xfs_buf_item.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#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_bit.h"
#include "xfs_mount.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_buf_item.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_error.h"


struct kmem_cache	*xfs_buf_item_cache;

static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
{ … }

/* Is this log iovec plausibly large enough to contain the buffer log format? */
bool
xfs_buf_log_check_iovec(
	struct xfs_log_iovec		*iovec)
{ … }

static inline int
xfs_buf_log_format_size(
	struct xfs_buf_log_format *blfp)
{ … }

static inline bool
xfs_buf_item_straddle(
	struct xfs_buf		*bp,
	uint			offset,
	int			first_bit,
	int			nbits)
{ … }

/*
 * Return the number of log iovecs and space needed to log the given buf log
 * item segment.
 *
 * It calculates this as 1 iovec for the buf log format structure and 1 for each
 * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
 * in a single iovec.
 */
STATIC void
xfs_buf_item_size_segment(
	struct xfs_buf_log_item		*bip,
	struct xfs_buf_log_format	*blfp,
	uint				offset,
	int				*nvecs,
	int				*nbytes)
{ … }

/*
 * Return the number of log iovecs and space needed to log the given buf log
 * item.
 *
 * Discontiguous buffers need a format structure per region that is being
 * logged. This makes the changes in the buffer appear to log recovery as though
 * they came from separate buffers, just like would occur if multiple buffers
 * were used instead of a single discontiguous buffer. This enables
 * discontiguous buffers to be in-memory constructs, completely transparent to
 * what ends up on disk.
 *
 * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
 * format structures. If the item has previously been logged and has dirty
 * regions, we do not relog them in stale buffers. This has the effect of
 * reducing the size of the relogged item by the amount of dirty data tracked
 * by the log item. This can result in the committing transaction reducing the
 * amount of space being consumed by the CIL.
 */
STATIC void
xfs_buf_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{ … }

static inline void
xfs_buf_item_copy_iovec(
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp,
	struct xfs_buf		*bp,
	uint			offset,
	int			first_bit,
	uint			nbits)
{ … }

static void
xfs_buf_item_format_segment(
	struct xfs_buf_log_item	*bip,
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp,
	uint			offset,
	struct xfs_buf_log_format *blfp)
{ … }

/*
 * This is called to fill in the vector of log iovecs for the
 * given log buf item.  It fills the first entry with a buf log
 * format structure, and the rest point to contiguous chunks
 * within the buffer.
 */
STATIC void
xfs_buf_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{ … }

/*
 * This is called to pin the buffer associated with the buf log item in memory
 * so it cannot be written out.
 *
 * We take a reference to the buffer log item here so that the BLI life cycle
 * extends at least until the buffer is unpinned via xfs_buf_item_unpin() and
 * inserted into the AIL.
 *
 * We also need to take a reference to the buffer itself as the BLI unpin
 * processing requires accessing the buffer after the BLI has dropped the final
 * BLI reference. See xfs_buf_item_unpin() for an explanation.
 * If unpins race to drop the final BLI reference and only the
 * BLI owns a reference to the buffer, then the loser of the race can have the
 * buffer fgreed from under it (e.g. on shutdown). Taking a buffer reference per
 * pin count ensures the life cycle of the buffer extends for as
 * long as we hold the buffer pin reference in xfs_buf_item_unpin().
 */
STATIC void
xfs_buf_item_pin(
	struct xfs_log_item	*lip)
{ … }

/*
 * This is called to unpin the buffer associated with the buf log item which was
 * previously pinned with a call to xfs_buf_item_pin().  We enter this function
 * with a buffer pin count, a buffer reference and a BLI reference.
 *
 * We must drop the BLI reference before we unpin the buffer because the AIL
 * doesn't acquire a BLI reference whenever it accesses it. Therefore if the
 * refcount drops to zero, the bli could still be AIL resident and the buffer
 * submitted for I/O at any point before we return. This can result in IO
 * completion freeing the buffer while we are still trying to access it here.
 * This race condition can also occur in shutdown situations where we abort and
 * unpin buffers from contexts other that journal IO completion.
 *
 * Hence we have to hold a buffer reference per pin count to ensure that the
 * buffer cannot be freed until we have finished processing the unpin operation.
 * The reference is taken in xfs_buf_item_pin(), and we must hold it until we
 * are done processing the buffer state. In the case of an abort (remove =
 * true) then we re-use the current pin reference as the IO reference we hand
 * off to IO failure handling.
 */
STATIC void
xfs_buf_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{ … }

