres.
 */
static int
xfs_defer_save_resources(
	struct xfs_defer_resources	*dres,
	struct xfs_trans		*tp)
{
	struct xfs_buf_log_item		*bli;
	struct xfs_inode_log_item	*ili;
	struct xfs_log_item		*lip;

	BUILD_BUG_ON(NBBY * sizeof(dres->dr_ordered) < XFS_D