STATIC uint
xfs_buf_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{ … }

/*
 * Drop the buffer log item refcount and take appropriate action. This helper
 * determines whether the bli must be freed or not, since a decrement to zero
 * does not necessarily mean the bli is unused.
 *
 * Return true if the bli is freed, false otherwise.
 */
bool
xfs_buf_item_put(
	struct xfs_buf_log_item	*bip)
{ … }

/*
 * Release the buffer associated with the buf log item.  If there is no dirty
 * logged data associated with the buffer recorded in the buf log item, then
 * free the buf log item and remove the reference to it in the buffer.
 *
 * This call ignores the recursion count.  It is only called when the buffer
 * should REALLY be unlocked, regardless of the recursion count.
 *
 * We unconditionally drop the transaction's reference to the log item. If the
 * item was logged, then another reference was taken when it was pinned, so we
 * can safely drop the transaction reference now.  This also allows us to avoid
 * potential races with the unpin code freeing the bli by not referencing the
 * bli after we've dropped the reference count.
 *
 * If the XFS_BLI_HOLD flag is set in the buf log item, then free the log item
 * if necessary but do not unlock the buffer.  This is for support of
 * xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
 * free the item.
 */
STATIC void
xfs_buf_item_release(
	struct xfs_log_item	*lip)
{ … }

STATIC void
xfs_buf_item_committing(
	struct xfs_log_item	*lip,
	xfs_csn_t		seq)
{ … }

/*
 * This is called to find out where the oldest active copy of the
 * buf log item in the on disk log resides now that the last log
 * write of it completed at the given lsn.
 * We always re-log all the dirty data in a buffer, so usually the
 * latest copy in the on disk log is the only one that matters.  For
 * those cases we simply return the given lsn.
 *
 * The one exception to this is for buffers full of newly allocated
 * inodes.  These buffers are only relogged with the XFS_BLI_INODE_BUF
 * flag set, indicating that only the di_next_unlinked fields from the
 * inodes in the buffers will be replayed during recovery.  If the
 * original newly allocated inode images have not yet been flushed
 * when the buffer is so relogged, then we need to make sure that we
 * keep the old images in the 'active' portion of the log.  We do this
 * by returning the original lsn of that transaction here rather than
 * the current one.
 */
STATIC xfs_lsn_t
xfs_buf_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{ … }

#ifdef DEBUG_EXPENSIVE
static int
xfs_buf_item_precommit(
	struct xfs_trans	*tp,
	struct xfs_log_item	*lip)
{ … }
#else
#define xfs_buf_item_precommit …
#endif

static const struct xfs_item_ops xfs_buf_item_ops = …;

STATIC void
xfs_buf_item_get_format(
	struct xfs_buf_log_item	*bip,
	int			count)
{ … }

STATIC void
xfs_buf_item_free_format(
	struct xfs_buf_log_item	*bip)
{ … }

/*
 * Allocate a new buf log item to go with the given buffer.
 * Set the buffer's b_log_item field to point to the new
 * buf log item.
 */
int
xfs_buf_item_init(
	struct xfs_buf	*bp,
	struct xfs_mount *mp)
{ … }


/*
 * Mark bytes first through last inclusive as dirty in the buf
 * item's bitmap.
 */
static void
xfs_buf_item_log_segment(
	uint			first,
	uint			last,
	uint			*map)
{ … }

/*
 * Mark bytes first through last inclusive as dirty in the buf
 * item's bitmap.
 */
void
xfs_buf_item_log(
	struct xfs_buf_log_item	*bip,
	uint			first,
	uint			last)
{ … }


/*
 * Return true if the buffer has any ranges logged/dirtied by a transaction,
 * false otherwise.
 */
bool
xfs_buf_item_dirty_format(
	struct xfs_buf_log_item	*bip)
{ … }

STATIC void
xfs_buf_item_free(
	struct xfs_buf_log_item	*bip)
{ … }

/*
 * xfs_buf_item_relse() is called when the buf log item is no longer needed.
 */
void
xfs_buf_item_relse(
	struct xfs_buf	*bp)
{ … }

void
xfs_buf_item_done(
	struct xfs_buf		*bp)
{ … }
linux/fs/xfs/xfs_buf_item.c
